An Explainable Physics-Informed Neural Frequency-Response Framework for Shunt-Parameter Identification in Semi-Active Piezoelectric Tuned Mass Dampers

2026-08-07

AI Summary

This study addresses the challenge of efficiently, accurately, and interpretably identifying hidden structural and shunt parameters in semi-active piezoelectric tuned mass dampers from frequency response data. To this end, the authors propose a hybrid framework that integrates a physics-driven forward model with neural inverse learning. By training a neural network on synthetically generated complex frequency response data and incorporating noise-robust training alongside multidimensional interpretability analyses—such as latent space organization, sensitivity mapping, and symbolic distillation—the method enables rapid, optimization-free inference of physically consistent parameters directly from measured frequency response functions. Experimental validation demonstrates that the approach achieves high data efficiency and strong generalization on real-world data while extracting electromechanical response descriptors with clear physical meaning.

Abstract

This paper proposes a Physics-Informed Neural Frequency Response Framework for learning and interpreting the frequency-domain behavior of semi-active shunted piezoelectric tuned mass dampers. The motivation is that the behavior of such systems is most naturally expressed through frequency response functions, while the governing electromechanical interactions depend strongly on hidden structural and shunt parameters. Conventional data-driven models can approximate these mappings, but they often lack physical consistency, require large training datasets, and provide limited interpretability. To address these limitations, the proposed framework combines a physics-based forward frequency-response model, a neural inverse learning module, and an explainability component. The forward model is used to generate synthetic complex-valued frequency-response data over a broad range of structural and shunt configurations while preserving the governing electromechanical behavior of the system. Based on synthetic frequency-response data, the neural inverse model is trained to estimate hidden parameters from spectral response signatures and is subsequently evaluated using independently measured experimental FRFs. This synthetic-to-experimental design enables fast parameter inference without solving a new optimization problem for each measured case. To improve robustness to realistic conditions, controlled noise is introduced only at the inverse-training stage, while the underlying physics model remains noise-free. In addition, the learned representation is analyzed through latent-space organization, sensitivity mapping, and reduced symbolic distillation in order to extract interpretable electromechanical response descriptors. The resulting framework provides a data-efficient and explainable ML approach for frequency-response-based identification and inverse tuning of STMD.

Problem

• shunt-parameter identification
• semi-active piezoelectric tuned mass dampers
• frequency-response
• explainable machine learning
• inverse problem

Innovation

• Physics-Informed Neural Networks
• Frequency Response Functions
• Shunt Parameter Identification
• Explainable AI
• Semi-Active Piezoelectric TMD