基于注意力机制堆叠LSTM的多传感器信息融合刀具磨损预测

doi:10.3969/j.issn.1007-7375.240063

工业工程 ›› 2024, Vol. 27 ›› Issue (3): 64-77,86.doi: 10.3969/j.issn.1007-7375.240063

• 复杂系统建模与运筹优化 • 上一篇下一篇

基于注意力机制堆叠LSTM的多传感器信息融合刀具磨损预测

成佳闻¹, 赛希亚拉图¹, 张超勇^1,2, 罗敏²

1. 华中科技大学机械科学与工程学院，湖北武汉 430074;
2. 湖北汽车工业学院电气与信息工程学院，湖北十堰 442002

收稿日期:2024-02-09 发布日期:2024-07-12
通讯作者: 张超勇 (1972—)，男，江苏省人，教授，博士，主要研究方向为智能调度算法、网络化制造、绿色制造。Email: zcyhust@hust.edu.cn E-mail:zcyhust@hust.edu.cn
作者简介:成佳闻 (1999—)，男，湖北省人，硕士，主要研究方向为刀具磨损和数字孪生
基金资助:
中德重点研发资助项目 (2023ZY01089)；工信部高质量发展专项资助项目 (2023ZY01089)

Tool Wear Prediction Based on Multi-sensor Information Fusion Using Stacked LSTM with Attention Mechanism

CHENG Jiawen¹, BAO Saixialt¹, ZHANG Chaoyong^1,2, LUO Min²

1. School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China;
2. School of Electrical and Information Engineering, Hubei University of Automotive Technology, Shiyan 442002, China

Received:2024-02-09 Published:2024-07-12

摘要/Abstract

摘要： 刀具磨损是影响数控机床加工质量和加工效率的重要因素之一。针对现有铣刀磨损预测中信号单一和预测精度不足的问题，提出了一种基于注意力机制的堆叠LSTM (long short-term memory，长短期记忆网络) 的多传感器信息融合刀具磨损预测方法。对多传感器信号进行预处理，然后提取多域特征，利用核主成分分析法对其进行特征级信息融合，得到后续网络的输入。采用基于注意力机制的堆叠LSTM网络模型，使得网络能够自适应地学习数据的重要信息，在PHM2010的数据集上预测精度达到99.9%。通过与其他算法的对比试验和加入人工噪声的方法，验证了本文所提出的模型的高精度和鲁棒性。

关键词: 刀具磨损, 核主成分分析 (KPCA), 信息融合, 注意力机制, 鲁棒性

Abstract: Tool wear is one of the critical factors affecting the quality and efficiency of computer numerical control (CNC) machine tools. To address the current issues of signal singularity and insufficient prediction accuracy in milling cutter wear predictions, a novel method for tool wear prediction is proposed, which involves the fusion of multi-sensor information based on a stacked long short-term memory (LSTM) network with attention mechanism. Initially multiple sensor signals are preprocessed, subsequently multi-domain features are extracted. These features are fused at the feature level using Kernel Principal Component Analysis (KPCA), providing the input for the subsequent network. A stacked LSTM network model with attention mechanism is used to enable adaptive learning of crucial information, achieving a predictive accuracy of 99.9% on the PHM2010 dataset. Comparative experiments are conducted with other algorithms and incorporating artificial noise to verify the high accuracy and robustness of the proposed model.

Key words: tool wear, kernel principal component analysis (KPCA), information fusion, attention mechanism, robustness

中图分类号:

成佳闻, 赛希亚拉图, 张超勇, 罗敏. 基于注意力机制堆叠LSTM的多传感器信息融合刀具磨损预测[J]. 工业工程, 2024, 27(3): 64-77,86.

CHENG Jiawen, BAO Saixialt, ZHANG Chaoyong, LUO Min. Tool Wear Prediction Based on Multi-sensor Information Fusion Using Stacked LSTM with Attention Mechanism[J]. Industrial Engineering Journal, 2024, 27(3): 64-77,86.

参考文献

[1] 刘献礼, 李雪冰, 丁明娜, 等. 面向智能制造的刀具全生命周期智能管控技术[J]. 机械工程学报, 2021, 57(10): 196-219
LIU Xianli, LI Xuebing, DING Mingna, et al. Intelligent management and control technology of cutting tool life-cycle for intelligent manufacturing[J]. Journal of Mechanical Engineering, 2021, 57(10): 196-219
[2] 聂鹏, 杨程越, 彭新月, 等. 采用scSE优化ResNet-50的CFRP/TC4叠层材料钻削刀具磨损状态监测[J/OL]. 中国机械工程: 1-10[2024-02-03]. http://kns.cnki.net/kcms/detail/42.1294.TH.20231220.1625.006.html.
NIE Peng, YANG Chengyue, PENG Xinyue, et al. Tool wear condition monitoring for drilling CFRP/TC4 laminated materials using scSE optimised ResNet-50[J/OL]. China Mechanical Engineering: 1-10[2024-02-03]. http://kns.cnki.net/kcms/detail/42.1294.TH.20231220.1625.006.html.
[3] 刘辉, 张超勇, 戴稳. 基于堆叠稀疏去噪自动编码网络与多隐层反向传播神经网络的铣刀磨损预测模型[J]. 计算机集成制造系统, 2021, 27(10): 2801-2812
LIU Hui, ZHANG Chaoyong, DAI Wen. Prediction model of milling cutter wear based on SSDAE-BPNN[J]. Computer Integrated Manufacturing Systems, 2021, 27(10): 2801-2812
[4] ZHOU J J, YU J B. Chisel edge wear measurement of high-speed steel twist drills based on machine vision[J]. Computers in Industry, 2021, 128: 103536
[5] 刘会永, 张松, 李剑峰, 等. 采用改进CNN-BiLSTM模型的刀具磨损状态监测[J]. 中国机械工程, 2022, 33(16): 1940-1947
LIU Huiyong, ZHANG Song, LI Jianfeng, et al. Tool wear detection based on improved CNN-BiLSTM model[J]. China Mechanical Engineering, 2022, 33(16): 1940-1947
[6] 戴稳, 张超勇, 孟磊磊, 等. 采用深度学习的铣刀磨损状态预测模型[J]. 中国机械工程, 2020, 31(17): 2071-2078
DAI Wen, ZHANG Chaoyong, MENG Leilei, et al. Prediction model of milling cutter wear status based on deep learning[J]. China Mechanical Engineering, 2020, 31(17): 2071-2078
[7] 段暕, 周宏娣, 刘智勇, 等. 基于改进PCANet模型的铣刀磨损预测方法研究[J]. 机械工程学报, 2023, 59(1): 278-285
DUAN Jian, ZHOU Hongdi, LIU Zhiyong, et al. Milling tool wear prediction research based on optimized PCANet model[J]. Journal of Mechanical Engineering, 2023, 59(1): 278-285
[8] 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
[9] ZENDEHDEL N, CHEN H, LEU M C, et al. Real-time tool detection in smart manufacturing using You-Only-Look-Once (YOLO) v5[J]. Manufacturing Letters, 2023, 35: 1052-1059
[10] HE Z, LIU Q. Deep regression neural network for industrial surface defect detection[J]. IEEE Access, 2020, 8: 35583-35591
[11] LIU J, WANG S, ZHU Q, et al. Overhead transmission line condition assessment based on intention classification and slot filling using optimized BERT model[J]. Energy Reports, 2023, 9: 838-846
[12] 陈光林, 于丽娅, 张成龙, 等. 基于麻雀算法优化宽度学习系统的轴承故障诊断[J]. 工业工程, 2023, 26(3): 151-158
CHEN Guanglin, YU Liya, ZHANG Chenglong, et al. Bearing fault diagnosis using sparrow algorithm to optimize broad learning systems[J]. Industrial Engineering Journal, 2023, 26(3): 151-158
[13] 周昊飞. 基于GRU神经网络的自相关过程残差控制图[J]. 工业工程, 2022, 25(1): 108-113
ZHOU Haofei. GRU Neural network-based residual control chart for autocorrelated processes[J]. Industrial Engineering Journal, 2022, 25(1): 108-113
[14] 何彦, 凌俊杰, 王禹林, 等. 基于长短时记忆卷积神经网络的刀具磨损在线监测模型[J]. 中国机械工程, 2020, 31(16): 1959-1967
HE Yan, LING Junjie, WANG Yulin, et al. In-process tool wear monitoring model based on LSTM-CNN[J]. China Mechanical Engineering, 2020, 31(16): 1959-1967
[15] 狄子钧, 袁东风, 李东阳, 等. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J/OL]. 机械工程学报: 1-9[2024-02-06]. http://kns.cnki.net/kcms/detail/11.2187.TH.20220414.0947.002.html.
DI Zijun, YUAN Dongfeng, LI Dongyang, et al. Tool Fault Diagnosis Method Based on Multiscale-Efficient ChannelAttention Network [J/OL]. Journal of Mechanical Engineering: 1-9 [2024-02-06]. http://kns.cnki.net/kcms/detail/11.2187.TH.20220414.0947.002.html.
[16] 董成祥, 魏昕, 张坤鹏, 等. 基于图卷积网络的乘客打车需求预测[J]. 工业工程, 2022, 25(5): 98-105
DONG Chengxiang, WEI Xin, ZHANG Kunpeng, et al. Passenger ride-hailing demand prediction based on graph convolutional networks[J]. Industrial Engineering Journal, 2022, 25(5): 98-105
[17] 张蓝天, 石宇强. 考虑特征学习的IPSO-LSTM晶圆加工周期预测[J]. 工业工程, 2023, 26(3): 143-150
ZHANG Lantian, SHI Yuqiang. Wafer cycle time prediction of IPSO-LSTM considering feature learning[J]. Industrial Engineering Journal, 2023, 26(3): 143-150
[18] LUO J, ZHANG X. Convolutional neural network based on attention mechanism and Bi-LSTM for bearing remaining life prediction[J]. Applied Intelligence, 2022, 52: 1-16
[19] PHM Society. PHM data challenge 2010[C/OL]//Annual Conference of the Prognostics and Health Management Society 2015. (2015-10-18) . Coronado, California: PHM Society. https: // www. phmsociety. org/ competition/phm/10 .
[20] WANG L, LONG J, LI X, et al. Industrial units modeling using self-attention network based on feature selection and pattern classification[J]. Chemical Engineering Research and Design, 2023, 200: 176-185

基于注意力机制堆叠LSTM的多传感器信息融合刀具磨损预测

Tool Wear Prediction Based on Multi-sensor Information Fusion Using Stacked LSTM with Attention Mechanism

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	陈彩华, 佘程熙, 王庆阳. 可信机器学习综述[J]. 工业工程, 2024, 27(2): 14-26.
[2]	李思瀚, 莫超雄, 刘建军, 陈庆新, 毛宁. 物料齐套时间不确定的多地总装作业前摄性调度[J]. 工业工程, 2021, 24(3): 104-114.
[3]	员慧慧, 温修春, 陆建飞, 孙华平. 建筑材料供应中断对承包商成本的冲击研究——基于鲁棒模型分析[J]. 工业工程, 2019, 22(1): 53-60.
[4]	张先超. 生产调度鲁棒性指标及其测度方法研究[J]. 工业工程, 2013, 16(6): 14-20.