ORIGINAL RESEARCH article
Front. Phys.
Sec. Interdisciplinary Physics
Volume 13 - 2025 | doi: 10.3389/fphy.2025.1642670
This article is part of the Research TopicNonlinear Vibration and Instability in Nano/Micro Devices: Principles and Control StrategiesView all 18 articles
A Surrogate Model for Predicting Bimorph Microscale Piezoelectric Energy Harvester Performance under Base Vibration and Thermal Effects
Provisionally accepted
- 1Shahid Chamran University of Ahvaz, Ahvaz, Iran
- 2Technical University of Berlin, Berlin, Germany
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
This paper introduces a machine learning-based surrogate model designed to predict the performance of bimorph microscale piezoelectric energy harvesters subjected to base excitation and thermal gradients. The analysis focuses on a three-layer clamped beam comprised of PZT-5H piezoelectric outer layers and an aluminum core, modeled using Euler-Bernoulli beam theory. The system's output power demonstrates significant nonlinear dependencies on geometric, material, and thermal parameters. To address the computational challenges of solving complex governing equations, a surrogate model is developed utilizing Gaussian Process Regression (GPR), which is trained on data generated through Latin Hypercube Sampling. This model successfully predicts power output and natural frequency across different design scenarios. Validation against numerical results confirms the accuracy of the surrogate model, showing exceptional prediction performance with R² values exceeding 0.99. This framework enhances design optimization, improving efficiency and reliability in thermalvibrational energy harvesting systems.
Keywords: Microscale energy harvesting system, Temperature gradient, Base renewable vibrational energy, Nonlinear dependence, Excitation frequency, Machine learning-based surrogate modeling
Received: 06 Jun 2025; Accepted: 11 Aug 2025.
Copyright: © 2025 Moory Shirbani, Marinkovic, Ehsan Alavi and Sh Khoram-Nejad. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Meisam Moory Shirbani, Shahid Chamran University of Ahvaz, Ahvaz, Iran
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.