Rolling element bearing fault diagnosis using wavelet transform

Kankar, Pavan Kumar; Sharma, Satish C.; Harsha, S. P.

doi:10.1016/j.neucom.2011.01.021

Cited by 231 publications

(113 citation statements)

References 20 publications

Supporting

Mentioning

109

Contrasting

Unclassified

Order By: Relevance

“…Example Feature-classifier combinations include WPT-BPNN/SVM/multinomial logistic regression, TDSF-ANN/SVM/MLP etc. [7][8][9][10][11][12][13][14]. These feature-classifier combinations have mostly been investigated in context of faults related to bearings, shafts, couplings and gearboxes.…”

Section: Introductionmentioning

confidence: 99%

Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines

Shaheryar¹,

Yin²,

Ramay³

2017

IJCA

View full text Add to dashboard Cite

Mechanical failures in rotating machinery (e.g. wind turbines, generators, motor-derives etc.) may result in catastrophic failures. Different mechanical faults induce characteristic vibrations in the equipment structure. Online vibration monitoring helps mitigate catastrophic failures through early detection and identification of underlying mechanical faults. However, extracting characteristic vibration features that improve fault classification performance and are robust to various noises in the vibration signals is a challenging task. Various statistical and signal processing-based vibrationfeatures have been proposed in the literature. These vibrationfeatures were devised on the basis of prior knowledge about characteristics of vibration signals from different fault types. Recently, automatic feature extraction through unsupervised learning in deep neural architectures has resulted in state of art performance on image and speech recognition tasks. So, Instead of feature-engineering, we, here, hypothesized that feature learning on raw vibration signal possibly will extract vibration-features that can improve fault identification performance of subsequent classifier. To the purpose, we explored Convolutional Neural Network for unsupervised feature learning on vibration signals and Denoising AutoEncoder for extracting vibration features that are robust and invariant to the noises in vibration signals. We proposed a Hybrid deep-model consisting of a Multi-channel Convolutional Neural Network followed by a stack of Denoising Auto-Encoders (MCNN-SDAE) with a single classification layer at the top. We compared the fault identification and classification performance of the proposed model with other models employing tradition statistical and signal processing based vibration-features. We validated the performance of all models on a benchmark vibration data collected from an experimental test-rig specifically designed to study vibration characteristics of bearing related faults.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines

Shaheryar¹,

Yin²,

Ramay³

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Chen et al [5] proposed block threshold signal noise minimization strategy and successfully applied it in machine error diagnosis. Kankar et al [6] used minimum Shannon entropy criterion to extract statistical characteristics of bearing fault from discomposed wavelet coefficient, and used the characteristics as the input vector of the classification recognizer to investigate faults. In 1992, Mallat noticed the differences in propagation characters between the modulus maxima of noise elements and signal elements and proposed a wavelet de-noising strategy based on the modulus maxima [7].…”

Section: Introductionmentioning

confidence: 99%

Investigation on Diesel Engine Fault Diagnosis Based on Winger Spectrum Singular Value Entropy

Ning¹,

Hongmao²,

You³

et al. 2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Since wavelet transform is a part of the multiresolution analysis, it gives a full insight into the time frequency character of a signal. For this reason, this approach is widely utilized in diagnostics of structures, constructions, and devices [46][47][48][49][50]. Wavelet-based methods also find applications, e.g., in control algorithms for autonomous vehicles [51], pattern recognition and texture classification [52], or automatic incident detection on freeways which is an important component of an Advanced Traffic Management and Information Systems [53].…”

Section: Introductionmentioning

confidence: 99%

Investigation of vehicle crash modeling techniques: theory and application

Pawlus

Karimi

Robbersmyr

2013

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Creating a mathematical model of a vehicle crash is a task which involves considerations and analysis of different areas which need to be addressed because of the mathematical complexity of a crash event representation. Therefore, to simplify the analysis and enhance the modeling process, in this work, a brief overview of different vehicle crash modeling methodologies is proposed. The acceleration of a colliding vehicle is measured in its center of gravity-this crash pulse contains detailed information about vehicle behavior throughout a collision. A virtual model of a collision scenario is established in order to provide an additional data set further used to evaluate a suggested approach. Three different approaches are discussed here: lumped parameter modeling of viscoelastic systems, data-based approach taking advantage of neural networks and autoregressive models and wavelet-based method of signal reconstruction. The comparative analysis between each method's outcomes is performed and reliability of the proposed methodologies and tools is evaluated.

show abstract

Rolling element bearing fault diagnosis using wavelet transform

Cited by 231 publications

References 20 publications

Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines

Robust Feature Extraction on Vibration Data under Deep-Learning Framework: An Application for Fault Identification in Rotary Machines

Investigation on Diesel Engine Fault Diagnosis Based on Winger Spectrum Singular Value Entropy

Investigation of vehicle crash modeling techniques: theory and application

Contact Info

Product

Resources

About