Control of industrial robot using neural network compensator

Abstract

In the paper is considered synthesis of the controller with tachometric feedback with feed forward compensation of disturbance torque, velocity and acceleration errors. It is difficult to obtain the desired control performance when the control algorithm is only based on the robot dynamic model. We use the neural network to generate auxiliary joint control torque to compensate these uncertainties. The two-layer neural network is used as the compensator. The main task of control system here is to track the required trajectory. Simulations are done in MATLAB for RzRyRy robot minimal configuration.U radu je razmatrana sinteza kontrolera sa tahometarskom povratnom spregom i unaprednom kompenzacijom momenta poremecaja, brzinske i akceleracijske greske. Tesko je dobiti zeljene performanse sistema kada se algoritam upravljanja zasniva samo na matematickom modelu robota. Za generisanje dodatnog momenta pogona po zglobovima, kojim se kompenzuju neodredjenosti, koristi se neuronska mreza. Kao kompenzator se upotrebljava dvoslojna neuronska mreza. Glavni zadatak sistema upravljanja je pracenje zadate trajektorije. Simulacije su uradjene u MATLAB-u za robot RzRyRy minimalne konfiguracije.