Fault Detection Using Support Vector Machines and Artificial Neural Networks, Augmented by Genetic Algorithms

Jack, L.B.; Nandi, Asoke K.

doi:10.1006/mssp.2001.1454

Cited by 324 publications

(152 citation statements)

References 17 publications

(16 reference statements)

Supporting

Mentioning

147

Contrasting

Unclassified

Order By: Relevance

“…Outputs from MLPNNs, in particular, have been compared with the performance from support vector machine (SVM) based techniques [14,15] for FDD in rotating machinery. Specially, in [16], ANNs are used with pre-processed vibration signals as input features. Although the SVM solution presented in [16] cannot be considered optimal in the cited instance, the authors nevertheless concluded that ANNs achieved a high performance success rate compared to solutions from SVMs, and that ANNs are more readily trained (with regard to required computation overhead) and more robust than SVMs.…”

Section: International Journal Of Automation and Computing 00(0) Monmentioning

confidence: 99%

Applied fault detection and diagnosis for industrial gas turbine systems

Zhang

Bingham

Garlick

et al. 2016

Int. J. Autom. Comput.

View full text Add to dashboard Cite

Abstract:The paper presents readily implementable approaches for fault detection and diagnosis (FDD) based on measurements from multiple sensor groups, for industrial systems. Specifically, the use of hierarchical clustering (HC) and self-organizing map neural networks (SOMNNs) are shown to provide robust and user-friendly tools for application to industrial gas turbine (IGT) systems. HC fingerprints are found for normal operation, and FDD is achieved by monitoring cluster changes occurring in the resulting dendrograms. Similarly, fingerprints of operational behaviour are also obtained using SOMNN based classification maps (CMs) that are initially determined during normal operation, and FDD is performed by detecting changes in their CMs. The proposed methods are shown to be capable of FDD from a large group of sensors that measure a variety of physical quantities. A key feature of the paper is the development of techniques to accommodate transient system operation, which can often lead to false-alarms being triggered when using traditional techniques if the monitoring algorithms are not first desensitized. Case studies showing the efficacy of the techniques for detecting sensor faults, bearing tilt pad wear and early stage pre-chamber burnout, are included. The presented techniques are now being applied operationally and monitoring IGTs in various regions of the world.Keywords: Fault detection and diagnosis, hierarchical clustering, self-organizing map neural network. Introduction 1The purpose of fault detection is to automatically generate an 'alarm' or 'flag' to inform operators of impending or developing failure, whilst fault diagnosis aims to identify the location and predict the consequences of the failure [1] . The adoption of 'early warning' systems to identify and localize emerging faults has therefore attracted considerable attention due to the widely-recognized benefits of facilitating reduced down-time and assurance of safety, through the use of fault detection and diagnosis (FDD) [2,3] algorithms.Of the methods previously explored to date, FDD techniques can be broadly divided into three categories viz. knowledge-, model-and signal processing-based approaches [3,4,5] . Knowledge-based approaches often rely on monitoring residuals Manuscript received date; revised date * Corresponding author:Tel: +44 1522 837912; Email:cbingham@lincoln.ac.uk between multiple sensor measurements [6] , however, due to the high number of sensors used on modern industrial gas turbines (IGTs) and other complex industrial systems, the adoption of additional redundant sensors is prohibitively expensive. When using model-based approaches, a virtual sensor (a 'model' by some description) is employed to provide an estimate of expected measurements, from which residuals are then used as an indicator of potential failure modes being present [3] . However, for large IGT systems, which are often custom-designed to meet individual orders, the use of application specific materials and components (for example, to satisfy off-s...

show abstract

Section: International Journal Of Automation and Computing 00(0) Monmentioning

confidence: 99%

Applied fault detection and diagnosis for industrial gas turbine systems

Zhang

Bingham

Garlick

et al. 2016

Int. J. Autom. Comput.

View full text Add to dashboard Cite

show abstract

“…Widodo and Yang (2007) have stated that the use of SVM in machine fault diagnosis is tending to develop towards expertise orientation and problem-oriented domain. Jack and Nandi (2002) have compared SVM and neural networks for condition monitoring applications. It has been concluded that SVM has high classification accuracy and good generalisation capabilities for crisp data.…”

Section: Introductionmentioning

confidence: 99%

Vibration signal analysis using histogram features and support vector machine for gear box fault diagnosis

Chandrasekaran

2017

IJSCC

View full text Add to dashboard Cite

This paper discusses about the extraction of histogram features from the vibration signal of the different conditions of the gear box under investigation, and the application of machine learning method, support vector machine in machine condition monitoring and diagnostics. This paper aims at using classification methods for fault diagnosis of the gear box under investigation. In this paper fault diagnostics of spur bevel gear box is treated as a pattern classification problem. The major steps in pattern classification are feature extraction, and classification. This work investigates the use histogram features and support vector machine for classification. The results show that the developed method can reliably diagnose different conditions of the gear box.

show abstract

“…Jack found that ANN outperformed SVM in terms of system fault diagnosis accuracy, and did so with less training time [16]. In 2007, Rafiee et al used ANN to diagnosis faults in a gearbox [10].…”

Section: Introductionmentioning

confidence: 99%

Rolling Element Bearing Condition Monitoring Based on Vibration Analysis Using Statistical Parameters of Discrete Wavelet Coefficients and Neural Networks

Golbaghi

2017

AUSMT

View full text Add to dashboard Cite

There are several techniques that can be used to determine the condition of a rolling element bearing. In this paper, vibration analysis is used to conduct fault diagnosis of a bearing. Vibration signal noise was eliminated using hard thresholding wavelet analysis. The best mother wavelet for the denoising process was selected using the minimum Shannon entropy criterion. Statistical parameters and other signal properties such as energy and entropy are powerful tools for analyzing vibration signals. These features were calculated in the time and wavelet domains and applied to Artificial Neural Networks (ANNs) as the feature vector to classify the condition of a bearing into one healthy and three faulty conditions. The ANN parameters were separately optimized using three optimization algorithms. The comparison of the results shows that if the ANN parameters are properly optimized, the statistical parameters in the time-frequency domain can optimize accuracy.

show abstract

Fault Detection Using Support Vector Machines and Artificial Neural Networks, Augmented by Genetic Algorithms

Cited by 324 publications

References 17 publications

Applied fault detection and diagnosis for industrial gas turbine systems

Applied fault detection and diagnosis for industrial gas turbine systems

Vibration signal analysis using histogram features and support vector machine for gear box fault diagnosis

Rolling Element Bearing Condition Monitoring Based on Vibration Analysis Using Statistical Parameters of Discrete Wavelet Coefficients and Neural Networks

Contact Info

Product

Resources

About