Tool Wear Online Recognition Method Based on Multi-source Synchronous Signals and Deep Learning

doi:10.3969/j.issn.1004-132X.2021.20.011

Abstract

Abstract: To improve the practicability of the tool condition monitoring systems and avoid signal interference caused by operation changes in the actual machining processes, a tool wear online recognition method was proposed based on multi-source synchronous signals and deep learning. The proposed method leveraged the automatic triggering to achieve the synchronous online collection of multi-source signals, i.e., tool vibration, spindle power, and CNC system parameters while the machine tool was running in a specific process. The synchronization of the collected signals might be ensured and the signal fluctuation interference caused by operation changes might be also avoided. Moreover, high-frequency vibration characteristics were employed to achieve the accurate division of samples collected during the “cutting process” and the “cutting interval”, and the Pearson correlation coefficient was utilized to extract the highly correlated features, guaranteeing the availability of the multi-source signal fusion samples. Finally, a tool wear online recognition model was established based on the one-dimensional convolutional neural network. The experimental results indicate that the proposed method fulfills the requirements of online recognition of tool wear in the actual machining processes in terms of recognition accuracy and diagnostic efficiency.

Key words: tool wear, multi-source synchronous signal, deep learning, online recognition

摘要： 为提高刀具状态监测系统的实用性、避免实际加工过程中工序变换产生的信号干扰，提出一种基于多源同步信号与深度学习的刀具磨损在线识别方法。该方法利用自动触发的方式实现了机床运行在特定工序时的刀具振动、主轴功率、数控系统参数等多源信号的同步在线采集，保证信号同步性的同时有效避免了因工序变换而产生的信号波动干扰；进一步利用高频振动特征实现了 “切削过程”与“切削间隙”采集样本的准确划分，并基于皮尔逊积矩相关系数筛选出强关联特征，保证了多源监测信号融合样本的可用性；最后基于一维卷积神经网络建立了刀具磨损在线识别模型。实验结果表明，该方法无论从识别精度还是诊断效率，均能实现实际加工过程中刀具磨损状态的在线识别。

关键词: 刀具磨损, 多源同步信号, 深度学习, 在线识别

CLC Number:

TH17

YIN Chen, ZHOU Shichao, HE Jianliang, SUN Yuxin, WANG Yulin. Tool Wear Online Recognition Method Based on Multi-source Synchronous Signals and Deep Learning[J]. China Mechanical Engineering, 2021, 32(20): 2482-2491.

尹晨, 周世超, 何建樑, 孙宇昕, 王禹林. 基于多源同步信号与深度学习的刀具磨损在线识别方法[J]. 中国机械工程, 2021, 32(20): 2482-2491.

References

［1］李亚, 黄亦翔, 赵路杰,等. 基于t分布邻域嵌入与XGBoost的刀具多工况磨损评估［J］. 机械工程学报, 2020, 56(1):132-140.
LI Ya, HUANG Yixiang, ZHAO Lujie, et al. Multi-condition Wear Evaluation of Tool Based on T-SNE and XGBoost［J］. Journal of Mechanical Engineering, 2020,56(1):132-140.
［2］刘建春, 江骏杰, 邹朝圣. 基于机器视觉的立铣刀磨损检测方法研究［J］. 制造技术与机床, 2020(1):136-140.
LIU Jianchun, JIANG Junjie, ZOU Chaosheng. Research on Wear Detection Method of Endmill Based on Machine Vision ［J］. Manufacturing Technology & Machine Tool, 2020(1):136-140.
［3］刘今越, 刘佳斌, 贾晓辉, 等. 基于面结构光投影法的刀具几何参数测量研究［J］.仪器仪表学报, 2017, 38(5):1276-1284.
LIU Jinyue, LIU Jiabin, JIA Xiaohui, et al. Research on Tool Geometry Parameter Measurement Based Onsurface Structured Light Projection［J］. Chinese Journal of Scientific Instrument, 2017, 38(5):1276-1284.
［4］张吉林. 基于机器视觉的铣削刀具磨损监测技术研究［D］. 南京:南京航空航天大学,2013.
ZHANG Jilin. Research on Tool Wear Monitoring Based on Machine Vision in NC Milling Process［D］. Nanjing:Nanjing University of Aeronautics and Astronautics, 2013.
［5］LI L， AN Q. An In-depth Study of Tool Wear Monitoring Technique Based on Image Segmentation and Texture Analysis ［J］. Measurement, 2016, 79(2):44-52.
［6］李威霖, 傅攀, 张尔卿. 基于粒子群优化LS-SVM的车刀磨损量识别技术研究［J］. 计算机应用研究, 2014, 31(4):1094-1101.
LI Weilin, FU Pan, ZHANG Eeqin. Application of Particle Swarm Optimization-least Square Support Vector Machine in Tool Wear Monitoring［J］. Application Research of Computers, 2014, 31(4):1094-1101.
［7］刘路, 王太勇, 蒋永翔,等. 基于超球面支持向量机的刀具磨损状态识别［J］. 农业机械学报, 2011, 42(1):218-222.
LIU Lu, WANG Taiyong, JIANG Yongxiang, et al. Tool Wear State Recognition Based on Hyper-sphere Support Vector Machine［J］. Transactions of the Chinese Society for Agricultural Machinery, 2011, 42(1):218-222.
［8］孙惠斌, 牛伟龙, 王俊阳. 基于希尔伯特黄变换的刀具磨损特征提取［J］. 振动与冲击, 2015, 34(4):158-164.
SUN Huibin, NIU Weilong, WANG Junyang. Tool Wear Feature Extraction Based on Hilbert-Huang Transformation［J］. Journal of Vibration and Shock, 2015, 34(4):158-164.
［9］关山, 闫丽红, 彭昶. LS-SVM回归算法在刀具磨损量预测中的应用［J］.中国机械工程,2015,26(2):217-222.
GUAN Shan, YAN Lihong, PENG Chang. Application of Regression Algorithm of LS-SVM in Tool Wear Prediction［J］. China Mechanical Engineering, 2015, 26(2):217-222.
［10］关山, 石志标, 刘炎. 基于多特征融合的刀具磨损识别方法［J］. 振动.测试与诊断,2014,34(3):576-584.
GUAN Shan, SHI Zhibiao, LIU Yan. Identification Method of Tool Wear Based on Multi-Feature Fusion［J］. Journal of Vibration Measurement & Diagnosis, 2014, 34(3):576-584.
［11］张锴锋, 袁惠群, 聂鹏. 基于广义分形维数的刀具磨损状态监测［J］. 振动与冲击, 2014, 33(1):162-164.
ZHANG Kaifeng, YUAN Huiqun, NIE Peng. Tool Wear Condition Monitoring Based on Generalized Fractal Dimensions［J］. Journal of Vibration and Shock, 2014, 33(1):162-164.
［12］王民, 刘利明, 宋铠钰, 等. 基于主轴驱动电流杂波的立铣刀复杂工况下磨损状态辨识［J/OL］.计算机集成制造系统:1-15.(2020-06-23). https://kns.cnki.net/kcms/detail/11.5946.TP.20200623.1439.030.html.
WANG Min, LIU Liming, SONG Kaiyu, et al. Wear Status Identification of End Milling Cutter under Complex Cutting Conditions Based on Clutter Signal of Spindle Current［J/OL］. Computer Integrated Manufacturing Systems. (2020-06-23). https://kns.cnki.net/kcms/detail/11.5946.TP.20200623.1439.030.html.
［13］谢楠, 马飞, 段明雷,等. 基于主成分分析与C-支持向量机的刀具磨损状态监测［J］. 同济大学学报(自然科学版), 2016, 44(3):434-439.
XIE Nan, MA Fei, DUAN Minglei, et al. Tool Wear Condition Monitoring Based on Principal Component Analysis and C-Support Vector Machine［J］. Journal of Tongji University (Natural Science), 2016, 44(3):434-439.
［14］MADHUSUDANA C K, GANGADHAR N, KUMAR H, et al. Use of Discrete Wavelet Features and Support Vector Machine for Fault Diagnosis of Face Milling Tool［J］. Structural Durability and Health Monitoring, 2018, 12(2):97-113.
［15］TOBON-MEJIA D A, MEDJAHER K, ZERHOUNI N. CNC Machine Tools Wear Diagnostic and Prognostic by Using Dynamic Bayesian Networks［J］. Mechanical Systems and Signal Processing, 2012, 28:167-182.
［16］张栋梁, 莫蓉, 孙惠斌, 等. 基于混沌时序分析方法与支持向量机的刀具磨损状态识别［J］. 计算机集成制造系统,2015, 21(8):2138-2146.
ZHANG Dongliang, MO Rong, SUN Huibin, et al. Tool Wearstate Recognition Based on Chaotic Time Series Analysis and Support Vector Machine［J］. Computer Integrated Manufacturing Systems, 2015, 21(8):2138-2146.
［17］陈志强, 陈旭东, de Olivira J V, 等. 深度学习在设备故障预测与健康管理中的应用［J］. 仪器仪表学报, 2019, 40(9):206-226.
CHEN Zhiqiang, CHEN Xudong, de OLIVIRA J V, et al. Application of Deep Learning in Equipment Prognostics and Health Management［J］. Chinese Journal of Scientific Instrument, 2019, 40(9):206-226.
［18］HINTON G E, SALAKHUTDINOV R R. Reducing the Dimensionality of Data with Neural Networks［J］. Science, 2006, 313:504-507.
［19］LECUN Y, BENGIO Y, HINTON G. Deep learning［J］. Nature, 2015, 521:436-444.
［20］CAO X C, CHEN B Q, YAO B, et al. Combining Translation-invariant Wavelet Frames and Convolutional Neuralnetwork for Intelligent Tool Wear State Identification［J］. Computers in Industry, 2019, 106:71-84.
［21］DOU J, XU C, JIAO S, et al. An Unsupervised Online Monitoring Method for Tool Wear Using a Sparse Auto-encoder［J］. The International Journal of Advanced Manufacturing Technology, 2020, 106(5):2493-2507.
［22］SOUALHI M, NGUYEN K T P, MEDJAHER K. Pattern Recognition Method of Fault Diagnostics Based on a New Health Indicator for Smart Manufacturing［J］. Mechanical Systems and Signal Processing, 2020, 142:106680.
［23］CAI W, ZHANG W, HU X, et al. A Hybrid Information Model Based on Long Short-term Memory Network for Tool Condition Monitoring［J］. Journal of Intelligent Manufacturing, 2020, 31:1-14.
［24］高宏力, 许明恒, 李登万, 等. 基于PCA和动态监测模型的刀具寿命在线检测技术［J］. 仪器仪表学报, 2010, 31(11):2416-2421.
GAO Hongli, XU Mingheng, LI Dengwan, et al. On-line Tool Life Measurement Technique Based on PCA and Dynamic Monitoring Model［J］. Chinese Journal of Scientific Instrument ,2010,31(11):2416-2421.
［25］何彦,凌俊杰,王禹林,等.基于长短时记忆卷积神经网络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. In-process Tool Wear Monitoring Model Based on LSTM-CNN［J］. China Mechanical Engineering, 2020, 31(16):1959-1967.
［26］卢志远, 马鹏飞, 肖江林,等. 基于机床信息的加工过程刀具磨损状态在线监测［J］. 中国机械工程, 2019, 30(2):220-225.
LU Zhiyuan, MA Pengfei, XIAO Jianglin, et al. On-line Monitoring of Tool Wear Conditions in Machining Processes Based on Machine Tool Data［J］. China Mechanical Engineering, 2019, 30(2):220-225.

[1]	ZHAO Zhihong, LI Lehao, YANG Shaopu, LI Qing. A Frequency Domain Feature Extraction Auto-encoder and Its Applications on Fault Diagnosis [J]. China Mechanical Engineering, 2021, 32(20): 2468-2474.
[2]	YU Haoshuai, TANG Baoping, ZHANG Kai, TAN Qian, WEI Jing. Fault Diagnosis Method of Wind Turbine Gearboxes Mixed with Attention Prototype Networks under Small Samples [J]. China Mechanical Engineering, 2021, 32(20): 2475-2481.
[3]	DAI Wen1;ZHANG Chaoyong1;MENG Leilei1;XUE Yanshe1;XIAO Pengfei1;YIN Yong2. Prediction Model of Milling Cutter Wear Status Based on Deep Learning [J]. China Mechanical Engineering, 2020, 31(17): 2071-2078.
[4]	HE Yan1;LING Junjie1;WANG Yulin2;LI Yufeng1;WU Pengcheng1;XIAO Zhen1. In-process Tool Wear Monitoring Model Based on LSTM-CNN [J]. China Mechanical Engineering, 2020, 31(16): 1959-1967.
[5]	LI Yousheng. Influences of TaC(NbC) on Cemented Carbide Tool Wear Resistance in High Speed Milling [J]. China Mechanical Engineering, 2020, 31(13): 1601-1605.
[6]	DING Hua, YANG Liangliang, YANG Zhaojian, WANG Yiliang, . Health Prediction of Shearers Driven by Digital Twin and Deep Learning [J]. China Mechanical Engineering, 2020, 31(07): 815-823.
[7]	LIU Peilei;YANG Shiqiang;BAI Lele;LI Zhuo;LI Dexin. Wear Model of Disc Hob Cutter Rings Based on Abrasive Wear [J]. China Mechanical Engineering, 2019, 30(15): 1782-1789.
[8]	LU Zhiyuan, MA Pengfei, XIAO Jianglin, WANG Meiqing, TANG Xiaoqing. On-line Monitoring of Tool Wear Conditions in Machining Processes Based on Machine Tool Data [J]. China Mechanical Engineering, 2019, 30(02): 220-225.
[9]	WANG Lihua1;YANG Jiawei1;ZHANG Yonghong1;ZHAO Xiaoping2;XIE Yangyang1. Tool Wear Condition Recognition Based on SDAE [J]. China Mechanical Engineering, 2018, 29(17): 2038-2045.
[10]	XIAO Pengfei1;ZHANG Chaoyong1;LUO Min1;LIN Wenwen2. Modeling Method for Tool Wear Prediction Based on ADNLSSVM [J]. China Mechanical Engineering, 2018, 29(07): 842-849.
[11]	DONG Caiyun1;ZHANG Chaoyong1;MENG Leilei1;XIAO Pengfei1;LUO Min2;LIN Wenwen3. State Recognition of Milling Tool Wears Based on Harmonic Wavelet Packet and BSA Optimization LS-SVM [J]. China Mechanical Engineering, 2017, 28(17): 2080-2089,2108.
[12]	SHI PeimingLIANG KaiZHAO NaAN Shujun. Intelligent Fault Diagnosis for Gears Based on Deep Learning Feature Extraction and Particle Swarm Optimization SVM State Identification [J]. China Mechanical Engineering, 2017, 28(09): 1056-1061,1068.
[13]	Gao Yanfeng, Xiao Jianhua. Characteristics of Cutting Tool Wear during LAM Processes for Ti-6Al-4V Alloy [J]. China Mechanical Engineering, 2016, 27(21): 2877-2883.
[14]	Huan Haixiang, , Xu Jiuhua, Su Honghua, Fu Yucan, Liang Xinghui, Ge Yingfei. Study on Tool Wear Characteristics during Turning Titanium Matrix Composite Using PCD and Carbide Tools [J]. China Mechanical Engineering, 2016, 27(14): 1877-1883.
[15]	Wu Haibing, Zuo Dunwen, Sun Quanping, Xu Feng. Tool Wear in ZrO2 Bioceramic Milling Processes [J]. China Mechanical Engineering, 2015, 26(7): 960-964,993.