基于改进EMD和GA-BPNN的机器人磨削颤振监测

PDF(3130 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (9) : 131-138.

论文

刘伟，刘旺，曹大虎，葛吉民，万林林，陈加

作者信息 +

Robot grinding chatter monitoring based on improved EMD and GA-BPNN

LIU Wei, LIU Wang, CAO Dahu, GE Jimin, WAN Linlin, CHEN Jia

Author information +

文章历史 +

摘要

工业机器人由于其灵活性，被广泛应用于机器人焊缝磨削任务中。但由于机器人的弱刚性，在焊缝磨削过程中系统容易发生颤振，因此对加工过程中的颤振监测是保证加工质量的基础。针对在加工振动信号处理过程中的模态混叠现象，提出了一种基于排列熵算法改进的经验模态分解方法，通过排列熵算法检测振动信号中的异常信号并剔除。通过相关系数法提取相关性最大的固有模态函数的能量熵作为特征值，同时提取方差、峰峰值、均方根和峭度四种时域特征。利用遗传算法优化BP神经网络（back propagation neural network，BPNN）建立颤振辨识模型，最后将提取的五种特征参数作为特征向量代入辨识模型中对加工状态进行监测。试验结果显示，提出的改进经验模态分解算法结合遗传算法优化的BP神经网络模型能够有效地对机器人焊缝磨削中的颤振进行监测。

Abstract

Industrial robots are widely used in robotic weld seam grinding tasks due to their flexibility. However, due to the weak rigidity of the robot, the system is prone to chattering in the process of weld grinding, so the monitoring of chattering in the machining process is the basis for ensuring the machining quality. Aiming at the phenomenon of modal aliasing in the processing of vibration signals, an improved empirical modal decomposition method based on the arrangement entropy algorithm was proposed, and the abnormal signals in the vibration signals were detected and eliminated by the arrangement entropy algorithm. The energy entropy of the intrinsic mode function with the largest correlation was extracted as the eigenvalue by the correlation coefficient method, and the four time-domain features of variance, peak-to-peak, root-mean-square, and crag were extracted at the same time. Using genetic algorithm to optimize the BP neural network to establish the chatter recognition model, and finally the five extracted feature parameters were substituted into the recognition model as feature vectors to monitor the machining state. The experimental results show that the proposed improved empirical modal decomposition algorithm combined with the BP neural network model optimized by genetic algorithm can effectively monitor the chatter in robotic weld grinding.

导出引用

刘伟，刘旺，曹大虎，葛吉民，万林林，陈加. 基于改进EMD和GA-BPNN的机器人磨削颤振监测[J]. 振动与冲击, 2024, 43(9): 131-138

LIU Wei, LIU Wang, CAO Dahu, GE Jimin, WAN Linlin, CHEN Jia. Robot grinding chatter monitoring based on improved EMD and GA-BPNN[J]. Journal of Vibration and Shock, 2024, 43(9): 131-138

参考文献

[1] WU G, LI G X, PAN W C, et al. A state-of-art review on chatter and geometric errors in thin-wall machining processes[J]. Journal of Manufacturing Processes, 2021, 68: 454-480. [2] MARCEL C, WOLFGANG H, YUSUF A. Chatter stability in robotic milling[J]. Robotics and Computer-Integrated Manufacturing, 2019, 55(1): 11-18. [3] LI X, WAN S, HUANG X. et al. Milling chatter detection based on VMD and difference of power spectral entropy[J]. The International Journal of Advanced Manufacturing Technology, 2020, 111: 2051–2063. [4] YAO Z H, MEI D Q, CHEN Z C. On-line chatter detection and identification based on wavelet and support vector machine[J]. Journal of Materials Processing Technology, 2010, 210(5): 713-719. [5] 熊振华, 孙宇昕, 丁龙杨. 智能车床的颤振实时辨识与在线抑制系统研究[J]. 机械工程学报, 2018, 54(17): 85-93. XIONG Zhenhua, SUN Yuxi, DING Longyang. Research on real-time identification and on-line suppression system for chattering of intelligent lathes[J]. Journal of Mechanical Engineering, 2018, 54(17): 85-93. [6] LIU T, DENG Z H, LUO C Y, et al. Chatter detection in camshaft high-speed grinding process based on VMD parametric optimization[J]. Measurement, 2022, 187: 1-13. [7] 顾文景, 周丽. 改进VMD算法在颤振试验信号模态参数辨识中的应用[J]. 振动工程学报, 2021, 34(2): 292-300. GU Wenjing, ZHOU Li. Application of Improved VMD algorithm for identification of modal parameters of flutter test signals[J]. Journal of Vibration Engineering, 2021, 34(2): 292-300. [8] 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. [9] 陈龙, 张纯龙. 基于EMD包络谱特征与PCA-PNN的滚动轴承故障诊断[J]. 煤矿机械, 2022, 43(10): 173-176. CHEN Long, ZHANG Chunlong. Rolling bearing fault diagnosis based on EMD envelope spectral features and PCA-PNN[J]. Coal Mine Machinery, 2022, 43(10): 173-176. [10] 王冉, 周雁翔, 胡雄, 等. 基于EMD多尺度威布尔分布与HMM的轴承性能退化评估方法[J]. 振动与冲击, 2022, 41(3): 209-215. WANG Ran, ZHOU Yanxiang, HU Xiong, et al. Evalution method of bearing performance degradation based on EMD multi-scale Weibull distribution and HMM[J]. Journal of Vibration and Shock, 2022, 41(3): 209-215. [11] YOGESH S, BHAGAT S, AMIT S. Identification of chatter in turning operation using WD and EMD[J]. Materials Today: Proceedings, 2018, 5(11): 23917-23926. [12] 密思佩, 徐锦泱, 明伟伟, 等. 基于EMD和SVM的缸盖加工颤振在线检测[J]. 工具技术, 2020, 54(2): 74-77. MI Sipei, XU Jinyang, MING Weiwei, et al. In-situ detection of machining chatter of cylinders based on EMD and SVM mathods[J]. Tool Technology, 2020, 54(2): 74-77. [13] PELIN S, BATIHAN Ş, A.MURAT Ö, et al. An evaluation study of EMD, EEMD, and VMD for chatter detection in milling[J]. Procedia Computer Science, 2022, 200: 160-174. [14] 吴石, 张轩瑞, 刘献礼. 基于CEEMD和GWO-SVR的铣削振动信号前瞻预测[J]. 振动与冲击, 2022, 41(11): 199-209+234. WU Shi, ZHANG Xunrui, LIU Xianli. Forward-looking prediction of milling vibration signal based on CEEMD and GWO-SVR[J]. Journal of Vibration and Shock, 2022, 41(11): 199-209+234. [15] 张明锴. 基于残差卷积网和支持向量机的机器人铣削颤振辨识研究[D].华中科技大学, 2019. [16] 朱欢欢, 李厚佳, 张梦梦, 等. 基于BP神经网络的外圆磨削颤振在线识别和监测方法[J]. 金刚石与磨料磨具工程, 2022, 42(1): 104-111. ZHU Huanhuan, LI Houjia, ZHANG Mengmeng, et al. Online identification and monitoring of chatter in cylindrical grinding based on BP neural network[J]. Diamond & Abrasives Engineering, 2022, 42(1): 104-111. [17] 李欣, 邓小雷, 张玉良, 等. 基于隐马尔科夫模型和支持向量机的曲面加工颤振识别与预报[J]. 航空制造技术, 2019, 62(6): 14-20. LI Xin, DENG Xiaolei, ZHANG Yuliang, et al. Identification and prediction of surface machining chatter based on hidden markov models and support vector machines[J]. Aeronautical Manufacturing Technology, 2019, 62(6): 14-20. [18] YUE C X, XIE Z L, LIU X L, et al. Chatter prediction of milling process for titanium alloy thin-walled workpiece based on EMD-SVM[J]. Journal of Advanced Manufacturing Science and Technology, 2022, 2(2): 2022010. [19] 李鹏伟. 基于小波包熵和排列熵的机器人磨削末端颤振检测研究[D]. 河北工业大学, 2022.