基于一维卷积神经网络的齿轮箱故障诊断

PDF(1892 KB)

振动与冲击 ›› 2018, Vol. 37 ›› Issue (22) : 51-56.

论文

基于一维卷积神经网络的齿轮箱故障诊断

吴春志,江鹏程,冯辅周, 陈汤,陈祥龙

作者信息 +

Faults diagnosis method for gearboxes based on a 1-D convolutional neural network

WU Chunzhi,JIANG Pengcheng, FENG fuzhou,CHEN Tang,CHEN Xianglong

Author information +

文章历史 +

摘要

传统复合故障诊断方法通常需要先人工提取特征再用模式识别方法进行分类，难以解决端到端故障诊断的问题，为此，论文提出了一种利用一维卷积神经网络的齿轮箱故障诊断模型。其特点是可以直接从原始振动信号中学习特征并完成故障诊断。采用PHM 2009 Challenge Data和某型坦克变速箱的复合故障数据对三种传统模型和一维卷积神经网络模型进行测试，结果表明，1-DCNN模型对单一和复合故障诊断准确率均高于传统诊断方法。

Abstract

Traditional diagnosis methods need to extract features manually and classify faults by pattern recognition methods.It’s difficult to solve the problem of end-to-end fault diagnosis.Therefore, a one-dimensional convolution neural network (1-DCNN) model suitable for analyzing vibration data was established.The model can learn features directly from raw vibration data and complete fault diagnosis in succession.Three traditional models and the 1-DCNN model were tested with the compound fault data collected from PHM 2009 Challenge Data and a tank gearbox.The results show that the precision of the 1-DCNN model for single and complex fault diagnosis is higher than that of traditional diagnostic methods.

导出引用

吴春志,江鹏程,冯辅周, 陈汤,陈祥龙. 基于一维卷积神经网络的齿轮箱故障诊断[J]. 振动与冲击, 2018, 37(22): 51-56

WU Chunzhi,JIANG Pengcheng, FENG fuzhou,CHEN Tang,CHEN Xianglong. Faults diagnosis method for gearboxes based on a 1-D convolutional neural network[J]. Journal of Vibration and Shock, 2018, 37(22): 51-56

参考文献

[1] C. LI, et al., Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals, Mech. Syst. Signal Process. 76 (2016) 283–293.
[2] S. Polak, Gearbox and gear system problems, in: Gears Conf. London, GEAR TECH., Imeche seminar, 1999, pp. 65–72.
[3] 罗毅,甄立敬.基于小波包与倒频谱分析的风电机组齿轮箱齿轮裂纹诊断方法[J].振动与冲击, 2015, (3): 210-214.
    LUO Yi, ZHEN Li-jing. Diagnosis method of turbine gearbox gearcrack based on wavelet packet and cepstrum analysis[J]. Journal of Vibration and Shock, 2015, (3): 210-214.
[4] 赵德尊,李建勇,程卫东等.变转速及齿轮噪源干扰下基于IDMM与EMD的滚动轴承故障诊断方法[J].振动与冲击, 2016, 35(10):101-107,119.
     ZHAO De-zun, LI Jian-yong, CHENG Wei-dong, et al. Method for rolling element bearing fault diagnosis based on IDMM and EMD under time-varying rotational speed and gear noise[J]. Journal of Vibration and Shock, 2016, 35(10): 101-107,119.
[5] 季忠,黄捷,秦树人等.提升小波在齿轮箱故障诊断中的应用[J].振动、测试与诊断, 2010, 30(3): 291-294.
     JI Zhong, HUANG Jie, QIN Shu-ren, et al. Gearbox Fault Diagnosis Using Lifting Wavelet[J]. Journal of Vibration measurement & diagnosis, 2010, 30(3): 291-294.
[6] 褚青青,肖涵,吕勇等.基于多重分形理论与神经网络的齿轮故障诊断[J].振动与冲击, 2015, (21):15-18.
     CHU Qing-qing, XIAO Han, Lv Yong, et al. Gear fault diagnosis based on multifractal theory and neural network[J]. Journal of Vibration and Shock, 2015, (21):15-18.
[7] 张超,陈建军,郭迅等.基于EEMD能量熵和支持向量机的齿轮故障诊断方法[J].中南大学学报（自然科学版）, 2012, 43(3): 932-939.
     ZHANG Chao, CHEN Jian-jun, GUO Xun, et al. Gear fault diagnosis method based on ensemble empirical mode decomposition energy entropy and support vector machine[J]. Journal of Central South University, 2012, 43(3): 932-939.
[8] G.E. Hinton, R.R. Salakhutdinov, Reducing the dimensionality of data with neural networks, Science 313 (5786) (2006) 504-507.
[9] R. Girshick, et al., Rich feature hierarchies for accurate object detection and semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014.
[10] J. Tompson, et al., Efficient object localization using convolutional networks, 2015, pp. 648-656.
[11] CHEN Z.Q，LI C，SANCHEZ R.V． Gearbox Fault Identification andClassification with Convolutional Neural Networks［J］．Shock＆Vi-bration，2015，2015(2):1-10．
[12] 韩涛,袁建虎,唐建,安立周. 基于MWT和CNN的滚动轴承智能复合故障诊断方法[J]. 机械传动, 2016, 40(12): 139-143.
    HAN Tao, YUAN Jian-hu, TANG Jian, AN Li-zhou. An Approach of Intelligent Compound Fault Diagnosis of Rolling Bearing based on MWT and CNN[J]. Journal of Mechanical Transmission, 2016, 40(12): 139-143.
[13] 袁建虎,韩涛,唐建,安立周. 基于小波时频图和CNN的滚动轴承智能故障诊断方法[J]. 机械设计与研究, 2017, 33(02): 93-97.
     YUAN Jian-hu, HAN Tao, TANG Jian, AN Li-zhou. An Approach to Intelligent Fault Diagnosis of Rolling Bearing[J]. Machine Design & Research, 2017, 33(02): 93-97.
[14] Sun W.F, Bin Y, Zeng N.Y, et al. An Intelligent Gear Fault Diagnosis Methodology Using a Complex Wavelet Enhanced Convolutional Neural Network. Materials ,2017, 10, 790.
[15] L Jing, M Zhao, P Li, X Xu, A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox[J]. Measurement, 111 (2017) 1–10.
[16] PHM data challenge 2009. Available from: <https://www.phmsociety.org/competition/PHM/09>.