The Importance of Feature Processing in Deep-Learning-Based Condition Monitoring of Motors

Soother, Dileep Kumar; Daudpoto, Jawaid; Harris, N.R.; Hussain, Majid; Mehran, Sanaullah; Kalwar, Imtiaz Hussain; Hussain, Tanweer; Memon, Tayab Din

doi:10.1155/2021/9927151

Cited by 14 publications

(4 citation statements)

References 119 publications

(125 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a recent comprehensive review, Soother et al [4] point out the importance of feature extraction and processing in order to improve classifier's performance in CM of motors. They analyze different DL architectures, such as multilayer Perceptron (MLP), autoencoders (AE), deep Boltzmann machine (DBN), convolutional neural networks (CNN), recurrent neural networks (RNN) and generative adversarial neural networks (GAN), with input features covering raw vibration, acoustic and sound signals, time domain features, frequency domain features and time-frequency domain features, addressing some well-known transformations such as fast Fourier transform (FFT), short-time Fourier transform (STFT) and wavelets.…”

Section: Literature Reviewmentioning

confidence: 99%

Aplicação de Machine Learning para Diagnóstico de Falha em Motores a Diesel utilizando Sinais de Áudio

JUNQUEIRA¹,

VIOLATO²,

SIMÕES³

et al. 2022

Blucher Engineering Proceedings

View full text Add to dashboard Cite

The present work aims to analyze machine learning techniques applied to pattern recognition of diesel engines audio files captured with a smartphone. Audio samples from 3 different engines were recorded, under 3 different operating conditions: normal operation, leaking hose and injector failure. Several combinations of data processing, audio feature extraction and classifiers were evaluated. The results show that this approach is very promising for fault diagnosis of diesel engines. RESUMOO presente trabalho tem como objetivo a análise de técnicas de machine learning aplicadas ao reconhecimento de padrões em arquivos de áudio contendo sons de motores a diesel capturados a partir de um smartphone. Foram gravadas amostras de áudio de 3 motores distintos, em 3 condições de operação diferentes: motor com funcionamento normal, com a mangueira furada e com falha no injetor. Várias combinações de tratamento dos dados, de atributos extraídos do áudio e de classificadores foram testadas. Os resultados mostram que essa abordagem é bastante promissora para diagnosticar falhas em motores a diesel.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Aplicação de Machine Learning para Diagnóstico de Falha em Motores a Diesel utilizando Sinais de Áudio

JUNQUEIRA¹,

VIOLATO²,

SIMÕES³

et al. 2022

Blucher Engineering Proceedings

View full text Add to dashboard Cite

show abstract

“…Feature Extraction. e objective of feature extraction is to determine a feature vector that characterizes the variability between samples based on a given set of samples so that the samples can be correctly classified [26].…”

Section: Feature Weight Transformationmentioning

confidence: 99%

Quantitative Analysis of Broken Rotor Bars in Cage Motor Based on Energy Characteristics of Vibration Signals

Shi

Shen

Ding

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The rotor, as the power output device of a cage motor, is subject to a type of invisible fault, BRB, during long-term use. The conventional motor vibration signal fault monitoring system only analyzes the rotor qualitatively for the fault of BRBs and cannot evaluate the fault degree of BRBs quantitatively. Moreover, the vibration signal used for monitoring has nonstationary and nonlinear characteristics. It is necessary to manually determine the time window and basis function when extracting the characteristics of the time-frequency domain. To address these problems, this paper proposes a method for quantitative analysis of BRBs based on CEEMD decomposition and weight transformation for feature extraction and then uses the AdaBoost to construct a classifier. The method applies CEEMD for adaptive decomposition while extracting IMFs’ energy as the initial feature values, uses OOB for contribution evaluation of features to construct weight vectors, and performs a spatial transformation on the original feature values to expand the differences between the feature vectors. To verify the effectiveness and superiority of the method, vibration signals were collected from motors in four BRB states to produce rotor fault data sets in this paper. The experiment results show that the feature extraction method based on CEEMD decomposition and weight transformation can better extract the feature vectors from the vibration signals, and the constructed classifier can accurately perform quantitative analysis of BRB fault.

show abstract

“…In the traditional method, a trained railway human operator walks alongside the track regularly and checks the tracks manually, and sometimes the defects may go unnoticed, and train accidents and derailments occur [13][14][15]. Recently condition monitoring systems for railway asset management have been proposed in [16][17][18] that mainly focus on the rolling stock part. But there is a rare state of art technique found in the literature to automate the onsite track deformation detection system.…”

Section: Introductionmentioning

confidence: 99%

Embedded System Development for Detection of Railway Track Surface Deformation Using Contour Feature Algorithm

Memon¹,

Memon²,

Kalwar³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Derailment of trains is not unusual all around the world, especially in developing countries, due to unidentified track or rolling stock faults that cause massive casualties each year. For this purpose, a proper condition monitoring system is essential to avoid accidents and heavy losses. Generally, the detection and classification of railway track surface faults in real-time requires massive computational processing and memory resources and is prone to a noisy environment. Therefore, in this paper, we present the development of a novel embedded system prototype for condition monitoring of railway track. The proposed prototype system works in real-time by acquiring railway track surface images and performing two tasks a) detect deformation (i.e., faults) like squats, shelling, and spalling using the contour feature algorithm and b) the vibration signature on that faulty spot by synchronizing acceleration and image data. A new illumination scheme is also proposed to avoid the sunlight reflection that badly affects the image acquisition process. The contour detection algorithm is applied here to detect the uneven shapes and discontinuities in the geometrical structure of the railway track surface, which ultimately detects unhealthy regions. It works by converting Red, Green, and Blue (RGB) images into binary images, which distinguishes the unhealthy regions by making them white color while the healthy regions in black color. We have used the multiprocessing technique to overcome the massive processing and memory issues. This embedded system is developed on Raspberry Pi by interfacing a vision camera, an accelerometer, a proximity sensor, and a Global Positioning System (GPS) sensors (i.e., multi-sensors). The developed embedded system prototype is tested in real-time onsite by installing it on a Railway Inspection Trolley (RIT), which runs at an average speed of 15 km/h. The functional verification of the proposed system is done successfully by detecting and recording the various railway track surface faults. An unhealthy frame's onsite detection processing time was recorded at approximately 25.6 ms. The proposed system can synchronize the acceleration data on specific railway track deformation. The proposed novel embedded system may be beneficial for detecting faults to overcome the conventional manual railway track condition monitoring, which is still being practiced in various developing or underdeveloped countries.

show abstract

The Importance of Feature Processing in Deep-Learning-Based Condition Monitoring of Motors

Cited by 14 publications

References 119 publications

Aplicação de Machine Learning para Diagnóstico de Falha em Motores a Diesel utilizando Sinais de Áudio

Aplicação de Machine Learning para Diagnóstico de Falha em Motores a Diesel utilizando Sinais de Áudio

Quantitative Analysis of Broken Rotor Bars in Cage Motor Based on Energy Characteristics of Vibration Signals

Embedded System Development for Detection of Railway Track Surface Deformation Using Contour Feature Algorithm

Contact Info

Product

Resources

About