Data-Driven Freeform MEMS Energy Harvester Design Enabled by Machine Learning


This paper reports a computational method for the design of freeform piezoelectric energyharvesters (PEHs) fabricated by micromachining processes based on the machine learning (ML)scheme. The geometry of candidate designs is first converted to pixelated images and assignedwith specific properties and analyzed by the finite element method (FEM). The resulting neuralnetwork machine learning algorithm is trained using the above dataset to identify the propertiesof similar freeform PEH designs, which is 30,000 times faster than those by the FEM simulations.With 200,000 freeform designs analyzed by the ML-analyzer, the best designs with broadoperation frequency bandwidth, low-frequency spectrum, and high output voltage are identified.

Publication date: 
January 9, 2022
Publication type: 
Conference Paper (Proceedings)
Kunying Li, Ruiqi Guo, Fanping Sui, and Liwei Lin, "Data-Driven Freeform MEMSEnergy Harvester Design Enabled by Machine Learning" Proceedings of the 35th IEEEMicro Electro Mechanical Systems Conference, Virtual, Jan. 2022.

*Only registered BSAC Industrial Members may view project materials & publications. Click here to request member-only access.