Optimizing 3D Printed MnO2 Electrode for Enhancing Supercapacitor Performances Through Machine Learning

Abstract The next generation of portable and wearable electronics demands the development of flexible and efficient energy storage systems. Supercapacitors are best suitable for portable energy storage because of their high-power density, fast charge/discharge capability, long cycle life, better safety, and lightweight. Extrusion based additive manufacturing is an efficient and ecofriendly method to fabricate 3D energy storage devices as it has better control over electrode, layer thickness and porosity, which enhances electrolyte ion diffusion and mechanical flexibility. Manganese dioxide (MnO2) has drawn much attention as a supercapacitor electrode material because of its high theoretical capacitance, low cost, and environmental safety. In this method, extrusion-based 3D printer (Hyrel Engine Hr) was used to fabricate customizable MnO2 electrode structures. The ink was prepared by mixing active material (MnO2), conductive agent (activated carbon) and binder (Poly(vinylidene fluoride)) with mass ratio of 8:1.5:0.5. The optimized printed supercapacitors exhibited high specific capacitance of 3.31 F/cm2, high energy density of 0.45 mWh/cm2 and a power density of 27.13 mW/cm2 at a current density of 2 mA/cm2 and stability over an extended number of charge-discharge cycles. The random forest (RF) algorithm was the most accurate for predicting the performances. The accuracy of the ML model was also cross-validated with the experimental data, showing strong predictive capability over performance metrics of different architectures of MnO2 electrodes. This work highlights the synergy between machine learning and additive manufacturing for the rapid design and optimization of supercapacitor performance for next-generation electronics.