基于CNC实时监测数据驱动方法的钛合金高速铣削刀具寿命预测

中国机械工程

基于CNC实时监测数据驱动方法的钛合金高速铣削刀具寿命预测

东华大学机械工程学院，上海，201620

出版日期:2018-02-25 发布日期:2018-02-27
基金资助:
国家自然科学基金资助项目（51475301,51435009）；
中央高校基本科研业务费专项资金资助项目
National Natural Science Foundation of China （No. 51475301,51435009）
Fundamental Research Funds for the Central Universities

Tool Life Prediction in Titanium High Speed Milling Processes Based on CNC Real Time Monitoring Data Driven

YUAN Guangchao;BAO Jingsong;ZHENG Xiaohu;ZHANG Jie

College of Mechanical Engineering，Donghua University,Shanghai，201620

Online:2018-02-25 Published:2018-02-27
Supported by:
National Natural Science Foundation of China （No. 51475301,51435009）
Fundamental Research Funds for the Central Universities

摘要/Abstract

摘要： 针对车间内不同设备的数据结构不一致导致车间监控数据中存在大量的多源异构数据，难以通过单一的通信协议采集与监控的问题，研究了基于OPC-UA技术与MTConnect协议的刀具、机床的数据模型、通信架构及访问策略，解决了多源异构数据的采集问题。针对硬质合金刀具在高速铣削钛合金工件时磨损较快、刀具剩余寿命的实时预测难度大的问题，建立了一种基于PCA前置处理数据的神经网络模型，实现了基于刀具剩余寿命的刀具健康状态信息的实时监测和预测。

关键词: 数控, 数据驱动, 钛合金铣削, 刀具健康预测

Abstract: A large number of multi-source heterogeneous data existed in the monitoring data due to the inconsistency of the data structures of the different equipment in the workshops, which were difficult to collect and monitor through a single communication protocol. To solve this problem, a data model of machine-tools, communication frameworks and access strategies were developed to realize multi-source heterogeneous data acquisition based on the OPC-UA and MTConnect herein. Carbide tools were easily damaged and quick-wear in high speed machining(HSM) of titanium alloys, as it was difficult to predict the remaining useful tool life in real time.Therefore, a BP neural network model based PCA method was developed to reflect the relationship among machine conditions and the parameters of the tools. The model realizes the monitoring and predicting of important informations of tool healthy conditions based on RUL.

Key words: computer numerical control(CNC), data-driven, titanium alloy milling, tool health condition prediction

中图分类号:

TG659

袁广超;鲍劲松;郑小虎;张洁. 基于CNC实时监测数据驱动方法的钛合金高速铣削刀具寿命预测[J]. 中国机械工程.

YUAN Guangchao;BAO Jingsong;ZHENG Xiaohu;ZHANG Jie. Tool Life Prediction in Titanium High Speed Milling Processes Based on CNC Real Time Monitoring Data Driven[J]. China Mechanical Engineering.

参考文献

[1]OPC UA——互联工厂方案[J].国内外机电一体化技术,2016(4):26-28.
OPC UA—Interconnected Plant Scheme[J]. International Mechatronics Technology,2016(4):26-28.
[2]TU N T T, QUYET T H. Development of an OPC UA SDK Based WCF Technology and Its Deployment for Environmental Monitoring Applications[C]//Context-Aware Systems and Applications: First International Conference.Ho Chi Minh City, 2012:347-356.
[3]安东，王峰丽. 美国先进制造中心四大研究热点解析[J].金属加工(冷加工)，2015(4): 16-19.
AN Dong, WANG Fengli. Analysis of the Four Major Research Areas of the Advanced Manufacturing Center in America [J]. Metal Working,2015(4): 16-19.
[4]VIJAYARAGHAVAN A, HUET L, DORNFELD D A. Addressing Process Planning and Verification Issues with MTConnect[J]. Transactions of the North American Manufacturing Research Institution of SME, 2009, 37:557-564.
[5]MICHALOSKI J, LEE B, PROCTOR F, et al. Quantifying the Performance of MT-Connect in a Distributed Manufacturing Environment[J]. ASME International Design Engineering Technical Conferences & Computers & Information in Engineering Conference. San Diego,2009:533-539.
[6]JAVED K. A Robust & Reliable Data-driven Prognostics Approach Based on Extreme Learning Machine and Fuzzy Clustering[D]. Lyon :Universite de Franche-Comte, 2014.
[7]UCKUN S, KAI G, LUCAS P J F. Standardizing Research Methods for Prognostics[C]//International Conference on Prognostics & Health Management.Denver, 2008:1-10.
[8]BENKEDJOUH T, MEDJAHER K, ZERHOUNI N, et al. Health Assessment and Life Prediction of Cutting Tools Based on Support Vector Regression[J]. Journal of Intelligent Manufacturing,2015, 26(2): 213-223.
[9]HUANG P, LEE W B. Cutting Force Prediction for Ultra-precision Diamond Turning by Considering the Effect of Tool Edge Radius[J]. International Journal of Machine Tools and Manufacture,2016,109:1-7.
[10]KARAM S, CENTOBELLI P, D ADDONA D M, et al. Online Prediction of Cutting Tool Life in Turning via Cognitive Decision Making[J]. Procedia CIRP， 2016, 41: 927-932.
[11]李锡文，杨明金，谢守勇，等.基于神经网络信息融合的铣刀磨损状态监测[J].农业机械学报,2007,38(7): 160-163.
LI Xiwen, YANG Mingjin, XIE Shouyong, et al. Wear Condition Monitoring of Helical Cutters Based on Neural Network Information Infusion Method[J].Transactions of the Chinese Society of Agricultural Machinery, 2007,38(7): 160-163.

[1]	刘强, . 数控机床发展历程及未来趋势[J]. 中国机械工程, 2021, 32(07): 757-770.
[2]	桂林;李升. 国内重型数控机床的现状及发展趋势[J]. 中国机械工程, 2020, 31(23): 2780-2787,2797.
[3]	张朝阳;吉卫喜;彭威. 基于迁移学习的数控机床节能控制决策方法[J]. 中国机械工程, 2020, 31(23): 2855-2863.
[4]	李聪波;尹誉先;肖溱鸽;龙云;赵希坤. 数据驱动下基于元动作的数控车削能耗预测方法[J]. 中国机械工程, 2020, 31(21): 2601-2611.
[5]	付国强, 饶勇建, 谢云鹏, 高宏力, 邓小雷. [误差建模及精度保证方法]几何误差贡献值影响下五轴数控机床运动轴误差灵敏度分析方法[J]. 中国机械工程, 2020, 31(13): 1518-1528.
[6]	黄智, 刘永超, 邓涛, 周涛, 祝云. [误差建模及精度保证方法]一种五轴数控机床热误差建模方法[J]. 中国机械工程, 2020, 31(13): 1529-1538.
[7]	阮大文, 茅健, 刘钢, 马丽. [误差建模及精度保证方法]双五轴数控铣削机床旋转轴误差辨识方法[J]. 中国机械工程, 2020, 31(13): 1548-1554.
[8]	刘红艺, 樊锐, 郭江真, 张维, 赵钦志, 陈五一. [可靠性建模及试验技术]面向数控机床可靠性试验的多维力随动加载装置[J]. 中国机械工程, 2020, 31(13): 1606-1612.
[9]	杨斌, 冉琰, 张根保. [可靠性建模及试验技术]基于元动作模块的多轴数控机床精度分析[J]. 中国机械工程, 2020, 31(13): 1621-1628.
[10]	刘世豪, 林茂. [综述]高速数控转台优化设计方法研究现状与展望[J]. 中国机械工程, 2020, 31(13): 1629-1637.
[11]	姜少飞;邬天骥;彭翔;李吉泉;李治;孙涛. 基于XGBoost特征提取的数据驱动故障诊断方法[J]. 中国机械工程, 2020, 31(10): 1232-1239.
[12]	侯晓莉;李言;杨明顺;柏朗;石珣;张成兴. 铝板数控单点渐进成形的成形极限曲线研究[J]. 中国机械工程, 2020, 31(08): 960-967.
[13]	李浩, 王昊琪, 程颖, 陶飞, 郝兵, 王新昌, 纪杨建, 宋文燕, 杜文辽, 文笑雨, 巩晓赟, 李客, 张映锋, 罗国富, 李奇峰. [数据驱动的智能服务]数据驱动的复杂产品智能服务技术与应用[J]. 中国机械工程, 2020, 31(07): 757-772.
[14]	吴扬东, 张太华, 刘丹, 王宜全. [数据驱动的产品设计]复杂产品设计方案的数据驱动多属性优化决策[J]. 中国机械工程, 2020, 31(07): 865-870.
[15]	赵旭升1,4;杨建中1;陈吉红1;Alexander FRADKOV2;Oleg GRANICHIN3;胡鹏程1. 服役破损叶片的曲面重构及刀路生成方法[J]. 中国机械工程, 2019, 30(24): 2906-2915,2924.