基于OHF Elman-AdaBoost算法的滚动轴承故障多时期诊断方法

PDF(1347 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (6) : 71-78.

论文

卓鹏程1，夏唐斌1,2，郑美妹1，郑宇1，奚立峰1,2

作者信息 +

Multi-period fault diagnosis of rolling bearings based on the OHF Elman-AdaBoost algorithm

ZHUO Pengcheng1，XIA Tangbin1,2，ZHENG Meimei1，ZHENG Yu1，XI Lifeng1,2

Author information +

文章历史 +

摘要

针对随机噪声下滚动轴承多时期(初期、中期、晚期)故障诊断需求，提出OHF Elman-AdaBoost (output hidden feedback Elman-adaptive boosting)算法，以实现滚动轴承的精确故障诊断。采用集合经验模态分解(ensemble empirical mode decomposition, EEMD)对原始信号进行分解、降噪、信号重构。设计OHF Elman方法在Elman神经网络的基础上增加输出层对隐含层的反馈，提高了其对动态数据的记忆功能。选择OHF Elman神经网络作为弱回归器，结合AdaBoost算法集成出一种新的强回归器：OHF Elman-AdaBoost算法。实验结果表明，该算法不仅对滚动轴承不同故障时期具有很好的诊断效果，而且提高了对全样本数据的诊断准确度，为滚动轴承故障诊断提供了新型工具和有效方案。

Abstract

In order to meet the needs of the multi-period fault diagnosis of rolling bearings under random noise, the OHF Elman-AdaBoost (output hidden feedback Elman-adaptive boosting) algorithm was proposed to achieve the accurate fault diagnosis of rolling bearings.The original signal was decomposed, denoised and reconstructed by the ensemble empirical mode decomposition (EEMD).The OHF Elman neural network improved the memory function for its dynamic data by adding feedback from the output layer to the hidden layer based on the Elman neural network.Then, a strong regressor (OHF Elman-AdaBoost algorithm) was integrated by selecting the OHF Elman neural network as the weak regressor and combining with the AdaBoost algorithm.The experimental results show that the OHF Elman-AdaBoost algorithm not only has a good diagnostic effect on different periods of rolling bearing faults, but also improves the diagnostic accuracy of the full sample data, providing a new tool and effective solution for the fault diagnosis.

导出引用

卓鹏程1，夏唐斌1,2，郑美妹1，郑宇1，奚立峰1,2. 基于OHF Elman-AdaBoost算法的滚动轴承故障多时期诊断方法[J]. 振动与冲击, 2021, 40(6): 71-78

ZHUO Pengcheng1，XIA Tangbin1,2，ZHENG Meimei1，ZHENG Yu1，XI Lifeng1,2. Multi-period fault diagnosis of rolling bearings based on the OHF Elman-AdaBoost algorithm[J]. Journal of Vibration and Shock, 2021, 40(6): 71-78

参考文献

［1］XIA T, DONG Y, XIAO L, et al.Recent advances in prognostics and health management for advanced manufacturing paradigms［J］.Reliability Engineering & System Safety, 2018,178(1): 255-268.

［2］RAI A, UPADHYAY S H.A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings［J］.Tribology International, 2016,96: 289-306.

［3］HUANG N E, SHEN Z, LONG S R, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis［J］.Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998,454(1971): 903-995.

［4］WU Z, HUANG N E.Ensemble empirical mode decomposition: a noise-assisted data analysis method［J］.Advances in Adaptive Data Analysis, 2009,1(1): 1-41.

［5］WANG Z, ZHANG Q, XIONG J, et al.Fault diagnosis of a rolling bearing using wavelet packet denoising and random forests［J］.IEEE Sensors Journal, 2017,17(17): 5581-5588.

［6］AMIRAT Y, BENBOUZID M E H, WANG T, et al.EEMD-based notch filter for induction machine bearing faults detection［J］.Applied Acoustics, 2018,133: 202-209.

［7］MIRIAM A, ANNA G.Classification of impact damage on a rubber-textile conveyor belt using Nave-Bayes methodology［J］.Wear, 2018,414/415: 59-67.

［8］LI J, ZHANG X, ZHOU X, et al.Reliability assessment of wind turbine bearing based on the degradation-Hidden-Markov model［J］.Renewable Energy, 2019,132: 1076-1087.

［9］SAARI J, STRMBERGSSON D, LUNDBERG J, et al.Detection and identification of windmill bearing faults using a one-class support vector machine (SVM)［J］.Measurement, 2019,137: 287-301.

［10］BEN ALI J, 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: 16-27.

［11］李恒,张氢,秦仙蓉,等.基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法［J］.振动与冲击, 2018,37(19): 124-131.
LI Heng, ZHANG Qing, QIN Xianrong, etal.Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network［J］.Journal of Vibration and Shock, 2018,37(19): 124-131.

［12］MANJURUL ISLAM M M, KIM J M.Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector Machines［J］.Reliability Engineering & System Safety, 2019,184: 55-66.

［13］SHI X, LIANG Y, LEE H,et al.Improved elman networks and applications for controlling ultrasonic motors［J］.Applied Artificial Intelligence, 2004,18(7): 603-629.

［14］SINGH N, SINGH P.A novel bagged Nave bayes-decision tree approach for multi-class classification problems［J］.Journal of Intelligent and Fuzzy Systems, 2019,36(3): 2261-2271.

［15］LI L, HUANG Y, TAO J, et al.Featured temporal segmentation method and AdaBoost-BP detector for internal leakage evaluation of a hydraulic cylinder［J］.Measurement, 2018,130: 279-289.

［16］NIE Q, JIN L, FEI S, et al.Neural network for multi-class classification by boosting composite stumps［J］.Neurocomputing, 2015,149: 949-956.

［17］LI L, WANG C, LI W, et al.Hyperspectral image classification by AdaBoost weighted composite kernel extreme learning machines［J］.Neurocomputing, 2018,275: 1725-1733.