Fast optimize arm wearable piezoelectric energy harvesters via artificial neural network

Converting actions of human's body into electrical energy via wearable energy harvesters is an exciting area. This study presents a ball impact piezoelectric energy converter consisting of two circular ceramic piezoelectric sheets to obtain energy from arm swing. 2264 sets of data were measured to train the artificial neural network (ANN) modes. The performance of ANN optimized by three different algorithms (Nadam, Adamax, and Adadelta) was compared and discussed. Treadmill experiments verified and confirmed the prediction results from ANN, an effective voltage of 11.3 V was demonstrated at a running speed of 9 km/h. Our results show that ANN can speed up the optimizing process for designing better energy harvesters.

Automated summary

This study proposes a method of converting human body actions into electrical energy via a ball impact piezoelectric energy converter, and optimizes its performance using an artificial neural network model. Treadmill experiments verify the prediction results of the model and demonstrate an effective voltage of 11.3 V.