On-line tool wear monitoring based on machine learning

Dianfang MU; Xianli LIU; Caixu YUE; Qiang LIU; Zhengyan BAI; Steven Y. LIANG; Yunpeng DING

doi:10.51393/j.jamst.2021002

On-line tool wear monitoring based on machine learning

doi: 10.51393/j.jamst.2021002

a Key Laboratory of Advanced Manufacturing and Intelligent Technology, Ministry of Education, Harbin 150080, China;
b George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta 30332, USA;
c Department of Precision Manufacturing Engineering, Suzhou Vocational Institute of Industrial Technology, Suzhou 215104, China

基金项目:

This research was funded by Projects of International Cooperation and Exchanges NSFC (Grant Number 51720105009) and National Key Research and Development Project (Grant Number 2019YFB1704800) and Outstanding Youth Fund of Heilongjiang Province (Grant Number YQ2019E029) and Natural Science Foundation for Colleges and Universities of Jiangsu Province (No. 19KJB460021)

详细信息

通讯作者:
Xianli LIU,E-mail:xianli.liu@hrbust.edu.cn

计量
- 文章访问数: 2165
- HTML全文浏览量: 897
- PDF下载量: 209
- 被引次数: 0
出版历程
- 收稿日期: 2021-02-02
- 修回日期: 2021-02-18
- 网络出版日期: 2021-03-05
- 刊出日期: 2021-03-04

On-line tool wear monitoring based on machine learning

a Key Laboratory of Advanced Manufacturing and Intelligent Technology, Ministry of Education, Harbin 150080, China;
b George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta 30332, USA;
c Department of Precision Manufacturing Engineering, Suzhou Vocational Institute of Industrial Technology, Suzhou 215104, China

Funds:

摘要

摘要:
Accurate tool condition monitoring is necessary for the development of automatic milling technology. In order to improve the accuracy and real-time of online monitoring of tool wear state in machining process, an online monitoring system of milling cutter state based on LabVIEW software development is proposed. Firstly, the modern monitoring technology is introduced into the online monitoring of tool state in principle. The vibration signal is analyzed by wavelet packet in time-frequency domain, and the online monitoring of tool state is realized by machine learning algorithm model. The system can be used for real-time monitoring of tool status, timely alarm to facilitate tool replacement, and ensure high efficiency and high quality of processing. The effectiveness and feasibility of the online monitoring system for milling cutter wear state are verified by experiments, and the purpose of online monitoring tool wear state is preliminarily realized.
- Tool condition monitoring /
- Tool wear /
- Vibration signal /
- LabVIEW
Abstract:
Accurate tool condition monitoring is necessary for the development of automatic milling technology. In order to improve the accuracy and real-time of online monitoring of tool wear state in machining process, an online monitoring system of milling cutter state based on LabVIEW software development is proposed. Firstly, the modern monitoring technology is introduced into the online monitoring of tool state in principle. The vibration signal is analyzed by wavelet packet in time-frequency domain, and the online monitoring of tool state is realized by machine learning algorithm model. The system can be used for real-time monitoring of tool status, timely alarm to facilitate tool replacement, and ensure high efficiency and high quality of processing. The effectiveness and feasibility of the online monitoring system for milling cutter wear state are verified by experiments, and the purpose of online monitoring tool wear state is preliminarily realized.
- Tool condition monitoring /
- Tool wear /
- Vibration signal /
- LabVIEW

HTML全文

下载: 全尺寸图片幻灯片

参考文献(22)

[1]	. Bhagat S N, Nalbalwar S L. LabVIEW based tool condition monitoring and control for CNC lathe based on parameter analysis. IEEE International Conference on Recent Trends in Electronics. 2016.
[2]	. Zhou CA. On-line monitoring vibration toolholder system and signal singularity analysis of milling tool wear state [dissertation]. Ji’nan: Shandong University, 2020 [Chinese].
[3]	. Liu XL, Liu Q, Yue CX, et al. Intelligent technology in cutting process. Journal of Mechanical Engineering 2018; 54(16):45-61 [Chinese].
[4]	. Bhuiyan M S H, Choudhury I A, Dahari M. Monitoring the tool wear, surface roughness and chip formation occurrences using multiple sensors in turning. Journal of Manufacturing Systems 2014; 33(4):476-87.
[5]	. Wang CD, Bao ZL, Zhang PQ, et al. Tool wear evaluation under minimum quantity lubrication by clustering energy of acoustic emission burst signals. Measurement 2019;138: 256–65.
[6]	. Ghosh N, Ravi Y B, Patra A, et al. Estimation of tool wear during CNC milling using neural network-based sensor fusion. Mechanical Systems & Signal Processing 2007; 21(1):466-79.
[7]	. He Y, Ling JJ, Wang YL. et al. Tool wear online monitoring model based on long-short-term memory convolution neural network. China Mechanical Engineering 2020; 31(16):73-81 [Chinese].
[8]	. Gui Y, Leng S, Dai Z, et al. A framework for big data driven on-line monitoring of tool wear. 2020 IEEE 7th International Conference on Industrial Engineering and Applications (ICIEA). 2020.
[9]	. Xu GH, Meng LH, Jiang KS, et al. On-line monitoring technology of tool condition based on intelligent alarm. Journal of Vibration. Measurement and Diagnosis 2013; 33(3):377-81,522 [Chinese].
[10]	. Lu ZY, Ma PF, Xiao JL, et al. On-line monitoring of tool wear state in machining process based on machine tool information. China Mechanical Engineering 2019;30(2):220-5 [Chinese].
[11]	. Li GH. Research on tool wear monitoring technology for rotary ultrasonic machining of hard and brittle materials[dissertation]. Harbin: Harbin Institute of Technology, 2016.
[12]	. Zhu H, Ni S, Chen W. Research and development on intelligent cutting tools with capability of on-line monitoring and prediction. Journal of Physics: Conference Series 2020; 1650(3): 032143.
[13]	. Huang M, Liu XL, Xie HZ. Tool Wear fault monitoring method and experimental system for high-grade CNC machine tools. Journal of Beijing University of Information Technology (Natural Science Edition) 2012; 27(1):16-21 [Chinese].
[14]	. Terrazas G, Martínez-Arellano G, Benardos P, et al. Online tool wear classification during dry machining using real time cutting force measurements and a CNN approach. Journal of Manufacturing & Materials Processing 2018; 2(4):2040072.
[15]	. Zhao CX, Bai CJ, Pan JT. On-line monitoring of tool wear of CNC machine tools based on LabVIEW. Equipment Management and Maintenance 2015;(11):97-100 [Chinese].
[16]	. Liu WB, Liu TJ, Shi YQ, et al. Design of temperature control system for internal cooling intelligent turning tool based on LabVIEW. Agricultural Equipment and Vehicle Engineering 2018; 56(10):6-8 [Chinese].
[17]	. Panda A, Sahoo AK, Panigrahi I, et al. Prediction models for on-line cutting tool and machined surface condition monitoring during hard turning considering vibration signal. Mechanics and Industry 2020; 21(5):520.
[18]	. Zhu K, Li G, Zhang Y. Big data oriented smart tool condition monitoring system. IEEE Transactions on Industrial Informatics 2020; 16(6):4007-4016.
[19]	. Zhang MZ. Study on wear condition monitoring of milling cutter based on spindle current [dissertation]. Dalian: Dalian University of Technology, 2018 [Chinese].
[20]	. Chen BJ, Chen XF, Li B, et al. Application of logistic regression model in reliability evaluation of machine tool. Chinese Journal of Mechanical Engineering 2011; 47(18):158-64.
[21]	. Aliustaoglu C, Ertunc HM, Ocak H. Tool wear condition monitoring using a sensor fusion model based on fuzzy inference system. Mechanical Systems & Signal Processing 2009; 23(2): 539-46.
[22]	. Shah H S, Patel PN, Shah SP, et al. 8 channel vibration monitoring and analyzing system using LabVIEW. 2013 Nirma University International Conference on Engineering (NUiCONE). 2014.