Deep learning-based optimization of a microfluidic membraneless fuel cell for maximum power density via data-driven three-dimensional multiphysics simulation

Dang Dinh Nguyen; Thinh Quy Duc Pham; Muhammad Tanveer; Haroon Khan; Ji Won Park; Cheol Woo Park; Gyu Man Kim

doi:10.1016/j.biortech.2022.126794

Deep learning-based optimization of a microfluidic membraneless fuel cell for maximum power density via data-driven three-dimensional multiphysics simulation

Bioresour Technol. 2022 Mar:348:126794. doi: 10.1016/j.biortech.2022.126794. Epub 2022 Feb 8.

Authors

Dang Dinh Nguyen¹, Thinh Quy Duc Pham², Muhammad Tanveer³, Haroon Khan³, Ji Won Park³, Cheol Woo Park³, Gyu Man Kim⁴

Affiliations

¹ School of Mechanical Engineering, Kyungpook National University, Daegu 41566, South Korea; National Research Institute of Mechanical Engineering, No.4 Pham Van Dong street, Cau Giay district, Ha Noi, Viet Nam.
² Institute of Strategies Development, Thu Dau Mot University, 06 Tran Van On, Phu Hoa, Binh Duong, Viet Nam.
³ School of Mechanical Engineering, Kyungpook National University, Daegu 41566, South Korea.
⁴ School of Mechanical Engineering, Kyungpook National University, Daegu 41566, South Korea. Electronic address: gyuman.kim@knu.ac.kr.

PMID: 35149180
DOI: 10.1016/j.biortech.2022.126794

Abstract

A deep learning-based method for optimizing a membraneless microfluidic fuel cell (MMFC)performance by combining the artificial neural network (ANN) and genetic algorithm (GA) was for the first time introduced. A three-dimensional multiphysics model that had an accuracy equivalent to experimental results (R² = 0.976) was employed to generate the ANN's training data. The constructed ANN is equivalent to the simulation (R² = 0.999) but with far better computation resource efficiency as the ANN's execution time is only 0.041 s. The ANN model is then used by the GA to determine the inputs (microchannel length = 10.040 mm, width = 0.501 mm, height = 0.635 mm; temperature = 288.210 K, cell voltage = 0.309 V) that lead to the maximum power density of 0.263 mWcm^-2 (current density of 0.852 mAcm^-2) of the MMFC. The ANN-GA and numerically calculated maximum power densities differed only by 0.766%.

Keywords: Artificial neural network; Genetic algorithm; Maximum power density; Membraneless microfluidic fuel cells.

MeSH terms

Computer Simulation
Deep Learning*
Microfluidics*
Neural Networks, Computer
Temperature