Abstract | ||
---|---|---|
To overcome the cost of numerical simulations of transient phenomena, the goal is to construct a robust spatio-temporal reduced model capable of long-term in time predictions. The construction proposed in this article has to deal with several constraints: the reference model is a black box with high dimensional inputs and outputs, long-term in time prediction, few learning samples available, non-linear behaviour and the construction time must remain reasonable while the prediction time must be negligible. Recurrent neural networks are predictive models adapted to this dynamic framework. The improvements of the construction methodology detailed in this paper are the weights optimization through a multilevel optimization approach, a robust construction based on cross-validation and an application of sensitivity analysis in order to reduce the input dimension of the network. Finally, this construction is validated on an industrial test case predicting the temperature of an electronic equipment located in the avionic bay and subjected to fluctuations of its boundary conditions. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/IJCNN.2015.7280679 | International Joint Conference on Neural Networks |
Keywords | Field | DocType |
avionics,optimisation,recurrent neural nets,sensitivity analysis,avionic bay,electronic equipment temperature prediction,long-term in time predictions,multilevel optimization approach,recurrent neural networks,sensitivity analysis,spatiotemporal reduced model,transient phenomena prediction | Black box (phreaking),Boundary value problem,Reference model,Computer science,Avionics,Recurrent neural network,Artificial intelligence,Electronic equipment,Artificial neural network,Machine learning,Multilevel optimization | Conference |
ISSN | Citations | PageRank |
2161-4393 | 0 | 0.34 |
References | Authors | |
7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jonathan Guerra | 1 | 0 | 0.34 |
Patricia Klotz | 2 | 2 | 1.09 |
Béatrice Laurent | 3 | 4 | 1.97 |
Fabrice Gamboa | 4 | 23 | 8.15 |