AI Assisted Optimization of Unimorph Tapered Cantilever for Piezoelectric Energy Harvesting

Abstract

This paper presents the results of the deploying machine learning models in the design and optimization of a unimorph tapered cantilever with proof mass, aimed for piezoelectric energy harvesting. Multiobjective optimization as described in the paper was performed in order to find the optimal dimensions of the structure, its length, its width at the anchor and the ratio between widths at the anchor and at the tip, with respect to the salient parameters for the energy harvesting applications, namely low frequency and high power generated by the structure. The method is applicable for the optimization of the design of more complex MEMS structures aimed for energy harvesting applications.