YANG Sha, GU Lichen, SHI Yuan, GENG Baolong, LIU Jiamin, ZHAO Baojian, WU Haoyu
（School of Mechatronic Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, China）
Abstract： Abundant system operation state information is included in the electrical signal of the hydraulic system motor. How to accurately extract and classify the operation information of electrical signal is the key to realize the condition monitoring of hydraulic system. The early fault characteristics of hydraulic gear pump hidden in the motor current signal are weak and difficult to extract by traditional time-frequency analysis. Based on the correlation coefficient and artificial bee colony algorithm (ABC), the parameter optimization of variational mode decomposition (VMD) is realized in this paper. At the same time, the principle of maximum signal correlation coefficient and kurtosis value is adopted to determine the effective intrinsic mode function (IMF). Moreover, the permutation entropy(PE) and root mean square(RMS) of the effective IMF components are input into the deep belief network (DBN-DNN) as high-dimensional feature vectors. The operation state of gear pump is monitored. The results show that the weak characteristics of current signal of gear pump fault are accurately and stably extracted by this method. The running state of gear pump is monitored and the accuracy of gear fault diagnosis is improved.
Key words： gear teeth fault； status monitoring； artificial bee colony algorithm (ABC)； variational mode decomposition (VMD)； deep belief network (DBN-DNN)
References
［1］Hang J, Zhang J Z, Cheng M, et al. An overview of condition monitoring and fault diagnostic for wind energy conversion system. Transactions of China Electrotechnical Society, 2013, 28(4): 261-271.
［2］Ding K, Li W H, Zhu X Y. Practical technology of gear and gearbox fault diagnosis. Beijing: Machinery Industry Press, 2005.
［3］Saadaoui W, Jelassi K. Gearbox-induction machine bearing fault diagnosis using spectral analysis. In: Proceedings of Second UKSIM European Symposium on Computer Modeling and Simulation, 2008: 347-352.
［4］Nagi R M. Helical gearbox fault detection using motor current signature analysis. Manchester: University of Manchester, 2007.
［5］Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
［6］Wu S J, Feng F Z, Wu C H, et al. Research on fault diagnosis method of tank planetary gearbox based on VMD-DE. Vibration and Impact, 2020, 39(10): 170-179.
［7］Sun C F, Wang Y R, Shen Y. Planetary gearbox fault diagnosis based on parameter adaptive variational mode decomposition. Journal of Aeronautical Dynamics, 2015, 33(11): 2756-2765.
［8］Zhou F C, Tang G J, He Y L. Wind power gearbox unbalanced fault feature extraction based on improved VMD. Vibration and Impact, 2020, 39(5): 170-176.
［9］Yang H G, Zhang H L, Jiang C, et al. Fault diagnosis of bearing combined variational mode decomposition with neural network. Machinery Design ＆ Manufacture, 2017, 6: 105.
［10］Men L C. Research on fault diagnosis method of planetary gearbox based on motor current. Taiyuan: Taiyuan University of Technology, 2019.
［11］Hinton G, Osindeo S, Teh Y W. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527-1554.
［12］Li W H, Shan W P, Zeng X Q. Bearing fault identification based on deep belief network. Journal of Vibration Engineering, 2016, 29(2): 340-347.
［13］Zheng X X, Chen G N, Ren H H. Fault warning for vulnerable parts of fan based on improved VMD and deep confidence network. Vibration and Impact, 2019, 38(8): 153-160.
［14］Blodt M, Granjon P, Raison B, et al. Models for bearing damage detection in induction motors using stator current monitoring, IEEE Transaction on Industrial Electronics, 2008, 55(4): 1813.
［15］Tang G J, Wang X L. Parameter optimized variational mode decomposition method with application to incipient fault diagnosis of rolling bearing. Journal of Xi’an Jiaotong University, 2015, 49(5): 73-81.
［16］Zhang X, Zhang X, Wang L. Antenna design by an adaptive variable differential artificial bee colony algorithm. IEEE Transactions on Magnetics, 2017, 9: 1-7.
［17］Zhang X, Liang Y, Zhou J. A novel bearing fault diagnosis model integrated permutation entrop, ensemble empirical mode decomposition and optimized SVM. Measurement, 2015, 69: 168-179.
［18］Donoso F A, Austin K J, Mcaree P R. Three new iterative closest point variant-methods that improve scan matching for surface mining terrain. Robotics & Autonomous Systems, 2017, 95: 117-128.
基于电信号的改进VMD和DBN-DNN液压齿轮泵轮齿故障监测方法研究
杨 莎， 谷立臣， 石 媛， 耿宝龙， 刘佳敏， 赵宝建， 仵浩宇
（西安建筑科技大学 机电工程学院， 陕西 西安 710055）
摘 要: 液压系统电机电信号中包含丰富的系统运行状态信息， 如何准确对电信号中的运行信息进行提取和分类是实现液压系统状态监测的关键。 电机电流信号中蕴含的液压齿轮泵早期故障特征微弱， 提取困难， 用传统时频分析方法难以实现故障特征分离。 本文提出基于相关系数和人工蜂群算法（Artificial bee colony, ABC）实现了对变分模态分解（Variational mode decomposition, VMD）参数的优化， 同时以信号相关系数和峭度值最大为选取原则， 确定有效的本征模态函数(Intrinsic mode function, IMF）， 并将IMF有效分量的排列熵和均方根值作为高维特征向量输入深度信念网络(Deep belief network, DBN-DNN)， 实现了对齿轮泵运行状态进行监测。 结果表明， 该方法能准确稳定地提取电流信号中携带的齿轮泵故障的微弱特征， 进行齿轮泵运行状态监测， 提高了齿轮故障诊断的准确性。
关键词: 轮齿故障； 状态监测； 人工蜂群算法； 变分模态分解法； 深度信念网络
引用格式： YANG Sha, GU Lichen, SHI Yuan, et al. Monitoring method of gear teeth failure of hydraulic gear pump based on improved VMD and DBN-DNN of electrical signal. Journal of Measurement Science and Instrumentation, 2021, 12（2）： 242-252. DOI： 10.3969／j.issn.1674-8042.2021.02.014
[full text view]
