Application of Deep Learning in Robot Milling Chattering Identification
-
摘要: 工业机器人在大型复杂零件的加工中被广泛应用，由其低刚度引发颤振问题是目前学者研究的重要领域之一。本文针对机器人铣削颤振辨识问题，使用变分模态分解-连续小波变换（VMD-CWT）方法对加工过程中产生的振动信号进行处理，构建去噪时频谱图表征机器人颤振状态并作为辨识模型的输入。使用深度残差卷积网络模型对其进行辨识，并通过确定连续小波变换的分解尺度和引入输入归一化，提升模型的收敛速度和预测精度。优化后模型的预测精度可达到95.28%。实现了离线状态下，对时频谱图的颤振状态辨识。Abstract: Industrial robots are widely used in the processing of large and complex parts. In this paper, for the problem of robot milling chatter identification, the variational mode decomposition-continuous wavelet transform (VMD-CWT) method is used to process the vibration signal collected during processing, and the denoising time-frequency spectrums are constructed to characterize the robot vibration states and used as the input of the identification model. The residual convolution network (ResNet) is used to identify the spectrums, and the convergence speed and prediction accuracy of the model are improved by determining the decomposition scale of wavelet transform and introducing input normalization. The prediction accuracy of the optimized model can reach 95.28%.The vibration state identification of the time-frequency spectrum graph is realized offline.
-
Key words:
- robot /
- chattering identification /
- ResNet /
- variational mode decomposition /
- wavelet transform
-
[1] LI X, YAO Z H, CHEN Z C. An effective EMD-based feature extraction method for boring chatter recognition[J]. Applied Mechanics and Materials, 2010, 34-35: 1058-1063 doi: 10.4028/www.scientific.net/AMM.34-35.1058 [2] CAO H R, ZHOU K, CHEN X F. Chatter identification in end milling process based on EEMD and nonlinear dimensionless indicators[J]. International Journal of Machine Tools and Manufacture, 2015, 92: 52-59 doi: 10.1016/j.ijmachtools.2015.03.002 [3] ZHANG Z, LI H G, MENG G, et al. Chatter detection in milling process based on the energy entropy of VMD and WPD[J]. International Journal of Machine Tools and Manufacture, 2016, 108: 106-112 doi: 10.1016/j.ijmachtools.2016.06.002 [4] 杨志刚. 基于主轴电机电流信号的镗削颤振监测研究[D]. 武汉: 华中科技大学, 2012.YANG Z G. Chatter detection in boring operations using spindle motor current[D]. Wuhan: Huazhong University of Science and Technology, 2012 (in Chinese). [5] 张攀. 数控机床在线振动监测与故障诊断关键技术研究[D]. 天津: 天津大学, 2014.ZHANG P. Research on vibration online monitoring and fault diagnosis of CNC machine tools[D]. Tianjin: Tianjin University, 2014 (in Chinese). [6] 韩振宇, 金鸿宇, 富宏亚. 基于ESPRIT频谱估计和隐马尔可夫模型的铣削颤振辨识系统建模[J]. 计算机集成制造系统, 2016, 22(8): 1937-1944HAN Z Y, JIN H Y, FU H Y. Modeling of chatter recognition system in CNC milling based on ESPRIT and hidden Markov model[J]. Computer Integrated Manufacturing Systems, 2016, 22(8): 1937-1944 (in Chinese) [7] LIU J, WU B, WANG Y, et al. An integrated condition-monitoring method for a milling process using reduced decomposition features[J]. Measurement Science and Technology, 2017, 28(8): 085101 doi: 10.1088/1361-6501/aa6bcc [8] 刘长福, 朱立达, 仇健, 等. 基于VMD和FFT的变切深侧铣颤振特征提取方法[J]. 东北大学学报, 2018, 39(8): 1153-1157LIU C F, ZHU L D, QIU J, et al. Chatter feature extraction method in variable cutting depth flank milling based on VMD and FFT[J]. Journal of Northeastern University, 2018, 39(8): 1153-1157 (in Chinese) [9] 吴杨宝. 工业机器人精镗飞机交点孔的颤振分析与识别[D]. 杭州: 浙江大学, 2018.WU Y B. Chatter analysis and identification in industrial robotic fine boring of aircraft intersection holes[D]. Hangzhou: Zhejiang University, 2018 (in Chinese). [10] AMAR M, GONDAL I, WILSON C. Vibration spectrum imaging: a novel bearing fault classification approach[J]. IEEE Transactions on Industrial Electronics, 2015, 62(1): 494-502 doi: 10.1109/TIE.2014.2327555 [11] WANG P, ANANYA, YAN R Q, et al. Virtualization and deep recognition for system fault classification[J]. Journal of Manufacturing Systems, 2017, 44: 310-316 doi: 10.1016/j.jmsy.2017.04.012 [12] OH H, JUNG J H, JEON B C, et al. Scalable and unsupervised feature engineering using vibration-imaging and deep learning for rotor system diagnosis[J]. IEEE Transactions on Industrial Electronics, 2018, 65(4): 3539-3549 doi: 10.1109/TIE.2017.2752151 [13] ZHU Z Y, PENG G L, CHEN Y H, et al. A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis[J]. Neurocomputing, 2019, 323: 62-75 doi: 10.1016/j.neucom.2018.09.050 [14] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778. [15] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544 doi: 10.1109/TSP.2013.2288675 -
下载:
点击查看大图
图(8)
计量
- 文章访问数: 190
- HTML全文浏览量: 62
- PDF下载量: 47
- 被引次数: 0
