Homogeneous Continuous-Time, Finite-State Hidden Semi-Markov Modeling for Enhancing Empirical Classification System Diagnostics of Industrial Components

被引：10

作者：

Cannarile, Francesco ^{[1
,2
]}

Compare, Michele ^{[1
,2
]}

Baraldi, Piero ^{[1
]}

Di Maio, Francesco ^{[1
]}

Zio, Enrico ^{[1
,3
,4
,5
]}

机构：

[1] Politecn Milan, Dipartimento Energia, I-20156 Milan, Italy

[2] Aramis Srl, I-20121 Milan, Italy

[3] Ecole Cent Paris, European Fdn New Energy Elect France, Syst Sci & Energet Challenge, F-91190 Paris, France

[4] Superlec, F-91190 Paris, France

[5] Kyung Hee Univ, Coll Engn, Dept Nucl Engn, Seoul 02447, South Korea

来源：

MACHINES | 2018年 / 6卷 / 03期

关键词：

hybrid diagnostic system; feature extraction; feature selection; k-nearest neighbors (KNN) classifier; homogeneous continuous-time finite-state hidden semi-Markov model (HCTFSHSMM); maximum likelihood estimation (MLE); differential evolution (DE); PROBABILISTIC FUNCTIONS; GENETIC ALGORITHM; DEGRADATION; OPTIMIZATION; INFERENCE; PROGNOSIS; FRAMEWORK; KERNEL;

D O I：

10.3390/machines6030034

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This work presents a method to improve the diagnostic performance of empirical classification system (ECS), which is used to estimate the degradation state of components based on measured signals. The ECS is embedded in a homogenous continuous-time, finite-state semi-Markov model (HCTFSSMM), which adjusts diagnoses based on the past history of components. The combination gives rise to a homogeneous continuous-time finite-state hidden semi-Markov model (HCTFSHSMM). In an application involving the degradation of bearings in automotive machines, the proposed method is shown to be superior in classification performance compared to the single-stage ECS.

引用

页数：18

共 49 条

[1] AN INTRODUCTION TO KERNEL AND NEAREST-NEIGHBOR NONPARAMETRIC REGRESSION [J].

ALTMAN, NS .

AMERICAN STATISTICIAN, 1992, 46 (03) :175-185

[2]

Alwadie A, 2017, MACHINES, V5, DOI 10.3390/machines5040027

[3]

[Anonymous], 2001, SPEA2 IMPROVING STRE, DOI DOI 10.3929/ETHZ-A-004284029

[4]

[Anonymous], 2008, LECT NOTES STAT

[5] Hierarchical document categorization with k-NN and concept-based thesauri [J].

Bang, SL ;

Yang, JD ;

Yang, HJ .

INFORMATION PROCESSING & MANAGEMENT, 2006, 42 (02) :387-406

[6] A Modeling Framework for Maintenance Optimization of Electrical Components Based on Fuzzy Logic and Effective Age [J].

Baraldi, P. ;

Balestrero, A. ;

Compare, M. ;

Benetrix, L. ;

Despujols, A. ;

Zio, E. .

QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 2013, 29 (03) :385-405

[7] Modelling the effects of maintenance on the degradation of a water-feeding turbo-pump of a nuclear power plant [J].

Baraldi, P. ;

Compare, M. ;

Despujols, A. ;

Zio, E. .

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART O-JOURNAL OF RISK AND RELIABILITY, 2011, 225 (O2) :169-183

[8] Application of a Niched Pareto Genetic Algorithm for Selecting Features for Nuclear Transients Classification [J].

Baraldi, P. ;

Pedroni, N. ;

Zio, E. .

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, 2009, 24 (02) :118-151

[9] Hierarchical k-nearest neighbours classification and binary differential evolution for fault diagnostics of automotive bearings operating under variable conditions [J].

Baraldi, Piero ;

Cannarile, Francesco ;

Di Maio, Francesco ;

Zio, Enrico .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2016, 56 :1-13

[10]

Baraldi P, 2013, P I MECH ENG O-J RIS, V227, P267, DOI [10.1177/1748006X13488479, 10.1177/1748006x13488479]

← 1 2 3 4 5 →