Comparison between Artificial Neural Network and Support Vector Method for a Fault Diagnostics in Rolling Element Bearings

Patel, Jayeshbhai; Upadhyay, S. H.

doi:10.1016/j.proeng.2016.05.148

Cited by 51 publications

(32 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After that, three different artificial neural network (ANN) models were trained to classify these features into undamaged or damaged states. Similarly, Patel and Upadhyay [16] This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.…”

Section: Introductionmentioning

confidence: 99%

Fault Detection and Severity Identification of Ball Bearings by Online Condition Monitoring

Abdeljaber

Sassi

Avcı

et al. 2019

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

The paper presents a fast, accurate and simple systematic approach for online condition monitoring and severity identification of ball bearings. This approach utilizes compact 1D convolutional neural networks (CNNs) to identify, quantify, and localize bearing damage. The proposed approach is verified experimentally under several single and multiple damage scenarios. The experimental results demonstrated that the proposed approach can achieve a high level of accuracy for damage detection, localization and quantification. Besides its realtime processing ability and superior robustness against the highlevel noise presence, the compact and minimally-trained 1D CNNs in the core of the proposed approach can handle new damage scenarios with utmost accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Fault Detection and Severity Identification of Ball Bearings by Online Condition Monitoring

Abdeljaber

Sassi

Avcı

et al. 2019

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

show abstract

“…For many years both statistic first and second-order: mean, variance, power spectrum, kurtosis [11,12] are common signal processing and analysis tools used widely for vibration analysis of the mechanical component. Bearing condition is often hidden by strong mechanical noise and the undesirable vibration-related element of the machine [8,9]. The bi-spectrum study is not sensitive to find random noise and bi-spectrum analysis of peak, which only related to frequency and phase component [11,12].…”

Section: Introductionmentioning

confidence: 99%

“…Bearing condition improved using the combination of high order spectral analysis and cyclostationary. This approach gives a better result to reduce bearing failure [9]. Demodulation of resonance, the based approach has been used to diagnosis of faulty bearing [1].…”

Section: Introductionmentioning

confidence: 99%

“…Demodulation of resonance, the based approach has been used to diagnosis of faulty bearing [1]. Many techniques have been developed in the recent years such as empirical mode decomposition, continuous wavelet, Hilbert transform and cepstral analysis and many more to fault diagnosis of bearing and machine component [3,9]. Many researchers have been used the spectral analysis of kurtosis for fault diagnosis of bearing in terms of optimal bands of frequency to improve the bearing life and reduce failure of the machine [10,13].…”

Section: Introductionmentioning

confidence: 99%

“…Conditioning monitoring is growing up in the recent year to improve the machine condition in the industry to reduce failure of the machine, loss of production, Diagnosis of a machine component, reduce maintenance cost and solving the problem of machine breakdown maintenance. Vibration analysis of machine condition is the simple and fast way uses for signal analysis and comparisons of normal and faulty condition to the diagnosis of machine component and reduce maintenance cost & total production cost [8,9]. Condition monitoring is the best way to a diagnosis of machine component [8,9].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bearing Fault Diagnosis using Support Vector Machine with Genetic Algorithms Based Optimization and K Fold Cross-Validation Method

Semil¹,

Jaiswal²

2019

IJRTE

View full text Add to dashboard Cite

Moving component bearing is utilized to convey radial load and axial load or both just as. REB has nonlinear conduct make issue misalignment, surface waviness, fault happen at the inward race, external race, enclosure, ball or roller, so REB has a restricted life. Our concentration to evacuate fault diagnosis of bearing at the outer race has been investigating. For this purpose, REB vibration analysis is used. This paper present a support vector machine algorithm (SVM) approach with GA (Genetic algorithm) based optimization compare the result with SVM with cross-validation (CV) method along these lines, the information is processed correctly and an exact way. Time-domain Analysis, high pass and low pass filtering etc. used for feature extraction from vibration signal. Further, these feature extraction used as input to the SVM classifier. Support vector machine, a training given projected preparing information, the procedure yield perfect hyperplane.Feature extraction help to provides the actual condition of bearing. In this work, different signal processing techniques and process are used for fault diagnosis of bearing.

show abstract

Adaptive Architecture for Fault Diagnosis of Rotating Machinery

Jorge

Sánchez-Pérez

Bíla

et al. 2021

Advanced Information Networking and Applications

View full text Add to dashboard Cite

Comparison between Artificial Neural Network and Support Vector Method for a Fault Diagnostics in Rolling Element Bearings

Cited by 51 publications

References 16 publications

Fault Detection and Severity Identification of Ball Bearings by Online Condition Monitoring

Fault Detection and Severity Identification of Ball Bearings by Online Condition Monitoring

Bearing Fault Diagnosis using Support Vector Machine with Genetic Algorithms Based Optimization and K Fold Cross-Validation Method

Adaptive Architecture for Fault Diagnosis of Rotating Machinery

Contact Info

Product

Resources

About