Classification of Ball Bearing Faults Using Vibro-Acoustic Sensor Data Fusion

This paper presents the novel technique for fault diagnosis of bearing by fusion of two different sensors: Vibration based and acoustic emission-based sensor. The diagnosis process involves the following steps: Data Acquisition and signal processing, Feature extraction, Classification of features, High-level data fusion and Decision making. Experiments are carried out upon test bearings with a fusion of sensors to obtain signals in time domain. Then, signal indicators for each signal have been calculated. Classifier called K-nearest neighbor (KNN) has been used for classification of fault conditions. Then, high-level sensor fusion was carried out to gain useful data for fault classification. The decision-making step allows understanding that vibration-based sensors are helpful in detecting inner race and outer race defect whereas the acoustic-based sensor is more useful for ball defects detection. These studies based on fusion helps to detect all the faults of rolling bearing at an early stage.

[1]  Lei Guo,et al.  Rolling Bearing Fault Classification Based on Envelope Spectrum and Support Vector Machine , 2009 .

[2]  Konstantinos C. Gryllias,et al.  A Support Vector Machine approach based on physical model training for rolling element bearing fault detection in industrial environments , 2012, Eng. Appl. Artif. Intell..

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

[4]  M. Elforjani,et al.  Accelerated natural fault diagnosis in slow speed bearings with Acoustic Emission , 2010 .

[5]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[6]  Robert B. Randall,et al.  USING TRANSIENT ANALYSIS SOFTWARE TO SIMULATE VIBRATION SIGNALS DUE TO ROLLING ELEMENT BEARING DEFECTS , 2002 .

[7]  N. Tandon,et al.  A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings , 1999 .

[8]  Hamid Moeenfard,et al.  Nonlinear dynamic modeling of surface defects in rolling element bearing systems , 2009 .

[9]  Anoushiravan Farshidianfar,et al.  Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine , 2007 .

[10]  Mo-Yuen Chow,et al.  Neural-network-based motor rolling bearing fault diagnosis , 2000, IEEE Trans. Ind. Electron..

[11]  David He,et al.  Low speed bearing fault diagnosis using acoustic emission sensors , 2016 .

[12]  David,et al.  A comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size , 2006 .

[13]  Amiya R Mohanty,et al.  Model based fault diagnosis of a rotor–bearing system for misalignment and unbalance under steady-state condition , 2009 .

[14]  M. S. Safizadeh,et al.  Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell , 2014, Inf. Fusion.

[15]  Zhiwen Liu,et al.  Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings , 2013, Neurocomputing.

[16]  Asoke K. Nandi,et al.  Classification of ball bearing faults using a hybrid intelligent model , 2017, Appl. Soft Comput..

[17]  Zhiqiang Chen,et al.  Deep neural networks-based rolling bearing fault diagnosis , 2017, Microelectron. Reliab..

[18]  B. Samanta,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES , 2003 .