An Improved Fault Diagnosis Method of Rotating Machinery Using Sensitive Features and RLS-BP Neural Network

An improved algorithm with feature selection and neural network classification is proposed in this paper to investigate the fault diagnosis problem of rotating machinery. The feature vectors are constructed by extracting the time- and frequency-domain characteristics of the overall machine under multiple operating conditions. To strengthen the fault diagnostic ability, an improved sensitive feature selection algorithm is proposed by improving the distance evaluation (DE) method and reconstructing a low-dimensional sensitive feature sample with selectively chosen parameters from multidimensional feature vectors. The recursive least square backpropagation (RLS-BP) neural network algorithm is used for fault diagnosis by classifying the feature vectors of normal signal and faulty signals. The effectiveness of the proposed method is verified via hardware experiments using wind turbine drivetrain diagnostics simulator (WTDDS) by comparing with conventional feature vector construction methods and neural network algorithm.

[1]  Andrea Klug,et al.  Theory And Design For Mechanical Measurements , 2016 .

[2]  V. Sugumaran,et al.  Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines , 2015 .

[3]  Jingxiang Lv,et al.  Weak Fault Feature Extraction of Rolling Bearings Using Local Mean Decomposition-Based Multilayer Hybrid Denoising , 2017, IEEE Transactions on Instrumentation and Measurement.

[4]  Peng Chen,et al.  Vibration-Based Intelligent Fault Diagnosis for Roller Bearings in Low-Speed Rotating Machinery , 2018, IEEE Transactions on Instrumentation and Measurement.

[5]  Zi Yanyang,et al.  Fault Diagnosis Based on Novel Hybrid Intelligent Model , 2008 .

[6]  Dongyang Dou,et al.  Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery , 2016, Appl. Soft Comput..

[7]  Yingxu Wang,et al.  Intelligent Fault Recognition and Diagnosis for Rotating Machines using Neural Networks , 2011, Int. J. Softw. Sci. Comput. Intell..

[8]  Qiao Hu,et al.  Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs , 2007 .

[9]  Yaguo Lei,et al.  Intelligent Fault Diagnosis and Remaining Useful Life Prediction of Rotating Machinery , 2016 .

[10]  Zaigang Chen,et al.  Mesh stiffness calculation of a spur gear pair with tooth profile modification and tooth root crack , 2013 .

[11]  Rajiv Tiwari,et al.  Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data , 2014 .

[12]  Aurobinda Routray,et al.  A Method for Detecting Half-Broken Rotor Bar in Lightly Loaded Induction Motors Using Current , 2016, IEEE Transactions on Instrumentation and Measurement.

[13]  Qiang Miao,et al.  Prognostics and Health Management: A Review of Vibration Based Bearing and Gear Health Indicators , 2018, IEEE Access.

[14]  Hossam A. Gabbar,et al.  Vibration Analysis and Time Series Prediction for Wind Turbine Gearbox Prognostics , 2020 .

[15]  I. R. Praveen Krishna,et al.  Empirical mode decomposition of acoustic signals for diagnosis of faults in gears and rolling element bearings , 2012 .

[16]  De-Shuang Huang.  The United Adaptive Learning Algorithm for The Link Weights and Shape Parameter in RBFN for Pattern Recognition , 1997, Int. J. Pattern Recognit. Artif. Intell..

[17]  Byeng D. Youn,et al.  Model-Based Fault Diagnosis of a Planetary Gear: A Novel Approach Using Transmission Error , 2016, IEEE Transactions on Reliability.

[18]  Mahmood R. Azimi-Sadjadi,et al.  Fast learning process of multilayer neural networks using recursive least squares method , 1992, IEEE Trans. Signal Process..

[19]  Zhongxiao Peng,et al.  A study of the effect of contaminant particles in lubricants using wear debris and vibration condition monitoring techniques , 2005 .

[20]  Theodore A. Tsiligiridis,et al.  Piecewise evolutionary segmentation for feature extraction in time series models , 2012, Neural Computing and Applications.

[21]  Yao Cheng,et al.  A Novel Condition-Monitoring Method for Axle-Box Bearings of High-Speed Trains Using Temperature Sensor Signals , 2019, IEEE Sensors Journal.

[22]  Takehisa Yairi,et al.  A review on the application of deep learning in system health management , 2018, Mechanical Systems and Signal Processing.

[23]  M. Nazmul Karim,et al.  A New Method for the Identification of Hammerstein Model , 1997, Autom..

[24]  Wentao Huang,et al.  Spur bevel gearbox fault diagnosis using wavelet packet transform and rough set theory , 2018, J. Intell. Manuf..

[25]  Ahmet Kahraman,et al.  A theoretical and experimental investigation of modulation sidebands of planetary gear sets , 2009 .

[26]  Yi Wang,et al.  Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network , 2013, J. Intell. Manuf..

[27]  Haibo He,et al.  Stacked Multilevel-Denoising Autoencoders: A New Representation Learning Approach for Wind Turbine Gearbox Fault Diagnosis , 2017, IEEE Transactions on Instrumentation and Measurement.

[28]  Han Zhang,et al.  Compressed-Sensing-Based Periodic Impulsive Feature Detection for Wind Turbine Systems , 2017, IEEE Transactions on Industrial Informatics.

[29]  Yi Cao,et al.  Fault diagnosis of planetary gear based on wavelet real modulation zooming and resonance demodulation , 2017, 2017 IEEE International Conference on Information and Automation (ICIA).

[30]  K. I. Ramachandran,et al.  Fault diagnosis of spur bevel gear box using discrete wavelet features and Decision Tree classification , 2009, Expert Syst. Appl..

[31]  Idriss El-Thalji,et al.  A summary of fault modelling and predictive health monitoring of rolling element bearings , 2015 .

[32]  Weihua Li,et al.  Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network , 2017, IEEE Transactions on Instrumentation and Measurement.

[33]  Thomas Villmann,et al.  Stochastic neighbor embedding (SNE) for dimension reduction and visualization using arbitrary divergences , 2012, Neurocomputing.

[34]  Jiangtao Wen,et al.  Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning , 2018, IEEE Transactions on Instrumentation and Measurement.

[35]  Patricia Melin,et al.  A hybrid learning method composed by the orthogonal least-squares and the back-propagation learning algorithms for interval A2-C1 type-1 non-singleton type-2 TSK fuzzy logic systems , 2015, Soft Comput..

[36]  Wei Qiao,et al.  Rotor-Current-Based Fault Diagnosis for DFIG Wind Turbine Drivetrain Gearboxes Using Frequency Analysis and a Deep Classifier , 2017, IEEE Transactions on Industry Applications.

[37]  ZhiQiang Chen,et al.  Multi-layer neural network with deep belief network for gearbox fault diagnosis , 2015 .