ADVANCED ENERGY HARVESTING IN MECHANICAL SYSTEMS VIA MACHINE LEARNING AND SMART MATERIALS

Authors

  • Archana Author

Abstract

Energy harvesting in mechanical systems has gained prominence as industries seek sustainable and self-powered solutions for sensors, actuators, and embedded electronics. This paper investigates the integration of machine learning (ML) and smart materials to optimize vibrational and thermal energy harvesting from mechanical systems. We develop a hybrid data-driven and physics-based framework to predict and enhance energy output of piezoelectric, triboelectric, and thermoelectric harvesters embedded in rotating and reciprocating machinery. A synthetic dataset representing energy harvester performance under various operating conditions is generated to illustrate methodology. Machine learning models are trained to predict power output and efficiency, and an optimization algorithm is used to maximize energy harvested while maintaining system stability. Results show improved prediction accuracy and demonstrate how ML assisted optimization can identify nonintuitive parameter settings that significantly increase energy recovery.

Downloads

Published

2025-12-09

How to Cite

Archana. (2025). ADVANCED ENERGY HARVESTING IN MECHANICAL SYSTEMS VIA MACHINE LEARNING AND SMART MATERIALS. International Journal of AI Electrical Civil and Mechanical Engineering, 1(4), 20-24. https://zesterapublications.com/journals/index.php/ijaecme/article/view/10