变工况下磨削振纹的深度迁移智能辨识方法

doi:10.3901/JME.2023.16.128

机械工程学报 ›› 2023, Vol. 59 ›› Issue (16): 128-136.doi: 10.3901/JME.2023.16.128

扫码分享

变工况下磨削振纹的深度迁移智能辨识方法

刘佳宁¹, 曹宏瑞¹, 闫鹏辉², 姬汶辰²

1. 西安交通大学机械制造系统工程国家重点实验室西安 710049;
2. 陕西法士特汽车传动集团有限责任公司西安 710049

收稿日期:2022-08-26 修回日期:2022-12-05 出版日期:2023-08-20 发布日期:2023-11-15
通讯作者: 曹宏瑞(通信作者),男,1982年出生,博士,教授,博士研究生导师。主要研究方向为机械设备动力学建模与故障诊断。E-mail:chr@mail.xjtu.edu.cn
作者简介:刘佳宁,女,1998年出生,博士研究生。主要研究方向为机械设备故障诊断。E-mail:liujianing032@stu.xjtu.edu.cn
基金资助:
国家重点研发计划资助项目(2018YFB2000502)。

Deep Transfer Learning Method and Its Application in Grinding Chatter Marks Identification under Variable Working Conditions

LIU Jianing¹, CAO Hongrui¹, YAN Penghui², JI Wenchen²

1. State Key Laboratory for Manufacturing Systems Engineering, Xi'an Jiaotong University, Xi'an 710049;
2. Shaanxi Fast Auto Drive Group Co., Ltd., Xi'an 710049

Received:2022-08-26 Revised:2022-12-05 Online:2023-08-20 Published:2023-11-15

摘要/Abstract

摘要： 磨削振纹是磨削加工过程中常见的缺陷之一,直接影响零件的表面质量和加工精度,对磨削振纹进行在线监测、智能辨识并及时采取措施具有十分重要的意义。然而实际加工过程中磨削工况多变,数据分布特征存在差异,传统的机器学习方法均以训练数据和测试数据具有相同的分布为前提,将不再适用。针对这一问题,提出变工况下磨削振纹的深度迁移智能辨识方法。首先根据磨削振动信号的特征频率建立基于边频带特征频率的振纹在线监测指标,并对典型工况下的磨削振动信号进行分析以获取源域样本标签信息。然后在此基础上构建基于加权最大均值差异算法的领域自适应网络(Weighted maximum mean discrepancy based domain adaptation network,WDAN)以提取域不变特征。最后开展变工况试验验证网络的有效性,结果表明在磨削参数多变的情况下,该网络优于卷积神经网络以及其他常用领域自适应网络,能够有效提高振纹识别精度。

关键词: 磨削加工, 表面振纹识别, 变工况, 深度迁移学习

Abstract: Grinding chatter marks are one of the common defects in the grinding process, which directly affect the surface quality and machining accuracy of the parts. It is very important to monitor and identify the grinding status intelligently, and take timely measures.However, in actual machining process, the grinding conditions are variable, and the data distribution characteristics are different. The traditional machine learning methods are based on assumption that the training and testing data have the same distribution, thus will no longer be applicable. Aiming at this problem, a deep transfer learning method is proposed for grinding chatter marks identification under variable working conditions. First, an online monitoring indicator of grinding chatter marks is established based on the characteristic frequency of the sideband, and then the grinding vibration signals under the typical working conditions are analyzed with the indicator to obtain labels of source domain. On this basis, the weighted maximum mean discrepancy based domain adaptation network is proposed to extract domain-invariant features of the source and target domains. Finally, variable-condition experiments are carried out to verify the effectiveness of the method. The results show that the method is superior to convolutional neural networks and other commonly used domain adaptation methods, which can effectively improve the accuracy of grinding chatter marks identification.

Key words: grinding, chatter marks identification, variable working conditions, deep transfer learning

中图分类号:

TG156

刘佳宁, 曹宏瑞, 闫鹏辉, 姬汶辰. 变工况下磨削振纹的深度迁移智能辨识方法[J]. 机械工程学报, 2023, 59(16): 128-136.

LIU Jianing, CAO Hongrui, YAN Penghui, JI Wenchen. Deep Transfer Learning Method and Its Application in Grinding Chatter Marks Identification under Variable Working Conditions[J]. Journal of Mechanical Engineering, 2023, 59(16): 128-136.

参考文献

[1] 苏建新,蒋闯,聂少武,等.内齿轮成形磨削砂轮架振动特性实验研究[J].振动与冲击,2021,40(14):100-107.SU Jianxin, JIANG Chuang, NIE Shaowu, et al.Experimental study on the vibration characteristics of a grinding-wheel-rack for internal gear form grinding[J].Journal of Vibration and Shock,2021,40(14):100-107.
[2] 刘永平,吴序堂,李鹤岐.数控锥面砂轮磨齿机磨削椭圆齿轮[J].机械工程学报,2006,42(12):70-75.LIU Yongping, WU Xutang, LI Heqi. Grinding of elliptical gears with cnc conical wheel gear grinding machine[J]. Journal of Mechanical Engineering,2006,42(12):70-75.
[3] 郭辉,赵宁,项云飞,等.六轴数控蜗杆砂轮磨齿机磨削面齿轮的方法[J].机械工程学报,2015,51(11):186-194.GUO Hui,ZHAO Ning,XIANG Yunfei,et al. Face gear grinding method using six-axis CNC worm wheel machine[J]. Journal of Mechanical Engineering,2015,51(11):186-194.
[4] 李国龙,刘鹏祥,周泓曲,等.面向降噪的蜗杆砂轮磨削齿面纹理改善方法[J].机械工程学报,2017,53(23):182-189.LI Guolong,LIU Pengxiang,ZHOU Hongqu,et al.Continuous generating grinding tooth surface texture improvement method for noise reduction[J]. Journal of Mechanical Engineering,2017,53(23):182-189.
[5] 王庆军,何彦杰,孙熙钊.轧机工作辊磨削振纹检测与控制[J].大型铸锻件,2021,1(2):52-54.WANG Qingjun,HE Yanjie,SUN Xizhao. Measurement and control of grinding chatter marks on working rolls of rolling mill[J]. Heavy Casting and Forging,2021,1(2):52-54.
[6] ZHEN Wang,PETER W,PAULO R,et al. Neural network detection of grinding burn from acoustic emission[J]. International Journal of Machine Tools and Manufacture,2001,41(2):283-309.
[7] MAHATA S,SHAKYA P,BABU N R. A robust condition monitoring methodology for grinding wheel wear identification using Hilbert Huang transform[J]. Precision Engineering,2021,70:77-91.
[8] YANG Zhensheng,YU Zhonghua. Experimental study of burn classification and prediction using indirect method in surface grinding of AISI 1045 steel[J]. The International Journal of Advanced Manufacturing Technology,2013,68(9-12):2439-2449.
[9] GUO Weicheng,LI Beizhi,SHEN Shouguo,et al. An intelligent grinding burn detection system based on two-stage feature selection and stacked sparse autoencoder[J]. The International Journal of Advanced Manufacturing Technology,2019,103(5):2837-2847.
[10] 邵海东,张笑阳,程军圣,等.基于提升深度迁移自动编码器的轴承智能故障诊断[J].机械工程学报,2020,56(9):84-90.SHAO Haidong,ZHANG Xiaoyang,CHENG Junsheng,et al. Intelligent fault diagnosis of bearing using enhanced deep transfer auto-encoder[J]. Journal of Mechanical Engineering,2020,56(9):84-90.
[11] 吴静然,刘建华,崔冉.子域适应无监督轴承故障诊断[J].振动与冲击,2021,40(15):34-40.WU Jingran,LIU Jianhua,CUI Ran. Sub-domain adaptive unsupervised bearing fault diagnosis[J]. Journal of Vibration and Shock,2021,40(15):34-40.
[12] 沈飞,陈超,严如强.奇异值分解与迁移学习在电机故障诊断中的应用[J].振动工程学报,2017,30(1):118-126.SHEN Fei,CHEN Chao,YAN Ruqiang. Application of SVD and transfer learning strategy on motorfault diagnosis[J]. Journal of Vibration Engineering,2017,30(1):118-126.
[13] 雷亚国,杨彬,杜兆钧,等.大数据下机械装备故障的深度迁移诊断方法[J].机械工程学报,2019,55(7):1-8.LEI Yaguo,YANG Bin,DU Zhaojun,et al. Deep transfer diagnosis method for machinery in big data era[J]. Journal of Mechanical Engineering,2019,55(7):1-8.
[14] LIU Han, ZHOU Jianzhong, XU Yanhe, et al.Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks[J]. Neurocomputing,2018,315(1):412-424.
[15] 陈祝云,钟琪,黄如意,等.基于增强迁移卷积神经网络的机械智能故障诊断[J].机械工程学报,2021,57(12):96-105.CHEN Zhuyun,ZHONG Qi,HUANG Ruyi,et al.Intelligent fault diagnosis for machinery based on enhanced transfer convolutional neural network[J].Journal of Mechanical Engineering,2021,57(12):96-105.
[16] TZENG E,HOFFMAN J,ZHANG N,et al. Deep domain confusion:maximizing for domain invariance[EB/OL].[2014-12-10]. https://arxiv.org/abs/1412.3474.
[17] LONG Mingsheng,CAO Yue,WANG Jianmin,et al.Learning transferable features with deep adaptation networks[C]//International Conference on Machine Learning. PMLR,2015:97-105.
[18] ZHU Yongchun,ZHUANG Fuzhen,WANG Jindong,et al. Deep subdomain adaptation network for image classification[J]. IEEE Transactions on Neural Networks and Learning Systems,2020,32(4):1713-1722.
[19] MAATEN L,HINTON G. Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9(11):2579-2605.

变工况下磨削振纹的深度迁移智能辨识方法

Deep Transfer Learning Method and Its Application in Grinding Chatter Marks Identification under Variable Working Conditions

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

本文评价

[1]	黄功瑞, 朱阳历, 熊军, 王星, 李文, 陈海生. 轴流涡轮长叶片级变工况特性研究综述[J]. 机械工程学报, 2024, 60(8): 271-290.
[2]	杨阳, 胡明辉, 江志农, 卢子元. 多分量同步提取变换驱动的无键相状态下中介轴承故障诊断[J]. 机械工程学报, 2024, 60(16): 83-97.
[3]	宰红斌, 刘建国, 张文岗, 封士永, 祖国强. 基于深度迁移学习的配电线路绝缘子状态监测方法^*[J]. 电气工程学报, 2022, 17(4): 275-281.
[4]	卢守相, 杨秀轩, 张建秋, 周聪, 殷景飞, 张璧. 关于硬脆材料去除机理与加工损伤的理性思考[J]. 机械工程学报, 2022, 58(15): 31-45.
[5]	雷亚国, 杨彬, 李乃鹏, 李响, 武通海. 跨设备的机械故障靶向迁移诊断方法[J]. 机械工程学报, 2022, 58(12): 1-9.
[6]	张浩峰, 胥建群, 孙友源, 黄喜军, 陈晓欣, 皇甫泽玉, 周丽丽. 汽轮机调节阀和调节级特性建模与配汽优化[J]. 机械工程学报, 2019, 55(18): 165-172.
[7]	丁文锋, 苗情, 李本凯, 徐九华. 面向航空发动机的镍基合金磨削技术研究进展[J]. 机械工程学报, 2019, 55(1): 189-215.
[8]	吴其林, 赵韩, 邱明明，黄康. 微线段齿轮磨削加工方法及性能分析[J]. 机械工程学报, 2017, 53(13): 179-187.
[9]	王婷, 谷波, 钱程, 马洪涛. 车用小通道平行流换热器传热流动试验与分析[J]. 机械工程学报, 2016, 52(4): 141-147.
[10]	郭隐彪;杨炜;王振忠;彭云峰;毕果;杨平. 大口径光学元件超精密加工技术与应用[J]. , 2013, 49(19): 171-178.
[11]	马育林;吴青;张蕊;叶蕾;严新平. 模拟自治车队行驶过程变工况速度跟踪控制[J]. , 2011, 47(7): 140-147.
[12]	孙月海;卢华武;王树人. 磨削TI蜗杆的砂轮廓形[J]. , 2008, 44(2): 170-174.
[13]	陈明君;赵清亮;董申;李旦. 基于双圆弧步长伸缩数控插补非圆曲线算法的研究?[J]. , 2003, 39(1): 111-116.
[14]	陈明君;董申;李旦;张飞虎. 脆性材料超精密磨削时影响表面质量因素的研究[J]. , 2001, 37(3): 1-4，10.