Adaptive<i>H<sub>∞</sub></i>nonlinear velocity tracking using RBFNN for linear DC brushless motor

Tsai, Ching‐Chih; Chan, Cheng-Kain; Li, Yi Yu

doi:10.1080/00207721003768183

Cited by 5 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the parameter updating laws (10)(11)(12), the next weights, center vectors and standard deviations are found by…”

Section: Update Laws For Rbfnn Parametersmentioning

confidence: 99%

“…In the hidden layer, neuron activation function is a Gaussian function. The RBFNN has been used in self-balancing two wheel-type vehicles, unmanned helicopters, and brushless motors [8][9][10]. In addition, the authors in [11] proposed a novel identification method using a RBFNN and heuristic optimization methods for modeling and control of bottle 2014 IEEE International Conference on Systems, Man, and Cybernetics October 5-8, 2014, San Diego, CA, USA 978-1-4799-3840-7/14/$31.00 ©2014 IEEE section weights in stretch blow moulding.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Two DOF temperature control using RBFNN for stretch PET blow molding machines

Tsai

Chang

Tung

2014

2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

Self Cite

View full text Add to dashboard Cite

This paper presents a novel two degrees-of-freedom (DOF) digital controller using radial basis function neural network (RBFNN) for a stretch polyethyleneterephthalate (PET) blow molding machine, in order to achieve satisfactory temperature control of the PET bottle performs passing through both heating ovens. The proposed two-DOF controller is composed of a feedforward controller used to improve the transient performance and track quickly temperature setpoints, and an RBFNN self-tuning digital proportional-integral-derivative (PID) controller employed to eliminate remaining temperature errors and achieve disturbances rejection. Such a controller not only retains the practical expertise of the control practitioners working for PET blow molding machines, but also keeps automatic tuning ability of the PID controller parameters. Finally, the computer simulation and experimental result reveal disturbance rejection and good setpoint tracking performance of the proposed control method. The results clearly indicate effectiveness and merit of the proposed method.

show abstract

“…From the parameter updating laws (10)(11)(12), the next weights, center vectors and standard deviations are found by…”

Section: Update Laws For Rbfnn Parametersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Two DOF temperature control using RBFNN for stretch PET blow molding machines

Tsai

Chang

Tung

2014

2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This fact was verified by the Stone-Weierstrass Theorem [23], which states that multilayer feed-forward networks with dense and separable functions are acceptable as estimators. In the case of mechanical systems, several studies have applied neural networks for estimation purposes [3], [24]- [25]. However, the efficient number of membership functions in fuzzy control emerges as a new problem.…”

Section: Introductionmentioning

confidence: 99%

Sliding-mode control of a wheeled vehicle using neural network estimator

Pamosoaji

Hong

Cát³

2013

2013 9th Asian Control Conference (ASCC)

View full text Add to dashboard Cite

A motion control problem of a rear-steered wheeled vehicle in consideration of the presence of uncertainties is addressed. Modeling error and additional uncertainties are taken into consideration. A sliding mode controller combining with a radial basis function neural network (RBFNN)-based estimator is proposed. The stability of the proposed control method is proven using Lyapunov stability analysis. Simulation results demonstrating the performance of the proposed control law are presented. It can be concluded that the driving velocity and steering angle performances of the proposed controllers are reasonably acceptable.

show abstract