Enhanced physics-constrained deep neural networks for modeling vanadium redox flow battery

TL;DR

This paper introduces an enhanced physics-constrained deep neural network (ePCDNN) for more accurate voltage prediction in vanadium redox flow batteries, combining physics-based modeling with an additional neural network to improve accuracy at extreme states of charge.

Contribution

The paper presents an improved ePCDNN approach that integrates a second neural network to mitigate errors from the simplified 0D model, enhancing voltage prediction accuracy across all charge states.

Findings

ePCDNN accurately captures voltage response throughout charge-discharge cycles.

Significant improvement in prediction accuracy over standard PCDNN.

Flexible loss function allows transferability to different battery systems.

Abstract

Numerical modeling and simulation have become indispensable tools for advancing a comprehensive understanding of the underlying mechanisms and cost-effective process optimization and control of flow batteries. In this study, we propose an enhanced version of the physics-constrained deep neural network (PCDNN) approach [1] to provide high-accuracy voltage predictions in the vanadium redox flow batteries (VRFBs). The purpose of the PCDNN approach is to enforce the physics-based zero-dimensional (0D) VRFB model in a neural network to assure model generalization for various battery operation conditions. Limited by the simplifications of the 0D model, the PCDNN cannot capture sharp voltage changes in the extreme SOC regions. To improve the accuracy of voltage prediction at extreme ranges, we introduce a second (enhanced) DNN to mitigate the prediction errors carried from the 0D model itself and call the resulting approach enhanced PCDNN (ePCDNN). By comparing the model prediction with experimental data, we demonstrate that the ePCDNN approach can accurately capture the voltage response throughout the charge--discharge cycle, including the tail region of the voltage discharge curve. Compared to the standard PCDNN, the prediction accuracy of the ePCDNN is significantly improved. The loss function for training the ePCDNN is designed to be flexible by adjusting the weights of the physics-constrained DNN and the enhanced DNN. This allows the ePCDNN framework to be transferable to battery systems with variable physical model fidelity.