Modeling and Simulation of a Serial Production Line with Constant Work-In-Process

Size: px
Start display at page:

Download "Modeling and Simulation of a Serial Production Line with Constant Work-In-Process"

Transcription

1 Modelig ad Simulatio of a Serial Productio Lie with Costat Wor-I-Process Mehmet Savsar Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 productio cotrol strategy. Coutless umber of other JIT Abstract This paper presets a model for a ureliable productio lie, which is operated accordig to demad with costat applicatios ad related models ca be see i the literature. Most of the literature deals with the efficiecy of JIT systems wor-i-process (CONWIP). A simulatio model is developed based uder differet operatioal coditios. Either mathematical o the discrete model ad several case problems are aalyzed usig models are developed based o restrictive assumptios or the model. The model is utilized to optimize storage space capacities at itermediate stages ad the umber of abas at the last stage, simulatio models are utilized i the aalysis of JIT systems. which is used to trigger the productio at the first stage. Furthermore, I relatio to the effects of itermediate buffer capacities o a effects of several lie parameters o productio rate are aalyzed usig desig of experimets. push type of serial productio lie ad optimum allocatios of buffers o the lie, several papers have bee published. I particular, papers related to buffer allocatios iclude [12]- Keywords Productio lie simulator, Push-pull system, JIT [22]. system, Costat WIP, Machie failures. I this paper, we developed a discrete mathematical model to aalyze a push-pull system of productio with costat I. INTRODUCTION wor-i-process (CONWIP). Whe a fial product is IMULATION has bee extesively used i modelig ad withdraw from the fiished products ivetory i the last Saalyzig productio cotrol systems. A particular type of stage, a aba is sigaled to the first stage to start the productio cotrol, which has become a commo tred i productio. Fig. 1 illustrates operatio of such a system. idustry, is just i time (JIT) or pull system of productio cotrol. I a JIT system, productio is iitiated accordig to demad for fiished products at each stage to produce what is 1 eeded at the right time ad i the right quatity. Alterative to a purely pull system is the hybrid push-pull system, where the productio at the first stage is scheduled accordig to the demad for the products i the last stage. Withdrawal of 1 M 1 2 M 2.. Demad m M m m+1 fiished products from the last stage triggers the productio at Fig. 1 A Push-pull productio cotrol system the first stage by a iformatio sigalig card, called a aba. Itermediate operatios are performed by a push system. Push-pull systems are commoly used i electroics assembly operatios. Several studies have bee carried out o the implemetatio ad efficiecy of JIT systems. [1]-[6] have aalyzed JIT systems from differet perspectives usig simulatio as well as other meta modelig approaches, icludig eural etwor models. [7]-[10] studied a hybrid push-pull system ad preseted a cotrol algorithm for multi-stage, multi-lie productio systems. [11] compared three pull cotrol policies, amely the aba, base stoc, ad geeralized aba. The effects of abas ad other factors o JIT system performace have bee ivestigated mostly for pull types of Mehmet Savsar is professor ad chairma of the Departmet of Idustrial & Maagemet Systems Egieerig at Kuwait Uiversity, College of Egieerig & Petroleum,, P.O. Box 5969, Safat 13060, Kuwait (phoe: ; fax: ; mehmet@uiv.edu.w or msavsar@yahoo.com). Successive operatios are carried out by completio of each product at each statio (Mi) ad its delivery to the succeedig statio or its buffer store (i), if the statio is busy. It is assumed that the itermediate buffer sizes, which represet maximum wor-i process at each stage, are limited i capacity. Thus, whe the storage of fiished uits i the fial products ivetory reaches a specified maximum capacity, the last statio stops its productio. Similarly, whe a itermediate buffer i is filled up to its maximum capacity, the precedig statio, Mi-1, stops its productio or the completed part stays o the statio util a part is removed from the succeedig buffer. The capacity of buffer i is zi. I productio systems, which operate accordig to demad, equipmet availability is importat sice machie failures sigificatly delivery time of products. While equipmet failures due to wear-outs ca be elimiated, failures due to radom causes could ot be elimiated. Whe optimizig 638

2 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 umbers of abas ad the sizes of i-process buffers, it is ecessary to cosider equipmet reliability i model developmet. I the followig sectio, we preset a discrete mathematical model, which is based o the flow of discrete parts or batches from stage to stage. The model is used to aalyze the behavior of the push-pull system uder various operatioal coditios icludig equipmet availabilities ad radomess i demad. II. MATHEMATICAL MODEL FOR THE PUSH-PULL SYSTEM The basic pricipal of the discrete model is to determie the total time a batch of parts speds i statio i, the time istat at which batch is completed i statio i, ad the time istat at which batch leaves the statio i. Storages 2,., m are called itermediate buffer storages, havig fiite capacity z i, i=2,,m. Iitial iput storage is assumed to have ulimited capacity for the raw material, while the fial output storage has limited capacity for completed batches of products with attached abas. The fial buffer (m+1) is assumed to be the fiished products storage with time betwee part departures beig equal to time betwee demad. The followig otatios are used i the formulatio: i = Time duratio that th batch stays o the i th statio ot cosiderig imposed stoppages due to equipmet failures; i=1,2,..,m. m = Number of statios o the lie. i = Processig time of batch o statio i (this may be a radom variable with certai distributio) i = Repair time of the i th statio required for correctio of a failure durig processig of the th batch. Time to failures ad the repair times are assumed to follow certai distributios, which are geerated ad icorporated ito the model whe the model is solved iteratively. i = Istat of time at which processig of the th batch is completed o the i th statio. i = Istat of time at which th batch departs from the i th statio. 0 = Istat of time at which th batch eters the first statio. i = Istat of time at which i th statio is ready to process the th batch. m+1, = Istat of time at which th batch departs from the fial buffer m+1. = Mea time betwee demad for batches -1 ad from the fial buffer. This time may also be a radom variable with certai distributio. A part stays i a statio for three reasos: (i) The part is beig machied; (ii) The machie has failed durig machiig of the part ad a repair is taig place; (iii) The successive buffer is full ad the part ca ot be trasferred to the ext statio due to a imposed stoppage. The residece time of the th part o the ith statio, i, without cosiderig imposed stoppages is give as follows: i i i (1) The discrete mathematical model of the push-pull system cosists of calculatig part completio times, i, ad part departure times, i, i a iterative fashio. The followig formulatio is developed for i ad i to be used i iterative calculatios. Processig of batch caot be started o statio i util the previous batch, -1 leaves statio i. Therefore the time istat at which i th statio is ready to begi the th batch, deoted by i, is give by i = i,-1. If, i-1, < i, the the th batch must wait i buffer i, sice it has left statio i-1 before statio i is ready to accept it. Therefore, processig of the th batch i the i th statio will start at the istat i. If however, i-1, i, the processig of the th batch i the i th statio ca start immediately at the time istat i-1,. Cosiderig both cases above, oe gets the relatio for the ready time of the th batch to be processed i the ith statio as follows: i = max[ i-1,, i,-1 ] (2) Sice the th batch will stay i statio i for a period of i time uits, its processig will be completed by the time istat i give by: i = max[ i-1,, i,-1 ] + i = i + i (3) where i=2,3,,m. I case of the first statio, a aba must arrive before the batch ca be processed. The arrival of a aba from storage m+1 is modeled as follows: Let =-L 2 where, L 2 =Total umber of batches iitially i statios S 2 ad storages 2,.., m. The, 1 = max[ 1,-1, m+1, ] + 1 (4) Time istat at which th batch is ready to eter the first statio is assumed to be 0 < 1,-1 sice we assumed that there are always batches of parts available i frot of the first statio. However, a aba must arrive from the buffer (m+1) to start the process at statio 1. Now, it remais to determie the time istat at which th batch departs from the i th statio, i. It is foud by cosiderig two cases. Let = z i+1 1 (5) I the first case, i, i1, (6) which idicates that the th batch has bee completed o the i th statio before processig of the (-z i +1) th batch has started o the (i+1) th statio. Sice buffer i+1, which is betwee statio i ad i+1 with capacity z i +1, is full ad statio i has completed the th batch, the th batch may leave the i th statio oly at the istat of time at which the ( z i +1) th batch of the (i+1) th statio has started processig. Therefore, i, i1, (7) I the secod case, i, i1, (8) which idicates that, at the istat i there are free spaces i buffer i +1 ad therefore part ca leave machie i immediately after it is completed; that is, i = i holds uder this case. Cosiderig both cases above, we have the followig relatios for i : i, i, if zi 1 1 (9) max (10) i, i,, i1, 639

3 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 if > z i+1 +1; i =1, 2, 3,, m-1, where = z i+1 1 ad, max (11) m, m,, m1, Where, m+1, = Departure time if the th batch from the fial buffer m+1. Departure time of a fiished product from the fial buffer (m+1) depeds o two coditios ad calculated as follows: I the first case, m, m+1,-1 +. I this case, m+1, = m+1,-1 +. (12) I the secod case, m, > m+1,-1 +. I this case, m+1, = m,. (13) Combiig both cases above, the followig geeral relatio is obtaied for m+1, : m+1, = max[ m,, m+1,-1 + ] (14) I real-world situatios, itermediate buffers may cotai batches of parts that are ofte left from a previous shift or day. Therefore, it is importat to start the iteratios with some iitial coditios as follows: Let: l i =Number of batches iitially i buffer i ad statio S i m ad, 1 L Total umber of batches o statios l i i S,..,S m ad storages,.., m+1. Whe iteratios are started, oe ca assume that, at the iitial time istat t=0, parts 1,2,, L i+1 are already processed o statio S i, sice these batches are iitially i the lie right after statio S i. Therefore, give the iitial values of l 1,.,l m+1, the iitial values of i ad i for =1,2,.,L i+1 are expressed by: i = i = 0; i = 1, 2,.., m. (15) I order to carry out iterative computatios, a simulatio procedure is developed ad implemeted o the computer to determie several productio lie performace measures, which iclude average umber of batches completed by the lie durig a specified period, average umber of batches completed by each statio durig the same time, percetage of time for which each statio is up ad dow due to imposed or iheret stoppages. III. COMPUTATIONS OF THE MODEL The discrete model is coded ito a simulatio program ad implemeted o the computer to calculate system performace measures. I additio to the variables described for the discrete model, the simulatio allows several distributios, icludig: expoetial, uiform, Weibull, ormal, log ormal, Erlag, gamma, beta ad costat values to be specified for failure ad repair times of the equipmet i each statio. Iterative simulatio model basically calculates the time istat at which each part eters a statio, duratio of its stay, ad the time it leaves the statio. This is cotiued util, for example oe shift, which is the specified simulatio time T sim, is completed. I order to obtai reliable results, several simulatio rus have to be obtaied ad the average performace measures should be calculated. The results of each iterative simulatio are utilized with statistical tests to determie if the specified coditios are met to stop the umber of simulatio iteratios (i.e., shifts). If the coditios are ot met, simulatio iteratios are cotiued with further rus. For each simulatio realizatio, calculatios of i, i, i, ad m+1, are performed iteratively with the cosideratio give to equipmet failures ad repairs as the parts flow through the system. Reliable results caot always be obtaied from a sigle simulatio realizatio. Therefore, additioal rus have to be performed ad the results tested statistically util the error i the lie productio rate is less tha a value with a probability, both of which are predefied. This is accomplished by comparig the average productio output rate from simulatio ( Q ) to the expected value (Q ) usig the cofidece iterval calculatio give below. Here, N N N i (16) Q ad T sim i1 where N i =productio output obtaied from simulatio ru i ad is the umber of simulatio rus. Z Pr1 2 V( Q) Q Q Q Z 1 2 V( Q) 1 Q (17) The aim is to have a estimated output rate, Q, as close to the actual mea output rate Q as possible. To achieve this, Z V ( Q ) 2 Q is miimized by obtaiig more rus. As this value gets closer to 0, Q Q with probability 1. A value is etered by the user; the simulatio program calculates Z V ( Q ) 2 Q after each iteratio; compares this quatity with ad termiates the program if it is less tha. If it is ot less tha after a maximum umber of rus, the program is still termiated to avoid excessive computatio. The iterative simulatio model allows oe to determie various parameters ad depedet variables with sigificat effects o productivity ad other performace measures. Estimatio idices are obtaied for such variables as the total, iheret, ad imposed time losses due to failures ad stoppages for each statio as follows: Q 60 / is the omial productivity of statio i, where i i i is the cycle time for statio i; Qr 60N i / T i sim is the relative productivity of statio i; K loss 1 Q r / Q i i is the total loss factor of statio i; K ih 1 tri /( tri t fi ) is iheret loss factor of statio i; ad K imp K loss K ih is the imposed loss factor for statio i, i = 1, 2,.., m. The terms t fi ad tri are mea times to failure ad to repairs, of statio i respectively. After determiig these loss factors, they are compared for all statios. The statio with the highest total loss factor is the 640

4 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 chose for improvemet. If K imp>k ih (i), stoppages are maily due to blocig ad starvatio; therefore it is ecessary to icrease the capacity of buffers immediately precedig ad succeedig it. If K ih (i)>k imp (i), stoppages are maily caused by iheret failures, that is breadows; therefore, the reliability of statio i, should be icreased or its mea repair time should be decreased i order to gai improvemet i total lie productivity. After the suggested chages are made, iterative simulatio is repeated to see the effects of the proposed chages i the desig. IV. STORAGE SPACE ALLOCATION Optimum storage space or buffer allocatio problem has bee studied by several researchers with respect to allocatio of a fixed amout of total buffer space o a serial productio lie. The problem ca be stated as follows: Give a total amout of acceptable buffer space of Z uits, allocate this total space to idividual buffers S 2,,S m+1, the quatities z 2, z 3,..,z m+1 respectively such that the total productio output rate of the lie, Q(z), is maximized. The problem is stated as follows: Choose z 2, z 3,..,z m+1 so as to Maximize Q(z) m Subject to: 1 zi Z (18) i2 z i 0 ad iteger (i=2,3,..m+1) This problem has bee discussed by [7] for productio lies with expoetial processig times i all statios. The optimizatio model is a liearly costraied iteger oliear programmig problem that is difficult to solve due to the fact that Q(z) has to be evaluated by either cotiuous time Marov chais or by some other stochastic processes approximatio. [7] evaluated Q(z) for the serial lie usig Marov chais approach ad idicated that the umber of states are too large ad exceeds well over 20,000 equatios to be solved to obtai the value of Q(z) for a give buffer size combiatio. Eve if it was practical to solve the problem, it would ot be still applicable to the cases with equipmet failures ad o-expoetial process times. The buffer allocatio model is applied to the push-pull system i this paper. However, we obtai the solutio for Q(z) usig the iterative solutio procedure preseted above. This procedure is ot restricted to expoetial process times ad all reliable equipmet, sice it is based o simulatio. A fixed umber of buffers are specified ad the iterative computatios are performed to determie optimum combiatios by evaluatig all buffer combiatios. The optimum correspods to the maximum productio output rate. For small size problems, such as lies with up to 8 statios ad up to 10 buffer capacities, computatioal time is i the order of miutes, depedig o the accuracy required. However, for larger problems, such as more tha m=10 statios ad more tha Z=15 buffer capacities, computatioal time is relatively large sice umber of possibilities evaluated is large. If a small accuracy with 5% error is acceptable, large problems ca also be solved i a reasoable time. V. SIMULATED CASE PROBLEMS The model is illustrated by several case problems. Table I ad Table II are the iput data ad the output results obtaied for a 5-statio lie with all statios available 85% of the time. Processig times, failure distributios, their parameters, repair distributios ad their parameters are show i Table I. Statio TABLE I INPUT DATA FOR PRODUCTION LINE SIMULATION Process No. of Failure Repair Distrib. Time Failures Distrib Expo(85) Normal Expo(85) Normal Expo(85) Normal Expo(85) Normal Expo(85) Normal The outputs for 2000 time uits of simulatio with =0.05, =0.005, ad maximum iteratios=100 are show i Table II. The results iclude relative productio rate of each statio ad various loss factors due to equipmet failures as discussed i sectio III. The output also icludes suggestios for lie improvemet. TABLE II UNITS Average Lie Output (Parts/Time Uit.)= Stadard Dev. of Lie Output Rate= Optimum Buffer Allocatios for Buffers m=2 to 6 are as Follows: Statio Relative Imposed Loss Factors Iheret Loss Factor Suggestios: Statio No. 1 has the Maximum Total Loss Factor. Dow Time is Maily Imposed. Icrease the Capacity of Storage Adjacet to This Statio. Also Icrease Reliability ad Productivity of Adjacet Statios ad Try Simulatio Agai. Error<Epsilo Is Reached at Iteratio = 100 Maximum Iteratio Is Reached At Iteratio = 100 Total Computatio Time = Secods I the secod case problem, a push-pull productio lie with 5 serial statios is cosidered as before. All statios are assumed to be reliable, except oe statio which was placed at 641

5 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 the begiig (B), i the middle (M), or at the ed (E) of the lie to see the effects of ureliable statio at differet segmets of the lie. Failure ad repairs for the ureliable statio are as i Table I. Stadard deviatio of the repair times was tae as 15% of the mea. Sice availability is A=MTBF/(MTBF+MTTR), selected parameters represeted 85% equipmet availability for the particular statio, whose effect o the lie was ivestigated. I other words, we wated to see how the buffers would be allocated if the ureliable statio was at the begiig, at the middle or at the ed of the lie. The system was aalyzed by the simulatio over a period of 2000 time uits. All itermediate buffer combiatios, which add up to less tha or equal to total buffer capacity Z (Z=0,1,23,5,10) are evaluated i order to determie lie productivity, as show i Fig. 2, ad optimum buffer combiatios (z 2, z 3, z 4, z 5 ), which resulted i maximum productio rate, as show i Table III, for three differet locatios of the ureliable equipmet at the begiig (B), i the middle (M), ad at the ed (E) of the lie. The correspodig productio output rates are give as the percetage of omial rate, which would be 100 if the lie was all reliable, balaced with costat processig times. A importat observatio related to buffer size allocatio ca be see i Table III. If the lie has a ureliable statio at the start or at the ed, the buffer capacity available should be located immediately after the last statio, except i the case of 5 ad 10 buffer sizes, i which case oe uit is allocated to buffer 4, after statio 3 i the ceter of the lie. A similar observatio is see i the case if the ceter statio is ureliable. I this case if there is oe buffer space to be allocated o the lie, it is preferred to be at buffer 3, immediately after statio 2. Lie Productivity (%) B M E Total Buffer Capacity (Z) Fig. 2 Lie productivity as a fuctio of Z Additioal buffer sizes are mostly allocated to the ed of the lie after statio 5, except i the case of 2 ad 10 buffer sizes, i which case oe space is allocated after the ceter statio. The mai reaso that the buffer spaces are mostly allocated to the ed of the lie could be due to the fact that the lie is operated as a push-pull system ad therefore the first statio ca ot start processig a part uless a part or batch is withdraw from the last statio. Buffer spaces after the last statio helps icreasig part availability durig demad. The TABLE III BUFFER CAPACITY DISTRIBUTION TO STATIONS Begiig Middle Ed Z z 2 z 3 z 4 z 5 z 6 z 2 z 3 z 4 z 5 z 6 z 2 z 3 z 4 z 5 z same three cases were evaluated for a purely push type of productio lie, where the last statio does ot have a limit o outputtig its product ad the first statio ca start without waitig for a part withdrawal from the last statio. The results, which are ot show here, are almost opposite of what is obtaied for the push-pull system ad the buffer allocatio is preferred to be immediately after the first statio ear the start of the lie i all cases. VI. EFFECTS OF LINE CONFIGURATIONS,MAINTENANCE POLICIES AND LINE PARAMETERS ON LINE PERFORMANCE I order to see effects of various productio related parameters ad factors o lie performace measure, such as the productio rate, several experimets were set up ad results were obtaied. I particular, the followig productio lie factors were tae ito cosideratio: 1. Productio lie legth (3, 5,ad 9 statios); 2. Buffer capacities betwee statios (0, 2, 4, 6, 8); 3. Process time variability measured by its coefficiet of variatio (CV pt =0, 0.2, 0.5, 0.7); 4. Demad iterval variability (CV dm =0, 0.2, 0.5, 0.7); 5. Type of maiteace applied (Desig out maiteace resultig i full reliability [REL], reliability cetered maiteace [CM-PM], corrective maiteace [CM]) Process time at each statio was assumed to be ormally distributed with mea of 3.0 time uits ad varied accordig to the coefficiet of variatio (CVp selected. Similarly, time iterval betwee the demads for withdrawal of products from the fiished products storage was assumed to be ormally distributed with mea of 3.0 time uits ad also varied accordig to the coefficiet of variatio (CV dm ) selected. The productio lies are simulated over 2400 time uits. 10 rus are carried out for each combiatio ad average values are recorded. Figures 3-5 illustrates the productio output rate as a fuctio of various lie cofiguratio ad factors metioed above. CM-i, CM-PM-i, ad REL-i represet two levels of maiteace ad full reliability case for each statio i. I order to compare effects of corrective maiteace (CM) oly to the CM with prevetive maiteace (PM), reliability cetered maiteace (RMC) cocept was icorporated ito the model. Uder RMC, equipmet is subjected to PM just before a failure is expected. Mea time betwee failures (MTBF) must be determied i advace. I this case, it is assumed that failures due to wear outs are elimiated ad oly 642

6 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 radom failures remai. This idea ca be implemeted aalytically if time betwee failures are uiformly distributed. This cocept has bee explaied i detail by Savsar[23]. Followig is a mathematical procedure to separate radom failures from the wear-out failures. This separatio is eeded i order to be able to see the effects of maiteace o the productivity ad availability of a lie whe simulatig the system. Let f( = Probability distributio fuctio (pdf) of time betwee failures. F( = Cumulative probability distributio fuctio (cdf) of time betwee failures. R( = Reliability fuctio (Probability that the equipmet survives by time. h( = Hazard rate (or istataeous failure rate). Hazard rate h( cosists of two compoets, the first due to radom failures ad the secod due to wear-out failures as: h( = h 1 ( + h 2 ( (19) h 1 ( = Hazard rate due to radom failures. h 2 ( = Hazard rate due to wear-out failures. Sice the equipmet failures are either due to chace causes or wear-outs, reliability of the equipmet, which is the probability that equipmet survives by time t, ca be expressed as follows: R( = R 1 ( R 2 ( (20) where, R 1 ( = Reliability due to chace causes (or radom failures) ad R 2 ( = Reliability due to wear-outs. Sice the hazard rate due to radom failures is idepedet of time ad therefore costat, we let h 1 (=. Thus, the reliability of the equipmet due to radom failures with costat hazard rate would be as follows: R 1 ( = e -t (21) h( = + h 2 ( (22) It is ow that h( =f(/r( = f(/[1-f(] = + h 2 ( (23) h 2 ( = h( - h 1 ( = f(/[1-f(] - (24) f f ( 1 F( f ( h2 ( R ( [ ][ ] [1 F( )] t t t 1 F( e e e 2( 2 t F 1 F( e 1 R ( 1 t e 2 ( 2 t R( t e df2 ( f 2 ( dt (25) R 2 ( = R(/R 1 ( = [1-F(]/ e -t (26) h 2 ( = f 2 (/R 2 ( (27) These derivatios show that, total time betwee failures, f( ca be separated ito two distributios, time betwee failures due to radom causes [f 1 (] ad time betwee failures due to wear-outs [f 2 (]. Sice the failures due to radom causes could ot be elimiated, we must cocetrate o the failures due to wear-outs i order to elimiate them by appropriate maiteace policies. By the procedure described above, it is possible to separate the two types of failures ad develop the best maiteace policy to elimiate the wear-out failures. This separatio is aalytically possible for uiform distributio. However, it is ot possible aalytically for other distributios. It is assumed that whe a prevetive maiteace policy is implemeted, failures due to wear-outs are elimiated ad oly failures due to radom causes remai. These radom failures are assumed to follow expoetial distributio with costat hazard rate sice they are completely radom with uow causes ad the memoryless property of expoetial is applicable. For uiformly distributed time betwee failures, t, i the iterval 0<t<, probability distributio fuctio of time betwee failures without itroductio of PM is give by: f ( 1 /. (28) If we let =1/, the, reliability is give as 1-t ad the total failure rate is give as: h(=f(/r(=/(1-. (29) Let us assume that hazard rate due to radom failures is a costat give by h 1 (=, the the hazard rate due to wear-out failures could be determied by: h 2 (=h(-h 1 (=/(1--= 2 t/(1- (30) The correspodig time to failure probability desity fuctios for each type of failure rate is: ( t ) f1 ( e 0 t (31) 2 ( t ) f 2 ( t e, 0 t (32) The reliability fuctio for each compoet would be is as follows: ( R1 ( e 0 t (33) t R2 ( (1 e, 0 t (34) R( R1 ( R2 ( (35) Whe the prevetive maiteace (PM) is itroduced, failures due to wearouts are elimiated ad thus the machiery fails oly due to radom causes, which are expoetially distributed as give by f 1 (. Samplig for the time to failures i simulatios is thus based o expoetial distributio with mea ad a costat failure rate of =1/. I case of CM without PM, i additio to the radom failures, wear-out failures are also preset ad thus the time betwee equipmet failures is uiformly distributed betwee 0 ad as give by f(. The justificatio behid this assumptio is that uiform distributio implies a icreasig failure rate with two compoets, amely, failure rate due to radom failures ad failure rate due to wearout failures as give by h 1 ( ad h 2 ( respectively. Iitially whe t = 0, failures are due to radom effect with a costat rate =1/. As the equipmet operates, wearout failures come ito play ad thus the total failure rate h( icreases with time t. Samplig for the time betwee failures i simulatio is based o a uiform distributio with mea /2 ad a icreasig rate, h(. I the simulatio experimets cosidered, time to failure is assumed uiformly distributed betwee 0 ad 200 time uits with a mea of 100 time uits for all statios for the case of CM oly. I the case of PM, wearouts are elimiated ad time to failure exteds; it becomes 643

7 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 expoetially distributed with a mea of 200 time uits. Time to repair was assumed ormally distributed with mea of 15 time uits ad stadard deviatio of 3 time uits. Fig. 3 illustrates simulatio results for the case whe CV=0.0 for process time (CVp ad the demad (CV dm ). As it is see i fig. 3, 800 uits (2400/3.0) are produced o ay legth of lie if the lie is fully reliable ad there is o other source of variability. However, if the lie is uder failures with CM oly, productio rate is sigificatly reduced whe lie legth is icreased. Whe PM is itroduced i additio to CM, productio rate is betwee the CM ad REL cases. It ca be see from figure 3 that betwee the cases of ureliable lies, the lowest productio rate is for a 9-statio lie with CM oly, while the highest rate is for a 3-statio lie with CM ad PM together. Fig. 4 shows the results for CVpt=0.0 ad CV dm =2.1; fig. 5 shows the results for CVpt=2.1 ad CV dm =0.0; fig. 6 shows the results for CVpt=2.1 ad CV dm =2.1. As it ca be see from figs. 3-6, as the process time ad demad variability icrease, productio rate decreases. It is also clear from figs. 5 ad 6 that as the process time becomes variable, the productio rate ca o loger reach to the maximum level of 800 uits eve for the reliable lie. I all cases however, as the lie legth icreases ad the buffer capacities decrease, productio rate decrease. Also, i all cases CM oly results i lower productio rate. CM-3 CM-9 CM-PM-5 REL-3 CM-5 CM-PM-3 CM-PM-9 REL Buffers Fig. 3 Lie productio rate uder differet factors (CV pt =CV dm =0.0) CM-3 CM-9 CM-PM-5 REL Buffers CM-5 CM-PM-3 CM-PM-9 REL-5 Fig. 4 Lie productio rate uder differet factors (CV pt =0.0; CV dm =2.1) VII. EXPERIMENTAL DESIGN I order to see sigificace of the effects of sigificat factors o lie productio rate, a geeral factorial desig was set up with five factors each at three levels. Thus, lie legths of 3, 5, ad 7; buffer capacities of 0, 2, ad 6; process time CV of 0, 0.2, ad 0.7; demad CV of 0, 0.2, ad 0.7; ad maiteace policies of REL, CM, ad CM-PM cases were CM-3 CM-5 CM-9 CM-PM-3 CM-PM-5 CM-PM-9 REL-3 REL-5 REL Buffers Fig. 5 Lie productio rate uder differet factors (CV pt =2.1; CV dm =0.0) 644

8 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 CM-3 CM-5 CM-9 CM-PM-3 CM-PM-5 CM-PM-9 REL-3 REL-5 REL Buffers Fig. 6 Lie productio rate uder differet factors (CV pt =2.1; CV dm =2.1) cosidered. The ANOVA results show i Table IV idicate that followig factors are sigificat: A: Lie legth: B: Buffers; D: Demad CV: E: Maiteace policy; ad three iteractios AE, BD, ad DE % of the variatio is explaied by these sigificat terms. It is iterestig that process time variatio was ot a sigificat factor for this model. I the geeral factorial desig model, the factors are cosidered as qualitative ad therefore the model is hierarchical. The productio rate is give as fuctio of sigificat factors ad their iteractios. Fig. 7, the ormal probability plot for the residuals shows that the ormality assumptio is valid. TABLE IV ANOVA FOR SELECTED FACTORIAL MODEL RESPONSE:PRODUCTION RATE Sum of Mea F Source Squares DF Square Value Prob. > F Model 4.3E E < sigificat A 4.2E E < B 7.9E E < D 8.4E E < E 1.94E E < AE < BD 1.13E < DE < Residual 1.07E Corrected Tot. 4.4E+6 Total DF: 242 The Model F-value of implies the model is sigificat. There is oly a 0.01% chace that a "Model F- Value" this large could occur due to oise. Values of "Prob > F" less tha 0.05 idicate model terms are sigificat. I this case A, B, D, E, AE, BD, DE are sigificat model terms. Values greater tha 0.1 idicate the model terms are ot sigificat. Other ANOVA related statistics are as follows: Std. Dev.=21.93; R-Squared=0.9756; Mea=591.67; Adj R- Squared=0.9734; C.V.=3.71; Pred R-Squared=0.9707; PRESS=1.279E+5; Adeq Precisio= The "Pred R-Squared" of is i reasoable agreemet with the "Adj R-Squared" of "Adeq Precisio" measures the sigal to oise ratio. A ratio greater tha 4 is desirable. The ratio of idicates a adequate sigal. Fial equatio, which relates the productio rate to the coded values of the sigificat factors, is give as follows: Productio Rate= *A[1]+7.34*A[2]-73.22*B[1] +7.29*B[2]+59.28*D[1]+20.67*D[2]-95.47*E[1]-24.07*E[2] *A[1]E[1]+0.56*A[2]E[1]+12.91*A[1]E[2]+2.19* A[2]E[2]+37.60*B[1]D[1]-11.48*B[2]D[1]-3.48*B[1]D[2] * B[2]D[2]-20.44*D[1]E[1]-6.75*D[2]E[1]-5.98* D[1]E[2]-1.61*D[2]E[2] DESIGN-EXPERT Plot ProductioRate Normal %Probability Normal Plot of Residuals Studetized Residuals Fig. 7 Normal probability plot of residuals VII. CONCLUDING REMARKS This paper has preseted a iterative mathematical model ad a computer simulatio procedure for a multi-stage productio flow lie operated accordig to demad at the last statio, while usig a push system at the itermediate statios. Based o the discrete mathematical model, simulatio process icorporates a three-stage procedure which allows the user to eter a set of data describig the system uder study, simulate the system iteratively util selected statistical criteria are satisfied, obtai the output, ad apply specific recommedatios for productivity improvemet util satisfied productio output is achieved. The simulatio model is very useful i estimatig productio lie productivity for realistic systems. It allows the lie desiger or maagers to evaluate effects of storage capacity ad repair/maiteace policies o productivity of a system. The model was utilized to see the optimum allocatios of storage uit capacities alog the lie if the equipmet were subject to radom failures. If all the equipmet had similar 645

9 Iteratioal Sciece Idex, Idustrial ad Maufacturig Egieerig waset.org/publicatio/13084 failure rates, it was observed that the optimum allocatio of buffer storages followed a bowl shape, meaig that more buffer spaces were allocated to the ceter statios. If oly oe statio was subject to failures, most of the buffers were allocated to the fial storage to achieve maximum productio output irrespective to the locatio of the ureliable statio beig either at the start, at the middle, or at the ed of the lie. As a future study, the suggested iterative model ca be icorporated ito iteractive computer software to be effectively utilized by egieers ad maagers. Simulatio model was utilized to ivestigate the effects of lie cofiguratios, maiteace policies, buffer capacities, process time variability, ad demad variability o productio rate of the lie. A factorial desig was set up to ivestigate the sigificat factors that affect the productio rate. It was foud that lie legth, buffer capacities, maiteace policies, ad demad variability had sigificat effects o productio rate. REFERENCES [1] Chu, C. ad Shih, W. Simulatio Studies i JIT Productio, Iteratioal Joural of Productio Research, 30 (11), 1992, pp [2] Fuuawa, T. ad Hog S.C., The Determiatio of Optimal Number of Kabas i a Just-I-Time Productio System, Computers Idustrial Egieerig, 24 (4), 1993, pp [3] Savsar, M. ad Aljawii, A., Simulatio Aalysis of Just-I-Time Productio Systems, Iteratioal Joural of Productio Ecoomics, 42, 1995, pp [4] Savsar, M., Effects of Kaba Withdrawal Policies ad Other Factors o the Performace of JIT Systems: A Simulatio Study, It. Joural of Prod. Res., 34 (10), 1996, pp [5] Savsar, M., Simulatio Aalysis of a Push-Pull System for a Electroic Assembly Lie, It. Joural of Prod. Ecoomics, 51, 1997, pp [6] Savsar, M. ad Choueii, H. M., A Neural Networ Procedure for Kaba Allocatio i JIT Productio Cotrol Systems, It. Joural of Prod. Research, 38 (14), 2000, pp [7] Olhager, J. ad Ostlug, B., A Itegrated Push-Pull Maufacturig Strategy Europea Joural of Operatioal Research, 45, 1990, pp [8] Hodgso, T.J. ad Wag, D., Optimal Hybrid Push/Pull Cotrol Strategies for Parallel Multistage System: Part II, Iteratioal Joural of Productio Research, 29 (7), 1991, pp [9] Wag, H. ad Xu, C., Hybrid Push/Pull Productio Cotrol Strategy Simulatio ad its Applicatios, Productio Plaig ad Cotrol, 8, 1997, pp [10] Beamo, B.M. ad Bermud, J.M., A hybrid push-pull Ccotrol algorithm for multi-stage, multi-lie productio systems, Productio Plaig & Cotrol,11(4), 2000, pp [11] Duri, C., Frei, Y., ad Dimascolo, M., Compariso amog three pull cotrol policies: Kaba, Base Stoc ad Geeralized Kaba, Aals of Operatios Research, 93(1), 2000, pp [12] Hillier, F.S. ad So, K. C., The Effect of the Coefficiet of Variatio of Operatio Times o the Allocatio of Storage Space i Productio Lie System, IIE Trasactios, (23), 1991, pp [13] Hillier, F.S., So, K. C., ad Bolig, R. W., Notes: Toward Characterizig the Optimal Allocatio of Storage Space i Productio Lie Systems with Variable Processig Times, Maagemet Sci. 39(1), 1993, pp [14] Papadopoulos, H. T. ad Heavey, C., Queuig Theory i Maufacturig Systems Aalysis ad Desig: A Classificatio of Models for Productio ad Trasfer Lies, Europea Joural of Operatioal Research, (92), 1996, pp [15] Papadopoulos, H. T., ad Vouros, G. A., A Model Maagemet System (MMS) for the Desig ad Operatio of Productio Lies, It. Joural of Productio Research, 35(8), 1996, [16] Powel, S. G. ad Pye, D. F., Allocatio of buffers to serial productio lies with bottleecs IIE Trasactios, 28, 1996, pp [17] Vouros, G. A. ad Papadopoulos, H.T., Buffer Allocatio i Ureliable Productio Lies Usig a Kowledge Based System, Computers & Operatios Research, 25(12), 1996, pp [18] Vouros, G. A., Vidalis, M. I., ad Papadopoulos, H. T., A Heuristic Algorithm for Buffer Allocatio i Ureliable Productio Lies, Iteratioal Joural of Quatitative Methods, 6(1), 2000, pp [19] Spiellis, D.D. ad Papadopoulos, C.T., Stochastic Algorithms for Buffer Allocatio i Reliable Productio Lies, Mathematical Problems i Egieerig, 5, 2000a, pp [20] Spiellis, D.D. ad Papadopoulos, C.T., A Simulated Aealig Approach for Buffer Allocatio i Reliable Productio Lies, Aals of Operatios Research, 93, 2000b, pp [21] Gershwi, S.B. ad Schor, J.E., Efficiet algorithms for buffer space allocatio, Aals of Operatios Research, 93, 2000, pp [22] Savsar, M. ad Youssef, A. S., A Itegrated Simulatio-Neural Networ Meta Model Applicatio i Desigig Productio Flow Lies, WSEAS Trasactios o Electroics, 2 (1), 2004, pp [23] Savsar, M. Effects of Maiteace Policies o the Productivity of Flexible Maufacturig Cells, OMEGA, Vol. 34, 2006, pp Mehmet Savsar is a professor ad chairma of the Idustrial & Maagemet Systems Egieerig Departmet at Kuwait Uiversity. Prof. Savsar received his B.Sc. degree from Blac Sea Techical Uiversity i Turey, his M.Sc. ad PhD. Degrees from the Pesylvaia State Uiversity, PA, USA i the area of Idustrial Egieerig. He has bee with Kuwait Uiversity sice Prior to joiig Kuwait Uiversity, he has wored as a faculty member at Aatolia Uiversity i Turey ad at Kig Saud Uiversity i Riyadh, Saudi Arabia ad as a researcher at Pesylvaia State Uiversity, USA. Prof. Savsar has taught a variety of courses i the areas of Productio Plaig ad Ivetory Cotrol, JIT Productio Cotrol, Quality Cotrol, Maiteace ad Reliability, Operatios Research, Stochastic Processes, Computer Simulatio, Plat Layout ad Facilities Plaig, Egieerig Cost Aalysis, ad Maufacturig Systems. His research iterests iclude: Modelig ad Aalysis of Productio Systems, Plat Layout, Reliability ad Maiteace Maagemet, Flexible Maufacturig Systems, Quality Cotrol, ad Just-I-Time (JIT) Productio Cotrol. He has over 100 publicatios i refereed iteratioal jourals ad iteratioal coferece proceedigs. He has completed several research projects. He serves i editorial boards of several iteratioal jourals ad is a referee to several jourals, icludig EJOR, IJAMT, Simulatio, It. J. of Systems Sciece, It. J. of Productio Ecoomics, It. Joural of Prod. Research. msavsar@yahoo.com 646

There is no straightforward approach for choosing the warmup period l.

There is no straightforward approach for choosing the warmup period l. B. Maddah INDE 504 Discrete-Evet Simulatio Output Aalysis () Statistical Aalysis for Steady-State Parameters I a otermiatig simulatio, the iterest is i estimatig the log ru steady state measures of performace.

More information

1 Inferential Methods for Correlation and Regression Analysis

1 Inferential Methods for Correlation and Regression Analysis 1 Iferetial Methods for Correlatio ad Regressio Aalysis I the chapter o Correlatio ad Regressio Aalysis tools for describig bivariate cotiuous data were itroduced. The sample Pearso Correlatio Coefficiet

More information

http://www.xelca.l/articles/ufo_ladigsbaa_houte.aspx imulatio Output aalysis 3/4/06 This lecture Output: A simulatio determies the value of some performace measures, e.g. productio per hour, average queue

More information

Lecture 2: Monte Carlo Simulation

Lecture 2: Monte Carlo Simulation STAT/Q SCI 43: Itroductio to Resamplig ethods Sprig 27 Istructor: Ye-Chi Che Lecture 2: ote Carlo Simulatio 2 ote Carlo Itegratio Assume we wat to evaluate the followig itegratio: e x3 dx What ca we do?

More information

c. Explain the basic Newsvendor model. Why is it useful for SC models? e. What additional research do you believe will be helpful in this area?

c. Explain the basic Newsvendor model. Why is it useful for SC models? e. What additional research do you believe will be helpful in this area? 1. Research Methodology a. What is meat by the supply chai (SC) coordiatio problem ad does it apply to all types of SC s? Does the Bullwhip effect relate to all types of SC s? Also does it relate to SC

More information

First come, first served (FCFS) Batch

First come, first served (FCFS) Batch Queuig Theory Prelimiaries A flow of customers comig towards the service facility forms a queue o accout of lack of capacity to serve them all at a time. RK Jaa Some Examples: Persos waitig at doctor s

More information

Queuing Theory. Basic properties, Markovian models, Networks of queues, General service time distributions, Finite source models, Multiserver queues

Queuing Theory. Basic properties, Markovian models, Networks of queues, General service time distributions, Finite source models, Multiserver queues Queuig Theory Basic properties, Markovia models, Networks of queues, Geeral service time distributios, Fiite source models, Multiserver queues Chapter 8 Kedall s Notatio for Queuig Systems A/B/X/Y/Z: A

More information

A New Solution Method for the Finite-Horizon Discrete-Time EOQ Problem

A New Solution Method for the Finite-Horizon Discrete-Time EOQ Problem This is the Pre-Published Versio. A New Solutio Method for the Fiite-Horizo Discrete-Time EOQ Problem Chug-Lu Li Departmet of Logistics The Hog Kog Polytechic Uiversity Hug Hom, Kowloo, Hog Kog Phoe: +852-2766-7410

More information

SINGLE-CHANNEL QUEUING PROBLEMS APPROACH

SINGLE-CHANNEL QUEUING PROBLEMS APPROACH SINGLE-CHANNEL QUEUING ROBLEMS AROACH Abdurrzzag TAMTAM, Doctoral Degree rogramme () Dept. of Telecommuicatios, FEEC, BUT E-mail: xtamta@stud.feec.vutbr.cz Supervised by: Dr. Karol Molár ABSTRACT The paper

More information

The target reliability and design working life

The target reliability and design working life Safety ad Security Egieerig IV 161 The target reliability ad desig workig life M. Holický Kloker Istitute, CTU i Prague, Czech Republic Abstract Desig workig life ad target reliability levels recommeded

More information

Because it tests for differences between multiple pairs of means in one test, it is called an omnibus test.

Because it tests for differences between multiple pairs of means in one test, it is called an omnibus test. Math 308 Sprig 018 Classes 19 ad 0: Aalysis of Variace (ANOVA) Page 1 of 6 Itroductio ANOVA is a statistical procedure for determiig whether three or more sample meas were draw from populatios with equal

More information

Mathematical Modeling of Optimum 3 Step Stress Accelerated Life Testing for Generalized Pareto Distribution

Mathematical Modeling of Optimum 3 Step Stress Accelerated Life Testing for Generalized Pareto Distribution America Joural of Theoretical ad Applied Statistics 05; 4(: 6-69 Published olie May 8, 05 (http://www.sciecepublishiggroup.com/j/ajtas doi: 0.648/j.ajtas.05040. ISSN: 6-8999 (Prit; ISSN: 6-9006 (Olie Mathematical

More information

Output Analysis (2, Chapters 10 &11 Law)

Output Analysis (2, Chapters 10 &11 Law) B. Maddah ENMG 6 Simulatio Output Aalysis (, Chapters 10 &11 Law) Comparig alterative system cofiguratio Sice the output of a simulatio is radom, the comparig differet systems via simulatio should be doe

More information

CHAPTER 10 INFINITE SEQUENCES AND SERIES

CHAPTER 10 INFINITE SEQUENCES AND SERIES CHAPTER 10 INFINITE SEQUENCES AND SERIES 10.1 Sequeces 10.2 Ifiite Series 10.3 The Itegral Tests 10.4 Compariso Tests 10.5 The Ratio ad Root Tests 10.6 Alteratig Series: Absolute ad Coditioal Covergece

More information

Scheduling under Uncertainty using MILP Sensitivity Analysis

Scheduling under Uncertainty using MILP Sensitivity Analysis Schedulig uder Ucertaity usig MILP Sesitivity Aalysis M. Ierapetritou ad Zheya Jia Departmet of Chemical & Biochemical Egieerig Rutgers, the State Uiversity of New Jersey Piscataway, NJ Abstract The aim

More information

Properties and Hypothesis Testing

Properties and Hypothesis Testing Chapter 3 Properties ad Hypothesis Testig 3.1 Types of data The regressio techiques developed i previous chapters ca be applied to three differet kids of data. 1. Cross-sectioal data. 2. Time series data.

More information

B. Maddah ENMG 622 ENMG /27/07

B. Maddah ENMG 622 ENMG /27/07 B. Maddah ENMG 622 ENMG 5 3/27/7 Queueig Theory () What is a queueig system? A queueig system cosists of servers (resources) that provide service to customers (etities). A Customer requestig service will

More information

Intermittent demand forecasting by using Neural Network with simulated data

Intermittent demand forecasting by using Neural Network with simulated data Proceedigs of the 011 Iteratioal Coferece o Idustrial Egieerig ad Operatios Maagemet Kuala Lumpur, Malaysia, Jauary 4, 011 Itermittet demad forecastig by usig Neural Network with simulated data Nguye Khoa

More information

Chapter 6 Sampling Distributions

Chapter 6 Sampling Distributions Chapter 6 Samplig Distributios 1 I most experimets, we have more tha oe measuremet for ay give variable, each measuremet beig associated with oe radomly selected a member of a populatio. Hece we eed to

More information

Statistics 511 Additional Materials

Statistics 511 Additional Materials Cofidece Itervals o mu Statistics 511 Additioal Materials This topic officially moves us from probability to statistics. We begi to discuss makig ifereces about the populatio. Oe way to differetiate probability

More information

CEE 522 Autumn Uncertainty Concepts for Geotechnical Engineering

CEE 522 Autumn Uncertainty Concepts for Geotechnical Engineering CEE 5 Autum 005 Ucertaity Cocepts for Geotechical Egieerig Basic Termiology Set A set is a collectio of (mutually exclusive) objects or evets. The sample space is the (collectively exhaustive) collectio

More information

ADVANCED SOFTWARE ENGINEERING

ADVANCED SOFTWARE ENGINEERING ADVANCED SOFTWARE ENGINEERING COMP 3705 Exercise Usage-based Testig ad Reliability Versio 1.0-040406 Departmet of Computer Ssciece Sada Narayaappa, Aeliese Adrews Versio 1.1-050405 Departmet of Commuicatio

More information

ANALYSIS OF EXPERIMENTAL ERRORS

ANALYSIS OF EXPERIMENTAL ERRORS ANALYSIS OF EXPERIMENTAL ERRORS All physical measuremets ecoutered i the verificatio of physics theories ad cocepts are subject to ucertaities that deped o the measurig istrumets used ad the coditios uder

More information

FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures

FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING Lectures MODULE 5 STATISTICS II. Mea ad stadard error of sample data. Biomial distributio. Normal distributio 4. Samplig 5. Cofidece itervals

More information

Double Stage Shrinkage Estimator of Two Parameters. Generalized Exponential Distribution

Double Stage Shrinkage Estimator of Two Parameters. Generalized Exponential Distribution Iteratioal Mathematical Forum, Vol., 3, o. 3, 3-53 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/.9/imf.3.335 Double Stage Shrikage Estimator of Two Parameters Geeralized Expoetial Distributio Alaa M.

More information

A statistical method to determine sample size to estimate characteristic value of soil parameters

A statistical method to determine sample size to estimate characteristic value of soil parameters A statistical method to determie sample size to estimate characteristic value of soil parameters Y. Hojo, B. Setiawa 2 ad M. Suzuki 3 Abstract Sample size is a importat factor to be cosidered i determiig

More information

1 Review of Probability & Statistics

1 Review of Probability & Statistics 1 Review of Probability & Statistics a. I a group of 000 people, it has bee reported that there are: 61 smokers 670 over 5 960 people who imbibe (drik alcohol) 86 smokers who imbibe 90 imbibers over 5

More information

t distribution [34] : used to test a mean against an hypothesized value (H 0 : µ = µ 0 ) or the difference

t distribution [34] : used to test a mean against an hypothesized value (H 0 : µ = µ 0 ) or the difference EXST30 Backgroud material Page From the textbook The Statistical Sleuth Mea [0]: I your text the word mea deotes a populatio mea (µ) while the work average deotes a sample average ( ). Variace [0]: The

More information

GUIDELINES ON REPRESENTATIVE SAMPLING

GUIDELINES ON REPRESENTATIVE SAMPLING DRUGS WORKING GROUP VALIDATION OF THE GUIDELINES ON REPRESENTATIVE SAMPLING DOCUMENT TYPE : REF. CODE: ISSUE NO: ISSUE DATE: VALIDATION REPORT DWG-SGL-001 002 08 DECEMBER 2012 Ref code: DWG-SGL-001 Issue

More information

A Model for Scheduling Deteriorating Jobs with Rate-Modifying-Activities on a Single Machine

A Model for Scheduling Deteriorating Jobs with Rate-Modifying-Activities on a Single Machine A Model for Schedulig Deterioratig Jobs with Rate-Modifyig-Activities o a Sigle Machie Yucel Ozturkoglu 1, Robert L. Bulfi 2, Emmett Lodree 3 1.2.3 Dept. of Idustrial ad Systems Egieerig, Aubur Uiversity,

More information

Expectation and Variance of a random variable

Expectation and Variance of a random variable Chapter 11 Expectatio ad Variace of a radom variable The aim of this lecture is to defie ad itroduce mathematical Expectatio ad variace of a fuctio of discrete & cotiuous radom variables ad the distributio

More information

Probability, Expectation Value and Uncertainty

Probability, Expectation Value and Uncertainty Chapter 1 Probability, Expectatio Value ad Ucertaity We have see that the physically observable properties of a quatum system are represeted by Hermitea operators (also referred to as observables ) such

More information

Module 1 Fundamentals in statistics

Module 1 Fundamentals in statistics Normal Distributio Repeated observatios that differ because of experimetal error ofte vary about some cetral value i a roughly symmetrical distributio i which small deviatios occur much more frequetly

More information

Reliability and Queueing

Reliability and Queueing Copyright 999 Uiversity of Califoria Reliability ad Queueig by David G. Messerschmitt Supplemetary sectio for Uderstadig Networked Applicatios: A First Course, Morga Kaufma, 999. Copyright otice: Permissio

More information

Topic 9: Sampling Distributions of Estimators

Topic 9: Sampling Distributions of Estimators Topic 9: Samplig Distributios of Estimators Course 003, 2016 Page 0 Samplig distributios of estimators Sice our estimators are statistics (particular fuctios of radom variables), their distributio ca be

More information

Simulation of Discrete Event Systems

Simulation of Discrete Event Systems Simulatio of Discrete Evet Systems Uit 9 Queueig Models Fall Witer 2014/2015 Uiv.-Prof. Dr.-Ig. Dipl.-Wirt.-Ig. Christopher M. Schlick Chair ad Istitute of Idustrial Egieerig ad Ergoomics RWTH Aache Uiversity

More information

R. van Zyl 1, A.J. van der Merwe 2. Quintiles International, University of the Free State

R. van Zyl 1, A.J. van der Merwe 2. Quintiles International, University of the Free State Bayesia Cotrol Charts for the Two-parameter Expoetial Distributio if the Locatio Parameter Ca Take o Ay Value Betwee Mius Iity ad Plus Iity R. va Zyl, A.J. va der Merwe 2 Quitiles Iteratioal, ruaavz@gmail.com

More information

OBJECTIVES. Chapter 1 INTRODUCTION TO INSTRUMENTATION FUNCTION AND ADVANTAGES INTRODUCTION. At the end of this chapter, students should be able to:

OBJECTIVES. Chapter 1 INTRODUCTION TO INSTRUMENTATION FUNCTION AND ADVANTAGES INTRODUCTION. At the end of this chapter, students should be able to: OBJECTIVES Chapter 1 INTRODUCTION TO INSTRUMENTATION At the ed of this chapter, studets should be able to: 1. Explai the static ad dyamic characteristics of a istrumet. 2. Calculate ad aalyze the measuremet

More information

Simulation. Two Rule For Inverting A Distribution Function

Simulation. Two Rule For Inverting A Distribution Function Simulatio Two Rule For Ivertig A Distributio Fuctio Rule 1. If F(x) = u is costat o a iterval [x 1, x 2 ), the the uiform value u is mapped oto x 2 through the iversio process. Rule 2. If there is a jump

More information

Stochastic Simulation

Stochastic Simulation Stochastic Simulatio 1 Itroductio Readig Assigmet: Read Chapter 1 of text. We shall itroduce may of the key issues to be discussed i this course via a couple of model problems. Model Problem 1 (Jackso

More information

AP Statistics Review Ch. 8

AP Statistics Review Ch. 8 AP Statistics Review Ch. 8 Name 1. Each figure below displays the samplig distributio of a statistic used to estimate a parameter. The true value of the populatio parameter is marked o each samplig distributio.

More information

Final Review for MATH 3510

Final Review for MATH 3510 Fial Review for MATH 50 Calculatio 5 Give a fairly simple probability mass fuctio or probability desity fuctio of a radom variable, you should be able to compute the expected value ad variace of the variable

More information

THE KALMAN FILTER RAUL ROJAS

THE KALMAN FILTER RAUL ROJAS THE KALMAN FILTER RAUL ROJAS Abstract. This paper provides a getle itroductio to the Kalma filter, a umerical method that ca be used for sesor fusio or for calculatio of trajectories. First, we cosider

More information

7-1. Chapter 4. Part I. Sampling Distributions and Confidence Intervals

7-1. Chapter 4. Part I. Sampling Distributions and Confidence Intervals 7-1 Chapter 4 Part I. Samplig Distributios ad Cofidece Itervals 1 7- Sectio 1. Samplig Distributio 7-3 Usig Statistics Statistical Iferece: Predict ad forecast values of populatio parameters... Test hypotheses

More information

DISTRIBUTION LAW Okunev I.V.

DISTRIBUTION LAW Okunev I.V. 1 DISTRIBUTION LAW Okuev I.V. Distributio law belogs to a umber of the most complicated theoretical laws of mathematics. But it is also a very importat practical law. Nothig ca help uderstad complicated

More information

Provläsningsexemplar / Preview TECHNICAL REPORT INTERNATIONAL SPECIAL COMMITTEE ON RADIO INTERFERENCE

Provläsningsexemplar / Preview TECHNICAL REPORT INTERNATIONAL SPECIAL COMMITTEE ON RADIO INTERFERENCE TECHNICAL REPORT CISPR 16-4-3 2004 AMENDMENT 1 2006-10 INTERNATIONAL SPECIAL COMMITTEE ON RADIO INTERFERENCE Amedmet 1 Specificatio for radio disturbace ad immuity measurig apparatus ad methods Part 4-3:

More information

Orthogonal Gaussian Filters for Signal Processing

Orthogonal Gaussian Filters for Signal Processing Orthogoal Gaussia Filters for Sigal Processig Mark Mackezie ad Kiet Tieu Mechaical Egieerig Uiversity of Wollogog.S.W. Australia Abstract A Gaussia filter usig the Hermite orthoormal series of fuctios

More information

EXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY

EXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY EXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA, 016 MODULE : Statistical Iferece Time allowed: Three hours Cadidates should aswer FIVE questios. All questios carry equal marks. The umber

More information

Comparison of Methods for Estimation of Sample Sizes under the Weibull Distribution

Comparison of Methods for Estimation of Sample Sizes under the Weibull Distribution Iteratioal Joural of Applied Egieerig Research ISSN 0973-4562 Volume 12, Number 24 (2017) pp. 14273-14278 Research Idia Publicatios. http://www.ripublicatio.com Compariso of Methods for Estimatio of Sample

More information

Overview. p 2. Chapter 9. Pooled Estimate of. q = 1 p. Notation for Two Proportions. Inferences about Two Proportions. Assumptions

Overview. p 2. Chapter 9. Pooled Estimate of. q = 1 p. Notation for Two Proportions. Inferences about Two Proportions. Assumptions Chapter 9 Slide Ifereces from Two Samples 9- Overview 9- Ifereces about Two Proportios 9- Ifereces about Two Meas: Idepedet Samples 9-4 Ifereces about Matched Pairs 9-5 Comparig Variatio i Two Samples

More information

Resampling Methods. X (1/2), i.e., Pr (X i m) = 1/2. We order the data: X (1) X (2) X (n). Define the sample median: ( n.

Resampling Methods. X (1/2), i.e., Pr (X i m) = 1/2. We order the data: X (1) X (2) X (n). Define the sample median: ( n. Jauary 1, 2019 Resamplig Methods Motivatio We have so may estimators with the property θ θ d N 0, σ 2 We ca also write θ a N θ, σ 2 /, where a meas approximately distributed as Oce we have a cosistet estimator

More information

Anna Janicka Mathematical Statistics 2018/2019 Lecture 1, Parts 1 & 2

Anna Janicka Mathematical Statistics 2018/2019 Lecture 1, Parts 1 & 2 Aa Jaicka Mathematical Statistics 18/19 Lecture 1, Parts 1 & 1. Descriptive Statistics By the term descriptive statistics we will mea the tools used for quatitative descriptio of the properties of a sample

More information

Study on Coal Consumption Curve Fitting of the Thermal Power Based on Genetic Algorithm

Study on Coal Consumption Curve Fitting of the Thermal Power Based on Genetic Algorithm Joural of ad Eergy Egieerig, 05, 3, 43-437 Published Olie April 05 i SciRes. http://www.scirp.org/joural/jpee http://dx.doi.org/0.436/jpee.05.34058 Study o Coal Cosumptio Curve Fittig of the Thermal Based

More information

If, for instance, we were required to test whether the population mean μ could be equal to a certain value μ

If, for instance, we were required to test whether the population mean μ could be equal to a certain value μ STATISTICAL INFERENCE INTRODUCTION Statistical iferece is that brach of Statistics i which oe typically makes a statemet about a populatio based upo the results of a sample. I oesample testig, we essetially

More information

Chapter 11 Output Analysis for a Single Model. Banks, Carson, Nelson & Nicol Discrete-Event System Simulation

Chapter 11 Output Analysis for a Single Model. Banks, Carson, Nelson & Nicol Discrete-Event System Simulation Chapter Output Aalysis for a Sigle Model Baks, Carso, Nelso & Nicol Discrete-Evet System Simulatio Error Estimatio If {,, } are ot statistically idepedet, the S / is a biased estimator of the true variace.

More information

Castiel, Supernatural, Season 6, Episode 18

Castiel, Supernatural, Season 6, Episode 18 13 Differetial Equatios the aswer to your questio ca best be epressed as a series of partial differetial equatios... Castiel, Superatural, Seaso 6, Episode 18 A differetial equatio is a mathematical equatio

More information

NOTES ON DISTRIBUTIONS

NOTES ON DISTRIBUTIONS NOTES ON DISTRIBUTIONS MICHAEL N KATEHAKIS Radom Variables Radom variables represet outcomes from radom pheomea They are specified by two objects The rage R of possible values ad the frequecy fx with which

More information

The New Assembly Line of the Car Corp. School Mathematics in Production Planning

The New Assembly Line of the Car Corp. School Mathematics in Production Planning MaMaEuSch Iteratioal Teacher Meetig 25. 29. September 2004 The New Assembly Lie of the Car Corp. School Mathematics i Productio Plaig Silvia Schwarze Silvia Schwarze, Uiversity of Kaiserslauter, Departmet

More information

Bayesian and E- Bayesian Method of Estimation of Parameter of Rayleigh Distribution- A Bayesian Approach under Linex Loss Function

Bayesian and E- Bayesian Method of Estimation of Parameter of Rayleigh Distribution- A Bayesian Approach under Linex Loss Function Iteratioal Joural of Statistics ad Systems ISSN 973-2675 Volume 12, Number 4 (217), pp. 791-796 Research Idia Publicatios http://www.ripublicatio.com Bayesia ad E- Bayesia Method of Estimatio of Parameter

More information

Generalized Semi- Markov Processes (GSMP)

Generalized Semi- Markov Processes (GSMP) Geeralized Semi- Markov Processes (GSMP) Summary Some Defiitios Markov ad Semi-Markov Processes The Poisso Process Properties of the Poisso Process Iterarrival times Memoryless property ad the residual

More information

Statisticians use the word population to refer the total number of (potential) observations under consideration

Statisticians use the word population to refer the total number of (potential) observations under consideration 6 Samplig Distributios Statisticias use the word populatio to refer the total umber of (potetial) observatios uder cosideratio The populatio is just the set of all possible outcomes i our sample space

More information

PH 425 Quantum Measurement and Spin Winter SPINS Lab 1

PH 425 Quantum Measurement and Spin Winter SPINS Lab 1 PH 425 Quatum Measuremet ad Spi Witer 23 SPIS Lab Measure the spi projectio S z alog the z-axis This is the experimet that is ready to go whe you start the program, as show below Each atom is measured

More information

Comparison Study of Series Approximation. and Convergence between Chebyshev. and Legendre Series

Comparison Study of Series Approximation. and Convergence between Chebyshev. and Legendre Series Applied Mathematical Scieces, Vol. 7, 03, o. 6, 3-337 HIKARI Ltd, www.m-hikari.com http://d.doi.org/0.988/ams.03.3430 Compariso Study of Series Approimatio ad Covergece betwee Chebyshev ad Legedre Series

More information

IE 230 Seat # Name < KEY > Please read these directions. Closed book and notes. 60 minutes.

IE 230 Seat # Name < KEY > Please read these directions. Closed book and notes. 60 minutes. IE 230 Seat # Name < KEY > Please read these directios. Closed book ad otes. 60 miutes. Covers through the ormal distributio, Sectio 4.7 of Motgomery ad Ruger, fourth editio. Cover page ad four pages of

More information

ESTIMATION OF QUALITY PARAMETERS IN THE RADIO FLIGHT SUPPORT OPERATIONAL SYSTEM

ESTIMATION OF QUALITY PARAMETERS IN THE RADIO FLIGHT SUPPORT OPERATIONAL SYSTEM VITION ISSN 648 7788 / eissn 8 48 6 Volume 3: 3 8 doi:.3846/6487788.6.754 ESTIMTION OF QULITY PMETES IN THE DIO FLIGHT SUPPOT OPETIONL SYSTEM Oleksadr SOLOMENTSEV, Maksym ZLISKYI, Oleksiy ZUIEV 3 Natioal

More information

Random Variables, Sampling and Estimation

Random Variables, Sampling and Estimation Chapter 1 Radom Variables, Samplig ad Estimatio 1.1 Itroductio This chapter will cover the most importat basic statistical theory you eed i order to uderstad the ecoometric material that will be comig

More information

Research on the Rework Strategies of RMS Based on Process Reliability

Research on the Rework Strategies of RMS Based on Process Reliability A publicatio of CHEMICAL ENGINEERING TRANSACTIONS VOL., 0 Guest Editors: Erico Zio, Piero Baraldi Copyright 0, AIDIC Servizi S.r.l., ISBN 978-88-95608--; ISSN 97-979 The Italia Associatio of Chemical Egieerig

More information

Estimating the Change Point of Bivariate Binomial Processes Experiencing Step Changes in Their Mean

Estimating the Change Point of Bivariate Binomial Processes Experiencing Step Changes in Their Mean Proceedigs of the 202 Iteratioal Coferece o Idustrial Egieerig ad Operatios Maagemet Istabul, Turey, July 3 6, 202 Estimatig the Chage Poit of Bivariate Biomial Processes Experiecig Step Chages i Their

More information

Principle Of Superposition

Principle Of Superposition ecture 5: PREIMINRY CONCEP O RUCUR NYI Priciple Of uperpositio Mathematically, the priciple of superpositio is stated as ( a ) G( a ) G( ) G a a or for a liear structural system, the respose at a give

More information

Statistical inference: example 1. Inferential Statistics

Statistical inference: example 1. Inferential Statistics Statistical iferece: example 1 Iferetial Statistics POPULATION SAMPLE A clothig store chai regularly buys from a supplier large quatities of a certai piece of clothig. Each item ca be classified either

More information

Bootstrap Intervals of the Parameters of Lognormal Distribution Using Power Rule Model and Accelerated Life Tests

Bootstrap Intervals of the Parameters of Lognormal Distribution Using Power Rule Model and Accelerated Life Tests Joural of Moder Applied Statistical Methods Volume 5 Issue Article --5 Bootstrap Itervals of the Parameters of Logormal Distributio Usig Power Rule Model ad Accelerated Life Tests Mohammed Al-Ha Ebrahem

More information

Goodness-Of-Fit For The Generalized Exponential Distribution. Abstract

Goodness-Of-Fit For The Generalized Exponential Distribution. Abstract Goodess-Of-Fit For The Geeralized Expoetial Distributio By Amal S. Hassa stitute of Statistical Studies & Research Cairo Uiversity Abstract Recetly a ew distributio called geeralized expoetial or expoetiated

More information

Basis for simulation techniques

Basis for simulation techniques Basis for simulatio techiques M. Veeraraghava, March 7, 004 Estimatio is based o a collectio of experimetal outcomes, x, x,, x, where each experimetal outcome is a value of a radom variable. x i. Defiitios

More information

MATH 320: Probability and Statistics 9. Estimation and Testing of Parameters. Readings: Pruim, Chapter 4

MATH 320: Probability and Statistics 9. Estimation and Testing of Parameters. Readings: Pruim, Chapter 4 MATH 30: Probability ad Statistics 9. Estimatio ad Testig of Parameters Estimatio ad Testig of Parameters We have bee dealig situatios i which we have full kowledge of the distributio of a radom variable.

More information

Activity 3: Length Measurements with the Four-Sided Meter Stick

Activity 3: Length Measurements with the Four-Sided Meter Stick Activity 3: Legth Measuremets with the Four-Sided Meter Stick OBJECTIVE: The purpose of this experimet is to study errors ad the propagatio of errors whe experimetal data derived usig a four-sided meter

More information

Empirical Distributions

Empirical Distributions Empirical Distributios A empirical distributio is oe for which each possible evet is assiged a probability derived from experimetal observatio. It is assumed that the evets are idepedet ad the sum of the

More information

Complex Algorithms for Lattice Adaptive IIR Notch Filter

Complex Algorithms for Lattice Adaptive IIR Notch Filter 4th Iteratioal Coferece o Sigal Processig Systems (ICSPS ) IPCSIT vol. 58 () () IACSIT Press, Sigapore DOI:.7763/IPCSIT..V58. Complex Algorithms for Lattice Adaptive IIR Notch Filter Hog Liag +, Nig Jia

More information

11 Correlation and Regression

11 Correlation and Regression 11 Correlatio Regressio 11.1 Multivariate Data Ofte we look at data where several variables are recorded for the same idividuals or samplig uits. For example, at a coastal weather statio, we might record

More information

Optimally Sparse SVMs

Optimally Sparse SVMs A. Proof of Lemma 3. We here prove a lower boud o the umber of support vectors to achieve geeralizatio bouds of the form which we cosider. Importatly, this result holds ot oly for liear classifiers, but

More information

Analysis of Experimental Data

Analysis of Experimental Data Aalysis of Experimetal Data 6544597.0479 ± 0.000005 g Quatitative Ucertaity Accuracy vs. Precisio Whe we make a measuremet i the laboratory, we eed to kow how good it is. We wat our measuremets to be both

More information

Analysis of Experimental Measurements

Analysis of Experimental Measurements Aalysis of Experimetal Measuremets Thik carefully about the process of makig a measuremet. A measuremet is a compariso betwee some ukow physical quatity ad a stadard of that physical quatity. As a example,

More information

Big Picture. 5. Data, Estimates, and Models: quantifying the accuracy of estimates.

Big Picture. 5. Data, Estimates, and Models: quantifying the accuracy of estimates. 5. Data, Estimates, ad Models: quatifyig the accuracy of estimates. 5. Estimatig a Normal Mea 5.2 The Distributio of the Normal Sample Mea 5.3 Normal data, cofidece iterval for, kow 5.4 Normal data, cofidece

More information

Queueing theory and Replacement model

Queueing theory and Replacement model Queueig theory ad Replacemet model. Trucks at a sigle platform weigh-bridge arrive accordig to Poisso probability distributio. The time required to weigh the truck follows a expoetial probability distributio.

More information

OPTIMAL PIECEWISE UNIFORM VECTOR QUANTIZATION OF THE MEMORYLESS LAPLACIAN SOURCE

OPTIMAL PIECEWISE UNIFORM VECTOR QUANTIZATION OF THE MEMORYLESS LAPLACIAN SOURCE Joural of ELECTRICAL EGIEERIG, VOL. 56, O. 7-8, 2005, 200 204 OPTIMAL PIECEWISE UIFORM VECTOR QUATIZATIO OF THE MEMORYLESS LAPLACIA SOURCE Zora H. Perić Veljo Lj. Staović Alesadra Z. Jovaović Srdja M.

More information

Chapter 2 The Monte Carlo Method

Chapter 2 The Monte Carlo Method Chapter 2 The Mote Carlo Method The Mote Carlo Method stads for a broad class of computatioal algorithms that rely o radom sampligs. It is ofte used i physical ad mathematical problems ad is most useful

More information

OPTIMAL ALGORITHMS -- SUPPLEMENTAL NOTES

OPTIMAL ALGORITHMS -- SUPPLEMENTAL NOTES OPTIMAL ALGORITHMS -- SUPPLEMENTAL NOTES Peter M. Maurer Why Hashig is θ(). As i biary search, hashig assumes that keys are stored i a array which is idexed by a iteger. However, hashig attempts to bypass

More information

THE SYSTEMATIC AND THE RANDOM. ERRORS - DUE TO ELEMENT TOLERANCES OF ELECTRICAL NETWORKS

THE SYSTEMATIC AND THE RANDOM. ERRORS - DUE TO ELEMENT TOLERANCES OF ELECTRICAL NETWORKS R775 Philips Res. Repts 26,414-423, 1971' THE SYSTEMATIC AND THE RANDOM. ERRORS - DUE TO ELEMENT TOLERANCES OF ELECTRICAL NETWORKS by H. W. HANNEMAN Abstract Usig the law of propagatio of errors, approximated

More information

SECTION 1.5 : SUMMATION NOTATION + WORK WITH SEQUENCES

SECTION 1.5 : SUMMATION NOTATION + WORK WITH SEQUENCES SECTION 1.5 : SUMMATION NOTATION + WORK WITH SEQUENCES Read Sectio 1.5 (pages 5 9) Overview I Sectio 1.5 we lear to work with summatio otatio ad formulas. We will also itroduce a brief overview of sequeces,

More information

Chapter 4. Fourier Series

Chapter 4. Fourier Series Chapter 4. Fourier Series At this poit we are ready to ow cosider the caoical equatios. Cosider, for eample the heat equatio u t = u, < (4.) subject to u(, ) = si, u(, t) = u(, t) =. (4.) Here,

More information

ENGI 4421 Confidence Intervals (Two Samples) Page 12-01

ENGI 4421 Confidence Intervals (Two Samples) Page 12-01 ENGI 44 Cofidece Itervals (Two Samples) Page -0 Two Sample Cofidece Iterval for a Differece i Populatio Meas [Navidi sectios 5.4-5.7; Devore chapter 9] From the cetral limit theorem, we kow that, for sufficietly

More information

Algorithm Analysis. Chapter 3

Algorithm Analysis. Chapter 3 Data Structures Dr Ahmed Rafat Abas Computer Sciece Dept, Faculty of Computer ad Iformatio, Zagazig Uiversity arabas@zu.edu.eg http://www.arsaliem.faculty.zu.edu.eg/ Algorithm Aalysis Chapter 3 3. Itroductio

More information

Discrete Mathematics for CS Spring 2008 David Wagner Note 22

Discrete Mathematics for CS Spring 2008 David Wagner Note 22 CS 70 Discrete Mathematics for CS Sprig 2008 David Wager Note 22 I.I.D. Radom Variables Estimatig the bias of a coi Questio: We wat to estimate the proportio p of Democrats i the US populatio, by takig

More information

w (1) ˆx w (1) x (1) /ρ and w (2) ˆx w (2) x (2) /ρ.

w (1) ˆx w (1) x (1) /ρ and w (2) ˆx w (2) x (2) /ρ. 2 5. Weighted umber of late jobs 5.1. Release dates ad due dates: maximimizig the weight of o-time jobs Oce we add release dates, miimizig the umber of late jobs becomes a sigificatly harder problem. For

More information

Confidence Intervals for the Population Proportion p

Confidence Intervals for the Population Proportion p Cofidece Itervals for the Populatio Proportio p The cocept of cofidece itervals for the populatio proportio p is the same as the oe for, the samplig distributio of the mea, x. The structure is idetical:

More information

Department of Civil Engineering-I.I.T. Delhi CEL 899: Environmental Risk Assessment HW5 Solution

Department of Civil Engineering-I.I.T. Delhi CEL 899: Environmental Risk Assessment HW5 Solution Departmet of Civil Egieerig-I.I.T. Delhi CEL 899: Evirometal Risk Assessmet HW5 Solutio Note: Assume missig data (if ay) ad metio the same. Q. Suppose X has a ormal distributio defied as N (mea=5, variace=

More information

Statistical Fundamentals and Control Charts

Statistical Fundamentals and Control Charts Statistical Fudametals ad Cotrol Charts 1. Statistical Process Cotrol Basics Chace causes of variatio uavoidable causes of variatios Assigable causes of variatio large variatios related to machies, materials,

More information

Goals. Discrete control concepts. History. Frederick Taylor: Chapter 5 Gunnar Lindstedt

Goals. Discrete control concepts. History. Frederick Taylor: Chapter 5 Gunnar Lindstedt Goals Discrete cotrol cocepts Chapter 5 Guar Lidstedt Goal: you should Uderstad how idustrial productio is orgaized ad the reasos why Be able to calculate a suitable productio rate ad ivetory for a certai

More information

The multi capacitated clustering problem

The multi capacitated clustering problem The multi capacitated clusterig problem Bruo de Aayde Prata 1 Federal Uiversity of Ceará, Brazil Abstract Clusterig problems are combiatorial optimizatio problems wi several idustrial applicatios. The

More information

STAT 350 Handout 19 Sampling Distribution, Central Limit Theorem (6.6)

STAT 350 Handout 19 Sampling Distribution, Central Limit Theorem (6.6) STAT 350 Hadout 9 Samplig Distributio, Cetral Limit Theorem (6.6) A radom sample is a sequece of radom variables X, X 2,, X that are idepedet ad idetically distributed. o This property is ofte abbreviated

More information

LOSS-MINIMIZATION CONTROL OF SCALAR- CONTROLLED INDUCTION MOTOR DRIVES

LOSS-MINIMIZATION CONTROL OF SCALAR- CONTROLLED INDUCTION MOTOR DRIVES LOSS-MINIMIZATION CONTROL OF SCALAR- CONTROLLED INDUCTION MOTOR DRIVES Hussei Sarha, Rateb Al-Issa, ad Qazem Jaber Departmet of Mechatroics Egieerig, Faculty of Egieerig Techology Al-Balqa Applied Uiversity,

More information