Research on Positioning Error Compensation of Industrial Robot Based on BP Neural Network

Abstract

Due to the existence of geometric error and non-geometric error factors, the positioning accuracy of industrial robots is greatly reduced, which can not meet the needs of industrial production, so we need to carry out positioning error compensation for industrial robots. The traditional compensation method of establishing geometric error model can only compensate geometric errors. Aiming at this shortage, this paper proposes a positioning error compensation method based on BP neural network, which takes into account both geometric error and non-geometric error factors. Experimental results show that the proposed method can greatly improve the positioning accuracy of industrial robots.