A Bayesian machine learning method for sensor selection and fusion with application to on-board fault diagnostics

Subrahmanya, Niranjan; Shin, Yung C.; Meckl, Peter H.

doi:10.1016/j.ymssp.2009.06.010

Cited by 30 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original measurements are treated by extracting fault feature information, and then the information is integrated called feature-level fusion for fault diagnosis [33]. A fuzzy-based method in feature-level fusion is presented for gas turbine fault detection and identification [38]. The intermediate decision of each module combined for final decision in the topmost layer is denoted by decision-level fusion.…”

Section: Data Hierarchical Fusion For Engine Gas-path Fault Diagnosismentioning

confidence: 99%

A Novel Data Hierarchical Fusion Method for Gas Turbine Engine Performance Fault Diagnosis

et al. 2016

View full text Add to dashboard Cite

Gas path fault diagnosis involves the effective utilization of condition-based sensor signals along engine gas path to accurately identify engine performance failure. The rapid development of information processing technology has led to the use of multiple-source information fusion for fault diagnostics. Numerous efforts have been paid to develop data-based fusion methods, such as neural networks fusion, while little research has focused on fusion architecture or the fusion of different method kinds. In this paper, a data hierarchical fusion using improved weighted Dempster-Shaffer evidence theory (WDS) is proposed, and the integration of data-based and model-based methods is presented for engine gas-path fault diagnosis. For the purpose of simplifying learning machine typology, a recursive reduced kernel based extreme learning machine (RR-KELM) is developed to produce the fault probability, which is considered as the data-based evidence. Meanwhile, the model-based evidence is achieved using particle filter-fuzzy logic algorithm (PF-FL) by engine health estimation and component fault location in feature level. The outputs of two evidences are integrated using WDS evidence theory in decision level to reach a final recognition decision of gas-path fault pattern. The characteristics and advantages of two evidences are analyzed and used as guidelines for data hierarchical fusion framework. Our goal is that the proposed methodology provides much better performance of gas-path fault diagnosis compared to solely relying on data-based or model-based method. The hierarchical fusion framework is evaluated in terms to fault diagnosis accuracy and robustness through a case study involving fault mode dataset of a turbofan engine that is generated by the general gas turbine simulation. These applications confirm the effectiveness and usefulness of the proposed approach.

show abstract

Section: Data Hierarchical Fusion For Engine Gas-path Fault Diagnosismentioning

confidence: 99%

A Novel Data Hierarchical Fusion Method for Gas Turbine Engine Performance Fault Diagnosis

et al. 2016

View full text Add to dashboard Cite

show abstract

“…They proposed the vector ℎ (9) = [1,4,5,6,12,14,22,25,26] as optimal, assuming that a sensor is more relevant if it is more informative (according to Shannon's entropy). Also in [16], the authors proposed the feature vector ℎ (9) = [1,7,25,9,6,21,20,8,10] as optimal, using expert knowledge about the process behavior in order to guide a wrapper 0 100 200 300 400 500 600 700…”

Section: B Selected Features Testmentioning

confidence: 99%

“…However, complete classical models are usually unavailable, mainly because the complexity of creating detailed mechanistic models. Thus, the role of data-based condition monitoring schemes that analyze direct processes measurements to obtain functional states has increased in recent years [3], [4]. Neural networks, expert systems, fuzzy and neuro-fuzzy systems have been applied on processes monitoring with relative success; but most of them depends on knowledge of system failures validated in a supervised ways [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised feature selection based on fuzzy partition optimization for industrial processes monitoring

Uribe

Isaza

2011

2011 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA) Proceedings

View full text Add to dashboard Cite

Industrial processes have enormous volumes of complex and high dimensional data available, with poorly defined domains and redundant, noisy or inaccurate measures with unknown parameters. Therefore, using just relevant and informative variables will decrease the high dimensionality in the data and will facilitate the use of data-based methods for developing monitoring and fault detection systems. In this paper, a new unsupervised feature selection method based on partition optimization for fuzzy clustering based monitoring systems is proposed. Application on monitoring an intensification reactor, the 'open plate reactor (OPR)' is studied. Results show fewer variables are needed to classify process data into accurate functional states.

show abstract

“…Their method is based on the general principle of variance reduction through data reconciliation. Subrahmanya et al (2009) converted the sensor selection problem to the problem of Chapter 1. Introduction 5 selecting an optimal set of groups of features during model selection and proposed an algorithm based on the use of a Bayesian framework for the purpose of selecting groups of features during regression and classification.…”

Section: Sensor Network Design (Snd)mentioning

confidence: 99%

Model-based computer-aided framework for design of process monitoring and analysis systems

Singh

Gernaey

Gani

2009

Computers & Chemical Engineering

View full text Add to dashboard Cite

A Bayesian machine learning method for sensor selection and fusion with application to on-board fault diagnostics

Cited by 30 publications

References 23 publications

A Novel Data Hierarchical Fusion Method for Gas Turbine Engine Performance Fault Diagnosis

A Novel Data Hierarchical Fusion Method for Gas Turbine Engine Performance Fault Diagnosis

Unsupervised feature selection based on fuzzy partition optimization for industrial processes monitoring

Model-based computer-aided framework for design of process monitoring and analysis systems

Contact Info

Product

Resources

About