Neural Network PID Algorithm for a Class of Discrete-Time Nonlinear Systems

Size: px
Start display at page:

Download "Neural Network PID Algorithm for a Class of Discrete-Time Nonlinear Systems"

Transcription

1 Neural Network PID Algorthm for a Class of Dscrete-Tme Nonlnear Systems Hufang Kong ", Yao Fang Hefe Unversty of Technology, Hefe, P.R.Chna konghufang@6.com Abstract The control of nonlnear system s the hotspot n the control feld. The paper proposes an algorthm to solve the trackng and robustness problem for the dscrete-tme nonlnear system. The completed control algorthm contans three parts. Frst, the dynamc lnearzaton model of nonlnear system s desgned based on Model Free Adaptve Control, whose model parameters are calculated by the nput and output data of system. Second, the model error s estmated usng the Quas-sldng mode control algorthm, hence, the whole model of system s estmated. Fnally, the neural network PID controller s desgned to get the optmal control law. The convergence and BIBO stablty of the control system s proved by the Lyapunov functon. The smulaton results n the lnear and nonlnear system valdate the effectveness and robustness of the algorthm. The robustness effort of Quas-sldng mode control algorthm n nonlnear system s also verfed n the paper. Keywords dynamc lnearzaton model, quas-sldng mode control, nonlnear system, neural network Introducton Wth ncreasng demands on the mprovement of the precson control, the control problem of nonlnear system s attractng more and more attenton[]. Especally, the robustness problem of nonlnear control system model has gradually become an mportant topc n control theory. In general, control algorthms of nonlnear system manly contan the neural network control, fuzzy logc control, the sldng mode control and model free adaptve control (MFAC). From unversal approxmaton theory, a sngle hdden layer neural network can approxmate any nonlnear functon to any prescrbed accuracy f suffcent hdden neurons are provded[]. However, the tranng examples are usually much larger than the hdden nodes, and selectng the approprate number of hdden nodes s the key factor whch determnng the error of the predcton model. And the algorthm of the control system can t ensure the global optmal value of weght[]. The fuzzy logc system can also approxmate any nonlnear functon to any prescrbed accuracy, and t has the advantages n dealng wth the tme-delay, tme-varyng, mult nput sngle output nonlnear system[4]. Especally, the combnaton between fuzzy control and PID JOE Vol. 4, No., 08 0

2 control algorthm, the objectve of mproved control algorthm s to elmnate the steady state error, and the algorthm can also mprove the control accuracy and statonary performance. However, the establshment of fuzzy rules s lack of the systemc approach, and t has to rely on the engneerng experments[5]. Sldng mode varable structure control (SMC) has good robustness to perturbaton and external dsturbance n sldng mode, so t becomes one of the effectve methods to deal wth nonlnear systems wth varous uncertantes[6]. However, the varable structure control wll be the quas-sldng mode control for nonlnear system. Especally, wth the applcaton of the computer, the propertes, stablty and reachng condtons of sldng mode varable structure are changed; and varable structure control method of contnuous tme systems can not be drectly appled to the dscrete tme system. Hence, the quassldng mode control has mportant theoretcal value and practcal sgnfcance to study the varable structure control method for dscrete-tme nonlnear systems. In recent years, the theory and desgn of varable structure control for dscrete tme systems are gradually ncreasng, and adaptve varable structure control method attracts many scholars because of ts advantages of adaptve control and varable structure control[7]. And, n order to solve the dsturbance problem n the system, the upper bound of uncertanty s adopted; t can also express that the dsturbance problem s solved by the worst stuaton. It s no doubt that the dynamc performance and robustness of system can be worse. However, the boundary parameters are dffcult to obtan n real control system. It s all known that the modelng of nonlnear systems s tmeconsumng and laborous, and t s very dffcult to buld relable models for many nonlnear systems, and the cost of modelng s very hgh. The Model Free Adaptve Control (MFAC) s proposed to buld the dynamc lnearzaton model of nonlnear system, the algorthm s based on the theory of pseudo-partal-dervatve (PPD), and the controller just uses the nput and output nformaton[8-9]. The paper combnes the dynamc lnearzaton deology of MFAC and quassldng mode control algorthm to buld a precse model and the neural network s desgned to obtan the optmal control law based on the above model. The control algorthm has the followng advantages, () a better robustness; () a better trackng performance of system. System dentfcaton and control law of the nonlnear system. Dynamc lnearzaton of the nonlnear system Consderng the followng unknown dscrete-tme SISO system yk ( + ) = ( yk ( ),..., yk ( " n), uk ( ),..., uk ( " n)) () y where "() s an unknown nonlnear dfference equaton representng the plant dynamcs, uk ( )" and yk ( )" are measurable scalar nput and output, n y u y and n u s the unknown order of the system. The system () s the normal NARMA model. u 04

3 The followng assumptons are made about the model (): A: The system model s observable and controllable. Ths s the basc requrement for desgnng controller parameters. A: The partal dervatve of () whch s wth respect to the nput parameters u ( s contnuous. Assumpton A s a typcal condton of control system desgn for general nonlnear system. A: The system generalzed Lpschtz, ths s yk ( + ) yk ( + ) " buk ( ) uk ( ) for any and k, k k, k, k" 0 and uk ( ) uk ( ).Assumpton A poses a lmtaton on the rate of change of the system output permssble before the control law to be formulated s applcable. Theorem For the nonlnear system () satsfyng the assumptons A-A, then there must exst a tme-varyng parameter (, called pseudo-partal-dervatve (PPD) [0]. If " u ( k ) 0, the system () can be descrbed as the followng model. yk ( + ) = yk ( ) + ( " uk ( ) () Where, yk ( ) s the estmaton output of system model, "( k ) b and b s the postve constant. Remark: In order to make the condton " u ( 0 n () be satsfed, and meanwhle to make the parameter estmaton algorthm has stronger ablty n trackng tme-varyng parameter, a reset algorthm has been added nto ths MFAC scheme as follows f ˆ "( k ) # or sgn ( ˆ( ) " sgn( ˆ( )) or $ u( k # ) " then ˆ ( k ) = ˆ(). Where s a small postve constant, and ˆ( ) s the ntal value of ˆ ( k ). Consderng ( s a tme-varyng parameter, only the nput and output data can be used to get the optmal soluton. The objectve functon can be desgned n the followng way ˆ J( ( ) = yk ( )" yk ( " ) "( k-) # uk ( -) + µ ( "( k" ) () ˆ where µ > 0 s weght factor, and "( k ) s the estmated value of the delay tme. Gettng the partal dervatve about the (,we can get the optmal estmate value ˆ ( ) ( ) ˆ # uk$ " k = "( k$ ) + ( yk ( ) $ yk ( $ ) $ ˆ "( k$ ) # uk ( -)) µ + # uk ( $ ) (4) where "(0,] s the step factor. JOE Vol. 4, No., 08 05

4 . Model error estmaton usng Quas-sldng mode algorthm In the last secton, the dynamc lnearzaton model (DL model) s desgned to represent the nonlnear system. But the model error stll exsts; n ths secton, we use the Quas-sldng mode control algorthm to estmate the model error. Defne the estmaton error of dynamc lnearzaton model e( e ( y( y( = (5) where y( and y( are the real output and dynamc lnearzaton model output [] respectvely. Defne the functon of sldng mode surface s( T s( = c E( = e( + c0 e( k ) (6) where reachng-law T T c = [,c 0], 0 c s a postve value. Adoptng dscrete-tme sldng mode ( s ( k + ) - s( )/ T = -qs( " sgn( s( ) (7) s ( k + ) = ( " qt ) s( " T sgn( s( ) (8) where > 0 > qt > 0 and > 0 T s samplng perod. Rewrtten (7) as T s( k + ) = ( qt ) s( " T sgn( s( ) = c E( k + ) (9) Accordng to the formula (6)-(9), we can get the estmaton of the model error ek+ ( ) at the next samplng tme: ek ( + ) = (" qtsk ) ( )" Tsgn( sk ( ))" cek ( ) (0) In summary, the dscrete-tme SISO model can be represented n the formula (): y(k +) = y(k +) + e (k +) () where y ( ) s the estmaton value of system model after the addton of Quas- ~ k sldng mode algorthm. ek+ ( ) and yk+ ( ) o represent the estmaton error and output of the dynamc lnearzaton model n the next sample tme, respectvely. The addton of QSMC s to predct the estmaton error n advance and feed back to the neural network controller, therefore, the system can converge n a shorter tme.. Control law desgn based on the artfcal neural network In order to get the optmal control law, we adopt the followng structure of the nonlnear system. NNC s a neural network controller. DL model represents the dynamc 06

5 lnearzaton model n form of (), and QSMC s the Quas-sldng mode controller n secton.. The structure of completed control algorthm s shown n the fgure. " y( k ) + ek () uk ( ) System yk ( ) NNC model yk+ ( ) + DL model " Learnng ek ( ) + " yk+ ( ) + + QSMC Fg.. the completed control structure of the nonlnear system The structure of NNC. The NNC (neural network controller) s represented by the followng structure, whch s the three-layer neural network. The frst layer of NNC s nput layer, the nput data X ( = [ e(, e( k ), e( k )], where e ( represents the trackng error between real output and expected output at sample tme k. where ( k ) y, ( e ( y ( y( = () y represent the desred output and real output respectvely. ek ( ) ek" ( ) ek" ( ) x ( x ( W( u( W( x ( W( Fg.. The nner structure of NNC The second layer s the hdden layer whch contans three neural unts; the response of a neural unt s as follows. $ x( = e( # x( = & e( = e( % e( k % ) " x( = & e( = e( % e( k % ) + e( k % ) () The output of neural network controller u = w x ( + w x ( + w x ( ) (4) ( k JOE Vol. 4, No., 08 07

6 where{ }, =,, w means the weght of neural network, when the approprate value of the w s selected, the controller usually can have a good performance. u ( = u( k " ) + u( k s the control law u( s varable rate of control law. ) at the samplng tme k. So the NNC has the structure of neural network PID controller. The weght of the neural network controller { w }, =,, can be traned by the optmal objectve functon J [ y ( ~ y ( ] c =. So w $ J c ( w ( = -" = " # $ w [ y ( ~ y ( ] ˆ( x ( % (5) where > 0 means the learnng rate of neural network controller, and =,,. ( = w ( k -) + w ( means the weght of neural network controller at the samplng tme k. The stablty and convergence of control algorthm In order to obtan the convergence and stablty of the controller of nonlnear system, another assumpton about the controlled system should be made. A4: The PPD satsfes " c ( > > 0 or " c ( < -, and s a small postve constant. Wthout the loss of generalty, t s assumed n ths paper. Theorem : The nonlnear system () satsfes Assumpton -, the estmaton algorthm of model adopts the formula (5-6). The control rate adopts formula (5). If the expected output of nonlnear system s bounded, and the estmaton of model s stable, and the control algorthm s stable. And the real output and nput s bounded. Proof ) Tme-varyng parameter ˆ( s bounded. Consderng the length of artcle, the paper don t gve the detaled proof, the detaled process s stated n the paper[0]. ) The convergence of the nonlnear system model Defne Lyapunov functon V ( = [ s( ] + (6) where s a small postve const to guarantee V ( whch s a postve functon. Accordng to the reachng-law of contnuous sldng mode control, the reachng law of dscrete-tme sldng mode control can be wrtten as []. " V ( = V ( k + ) V ( < 0 (7) 08

7 " V ( = V ( k + ) V ( = ( s( k + )) = [( qt ) s( # T sgn( s( )] ( s( ) (8) = qt ( qt ) # T( qt ) s( - ( s( ), hence "V 0. Snce > qt > 0,, q, T > 0 Accordng to the Lyapunov stablty theorem, the dentfcaton model s stable. On the promse of the gven ntal value, V (0) s bounded, usng the control law (4), the estmaton of model error e ( tends to zero, ths s lm y( ~ y ( = y( y( = 0. k#" ) The convergence of control algorthm Accordng to the approach ablty of neural network, the network can optmze the parameters of controller by the error back-propagaton way, so the output of controller can approach the desred output[]. Defne global Lyapunov functon V g ( = 0.5( e( ) (9) V g ( = 0.5( e( + e( ) " = e( e( + 0.5( 0.5( e( ) e( ) (0) { As we all know, e( s the functon about the } w, t also ( w e f ( w, w, ). Accordng to the prncple of calculus, we can get the followng expresson. # e( = = " = = " ˆ( & % e( # w = % w = = " '( ˆ( & ) %( y %( y( k " ) + ˆ( & $ # u( ) $ # w % w %(# u( ) $ # w % w [ y ( " ~ y ( ] ( " ~ y ( ) # w % w = ( x ( ) Due to the estmaton model s convergence, so the real output y ( tends to equal to the estmaton value ~ y ( k ). So we can get the followng concluson. () JOE Vol. 4, No., 08 09

8 $ e ( # " ( ˆ( % ) [ y ( " y( ] = & ( x ( ) () Accordng to the formula (0) and (), # V = " g ( = # e( ( e( # e( ) ˆ( [ " ] y ( y( ( x ( ) [ " 0.5 %( ˆ( $ ) %( $ ) () If ( ˆ( # ) = = = $ ( x ( ) ", hence " V g ( 0 ( x ( ), accordng to the prncple of Lyapunov stablty, the control system s stable. Overall, the maxmal trackng error of nonlnear system can be expressed Max ( e( ) = max y ( " y( <. In the range of allowable error, the control system has a global convergence. 4) The boundness of real output and nput Max ( e( ) = max y ( " y( <, e( s bounded, and the desred output s bounded. So the real output s bounded. Snce the tme-varyng parameter ( ) s u ( " k + Max( y( ) ) bounded, and, and also bounded. Clearly, the Theorem can be proved. 4 Smulaton results ] ˆ k, s a const. Hence ( u s In ths secton, the two smulatons are used to show the effectveness and robustness of the control algorthm.. The convergence and superorty of algorthm compared wth the tradtonal PID algorthm n lnear system.. The convergence and robustness of control system n nonlnear system. 4. The convergence and robustness of algorthm n lnear system The convergence of algorthm n lnear system. As we all known, the tradtonal PID algorthm s the most mportant control algorthm n lnear system. The output of the ncremental PID algorthm s uk = k ek + kek + k ek (4) ( ) p ( ) ( ) d ( ( )) 0

9 In order to verfy the superorty compared wth the tradtonal PID algorthm, the dscrete-tme lnear system s defned as follows yk ( ) = 0.8 yk ( ) 0.5 yk ( ) uk ( ) (5) where k s a postve nteger, and the desred output be wrtten as (6) y( = k< 40 (6).5 New algorthm Desred output Tradtonal pd algorthm The system output Sample tme k Fg.. The trackng performance compared wth tradtonal PID n lnear system The smulaton dagram s showed n fgure, as we can see, f the samplng tme s less than, the controller needs to collect the error nformaton of the trackng system, so the real output equal to zero; After three sample tme, the control system can be stable n the fnte tme; the real output can track the desred output perfectly and the error of trackng can be n allowable range. The smulaton results show the new algorthm can depress the overshoot compared wth the tradtonal PID algorthm, decrease the adjustment tme and get the satsfactory trackng performance. The robustness of algorthm n lnear system. The robustness of system s the mportant ndex n control systems, t refers to the perturbaton of system parameters or system structure, the system stll can mantan the characterstcs, lke convergence or stablty. In order to verfy the robustness of lnear system compared wth the tradtonal PID algorthm, the smulaton model s as follows, the parameters perturbaton happens at sample tme k = 0. " 0.8 yk ( ) 0.5 yk ( ) uk ( ) k < 0 yk ( ) = # $ 0.8 yk ( ) 0.8 yk ( ) uk ( ) k >= 0 (7) JOE Vol. 4, No., 08

10 .5 New algorthm Desred output Tradtonal pd algorthm The system output Sample tme k Fg. 4. The robustness of algorthm compared wth tradtonal PID algorthm n lnear system As we can see n the fgure 4, when the structure parameters of system change at the sample tme k = 0, the new algorthm stll has the better trackng performance, and the trackng error can be n the range of allowable at the fnte tme. And the adjustment tme and adjustment ampltude of new algorthm can be smaller durng the perod of the system parameters perturbaton compared wth tradtonal PID algorthm. 4. The convergence and robustness of nonlnear system The convergence and superorty compared wth the MFAC algorthm. MFAC (model free adaptve control), as we know, has the good performance n the nonlnear control system. So, n order to verfy the superorty, we compare wth the MFAC algorthm. The dscrete-tme nonlnear system y( k ) y ( + ) + ( y( k )) = ( u( (8) where u ( s the control varable of controller, y( and y ( k ) are the current and the one step delayed outputs, respectvely. And the desred output of the system s as follows: " 0.5sn( k 500) + 0.cos( k 500)... k < 000 # ( ) = $ > k >= 000 # & % 0... k >= 500 y k (9)

11 New algorthm Desred output MFAC algorthm The system output Sample tme k (a) the comparatve fgure between new algorthm and MFAC algorthm The system output New algorthm Desred output MFAC algorthm Sample tme k (b) Local enlarged fgure of smulaton results Fg. 5. The superorty of control system compared wth the MFAC algorthm As we can see from the fgure 5(a), the trackng error of system can be gnored n the range of error allowed except the sudden change of desred output. The smulaton result valdates the convergence of the algorthm and the stablty of the system dentfcaton n nonlnear system. As shown n the local enlarged fgure 5(b), the MFAC and new algorthm can track the desred output after the several step tmes. And the adjustment tme and adjustment ampltude of the new algorthm have a great mprovement compared wth the MFAC algorthm. The robustness of control system. In order to verfy the robustness of the algorthm, the paper adopts the same control parameters to valdate the robustness of the JOE Vol. 4, No., 08

12 new control algorthm; the trackng performance s shown n the fgure 6. The smulaton model s adopted (0), and the desred output s as the form of (9). yk ( " ) # + ( uk ( ))... k< 00 # + ( yk ( " )) # yk ( " ) yk ( ) = $ + ( uk ( ))...00 > k>= 00 # + ( yk ( " )) # 0.8 yk ( " ) # + ( uk ( ))... k>= 00 % + ( yk ( " )) (0) New algorthm Desred output MFAC The system output Sample tme k (a) The robustness analyss fgure n nonlnear system 0.6 New algorthm Desred output MFAC 0.5 The system output Sample tme k (b) The local enlarged fgure between new algorthm and MFAC algorthm Fg. 6. The robust analyss n the nonlnear system 4

13 As we can see n the fgure 6, when the structure parameters of system change at the samplng tme k = 00, k = 00, the algorthm stll has the better trackng performance, and the trackng error can be n the range of allowable at the fnte tme. From the local enlarged fgure 6(b), we can see that the adjustment tme and adjustment ampltude of the new algorthm s less than the MFAC algorthm. 5 Concluson In ths paper, a new dynamc lnearzaton model about the Quas-Sldng Mode algorthm was proposed for dentfcaton of complex nonlnear system. A neural network PID controller s desgned to get the optmzed control rate based on the above model. The advantages of algorthm are as follows:. better robustness. better trackng performance. less adjustment tme and ampltude. And the global stablty of the system s proved by the way of the Lyponou functon and Matlab smulaton. 6 Acknowledgment The work s supported by the Natonal Scence and technology support program (NO 04BAG06B0) and Fundamental Research Funds for the Central Unverstes (No 04HGCH000). 7 References [] Dng, Feng. "Herarchcal mult-nnovaton stochastc gradent algorthm for Hammersten nonlnear system modelng." Appled Mathematcal Modellng 7.4 (0): [] Ngam, Vvek Prakash, and Danel Graupe. "A neural-network-based detecton of eplepsy." Neurologcal Research 6. (004): [] Wang, Tong, Hujun Gao, and Janbn Qu. "A combned adaptve neural network and nonlnear model predctve control for multrate networked ndustral process control." IEEE Transactons on Neural Networks and Learnng Systems 7. (06): [4] L, Hongy, et al. "Control of nonlnear networked systems wth packet dropouts: nterval type- fuzzy model-based approach." IEEE Transactons on Cybernetcs 45. (05): [5] Lu, Yan-Jun, Shaocheng Tong, and CL Phlp Chen. "Adaptve fuzzy control va observer desgn for uncertan nonlnear systems wth unmodeled dynamcs."ieee Transactons on Fuzzy Systems. (0): JOE Vol. 4, No., 08 5

14 [6] Hou, Y-You, and Zhang-Ln Wan. "Robust Stablty for Nonlnear Systems wth Tme- Varyng Delay and Uncertantes va the Quas-Sldng Mode Control." Internatonal Journal of Antennas and Propagaton 04 (04). [7] Ma, Hafeng, Janhua Wu, and Zhenhua Xong. "Dscrete-tme sldng-mode control wth mproved quas-sldng-mode doman." IEEE Transactons on Industral Electroncs 6.0 (06): [8] Zhu, Yuanmng, and Zhongsheng Hou. "Data-drven MFAC for a class of dscrete-tme nonlnear systems wth RBFNN." IEEE transactons on neural networks and learnng systems 5.5 (04): [9] Ma, Png, et al. "Man steam temperature control system based on MFAC." Electrc Power Scence and Engneerng (006): 006. [0] Cheng, Zhhu, Zhongsheng Hou, and Shangta Jn. "MFAC-based balance control for freeway and auxlary road system wth mult-ntersectons." Control Conference (ASCC), 05 0th Asan. IEEE, 05. [] Han, Yueqao, Yonggu Kao, and Cunchen Gao. "Robust sldng mode control for uncertan dscrete sngular systems wth tme-varyng delays and external dsturbances." Automatca 75 (07): [] Sarpturk, S. Z., Yorgo Istefanopulos, and Okyay Kaynak. "On the stablty of dscrete-tme sldng mode control systems." IEEE Transactons on Automatc Control.0 (987): [] Mukhopadhyay, Snehass, and Kumpat S. Narendra. "Dsturbance rejecton n nonlnear systems usng neural networks." IEEE Transactons on Neural Networks 4. (99): [4] Chandrasena Premawardhena, N., ICT n the foregn language classroom n Sr Lanka: A journey through a decade. 0th World Conference on Computers n Educaton (WCCE 0), Ncolaus Coperncus Unversty, July -5 0, Torun, Poland.pp -4 8 Authors Hufang Kong s the Professor and the Drector of the Research Center of Automotve Electroncs and Control Technology n Hefe Unversty of Technology, No 9, Tunx Road, Hefe, Chna, Her research nterests ncludng Control Engneerng, Industral Automaton, and Dynamcs and Control. (konghufang@6.com). Yao Fang s a PH.D student n the Automotve Electroncs and Control Research Center n Hefe Unversty of Technology, Majorng n modelng and control of complex nonlnear systemsenergy management of hybrd electrc vehcle and the behavor decson of drvers. Artcle submtted October 07. Resubmtted December 07. Fnal acceptance 06 February 08. Fnal verson publshed as submtted by the authors. 6

A Fuzzy-Neural Adaptive Iterative Learning Control for Freeway Traffic Flow Systems

A Fuzzy-Neural Adaptive Iterative Learning Control for Freeway Traffic Flow Systems Proceedngs of the Internatonal MultConference of Engneers and Computer Scentsts 016 Vol I, IMECS 016, March 16-18, 016, Hong Kong A Fuzzy-Neural Adaptve Iteratve Learnng Control for Freeway Traffc Flow

More information

De-noising Method Based on Kernel Adaptive Filtering for Telemetry Vibration Signal of the Vehicle Test Kejun ZENG

De-noising Method Based on Kernel Adaptive Filtering for Telemetry Vibration Signal of the Vehicle Test Kejun ZENG 6th Internatonal Conference on Mechatroncs, Materals, Botechnology and Envronment (ICMMBE 6) De-nosng Method Based on Kernel Adaptve Flterng for elemetry Vbraton Sgnal of the Vehcle est Kejun ZEG PLA 955

More information

EEE 241: Linear Systems

EEE 241: Linear Systems EEE : Lnear Systems Summary #: Backpropagaton BACKPROPAGATION The perceptron rule as well as the Wdrow Hoff learnng were desgned to tran sngle layer networks. They suffer from the same dsadvantage: they

More information

Numerical Heat and Mass Transfer

Numerical Heat and Mass Transfer Master degree n Mechancal Engneerng Numercal Heat and Mass Transfer 06-Fnte-Dfference Method (One-dmensonal, steady state heat conducton) Fausto Arpno f.arpno@uncas.t Introducton Why we use models and

More information

Adaptive Consensus Control of Multi-Agent Systems with Large Uncertainty and Time Delays *

Adaptive Consensus Control of Multi-Agent Systems with Large Uncertainty and Time Delays * Journal of Robotcs, etworkng and Artfcal Lfe, Vol., o. (September 04), 5-9 Adaptve Consensus Control of Mult-Agent Systems wth Large Uncertanty and me Delays * L Lu School of Mechancal Engneerng Unversty

More information

Transfer Functions. Convenient representation of a linear, dynamic model. A transfer function (TF) relates one input and one output: ( ) system

Transfer Functions. Convenient representation of a linear, dynamic model. A transfer function (TF) relates one input and one output: ( ) system Transfer Functons Convenent representaton of a lnear, dynamc model. A transfer functon (TF) relates one nput and one output: x t X s y t system Y s The followng termnology s used: x y nput output forcng

More information

Study on Active Micro-vibration Isolation System with Linear Motor Actuator. Gong-yu PAN, Wen-yan GU and Dong LI

Study on Active Micro-vibration Isolation System with Linear Motor Actuator. Gong-yu PAN, Wen-yan GU and Dong LI 2017 2nd Internatonal Conference on Electrcal and Electroncs: echnques and Applcatons (EEA 2017) ISBN: 978-1-60595-416-5 Study on Actve Mcro-vbraton Isolaton System wth Lnear Motor Actuator Gong-yu PAN,

More information

Application research on rough set -neural network in the fault diagnosis system of ball mill

Application research on rough set -neural network in the fault diagnosis system of ball mill Avalable onlne www.ocpr.com Journal of Chemcal and Pharmaceutcal Research, 2014, 6(4):834-838 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 Applcaton research on rough set -neural network n the

More information

Adaptive sliding mode reliable excitation control design for power systems

Adaptive sliding mode reliable excitation control design for power systems Acta Technca 6, No. 3B/17, 593 6 c 17 Insttute of Thermomechancs CAS, v.v.. Adaptve sldng mode relable exctaton control desgn for power systems Xuetng Lu 1, 3, Yanchao Yan Abstract. In ths paper, the problem

More information

For now, let us focus on a specific model of neurons. These are simplified from reality but can achieve remarkable results.

For now, let us focus on a specific model of neurons. These are simplified from reality but can achieve remarkable results. Neural Networks : Dervaton compled by Alvn Wan from Professor Jtendra Malk s lecture Ths type of computaton s called deep learnng and s the most popular method for many problems, such as computer vson

More information

The Two-scale Finite Element Errors Analysis for One Class of Thermoelastic Problem in Periodic Composites

The Two-scale Finite Element Errors Analysis for One Class of Thermoelastic Problem in Periodic Composites 7 Asa-Pacfc Engneerng Technology Conference (APETC 7) ISBN: 978--6595-443- The Two-scale Fnte Element Errors Analyss for One Class of Thermoelastc Problem n Perodc Compostes Xaoun Deng Mngxang Deng ABSTRACT

More information

Design and Optimization of Fuzzy Controller for Inverse Pendulum System Using Genetic Algorithm

Design and Optimization of Fuzzy Controller for Inverse Pendulum System Using Genetic Algorithm Desgn and Optmzaton of Fuzzy Controller for Inverse Pendulum System Usng Genetc Algorthm H. Mehraban A. Ashoor Unversty of Tehran Unversty of Tehran h.mehraban@ece.ut.ac.r a.ashoor@ece.ut.ac.r Abstract:

More information

Design and Analysis of Bayesian Model Predictive Controller

Design and Analysis of Bayesian Model Predictive Controller Computer and Informaton Scence; Vol. 7, No. 3; 014 ISSN 1913-8989 E-ISSN 1913-8997 Publshed by Canadan Center of Scence and Educaton Desgn and Analyss of Bayesan Model Predctve Controller Yjan Lu 1, Wexng

More information

Generalized Linear Methods

Generalized Linear Methods Generalzed Lnear Methods 1 Introducton In the Ensemble Methods the general dea s that usng a combnaton of several weak learner one could make a better learner. More formally, assume that we have a set

More information

829. An adaptive method for inertia force identification in cantilever under moving mass

829. An adaptive method for inertia force identification in cantilever under moving mass 89. An adaptve method for nerta force dentfcaton n cantlever under movng mass Qang Chen 1, Mnzhuo Wang, Hao Yan 3, Haonan Ye 4, Guola Yang 5 1,, 3, 4 Department of Control and System Engneerng, Nanng Unversty,

More information

CHAPTER 5 NUMERICAL EVALUATION OF DYNAMIC RESPONSE

CHAPTER 5 NUMERICAL EVALUATION OF DYNAMIC RESPONSE CHAPTER 5 NUMERICAL EVALUATION OF DYNAMIC RESPONSE Analytcal soluton s usually not possble when exctaton vares arbtrarly wth tme or f the system s nonlnear. Such problems can be solved by numercal tmesteppng

More information

RBF Neural Network Model Training by Unscented Kalman Filter and Its Application in Mechanical Fault Diagnosis

RBF Neural Network Model Training by Unscented Kalman Filter and Its Application in Mechanical Fault Diagnosis Appled Mechancs and Materals Submtted: 24-6-2 ISSN: 662-7482, Vols. 62-65, pp 2383-2386 Accepted: 24-6- do:.428/www.scentfc.net/amm.62-65.2383 Onlne: 24-8- 24 rans ech Publcatons, Swtzerland RBF Neural

More information

Neuro-Adaptive Design - I:

Neuro-Adaptive Design - I: Lecture 36 Neuro-Adaptve Desgn - I: A Robustfyng ool for Dynamc Inverson Desgn Dr. Radhakant Padh Asst. Professor Dept. of Aerospace Engneerng Indan Insttute of Scence - Bangalore Motvaton Perfect system

More information

Operating conditions of a mine fan under conditions of variable resistance

Operating conditions of a mine fan under conditions of variable resistance Paper No. 11 ISMS 216 Operatng condtons of a mne fan under condtons of varable resstance Zhang Ynghua a, Chen L a, b, Huang Zhan a, *, Gao Yukun a a State Key Laboratory of Hgh-Effcent Mnng and Safety

More information

Parameter Estimation for Dynamic System using Unscented Kalman filter

Parameter Estimation for Dynamic System using Unscented Kalman filter Parameter Estmaton for Dynamc System usng Unscented Kalman flter Jhoon Seung 1,a, Amr Atya F. 2,b, Alexander G.Parlos 3,c, and Klto Chong 1,4,d* 1 Dvson of Electroncs Engneerng, Chonbuk Natonal Unversty,

More information

A Hybrid Variational Iteration Method for Blasius Equation

A Hybrid Variational Iteration Method for Blasius Equation Avalable at http://pvamu.edu/aam Appl. Appl. Math. ISSN: 1932-9466 Vol. 10, Issue 1 (June 2015), pp. 223-229 Applcatons and Appled Mathematcs: An Internatonal Journal (AAM) A Hybrd Varatonal Iteraton Method

More information

Econ107 Applied Econometrics Topic 3: Classical Model (Studenmund, Chapter 4)

Econ107 Applied Econometrics Topic 3: Classical Model (Studenmund, Chapter 4) I. Classcal Assumptons Econ7 Appled Econometrcs Topc 3: Classcal Model (Studenmund, Chapter 4) We have defned OLS and studed some algebrac propertes of OLS. In ths topc we wll study statstcal propertes

More information

PREDICTIVE CONTROL BY DISTRIBUTED PARAMETER SYSTEMS BLOCKSET FOR MATLAB & SIMULINK

PREDICTIVE CONTROL BY DISTRIBUTED PARAMETER SYSTEMS BLOCKSET FOR MATLAB & SIMULINK PREDICTIVE CONTROL BY DISTRIBUTED PARAMETER SYSTEMS BLOCKSET FOR MATLAB & SIMULINK G. Hulkó, C. Belavý, P. Buček, P. Noga Insttute of automaton, measurement and appled nformatcs, Faculty of Mechancal Engneerng,

More information

Module 3 LOSSY IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur

Module 3 LOSSY IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur Module 3 LOSSY IMAGE COMPRESSION SYSTEMS Verson ECE IIT, Kharagpur Lesson 6 Theory of Quantzaton Verson ECE IIT, Kharagpur Instructonal Objectves At the end of ths lesson, the students should be able to:

More information

AN IMPROVED PARTICLE FILTER ALGORITHM BASED ON NEURAL NETWORK FOR TARGET TRACKING

AN IMPROVED PARTICLE FILTER ALGORITHM BASED ON NEURAL NETWORK FOR TARGET TRACKING AN IMPROVED PARTICLE FILTER ALGORITHM BASED ON NEURAL NETWORK FOR TARGET TRACKING Qn Wen, Peng Qcong 40 Lab, Insttuton of Communcaton and Informaton Engneerng,Unversty of Electronc Scence and Technology

More information

COMPARISON OF SOME RELIABILITY CHARACTERISTICS BETWEEN REDUNDANT SYSTEMS REQUIRING SUPPORTING UNITS FOR THEIR OPERATIONS

COMPARISON OF SOME RELIABILITY CHARACTERISTICS BETWEEN REDUNDANT SYSTEMS REQUIRING SUPPORTING UNITS FOR THEIR OPERATIONS Avalable onlne at http://sck.org J. Math. Comput. Sc. 3 (3), No., 6-3 ISSN: 97-537 COMPARISON OF SOME RELIABILITY CHARACTERISTICS BETWEEN REDUNDANT SYSTEMS REQUIRING SUPPORTING UNITS FOR THEIR OPERATIONS

More information

Unknown input extended Kalman filter-based fault diagnosis for satellite actuator

Unknown input extended Kalman filter-based fault diagnosis for satellite actuator Internatonal Conference on Computer and Automaton Engneerng (ICCAE ) IPCSI vol 44 () () IACSI Press, Sngapore DOI: 776/IPCSIV44 Unnown nput extended Kalman flter-based fault dagnoss for satellte actuator

More information

Chapter 2 A Class of Robust Solution for Linear Bilevel Programming

Chapter 2 A Class of Robust Solution for Linear Bilevel Programming Chapter 2 A Class of Robust Soluton for Lnear Blevel Programmng Bo Lu, Bo L and Yan L Abstract Under the way of the centralzed decson-makng, the lnear b-level programmng (BLP) whose coeffcents are supposed

More information

Solving Nonlinear Differential Equations by a Neural Network Method

Solving Nonlinear Differential Equations by a Neural Network Method Solvng Nonlnear Dfferental Equatons by a Neural Network Method Luce P. Aarts and Peter Van der Veer Delft Unversty of Technology, Faculty of Cvlengneerng and Geoscences, Secton of Cvlengneerng Informatcs,

More information

Fuzzy Boundaries of Sample Selection Model

Fuzzy Boundaries of Sample Selection Model Proceedngs of the 9th WSES Internatonal Conference on ppled Mathematcs, Istanbul, Turkey, May 7-9, 006 (pp309-34) Fuzzy Boundares of Sample Selecton Model L. MUHMD SFIIH, NTON BDULBSH KMIL, M. T. BU OSMN

More information

Digital Signal Processing

Digital Signal Processing Dgtal Sgnal Processng Dscrete-tme System Analyss Manar Mohasen Offce: F8 Emal: manar.subh@ut.ac.r School of IT Engneerng Revew of Precedent Class Contnuous Sgnal The value of the sgnal s avalable over

More information

A revised adaptive fuzzy sliding mode controller for robotic manipulators

A revised adaptive fuzzy sliding mode controller for robotic manipulators A revsed adaptve fuzzy sldng mode controller for robotc manpulators Xaosong Lu* Department of Systems and Computer Engneerng, Carleton Unversty, 5 Colonel By Drve, Ottawa, Ontaro, Canada E-mal: luxaos@sce.carleton.ca

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(5): Research Article

Journal of Chemical and Pharmaceutical Research, 2014, 6(5): Research Article Avalable onlne www.jocpr.com Journal of Chemcal and Pharmaceutcal Research, 014, 6(5):1683-1688 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 Multple mode control based on VAV ar condtonng system

More information

Adaptive Tracking Control of Uncertain MIMO Nonlinear Systems with Time-varying Delays and Unmodeled Dynamics

Adaptive Tracking Control of Uncertain MIMO Nonlinear Systems with Time-varying Delays and Unmodeled Dynamics Internatonal Journal of Automaton and Computng (3), June 3, 94- DOI:.7/s633-3-7- Adaptve Trackng Control of Uncertan MIMO Nonlnear Systems wth Tme-varyng Delays and Unmodeled Dynamcs Xao-Cheng Sh Tan-Png

More information

Additional Codes using Finite Difference Method. 1 HJB Equation for Consumption-Saving Problem Without Uncertainty

Additional Codes using Finite Difference Method. 1 HJB Equation for Consumption-Saving Problem Without Uncertainty Addtonal Codes usng Fnte Dfference Method Benamn Moll 1 HJB Equaton for Consumpton-Savng Problem Wthout Uncertanty Before consderng the case wth stochastc ncome n http://www.prnceton.edu/~moll/ HACTproect/HACT_Numercal_Appendx.pdf,

More information

Note 10. Modeling and Simulation of Dynamic Systems

Note 10. Modeling and Simulation of Dynamic Systems Lecture Notes of ME 475: Introducton to Mechatroncs Note 0 Modelng and Smulaton of Dynamc Systems Department of Mechancal Engneerng, Unversty Of Saskatchewan, 57 Campus Drve, Saskatoon, SK S7N 5A9, Canada

More information

Week 5: Neural Networks

Week 5: Neural Networks Week 5: Neural Networks Instructor: Sergey Levne Neural Networks Summary In the prevous lecture, we saw how we can construct neural networks by extendng logstc regresson. Neural networks consst of multple

More information

A Dioid Linear Algebra Approach to Study a Class of Continuous Petri Nets

A Dioid Linear Algebra Approach to Study a Class of Continuous Petri Nets A Dod Lnear Algebra Approach to Study a Class of Contnuous Petr Nets Duan Zhang, Huapng Da, Youxan Sun Natonal Laboratory of Industral Control Technology, Zhejang Unversty, Hangzhou, P.R.Chna, 327 {dzhang,

More information

On an Extension of Stochastic Approximation EM Algorithm for Incomplete Data Problems. Vahid Tadayon 1

On an Extension of Stochastic Approximation EM Algorithm for Incomplete Data Problems. Vahid Tadayon 1 On an Extenson of Stochastc Approxmaton EM Algorthm for Incomplete Data Problems Vahd Tadayon Abstract: The Stochastc Approxmaton EM (SAEM algorthm, a varant stochastc approxmaton of EM, s a versatle tool

More information

Microwave Diversity Imaging Compression Using Bioinspired

Microwave Diversity Imaging Compression Using Bioinspired Mcrowave Dversty Imagng Compresson Usng Bonspred Neural Networks Youwe Yuan 1, Yong L 1, Wele Xu 1, Janghong Yu * 1 School of Computer Scence and Technology, Hangzhou Danz Unversty, Hangzhou, Zhejang,

More information

Experience with Automatic Generation Control (AGC) Dynamic Simulation in PSS E

Experience with Automatic Generation Control (AGC) Dynamic Simulation in PSS E Semens Industry, Inc. Power Technology Issue 113 Experence wth Automatc Generaton Control (AGC) Dynamc Smulaton n PSS E Lu Wang, Ph.D. Staff Software Engneer lu_wang@semens.com Dngguo Chen, Ph.D. Staff

More information

The Chaotic Robot Prediction by Neuro Fuzzy Algorithm (2) = θ (3) = ω. Asin. A v. Mana Tarjoman, Shaghayegh Zarei

The Chaotic Robot Prediction by Neuro Fuzzy Algorithm (2) = θ (3) = ω. Asin. A v. Mana Tarjoman, Shaghayegh Zarei The Chaotc Robot Predcton by Neuro Fuzzy Algorthm Mana Tarjoman, Shaghayegh Zare Abstract In ths paper an applcaton of the adaptve neurofuzzy nference system has been ntroduced to predct the behavor of

More information

Identification of Linear Partial Difference Equations with Constant Coefficients

Identification of Linear Partial Difference Equations with Constant Coefficients J. Basc. Appl. Sc. Res., 3(1)6-66, 213 213, TextRoad Publcaton ISSN 29-434 Journal of Basc and Appled Scentfc Research www.textroad.com Identfcaton of Lnear Partal Dfference Equatons wth Constant Coeffcents

More information

A NOVEL DESIGN APPROACH FOR MULTIVARIABLE QUANTITATIVE FEEDBACK DESIGN WITH TRACKING ERROR SPECIFICATIONS

A NOVEL DESIGN APPROACH FOR MULTIVARIABLE QUANTITATIVE FEEDBACK DESIGN WITH TRACKING ERROR SPECIFICATIONS A OVEL DESIG APPROACH FOR MULTIVARIABLE QUATITATIVE FEEDBACK DESIG WITH TRACKIG ERROR SPECIFICATIOS Seyyed Mohammad Mahd Alav, Al Khak-Sedgh, Batool Labb Department of Electronc and Computer Engneerng,

More information

The Study of Teaching-learning-based Optimization Algorithm

The Study of Teaching-learning-based Optimization Algorithm Advanced Scence and Technology Letters Vol. (AST 06), pp.05- http://dx.do.org/0.57/astl.06. The Study of Teachng-learnng-based Optmzaton Algorthm u Sun, Yan fu, Lele Kong, Haolang Q,, Helongang Insttute

More information

Neural Networks & Learning

Neural Networks & Learning Neural Netorks & Learnng. Introducton The basc prelmnares nvolved n the Artfcal Neural Netorks (ANN) are descrbed n secton. An Artfcal Neural Netorks (ANN) s an nformaton-processng paradgm that nspred

More information

General viscosity iterative method for a sequence of quasi-nonexpansive mappings

General viscosity iterative method for a sequence of quasi-nonexpansive mappings Avalable onlne at www.tjnsa.com J. Nonlnear Sc. Appl. 9 (2016), 5672 5682 Research Artcle General vscosty teratve method for a sequence of quas-nonexpansve mappngs Cuje Zhang, Ynan Wang College of Scence,

More information

A Network Intrusion Detection Method Based on Improved K-means Algorithm

A Network Intrusion Detection Method Based on Improved K-means Algorithm Advanced Scence and Technology Letters, pp.429-433 http://dx.do.org/10.14257/astl.2014.53.89 A Network Intruson Detecton Method Based on Improved K-means Algorthm Meng Gao 1,1, Nhong Wang 1, 1 Informaton

More information

An Improved multiple fractal algorithm

An Improved multiple fractal algorithm Advanced Scence and Technology Letters Vol.31 (MulGraB 213), pp.184-188 http://dx.do.org/1.1427/astl.213.31.41 An Improved multple fractal algorthm Yun Ln, Xaochu Xu, Jnfeng Pang College of Informaton

More information

ANSWERS. Problem 1. and the moment generating function (mgf) by. defined for any real t. Use this to show that E( U) var( U)

ANSWERS. Problem 1. and the moment generating function (mgf) by. defined for any real t. Use this to show that E( U) var( U) Econ 413 Exam 13 H ANSWERS Settet er nndelt 9 deloppgaver, A,B,C, som alle anbefales å telle lkt for å gøre det ltt lettere å stå. Svar er gtt . Unfortunately, there s a prntng error n the hnt of

More information

DUE: WEDS FEB 21ST 2018

DUE: WEDS FEB 21ST 2018 HOMEWORK # 1: FINITE DIFFERENCES IN ONE DIMENSION DUE: WEDS FEB 21ST 2018 1. Theory Beam bendng s a classcal engneerng analyss. The tradtonal soluton technque makes smplfyng assumptons such as a constant

More information

Introduction. - The Second Lyapunov Method. - The First Lyapunov Method

Introduction. - The Second Lyapunov Method. - The First Lyapunov Method Stablty Analyss A. Khak Sedgh Control Systems Group Faculty of Electrcal and Computer Engneerng K. N. Toos Unversty of Technology February 2009 1 Introducton Stablty s the most promnent characterstc of

More information

Supporting Information

Supporting Information Supportng Informaton The neural network f n Eq. 1 s gven by: f x l = ReLU W atom x l + b atom, 2 where ReLU s the element-wse rectfed lnear unt, 21.e., ReLUx = max0, x, W atom R d d s the weght matrx to

More information

risk and uncertainty assessment

risk and uncertainty assessment Optmal forecastng of atmospherc qualty n ndustral regons: rsk and uncertanty assessment Vladmr Penenko Insttute of Computatonal Mathematcs and Mathematcal Geophyscs SD RAS Goal Development of theoretcal

More information

Off-policy Reinforcement Learning for Robust Control of Discrete-time Uncertain Linear Systems

Off-policy Reinforcement Learning for Robust Control of Discrete-time Uncertain Linear Systems Off-polcy Renforcement Learnng for Robust Control of Dscrete-tme Uncertan Lnear Systems Yonglang Yang 1 Zhshan Guo 2 Donald Wunsch 3 Yxn Yn 1 1 School of Automatc and Electrcal Engneerng Unversty of Scence

More information

A Robust Method for Calculating the Correlation Coefficient

A Robust Method for Calculating the Correlation Coefficient A Robust Method for Calculatng the Correlaton Coeffcent E.B. Nven and C. V. Deutsch Relatonshps between prmary and secondary data are frequently quantfed usng the correlaton coeffcent; however, the tradtonal

More information

3.1 Expectation of Functions of Several Random Variables. )' be a k-dimensional discrete or continuous random vector, with joint PMF p (, E X E X1 E X

3.1 Expectation of Functions of Several Random Variables. )' be a k-dimensional discrete or continuous random vector, with joint PMF p (, E X E X1 E X Statstcs 1: Probablty Theory II 37 3 EPECTATION OF SEVERAL RANDOM VARIABLES As n Probablty Theory I, the nterest n most stuatons les not on the actual dstrbuton of a random vector, but rather on a number

More information

Uncertainty in measurements of power and energy on power networks

Uncertainty in measurements of power and energy on power networks Uncertanty n measurements of power and energy on power networks E. Manov, N. Kolev Department of Measurement and Instrumentaton, Techncal Unversty Sofa, bul. Klment Ohrdsk No8, bl., 000 Sofa, Bulgara Tel./fax:

More information

DETERMINATION OF TEMPERATURE DISTRIBUTION FOR ANNULAR FINS WITH TEMPERATURE DEPENDENT THERMAL CONDUCTIVITY BY HPM

DETERMINATION OF TEMPERATURE DISTRIBUTION FOR ANNULAR FINS WITH TEMPERATURE DEPENDENT THERMAL CONDUCTIVITY BY HPM Ganj, Z. Z., et al.: Determnaton of Temperature Dstrbuton for S111 DETERMINATION OF TEMPERATURE DISTRIBUTION FOR ANNULAR FINS WITH TEMPERATURE DEPENDENT THERMAL CONDUCTIVITY BY HPM by Davood Domr GANJI

More information

Errors in Nobel Prize for Physics (7) Improper Schrodinger Equation and Dirac Equation

Errors in Nobel Prize for Physics (7) Improper Schrodinger Equation and Dirac Equation Errors n Nobel Prze for Physcs (7) Improper Schrodnger Equaton and Drac Equaton u Yuhua (CNOOC Research Insttute, E-mal:fuyh945@sna.com) Abstract: One of the reasons for 933 Nobel Prze for physcs s for

More information

Research Article Green s Theorem for Sign Data

Research Article Green s Theorem for Sign Data Internatonal Scholarly Research Network ISRN Appled Mathematcs Volume 2012, Artcle ID 539359, 10 pages do:10.5402/2012/539359 Research Artcle Green s Theorem for Sgn Data Lous M. Houston The Unversty of

More information

High resolution entropy stable scheme for shallow water equations

High resolution entropy stable scheme for shallow water equations Internatonal Symposum on Computers & Informatcs (ISCI 05) Hgh resoluton entropy stable scheme for shallow water equatons Xaohan Cheng,a, Yufeng Ne,b, Department of Appled Mathematcs, Northwestern Polytechncal

More information

NUMERICAL DIFFERENTIATION

NUMERICAL DIFFERENTIATION NUMERICAL DIFFERENTIATION 1 Introducton Dfferentaton s a method to compute the rate at whch a dependent output y changes wth respect to the change n the ndependent nput x. Ths rate of change s called the

More information

On the Multicriteria Integer Network Flow Problem

On the Multicriteria Integer Network Flow Problem BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 5, No 2 Sofa 2005 On the Multcrtera Integer Network Flow Problem Vassl Vasslev, Marana Nkolova, Maryana Vassleva Insttute of

More information

Fault Diagnosis of Autonomous Underwater Vehicles

Fault Diagnosis of Autonomous Underwater Vehicles Research Journal of Appled Scences, Engneerng and Technology 5(6): 407-4076, 03 SSN: 040-7459; e-ssn: 040-7467 Maxwell Scentfc Organzaton, 03 Submtted: March 3, 0 Accepted: January, 03 Publshed: Aprl 30,

More information

Wavelet chaotic neural networks and their application to continuous function optimization

Wavelet chaotic neural networks and their application to continuous function optimization Vol., No.3, 04-09 (009) do:0.436/ns.009.307 Natural Scence Wavelet chaotc neural networks and ther applcaton to contnuous functon optmzaton Ja-Ha Zhang, Yao-Qun Xu College of Electrcal and Automatc Engneerng,

More information

Comparison of the Population Variance Estimators. of 2-Parameter Exponential Distribution Based on. Multiple Criteria Decision Making Method

Comparison of the Population Variance Estimators. of 2-Parameter Exponential Distribution Based on. Multiple Criteria Decision Making Method Appled Mathematcal Scences, Vol. 7, 0, no. 47, 07-0 HIARI Ltd, www.m-hkar.com Comparson of the Populaton Varance Estmators of -Parameter Exponental Dstrbuton Based on Multple Crtera Decson Makng Method

More information

The Quadratic Trigonometric Bézier Curve with Single Shape Parameter

The Quadratic Trigonometric Bézier Curve with Single Shape Parameter J. Basc. Appl. Sc. Res., (3541-546, 01 01, TextRoad Publcaton ISSN 090-4304 Journal of Basc and Appled Scentfc Research www.textroad.com The Quadratc Trgonometrc Bézer Curve wth Sngle Shape Parameter Uzma

More information

Irregular vibrations in multi-mass discrete-continuous systems torsionally deformed

Irregular vibrations in multi-mass discrete-continuous systems torsionally deformed (2) 4 48 Irregular vbratons n mult-mass dscrete-contnuous systems torsonally deformed Abstract In the paper rregular vbratons of dscrete-contnuous systems consstng of an arbtrary number rgd bodes connected

More information

NON-CENTRAL 7-POINT FORMULA IN THE METHOD OF LINES FOR PARABOLIC AND BURGERS' EQUATIONS

NON-CENTRAL 7-POINT FORMULA IN THE METHOD OF LINES FOR PARABOLIC AND BURGERS' EQUATIONS IJRRAS 8 (3 September 011 www.arpapress.com/volumes/vol8issue3/ijrras_8_3_08.pdf NON-CENTRAL 7-POINT FORMULA IN THE METHOD OF LINES FOR PARABOLIC AND BURGERS' EQUATIONS H.O. Bakodah Dept. of Mathematc

More information

On the Interval Zoro Symmetric Single-step Procedure for Simultaneous Finding of Polynomial Zeros

On the Interval Zoro Symmetric Single-step Procedure for Simultaneous Finding of Polynomial Zeros Appled Mathematcal Scences, Vol. 5, 2011, no. 75, 3693-3706 On the Interval Zoro Symmetrc Sngle-step Procedure for Smultaneous Fndng of Polynomal Zeros S. F. M. Rusl, M. Mons, M. A. Hassan and W. J. Leong

More information

Linear Approximation with Regularization and Moving Least Squares

Linear Approximation with Regularization and Moving Least Squares Lnear Approxmaton wth Regularzaton and Movng Least Squares Igor Grešovn May 007 Revson 4.6 (Revson : March 004). 5 4 3 0.5 3 3.5 4 Contents: Lnear Fttng...4. Weghted Least Squares n Functon Approxmaton...

More information

Short Term Load Forecasting using an Artificial Neural Network

Short Term Load Forecasting using an Artificial Neural Network Short Term Load Forecastng usng an Artfcal Neural Network D. Kown 1, M. Km 1, C. Hong 1,, S. Cho 2 1 Department of Computer Scence, Sangmyung Unversty, Seoul, Korea 2 Department of Energy Grd, Sangmyung

More information

Control of Uncertain Bilinear Systems using Linear Controllers: Stability Region Estimation and Controller Design

Control of Uncertain Bilinear Systems using Linear Controllers: Stability Region Estimation and Controller Design Control of Uncertan Blnear Systems usng Lnear Controllers: Stablty Regon Estmaton Controller Desgn Shoudong Huang Department of Engneerng Australan Natonal Unversty Canberra, ACT 2, Australa shoudong.huang@anu.edu.au

More information

Using Immune Genetic Algorithm to Optimize BP Neural Network and Its Application Peng-fei LIU1,Qun-tai SHEN1 and Jun ZHI2,*

Using Immune Genetic Algorithm to Optimize BP Neural Network and Its Application Peng-fei LIU1,Qun-tai SHEN1 and Jun ZHI2,* Advances n Computer Scence Research (ACRS), volume 54 Internatonal Conference on Computer Networks and Communcaton Technology (CNCT206) Usng Immune Genetc Algorthm to Optmze BP Neural Network and Its Applcaton

More information

MODELING TRAFFIC LIGHTS IN INTERSECTION USING PETRI NETS

MODELING TRAFFIC LIGHTS IN INTERSECTION USING PETRI NETS The 3 rd Internatonal Conference on Mathematcs and Statstcs (ICoMS-3) Insttut Pertanan Bogor, Indonesa, 5-6 August 28 MODELING TRAFFIC LIGHTS IN INTERSECTION USING PETRI NETS 1 Deky Adzkya and 2 Subono

More information

A PROBABILITY-DRIVEN SEARCH ALGORITHM FOR SOLVING MULTI-OBJECTIVE OPTIMIZATION PROBLEMS

A PROBABILITY-DRIVEN SEARCH ALGORITHM FOR SOLVING MULTI-OBJECTIVE OPTIMIZATION PROBLEMS HCMC Unversty of Pedagogy Thong Nguyen Huu et al. A PROBABILITY-DRIVEN SEARCH ALGORITHM FOR SOLVING MULTI-OBJECTIVE OPTIMIZATION PROBLEMS Thong Nguyen Huu and Hao Tran Van Department of mathematcs-nformaton,

More information

Multilayer Perceptron (MLP)

Multilayer Perceptron (MLP) Multlayer Perceptron (MLP) Seungjn Cho Department of Computer Scence and Engneerng Pohang Unversty of Scence and Technology 77 Cheongam-ro, Nam-gu, Pohang 37673, Korea seungjn@postech.ac.kr 1 / 20 Outlne

More information

Semi-supervised Classification with Active Query Selection

Semi-supervised Classification with Active Query Selection Sem-supervsed Classfcaton wth Actve Query Selecton Jao Wang and Swe Luo School of Computer and Informaton Technology, Beng Jaotong Unversty, Beng 00044, Chna Wangjao088@63.com Abstract. Labeled samples

More information

Introduction to the Introduction to Artificial Neural Network

Introduction to the Introduction to Artificial Neural Network Introducton to the Introducton to Artfcal Neural Netork Vuong Le th Hao Tang s sldes Part of the content of the sldes are from the Internet (possbly th modfcatons). The lecturer does not clam any onershp

More information

Erratum: A Generalized Path Integral Control Approach to Reinforcement Learning

Erratum: A Generalized Path Integral Control Approach to Reinforcement Learning Journal of Machne Learnng Research 00-9 Submtted /0; Publshed 7/ Erratum: A Generalzed Path Integral Control Approach to Renforcement Learnng Evangelos ATheodorou Jonas Buchl Stefan Schaal Department of

More information

Interactive Bi-Level Multi-Objective Integer. Non-linear Programming Problem

Interactive Bi-Level Multi-Objective Integer. Non-linear Programming Problem Appled Mathematcal Scences Vol 5 0 no 65 3 33 Interactve B-Level Mult-Objectve Integer Non-lnear Programmng Problem O E Emam Department of Informaton Systems aculty of Computer Scence and nformaton Helwan

More information

Suppose that there s a measured wndow of data fff k () ; :::; ff k g of a sze w, measured dscretely wth varable dscretzaton step. It s convenent to pl

Suppose that there s a measured wndow of data fff k () ; :::; ff k g of a sze w, measured dscretely wth varable dscretzaton step. It s convenent to pl RECURSIVE SPLINE INTERPOLATION METHOD FOR REAL TIME ENGINE CONTROL APPLICATIONS A. Stotsky Volvo Car Corporaton Engne Desgn and Development Dept. 97542, HA1N, SE- 405 31 Gothenburg Sweden. Emal: astotsky@volvocars.com

More information

Research on Complex Networks Control Based on Fuzzy Integral Sliding Theory

Research on Complex Networks Control Based on Fuzzy Integral Sliding Theory Advanced Scence and Technoogy Letters Vo.83 (ISA 205), pp.60-65 http://dx.do.org/0.4257/ast.205.83.2 Research on Compex etworks Contro Based on Fuzzy Integra Sdng Theory Dongsheng Yang, Bngqng L, 2, He

More information

Inner Product. Euclidean Space. Orthonormal Basis. Orthogonal

Inner Product. Euclidean Space. Orthonormal Basis. Orthogonal Inner Product Defnton 1 () A Eucldean space s a fnte-dmensonal vector space over the reals R, wth an nner product,. Defnton 2 (Inner Product) An nner product, on a real vector space X s a symmetrc, blnear,

More information

Robust observed-state feedback design. for discrete-time systems rational in the uncertainties

Robust observed-state feedback design. for discrete-time systems rational in the uncertainties Robust observed-state feedback desgn for dscrete-tme systems ratonal n the uncertantes Dmtr Peaucelle Yosho Ebhara & Yohe Hosoe Semnar at Kolloquum Technsche Kybernetk, May 10, 016 Unversty of Stuttgart

More information

Speeding up Computation of Scalar Multiplication in Elliptic Curve Cryptosystem

Speeding up Computation of Scalar Multiplication in Elliptic Curve Cryptosystem H.K. Pathak et. al. / (IJCSE) Internatonal Journal on Computer Scence and Engneerng Speedng up Computaton of Scalar Multplcaton n Ellptc Curve Cryptosystem H. K. Pathak Manju Sangh S.o.S n Computer scence

More information

A New Evolutionary Computation Based Approach for Learning Bayesian Network

A New Evolutionary Computation Based Approach for Learning Bayesian Network Avalable onlne at www.scencedrect.com Proceda Engneerng 15 (2011) 4026 4030 Advanced n Control Engneerng and Informaton Scence A New Evolutonary Computaton Based Approach for Learnng Bayesan Network Yungang

More information

Convexity preserving interpolation by splines of arbitrary degree

Convexity preserving interpolation by splines of arbitrary degree Computer Scence Journal of Moldova, vol.18, no.1(52), 2010 Convexty preservng nterpolaton by splnes of arbtrary degree Igor Verlan Abstract In the present paper an algorthm of C 2 nterpolaton of dscrete

More information

Time-Varying Systems and Computations Lecture 6

Time-Varying Systems and Computations Lecture 6 Tme-Varyng Systems and Computatons Lecture 6 Klaus Depold 14. Januar 2014 The Kalman Flter The Kalman estmaton flter attempts to estmate the actual state of an unknown dscrete dynamcal system, gven nosy

More information

Chapter 5 Multilevel Models

Chapter 5 Multilevel Models Chapter 5 Multlevel Models 5.1 Cross-sectonal multlevel models 5.1.1 Two-level models 5.1.2 Multple level models 5.1.3 Multple level modelng n other felds 5.2 Longtudnal multlevel models 5.2.1 Two-level

More information

MMA and GCMMA two methods for nonlinear optimization

MMA and GCMMA two methods for nonlinear optimization MMA and GCMMA two methods for nonlnear optmzaton Krster Svanberg Optmzaton and Systems Theory, KTH, Stockholm, Sweden. krlle@math.kth.se Ths note descrbes the algorthms used n the author s 2007 mplementatons

More information

Improved delay-dependent stability criteria for discrete-time stochastic neural networks with time-varying delays

Improved delay-dependent stability criteria for discrete-time stochastic neural networks with time-varying delays Avalable onlne at www.scencedrect.com Proceda Engneerng 5 ( 4456 446 Improved delay-dependent stablty crtera for dscrete-tme stochastc neural networs wth tme-varyng delays Meng-zhuo Luo a Shou-mng Zhong

More information

Stability and Stabilization for Discrete Systems with Time-varying Delays Based on the Average Dwell-time Method

Stability and Stabilization for Discrete Systems with Time-varying Delays Based on the Average Dwell-time Method Proceedngs of the 29 IEEE Internatonal Conference on Systems, an, and Cybernetcs San Antono, TX, USA - October 29 Stablty and Stablzaton for Dscrete Systems wth Tme-varyng Delays Based on the Average Dwell-tme

More information

Lecture Notes on Linear Regression

Lecture Notes on Linear Regression Lecture Notes on Lnear Regresson Feng L fl@sdueducn Shandong Unversty, Chna Lnear Regresson Problem In regresson problem, we am at predct a contnuous target value gven an nput feature vector We assume

More information

ON A DETERMINATION OF THE INITIAL FUNCTIONS FROM THE OBSERVED VALUES OF THE BOUNDARY FUNCTIONS FOR THE SECOND-ORDER HYPERBOLIC EQUATION

ON A DETERMINATION OF THE INITIAL FUNCTIONS FROM THE OBSERVED VALUES OF THE BOUNDARY FUNCTIONS FOR THE SECOND-ORDER HYPERBOLIC EQUATION Advanced Mathematcal Models & Applcatons Vol.3, No.3, 2018, pp.215-222 ON A DETERMINATION OF THE INITIAL FUNCTIONS FROM THE OBSERVED VALUES OF THE BOUNDARY FUNCTIONS FOR THE SECOND-ORDER HYPERBOLIC EUATION

More information

Neuro-Adaptive Design II:

Neuro-Adaptive Design II: Lecture 37 Neuro-Adaptve Desgn II: A Robustfyng Tool for Any Desgn Dr. Radhakant Padh Asst. Professor Dept. of Aerospace Engneerng Indan Insttute of Scence - Bangalore Motvaton Perfect system modelng s

More information

Finite Element Modelling of truss/cable structures

Finite Element Modelling of truss/cable structures Pet Schreurs Endhoven Unversty of echnology Department of Mechancal Engneerng Materals echnology November 3, 214 Fnte Element Modellng of truss/cable structures 1 Fnte Element Analyss of prestressed structures

More information

ADVANCED MACHINE LEARNING ADVANCED MACHINE LEARNING

ADVANCED MACHINE LEARNING ADVANCED MACHINE LEARNING 1 ADVANCED ACHINE LEARNING ADVANCED ACHINE LEARNING Non-lnear regresson technques 2 ADVANCED ACHINE LEARNING Regresson: Prncple N ap N-dm. nput x to a contnuous output y. Learn a functon of the type: N

More information

Errors for Linear Systems

Errors for Linear Systems Errors for Lnear Systems When we solve a lnear system Ax b we often do not know A and b exactly, but have only approxmatons  and ˆb avalable. Then the best thng we can do s to solve ˆx ˆb exactly whch

More information