Gasification process prediction using a novel and reliable metaheuristic algorithm coupled with the K-nearest neighbors

Abstract

Listen

Translate article

Abstract The present work introduces a new method for forecasting the formation of CH4 and C2Hn gases in the gasification of biomass. The K-nearest neighbors (KNN) algorithm is utilized as the base model, while two innovative optimization techniques, Artificial Rabbits Optimization (ARO) and Smell Agent Optimization (SAO), are employed to enhance the overall performance and achieve optimal results. The goal of this investigation is to create a prediction model that can reliably and accurately anticipate the amount of CH4 and C2Hn gases produced during the gasification of biomass. By combining the strengths of the KNN algorithm with the optimization capabilities of ARO and SAO, the proposed approach aims to overcome existing limitations in gasification process predictions. The experimental results demonstrate the effectiveness of the combined approach in accurately predicting the gasification process and estimating the quantities of CH4 and C2Hn gases produced. The integration of ARO and SAO with the KNN algorithm enables better optimization of the model, leading to improved accuracy and reliability in predicting gasification outcomes. Additionally, the effectiveness of the suggested models was thoroughly evaluated and assessed utilizing performance evaluators. Remarkably, the KNSA (combination of KNN and SAO) model achieved the highest R 2 values of 0.994 and 0.995 for CH4 and C2Hn, correspondingly, which demonstrates the effectiveness of the suggested methods. The conclusion of this study contributes to the field of biomass gasification, as it proposed a new methodology that used the KNN algorithm as a base model, further improving its performance through the implementation of new optimization techniques. Further optimizations of the gasification process may now be opened, and a set of insights may be derived from the research for curiosity-driven scholars and practitioners in renewable energy production.