Prediction of industrial equipment Remaining Useful Life by fuzzy similarity and belief function theory

被引:23
作者
Baraldi, Piero [1 ]
Di Maio, Francesco [1 ]
Al-Dahidi, Sameer [1 ]
Zio, Enrico [1 ,2 ]
Mangili, Francesca [3 ]
机构
[1] Politecn Milan, Dipartimento Energia, Via La Masa 34, I-20156 Milan, Italy
[2] Univ Paris Saclay, Fdn Elect France EDF, Chair Syst Sci & Energy Challenge, Cent Supelec, F-92290 Chatenay Malabry, France
[3] USI, SUPSI, Ist Dalle Molle Studi Intelligenza Artificiale ID, Galleria 2,Via Cantonale 2C, CH-6928 Manno, Switzerland
关键词
Prognostics; Remaining Useful Life; Uncertainty; Fuzzy similarity; Belief function; Boiling Water Reactor condenser; PROGNOSTICS; MODEL; UNCERTAINTY; SYSTEM;
D O I
10.1016/j.eswa.2017.04.035
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We develop a novel prognostic method for estimating the Remaining Useful Life (RUL) of industrial equipment and its uncertainty. The novelty of the work is the combined use of a fuzzy similarity method for the RUL prediction and of Belief Function Theory for uncertainty treatment. This latter allows estimating the uncertainty affecting the RUL predictions even in cases characterized by few available data, in which traditional uncertainty estimation methods tend to fail. From the practical point of view, the maintenance planner can define the maximum acceptable failure probability for the equipment of interest and is informed by the proposed prognostic method of the time at which this probability is exceeded, allowing the adoption of a predictive maintenance approach which takes into account RUL uncertainty. The method is applied to simulated data of creep growth in ferritic steel and to real data of filter clogging taken from a Boiling Water Reactor (BWR) condenser. The obtained results show the effectiveness of the proposed method for uncertainty treatment and its superiority to the Kernel Density Estimation (KDE) and the Mean-Variance Estimation (MVE) methods in terms of reliability and precision of the RUL prediction intervals. (C) 2017 Elsevier Ltd. All rights reserved.
引用
收藏
页码:226 / 241
页数:16
相关论文
共 47 条
[1]   A novel fault detection system taking into account uncertainties in the reconstructed signals [J].
Al-Dahidi, Sameer ;
Baraldi, Piero ;
Di Maio, Francesco ;
Zio, Enrico .
ANNALS OF NUCLEAR ENERGY, 2014, 73 :131-144
[2]   Ensembling evidential k-nearest neighbor classifiers through multi-modal perturbation [J].
Altincay, Hakan .
APPLIED SOFT COMPUTING, 2007, 7 (03) :1072-1083
[3]  
Angstenberger L., 2001, INT SER INTELL TECHN, V17
[4]  
[Anonymous], 2010, INT J PERFORMABILITY
[5]  
[Anonymous], 2010, TRAJECTORY SIMILARIT
[6]  
Baraldi P., 2013, 2013 PROGN SYST HLTH
[7]  
Baraldi P., 2012, 2012 IEEE C PROGNOST
[8]   A belief function theory based approach to combining different representation of uncertainty in prognostics [J].
Baraldi, Piero ;
Mangili, Francesca ;
Zio, Enrico .
INFORMATION SCIENCES, 2015, 303 :134-149
[9]   Model-based and data-driven prognostics under different available information [J].
Baraldi, Piero ;
Cadini, Francesco ;
Mangili, Francesca ;
Zio, Enrico .
PROBABILISTIC ENGINEERING MECHANICS, 2013, 32 :66-79
[10]   Investigation of uncertainty treatment capability of model-based and data-driven prognostic methods using simulated data [J].
Baraldi, Piero ;
Mangili, Francesca ;
Zio, Enrico .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2013, 112 :94-108