基于IGA-ELM网络的滚动轴承故障诊断

皮骏; 马圣; 贺嘉诚; 孔庆国; 林家泉; 刘光才

doi:10.7527/S1000-6893.2018.22025

航空学报 >

2018 , Vol. 39 >Issue 9: 422025 - 422036

DOI: https://doi.org/10.7527/S1000-6893.2018.22025

材料工程与机械制造

基于IGA-ELM网络的滚动轴承故障诊断

皮骏 ,
马圣 ,
贺嘉诚 ,
孔庆国 ,
林家泉 ,
刘光才

展开

1. 中国民航大学通用航空学院, 天津 300300;
2. 中国民航大学航空工程学院, 天津 300300;
3. 中国民航大学中欧航空工程师学院, 天津 300300;
4. 中国民航大学电子信息与自动化学院, 天津 300300

收稿日期: 2018-01-17

修回日期: 2018-03-14

网络出版日期: 2018-06-01

基金资助

中央高校基本科研业务费项目中国民航大学专项资助（3122017056）

收起

Rolling bearing fault diagnosis based on IGA-ELM network

PI Jun ,
MA Sheng ,
HE Jiacheng ,
KONG Qingguo ,
LIN Jiaquan ,
LIU Guangcai

Expand

1. General Aviation College, Civil Aviation University of China, Tianjin 300300, China;
2. College of Aeronautical Engineering, Civil Aviation University of China, Tianjin 300300, China;
3. Sino-European Institute of Aviation Engineering, Civil Aviation University of China, Tianjin 300300, China;
4. College of Electronic information and Automation, Civil Aviation University of China, Tianjin 300300, China

Received date: 2018-01-17

Revised date: 2018-03-14

Online published: 2018-06-01

Supported by

Central University Basic Research Business Fee Project Civil Aviation University of China Special Funding (3122017056)

Fold

摘要

为了提高航空发动机轴承故障诊断准确率，提出基于改进遗传算法优化极限学习机网络（IGA-ELM）的诊断模型。针对传统遗传算法易早熟等缺陷，对遗传算法的交叉操作和变异操作进行改进，并用改进的遗传算法优化极限学习机的输入权值矩阵和隐含层阈值，利用Moore-Penrose算法计算极限学习机的输出权值矩阵。使用IGA-ELM诊断模型对滚动轴承正常、内环故障、外环故障和滚珠故障4种工况进行诊断，并分析极限学习机隐含层神经元的数量和激活函数对轴承故障诊断的影响。为了验证改进遗传算法优化极限学习机的有效性，将传统遗传算法、自适应遗传算法和粒子群算法作为对比算法。经过分析表明：改进遗传算法收敛速度和收敛误差，均优于对比算法。

关键词： 航空发动机; 轴承故障诊断; 极限学习机; 交叉操作; 变异操作; 遗传算法

本文引用格式

皮骏 , 马圣 , 贺嘉诚 , 孔庆国 , 林家泉 , 刘光才 . 基于IGA-ELM网络的滚动轴承故障诊断[J]. 航空学报, 2018 , 39(9) : 422025 -422036 . DOI: 10.7527/S1000-6893.2018.22025

Abstract

To improve the accuracy of fault diagnosis of aero-engine bearings, a diagnosis model is proposed based on the Optimized Extreme Learning Machine by Improved Genetic Algorithm (IGA-ELM). Crossover operation and mutation operation of the genetic algorithm is improved in this paper to overcome the flaw of the traditional genetic algorithm. The input weight matrix of the connection between the input and hidden layers and biases of hidden neurons of the extreme learning machine is optimized by the improved genetic algorithm. The output matrix of the connection between the hidden and output layers was calculated by using the Moore-Penrose algorithm. Four cases including normal rolling bearing, inner ring fault, out ring fault, and ball fault are diagnosed by using the optimized extreme learning machine. The influence of the number of the hidden layer neurons and the activation function on bearing fault diagnosis of the extreme learning machine is also analyzed. To verify to, as a comparative algorithm A comparison of the traditional genetic algorithm, adaptive genetic algorithm and particle swarm optimization algorithm shows the effectiveness of the improved genetic algorithm in extreme learning machine optimization. Analysis shows that the improved genetic algorithm are better than the other algorithms in terms of convergence speed and convergence error.

Key words： aero-engine; bearing fault diagnosis; extreme learning machine; crossover operation; mutation operation; genetic algorithm

参考文献

[1] 皮骏, 黄江博. 基于IPSO-Elman神经网络的航空发动机故障诊断[J]. 航空动力学报, 2017, 32(12):3031-3038. PI J, HUANG J B. Aero-engine fault diagnosis based on IPSO-Elman neural network[J]. Journal of Aerospace Power, 2017, 32(12):3031-3038(in Chinese).
[2] 孙灿飞, 王友仁. 直升机行星传动轮系故障诊断研究进展[J]. 航空学报, 2017, 38(7):111-124. SUN C F, WANG Y R. Advance in study of fault diagnosis of helicopter planetary gears[J]. Acta Aeronautica et Astronautica Sinca, 2017, 38(7):111-124(in Chinese).
[3] HE J J, QI R Y, JIANG B, et al. Fault-tolerant control with mixed aerodynamic surfaces and RCS jets for hypersonic reentry vehicles[J]. Chinese Journal of Aeronautics,2017, 30(2):780-795.
[4] DESAVALE R G, KANAI R A, CHAVAN S P, et al. Vibration characteristics diagnosis of roller bearing using the new empirical model[J]. Journal of Tribology, 2016, 138(1):4031065.
[5] 廖明夫, 马振国, 刘永泉, 等. 航空发动机中介轴承的故障特征与诊断方法[J]. 航空动力学报, 2013, 28(12):2752-2758. LIAO M F, MA Z G, LIU Y Q, et al. Fault characteristics and diagnosis method of intershaft bearing in aero-engine[J]. Journal of Aerospace Power, 2013, 28(12):2752-2758(in Chinese).
[6] 赵志宏, 杨绍普. 一种基于样本熵的轴承故障诊断方法[J]. 振动与冲击, 2012, 31(6):136-140. ZHAO Z H, YANG S P. Sample entropy-base roller bearing fault diagnosis method[J]. Journal of Vibration and Shock, 2012, 31(6):136-140(in Chinese).
[7] 向丹, 岑健. 基于EMD熵特征融合的滚动轴承故障诊断方法[J]. 航空动力学报, 2015, 30(5):1149-1155. XIANG D, CEN J. Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J]. Journal of Aerospace Power, 2015, 30(5):1149-1155(in Chinese).
[8] 万书亭, 佟海侠, 董炳辉. 基于最小二乘支持向量机的滚动轴承故障诊断[J]. 振动、测试与诊断, 2010, 30(2):149-152. WAN S T, TONG H X, DONG B H. Bearing fault diagnosis using wavelet packet transform and least square support vector machines[J]. Journal of Vibration, Measurement & Diagnosis, 2010, 30(2):149-152(in Chinese).
[9] 郑红, 周雷, 杨浩. 基于小波包分析与多核学习的滚动轴承故障诊断[J]. 航空动力学报, 2015, 30(12):3035-3042. ZHENG H, ZHOU L, YANG H. Rolling bearing fault diagnosis based on wavelet packet analysis and multi kernel learning[J]. Journal of Aerospace Power, 2015, 30(12):3035-3042(in Chinese).
[10] ALI J B, FNAIECH N, SAIDI L, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals[J]. Applied Acoustics, 2015, 89(3):16-27.
[11] KANAI R A, DESAVALE R G, CHAVAN S P. Experimental-based fault diagnosis of rolling bearings using artificial neural network[J]. Journal of Tribology, 2016, 138(3):4032525.
[12] GOU Y Y, LI H B, DONG X M, et al. Constrained adaptive neural network control of an MIMO aeroelastic system with input nonlinearities[J]. Chinese Journal of Aeronautics, 2017, 30(2):796-806.
[13] PI J, HUANG J B, MA L. Aero-engine fault diagnosis using optimized Elman neural network[J]. Mathematical Problems in Engineering, 2017(9):1-8.
[14] ZHAO N, ZHENG H, YANG L, et al. A fault diagnosis approach for rolling element bearing based on S-transform and artificial neural network[C]//ASME Turbo Expo:Power for Land, Sea, and Air, Volume 6:Ceramics; Controls, Diagnostics and Instrumentation; Education; Manufacturing Materials and Metallurgy, 2017:V006T05A003.
[15] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine:Theory and applications[J]. Neurons Computing, 2006, 70(1-3):489-501.
[16] 卢锦玲, 绳菲菲, 赵洪山. 基于极限学习机的风电机组主轴承故障诊断方法[J]. 可再生能源, 2016, 34(11):1588-1594. LU J L, SHENG F F, ZHAO H S. Fault diagnosis method of wind turbine main bearing based on extreme learning machine[J]. Renewable Energy Resources, 2016, 34(11):1588-1594(in Chinese).
[17] 徐继亚, 王艳, 纪志成. 基于鲸鱼算法优化WKELM的滚动轴承故障诊断[J]. 系统仿真学报,2017(9):2189-2197. XU J Y, WANG Y, JI Z C. Fault diagnosis method of rolling bearing based on WKELM optimized by whale optimization algorithm[J]. Journal of System Simulation, 2017(9):2189-2197(in Chinese).
[18] YANG X, PANG S, SHEN W, et al. Aero-engine fault diagnosis using an optimized extreme learning machine[J]. International Journal of Aerospace Engineering, 2016:7892875.
[19] LU J, HUANG J, LU F. Sensor fault diagnosis for aero-engine based on online sequential extreme learning machine with memory principle[J]. Energies, 2017, 10(1):39.
[20] ZHU Q Y, QIN A K, SUGANTHAN P N, et al. Evolutionary extreme learning machine[J]. Pattern Recognition, 2005, 38(10):1759-1763.
[21] 关晓颖, 陈果, 林桐. 特征选择的多准则融合差分遗传算法及其应用[J]. 航空学报, 2016, 37(11):3455-3465. GUAN X Y, CHEN G, LIN T. Feature selection method based on differential evolution and genetic algorithm with multi-criteria evaluation and its applications[J]. Acta Aeronautica et Astronautica Sinca,2016,37(11):3455-3465(in Chinese).
[22] YAN M F, HU H, OTAKE Y, et al. Improved adaptive genetic algorithm with sparsity constraint applied to thermal neutron CT reconstruction of two phase flow[J]. Measurement Science & Technology, 2018, 29(5):055404.
[23] LAM H K, LING S H, LEUNG F H F, et al. Tuning of the structure and parameters of neural network using an improved genetic algorithm[C]//Conference of the IEEE 2001 Industrial Electronics Society, 2003:25-30.
[24] HUANG G B, CHEN L, SIEW C K. Universal approximation using incremental constructive feed-forward networks with random hidden nodes[J]. IEEE Transactions on Neural Networks, 2006, 17(4):879.
[25] MATIAS T,SOUZA F,SOUZA F, et al. Learning of a single-hidden layer feed-forward neural network using an optimized extreme learning machine[J]. Neuro Computing, 2014, 129:428-436.
[26] 郁磊, 史峰, 王辉, 等. MATLAB智能算法30个案例分析[M]. 2版. 北京:北京航空航天大学出版社, 2016:8. YU L, SHI F, WANG H, et al. Intelligent algorithm of MATLAB 30 case analysis[M]. 2nd ed. Beijing:Beihang University Press, 2016:8(in Chinese).

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献