Estimation of the wrist torque of robot gripper using data fusion and ANN techniques

Size: px
Start display at page:

Download "Estimation of the wrist torque of robot gripper using data fusion and ANN techniques"

Transcription

1 Estimation of the wrist torque of robot gripper using data fusion and ANN techniques Wu Ting 1 Tang Xue-hua 1 Li Zhu 1 School of Mechanical Engineering Shanghai Dianji Universit Shanghai 0040 China School of Mechanical Science & Engineering Huazhong Universit of Science & Technolog Wuhan China Tel.: + 86 [1] wut@sdju.edu.cn Abstract This paper proposes a ind of measurement method of wrist force/torque for robotic multi-sensor gripper. The method adopts the data fusion technique according to the output variations of the finger force sensors installed in the gripper. The finger force sensors are used to measure the clamping force of the gripper in the design. When the accurac of measurement is not required exactl and there is the limitation of weight and volume in space robots we utilize the existing devices to estimate the wrist force/torque without the wrist force/torque sensor which not onl meets the practical requirement but also decreases the weight and cost of robots. An experimental bench is developed and the calibration experiments are conducted to detect the relationship between the wrist force/torque and finger forces. The experimental data are used to train three laers of radial basis function (RBF artificial neural networ and the structure and weight values of the networ are obtained. Comparing with BP networ and single RBF networ based on the same samples this method can reduce the training time greatl and increase the estimation accurac significantl. The results of data fusion of the wrist force/torque are consistent with the practical calibration values and the effectiveness of the wrist force/torque estimating technique is proved. Kewords: Robot gripper wrist force neural networ data fusion 1. Introduction In the space robots often assist or replace the astronaut to do some tass out of the spaceship such as checing the space station grasping and operating the wor-pieces and catching the floating objects etc. When robot taes these operations the wrist of its gripper will receive force. If the force exceeds its limitation the flange at the root of gripper will be fractured even the robot probabl separates itself from the experimental platform and becomes the space rubbish [1~] this situation is ver dangerous. Therefore to ensure the safet of operation of robots it is necessar to monitor the wrist force/torque for robot gripper. In theor the wrist/torque sensor can measure the force precisel. However for the specialt of space robot the wrist force sensor sometimes can not be equipped on it because of the limitations of its weight and dimension. Can other sensors on the gripper be utilized to measure the wrist force/torque of space robot? We found that the output variations of finger force sensors can reflect the value of the wrist force/torque although their relationship is ver complex and difficult to be described using a mathematical model based on analtical methods. Therefore this paper presents a novel method that utilize artificial neural networ which possesses the good propert of approximating an functions to describe the relationship.. Multi-sensor gripper A multi-sensor gripper is shown in Fig. 1 which is developed b Hefei Institute of Intelligent Machines Chinese Academ of Sciences [4]. It consists of a gripper mechanism and a sensing sstem. The gripper mechanism is a one-dimensional actuating mechanism and the operations of open and close are controlled b a motor. A gripper has two fingers. The left finger has five clamping faces s1 s s s4 and s5 and the right finger also has five clamping faces s6 s7 s8 s9 and s10. The s1 s s s4 s6 s7 s8 and s9 form one V-shaped groove to grasp the I-shaped beam or objects. The s5 and s10 form another V-shaped groove to grasp the small objects. Eight finger force sensors can measure the force in the vertical direction along the clamping face. The outputs of eight finger force sensors show the contacting force between the gripper and objects.. Experiment of calibration Before we determine the structure of an artificial neural networ (ANN it needs a number of samples for training. So we developed an experimental platform and had the experiment of calibration. The experimental equipment consists of a robot s gripper of EMR (the extravehicular mobile robot which is developed b Institute of Intelligent Machines Chinese Academ of Sciences a flange of gripper a square experimental bench made of iron several weights a personal computer (PC and a data reception and control sstem and so on. 4-06

2 Fig. 1. Structure of gripper. Fig.. Calibration diagram of Fx (a Vertical view (b Front view. We simulate the circumstance that the space robot wals on the ground and grasps wor-piece the motor-driven maes the gripper with four fingers firml grasp the I-shaped beam which is shown in Fig.. We can acquire the outputs of eight finger force sensors when the gripper is connected safel. The outputs at this moment are recorded as the initial value. Then the flange of the gripper is exerted the forces and torques through hanging the weights on the plate at the directions of Fx F-x F F- Fz Mx M-x M M- Mz and M-z and the weights are hanged in proper order such as 0g 5.5g 10.5g 15.5g then uninstall the weights in the invert order such as 15.5g 10.5g 5.5g 0g and record the outputs of the finger force sensors at ever time. In this wa a calibration ccle in one direction is completed there are four ccles made in ever directions. So we receive a number of calibration data through dealing with it b ANN we can determine the wrist force/torque of gripper when waling on the ground or operating worpiece and provide basis for controlling the whole space robot. 4. Data fusion In this paper a method for decreasing the spatial component of the measurement error of the triangulation scheme has been described. The method is based on polarization filtration of the radiation scattered from the surface. The experimental investigations performed have given an increase in the accurac of measurements b a factor of more than two. We ever utilized the classic ANN for example BP RBF to fuse the wrist force/torque according to the output of finger force sensors [5] but it can not satisf the precision well. Therefore we design a RBF_RBF_RBF i.e. R neural networ to do the data fusion. 4.1 R neural networ R neural networ consists of laers RBF. The output of the first laer RBF is regarded as the input of the second laer RBF the output of the second laer RBF is regarded as the input of the third laer RBF the final result is the output of the third laer RBF. The structure of three RBF is same but the spread constants (SP of radial basis functions are different. There are 8 input nodes (8 outputs of the finger force sensor and 6 output nodes (the wrist force and torque in directions. The whole structure and diagram of R neural networ is shown in Fig.. Fig.. Architecture of R networ. (1 The first laer RBF The input vector P1 i.e. the input vector Pr of the whole networ has R1 elements i.e. R1 nodes that express the outputs of eight finger force sensors. An input weight matrix W1 is made of S11 rows and R1 columns [6]. dist is Euclidean distance between P1 and W11 in response the distance of the nth radial basis function is given b 4-07

3 dist ( n ( W11( n P A basis vector b11 having S1 elements and the lg b11( n SP ( n 1 The input vector n11 is the basis vector b11 multipling b dist element-b-element dist b n The output of the first laer the networ can be obtained with following formulation a exp( ( n exp( ( dist b 1 11 The vector in the linear laer is given b n W a (5 W is the weight matrix of the linear laer(w=s1 S; b1 is the basis vector of the linear laer and has S1 elements. The output of the first laer RBF networ is a b1 1 n 1 ( The second laer RBF The input of this laer is the output of the first one i.e. P1 a1 n1 Similarl it has the following expressions dist ( n ( W1( n P 1 lg b1( n SP ( n n1 dist b 1 a1 exp( ( n1 exp( ( dist b n W a1 b The output of the second laer RBF networ is a n 1 (1 ( ( (4 (6 (7 (8 (9 (10 (11 (1 ( The third laer RBF The input of this laer is the output of the second i.e. P a Similarl it also has the following expressions dist ( n ( W1( n P 1 lg b1( n SP ( n n1 dist b1 a1 exp( ( n1 exp( ( dist b n W a1 b The output of the third laer RBF networ is 1 (1 (14 (15 (16 (17 (

4 a n The output of whole networ is a (0 The training progress includes three steps: the first step is to establish and train the first laer RBF then record the architecture the second step is to establish and train the second laer RBF based on the first laer then record the architecture the third step is to establish and train the third laer RBF based on the two laers before then record the architecture. When the result satisfies with requirement or the number of nerve cell reaches the limitation training will be stopped. Ever RBF networ has 6 output nodes and the function of the two bac laers is revising output error and stabilizing the performance of networ. Comparing with monolaer RBF networ multi-laer RBF networ improves the reliabilit and stabilit obviousl. 4. Procedure of data fusion The output of eight finger sensors at the initial unloaded condition is considered as the basis values (at this time the finger sensors have outputs but the wrist has not been received force. Others outputs minus the basis values. In this wa the output variations of finger force sensors are obtained i.e. the input of the whole networ the wrist force/torque of different directions are as the output nodes. According to following two equations (1~ the input data of R networ is normalized to [-11] the output data is normalized to [0.10.9]. ( pr pr pr ih Where pr prih ih i max pr i min i min 1 h 1... H i 1... is the hth sample of the ith input node before normalization pr i max R p i min pr ih (19 (1 is the value after normalization is the max. of the ith input node and is the min. H is the total number of samples. 0.8( jmin 0.1 jmax jmin h 1...H j 1...S ( Where is the hth sample of the jth output node before normalization is the output after j max normalization is the max. of the jth output node and is the min. of the jth output node. The samples are divided into two groups. One group (A is used for training the networ the other group (B is used for testing the accurac of the data fusion. A+B=H. During the progress of training adjust the parameters continuousl especiall the spread constant of radial basis function is ver important and have a significant effect on the training result. After we get the architecture of R networ the samples of B group are sent into R networ and calculated the result of fusion. In order to compare it with the output of the samples it needs to be renormalized according to equation ( ( 0.1( j max 0.8 j min j min j min l 1...Q j 1... S is the lth ouput of jth node before renormalization is the one after renormalization. The error between the result of fusion and calibration value is calculated according equation (4 Max E jfs 100% l 1...Q j 1... S where is the ith calibration value of jth ouput node is its ith fusion result is the full scale range of the jth output node. 4. Result of fusion When calculating error different output nodes have different full measurement scale. Respectivel the scale of Fx F Fz Mx M Mz is 0.8N 0.8N 151.9N 1.67N.m 1.67N.m 15.19N.m. the jfs ( (4 4-09

5 max error in Table 1 is the max fusion error of calibration data in the same group. The motor of gripper is driven b voltage of 18V DC. Accordingl Table 1 is the result and error of fusion. Table 1. Results of fusion. result of fusion (wrist force/torque of 6 dimention Fx(N F(N Fz(N Mx(N.M M(N.M Mz(N.M max error % % % % % % % % % % % % % 5. Conclusion (1 Dealing with different problems we should use different tpes of NN. The wrist force/torque is related with its temporal station so we should select the front NN. Although the training need a long time as far as measuring the wrist force/torque to be concerned if we onl need to now the architecture of networ so we can training networ offline and fusing data online. It has no effect on calculation in real time. ( We ever adopt BP networ to solve the problem. But it indicates that the training progress taes a long time and the precise is not ver good. Because BP algorithm is characterized b grad dropping and global approximation sometimes it probabl gets into local least. However RBF networ is local approximation. It has the capabilit of fast learning and can reduce sensitivit to the order of presentation of training data. ( Although RBF networ has solved the problem of training time but the precise of fusion is not quite ideal [7]. Then we use R networ. Actuall it is combined b RBF organicall. It not onl possesses the virtues of RBF networ but also can improve the capabilit of approximation because of increasing laers of nerve cell. Most importantl the precise of fusion comparing with BP and RBF has been improved significantl. Using the same experiment data the max error of BP is % RBF is % but s % the precise exceeds far from the other two networs. (4 The spread constant (SP is one of the most important parameters in the radial basis function (RBF networ. We need adjust its value constantl so that the fusion results reach the best accurac. However the rule of adjustment is not exist it need to rectif SP based on practical experience. Usuall we select SP from 0.1~ Acnowledgements Authors would lie to than Dr. Chen Yu-wang for valuable contribution and helpful proof-reading. References 1. G. Hirzinger B. Brunner J. Dietrich and J. Heindl. Sensor-Based Space Robotics--ROTEX and It s Telerobotic features. IEEE Transactions on Robotics and Automation. 199 vol. 9 No. 5 pp K. Machida Y. Toda Y. Murase and S. Komada. Precise space telerobotic sstem using -finger multisensor hand. Proc. of the 1995 IEEE International Conference on Robotics and Automation. Part 1 (of Nagoa Japan pp K. Machida T. Mimi S. Komada. Precise EV Robot: Flight Model and telerobotic operation for ETS- VII. Proc. of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Sstems. Osaa Japan. Part (of pp D.M. Perr. Multi-axis force and torque sensing. Sensor Review vol. 17 No. pp L.-P. Chao K.-T. Chen. Shape optimal design and force sensitivit evaluation of six-axis force sensors. Sensors and Actuators A vol. 6 pp C.-F. Xie. Development of a Multi-sensor Gripper Sstem for an Extravehicular Mobile Robot. Master thesis. Hefei Institute of Intelligent Machines Chinese Academ Sciences China Q.-Li Li K.-J. Xu. Multi-sensors data Fusion based Measurement of Wrist Force for Robots. Chinese Journal of Scientific Instrument

An Accurate Incremental Principal Component Analysis method with capacity of update and downdate

An Accurate Incremental Principal Component Analysis method with capacity of update and downdate 0 International Conference on Computer Science and Information echnolog (ICCSI 0) IPCSI vol. 5 (0) (0) IACSI Press, Singapore DOI: 0.7763/IPCSI.0.V5. An Accurate Incremental Principal Component Analsis

More information

2015 AASRI International Conference on Industrial Electronics and Applications (IEA 2015) Study on Optimization for Grey Forecasting Model.

2015 AASRI International Conference on Industrial Electronics and Applications (IEA 2015) Study on Optimization for Grey Forecasting Model. 05 AASRI International Conference on Industrial Electronics and Applications (IEA 05 Stud on Optimiation for Gre Forecasting Model Ying Li Min-an Tang Tao Liu Min-an Tang School of Automation and Electrical

More information

Speaker Recognition Using Artificial Neural Networks: RBFNNs vs. EBFNNs

Speaker Recognition Using Artificial Neural Networks: RBFNNs vs. EBFNNs Speaer Recognition Using Artificial Neural Networs: s vs. s BALASKA Nawel ember of the Sstems & Control Research Group within the LRES Lab., Universit 20 Août 55 of Sida, BP: 26, Sida, 21000, Algeria E-mail

More information

CONTROL OF ROBOT CAMERA SYSTEM WITH ACTUATOR S DYNAMICS TO TRACK MOVING OBJECT

CONTROL OF ROBOT CAMERA SYSTEM WITH ACTUATOR S DYNAMICS TO TRACK MOVING OBJECT Journal of Computer Science and Cybernetics, V.31, N.3 (2015), 255 265 DOI: 10.15625/1813-9663/31/3/6127 CONTROL OF ROBOT CAMERA SYSTEM WITH ACTUATOR S DYNAMICS TO TRACK MOVING OBJECT NGUYEN TIEN KIEM

More information

APPLICATION OF RADIAL BASIS FUNCTION NEURAL NETWORK, TO ESTIMATE THE STATE OF HEALTH FOR LFP BATTERY

APPLICATION OF RADIAL BASIS FUNCTION NEURAL NETWORK, TO ESTIMATE THE STATE OF HEALTH FOR LFP BATTERY International Journal of Electrical and Electronics Engineering (IJEEE) ISSN(P): 2278-9944; ISSN(E): 2278-9952 Vol. 7, Issue 1, Dec - Jan 2018, 1-6 IASET APPLICATION OF RADIAL BASIS FUNCTION NEURAL NETWORK,

More information

RESEARCH ON PIEZOELECTRIC QUARTZ UNDER MULTIDIMENSIONAL FORCES

RESEARCH ON PIEZOELECTRIC QUARTZ UNDER MULTIDIMENSIONAL FORCES aterials Phsics and echanics (015) 94-100 eceived: October 31, 014 ESEACH ON PIEZOELECTIC QUATZ UNDE ULTIDIENSIONAL OCES ei Wang *, uji Wang, Zongjin en, Zhenuan Jia, Liqi Zhao, Dong Li Ke Laborator for

More information

LATERAL BUCKLING ANALYSIS OF ANGLED FRAMES WITH THIN-WALLED I-BEAMS

LATERAL BUCKLING ANALYSIS OF ANGLED FRAMES WITH THIN-WALLED I-BEAMS Journal of arine Science and J.-D. Technolog, Yau: ateral Vol. Buckling 17, No. Analsis 1, pp. 9-33 of Angled (009) Frames with Thin-Walled I-Beams 9 ATERA BUCKING ANAYSIS OF ANGED FRAES WITH THIN-WAED

More information

Vibration of Plate on Foundation with Four Edges Free by Finite Cosine Integral Transform Method

Vibration of Plate on Foundation with Four Edges Free by Finite Cosine Integral Transform Method 854 Vibration of Plate on Foundation with Four Edges Free b Finite Cosine Integral Transform Method Abstract The analtical solutions for the natural frequencies and mode shapes of the rectangular plate

More information

SHADOW AND BACKGROUND ORIENTED SCHLIEREN INVESTIGATION OF SHOCK WAVES IN GAS-DISCHARGE MEDIUM

SHADOW AND BACKGROUND ORIENTED SCHLIEREN INVESTIGATION OF SHOCK WAVES IN GAS-DISCHARGE MEDIUM SHADOW AND BACKGROUND ORIENTED SCHLIEREN INVESTIGATION OF SHOCK WAVES IN GAS-DISCHARGE MEDIUM J. JIN 1, I.V. MURSENKOVA 1,c, N. N. SYSOEV 1 and I.A. ZNAMENSKAYA 1 1 Department of Phsics, Lomonosov Moscow

More information

Acceleration of Levenberg-Marquardt method training of chaotic systems fuzzy modeling

Acceleration of Levenberg-Marquardt method training of chaotic systems fuzzy modeling ISSN 746-7233, England, UK World Journal of Modelling and Simulation Vol. 3 (2007) No. 4, pp. 289-298 Acceleration of Levenberg-Marquardt method training of chaotic systems fuzzy modeling Yuhui Wang, Qingxian

More information

Research Article Chaotic Attractor Generation via a Simple Linear Time-Varying System

Research Article Chaotic Attractor Generation via a Simple Linear Time-Varying System Discrete Dnamics in Nature and Societ Volume, Article ID 836, 8 pages doi:.//836 Research Article Chaotic Attractor Generation via a Simple Linear Time-Varing Sstem Baiu Ou and Desheng Liu Department of

More information

COMPARISON STUDY OF SENSITIVITY DEFINITIONS OF NEURAL NETWORKS

COMPARISON STUDY OF SENSITIVITY DEFINITIONS OF NEURAL NETWORKS COMPARISON SUDY OF SENSIIVIY DEFINIIONS OF NEURAL NEORKS CHUN-GUO LI 1, HAI-FENG LI 1 Machine Learning Center, Facult of Mathematics and Computer Science, Hebei Universit, Baoding 07100, China Department

More information

2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media,

2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in an current or future media, including reprinting/republishing this material for advertising

More information

Experimental Calibration and Head Loss Prediction of Tuned Liquid Column Damper

Experimental Calibration and Head Loss Prediction of Tuned Liquid Column Damper Tamkang Journal of Science and Engineering, Vol. 8, No 4, pp. 319-35 (005) 319 Experimental Calibration and Head Loss Prediction of Tuned Liquid Column Damper Jong-Cheng Wu Department of Civil Engineering,

More information

The approximation of piecewise linear membership functions and Łukasiewicz operators

The approximation of piecewise linear membership functions and Łukasiewicz operators Fuzz Sets and Sstems 54 25 275 286 www.elsevier.com/locate/fss The approimation of piecewise linear membership functions and Łukasiewicz operators József Dombi, Zsolt Gera Universit of Szeged, Institute

More information

On the design of Incremental ΣΔ Converters

On the design of Incremental ΣΔ Converters M. Belloni, C. Della Fiore, F. Maloberti, M. Garcia Andrade: "On the design of Incremental ΣΔ Converters"; IEEE Northeast Workshop on Circuits and Sstems, NEWCAS 27, Montreal, 5-8 August 27, pp. 376-379.

More information

A FUZZY NEURAL NETWORK MODEL FOR FORECASTING STOCK PRICE

A FUZZY NEURAL NETWORK MODEL FOR FORECASTING STOCK PRICE A FUZZY NEURAL NETWORK MODEL FOR FORECASTING STOCK PRICE Li Sheng Institute of intelligent information engineering Zheiang University Hangzhou, 3007, P. R. China ABSTRACT In this paper, a neural network-driven

More information

Effect of Bi-axial Residual Stresses on the Micro-Indentation Behaviour of Bulk Materials

Effect of Bi-axial Residual Stresses on the Micro-Indentation Behaviour of Bulk Materials Effect of Bi-axial Residual Stresses on the Micro-Indentation Behaviour of Bulk Materials Prakash Jadhav Department of Mechanical Engineering CMR Institute of Technolog, Bangalore, India Prakash.k@cmrit.ac.in

More information

FABRICATION, TESTING AND CALIBRATION OF TWO DIRECTIONAL FORCE SENSOR

FABRICATION, TESTING AND CALIBRATION OF TWO DIRECTIONAL FORCE SENSOR FABRICATION, TESTING AND CALIBRATION OF TWO DIRECTIONAL FORCE SENSOR Kuruva Veerakantha 1, G.Kirankumar 2 1 Assistant Professor, Mechanical Engineering, NNRG, Telangana, India 2 Assistant Professor, Mechanical

More information

The Design of Fuzzy Adaptive PID Controller of Two-Wheeled Self-Balancing Robot

The Design of Fuzzy Adaptive PID Controller of Two-Wheeled Self-Balancing Robot The esign of Fuzz Adaptive PI Controller of Two-Wheeled Self-Balancing Robot Conging Qiu and Yibin Huang Abstract A two-wheeled self-balancing robot sstem is developed and the hardware sstem mainl consists

More information

A novel six-axis force sensor for measuring the loading of the racing tyre on track

A novel six-axis force sensor for measuring the loading of the racing tyre on track bstract novel si-ais force sensor for measuring the loading of the racing tre on track Wei Shi, Stephen D Hall School of echanical and anufacturing Engineering The Universit of New South Wales, Sdne, ustralia

More information

Mechanical Spring Reliability Assessments Based on FEA Generated Fatigue Stresses and Monte Carlo Simulated Stress/Strength Distributions

Mechanical Spring Reliability Assessments Based on FEA Generated Fatigue Stresses and Monte Carlo Simulated Stress/Strength Distributions Purdue Universit Purdue e-pubs International Compressor Engineering Conference School of Mechanical Engineering 4 Mechanical Spring Reliabilit Assessments Based on FEA Generated Fatigue Stresses and Monte

More information

Parameterized Joint Densities with Gaussian and Gaussian Mixture Marginals

Parameterized Joint Densities with Gaussian and Gaussian Mixture Marginals Parameterized Joint Densities with Gaussian and Gaussian Miture Marginals Feli Sawo, Dietrich Brunn, and Uwe D. Hanebeck Intelligent Sensor-Actuator-Sstems Laborator Institute of Computer Science and Engineering

More information

Study on Nonlinear Vibration and Crack Fault of Rotor-bearing-seal Coupling System

Study on Nonlinear Vibration and Crack Fault of Rotor-bearing-seal Coupling System Sensors & Transducers 04 b IFSA Publishing S. L. http://www.sensorsportal.com Stud on Nonlinear Vibration and Crack Fault of Rotor-bearing-seal Coupling Sstem Yuegang LUO Songhe ZHANG Bin WU Wanlei WANG

More information

Overview. IAML: Linear Regression. Examples of regression problems. The Regression Problem

Overview. IAML: Linear Regression. Examples of regression problems. The Regression Problem 3 / 38 Overview 4 / 38 IAML: Linear Regression Nigel Goddard School of Informatics Semester The linear model Fitting the linear model to data Probabilistic interpretation of the error function Eamples

More information

ESMF Based Multiple UAVs Active Cooperative Observation Method in Relative Velocity Coordinates

ESMF Based Multiple UAVs Active Cooperative Observation Method in Relative Velocity Coordinates Joint 48th IEEE Conference on Decision and Control and 8th Chinese Control Conference Shanghai, P.R. China, December 6-8, 009 WeCIn5.4 ESMF Based Multiple UAVs Active Cooperative Observation Method in

More information

Multilayer Neural Networks

Multilayer Neural Networks Pattern Recognition Multilaer Neural Networs Lecture 4 Prof. Daniel Yeung School of Computer Science and Engineering South China Universit of Technolog Outline Introduction (6.) Artificial Neural Networ

More information

An Novel Continuation Power Flow Method Based on Line Voltage Stability Index

An Novel Continuation Power Flow Method Based on Line Voltage Stability Index IOP Conference Series: Earth and Environmental Science PAPER OPEN ACCESS An Novel Continuation Power Flow Method Based on Line Voltage Stability Index To cite this article: Jianfang Zhou et al 2018 IOP

More information

Iran University of Science and Technology, Tehran 16844, IRAN

Iran University of Science and Technology, Tehran 16844, IRAN DECENTRALIZED DECOUPLED SLIDING-MODE CONTROL FOR TWO- DIMENSIONAL INVERTED PENDULUM USING NEURO-FUZZY MODELING Mohammad Farrokhi and Ali Ghanbarie Iran Universit of Science and Technolog, Tehran 6844,

More information

Assessing Slope Stability of Open Pit Mines using PCA and Fisher Discriminant Analysis

Assessing Slope Stability of Open Pit Mines using PCA and Fisher Discriminant Analysis Assessing Sloe Stabilit of Oen Pit Mines using PCA and Fisher Discriminant Analsis Shiao Xiang College of Geoscience and Surveing Engineering, China Universit of Mining and echnolog (Beijing), Beijing

More information

Selection of the Appropriate Lag Structure of Foreign Exchange Rates Forecasting Based on Autocorrelation Coefficient

Selection of the Appropriate Lag Structure of Foreign Exchange Rates Forecasting Based on Autocorrelation Coefficient Selection of the Appropriate Lag Structure of Foreign Exchange Rates Forecasting Based on Autocorrelation Coefficient Wei Huang 1,2, Shouyang Wang 2, Hui Zhang 3,4, and Renbin Xiao 1 1 School of Management,

More information

VIBRATION TRANSFER PATH ANALYSIS BASED ON PSEUDO FORCE

VIBRATION TRANSFER PATH ANALYSIS BASED ON PSEUDO FORCE VIBRATION TRANSFER PATH ANALYSIS BASED ON PSEUDO FORCE Yan Weiguang, Wuhan University of Technology, School of Mechanical and Electrical Engineering, Wuhan, China Pan Yunping Wuhan University of Technology,

More information

792. Experimental studies of stabilization of boring cutter form building top oscillation

792. Experimental studies of stabilization of boring cutter form building top oscillation 792. Experimental studies of stabilization of boring cutter form building top oscillation M. R. Sikhimbaev 1, K. Т. Sherov 2, О. М. Zharkevich 3, А. K. Sherov 4, Yu. О. Тkachova 5 Karaganda State Technical

More information

Decision tables and decision spaces

Decision tables and decision spaces Abstract Decision tables and decision spaces Z. Pawlak 1 Abstract. In this paper an Euclidean space, called a decision space is associated with ever decision table. This can be viewed as a generalization

More information

Modeling and Compensation for Capacitive Pressure Sensor by RBF Neural Networks

Modeling and Compensation for Capacitive Pressure Sensor by RBF Neural Networks 21 8th IEEE International Conference on Control and Automation Xiamen, China, June 9-11, 21 ThCP1.8 Modeling and Compensation for Capacitive Pressure Sensor by RBF Neural Networks Mahnaz Hashemi, Jafar

More information

QUICK AND PRECISE POSITION CONTROL OF ULTRASONIC MOTORS USING ADAPTIVE CONTROLLER WITH DEAD ZONE COMPENSATION

QUICK AND PRECISE POSITION CONTROL OF ULTRASONIC MOTORS USING ADAPTIVE CONTROLLER WITH DEAD ZONE COMPENSATION Journal of ELECTRICAL ENGINEERING, VOL. 53, NO. 7-8, 22, 197 21 QUICK AND PRECISE POSITION CONTROL OF ULTRASONIC MOTORS USING ADAPTIVE CONTROLLER WITH DEAD ZONE COMPENSATION Li Huafeng Gu Chenglin A position

More information

Myoelectrical signal classification based on S transform and two-directional 2DPCA

Myoelectrical signal classification based on S transform and two-directional 2DPCA Myoelectrical signal classification based on S transform and two-directional 2DPCA Hong-Bo Xie1 * and Hui Liu2 1 ARC Centre of Excellence for Mathematical and Statistical Frontiers Queensland University

More information

Hover Control for Helicopter Using Neural Network-Based Model Reference Adaptive Controller

Hover Control for Helicopter Using Neural Network-Based Model Reference Adaptive Controller Vol.13 No.1, 217 مجلد 13 العدد 217 1 Hover Control for Helicopter Using Neural Network-Based Model Reference Adaptive Controller Abdul-Basset A. Al-Hussein Electrical Engineering Department Basrah University

More information

Research on the Influence of Open Community on Road Traffic

Research on the Influence of Open Community on Road Traffic Research on the Influence of Open Communit on Road raffic Yiwen Wu a Wei Xiang b Xiaofei Wen 2* College of Electric and Information Engineering Southwest Universit for Nationalities Chengdu 6004 China

More information

NUMERIC SIMULATION OF ULTRA-HIGH PRESSURE ROTARY ATOMIZING WATERJET FLOW FIELD

NUMERIC SIMULATION OF ULTRA-HIGH PRESSURE ROTARY ATOMIZING WATERJET FLOW FIELD 2005 WJTA American Waterjet Conference August 21-23, 2005 Houston, Texas Paper 6A-4 NUMERIC SIMULATION OF ULTRA-HIGH PRESSURE ROTARY ATOMIZING WATERJET FLOW FIELD Xue Shengxiong, Li Jiangyun *, Peng Haojun,

More information

MODELING AND EXPERIMENTAL STUDY ON DRILLING RIG ANTI-JAMMING VALVE WITH BP NEURAL NETWORK

MODELING AND EXPERIMENTAL STUDY ON DRILLING RIG ANTI-JAMMING VALVE WITH BP NEURAL NETWORK Engineering Review, Vol. 3, Issue 2, 99-0, 20. 99 MODELING AND EXPERIMENTAL STUDY ON DRILLING RIG ANTI-JAMMING VALVE WITH BP NEURAL NETWORK Wei Ma * Fei Ma School of Mechanical Engineering, University

More information

Journal of Engineering Science and Technology Review 6 (2) (2013) Research Article. Received 25 June 2012; Accepted 15 January 2013

Journal of Engineering Science and Technology Review 6 (2) (2013) Research Article. Received 25 June 2012; Accepted 15 January 2013 Jestr Journal of Engineering Science and Technology Review 6 () (3) 5-54 Research Article JOURNAL OF Engineering Science and Technology Review www.jestr.org Fault Diagnosis and Classification in Urban

More information

Characterization of the Skew-Normal Distribution Via Order Statistics and Record Values

Characterization of the Skew-Normal Distribution Via Order Statistics and Record Values International Journal of Statistics and Probabilit; Vol. 4, No. 1; 2015 ISSN 1927-7032 E-ISSN 1927-7040 Published b Canadian Center of Science and Education Characterization of the Sew-Normal Distribution

More information

Online Identification And Control of A PV-Supplied DC Motor Using Universal Learning Networks

Online Identification And Control of A PV-Supplied DC Motor Using Universal Learning Networks Online Identification And Control of A PV-Supplied DC Motor Using Universal Learning Networks Ahmed Hussein * Kotaro Hirasawa ** Jinglu Hu ** * Graduate School of Information Science & Electrical Eng.,

More information

Study of Fault Diagnosis Method Based on Data Fusion Technology

Study of Fault Diagnosis Method Based on Data Fusion Technology Available online at www.sciencedirect.com Procedia Engineering 29 (2012) 2590 2594 2012 International Workshop on Information and Electronics Engineering (IWIEE) Study of Fault Diagnosis Method Based on

More information

Design and performance of Hall probe measurement system in CSNS

Design and performance of Hall probe measurement system in CSNS Radiat Detect Technol Methods (2017) 1:18 https://doi.org/10.1007/s41605-017-0017-z ORIGINAL PAPER Design and performance of Hall probe measurement system in CSNS Xi Wu 1,2 Wen Kang 1,2 Wan Chen 1,2 Chang-dong

More information

A HAND-HELD SENSOR FOR LOCAL MEASUREMENT OF MAGNETIC FIELD, INDUCTION AND ENERGY LOSSES

A HAND-HELD SENSOR FOR LOCAL MEASUREMENT OF MAGNETIC FIELD, INDUCTION AND ENERGY LOSSES A HAND-HELD SENSOR FOR LOCAL MEASUREMENT OF MAGNETIC FIELD, INDUCTION AND ENERGY LOSSES G. Krismanic, N. Baumgartinger and H. Pfützner Institute of Fundamentals and Theor of Electrical Engineering Bioelectricit

More information

Research of Dynamic Parameter Identification of LuGre Model Based on Weights Boundary Neural Network

Research of Dynamic Parameter Identification of LuGre Model Based on Weights Boundary Neural Network International Conference on Computer and Automation Engineering (ICCAE ) IPCSIT vol. 44 () () IACSIT Press, Singapore DOI:.7763/IPCSIT..V44.9 Research of Dynamic Parameter Identification of LuGre Model

More information

Two Levels Data Fusion Filtering Algorithms of Multimode Compound Seeker

Two Levels Data Fusion Filtering Algorithms of Multimode Compound Seeker TELKOMNKA, Vol.11, No.11, November 13, pp. 674~68 e-ssn: 87-78X 674 Two Levels Data Fusion Filtering Algorithms of Multimode Compound Seeker Guodong Zhang*, Zhong Liu, Ke Li College of Electronic Engineering,

More information

Regulation Performance of Regulatable Dry Gas Seal

Regulation Performance of Regulatable Dry Gas Seal Regulation Performance of Regulatable Dr Gas Seal SHUANGXI LI, QIAOFENG ZHU, JINING CAI, QIUXIANG ZHANG, ZHAOXU JIN Colleague of Mechanical and Engineering Beijing Universit of Chemical Technolog No.15

More information

NON-LINEAR CONTROL OF OUTPUT PROBABILITY DENSITY FUNCTION FOR LINEAR ARMAX SYSTEMS

NON-LINEAR CONTROL OF OUTPUT PROBABILITY DENSITY FUNCTION FOR LINEAR ARMAX SYSTEMS Control 4, University of Bath, UK, September 4 ID-83 NON-LINEAR CONTROL OF OUTPUT PROBABILITY DENSITY FUNCTION FOR LINEAR ARMAX SYSTEMS H. Yue, H. Wang Control Systems Centre, University of Manchester

More information

Prediction of Vegetable Price Based on Neural Network and Genetic Algorithm

Prediction of Vegetable Price Based on Neural Network and Genetic Algorithm Prediction of Vegetable Price Based on Neural Network and Genetic Algorithm Changshou uo 1, Qingfeng Wei 1, iying Zhou 2,, Junfeng Zhang 1, and ufen un 1 1 Institute of Information on cience and Technology

More information

Nonlinear Function Approximation Using Fuzzy Functional SIRMs Inference Model

Nonlinear Function Approximation Using Fuzzy Functional SIRMs Inference Model Nonlinear Function Approximation Using Fuzz Functional SIRMs Inference Model HIROSATO SEKI Osaka Institute of Technolog Department of Technolog Management 5-6-, Omia, Asahi-ku, Osaka JAPAN h seki@ieee.org

More information

Fuzzy control of a class of multivariable nonlinear systems subject to parameter uncertainties: model reference approach

Fuzzy control of a class of multivariable nonlinear systems subject to parameter uncertainties: model reference approach International Journal of Approximate Reasoning 6 (00) 9±44 www.elsevier.com/locate/ijar Fuzzy control of a class of multivariable nonlinear systems subject to parameter uncertainties: model reference approach

More information

Application of Fully Recurrent (FRNN) and Radial Basis Function (RBFNN) Neural Networks for Simulating Solar Radiation

Application of Fully Recurrent (FRNN) and Radial Basis Function (RBFNN) Neural Networks for Simulating Solar Radiation Bulletin of Environment, Pharmacology and Life Sciences Bull. Env. Pharmacol. Life Sci., Vol 3 () January 04: 3-39 04 Academy for Environment and Life Sciences, India Online ISSN 77-808 Journal s URL:http://www.bepls.com

More information

ESTIMATING THE ACTIVATION FUNCTIONS OF AN MLP-NETWORK

ESTIMATING THE ACTIVATION FUNCTIONS OF AN MLP-NETWORK ESTIMATING THE ACTIVATION FUNCTIONS OF AN MLP-NETWORK P.V. Vehviläinen, H.A.T. Ihalainen Laboratory of Measurement and Information Technology Automation Department Tampere University of Technology, FIN-,

More information

Effect of Pass Schedule on Cross-Sectional Shapes of Circular Seamless Pipes Reshaped into Square Shapes by Hot Roll Sizing Mill*

Effect of Pass Schedule on Cross-Sectional Shapes of Circular Seamless Pipes Reshaped into Square Shapes by Hot Roll Sizing Mill* Materials Transactions, Vol. 45, No. 4 (4) pp. 13 to 137 #4 The Japan Institute of Metals Effect of Pass Schedule on Cross-Sectional Shapes of Circular Seamless Pipes Reshaped into Square Shapes b Hot

More information

A Wavelet Neural Network Forecasting Model Based On ARIMA

A Wavelet Neural Network Forecasting Model Based On ARIMA A Wavelet Neural Network Forecasting Model Based On ARIMA Wang Bin*, Hao Wen-ning, Chen Gang, He Deng-chao, Feng Bo PLA University of Science &Technology Nanjing 210007, China e-mail:lgdwangbin@163.com

More information

Motion Control of Passive Haptic Device Using Wires with Servo Brakes

Motion Control of Passive Haptic Device Using Wires with Servo Brakes The IEEE/RSJ International Conference on Intelligent Robots and Systems October 8-,, Taipei, Taiwan Motion Control of Passive Haptic Device Using Wires with Servo Brakes Yasuhisa Hirata, Keitaro Suzuki

More information

The Diagnosis and Optimization of Scroll Compressor Noise Based on the Theory of Near- Field Acoustical Holography

The Diagnosis and Optimization of Scroll Compressor Noise Based on the Theory of Near- Field Acoustical Holography Purdue Universit Purdue e-pubs International Compressor Engineering Conference chool of Mechanical Engineering 2010 The Diagnosis and Optimiation of croll Compressor oise Based on the Theor of ear- Field

More information

An Earth Auger as Excavator for Planetary Underground Explorer Robot. Using Peristaltic Crawling

An Earth Auger as Excavator for Planetary Underground Explorer Robot. Using Peristaltic Crawling An Earth Auger as Excavator for Planetary Underground Explorer Robot Using Peristaltic Crawling H. Omori *, T. Murakami, H. Nagai, T. Nakamura **, and T. Kubota *** * Department of Precision Mechanics,

More information

Description of 2009 FUZZ-IEEE Conference Competition Problem

Description of 2009 FUZZ-IEEE Conference Competition Problem Description of 009 FUZZ-IEEE Conference Competition Problem Designed by Hao Ying and Haibo Zhou Tas Force on Competitions, Fuzzy Systems Technical Committee IEEE Computational Intelligence Society 1. Introduction

More information

Solitary Wave Solutions of KP equation, Cylindrical KP Equation and Spherical KP Equation

Solitary Wave Solutions of KP equation, Cylindrical KP Equation and Spherical KP Equation Commun. Theor. Phs. 67 (017) 07 11 Vol. 67 No. Februar 1 017 Solitar Wave Solutions of KP equation Clindrical KP Equation and Spherical KP Equation Xiang-Zheng Li ( 李向正 ) 1 Jin-Liang Zhang ( 张金良 ) 1 and

More information

ScienceDirect. Analogy of stress singularities analysis between piezoelectric materials and anisotropic materials

ScienceDirect. Analogy of stress singularities analysis between piezoelectric materials and anisotropic materials Available online at www.sciencedirect.com Scienceirect Procedia Materials Science ( 4 ) 767 77 th European Conference on Fracture (ECF) Analog of stress singularities analsis between piezoelectric materials

More information

Simulation of Acoustic and Vibro-Acoustic Problems in LS-DYNA using Boundary Element Method

Simulation of Acoustic and Vibro-Acoustic Problems in LS-DYNA using Boundary Element Method 10 th International LS-DYNA Users Conference Simulation Technolog (2) Simulation of Acoustic and Vibro-Acoustic Problems in LS-DYNA using Boundar Element Method Yun Huang Livermore Software Technolog Corporation

More information

Effect of Structural Design Parameters of a Six-Axis Force/Torque Sensor Using Full Factorial Design

Effect of Structural Design Parameters of a Six-Axis Force/Torque Sensor Using Full Factorial Design Proceedings of the 3rd RI International Conference on Robotics and Mechatronics October 7-9, 2015, Tehran, Iran Effect of tructural Design Parameters of a ix-axis Force/Torque ensor Using Full Factorial

More information

A new Algorithm for Reverse Car Parking Problem

A new Algorithm for Reverse Car Parking Problem A new Algorithm for Reverse Car Paring Problem SALVATORE PENNACCHIO, EMANUELE BELLAFIORE, FRANCESCO FONTANA, ORAZIO NEVOLOSO Universit of Palermo Viale delle Scienze, 90128 Palermo Ital Abstract: - This

More information

for Articulated Robot Arms and Its Applications

for Articulated Robot Arms and Its Applications 141 Proceedings of the International Conference on Information and Automation, December 15-18, 25, Colombo, Sri Lanka. 1 Forcefree Control with Independent Compensation for Articulated Robot Arms and Its

More information

Parameterized Joint Densities with Gaussian Mixture Marginals and their Potential Use in Nonlinear Robust Estimation

Parameterized Joint Densities with Gaussian Mixture Marginals and their Potential Use in Nonlinear Robust Estimation Proceedings of the 2006 IEEE International Conference on Control Applications Munich, Germany, October 4-6, 2006 WeA0. Parameterized Joint Densities with Gaussian Mixture Marginals and their Potential

More information

Method for Optimizing the Number and Precision of Interval-Valued Parameters in a Multi-Object System

Method for Optimizing the Number and Precision of Interval-Valued Parameters in a Multi-Object System Method for Optimizing the Number and Precision of Interval-Valued Parameters in a Multi-Object System AMAURY CABALLERO*, KANG YEN*, *, JOSE L. ABREU**, ALDO PARDO*** *Department of Electrical & Computer

More information

THE UNIVERSITY OF MICHIGAN. Timing Analysis of Domino Logic

THE UNIVERSITY OF MICHIGAN. Timing Analysis of Domino Logic Timing Analsis of Domino Logic b David Van Campenhout, Trevor Mudge and Karem Sakallah CSE-T-296-96 THE UNIVESITY O MICHIGAN Computer Science and Engineering Division Department of Electrical Engineering

More information

Bayesian Network-Based Road Traffic Accident Causality Analysis

Bayesian Network-Based Road Traffic Accident Causality Analysis 2010 WASE International Conference on Information Engineering Bayesian Networ-Based Road Traffic Accident Causality Analysis Xu Hongguo e-mail: xhg335@163.com Zong Fang (Contact Author) Abstract Traffic

More information

Bidirectional Representation and Backpropagation Learning

Bidirectional Representation and Backpropagation Learning Int'l Conf on Advances in Big Data Analytics ABDA'6 3 Bidirectional Representation and Bacpropagation Learning Olaoluwa Adigun and Bart Koso Department of Electrical Engineering Signal and Image Processing

More information

The Design of the Best Penetration Maneuvers Parameter of Variable Trajectory Maneuvers of Target Missiles

The Design of the Best Penetration Maneuvers Parameter of Variable Trajectory Maneuvers of Target Missiles Modeling Simulation Optimiation Technologies Applications (MSOTA 6) The Design of Best Penetration Maneuvers Parameter of Variable Trajector Maneuvers of Target Missiles Kaibo Bi Yifei Zhang Xianhui Sui

More information

DESIGN AND PERFORMANCE OF THE CONVERGING-DIVERGING VORTEX FLOWMETER

DESIGN AND PERFORMANCE OF THE CONVERGING-DIVERGING VORTEX FLOWMETER Metrol. Meas. Syst., Vol. XVIII (011), No. 1, pp. 19-136 METROLOGY AND MEASUREMENT SYSTEMS Index 330930, ISSN 0860-89 www.metrology.pg.gda.pl DESIGN AND PERFORMANCE OF THE CONVERGING-DIVERGING VORTEX FLOWMETER

More information

Direct Estimation of Wrist Joint Angular Velocities from Surface EMGs by Using an SDNN Function Approximator

Direct Estimation of Wrist Joint Angular Velocities from Surface EMGs by Using an SDNN Function Approximator Direct Estimation of Wrist Joint Angular Velocities from Surface EMGs by Using an SDNN Function Approximator Kazumasa Horie 1, Atsuo Suemitsu 2, Tomohiro Tanno 1, and Masahiko Morita 1 1 University of

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(7): Research Article

Journal of Chemical and Pharmaceutical Research, 2014, 6(7): Research Article Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 4, 6(7): 44-4 Research Article ISSN : 975-784 CODEN(USA) : JCPRC5 Analysis on static characteristics of linear rolling guide

More information

A PROTOCOL FOR DETERMINATION OF THE ADHESIVE FRACTURE TOUGHNESS OF FLEXIBLE LAMINATES BY PEEL TESTING: FIXED ARM AND T-PEEL METHODS

A PROTOCOL FOR DETERMINATION OF THE ADHESIVE FRACTURE TOUGHNESS OF FLEXIBLE LAMINATES BY PEEL TESTING: FIXED ARM AND T-PEEL METHODS 1 A PROTOCOL FOR DETERMINATION OF THE ADHESIVE FRACTURE TOUGHNESS OF FLEXIBLE LAMINATES BY PEEL TESTING: FIXED ARM AND T-PEEL METHODS An ESIS Protocol Revised June 2007, Nov 2010 D R Moore, J G Williams

More information

Electric Load Forecasting Using Wavelet Transform and Extreme Learning Machine

Electric Load Forecasting Using Wavelet Transform and Extreme Learning Machine Electric Load Forecasting Using Wavelet Transform and Extreme Learning Machine Song Li 1, Peng Wang 1 and Lalit Goel 1 1 School of Electrical and Electronic Engineering Nanyang Technological University

More information

Generalized projective synchronization of a class of chaotic (hyperchaotic) systems with uncertain parameters

Generalized projective synchronization of a class of chaotic (hyperchaotic) systems with uncertain parameters Vol 16 No 5, May 2007 c 2007 Chin. Phys. Soc. 1009-1963/2007/16(05)/1246-06 Chinese Physics and IOP Publishing Ltd Generalized projective synchronization of a class of chaotic (hyperchaotic) systems with

More information

ARTIFICIAL SATELLITES, Vol. 41, No DOI: /v

ARTIFICIAL SATELLITES, Vol. 41, No DOI: /v ARTIFICIAL SATELLITES, Vol. 41, No. 1-006 DOI: 10.478/v10018-007-000-8 On InSAR AMBIGUITY RESOLUTION FOR DEFORMATION MONITORING P.J.G. Teunissen Department of Earth Observation and Space Sstems (DEOS)

More information

A New Closed-loop Identification Method of a Hammerstein-type System with a Pure Time Delay

A New Closed-loop Identification Method of a Hammerstein-type System with a Pure Time Delay A New Closed-loop Identification Method of a Hammerstein-tpe Sstem with a Pure Time Dela Edin Drljević a, Branislava Peruničić b, Željko Jurić c, Member of IEEE Abstract A procedure for the closed-loop

More information

An Experimental Study of In-plane Oval Damper

An Experimental Study of In-plane Oval Damper Proceedings of the 3 rd World Congress on Civil, Structural, and Environmental Engineering (CSEE 18) Budapest, Hungar April 8-10, 2018 Paper No. ICSENM 110 DOI: 10.11159/icsenm18.110 An Experimental Stud

More information

CMAC-based modelling for HPDDL welding process control. Peiyong Duan. Yu Ming Zhang*

CMAC-based modelling for HPDDL welding process control. Peiyong Duan. Yu Ming Zhang* Int. J. Modelling, Identification and Control, Vol., No. 2, 2006 07 CMAC-based modelling for HPDDL welding process control Peiyong Duan School of Information and Electrical Engineering, Shandong Institute

More information

THE ADJOINT OF A MATRIX The transpose of this matrix is called the adjoint of A That is, C C n1 C 22.. adj A. C n C nn.

THE ADJOINT OF A MATRIX The transpose of this matrix is called the adjoint of A That is, C C n1 C 22.. adj A. C n C nn. 8 Chapter Determinants.4 Applications of Determinants Find the adjoint of a matrix use it to find the inverse of the matrix. Use Cramer s Rule to solve a sstem of n linear equations in n variables. Use

More information

Calibration and Temperature Retrieval of Improved Ground-based Atmospheric Microwave Sounder

Calibration and Temperature Retrieval of Improved Ground-based Atmospheric Microwave Sounder PIERS ONLINE, VOL. 6, NO. 1, 2010 6 Calibration and Temperature Retrieval of Improved Ground-based Atmospheric Microwave Sounder Jie Ying He 1, 2, Yu Zhang 1, 2, and Sheng Wei Zhang 1 1 Center for Space

More information

Nonlinear PD Controllers with Gravity Compensation for Robot Manipulators

Nonlinear PD Controllers with Gravity Compensation for Robot Manipulators BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 4, No Sofia 04 Print ISSN: 3-970; Online ISSN: 34-408 DOI: 0.478/cait-04-00 Nonlinear PD Controllers with Gravity Compensation

More information

Diesel Fault Diagnosis Technology Based on the theory of Fuzzy Neural Network Information Fusion

Diesel Fault Diagnosis Technology Based on the theory of Fuzzy Neural Network Information Fusion Diesel Fault Diagnosis Technology Based on the theory of Fuzzy Neural Network Information Fusion i ongkun a Xiaojiang e Yong Institute of Vibration Engineering, Dalian University of Technology, Dalian,

More information

School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Graduate School Shenzhen, Guangdong Province, China

School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Graduate School Shenzhen, Guangdong Province, China 2016 International Conference on Mechanics Design, Manufacturing and Automation (MDM 2016) ISBN: 978-1-60595-354-0 A New Decoupling Measurement Method of Five-axis Machine ools Geometric Errors Based on

More information

Exploiting Spatial and Temporal Flexibility for Plan Execution of Hybrid, Under-actuated Systems

Exploiting Spatial and Temporal Flexibility for Plan Execution of Hybrid, Under-actuated Systems Exploiting Spatial and Temporal Flexibilit for Plan Execution of Hbrid, Under-actuated Sstems Andreas G. Hofmann and Brian C. Williams Computer Science and Artificial Intelligence Lab, MIT 32 Vassar St.

More information

Heat Transfer Experiment and Simulation of the Verification Facility for High Power Rotating Tritium Target System

Heat Transfer Experiment and Simulation of the Verification Facility for High Power Rotating Tritium Target System J Fusion Energ (2015) 34:1252 1256 DOI 10.1007/s10894-015-9952-1 ORIGINAL RESEARCH Heat Transfer Experiment and Simulation of the Verification Facility for High Power Rotating Tritium Target System Gang

More information

Hand Written Digit Recognition using Kalman Filter

Hand Written Digit Recognition using Kalman Filter International Journal of Electronics and Communication Engineering. ISSN 0974-2166 Volume 5, Number 4 (2012), pp. 425-434 International Research Publication House http://www.irphouse.com Hand Written Digit

More information

Classification of High Spatial Resolution Remote Sensing Images Based on Decision Fusion

Classification of High Spatial Resolution Remote Sensing Images Based on Decision Fusion Journal of Advances in Information Technology Vol. 8, No. 1, February 2017 Classification of High Spatial Resolution Remote Sensing Images Based on Decision Fusion Guizhou Wang Institute of Remote Sensing

More information

Least-Squares Independence Test

Least-Squares Independence Test IEICE Transactions on Information and Sstems, vol.e94-d, no.6, pp.333-336,. Least-Squares Independence Test Masashi Sugiama Toko Institute of Technolog, Japan PRESTO, Japan Science and Technolog Agenc,

More information

Laser on-line Thickness Measurement Technology Based on Judgment and Wavelet De-noising

Laser on-line Thickness Measurement Technology Based on Judgment and Wavelet De-noising Sensors & Transducers, Vol. 168, Issue 4, April 214, pp. 137-141 Sensors & Transducers 214 by IFSA Publishing, S. L. http://www.sensorsportal.com Laser on-line Thickness Measurement Technology Based on

More information

Implement an Advanced Soft Measurement Method of Mine Dust Concentration Based on K-RBF Neural Network

Implement an Advanced Soft Measurement Method of Mine Dust Concentration Based on K-RBF Neural Network Implement an Advanced Soft Measurement Method of Mine Dust Concentration Based on K-RBF eural etwor Hong Yu, Xuezhen Cheng 2, Maoyong Cao, Xiaohang Gao 4 Capitol Technology University,Laurel,Maryland,20708,USA

More information

Short-Term Wind Speed Forecasting Using Regularization Extreme Learning Machine Da-cheng XING 1, Ben-shuang QIN 1,* and Cheng-gang LI 2

Short-Term Wind Speed Forecasting Using Regularization Extreme Learning Machine Da-cheng XING 1, Ben-shuang QIN 1,* and Cheng-gang LI 2 27 International Conference on Mechanical and Mechatronics Engineering (ICMME 27) ISBN: 978--6595-44- Short-Term Wind Speed Forecasting Using Regularization Extreme Learning Machine Da-cheng XING, Ben-shuang

More information

Research on Short-term Load Forecasting of the Thermoelectric Boiler. Based on a Dynamic RBF Neural Network

Research on Short-term Load Forecasting of the Thermoelectric Boiler. Based on a Dynamic RBF Neural Network Research on Short-term Load Forecasting of the Thermoelectric Boiler Based on a Dynamic RBF Neural Networ Wei-Bao DAI, Ping-Hua ZOU, Cheng-Xian, YAN School of Municipal and Environmental Engineering Harbin

More information

Other examples of neurons can be found in:

Other examples of neurons can be found in: 4 Concept neurons Introduction to artificial neural networks 41 Tpical neuron/nerve cell: from Kandel, Schwartz and Jessel, Principles of Neural Science The cell od or soma contains the nucleus, the storehouse

More information

Short-term Streamflow Forecasting: ARIMA Vs Neural Networks

Short-term Streamflow Forecasting: ARIMA Vs Neural Networks Short-term Streamflow Forecasting: ARIMA Vs Neural Networks,JUAN FRAUSTO-SOLIS 1, ESMERALDA PITA 2, JAVIER LAGUNAS 2 1 Tecnológico de Monterre, Campus Cuernavaca Autopista del Sol km 14, Colonia Real del

More information