A Five- axis Contour Error Pre-compensation Method Based on Neural Network Prediction

In this article, a pre-compensation method is proposed for contour error control. This method predict the contour error indirectly using an imporoved neural network named Long and short-term Time-series network(LSTNet). By analyzing the characteristics of machine tool operation, the tracking error is divided into linear tracking error and nonlinear tracking error. The single-axis tracking error model is established using the neural network. First, the trajectory contour error is estimated according to the predicted trajectory and the reference trajectory. Then, the reference trajectory is compensated based on the predicted contour error. Finally, the experiment is implemented on a five-axis machine tool with BC revolving stage, and the results show that the proposed error compensation performs well.