Flow Battery Manifold Design with Heterogeneous Inputs Through Generative Adversarial Neural Networks

TL;DR

This paper introduces a systematic framework combining generative adversarial networks and Bayesian optimization to design flow battery manifolds with heterogeneous inputs, improving interpretability and exploration of feasible configurations.

Contribution

It presents a novel framework for generating archetypes with heterogeneous inputs and integrating generative models with Bayesian optimization for interpretable design exploration.

Findings

Successfully designed flow battery manifolds with diverse configurations

Enhanced interpretability of the design space through latent space analysis

Demonstrated efficient exploration of feasible and novel designs

Abstract

Generative machine learning has emerged as a powerful tool for design representation and exploration. However, its application is often constrained by the need for large datasets of existing designs and the lack of interpretability about what features drive optimality. To address these challenges, we introduce a systematic framework for constructing training datasets tailored to generative models and demonstrate how these models can be leveraged for interpretable design. The novelty of this work is twofold: (i) we present a systematic framework for generating archetypes with internally homogeneous but mutually heterogeneous inputs that can be used to generate a training dataset, and (ii) we show how integrating generative models with Bayesian optimization can enhance the interpretability of the latent space of admissible designs. These findings are validated by using the framework to design a flow battery manifold, demonstrating that it effectively captures the space of feasible designs, including novel configurations while enabling efficient exploration. This work broadens the applicability of generative machine-learning models in system designs by enhancing quality and reliability.