Bearing fault detection using motor current signal analysis based on wavelet packet decomposition and Hilbert envelope

Imaouchen, Yacine; Alkama, Rezak; Thomas, Marc

doi:10.1051/matecconf/20152003002

Cited by 5 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding bearing defects in particular, interesting findings can be found in [32,33], where a Discrete Wavelet Transform (DWT) and a CWT were used on vibration signals for the diagnosis of bearing defects. In [34], a wavelet packet decomposition and a Hilbert envelope were used on the motor current signal for bearing fault detection. Other works dealing with Wavelet Transforms for the diagnosis of induction machines include [35][36][37].…”

Section: Methodsmentioning

confidence: 99%

Convolutional Neural Networks for Automated Rolling Bearing Diagnostics in Induction Motors Based on Electromagnetic Signals

et al. 2021

View full text Add to dashboard Cite

Bearing faults account for over 40% of induction motor faults, and for this reason, for several decades, much attention has been paid to their condition monitoring, through vibration measurements and, more recently, through electromagnetic signal analysis. Furthermore, in the last few years, research has been focused on evaluating deep learning algorithms for the automatic diagnosis of these faults. Therefore, the purpose of this study is to propose a novel procedure to automatically diagnose different types of bearing faults and load anomalies by means of the stator current and the external stray flux measured on the induction motor in which the bearings are installed. All the data were collected by performing experimental tests in the laboratory. Then, these data were processed to obtain images (scalograms and spectrograms), which were elaborated by a pre-trained Deep Convolutional Neural Network, modified through the transfer learning technique. The results demonstrated the ability of the electromagnetic signals, and in particular of the stray flux, to detect bearing faults and mechanical anomalies, in agreement with the recent literature. Moreover, the Convolutional Neural Network has been proven to be able to automatically discriminate bearing defects and with respect to the healthy condition.

show abstract

Section: Methodsmentioning

confidence: 99%

Convolutional Neural Networks for Automated Rolling Bearing Diagnostics in Induction Motors Based on Electromagnetic Signals

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Wavelet packet decomposition (WPD) is a method of decomposing signals both in low-frequency and high-frequency ranges and has the ability to characterize local features in a time-frequency domain. Therefore, WPD is quite suitable for detecting transient anomalies in normal signals and has significant application value [9][10][11]. As for a given orthogonal scaling function, ( ), and the wavelet function, ( ), the two-scale relation equations are as follows:…”

Section: Feature Extractionmentioning

confidence: 99%

Curve similarity recognition based rolling bearing degradation state estimation and lifetime prediction

Li-pin¹,

Lu²,

Tao³

2016

J. vibroeng.

View full text Add to dashboard Cite

The health state of a rolling bearing keeps changing from a normal state to a slight degradation state followed eventually by a severely degraded state. To make reasonable inspection and maintenance plans, it is necessary to estimate the degradation state and predict the lifetime of a running rolling bearing accurately and in a timely fashion. This paper presents a new method for rolling bearing degradation state estimation and lifetime prediction based on curve similarity recognition. Different from existing methods, this method employs a dynamic time warping algorithm to recognize the curve similarity of those extracted features of rolling bearings in different states of health, which can reflect the intrinsic state of the rolling bearing; it discretizes the bearing degradation state reasonably through curve similarity. Next, the curve similarity is used to train the degradation state estimation model and a support vector machine based lifetime prediction model. Finally, this paper conducts a case study for a rolling bearing with impact degradation and one with wear degradation, respectively. The experimental results indicate that the new proposed method is highly efficient in recognizing the bearing's degradation state and predicting its lifetime. University. Ph.D. in System Engineering (2014). His research is focused on fault diagnosis, prognostics and health management for electromechanical systems especially for rotating machinery, battery, and wind turbine. It comprises the analysis, development, and optimization of related algorithms and systems.

show abstract

Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis

Alhams,

Abdelhadi,

Badri

et al. 2024

J. Vib. Eng. Technol.

View full text Add to dashboard Cite

Purpose This research introduces a groundbreaking method for bearing defect detection. It leverages ensemble machine learning (ML) models and conducts comprehensive feature importance analysis. The key innovation is the training and benchmarking of three tree ensemble models—Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—on an extensive experimental dataset (QU-DMBF) collected from bearing tests with seeded defects of varying sizes on the inner and outer raceways under different operating conditions. Method The dataset was meticulously prepared with categorical variable encoding and Min–Max data normalization to ensure consistent class distribution and model accuracy. Implementing the ML models involved a grid search method for hyperparameter tuning, focusing on reporting the models’ accuracy. The study also explores applying ensemble methods and using supervised and unsupervised learning algorithms for bearing fault detection. It underscores the value of feature importance analysis in understanding the contributions of specific inputs to the model’s performance. The research compares the ML models to traditional methods and discusses their potential for advanced fault diagnosis in bearing systems. Results and Conclusions The XGBoost model, trained on data from actual bearing tests, outperformed the others, achieving 92% accuracy in detecting bearing health and fault location. However, a deeper analysis of feature importance reveals that the models weigh certain experimental conditions differently—such as sensor location and motor speed. This research’s primary novelties and contributions are comparative evaluation, experimental validation, accuracy benchmarking, and interpretable feature importance analysis. This comprehensive methodology advances the bearing health monitoring field and has significant practical implications for condition-based maintenance, potentially leading to substantial cost savings and improved operational efficiency.

show abstract

Bearing fault detection using motor current signal analysis based on wavelet packet decomposition and Hilbert envelope

Cited by 5 publications

References 10 publications

Convolutional Neural Networks for Automated Rolling Bearing Diagnostics in Induction Motors Based on Electromagnetic Signals

Convolutional Neural Networks for Automated Rolling Bearing Diagnostics in Induction Motors Based on Electromagnetic Signals

Curve similarity recognition based rolling bearing degradation state estimation and lifetime prediction

Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis

Contact Info

Product

Resources

About