Interaction effect of process parameters and Pd‐electrocatalyst in formic acid electro‐oxidation for fuel cell applications: Implementing supervised machine learning algorithms

Abstract

The increasing interest in renewable and sustainable energy production as a means of attaining net-zero carbon emissions in the near future has spurred research attention in the development of fuel cells that convert chemical energy to electrical energy. In this study machine learning algorithms namely Support Vector Machine (SVM) regression, Regression Trees, and Gaussian Process Regression (GPR) were configured for modeling the effect of palladium supported on carbon nanotube used for formic acid electro-oxidation. The effect of process parameters such as the amount of palladium, the amount of sodium tetrahydridoborate (NaBH 4 ), amount of water, and the electro-oxidation reaction time on the formic acid electro-oxidation to generate current density was evaluated by the various models. The trained SVM regressions models incorporated with linear, quadratic, cubic, and fine Gaussian kernel functions, as well as the Boosted and the Bagged regression Trees, did not show impressive performance as indicated by a low coefficient of determination (R 2 ) < 0.5 and high prediction errors. However, the SVM regression modeled with Median Gaussian kernel function, the GPR incorporated with rotational quadratic and squared exponential kernel functions displayed higher performance with R 2 > 0.6 but less than 0.7. The optimization of the SVM, Ensemble Tree, and GPR models resulted in significant performance with R 2 of 0.82, 0.83, and 0.85, respectively. The sensitivity analysis using modified Garson algorithm to determine how each of these parameters influences the predicted current density from the direct formic acid fuel cells showed that the level of importance of the input parameters on the predicted current density can be ranked as Pd composition > electro-oxidation time > amount of water > NaBH 4 proportion.

Study of Friction and Wear Behavior of Graphene-Reinforced AA7075 Nanocomposites by Machine Learning

“…Delamination wear causes thin laminates to discard as waste due to the instability of crack propagation at the tribosurface's subsurface. Exfoliation, craters, and scratches are far less common on AA7075graphene nanocomposites than on base AA7075, according to research by Li et al [27] and Hossain et al [28].…”

Machine Learning-Based Current Density Simulation for Direct Borohydride Fuel Cell

“…Many current findings have offered machine learning-based fuel cell modeling methods. Hossain et al [6] have proposed a machine learning algorithm namely Support Vector Machine (SVM) regression, Regression Trees, and Gaussian Process Regression (GPR) for modeling the effect of palladium supported on carbon nanotube used for formic acid electro-oxidation for DBFC. In previous research, we also have developed an artificial neural network-based fuel cell design approach for proton exchange membranes, the most prevalent and commonly used fuel cell type [7].…”

Predictive Modeling of Bioenergy Production from Fountain Grass Using Gaussian Process Regression: Effect of Kernel Functions

“…The bioethanol production is most favorable at 240 h, pH of 9, the temperature of 300 K, and yeast extract of 4500 mg/L. The application of machine learning algorithms such as GPR can harness the enormous potential of renewable energy [34]. The renewable energy industry would be left behind were GPR not adopted for the full transition process.…”