Motion Control System of Numerical Control Machine Tool Under Image Processing

Abstract

The study is employed to reduce mechanical faults and improve the work efficiency of machinery. This paper adopts intelligent detection means and systematically detects the machinery faults. First, a new feature extraction method is used for the sparse automatic encoder that proposed to solve the problem of insufficient feature extraction of the informational fault of the equipment. Second, the binary tree support vector machine (SVM) is used to classify faults. Finally, the electronic circuit of the three-spot resistance welder's fault is detected to verify the reliability of the sparse automatic encoder. The research result shows that the use of sparse automatic encoders can enhance the robustness of non-Gaussian noise. At the same time, the convolutional neural network (CNN) technology is combined to perform edge noise reduction on its encoder. It can improve the feature extraction degree of electronic circuit information. The binary tree SVM can effectively classify mechanical faults and the results of output judgment whether the mechanical equipment is faulty or not. The automatic encoder is used to detect the fault of the three-spot resistance welder, and the fault detection result of the new detection method has higher accuracy and high reliability. The new fault detection method can efficiently detect mechanical faults and promotes the work efficiency of machinery, and ultimately the entire society.