随着“中国制造2025”战略的提出，加工制造业逐渐向着自动化与智能化方向发展，越来越多的企业对刀具状态监测提出了更高要求。然而，现阶段刀具状态监测技术并不成熟，尚未广泛应用在实际加工生产中。在此背景下，本文以刀具切削过程中的振动信号、AE信号为研究对象，借助LabVIEW来构建刀具状态监测系统。论文的主要工作和成果如下：

（1）在时域、频域、时频域内提取振动信号、AE信号的幅值变化波形图，完成其特征参数的提取。在时域内，完成振动信号和AE信号的均值、方差、均方根的提取；在频域内，对振动信号和AE信号的功率谱展开分析；在时频域内，对振动信号展开4层小波包分解，对AE信号展开8层多分辨率分解，并且计算出各频段的能量百分比，从而实现31维特征向量的组建。

（2）原始特征中包含着大量的无用信息，会对分类效果造成影响。因此借助Relief-F特征选择算法对获取的信号进行筛选，最终选择权重排在前8位的特征作为训练样本。实验结果表明，特征选择前后模型的识别准确率提高了20%。

（3）对BP神经网络的缺点进行分析，通过WOA算法优化BP神经网络的阈值和权值，建立了WOA-BP神经网络模型。实验结果表明，WOA-BP神经网络的刀具磨损状态识别模型的平均绝对误差、均方误差、均方根误差、平均绝对百分比误差的值都比BP神经网络的值小，说明WOA-BP神经网络的预测精度更高，预测更准确。

（4）基于LabVIEW软件和MATLAB软件开发出一套完整的刀具状态监测系统，该系统可以完成数据采集、信号分析、波形显示、数据读取以及存储与刀具状态识别等功能，并对系统进行可视化展示。

With the introduction of the "Made in China 2025" strategy, the processing and manufacturing industry is gradually developing towards automation and intelligence. More and more enterprises put forward higher requirements for tool condition monitoring. However, at present, the tool condition monitoring technology is not perfect and has not yet been widely applied in actual processing and production. In this context, this article focuses on the vibration signals and AE signals during tool cutting process, and constructs a tool condition monitoring system using LabVIEW. The main work and achievements of the paper are as follows:

(1) Extract waveform maps of vibration signals and AE signals in time, frequency, and time-frequency domains, and complete the extraction of their characteristic parameters. Complete the extraction of mean, variance, and root mean square of vibration signals and AE signals in the time domain; Analyze the power spectrum of vibration signals and AE signals in the frequency domain; In the time-frequency domain, 4-layer wavelet packet decomposition is performed on the vibration signal, 8-layer multi resolution decomposition is performed on the AE signal, and the energy percentage of each frequency band is calculated to achieve the construction of a 31 dimensional feature vector.

(2) The original features contain a large amount of useless information, which can affect the classification effect. Therefore, the Relief-F feature selection algorithm is used to filter the obtained signals, and the top 8 weighted features are ultimately selected as training samples. The experimental results show that the recognition accuracy of the model before and after feature selection has improved by 20%.

(3) This paper analyzes the shortcomings of BP neural network, optimizes the threshold and weight value of BP neural network through WOA algorithm, and establishes the WOA-BP neural network model, which can identify the tool wear status more accurately. The experimental results show that the average absolute error, mean square error, root mean square error and average absolute percentage error of the tool wear state recognition model based on WOA-BP neural network are smaller than those of the BP neural network, which indicates that the prediction accuracy of WOA-BP neural network is higher and the prediction is more accurate.

(4) A complete tool status monitoring system has been developed based on LabVIEW and MATLAB software. The system can complete functions such as data acquisition, signal analysis, waveform display, data reading, storage, and tool status recognition, and visualize the system.

[1] 黎丽，谢伟，魏书传等．中国制造2025[J]．金融经济，2015，13(190)：10-10．

[2] Dimla D E. Sensor signals for tool-wear monitoring in metal cutting operations a review of methods[J]. International Journal of Machine Tools and Manufacture, 2000, 40(8): 1073-1098.

[3] 常艳丽．镍基高温合金GH4169的切削力与刀具磨损实验研究[D]．黑龙江：哈尔滨工业大学，2011．

[4] 徐作栋，董月清，阳小勇．低温微量润滑和超声椭圆振动下GH4169合金切削研究[J]．组合机床与自动化加工技术，2023(4)：125-127．

[5] 梁军华，高宏力．刀具磨损过程中铣削力与主轴电流试验研究[J]．机械设计与制造，2023，385(3)：43-45，52．

[6] Dimla D E, Lister P M. On-line metal cutting tool condition monitoring[J]. International Journal of Machine Tools and Manufacture, 2000, 40(5): 739-768.

[7] Ghasempoor A, Jeswiet J, Moore T N. Real time implementation of on-line tool condition monitoring in turning[J]. International Journal of Machine Tools and Manufacture, 1999, 39(12): 1883-1902.

[8] Sikdar S K, Chen M. Relationship between tool flank wear area and component forces in single point turning[J]. Journal of Materials Processing Technology, 2002,128(1-3): 210-215.

[9] 杨斌，樊志刚，王建国等．一维残差卷积神经网络的刀具磨损识别方法研究[J]．机械科学与技术，2022，41(11)：1746-1752．

[10] Teti R, Jemielniak K, O Donnell G, et al. Advanced monitoring of machining operations[J]. CIRP Annals, 2010, 59(2): 717-739.

[11] 谢松峰，陈燕，晏超仁等．基于力信号的低频振动制孔刀具磨损状态分析[J]．机械制造与自动化，2022，51(1)：11-14．

[12] Alonso F J, Salgado D R. Analysis of the structure of vibration signals for tool wear detection[J]. Mechanical Systems and Signal Processing, 2008, 22(3): 735-748.

[13] Rao K V, Murthy B S N, Rao N M. Cutting tool condition monitoring by analyzing surface roughness, work piece vibration and volume of metal removed for AISI 1040 steel in boring[J]. Measurement, 2013, 46(10): 4075-4084.

[14] Bhuiyan M S H, Choudhury I A, Nukman Y. Tool Condition Monitoring using Acoustic Emission and Vibration Signature in Turning[J]. Lecture Notes in Engineering and Computer Science, 2012, 2199(1): 531-538.

[15] Rajesh V G, Narayanan Namboothiri V N. Flank wear detection of cutting tool inserts in turning operation: application of nonlinear time series analysis[J]. Soft Computing, 2010, 14(9): 913-919.

[16] Li X. A brief review: acoustic emission method for tool wear monitoring during turning[J]. International Journal of Machine Tools and Manufacture, 2002, 42(2): 157-165.

[17] 周兆锋，洪捐，黄传锦．基于声发射信号分析的刀具磨损状态在线监测研究[J]．工具技术，2022，56(12)：51-55．

[18] 关山．基于声发射信号多特征分析与融合的刀具磨损分类与预测技术[D]．吉林：吉林大学，2011．

[19] Kakade S, Vijayaraghavan L, Krishnamuilhy R. In-process tool wear and chip-form monitoring in face milling operation using acoustic emission[J]. Journal of Materials Processing Technology, 1994, 44(3-4): 207-214.

[20] Siddhpura M, Paurobally R. A review of chatter vibration research in turning[J]. International Journal of Machine Tools and Manufacture, 2012, 61(1): 27-47.

[21] 杨博宇，曹忠，郭国强等．基于卷积神经网络的铣刀后刀面磨损状态预测方法研究[J]．工具技术，2022，56(5)：22-26．

[22] Korkut I, Acir A, Boy M. Application of regression and artificial neural network analysis in modelling of tool-chip interface temperature in machining[J]. Expert Systems with Applications, 2011, 38(9): 11651-11656.

[23] Abouelatta, Zhang J Z, Chen J C, et al. ED developed an adaptive control system for surface roughness during turning operation[J]. Journal of Intelligent Manufacturing, 2007, 18, 301-311.

[24] Venkata K, Rao B S, Murthy N. Cutting tool condition monitoring by analyzing surface roughness, work piece vibration and volume of metal removed for AISI 1040 steel in boring[J]. Measurement, 2013, 46(10): 4075-4084.

[25] Tuğrul Özel, Yiğit Karpat. Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks[J]. International Journal of Machine Tools and Manufacture, 2004, 45(4): 467-479.

[26] Chinchanikar S, Choudhury S K. Evaluation of Chip-tool Interface Temperature: Effect of Tool Coating and Cutting Parameters during Turning Hardened AIS I 4340 Steel[J]. Procedia a Materials Science, 2014(6): 996-1005.

[27] Zhu K, San W Y, Soon H G. Wavelet analysis of sensor signals for tool condition monitoring: A review and some new results[J]. International Journal of Machine Tools and Manufacture, 2009, 49(7-8): 537-553.

[28] Jaidine A K S, Lin D, Banjevic D. A review on machinery diagnostics and prognostics implementing condition-based maintenance[J]. Mechanical Systems and Signal Processing, 2006, 20(7): 1483-1510.

[29] 潘春龙，王二化，张屹．微铣削刀具磨损状态监测方法研究[J]．计算机测量与控制，2021，29(11)：22-28,40．

[30] 廖小平，黎宇嘉，陈超逸等．基于核主成分和灰狼优化算法的刀具磨损状态识别[J]．计算机集成制造系统，2020，26(11)：3031-3039．

[31] 李涛，黄新宇，罗明．基于小波包分解的刀具磨损特征分析[J]．组合机床与自动化加工技术，2020(7)：10-15．

[32] 高龙．基于小波分析和集成神经网络的刀具磨损监测技术研究[D]．成都，西南交通大学，2007．

[33] Kalvoda T, Hwang Y, Vrabec M. Cutter tool fault detection using a new spectral analysis method[J]. Proceedings of the Institution of Mechanical Engineers, Part B:Journal of Engineering Manufacture, 2010, 224(12): 1784-1791.

[34] 刘清荣，阎长罡．基于铣削力与神经网络刀具磨损状态识别研究[J]．制造技术与机床，2008(2)：72-76．

[35] 王二化，郭伟，赵宇航等．EMD和BPNN-GA在微铣刀磨损预测中的应用[J]．机械设计与制造，2022(12) ：137-140，146．

[36] 杨斌，樊志刚，王建国等．一维残差卷积神经网络的刀具磨损识别方法研究[J]．机械科学与技术，2022，41(11)：1746-1752．

[37] 滕瑞，黄海松，杨凯等．基于图像编码技术和卷积神经网络的刀具磨损值在线监测方法[J]．计算机集成制造系统，2022，28(4)：1042-1051．

[38] 谢振龙，岳彩旭，刘献礼等．基于EMD-SVM的钛合金铣削过程刀具磨损监测[J]．振动、测试与诊断2022，42(5)：988-996．

[39] 惠铭心．基于加工，参数的铣削刀具状态监测研究[D]．中国科学院大学，2021．

[40] 文妍．基于多源信息融合的数控机床进给系统机械故障诊断研究[D]．山东：青岛理工大学，2016．

[41] Balazinski M, Czogala E, Jemielniak K, et al. Tool condition monitoring using artificial intelligence methods[J]. Engineering Applications of Artificial Intelligence, 2002, 15(1): 73-80.

[42] Wang M, Wang J. CHMM for tool condition monitoring and remaining useful life prediction[J]. The International Journal of Advanced Manufacturing Technology, 2012, 59(5-8): 463-471.

[43] 陈侃，傅攀，李威霖等．钛合金车削加工过程中刀具磨损状态监测的小波包子带能量变换特征提取新方法[J]．组合机床与自动化加工技术，2011，6(1)：35-38．

[44] 邓丰曼．一种基于LMD与HMM的刀具磨损故障诊断方法[J]．机械设计与制造工程，2019，48(12)：111-114．

[45] 侍相龙，张屹，彭明松等．基于LDA和支持向量机的微铣刀磨损状态识别研究[J]．制造业自动化，2023，45(2)：179-183．

[46] 聂鹏，马尧，郭勇翼等．基于IPSO优化LS-SVM的铣削刀具磨损状态监测方法研究[J]．振动与冲击，2022，41(22)：137-143．

[47] 张建华，许衍彬，王雄伟．基于支持向量机和遗传算法的柔性砂带磨削刀具状态研究[J]．工具技术，2021，55(12)：55-59．

[48] Qian Y, Tian J, Liu L,et al. A tool wear predictive model based on SVM[C]. Chinese Control and Decision Conference. Hebei, 2010.

[49] Shi D, Gindy N N. Tool wear predictive model based on least squares support vector machines[J]. Mechanical Systems & Signal Processing, 2007,21(4): 1799-1814.

[50] Kira K, Rendell L A. The feature selection problem: Traditional methods and a new algorithm. Proceedings of 10th National Conference on Artificial Intelligence. San Jose, CA, USA. 1992: 129-134.

[51] Kononenko I. Estimating attributes: Analysis and extensions of RELIEF. Proceedings of the European Conference on Machine Learning. Catania, Italy. 1994. 171-182.