Cerebellar model articulation controller proportional velocity parameters variations and learning schemes

Abstract

Cerebellar model articulation controller neural networks is one of the computational intelligence tools that can be applied for modeling, classification, and control. Proportional velocity controller is a servo-type controller, which is commonly applied to motion control systems. This paper presents a novel combination of cerebellar model articulation controller neural networks and optimal proportional velocity controller. A simple mathematical model for applying and studying cerebellar model articulation controller is introduced, and a study of its parameters is presented individually. The effect of parameters variation on cerebellar model articulation controller performance is identified. Learning algorithms highly affect the cerebellar model articulation controller behavior even when the parameters are optimized, and proper selection of the learning scheme must be taken under consideration. Three different learning algorithms are studied for evaluating transient and steady-state cerebellar model articulation controller responses. The results showed that the change of cerebellar model articulation controller generalization size and scale of the control signal has a marked effect on the performance of cerebellar model articulation controller. Furthermore, the constant learning rate algorithm gives the best overall performance.

Keywords

Neural networks CMAC PV control learning algorithms

Get full access to this article

View all access options for this article.

References

Albus JS. A new approach to manipulator control: the cerebellar model articulation controller (CMAC). J Dyn Syst Meas Control Trans ASME Series G 1975: 220–227.

Horvath G and Gati K. Kernel CMAC with reduced memory complexity. In: International conference on advanced nanomaterials and nanotechnology (ICANN 2009), Part I, Guwahati, December 9–11, 2009, pp.698–707. LNCS 5768.

Abdelhameed

Pinspon

Cetinkunt

. Adaptive learning algorithm for cerebellar model articulation controller. Mechatronics 2002; 12: 859–873.

Hsu

C-F

Chung

C-M

Lin

C-M

. Adaptive CMAC neural control of chaotic systems with a PI-type learning algorithm. Expert Syst Appl 2009; 36: 11836–11843.

Moreno-Armendariz

Rodriguez

. Stable adaptive compensation with fuzzy CMAC for an overhead crane. Inf Sci 2011; 181: 4895–4907.

Li Y and Xu Q. CMAC-based PID control of an XY parallel micropositioning stage. In: Sixth international symposium on neural networks (ISNN 2009), Part II, Wuhan, China, May 26–29, 2009, pp.1040–1049. LNCS 5552.

Yeh

M-F

Tsai

C-H

. Standalone CMAC control system with online learning ability. IEEE Trans Syst Man Cybern Part B: Cybern 2010; 40: 43–53.

Yeh

M-F

. Single-input CMAC control system. Neurocomputing 2007; 70: 2638–2644.

Tsai

C-H

Yeh

M-F

. Application of CMAC neural network to the control of induction motor drives. Appl Soft Comput 2009; 9: 1187–1196.

10.

Ding M, Zhou Q and Song K. A new method for accelerometer dynamic compensation based on CMAC. In: Sixth international symposium on neural networks (ISNN 2009), Part I, Wuhan, China, 2009, pp.667–675. LNCS 4491.

11.

Bucak

Baki

. Diagnosis of liver disease by using CMAC neural network approach. Expert Syst Appl 2010; 37: 6157–6164.

12.

J-Y

. MIMO CMAC neural network classifier for solving classification problems. Appl Soft Comput 2011; 11: 2326–2333.

13.

Wen

Lin

T-C

Chang

K-C

. Classification of ECG complexes using selforganizing CMAC. Measurement 2009; 42: 399–407.

14.

Teddy SD. KCMAC: a novel fuzzy cerebellar model for medical decision support. Artificial Neural Networks-ICANN 2008. Berlin Heidelberg: Springer, 2008, pp.537–546.

15.

Cheng

K-H

. CMAC-based neuro-fuzzy approach for complex system modeling. Neurocomputing 2009; 72: 1763–1774.

16.

Ortiz F, Yu W, Moreno-Armendariz M, et al. Recurrent fuzzy CMAC for nonlinear system modeling. In: Sixth international symposium on neural networks (ISNN 2007), Part I, pp.487–495. LNCS 4491.

17.

Lin

C-J

Lee

C-Y

. A novel parametric fuzzy CMAC network and its applications. Appl Soft Comput 2009; 9: 775–785.

18.

. Hierarchical fuzzy CMAC for nonlinear systems modeling. IEEE Trans Fuzzy Syst 2008; 16: 1302–1314.

19.

Moreno-Armendariz

Perez-Olvera

Rodriguez

. Indirect hierarchical FCMAC control for the ball and plate system. Neurocomputing 2010; 73: 2454–2463.

20.

Shen

Guo

Zhang

. A general fuzzified CMAC based reinforcement learning control for ship steering using recursive least-squares algorithm. Neurocomputing 2010; 73: 700–706.

21.

Nguyen

Shi

. An online Bayesian Ying–Yang learning applied to fuzzy CMAC. Neurocomputing 2008; 72: 562–572.

22.

H-C

Chuang

C-Y

Yeh

M-F

. Design of a hybrid adaptive CMAC with supervisory controller for a class of nonlinear system. Neurocomputing 2009; 72: 1920–1933.

23.

Tao

S-F

. CMAC-based previous step supervisory control schemes for relaxing bound in adaptive fuzzy control. Appl Soft Comput 2011; 11: 5715–5723.

24.

C-J

J-Y

. An efficient CMAC neural network for stock index forecasting. Expert Syst Appl 2011; 38: 15194–15201.

25.

H-C

Chuang

C-Y

. Robust parametric CMAC with self-generating design for uncertain nonlinear systems. Neurocomputing 2011; 74: 549–562.

Cerebellar model articulation controller proportional velocity parameters variations and learning schemes—A study on electrohydraulic servo system

Abstract

Keywords

Get full access to this article

References