[1]李 鹏,黄亦翔,夏鹏程,等. 基于一维卷积长短时记忆网络的多信号融合刀具磨损评估 [J].机械与电子,2021,(05):8-14.
　LI Peng,HUANG Yixiang,XIA Pengcheng,et al.Multi-signal Fusion Assessment of Tool Wear Based on １DCNN-LSTM[J].Machinery & Electronics,2021,(05):8-14.
点击复制

基于一维卷积长短时记忆网络的多信号融合刀具磨损评估
()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2021年05期
页码:
8-14
栏目:
设计与研究
出版日期:
2021-05-24

文章信息/Info

Title:
Multi-signal Fusion Assessment of Tool Wear Based on １DCNN-LSTM
文章编号:
１００１-２２５７(２０２１) ０５-０００８-０７
作者:
李 鹏1; 黄亦翔1; 夏鹏程1; 时 轮1 ; 2
１．上海交通大学机械与动力工程学院,上海 ２００２４０;
２．上海交大智邦科技有限公司,上海 ２０１３０６
Author(s):
LI Peng1; HUANG Yixiang1; XIA Pengcheng1; SHI Lun1; 2
(１．School of Mechanical Engineering,Shanghai Jiao Tong University ,Shanghai ２００２４０,China;
２．Shanghai SmartState TechnologyCo．,Ltd．,Shanghai ２０１３０６, China)
关键词:
刀具磨损; 状态评估; 多信号融合; 一维卷积; 长短时记忆网络
Keywords:
tool wear; condition assessment; multi-signal fusion; １DCNN; LSTM
分类号:
TG７１;TP１８３
文献标志码:
A
摘要:
为实现刀具磨损状态的有效在线监测,提出一种基于一维卷积长短时记忆网络的多信号融合刀具磨损评估模型.该模型综合使用加工过程中主轴和工作台的振动和声发射信号,以实现信号间的优势互补,弥补单一信号的不足;基于一维卷积的特征学习能力和长短时记忆网络的时序特征分析能力,充分挖掘信号中包含的刀具磨损状态信息;最后通过全连接层和 softmax 分类器对刀具磨损状态进行评估.试验结果表明,该模型在各单一工况下对刀具磨损状态的识别准确率均可达９３．８％以上,整体工况下识别准确率达９５．３％,具有很好的稳定性和多工况通用性.
Abstract:
In order to effectively monitor the tool wear condition,a multi-signal fusion tool wear evaluation model based on １DCNN-LSTM is proposed．The vibration signal and acoustic emission signal of the spindle and working table are utilized to realize advantageous complementarities between signals to offset the defects of single signal;１D convolution and LSTM are applied to adaptively extract features and temporal properties of signals to obtain more information relative to tool wear condition;fully connected layers and the softmax classifier are used to evaluate the stage of tool wear finally．The experiment indicates that the proposed １DCNN-LSTM model can acquire accuracy of more than ９３．８％ under each signal working condition and accuracyof ９５．３％ under overall working condition,which has great stability and versatility．

参考文献/References:

[１] REHORN A G,JIANG J,ORBAN P E．State-of-the-art methods and results in tool condition monitoring:a review[J]． International journal of advanced manufacturing technology,２００５,２６(７): ６９３-７１０．

[２] KASSIM A A,MANNAN M A, MIAN Z．Texture analysis methods for tool condition monitoring[J]．Image and vision computing,２００７ ,２５(７):１０８０-１０９０．
[３] WILKINSON A J．Constriction-resistance concept applied to wear measurement of metal-cutting tools[J]．Proceedings of the institution of electrical engineers,１９７１,１１８(２):３８１-３８６．
[４] LUNDG G,ANDERSON P B．A study of the wear processes on cemented carbide cutting tool by a radioactive tracer technique[ J]．International journal of machine tool design and research,１９７０,１０(１):７９-９３．
[５] 关山,康晓峰．在线金属切削刀具磨损状态监测研究的回顾与展望I:监测信号的选择[J]．机床与液压,２０１０,３８(１１):１２７-１３２．
[６] GAO D,LIAO Z R,LV Z K,et al．Multi-scale statistical signal processing of cutting force incutting tool condition monitoring[J]． International journal of advanced manufacturing technology,２０１５,８０:１８４３-１８５３．
[７] 李宏坤,汪寅虎,杨树华,等．基于声发射信号的铣刀运行可靠性评估[J]．大连理工大学学报,２０１４,５４(４):４１８-４２３．
[８] 赵帅,黄亦翔,王浩任,等．基于随机森林与主成分分析的刀具磨损评估[J]．机械工程学报,２０１７,５３(２１):１８１-１８９．
[９] 戴稳,张超勇,孟磊磊,等．采用深度学习的铣刀磨损状态预测模型[J]．中国机械工程,２０２０,３１(１７):２０７１-２０７８．
[１０] 林杨,高思煜,刘同舜,等．基于深度学习的高速铣削刀具磨损状态预测方法[J]．机械与电 子, ２０１７,３５(７):１２-１７．
[１１] LECUN Y,BENGIO Y,HINTON G．Deep learning[J]．Nature,２０１５,５２１:４３６-４４４．
[１２] HOCHREITER S,SCHMIDHUBER J．Long shortterm memory[J]．Neural computation,１９９７,９(８):１７３５-１７８０．
[１３] KADU R S,AWARI G K,SAKHALE C N,et al．Formulation of mathematical model for the investigation of tool wears in boring machining operation on cast iron using carbide and CBN tools[J]．Procedia materials science,２０１４,６:１７１０-１７２４．

相似文献/References:

[1]李鸿奎,程昭龙,周 蕾,等.智能变电站设备管控大数据分析系统研究[J].机械与电子,2020,(10):72.
　LI Hongkui,CHENG Zhaolong,ZHOU Lei,et al.Big Data Analysis System of Intelligent Substation Equipment Management and Control[J].Machinery & Electronics,2020,(05):72.

备注/Memo

备注/Memo:
收稿日期:２０２０-１０-２８
基金项目:上海市人工智能创新发展专项(２０１９-RGZN-０１０２６)
作者简介:李 鹏(１９９６－),男,安徽阜阳人,硕士研究生,研究方向为数控机床智能监测;黄亦翔(１９８０－),男,上海人,博士,副研究员,研究方向为机电系统智能维护,通信作者.
更新日期/Last Update: 2021-05-25