基于多通道一维卷积神经网络的刀具磨损动态预测模型

PDF(1579 KB)

振动与冲击 ›› 2023, Vol. 42 ›› Issue (2) : 60-67.

论文

黄华1，姚嘉靖1，王永和1，吕延军2

作者信息 +

Dynamic prediction model for tool wear based on a multi-channel one-dimensional convolutional neural network

HUANG Hua1，YAO Jiajing1，WANG Yonghe1，L Yanjun2

Author information +

文章历史 +

摘要

针对同一工况下不同刀具磨损预测建模中的数据分布不同，从而导致的历史模型失效问题，提出了一种基于多通道一维卷积神经网络的刀具磨损动态预测建模方法。历史刀具磨损数据训练的多通道一维卷积神经网络，作为初始的刀具磨损预测历史模型。最大均值差异法(maximum mean difference ，MMD)对不同刀具磨损数据进行相似度检测，相似度相差较大时在历史模型的基础上进行迭代更新，更新后的模型再对磨损数据进行预测。铣削实验验证结果表明，该方法能够准确预测不同刀具的磨损值大小，具有较好的自适应能力。

Abstract

Aiming at the failure of historical model caused by different data distribution in tool wear prediction modeling under the same working condition, a tool wear dynamic prediction modeling method based on multi-channel one-dimensional convolutional neural network is proposed. The multi-channel one-dimensional convolutional neural network trained on historical tool wear data serves as historical model of the initial tool wear prediction. The maximum mean difference method (MMD) was used to detect the similarity of different tool wear data. When the similarity difference is large, the iterative update is carried out on the basis of the historical model, and then the updated model is used to predict the wear data. The results of milling experiments show that the method can accurately predict the wear values of different tools and has great adaptive ability.

导出引用

黄华1，姚嘉靖1，王永和1，吕延军2. 基于多通道一维卷积神经网络的刀具磨损动态预测模型[J]. 振动与冲击, 2023, 42(2): 60-67

HUANG Hua1，YAO Jiajing1，WANG Yonghe1，L Yanjun2. Dynamic prediction model for tool wear based on a multi-channel one-dimensional convolutional neural network[J]. Journal of Vibration and Shock, 2023, 42(2): 60-67

参考文献

[1] 李宏波, 孙振川, 周建军, 等. 一种新型TBM刀具磨损检测技术[J]. 振动与冲击, 2017, 36(24): 7-12.
Li Hongbo, sun Zhenchuan, Zhou Jianjun, et al. A new wear detection technique for TBM cutters [J]. Journal of Vibration and Shock, 2017, 36 (24): 7-12.
[2] 周俊杰，余建波. 基于机器视觉的加工刀具磨损量在线测量[J]. 上海交通大学学报, 2021, 55(6): 741-749.
Zhou Junjie, Yu Jianbo. Online measurement of machining tool wear based on machine vision [J]. Journal of Shanghai Jiaotong University, 2021, 55 (6): 741-749.
[3] 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 & Engineering, 2017, 139(7): 1-9.
[4] 程灿, 李建勇, 徐文胜, 等. 基于支持向量机与粒子滤波的刀具磨损状态识别[J]. 振动与冲击, 2018, 37(17): 48-55+71.
Cheng can, Li Jianyong, Xu Wensheng, et al. Tools' wear state recognition based on support vector machine and particle filtering [J]. Journal of Vibration and Shock, 2018, 37 (17): 48-55 + 71.
[5] LIU C, Li Y, Zhou G , et al. A sensor fusion and support vector machine based approach for recognition of complex machining conditions[J]. Journal of Intelligent Manufacturing, 2018, 29(8): 1739-1752.
[6] 徐彦伟, 陈立海, 袁子皓,等. 基于信息融合的刀具磨损状态智能识别[J]. 振动与冲击, 2017, 36(21): 257-264.
Xu Yanwei, Chen Lihai, Yuan Zihao, Jie Tancheng. Intelligent recognition of tool wear conditions based on the information fusion [J]. Journal of Vibration and Shock, 2017, 36 (21): 257-264.
[7] 肖鹏飞, 张超勇, 罗敏, 等. 基于自适应动态无偏最小二乘支持向量机的刀具磨损预测建模[J]. 中国机械工程, 2018, 29(007): 842-849.
XIAO Pengfei, ZHANG Chaoyong, LUO Ming, et al. Modeling method for tool wear prediction based on ADNLSSVM [J]. China Mechanical Engineering, 2018, 29(007): 842-849.
[8] 董彩云, 张超勇, 孟磊磊, 等. 基于谐波小波包和BSA优化LS-SVM的铣刀磨损状态识别研究[J]. 中国机械工程, 2017, 28(017): 2080-2089.
DONG Caiyun, ZHANG Chaoyong, MENG Leilei, et al. State Recognition of milling tool wears based on harmonic wavelet packet and BSA optimization LS-SVM [J]. China Mechanical Engineering, 2017, 28(017): 2080-2089.
[9] 尹晨, 周世超, 何建樑, 等. 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/OL]. 中国机械工程: 1-10[2021-09-10]. http: //kns. cnki. net/ kcms/ detail/42.1294. TH.20210601. 1332.006. html.
Yin Chen, Zhou Shichao, He Jianliang, et al. Tool wear online recognition method based on multi-source synchronous signals and deep learning [J/OL]. China Mechanical Engineering: 1-10 [2021-09-10]. http: //kns. cnki. net/ kcms/ detail/ 42.1294. TH. 20210601. 1332. 006. html.
[10] 曹大理, 孙惠斌, 张纪铎, 等. 基于卷积神经网络的刀具磨损在线监测[J]. 计算机集成制造系统, 2020, 26(01): 74-80.
Cao Dali, Sun Huibin, Zhang Jiduo, et al. In-process tool condition monitoring based on convolution neural network [J]. Computer Integrated Manufacturing Systems, 2020, 26 (01): 74-80.
[11] 刘思辰, 杨飞然, 杨军. 基于多传感器融合的刀具剩余寿命预测[J]. 振动与冲击, 2021, 40(17): 47-54.
Liu sichen, Yang feiran, Yang Jun. Tool residual life prediction based on multi-sensor fusion [J]. Journal of Vibration and Shock, 2021, 40 (17): 47-54.
[12] 李聪波, 孙鑫, 侯晓博, 等. 数字孪生驱动的数控铣削刀具磨损在线监测方法[J/OL]. 中国机械工程: 1-11[2021-09-10]. http: // kns. cnki.net/ kcms/ detail/ 42.1294. TH. 20210519. 1545.006. html.
Li Congbo, Sun Xin, Hou Xiaobo, et al. Online monitoring method for nc milling tool wear by digital twin-driven [J/OL]. China Mechanical Engineering: 1-11[2021-09-10]. http: // kns. cnki.net/ kcms/ detail/ 42.1294. TH. 20210519. 1545.006. html.
[13] Wang J, Zou B, Liu M, et al. Milling force prediction model based on transfer learning and neural network[J]. Journal of Intelligent Manufacturing, 2021, 32: 947-956.
[14] PHM Society. PHM data challenge 2010[DB/OL].