Uncertainty quantification for industrial design using dictionaries of reduced order models

TL;DR

This paper demonstrates the application of a dictionary-based ROM-net framework to quantify uncertainty in an industrial elastoviscoplastic turbine blade model, achieving significant computational speedup with acceptable accuracy.

Contribution

It applies the ROM-net framework to a real industrial problem, improving uncertainty quantification efficiency and deriving a meta-model for reconstructing detailed quantities.

Findings

Speedup greater than 600 times compared to traditional solvers

Achieved a relative error of about 2% in predictions

Successfully quantified uncertainty on dual quantities in a complex industrial model

Abstract

We consider the dictionary-based ROM-net (Reduced Order Model) framework [T. Daniel, F. Casenave, N. Akkari, D. Ryckelynck, Model order reduction assisted by deep neural networks (ROM-net), Advanced modeling and Simulation in Engineering Sciences 7 (16), 2020] and summarize the underlying methodologies and their recent improvements. The main contribution of this work is the application of the complete workflow to a real-life industrial model of an elastoviscoplastic high-pressure turbine blade subjected to thermal, centrifugal and pressure loadings, for the quantification of the uncertainty on dual quantities (such as the accumulated plastic strain and the stress tensor), generated by the uncertainty on the temperature loading field. The dictionary-based ROM-net computes predictions of dual quantities of interest for 1008 Monte Carlo draws of the temperature loading field in 2 hours and 48 minutes, which corresponds to a speedup greater than 600 with respect to a reference parallel solver using domain decomposition, with a relative error in the order of 2%. Another contribution of this work consists in the derivation of a meta-model to reconstruct the dual quantities of interest over the complete mesh from their values on the reduced integration points.