A Multi Class Domain Adaptive Transfer Identification Method for Tool Wear States under Different Processing Conditions

doi:10.3969/j.issn.1004-132X.2022.15.010

Abstract

Abstract: Under the new processing conditions， aiming at the problems of low identification accuracy rate of tool wear identification model trained under historical processing conditions， a tool wear state identification model across processing conditions was proposed based on transfer learning. Firstly， convolutional neural network was constructed to extract the transfer features of tool samples， and the difference of tool sample distributions was measured by the maximum mean difference under different processing conditions. Secondly， the sample distance of source domain features was improved by IDC. The strategy of maximizing the norm was adopted for the probability matrix of target data to extract the fault features of target domain samples with high discrimination. Finally， the milling cutter machining tests were taken as an example to verify the validity of the model. The average identification accuracy rate of the model is as 96.8%， which is as 4.9% higher than that of the method without IDC and maximum kernel norm.

Key words: , tool wear, processing condition, transfer state identification, inter-class-intra-class distance constraint（IDC）, maximizing kernel norm

摘要： 在新的工艺条件下，针对采用历史工艺条件进行训练的刀具磨损状态辨识模型识别准确率低的问题，提出了一种基于迁移学习的跨工艺条件刀具磨损状态辨识模型。构建卷积神经网络提取刀具样本可迁移特征，利用最大均值差异测量不同工艺条件下刀具样本分布差异，通过类间-类内距离约束提升源域特征的样本距离，对目标域数据概率矩阵采取最大化核范数的策略，以提取区分性高的目标域样本故障特征。以铣刀加工试验为例验证了模型的有效性，模型的平均辨识准确率为96.8%，比没有类间-类内距离约束与最大化核范数的方法平均辨识准确率提升4.9%。

关键词: 刀具磨损, 工艺条件, 迁移状态辨识, 类间-类内距离约束, 最大化核范数

CLC Number:

TP206.3

SHI Keming, ZOU Yisheng, LIU Yongzhi, DING Kun, DING Guofu. A Multi Class Domain Adaptive Transfer Identification Method for Tool Wear States under Different Processing Conditions[J]. China Mechanical Engineering, 2022, 33(15): 1841-1849.

史珂铭, 邹益胜, 刘永志, 丁昆, 丁国富. 一种不同工艺条件下刀具磨损状态多类域适应迁移辨识方法[J]. 中国机械工程, 2022, 33(15): 1841-1849.

References

［1］LI Weijian， LIU Tongshun. Time Varying and Condition Adaptive Hidden Markov Model for Tool Wear State Estimation and Remaining Useful Life Prediction in Micro-milling［J］. Mechanical Systems and Signal Processing， 2019， 131：689-702.
［2］PATANGEA D， JEGADEESHWARAN R. Review on Tool Condition Classification in Milling：a Machine Learning Approach［J］. Materials Today：Proceedings， 2021， 46：1106-1115.
［3］刘献礼，李雪冰，丁明娜，等. 面向智能制造的刀具全生命周期智能管控技术［J］. 机械工程学报， 2021， 57（10）：196-219.
LIU Xianli， LI Xuebing， DING Mingna， et al. Intelligent Management and Control Technology of Cutting Tool Life-cycle for Intelligent Manufacturing［J］. Journal of Mechanical Engineering， 2021， 57（10）：196-219.
［4］何彦，凌俊杰，王禹林，等. 基于LSTM-CNN的刀具磨损在线监测模型［J］. 中国机械工程， 2020， 31（16）：1959-1967.
HE Yan， LING Junjie， WANG Yulin， et al. Online Tool Wear Monitoring Model Based on LSTM-CNN［J］. China Mechanical Engineering， 2020， 31（16）：1959-1967.
［5］陈启鹏，谢庆生，袁庆霓，等. 基于深度门控循环单元神经网络的刀具磨损状态实时监测方法［J］. 计算机集成制造系统， 2020， 26（7）：1782-1793.
CHEN Qipeng， XIE Qingsheng， YUAN Qingni， et al. Real Time Monitoring Method of Tool Wear State Based on Deep Gating Cycle Unit Neural Network［J］. Computer Integrated Manufacturing Systems， 2020， 26（7）：1782-1793.
［6］WANG Yongqing， QIN Bo， LIU Kuo， et al. A New Multi-Task Learning Method for Tool Wear Condition and Part Surface Quality Prediction［J］. IEEE Transactions on Industrial Informatics， 2021， 17（9）：6023-6033.
［7］WEN Yandong， ZHANG Kaipeng， LI Zhifeng， et al. A Discriminative Feature Learning Approach for Deep Face Recognition［C］∥ European Conference on Computer Vision. Amsterdam， 2016：499-515.
［8］ZHU Yongchun， ZHUANG Fuzhen， WANG Jindong， et al. Deep Subdomain Adaptation Network for Image Classification［J］. IEEE Transactions on Neural Networks and Learning Systems， 2021， 32（4）：1713-1722.
［9］CHEN Xinyang， WANG Sinan， LONG Mingsheng， et al. Transferability vs. Discriminability：Batch Spectral Penalization for Adversarial Domain Adaptation［C］∥ Proceedings of the 36th International Conference on Machine Learning. Long Beach， 2019：1081-1090.
［10］CHEN Chao， FU Zhihang， CHEN Zhihong， et al. HoMM：Higher-order Moment Matching for Unsupervised Domain Adaptation［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2020， 34（4）：3422-3429.
［11］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.
［12］KUREK J， WIECZOREK G， KRUK B， et al. Transfer Learning in Recognition of Drill Wear Using Convolutional Neural Network［C］∥ 2017 18th International Conferenceon Computational Problems of Electrical Engineering（CPEE）. Kutna Hora， 2017：17335147.
［13］陈仁祥，吴志元，胡小林，等. 深度特征联合匹配的不同刀具间磨损状态识别［J］. 仪器仪表学报， 2020， 41（12）：138-145.
CHEN Renxiang， WU Zhiyuan， HU Xiaolin， et al. Wear State Recognition of Different Cutting Tools Based on Joint Matching of Depth Features［J］. Chinese Journal of Scientific Instrument， 2020， 41（12）：138-145.
［14］WANG Yu， SUN Xiaojie， LI Jie， et al. Intelligent Fault Diagnosis with Deep Adversarial Domain Adaptation［J］. IEEE Transactions on Instrumentation and Measurement， 2020， 70：2503509.
［15］ZOU Yisheng， LIU Yongzhi， DENG Jialin， et al. A Novel Transfer Learning Method for Bearing Fault Diagnosis under Different Working Conditions［J］. Measurement， 2021， 171：108767.
［16］GRETTON A， BORGWARDT K M， RASCH M J， et al. A Kernel Method for the Two-sample-problem［M］∥SCHLKOPF B， PLATT J， HOFMANN T， et al. Advances in Neural Information Processing Systems 19：Proceedings of the 2006 Conference. Cambridge：MIT Press， 2007：513-520.
［17］CUI Shuhao， WANG Shuhui， ZHUO Junbao， et al. Towards Discriminability and Diversity：Batch Nuclear-norm Maximization under Label Insufficient Situations［C］∥ 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）. Seattle， 2020：3940-3949. ［18］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.
DAI Wen， ZHANG Chaoyong， MENG Leilei， et al. Prediction Model of Milling Cutter Wear State Based on Deep Learning［J］. China Mechanical Engineering， 2020， 31（17）：2071-2078.
［19］GUO Liang， LEI Yaguo， XING Saibo， et al. Deep Convolutional Transfer Learning Network：a New Method for Intelligent Fault Diagnosis of Machines with Unlabeled Data［J］. IEEE Transactions on Industrial Electronics， 2019， 66（9）：7316-7325.
［20］LAURENS V. Accelerating t-SNE Using Tree-Based Algorithms［J］. Journal of Machine Learning Research， 2014， 15（1）：3221-3245.

[1]	ZHANG Rongshen, WANG Yutian, HU Rongquan, YANG Lingfang, HUANG Zhi. Avoidance Planning for Intelligent Vehicles in Dilemma Based on Nominal Cost [J]. China Mechanical Engineering, 2022, 33(15): 1849-1856.
[2]	ZHANG Wenjun, ZHANG Yandong, LIN Wei, ZHAI Qianjun, BAI Zhenhua, . Research on Influence Model and Influence Factors of Welding Quality of Continuous Annealing Units [J]. China Mechanical Engineering, 2022, 33(15): 1876-1881.
[3]	ZHANG Xingui, SHI Xinglei, YU Zilin, ZHONG Zhenyuan, LI Jia. Drag Torque Algorithm of Wet DCT and Its ApplicationsLIU Bo [J]. China Mechanical Engineering, 2022, 33(15): 1882-1889.
[4]	XIE Zhijiang, CHENG Qing, DING Jun, HE Miao, FAN Naiji, WU Xiaoyong. Dimensional Design and Performance Analysis of a 6-DOF Parallel Manipulator with Two Limbs [J]. China Mechanical Engineering, 2022, 33(14): 1680-1690.
[5]	WEN Jiangtao, ZHANG Pengcheng, SUN Jiedi, LEI Ming. Unsupervised Transfer Learning with Residual Convolutional Autoencoder Networks for Bearing Fault Diagnosis [J]. China Mechanical Engineering, 2022, 33(14): 1707-1716.
[6]	LIU Siyuan, SONG Chaosheng, ZHU Caichao. Design Methodology and Mesh Characteristics of Face-milled Hypoid Gears with Low Crossed Shaft Angle [J]. China Mechanical Engineering, 2022, 33(13): 1521-1528,1536.
[7]	MING Xingzu, XIAO Yongbo, LIU Kefei, ZHOU Xian, ZHANG Haibo, MING Rui. Scanning Ablation Characteristic Control for Femtosecond Laser Finishing of Face Gears [J]. China Mechanical Engineering, 2022, 33(13): 1544-1550.
[8]	WANG Qiancheng, SU Chun, WEN Zejun. Multi-condition Monitoring and Fault Diagnosis of Wind Turbines Based on Cointegration Analysis [J]. China Mechanical Engineering, 2022, 33(13): 1596-1603.
[9]	LIAO Yihong, ZHANG Guiming, XU Jing. Influence Law and Mechanism of Texturized Controllable Interfaces on Leakage of Steam Turbine Regulating Valves [J]. China Mechanical Engineering, 2022, 33(12): 1427-1434.
[10]	LIANG Xingxin, ZHANG Sen, QI Shihuang, JIN Shuanbao. Experimental Study of Load Carrying Performance of Water Lubricated PCD Thrust Bearings for Rim Driven Thrusters [J]. China Mechanical Engineering, 2022, 33(12): 1452-1458，1467.
[11]	FAN Xin, REN Siming, WANG Haixin , PU Jibin. Environmental Adaptability and Tribological Properties of MoS2/WS2 Composite Films [J]. China Mechanical Engineering, 2022, 33(12): 1468-1476.
[12]	JIN Chao, QUAN Long, XIA Lianpeng, GE Lei, ZHAO Bin. Study and Optimization of Energy Storage Hydraulic Cylinders Synergistically Driving Heavy Manipulator Systems [J]. China Mechanical Engineering, 2022, 33(11): 1287-1293,1301.
[13]	LI Chong, TONG Yujian, LIANG Kang, ZHONG Wei, FANG Jiwen. Design and Experimental Study of Piezoelectric Actuated Micro Precision Clamping Mechanisms [J]. China Mechanical Engineering, 2022, 33(11): 1302-1308,1385.
[14]	JIANG Wanlu, LI Man, ZHANG Peiyao, ZHAO Yapeng, ZHANG Shuqing. Intelligent Fault Diagnosis Method for Rotating Equipment Based on Full Vector Enhanced Deep Forest [J]. China Mechanical Engineering, 2022, 33(11): 1324-1335.
[15]	ZHANG Ming, ZHI Pengpeng, HUO Wenbiao, LI Zhiyong. Research on Fracture Mechanism and Tests of Wheel Flange Lubrication Device Hangers for Metro Vehicles [J]. China Mechanical Engineering, 2022, 33(11): 1369-1376.