Intelligent motion control of voice coil motor using PID-based fuzzy neural network with optimized membership function

• Published in: Engineering computations Vol. 33; no. 8; pp. 2302 - 2319
• Main Authors: Chen, Syuan-Yi, Lee, Cheng-Yen, Wu, Chien-Hsun, Hung, Yi-Hsuan
• Format: Journal Article
• Language: English
• Published: Bradford Emerald Group Publishing Limited 07.11.2016
• Subjects: Accuracy; Adaptive control; Artificial neural networks; Back propagation; Bacteria; Control algorithms; Control systems; Controllers; Digital signal processing; Digital signal processors; Floating point arithmetic; Foraging behavior; Fuzzy control; Fuzzy logic; Load; Machine learning; Mathematical models; Microprocessors; Motion control; Motors; Neural networks; On-line systems; Optimization; Optimization algorithms; Proportional integral derivative; Real time; Voice control; Bacterial foraging optimization; Voice coil motor; Fuzzy neural network; Proportional-integral-derivative control
• ISSN: 0264-4401; 1758-7077
• DOI: 10.1108/EC-08-2015-0250

Purpose The purpose of this paper is to develop a proportional-integral-derivative-based fuzzy neural network (PIDFNN) with elitist bacterial foraging optimization (EBFO)-based optimal membership functions (PIDFNN-EBFO) position controller to control the voice coil motor (VCM) for tracking reference trajectory accurately. Design/methodology/approach Because the control characteristics of the VCM are highly nonlinear and time varying, a PIDFNN, which integrates adaptive PID control with fuzzy rules, is proposed to control the mover position of the VCM. Moreover, an EBFO algorithm is further proposed to find the initial optimal fuzzy membership functions for the PIDFNN controller. Findings Due to the gradient descent method used in back propagation (BP) to derive the on-line learning algorithm for the PIDFNN, it may reach the local optimal solution due to the inappropriate initial values. Hence, a hybrid learning method, which includes BP and EBFO algorithms, is proposed to improve the learning performance of the PIDFNN controller. Research limitations/implications Future work will consider reducing the computational burden of bacterial foraging optimization algorithm for on-line parameters optimization. Practical implications The real-time control system is implemented on a 32-bit floating-point digital signal processor (DSP). The experimental results demonstrate the favorable effectiveness of the proposed PIDFNN-EBFO controlled VCM system. Originality/value A new PIDFNN-EBFO control scheme is proposed and implemented via DSP for real-time VCM position control. The experimental results show the superior control performance of the proposed PIDFNN-EBFO compared with the other control systems.