A machine learning approach for the condition monitoring of rotating machinery

Kateris, Dimitrios; Moshou, Dimitrios; Pantazi, Xanthoula Eirini; Gravalos, İoannis; Sawalhi, Nader; Loutridis, S.

doi:10.1007/s12206-013-1102-y

Cited by 75 publications

(39 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A large margin indicates that the SVM is stable and will be less susceptible to misclassifying data . Both classifiers are well established, and more information can be found about their application in previous works …”

Section: Methodsmentioning

confidence: 99%

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

et al. 2019

View full text Add to dashboard Cite

Reducing wind turbine downtime through innovations surrounding asset management has the potential to greatly influence the levelised cost of energy (LCoE) for large wind farm developments. Focusing on generator bearing failure and vibration data, this paper presents a two‐stage methodology to predict failure within 1 to 2 months of occurrence. Results are obtained by building up a database of failures and training machine learning algorithms to classify the bearing as healthy or unhealthy. This is achieved by first using clustering techniques to produce subpopulations of data based on operating conditions, which this paper demonstrates can greatly influence the ability to diagnose a fault. Secondly, this work classifies individual clusters as healthy or unhealthy from vibration‐based condition monitoring systems by applying order analysis techniques to extract features. Using the methodology explained in the report, an accuracy of up to 81.6% correct failure prediction was achieved.

show abstract

Section: Methodsmentioning

confidence: 99%

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Rajakarunakaran (6) considered a centrifugal pumping rotary system where the fault detection model was developed by using two different artificial neural network approaches which included feed forward network with back propagation algorithm and binary adaptive resonance network (ART1).Enrico Zio (7) in his paper developed a Neuro Fuzzy approach for pattern classification. J. Rafiee (8) presented a gear fault identification system using genetic algorithm (GA) and artificial neural networks (ANNs).Gang Niu (9) proposed a data-fusion strategy where vibration signals were collected, trend features were extracted, normalized and sent into neural network for feature-level fusion.Karim Salahshoor (10) used distributed pattern of three adaptive Neuro-fuzzy inference system (ANFIS) classifiers for an industrial 440 MW power plant steam turbine with once-through Benson Type boiler.Ilyes Khelf (11) accurate identified the defects in rotating machines, using the combination of pattern recognition and nondestructive testing techniques such as vibration analysis and its indicators.Dimitrios Kateris (12) in his paper presented the architecture of a diagnostic system for extended faults in bearings based on neural networks which highlighted the combined use of kurtosis and the line integral of the acceleration signal. Unbalance faults were identified through a data driven approach applied to a rotor dynamic test rig fitted with multiple discs by R.B.…”

Section: Literature Reviewmentioning

confidence: 99%

Application ofArtificial Neural Networking for Determining the Plane of Vibration in Rotating System

A¹,

Majumder²,

Mukhopadhyay³

et al. 2017

IOSR JMCE

View full text Add to dashboard Cite

“…Kateris et al [169] presented neural network based architecture of a diagnostic system for extended faults in the bearings. The vibration feature selection is based on Bayesian automatic relevance determination technique for finding better feature combinations.…”

Section: Vibration Signals and Condition Monitoringmentioning

confidence: 99%

A Review on Application of Dynamic Parameters of Journal Bearing for Vibration and Condition Monitoring

Babu

Raj²,

Lakshmanan

2015

J. mech.

View full text Add to dashboard Cite

The journal bearings are used to support high-speed rotors in turbo machinery which often operate above the rotor first bending critical speed. This bearing provide both lateral support and dynamic coefficients: Stiffness, damping, and mass terms, related to machine vibrations. The various methods of identifying journal bearing dynamic characteristics, from measured data, obtained from different measurement systems, are reviewed. The various approaches to the bearing identification problem are discussed. The various data processing methods in the time and frequency domains are presented. Also, vibration and condition monitoring techniques are presented. In this review, the relative strengths and weaknesses of bearing are presented and developments and trends in improving bearing measurements are documented. Future trends of journal bearing are discussed.

show abstract

A machine learning approach for the condition monitoring of rotating machinery

Cited by 75 publications

References 24 publications

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

Application ofArtificial Neural Networking for Determining the Plane of Vibration in Rotating System

A Review on Application of Dynamic Parameters of Journal Bearing for Vibration and Condition Monitoring

Contact Info

Product

Resources

About