An Optimal Stacking Ensemble for Remaining Useful Life Estimation of Systems Under Multi-Operating Conditions
Open Access
- 12 February 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 31854-31868
Abstract
Remaining useful life (RUL) estimation is expected to provide appropriate maintenance for components or systems in industry to improve the reliability of the systems. Most data-based methods are limited to a single model, which is susceptible to various factors like environmental variability and diversity of operating conditions. In this paper, we propose an optimal stacking ensemble method combining different learning algorithms as meta-learners to mitigate the impact of multi-operating conditions. The selection of meta-learners follows a multi-objective evolutionary algorithm named non-dominated sorting genetic algorithms-II to balance the two conflicting objectives in terms of accuracy and diversity. Then the eventually evolved meta-learners are integrated by the meta-classifier for RUL estimation. In addition, a long-short-term feature extraction strategy is proposed to capture more degradation information from lifecycle data dynamically. Extensive experiments are performed on aero-engine dataset and battery dataset provided by NASA, which achieves the higher prognostic accuracy compared with the single models and existing methods.Keywords
Funding Information
- National Natural Science Foundation of China (61672537, 61873353, 61672539)
This publication has 38 references indexed in Scilit:
- A novel health indicator for on-line lithium-ion batteries remaining useful life predictionJournal of Power Sources, 2016
- Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life2016
- Applying Ant Colony Optimization to configuring stacking ensembles for data miningExpert Systems with Applications, 2014
- Prognostics and health management design for rotary machinery systems—Reviews, methodology and applicationsMechanical Systems and Signal Processing, 2014
- Optimization of stacking ensemble configurations through Artificial Bee Colony algorithmSwarm and Evolutionary Computation, 2013
- Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful lifeReliability Engineering & System Safety, 2012
- Multi-objective optimization of a stacked neural network using an evolutionary hyper-heuristicApplied Soft Computing, 2012
- Classifier ensembles: Select real-world applicationsInformation Fusion, 2008
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- Stacked generalizationNeural Networks, 1992