针对无法精确掌控机械加工过程中刀具磨损状态的现状，提出一种基于多传感器信息决策级融合的刀具磨损在线动态监测模型。该模型对采集的振动、力、声发射传感器信号进行特征提取后，将特征按传感器类型划分为独立样本。划分后的独立样本分别对同一个刀具磨损量进行回归预测，进而对每一个独立样本预测得到的刀具磨损量进行加权综合决策，最终决策出刀具磨损量。实验结果表明：刀具磨损在线动态监测模型能够有效地提高刀具磨损动态预测精度，平均预测准确率可达97.9%；与现有研究方法相比，预测准确率至少提升4%以上，预测时间仅为0.016 s，具有较大优势。
Abstract
An online dynamic monitoring model of tool wear based on multi-sensor information decision-making level fusion is proposed for accurately controlling the tool wear state in the machining process. After extracting the time, frequency and time-frequency features from the collected vibration, force and acoustic emission sensor signals, the monitoring model divides the sensor signal features into independent samples according to the sensor type. The same tool wear extent is regressively predicted using the independent samples, respectively. Then the tool wear extent predicted from the signal characteristics of each sensor is comprehensively determined. Finally, the tool wear extent is determined. The experimental results show that the on-line dynamic monitoring model of tool wear can effectively improve the accuracy of tool wear dynamic prediction, and the average prediction accuracy is 97.9%. Compared with existing research methods, the proposed method is used to increase the prediction accuracy rate by at least 4%, and the prediction time is only 0.016 s.
关键词
刀具磨损 /
在线监测 /
信息决策级融合 /
多层神经网络 /
特征提取
{{custom_keyword}} /
Key words
toolwear /
onlinemonitoring /
informationdecision-makinglevelfusion /
multi-layerneuralnetwork /
featureextraction
{{custom_keyword}} /
基金
国家重点研发计划项目（2018YFB2002205）；国家自然科学基金项目（52075267）；中央高校基本科研业务费专项项目（30920010005）
{{custom_fund}}
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］王凯，孙剑飞，杜大喜，等.硬质合金刀具月牙洼磨损定量化实验研究［J］.兵工学报,2017,38(8): 1578-1585.
WANG K,SUN J F,DU D X,et al.Quantitative experimental ana-lysison crater wear of cemented carbide tools［J］.Acta Armamentarii,2017,38(8):1578-1585.(in Chinese)
［2］CHENN,HAO B J,GUO Y L,et al.Research on tool wear monitoring in drilling process based on APSO-LS-SVM approach［J］. International Journal of Advanced Manufacturing Technology, 2020, 108: 2091-2101.
［3］金成哲，贾春德，庞思勤，等.正交车铣高强度钢刀具磨损的研究［J］.兵工学报,2005,26(3):397-400.
JIN C Z,JIA C D,PANG S Q,et al.Wearing mechanism of tools in the orthogonal turn-milling of high strength steel［J］.Acta Armamentarii,2005,26(3):397-400.(in Chinese)
［4］PENG R T,PANG H L,JIANG H J,et al.Study of tool wear monitoring using machine vision［J］.Automatic Control and Computer Sciences,2020,54(3):259-270.
［5］SHI X C,WANG X B,JIAO L,et al.A real-time tool failure monitoring system based on cutting force analysis［J］.The International Journal of Advanced Manufacturing Technology,2018, 95：2567-2583.
［6］张锴锋,袁惠群,聂鹏.基于广义维数与优化BP神经网络的刀具磨损量预测［J］.东北大学学报(自然科学版),2013,34(9): 1292-1295.
ZHANG K F,YUAN H Q,NIE P.Prediction of tool wear based on generalized dimensions and optimized BP neural network［J］.Journal of Northeastern University(Natural Science), 2013,34(9): 1292-1295. (in Chinese)
［7］PETER M,KATARINA M,MAREK U,et al. Vibrodiagnostics as the tool of a tap wear monitoring［J］.Procedia Structural Integrity,2018,13:959-964.
［8］AKBARI A,DANESH M,KHALILI K.A method based on spindle motor current harmonic distortion measurements for tool wear monitoring［J］.Journal of The Brazilian Society of Mechanical Sciences and Engineering, 2017,39:5049-5055.
［9］FU P,HOPE A D,GAO H L.A neural-fuzzy pattern recognition algorithm based cutting tool condition monitoring procedure［C］∥Proceedings of the 3rd International Conference on Natural Computation. Haikou, China: IEEE, 2007.
［10］DUOA,BASAGOITI R,ARRAZOLA P J,et al.The capacity of statistical features extracted from multiple signals to predict tool wear in the drilling process［J］.The International Journal of Advanced Manufacturing Technology, 2019,102: 2133-2146.
［11］HUANG Z W, ZHU J M, LEI J T, et al. Tool wear predicting based on multi domain feature fusion by deep convolutional neural network in milling operations［J］. Journal of Intelligent Manufacturing,2020,31(4): 953-966.
［12］ZHAO R,WANG J J,YAN R Q,et al.Machine health monitoring with LSTM networks［C］∥Proceedings of the 2016 10th International Conference on Sensing Technology. Nanjing, China：IEEE, 2016.
［13］ZHANG K F,YUAN H Q,NIE P.A method for tool condition monitoring based on sensor fusion［J］. Journal of Intelligent Manufacturing,2015,26(5):1011-1026.
［14］LI X H,LIM B S,ZHOU J H, et al. Fuzzy neural network modelling for tool wear estimation in dry milling operation［C］∥Proceedings of the Annual Conference of the Prognostics and Health Management Society. Montreal,QC,Canada: the Prognostics and Health Management Society, 2009.
［15］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(1):74-80.
CAO D L,SUN H B,ZHANG J D,et al.In-process tool condition monitoring based on convolution neural network［J］.Computer Integrated Manufacturing Systems,2020,26(1):74-80. (in Chinese)
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
