Research on the Technology of Workpiece Surface Detection Based on Convolutional Neural Network

With the advancement of science and technology, people have higher requirements for the quality of products produced. Defect detection on the surface of products can improve the overall quality of products. In this day and a time of growing industrial automation, the traditional artificial defect detection in accuracy, speed and so on already cannot meet the requirement of the industrial production, in order to improve the productivity, enhance the level of industrial manufacturer defect detection, it is necessary to find a more effective detection method, namely the surface defect detection based on machine learning techniques. Due to the development of machine learning and deep learning in recent years, the technology has been able to applied to the workpiece surface defect detection, in several kinds of defect detection technology based on the deep learning, through the way of experiment, it is concluded that Domen proposed dual phase depth convolution neural network can be in the same conditions to get higher precision rate and recall rate of accuracy, This paper focuses on the structure and function of the Convolutional neural network.