Diagnosis of ball-bearing faults using support vector machine based on the artificial fish-swarm algorithm

Abstract

Ball bearings are important parts of all modern rotating machines. Their function is to reduce friction, support rotating shafts and spindles, and bear loads. Bearing damage can result in abnormal vibrations, cause machine malfunction, and even be dangerous. In this study, analysis of four different ball-bearing conditions was carried out: normal bearings and bearings with inner ring, rolling body, and outer ring malfunction. This was based on electromechanical vibration signals produced on a fault diagnosis simulation platform. The objective was to use a series of signal processing analytical methods to build a set of identification models used to forecast malfunction. Wavelet packet transform technology was first used to process the vibration signal. The signals were pre-processed and analyzed before eigenvalue calculation was done to analyze the signal changes which allowed determination of the nature of the bearing malfunction to be made. The extracted eigenvalues and ball-bearing status categories were input to the support vector machine for model training and testing. Finally, the constructed model parameters were integrated with particle swarm optimization, and the artificial fish-swarm algorithm was used to obtain the optimal parameters for the classifier, and this improved the accuracy of malfunction classification.

Early Fault Diagnostic System for Rolling Bearing Faults in Wind Turbines

“…Over the past two decades, the use of machine learning techniques have developed from a mere speculative idea into a broad topic of research. Due to their high accuracy fault classification, they are also favoured by researchers focusing in this particular area: Sugumaran used a decision tree for fault diagnostics of roller bearings [28]; Pandya used multinomial logistic regression techniques [29]; and Lin et al applied a support vector machine based on an artificial fish-swarm algorithm [30]. Apart from these traditional machines learning approaches, deep learning 6 models including CNNs (convolutional neural network) and RNNs (recurrent neural networks) [31,32] have been adapted into the design of a rolling bearing prognostic system.…”

Mechanical Loading Model of Main Bearing of Wind Turbine Based on Test Bench

“…Although many literatures take test benches to carry out loading experiments on bearings to detect bearings or analyze dynamic characteristics of bearings [28][29][30], the size of these tested bearings is too small to meet the test standards for the main bearings of large wind turbines. Therefore, this study proposes a loading method based on the test-bed to detect the bearing, that is, according to actual load of the main bearing of large-scale wind turbine, eight hydraulic cylinders in test-bed are used to load to simulate the bearing's ultimate load, and the DC motor runs and drives the main bearing to rotate.…”

Hazards That Can Affect CNC Machine Tools during Operation—An AHP Approach

“…For example, bearing malfunction can dramatically increase the level of vibrations and resistant torques. A new method of diagnosing the ball-bearing faults by means of the artificial fish-swarm algorithm was presented in [8].…”