An Ensemble Approach for Robust Data-Driven Prognostics

Prognostics aims at determining whether a failure of an engineered system (e.g., a nuclear power plant) is impending and estimating the remaining useful life (RUL) before the failure occurs. The traditional data-driven prognostic approach involves the following three steps: (Step 1) construct multiple candidate algorithms using a training data set; (Step 2) evaluate their respective performance using a testing data set; and (Step 3) select the one with the best performance while discarding all the others. There are three main challenges in the traditional data-driven prognostic approach: (i) lack of robustness in the selected standalone algorithm; (ii) waste of the resources for constructing the algorithms that are discarded; and (iii) demand for the testing data in addition to the training data. To address these challenges, this paper proposes an ensemble approach for data-driven prognostics. This approach combines multiple member algorithms with a weighted-sum formulation where the weights are estimated by using one of the three weighting schemes, namely the accuracy-based weighting, diversity-based weighting and optimization-based weighting. In order to estimate the prediction error required by the accuracy- and optimization-based weighting schemes, we propose the use of the k-fold cross validation (CV) as a robust error estimator. The performance of the proposed ensemble approach is verified with three engineering case studies. It can be seen from all the case studies that the ensemble approach achieves better accuracy in RUL predictions compared to any sole algorithm when the member algorithms with good diversity show comparable prediction accuracy.