Neuro-Symbolic Operator for Interpretable and Generalizable Characterization of Complex Piezoelectric Systems

TL;DR

This paper introduces a neuro-symbolic operator that combines neural networks and symbolic models to provide interpretable and generalizable characterization of complex piezoelectric systems, addressing limitations of black-box neural operators.

Contribution

It proposes a novel neuro-symbolic framework that learns analytical operators for hysteresis, enhancing interpretability and generalization over existing neural operator methods.

Findings

Accurately predicts voltage-displacement hysteresis including butterfly shapes.

Robust to noisy and low-fidelity voltage data.

Outperforms state-of-the-art neural operators in evaluation metrics.

Abstract

Complex piezoelectric systems are foundational in industrial applications. Their performance, however, is challenged by the nonlinear voltage-displacement hysteretic relationships. Efficient characterization methods are, therefore, essential for reliable design, monitoring, and maintenance. Recently proposed neural operator methods serve as surrogates for system characterization but face two pressing issues: interpretability and generalizability. State-of-the-art (SOTA) neural operators are black-boxes, providing little insight into the learned operator. Additionally, generalizing them to novel voltages and predicting displacement profiles beyond the training domain is challenging, limiting their practical use. To address these limitations, this paper proposes a neuro-symbolic operator (NSO) framework that derives the analytical operators governing hysteretic relationships. NSO first learns a Fourier neural operator mapping voltage fields to displacement profiles, followed by a library-based sparse model discovery method, generating white-box parsimonious models governing the underlying hysteresis. These models enable accurate and interpretable prediction of displacement profiles across varying and out-of-distribution voltage fields, facilitating generalizability. The potential of NSO is demonstrated by accurately predicting voltage-displacement hysteresis, including butterfly-shaped relationships. Moreover, NSO predicts displacement profiles even for noisy and low-fidelity voltage data, emphasizing its robustness. The results highlight the advantages of NSO compared to SOTA neural operators and model discovery methods on several evaluation metrics. Consequently, NSO contributes to characterizing complex piezoelectric systems while improving the interpretability and generalizability of neural operators, essential for design, monitoring, maintenance, and other real-world scenarios.