基于SFS-SVR的高速铣削刀具剩余使用寿命预测

doi:10.12068/j.issn.1005-3026.2023.06.009

东北大学学报（自然科学版） ›› 2023, Vol. 44 ›› Issue (6): 824-831.DOI: 10.12068/j.issn.1005-3026.2023.06.009

基于SFS-SVR的高速铣削刀具剩余使用寿命预测

黄贤振¹，孙良仕¹，高娓²，李禹雄¹

(1.东北大学机械工程与自动化学院，辽宁沈阳110819； 2.中国重汽集团济南卡车股份有限公司，山东济南250116)

发布日期:2023-06-20
通讯作者: 黄贤振
作者简介:黄贤振(1982-)，男，山东定陶人，东北大学教授，博士生导师.
基金资助:
国家自然科学基金资助项目(51975110).

Remaining Useful Life Prediction of Cutting Tools Based on SFS-SVR in High Speed Milling Operations

HUANG Xian-zhen¹， SUN Liang-shi¹， GAO Wei²， LI Yu-xiong¹

1. School of Mechanical Engineering & Automation， Northeastern University， Shenyang 110819， China； 2. China National Heavy Duty Truck Group Jinan Truck Co.， Ltd.， Jinan 250116， China.

Published:2023-06-20
Contact: HUANG Xian-zhen
About author:-
Supported by:
-

摘要/Abstract

摘要： 在高速铣削加工中，为了判断更换刀具的最佳时间，迫切地需要对刀具的剩余使用寿命进行准确地预测，但预测中常常会存在历史数据不足的问题.因此，本文提出了一种解决小样本空间的刀具剩余使用寿命预测方法.该方法基于支持向量回归(SVR)方法，通过随机分形搜索(SFS)算法优化模型中的关键参数.相比于传统方法，本文所采用的方法可获得更优的模型参数和更快的收敛速度.最后，将所采用的方法与隐马尔可夫模型(HMM)方法进行比较，平均精确度由0.6277提高至0.8199，为刀具的更换提供了可靠的参考.

关键词: 高速铣削；刀具磨损；剩余使用寿命；随机分形搜索；支持向量回归

Abstract: In high speed milling operations， it is urgent to accurately predict the remaining useful life of cutting tools to determine the best time to replace them， but there is often a problem of insufficient historical data in the prediction. Therefore， a method for remaining useful life prediction of cutting tools in small sample space is proposed， which is based on the support vector regression (SVR) method. And the stochastic fractal search (SFS) algorithm is used to optimize the key parameters of SVR. Compared with the traditional method， it obtains better model parameters and faster convergence speed. Finally， the as-adopted method is compared with the hidden Markov model (HMM) approach. The accuracy rate increases from 0.6277 to 0.8199， which provides a reliable reference for tool replacement.

Key words: high-speed milling; tool wear; remaining useful life; stochastic fractal search; support vector regression

中图分类号:

TG71

黄贤振，孙良仕，高娓，李禹雄. 基于SFS-SVR的高速铣削刀具剩余使用寿命预测[J]. 东北大学学报（自然科学版）, 2023, 44(6): 824-831.

HUANG Xian-zhen， SUN Liang-shi， GAO Wei， LI Yu-xiong. Remaining Useful Life Prediction of Cutting Tools Based on SFS-SVR in High Speed Milling Operations[J]. Journal of Northeastern University(Natural Science), 2023, 44(6): 824-831.

参考文献

[1]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):220-224.(Lu Zhi-yuan， Ma Peng-fei， Xiao Jiang-lin， et al.Online monitoring of tool wear conditions in machining processes based on machine tool data［J］.China Mechanical Engineering，2019，30(2):220-224.)
[2]Silva R，Reuben R，Baker K，et al.Tool wear monitoring of turning operations by neural network and expert system classification of a feature set generated from multiple sensors［J］.Mechanical Systems and Signal Processing，1998，12(2):319-332.
[3]Wang J，Gao R X，Yuan Z，et al.A joint particle filter and expectation maximization approach to machine condition prognosis［J］.Journal of Intelligent Manufacturing，2019，30(2):605-621.
[4]Li W J，Liu T S.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(15):689-702.
[5]Sun H B，Pan J L，Zhang J D，et al.Non-linear Wiener process-based cutting tool remaining useful life prediction considering measurement variability［J］.The International Journal of Advanced Manufacturing Technology，2020，107:4493-4502.
[6]Huang Y X，Lu Z Y，Dai W，et al.Remaining useful life prediction of cutting tools using an inverse Gaussian process model［J］.Applied Sciences，2021，11(11):5011.
[7]Drouillet C，Karandikar J，Nath C，et al.Tool life predictions in milling using spindle power with the neural network technique［J］.Journal of Manufacturing Processes，2016，22:161-168.
[8]Huang Q Q，Kang Z，Zhang Y，et al.Tool remaining useful life prediction based on edge data processing and LSTM recurrent neural network［C］//2020 IEEE International Conference on Prognostics and Health Management(ICPHM).Detroit，2020:1-5.
[9]Zhang X Y，Lu X，Li W D，et al.Prediction of the remaining useful life of cutting tool using the hurst exponent and CNN-LSTM［J］.The International Journal of Advanced Manufacturing Technology，2021，112:2277-2299.
[10]Smola A J，Scholkopf B.A tutorial on support vector regression［J］.Statistics and Computing，2004，14:199-222.
[11]PHM Society.PHM data challenge 2010［EB/OL］.(2010-05-18)［2020-12-10］.https://www.phmsociety.org/competition/phm/10.
[12]Huang Z W，Zhu J M，Lei J T，et al.Tool wear predicting based on multisensory raw signals fusion by reshaped time series convolutional neural network in manufacturing［J］.IEEE Access，2019，7:178640-178651.
[13]Cortes C，Vapnik V.Support-vector networks［J］.Machine Learning，1995，20:273-297.
[14]Li Y X，Huang X Z，Zhao C Y，et al.Stochastic fractal search-optimized multi-support vector regression for remaining useful life prediction of bearings［J］.Journal of the Brazilian Society of Mechanical Sciences and Engineering，2021，43:1-18.
[15]Salimi H.Stochastic fractal search:a powerful metaheuristic algorithm［J］.Knowledge-Based Systems，2015，75:1-18.
[16]Yu J S，Liang S，Tang D Y，et al.A weight hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction［J］.The International Journal of Advanced Manufacturing Technology，2017，91:201-211.

基于SFS-SVR的高速铣削刀具剩余使用寿命预测

Remaining Useful Life Prediction of Cutting Tools Based on SFS-SVR in High Speed Milling Operations

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价