Skip to Main Content
Article navigation
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.

Licensed re-use rights only
You do not currently have access to this content.
Don't already have an account? Register

Purchased this content as a guest? Enter your email address to restore access.

Please enter valid email address.
Email address must be 94 characters or fewer.
Pay-Per-View Access
$41.00
Rental

or Create an Account

Close Modal
Close Modal