(87h) Optimization of Capacitance in Supercapacitors By Constructing an Experimentally Validated Hybrid Artificial Neural Networks-Genetic Algorithm Framework

Supercapacitors are high power electrochemical energy storage systems that are attractive candidates for use in high power applications. Yet, their widespread adoption has been restricted due to their relatively low energy density. Improving the energy storage performance of supercapacitors is linked to rationally optimizing the key descriptors that affect capacitance. This work presents a systematic approach based on a hybrid artificial neural network (ANN) and genetic algorithm (GA) integrated with the Big M method to efficiently and rationally design carbon-based supercapacitors with improved energy storage performance. By performing structural and electrochemical characterization on systems we fabricate, we experimentally validate the robustness and generalizability of the developed ANN-GA framework. This study takes a step towards the rational design of supercapacitors by implementing the hybrid ANN-GA framework as an optimization tool to provide guidelines for rationally tuning material properties and operational conditions for improved capacitance.