A Fault Feature Extraction Method for Rolling Bearing Based on Pulse Adaptive Time-Frequency Transform

Defects in railway axle bearings can affect operational efficiency, or cause in-service failures, damaging the track and train. Healthy bearings produce a certain level of vibration and noise, but a bearing with a defect causes substantial changes in the vibration and noise levels. It is possible to detect the bearing defects at an early stage of their development, allowing an operator to repair the damage before it becomes serious. When a vehicle is scheduled for maintenance, or due for overhaul, knowledge of bearing damage and severity is beneficial, resulting in fewer operational problems and optimised fleet availability. This paper is a review of the state of the art in condition monitoring systems for rolling element bearings, especially the axlebox bearings. This includes exploring the sensing technologies, summarising the main signal processing methods and condition monitoring techniques, i.e. wayside and on-board. Examples of commercially available systems and outputs of current research work are presented. The effectiveness of the current monitoring technologies is assessed and the p– f curve is presented. It is concluded that the research and practical tests on axlebox bearing monitoring are limited compared to the generic bearing applications.

show abstract

“…This could be because of the sensitivity of the SPM to background noise and other sources of shocks in a complex system (e.g. trains) [81].…”

Section: Shock Pulse Methodsmentioning

confidence: 99%

Perspectives on railway axle bearing condition monitoring

Entezami

Roberts

Weston

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part F:

View full text Add to dashboard Cite

show abstract

“…Its failure can cause economic losses and possible personal injury [1]. For example, a major derailment accident of Lanzhou Railway Branch 1479 train happened on November 30, 1991, due to poor-quality bearing and cage broken [2]. In June 1992, a 600 MW supercritical forming unit from Japan Kansai Electric Power Company Hainan Power Plant in the speeding test caused a strong unit vibration due to the unit bearing failure and the critical speed drop.…”

Section: Introductionmentioning

confidence: 99%

“…Otherwise, keep the fitness value and divide the subpopulation. (3) Perform iterative optimization on each subpopulation and then mix all the subpopulations to form a new population and return to step(2). Repeat the steps(2)and(3)until the number of iterations of the total population is reached and returns x G .…”

mentioning

confidence: 99%

Comparison of Support Vector Machine‐Based Techniques for Detection of Bearing Faults

Wang

2018

Shock and Vibration

View full text Add to dashboard Cite

This paper presents a method that combines Shuffled Frog Leaping Algorithm (SFLA) with Support Vector Machine (SVM) method in order to identify the fault types of rolling bearing in the gearbox. The proposed method improves the accuracy of fault diagnosis identification after processing the collected vibration signals through wavelet threshold denoising. The global optimization and high computational efficiency of SFLA are applied to the SVM model. Simulation results show that the SFLA-SVM algorithm is effective in fault diagnosis. Compared with SVM and Particle Swarm Optimization SVM (PSO-SVM) algorithms, it is demonstrated that the SFLA-SVM algorithm has the advantages of better global optimization, higher accuracy, and better reliability of diagnosis. Its accuracy is further improved through the integration of the wavelet threshold denoising method.

show abstract

Section: Introductionmentioning

confidence: 99%

“…At present, there are three types of characteristic extraction methods for rolling bearing faults i.e. spectrum analysis method, envelope analysis method and shock pulse method [1][2][3][4].At the work site, when different types of rolling bearings faults occur, it will produce different sounds during the process of rotating. As a result of that vibration signals and noise signals are homologous, it is able to conduct characteristic extraction and fault identification to vibration signals of bearings through the processing mechanism of human auditory system.…”

mentioning

confidence: 99%

An Analysis on Diagnostic Method of Roller Bearing Faults Based on Auditory Spectrum and Spectral Correlation

Li¹,

Jinfang²,

Li³

et al. 2017

Topics in Intelligent Computing and Industry Design (ICID)

View full text Add to dashboard Cite

Human auditory system possesses a desirable capacity for analyzing, processing and identifying signals. Whereas different types of rolling bearing faults cause different vibration noises, a new method based on early auditory model (EA model) is proposed for the diagnosis of rolling bearing faults. Firstly, according to characteristics of mechanical vibration signal, the EA model was established by simulating the human auditory system. Secondly, sample signals were processed by the EA model to build sets of auditory spectrums, the characteristics of which were extracted with the purpose of obtaining the characteristic auditory spectrums that reflected the overall characteristics of failure states, so as to further simplify the data. At last, based on spectral correlation, it applied integrated correlation coefficient to identify fault type. Experimental results show that the method is capable of extracting and distinguishing the overall characteristics of 12 types of rolling bearing fault states (four different degrees of faults and normal state of inner race, outer race and rolling element) with almost 100 percent accuracy possesses considerable feasibility and certain potentialities in practical application. IntroductionRolling bearings are widely used in rotating machineries, so that their states directly affect the performance of machinery equipment. In order to reduce the accidents of rotating machinery, it is necessary to realize accurate diagnosis of rolling bearing faults. At present, there are three types of characteristic extraction methods for rolling bearing faults i.e. spectrum analysis method, envelope analysis method and shock pulse method [1][2][3][4].At the work site, when different types of rolling bearings faults occur, it will produce different sounds during the process of rotating. As a result of that vibration signals and noise signals are homologous, it is able to conduct characteristic extraction and fault identification to vibration signals of bearings through the processing mechanism of human auditory system. With respect to auditory system simulation, the current auditory model in the field of auditory periphery system simulation is already mature, and its performance is comparatively close to biological experiments [5].In consideration of advantages of auditory model and the conditions of diagnosis of rolling bearing faults, this paper will introduce EA model into diagnosis of rolling bearing faults, and also design the method of fault characteristics extraction and identification in line with multiple auditory spectrum. By utilizing the data validation for bearing vibration provided by the American Case Western Reserve University, it indicates that the proposed method possesses relatively high accuracy in diagnosis of roller bearing faults. METHOD OVERVIEWImplementation process of the proposed method is shown in Figure 1.

show abstract

A Fault Feature Extraction Method for Rolling Bearing Based on Pulse Adaptive Time-Frequency Transform

Cited by 15 publications

References 15 publications

Perspectives on railway axle bearing condition monitoring

Perspectives on railway axle bearing condition monitoring

Comparison of Support Vector Machine‐Based Techniques for Detection of Bearing Faults

An Analysis on Diagnostic Method of Roller Bearing Faults Based on Auditory Spectrum and Spectral Correlation

Contact Info

Product

Resources

About