Motion error tracing of NC machine tools based on deep learning framework

To identify the error factors of NC machine tools quickly and accurately, an intelligent method of motion error tracing based on deep learning framework is proposed. First, the reference circle model of circular motion error trajectory is established, and a large number of theoretical samples are generated with the model. Then, the motion error tracing model based on Faster R-CNN framework is presented. The deep convolution network of the model is constructed to automatically extract the feature of circular track. The generation mechanism of the candidate region is improved to realize trajectory discrimination and region generation. Finally, the error trajectory type is identified accurately by the region recognition layer of the model. Motion error is traced intelligently and quickly according to mapping the circular motion trajectory to the error source. Experimental results show that this method is workable and adaptable, and the accuracy of traceability is higher than 96%. © 2019, Science Press. All right reserved.