Fault detection and diagnosis of an industrial steam turbine using fusion of SVM (support vector machine) and ANFIS (adaptive neuro-fuzzy inference system) classifiers

Salahshoor, Karim; Kordestani, Mojtaba; Khoshro, Majid S.

doi:10.1016/j.energy.2010.06.001

Cited by 207 publications

(98 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For stochastic system,the two kinds of approaches include the system identification techniques [6] and the statistic approaches based on the Likelihood methods, Bayesian theorem,and Hypothesis test techniques ( [1]) can be used to deal with the related FDD problems. Besides, we have known that observers or filters have been extensively applied to generate the residual signal for fault detection and diagnosis( [7], [8]), and many significant approaches of them have been applied to practical processes successfully( [9], [10]). …”

Section: Introductionmentioning

confidence: 99%

Fault Detection and Diagnosis for Non-Gaussian Singular Stochastic Distribution Systems via Output PDFs

2012

Automatika

View full text Add to dashboard Cite

This paper investigates the problem of fault detection and diagnosis (FDD) problem for non-Gaussian singular stochastic distribution control (SDC) systems via the output probability density functions(PDFs). The PDFs can be approximated by using square-root B-spline expansion, via this expansions to represent the dynamics weighting systems between the system input and the weights related to the output PDFs. In this work, an optimal fault detection and diagnosis algorithm is presented by introducing the parameter-updating. When the fault occurs, an adaptive network parameter-updating law is designed to approximated the fault. Finally, the simulation result are given to show that the approach can detect fault and estimate the size of fault.Key words: Probability density fuctions, Non-gausian singular stochastic distribution control, Fault detection and diagnosis, Adaptive network parameter-updatingDetekcija pogreške i dijagnostika za singularne stohastičke sustave s ne-Gaussovom razdiobom preko izlazne funkcije gustoće razdiobe. U ovome radu prikazan je problem detekcije pogreške i dijagnostike (FDD), za singularne stohastičke sustave upravljanja koji nemaju normalnu razdiobu, preko izlazne gustoće vjerojatnosti, koja se može aproksimirati koristeći square-root B-spline ekspanziju. Prikazan je optimalni algoritam za detekciju i dijagnostiku grešaka uvodeći postupak izmjene parametara. U trenutku pojave greške, adaptivna mreža za izmjenu parametara je dizajnirana u svrhu aproksimacije nastale pogreške. U radu su dani simulacijski rezultati koji prikazuju ispravnost ovakvog načina detekcije pogreške i procjene njezine veličine.Ključne riječi: funkcija gustoće vjerojatnosti, upravljanje sustavima sa stohastičkom razdiobom koja nije normalna, detekcija pogreške i dijagnostika, adaptivna mreža podešavanja parametara

show abstract

Section: Introductionmentioning

confidence: 99%

Fault Detection and Diagnosis for Non-Gaussian Singular Stochastic Distribution Systems via Output PDFs

2012

Automatika

View full text Add to dashboard Cite

show abstract

“…SVM algorithm is proposed. Using SVM well solve the problem of small samples and the classification problem, which can the inherent through methods such as neural network learning and owe learning problems, and SVM also has a strong ability of nonlinear classification [4]. It based on the advantages of the above three algorithms, and applies them to the condenser fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Research on Condenser Fault Diagnosis Based on Three Different Algorithms

Xia¹,

Shuotao²,

Zhang³

et al. 2014

TOEEJ

View full text Add to dashboard Cite

Abstract:In view of artificial neural network, there are some deficiencies in condenser fault diagnosis. The BP neural network used for condenser fault diagnosis is highly nonlinear pattern recognition and high precision of fault diagnosis. The PSO-BP neural network can effectively solve the problem of BP neural network that training time is long and training process is easy to fall into the local minimum. The training results of PSO-BP network in convergence speed and convergence effect are significantly improved. Under the condition of small samples, the calculation results of SVM method are better than the calculation result of the other two methods. Although the recognition ratio of improved PSO-BP(2) and SVM is the same, training time of improved PSO-BP (2) is longer than training time of SVM. The generalization ability of SVM is stronger, and the efficiency of SVM is higher than the neural network. With MATLAB programming, three different algorithms, which are BP neural network, PSO-BP neural network and SVM, are studied and compared for the performance of condenser fault diagnosis. In the models of this study, the research results show that condenser fault diagnosis based on SVM has the fastest convergence speed and the best accuracy.

show abstract

“…During the course of an engine's life, various physical failures might happen, such as corrosion, erosion, fouling, and foreign object damage [2,3]. These failures lead to gas-path performance degradation, either gradually or abruptly, which is recognized as engine gas-path fault and is greatly harmful to flight safety [4,5]. For the purpose of enhancing operating reliability and reducing maintenance costs of aircraft propulsion systems, engine gas-path fault diagnosis technology has attracted interest.…”

Section: Introductionmentioning

confidence: 99%

An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis

et al. 2018

View full text Add to dashboard Cite

To improve gas-path performance fault pattern recognition for aircraft engines, a new data-driven diagnostic method based on hidden Markov model (HMM) is proposed. A redundant sensor somewhat interferes with fault diagnostic results of the HMM, and it also increases the computational burden. The contribution of this paper is to develop an iterative reduced kernel principal component analysis (IRKPCA) algorithm to extract fault features from original high-dimension observation without large additional calculation load and combine it with the HMM for engine gas-path fault diagnosis. The optimal kernel features are obtained by iterative sequential forward selection of the IRKPCA, and the features with lower dimensions are contracted through a trade-off between the fault information and modeling data scale in reduced kernel space. The similarity degree is designed to simplify the HMM modeling data using fault kernel features. Test results show that the proposed methodology brings a significant improvement in diagnostic confidence and computational efforts in the applications of a turbofan engine fault diagnosis during its steady and dynamic process.

show abstract

Fault detection and diagnosis of an industrial steam turbine using fusion of SVM (support vector machine) and ANFIS (adaptive neuro-fuzzy inference system) classifiers

Cited by 207 publications

References 49 publications

Fault Detection and Diagnosis for Non-Gaussian Singular Stochastic Distribution Systems via Output PDFs

Fault Detection and Diagnosis for Non-Gaussian Singular Stochastic Distribution Systems via Output PDFs

A Comparative Research on Condenser Fault Diagnosis Based on Three Different Algorithms

An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis

Contact Info

Product

Resources

About