摘要
提出了一种基于堆叠降噪自编码(SDAE)的刀具磨损状态识别方法。构建了SDAE神经网络来学习声发射(AE)信号的特征,并对自编码网络进行有监督的微调,从而对刀具磨损状态进行精确识别。实验结果表明,SDAE方法能够自适应地学习,得到有效的特征表达,且刀具磨损状态识别结果精确度高,该方法能够有效地进行刀具磨损状态识别。
A new method of condition recognition for tool wear was proposed based on SADE.A SDAE neural network was constructed to learn the characteristics of AE signals,and a supervised finetuning of the autoencoder network was carried out,so that the tool wear conditions were accurately recognized.The experimental results show that the SDAE method may learn adaptively to get effective feature expressions and the tool wear condition recognition precision is high.The proposed method may be used to recognize tool wear conditions effectively.
作者
王丽华
杨家巍
张永宏
赵晓平
谢阳阳
WANG Lihua;YANG Jiawei;ZHANG Yonghong;ZHAO Xiaoping;XIE Yangyang(School of Information and Control,Nanjing University of Information Science&Technology,Nanjing,210044;School of Computer&Software,Nanjing University of Information Science&Technology,Nanjing,210044)
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2018年第17期2038-2045,共8页
China Mechanical Engineering
基金
国家自然科学基金资助项目(51405241
51575283
51505234)
关键词
刀具磨损
声发射
深度学习
堆叠降噪自编码
tool wear
acoustic emission(AE)
deep learning
stacked denoising autoencoder(SDAE)
作者简介
王丽华,女,1974年生,高级实验师。研究方向为故障诊断、模式识别及信号处理。E-mail:309849375@qq.com。;杨家巍(通信作者),男,1992年生,硕士研究生。研究方向为故障诊断、模式识别及信号处理。E-mail:765307501@qq.com。
