A new inverse controller for servo‐system based on neural network model reference adaptive control

Abstract

PurposeThe purpose of this paper is to develop a new inverse controller for servo‐system position tracking control based on neural network (NN) and model reference adaptive control (MRAC).Design/methodology/approachFirst, the model of general servo‐systems is analyzed. Then, a MRAC based on neural network control (NNC) is proposed with mathematical prove of stability. In addition, several simulation cases and experiments are listed to verify the usability of the control scheme.FindingsThis scheme consists of an MRAC, an online NN controller and a robust controller in velocity‐loop. For reducing influence which arose from modeling error, unknown model dynamics, parameter variation, and load changes, the NN controller is introduced to counteract the various influence mentioned above dynamically. MRAC, NNC, and robust controller adjust system to track the approximate velocity‐loop reference model. In this way, the position‐loop is not sensitive to the disturbance on velocity‐loop, and the whole velocity‐loop can be treated as a simple linear model when designing the other parts of the system. In addition, a novel inverse control method based on linear velocity signal filter is introduced to this scheme. In this case, the MRAC, NNC, and robust controller perform as an adaptive inverse controller, which keeps the velocity signal tracking the position loop controller output.Originality/valueThe paper presents a new inverse controller with NNC and MRAC which is practical and flexible.