%0 Journal Article
%T 基于深度学习的刀具磨损检测研究综述<br>Overview of Tool Wear Detection Based on Deep Learning
%A 陈希
%A 宋育斌
%A 孔维宾
%A 陈登钱
%A 杨晓芳
%J Operations Research and Fuzziology
%P 1186-1203
%@ 2163-1530
%D 2023
%I Hans Publishing
%R 10.12677/ORF.2023.132122
%X 在现代化智能制造加工过程中，刀具的磨损状态直接决定工件产品的质量。传统的刀具磨损检测方法存在检测精度低、鲁棒性差等问题。近年来，深度学习的发展为刀具磨损检测提供了更加智能的解决方案。从刀具磨损检测流程开始梳理，对刀具磨损信号的检测方法进行阐述，将采集刀具磨损信号的常用处理方法进行归纳，并对常用的刀具磨损深度学习模型进行分类，说明不同模型的原理，特点以及研究现状，最后分析了不同方法的特点和应用场景。<br />
In the modern intelligent manufacturing process, the wear status of the tool directly determines the quality of the workpiece product. Traditional tool wear detection methods have problems such as low detection accuracy and poor robustness. In recent years, the development of deep learning has provided a more intelligent solution for tool wear detection. Starting from the process of tool wear detection, the detection methods of tool wear signals are explained, the common processing methods for collecting tool wear signals are summarized, and the common deep learning models for tool wear are classified, the principles, characteristics and research status of different models are explained, and finally the characteristics and application scenarios of different methods are analyzed.
%K 刀具磨损，信号处理，特征提取，深度学习，智能制造<br>Tool Wear
%K Signal Processing
%K Feature Extraction
%K Deep Learning
%K Smart Manufacturing
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=64599