Tracking Control of Cable-Driven Planar Robot Based on Discrete-Time Recurrent Neural Network With Immediate Discretization Method

Abstract

In recent years, the cable-driven planar robot has made fruitful achievements in many fields, but the related researches are scarce yet in the industrial engineering field. In this paper, as a powerful tool for solving discrete time-varying problems, discrete-time recurrent neural network (DTRNN) is extended to drive the cable-driven planar robot for discrete real-time tracking control, which is derived by a new immediate discretization method, and thus is termed as ID-DTRNN model. Specifically, firstly, we present the physical structure and mathematical model of cable-driven planar robot. Then, new ID-DTRNN model is proposed and applied for driving such cable-driven planar robot, which bases on the a different way of construction of traditional DTRNN model. Through numerical experiments, the feasibility, validity and physical reliability of the ID-DTRNN model for discrete real-time tracking control of cable-driven planar robot are fully verified. In addition, in the real world, physical experiments of the cable-driven planar robot are presented, which successfully promote the development of physical application of ID-DTRNN model, and fill the gap of such model in the industrial engineering field.