基于高斯过程潜力模型的刀具磨损预测

doi:10.3901/JME.2023.17.310

摘要/Abstract

摘要： 刀具磨损预测对于提高加工精度和生产效率具有重要意义。刀具磨损预测模型主要包括基于物理的模型和基于数据驱动的模型。基于物理的模型一般使用经验公式或简化公式对刀具磨损过程进行建模，在切削参数变化的情况下其预测精度通常会变低。另一方面，数据驱动模型通过测量数据来估计刀具磨损，没有考虑刀具磨损机理，导致模型泛化性和结果可解释性较差。为了解决这些问题，提出了一种新的用于刀具磨损预测的高斯过程潜力模型。所提出的模型使用高斯过程对刀具磨损物理模型的未知参数进行建模，建立了一个物理信息机器学习模型。高斯过程潜力模型不仅避免了物理模型的参数识别，而且挖掘了来自物理域和数据域的隐藏信息。此外，通过将物理模型与高斯过程的协方差函数相结合，构建了一个物理信息协方差函数来约束模型的输出，提高了预测精度。多工况试验结果表明，所提方法的绝对平均误差和均方根误差分别为2.594 5、3.740 8，比传统数据驱动模型的预测误差要更小，预测精度进一步提升。

关键词: 刀具磨损预测, 高斯过程, 潜力模型

Abstract: Tool wear prediction is of great significance for improving machining accuracy and production efficiency. Tool wear prediction models include physics-based models and data-driven models. The physics-based models often apply empirical or simplified formula to model the tool wear process which often loss prediction accuracy under changing cutting parameters. On the other side, the data-driven models estimate the tool wear by monitor data without considering the mechanisms of tool wear, resulting in low model generalization and results interpretation. To address these issues, a novel Gaussian process latent force model for tool wear prediction is proposed. The proposed model applies Gaussian process to model the unknown parameters of the tool wear physical model, and establishes a physics-informed machine learning model. The Gaussian process latent force model not only avoids identifying parameters in the physical model, but also explores hidden information from physics and data domains. Moreover, by integrating the physical model with the Gaussian process covariance function, a physics-informed covariance function is constructed to constrain the outputs of the model and improve the prediction accuracy. The multi-condition experiments results show that the mean absolute error and root mean square error of the proposed method are 2.5 945 and 3.7 408, respectively, which are smaller than the prediction error of the traditional data-driven models and further improve the prediction accuracy.

Key words: tool wear prediction, Gaussian process, latent force model

中图分类号:

TH165

刘洪成, 袁德志, 朱锟鹏. 基于高斯过程潜力模型的刀具磨损预测[J]. 机械工程学报, 2023, 59(17): 310-324.

LIU Hongcheng, YUAN Dezhi, ZHU Kunpeng. Tool Wear Prediction Based on Gaussian Process Latent Force Model[J]. Journal of Mechanical Engineering, 2023, 59(17): 310-324.

参考文献

[1] ULLAH I, ZHANG S,ZHANG Q,et al. Numerical investigation on serrated chip formation during high-speed milling of Ti-6Al-4V alloy[J]. Journal of Manufacturing Processes,2021,71:589-603.
[2] MOHANRAJ T,SHANKAR S,RAJASEKAR R,et al. Tool condition monitoring techniques in milling process-a review[J]. Journal of Materials Research and Technology,2020,9(1):1032-1042.
[3] LI B. A review of tool wear estimation using theoretical analysis and numerical simulation technologies[J]. International Journal of Refractory Metals and Hard Materials,2012,35:143-151.
[4] LI Y,LIU C,HUA J,et al. A novel method for accurately monitoring and predicting tool wear under varying cutting conditions based on meta-learning[J]. CIRP Annals,2019,68(1):487-490.
[5] ZHANG X,GAO Y,GUO Z,et al. Physical model-based tool wear and breakage monitoring in milling process[J]. Mechanical Systems and Signal Processing,2023,184:109641.
[6] ZHOU L,DENG B,PENG F,et al. Analytical modelling and experimental validation of micro-ball-end milling forces with progressive tool flank wear[J]. The International Journal of Advanced Manufacturing Technology,2020,108(9):3335-3349.
[7] HOU Y,ZHANG D,WU B,et al. Milling force modeling of worn tool and tool flank wear recognition in end milling[J]. IEEE/ASME Transactions on Mechatronics,2014,20(3):1024-1035.
[8] 史恺宁. 考虑刀具磨损的加工过程功耗模型及其应用研究[D]. 西安:西北工业大学,2018. SHI Kaining. Research on power consumption model and applications in machining process considering tool wear[D]. Xi'an:Northwestern Polytechnical University,2018.
[9] SHAO H,WANG H L,ZHAO X M. A cutting power model for tool wear monitoring in milling[J]. International Journal of Machine Tools and Manufacture,2004,44(14):1503-1509.
[10] HORMAN I,BUSULADŽIĆ I,AZEMOVIĆ E. Temperature influence on wear characteristics and blunting of the tool in continuous wood cutting process[J]. Procedia Engineering,2014,69:133-140.
[11] WANIGARATHNE P C,KARDEKAR A D,DILLON O W,et al. Progressive tool-wear in machining with coated grooved tools and its correlation with cutting temperature[J]. Wear,2005,259(7-12):1215-1224.
[12] LIU Y P,KILIC Z M,ALTINTAS Y. Monitoring of in-process force coefficients and tool wear[J]. CIRP Journal of Manufacturing Science and Technology,2022,38:105-119.
[13] LIU T,ZHU K,WANG G. Micro-milling tool wear monitoring under variable cutting parameters and runout using fast cutting force coefficient identification method[J]. The International Journal of Advanced Manufacturing Technology,2020,111(11):3175-3188.
[14] PÁLMAI Z. Proposal for a new theoretical model of the cutting tool's flank wear[J]. Wear,2013,303(1-2):437-445.
[15] TAYLOR F W. On the art of cutting metals[M]. New York:American Society of Mechanical Engineers,1906.
[16] YEN Y C,SÖHNER J,LILLY B,et al. Estimation of tool wear in orthogonal cutting using the finite element analysis[J]. Journal of Materials Processing Technology,2004,146(1):82-91.
[17] SIPOS Z. Investigation of cutting performance of coated HSS tools made in Hungary[J]. NME,Miskolc Egyetem,1986.
[18] LAAKSO S V A,JOHANSSON D. There is logic in logit including wear rate in Colding's tool wear model[J]. Procedia Manufacturing,2019,38:1066-1073.
[19] ZHU K,ZHANG Y. A generic tool wear model and its application to force modeling and wear monitoring in high speed milling[J]. Mechanical Systems and Signal Processing,2019,115:147-161.
[20] JAINI S N B,LEE D W,LEE S J,et al. Indirect tool monitoring in drilling based on gap sensor signal and multilayer perceptron feed forward neural network[J]. Journal of Intelligent Manufacturing,2021,32(6):1605-1619.
[21] WICIAK-PIKUŁA M,FELUSIAK-CZYRYCA A,TWARDOWSKI P. Tool wear prediction based on artificial neural network during aluminum matrix composite milling[J]. Sensors,2020,20(20):5798.
[22] KONG D,CHEN Y,LI N,et al. Tool wear monitoring based on kernel principal component analysis and v-support vector regression[J]. The International Journal of Advanced Manufacturing Technology,2017,89(1):175-190.
[23] GAO C,BINTAO S,WU H,et al. New tool wear estimation method of the milling process based on multisensor blind source separation[J]. Mathematical Problems in Engineering,2021,2021:1-11.
[24] ZHANG X,YU T,XU P,et al. In-process stochastic tool wear identification and its application to the improved cutting force modeling of micro milling[J]. Mechanical Systems and Signal Processing,2022,164:108233.
[25] JIA W,WANG W,LI Z,et al. Prediction of tool wear in sculpture surface by a new fusion method of temporal convolutional network and self-attention[J]. The International Journal of Advanced Manufacturing Technology,2022,121(3):2565-2583.
[26] KONG D,CHEN Y,LI N. Gaussian process regression for tool wear prediction[J]. Mechanical Systems and Signal Processing,2018,104:556-574.
[27] WU D,JENNINGS C,TERPENNY J,et al. A comparative study on machine learning algorithms for smart manufacturing:tool wear prediction using random forests[J]. Journal of Manufacturing Science and Engineering,2017,139(7):1-9.
[28] GUO H,LIN X,ZHU K. Pyramid LSTM network for tool condition monitoring[J]. IEEE Transactions on Instrumentation and Measurement,2022,71:1-11.
[29] HUANG Z,ZHU J,LEI J,et al. Tool wear predicting based on multi-domain feature fusion by deep convolutional neural network in milling operations[J]. Journal of Intelligent Manufacturing,2020,31(4):953-966.
[30] ZHANG C,WANG W,LI H. Tool wear prediction method based on symmetrized dot pattern and multi-covariance Gaussian process regression[J]. Measurement,2022,189:110466.
[31] HANACHI H,YU W,KIM I Y,et al. Hybrid data-driven physics-based model fusion framework for tool wear prediction[J]. The International Journal of Advanced Manufacturing Technology,2019,101(9):2861-2872.
[32] WANG J,LI Y,ZHAO R,et al. Physics guided neural network for machining tool wear prediction[J]. Journal of Manufacturing Systems,2020,57:298-310.
[33] ALVAREZ M A,LUENGO D,LAWRENCE N D. Linear latent force models using Gaussian processes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(11):2693-2705.
[34] WILLIAMS C K I,RASMUSSEN C E. Gaussian processes for machine learning[M]. Cambridge,MA:MIT Press,2006.
[35] NAYEK R,CHAKRABORTY S,NARASIMHAN S. A Gaussian process latent force model for joint input-state estimation in linear structural systems[J]. Mechanical Systems and Signal Processing,2019,128:497-530.
[36] HU X,LI Y,ZHAO Z,et al. Residual stresses field estimation based on deformation force data using Gaussian process latent variable model[J]. Procedia Manufacturing,2021,54:279-283.
[37] SUN Y,SUN J,LI J,et al. Modeling of cutting force under the tool flank wear effect in end milling Ti6Al4V with solid carbide tool[J]. The International Journal of Advanced Manufacturing Technology,2013,69(9):2545-2553.
[38] SONG W. Development of predictive force models for classical orthogonal and oblique cutting and turning operations incorporating tool flank wear effects[D]. Queensland University of Technology,2006.
[39] BUDAK E,ALTINTAS Y,ARMAREGO E J A. Prediction of milling force coefficients from orthogonal cutting data[J]. Journal of Manufacturing Science and Engineering,1996,118(2):216-224.
[40] ALTINTAS Y,BER A A. Manufacturing automation:metal cutting mechanics,machine tool vibrations,and CNC design[J]. Appl. Mech. Rev,2001,54(5):B84.
[41] 李科选. 微铣削加工铣削力建模及刀具磨损规律研究[D]. 合肥:中国科学技术大学,2016. LI Kexuan. Investigation on cutting force modeling and tool wear factor in micromilling[D]. Hefei:University of Science and Technology of China,2016.
[42] FARHADMANESH M,AHMADI K. Online identification of mechanistic milling force models[J]. Mechanical Systems and Signal Processing,2021,149:107318.