Name
Abstract | ||
|---|---|---|
The use of Echo State Networks (ESNs) for the prediction of the Remaining Useful Life (RUL) of industrial components, i.e. the time left before the equipment will stop fulfilling its functions, is attractive because of their capability of handling the system dynamic behavior, the measurement noise, and the stochasticity of the degradation process. In particular, in this paper we originally resort to an ensemble of ESNs, for enhancing the performances of individual ESNs and providing also an estimation of the uncertainty affecting the RUL prediction. The main methodological novelties in our use of ESNs for RUL prediction are: i) the use of the individual ESN memory capacity within the dynamic procedure for aggregating of the ESNs outcomes; ii) the use of an additional ESN for estimating the RUL uncertainty, within the Mean Variance Estimation (MVE) approach. With these novelties, the developed approach outperforms a static ensemble and a standard MVE approach for uncertainty estimation in tests performed on a synthetic and two industrial datasets. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1016/j.neucom.2017.11.062 | Neurocomputing |
Keywords | Field | DocType |
Echo state networks,Recurrent neural networks,Ensembles,Prediction uncertainty,Prediction Intervals,Differential Evolution | Variance estimation,Recurrent neural network,Differential evolution,Prediction interval,Uncertainty estimation,Artificial intelligence,Degradation process,Mathematics,Machine learning | Journal |
Volume | ISSN | Citations |
281 | 0925-2312 | 5 |
PageRank | References | Authors |
0.40 | 34 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marco Rigamonti | 1 | 8 | 1.49 |
| Piero Baraldi | 2 | 236 | 21.96 |
| Enrico Zio | 3 | 77 | 7.43 |
| Indranil Roychoudhury | 4 | 67 | 6.19 |
| Kai Goebel | 5 | 189 | 22.36 |
| Scott Poll | 6 | 56 | 5.60 |