Abstract
• Using artificial neural networks to optimize piezoelectric devices allows skipping the construction of physical models. • The ball impact energy harvesting device is more suitable for human energy harvesting. • Considering different optimization algorithms can effectively improve the predictive power of artificial neural networks. • It is necessary to adjust the initial learning rate of the algorithm. 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.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
