基于电机电流信号的多机床运行状态监测
PDF下载 (74)金 汉,李国富.基于电机电流信号的多机床运行状态监测[J].宁波大学学报(理工版),2026,39(2):28-35.DOI:10.20098/j.cnki.1001-5132.2025.0129
JIN Han,LI Guofu.Monitoring of multi-machine tool operation status based on motor current signals[J].Journal of Ningbo University(Natural Science & Engineering Edition),2026,39(2):28-35.DOI:10.20098/j.cnki.1001-5132.2025.0129
| Title: | Monitoring of multi-machine tool operation status based on motor current signals |
| 作者: | 金 汉, 李国富 |
| Author(s): | JIN Han, LI Guofu |
| 关键词: | 运行状态监测; 电机电流信号; 门控循环单元; 变分模态分解 |
| Keywords: | operation statusmonitoring; motor current signal; gated recurrent unit; variational modedecomposition |
| 分类号: | TH164 |
| DOI: | 10.20098/j.cnki.1001-5132.2025.0129 |
| 文献标识码: | A |
| 摘要: | 针对离散制造车间中人工记录生产数据无法满足生产制造任务及时安排的问题，通过分析机床电机电流信号实现机床运行状态监测，以提高车间智能化水平。基于机床电机电流信号易采集、低成本的特性，提出一种能够准确识别机床组中运行机床的监测新方法。新方法将灰狼优化算法（Grey Wolf Optimization，GWO）与变分模态分解（Variational Mode Decomposition，VMD）相结合，对多机床复合电机电流信号进行频谱重构，强化特征频段信息，再搭建CNN-GRU神经网络模型完成运动状态分类。结果表明，此频谱重构方法能够有效强化电流信号中的微弱特征频段，显著提升模型识别效果，不仅识别准确率达到98%以上，且具有一定通用性。 |
| Abstract: | Aiming to address the problem that manual recording of production data in discrete manufacturing workshops cannot satisfy the timely scheduling of production tasks, this paper studied the current signal of the machine tool motor to monitor the running state of the machine tool, thereby improving the workshop intelligence. By exploiting the characteristics of easy collection and low cost of motor current signal, a monitoring method was proposed that can accurately identify the running machine tools within a machine tool group. In this method, both Grey Wolf Optimization (GWO) and Variational Mode Decomposition (VMD) were combined to reconstruct the frequency spectrum of the composite motor current signals from multiple machine tools and to enhance the characteristic frequency band information. A CNN-GRU neural network model was established for the classification of the operation status. The experimental results show that this method can effectively enhance the weak characteristic frequency band in the current signal and improve the model’s recognition performance. The accuracy rate has shown to exceed 98%, demonstrating a certain level of universality. |
| 参考文献 /References: | [1] 李聪波, 曹宝, 吴畏, 等. 基于数字孪生的机械加工车间多级能效监测[J]. 计算机集成制造系统, 2023, 29(6): 2102-2117. [2] 刘华一, 鄢萍, 周强, 等. 基于语义网的机床故障诊断知识扩展方法[J]. 计算机集成制造系统, 2020, 26(3): 609-622. [3] 刘飞, 刘培基, 李聪波, 等. 制造系统能量效率研究的现状及难点问题[J]. 机械工程学报, 2017, 53(5):1-11. [4] SEEMUANG N, MCLEAY T, SLATTER T. Using spindle noise to monitor tool wear in a turning process[J]. The international journal of advanced manufacturing technology, 2016, 86(9):2781-2790. [5] ZOU Z X, LI C, SHEN G J, et al. Modulation signal bispectrum analysis of motor current signals for online monitoring of turning conditions[J]. Measurement and control, 2024, 57(5):540-550. [6] KALEEM M, GUERGACHI A, KRISHNAN S. Hierarchical decomposition based on a variation of empirical mode decomposition[J]. Signal, image and video processing, 2017, 11(5):793-800. [7] COLOMINAS M A, SCHLOTTHAUER G, TORRES M E. Improved complete ensemble EMD: a suitable tool for biomedical signal processing[J]. Biomedical signal processing and control, 2014, 14:19-29. [8] ARRIETA PATERNINA M R, TRIPATHY R K, ZAMORA-MENDEZ A, et al. Identification of electro- mechanical oscillatory modes based on variational mode decomposition[J]. Electric power systems research, 2019, 167:71-85. [9] YAN W, LU C X, LIU Y, et al. An energy data-driven approach for operating status recognition of machine tools based on deep learning[J]. Sensors, 2022, 22(17): 6628. [10] 施莹, 曾绍坤, 李沨, 等. 基于深度卷积神经网络的机床有效加工状态识别[J]. 军民两用技术与产品, 2020(11): 54-58. [11] WU S, LEI W, YU T, et al. Effect of the stiffness of the turntable bearing joint on the dynamic characteristics of the five-axis machine tool rotary system[J]. Machines, 2023, 11(3):389. [12] WANG Q H, WANG L J, YU H T, et al. Utilizing SVD and VMD for denoising non-stationary signals of roller bearings[J]. Sensors, 2021, 22(1):195. [13] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in engineering software, 2014, 69: 46-61. [14] 李玉珠, 金永. 基于CCSO-VMD的声发射脱粘信号特征提取[J]. 电子测量技术, 2024, 47(19):96-103. [15] WANG H, LIU Z L, PENG D D, et al. Interpretable convolutional neural network with multilayer wavelet for Noise-Robust Machinery fault diagnosis[J]. Mechanical systems and signal processing, 2023, 195:110314. [16] 邓志光, 李政希, 何亮, 等. 基于改进CWT-CNN的核电厂传感器故障诊断研究[J]. 核动力工程, 2024, 45(增刊2):156-162. [17] ZHOU Z X, WANG H, LI Z X, et al. Fault diagnosis of rolling bearing based on deep convolutional neural network and gated recurrent unit[J]. Journal of advanced mechanical design, systems, and manufacturing, 2023, 17(2):17. [18] 李巧君, 郭彍. 基于改进K均值聚类的语音情感识别深度学习方法[J]. 计算机应用与软件, 2024, 41(9):224- 229. [19] 盛宇, 李维武, 杨吴奔, 等. 基于VMD-GRU-Transformer的电梯轴承故障诊断方法[J]. 机械设计, 2024, 41(11): 178-185. |
| 备注/Memo: | 收稿日期：2025-01-23 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ 基金项目：国家自然科学基金（22078164） 第一作者：金 汉，硕士研究生，主要研究方向为机床监测与信号处理。E-mail: jhan54999@163.com *通信作者：李国富，教授，主要研究方向为制造系统、自动控制和计算机应用。E-mail: lgfdp@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
