Artificial Intelligence-Based Optimization of a Bimorph-Segmented Tapered Piezoelectric MEMS Energy Harvester for Multimode Operation

Osor Pertin,Koushik Guha,Olga Jakšić

doi:10.3390/computation9080084

Osor Pertin, Koushik Guha + Show 1 more

Open Access

https://doi.org/10.3390/computation9080084

Copy DOI

Abstract

This paper presents a study on the design and multiobjective optimization of a bimorph-segmented linearly tapered piezoelectric harvester for low-frequency and multimode vibration energy harvesting. The procedure starts with a significant number of FEM simulations of the structure with different geometric dimensions—length, width, and tapering ratio. The datasets train the artificial neural network (ANN) that provides the fitting function to be modified and used in algorithms for optimization, aiming to achieve minimal resonant frequency and maximal generated power. Levenberg–Marquardt (LM) and scaled conjugate gradient (SCG) methods were used to train the ANN, then the goal attainment method (GAM) and genetic algorithm (GA) were used for optimization. The dominant solution resulted from optimization by the genetic algorithm integrated with the ANN fitting function obtained by the SCG training method. The optimal piezoelectric harvester is 121.3 mm long and 71.56 mm wide and has a taper ratio of 0.7682. It ensures over five times greater output power at frequencies below 200 Hz, which benefits the low frequency of the vibration spectrum. The optimized design can harness the power of higher-resonance modes for multimode applications.

Highlights

The triplet choice is obtained by the goal attainment method applied to the artificial neural network (ANN) function adapted for single-objective optimization that fitted examples with the scaled conjugate gradient method
The paper presents the method for designing and optimizing the piezoelectric vibration energy harvester based on a bimorph PZT-5 segmented linearly tapered cantilever of steel with a proof mass at its end
The datasets were generated by finite element model (FEM) simulations and used for training the artificial neural network (ANN) that provided the fitting function in the optimization algorithms

Summary

Introduction

A vibration energy harvester (VEH) provides a self-sufficient and sustainable power solution for low-power devices in a wireless sensor network (WSN), replacing conventional bulky batteries with a limited lifetime [1]. The major challenge in a micro-energy harvester is low power generation. Sil et al showed that increasing the beam’s length and reducing the beam’s width and thickness improved the output generation of the VEH [2]. The tapered beam design of the linear PVEH produces greater output voltage, as the beam will experience a higher strain for a particular mechanical input. The cantilever-based PVEH in higher vibration modes has specific strain nodes where the cancellation of electric charge reduces the generated output [6]. Segmentation of the piezoelectric layer or electrodes at this strain node reduces the resonant frequency and increases the power generation in higher vibration modes [7]

Objectives

Methods

Results

Conclusion