文献类型：期刊文献

英文题名：Research on the Technology of Workpiece Surface Detection Based on Convolutional Neural Network

作者：Jia, ChenHao[1]; Chang, Qing[1]; Bao, LingYi[1]; Sun, QiuRan[1]; Xiong, PengBo[1]

机构：[1] East China University of Science and Technology, SHH 10251, China

年份：2022

起止页码：339

外文期刊名：Proceedings - 2022 International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2022

收录：EI(收录号：20224913202183)

语种：英文

外文关键词：Convolution - Deep learning - Engineering education - Learning systems - Manufacture - Surface defects

摘要：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. ? 2022 IEEE.