Transfer learning for predicting source terms of principal component transport in chemically reactive flow

TL;DR

This study explores transfer learning techniques to improve the prediction of chemical source terms in reduced-order models for hydrogen/air ignition, especially when training data is limited, introducing a novel method called PaPIR.

Contribution

The paper proposes a new transfer learning approach, PaPIR, that systematically adjusts knowledge transfer in neural networks for reactive flow modeling with sparse data.

Findings

Transfer learning significantly improves model accuracy with limited data.

PaPIR method enhances performance by controlling knowledge transfer.

Adjusting initialization schemes benefits low similarity tasks.

Abstract

The objective of this study is to evaluate whether the number of requisite training samples can be reduced with the use of various transfer learning models for predicting, for example, the chemical source terms of the data-driven reduced-order model that represents the homogeneous ignition process of a hydrogen/air mixture. Principal component analysis is applied to reduce the dimensionality of the hydrogen/air mixture in composition space. Artificial neural networks (ANNs) are used to tabulate the reaction rates of principal components, and subsequently, a system of ordinary differential equations is solved. As the number of training samples decreases at the target task (i.e.,for T0 > 1000 K and various phi), the reduced-order model fails to predict the ignition evolution of a hydrogen/air mixture. Three transfer learning strategies are then applied to the training of the ANN model with a sparse dataset. The performance of the reduced-order model with a sparse dataset is found to be remarkably enhanced if the training of the ANN model is restricted by a regularization term that controls the degree of knowledge transfer from source to target tasks. To this end, a novel transfer learning method is introduced, parameter control via partial initialization and regularization (PaPIR), whereby the amount of knowledge transferred is systemically adjusted for the initialization and regularization of the ANN model in the target task. It is found that an additional performance gain can be achieved by changing the initialization scheme of the ANN model in the target task when the task similarity between source and target tasks is relatively low.