Predicting component reliability and level of degradation with complex-valued neural networks

Autor: Olga Fink, Enrico Zio, Ulrich Weidmann
Přispěvatelé: Institute for Transport Planning and Systems, Chaire Sciences des Systèmes et Défis Energétiques EDF/ECP/Supélec (SSEC), Ecole Centrale Paris-Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-CentraleSupélec-EDF R&D (EDF R&D), EDF (EDF)-EDF (EDF)
Jazyk: angličtina
Rok vydání: 2014
Předmět:
Risk
0209 industrial biotechnology
Engineering
[SCCO.COMP]Cognitive science/Computer science
02 engineering and technology
Machine learning
computer.software_genre
Industrial and Manufacturing Engineering
Complex valued neural networks
Level of degradation Railway turnout system
Neural networks
Reliability prediction
Safety
Risk
Reliability and Quality
Applied Mathematics
[SPI]Engineering Sciences [physics]
020901 industrial engineering & automation
Component (UML)
0202 electrical engineering
electronic engineering
information engineering
Time series
Reliability (statistics)
Series (mathematics)
Artificial neural network
business.industry
Railway turnout system
Reliability and Quality
Benchmark (computing)
Feedforward neural network
Level of degradation
020201 artificial intelligence & image processing
Artificial intelligence
Safety
business
computer
Degradation (telecommunications)
Zdroj: Reliability Engineering and System Safety
Reliability Engineering and System Safety, Elsevier, 2014, 121, pp.198-206. ⟨10.1016/j.ress.2013.08.004⟩
Reliability Engineering & System Safety
ISSN: 0951-8320
1879-0836
DOI: 10.1016/j.ress.2013.08.004⟩
Popis: International audience; In this paper, multilayer feedforward neural networks based on multi-valued neurons (MLMVN), a specific type of complex valued neural networks, are proposed to be applied to reliability and degradation prediction problems, formulated as time series. MLMVN have demonstrated their ability to extract complex dynamic patterns from time series data for mid- and long-term predictions in several applications and benchmark studies. To the authors' knowledge, it is the first time that MLMVN are applied for reliability and degradation prediction. MLMVN are applied to a case study of predicting the level of degradation of railway track turnouts using real data. The performance of the algorithms is first evaluated using benchmark study data. The results obtained in the reliability prediction study of the benchmark data show that MLMVN outperform other machine learning algorithms in terms of prediction precision and are also able to perform multi-step ahead predictions, as opposed to the previously best performing benchmark studies which only performed up to two-step ahead predictions. For the railway turnout application, MLMVN confirm the good performance in the long-term prediction of degradation and do not show accumulating errors for multi-step ahead predictions.
Databáze: OpenAIRE
Externí odkaz: