Application of supervised machine learning and Taylor diagrams for prognostic analysis of performance and emission characteristics of biogas-powered dual-fuel diesel engine - Research article

Aug 6, 2026

Upload by Violet

Biogas provides an attractive alternative to diesel in dual-fuel operation, using diesel as pilot fuel. This study models injection strategies for a waste-derived biogas dual-fuel engine and predicts performance and emissions through supervised machine learning, including random forest, lasso regression, and support vector machines. Model quality is assessed using MSE, R², and MAPE across key targets such as brake thermal efficiency, brake specific energy consumption, CO₂, CO, and NOx. Random forest achieves the highest accuracy overall with consistently strong predictive behavior.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Biogas as an alternative sustainable energy source

Diesel engine emissions and the role of alternative fuels

Using biogas in engines: single-fuel vs dual-fuel modes

| 1175 | |
Contents list available at CBIORE journal website
International Journal of Renewable Energy Development
Journal homepage: [https://ijred.cbiore.id](https://ijred.cbiore.id) | | --- | --- | Research Article Application of supervised machine learning and Taylor diagrams for prognostic analysis of performance and emission characteristics of biogas-powered dual-fuel diesel engine Khac Binh Lea, Minh Thai Duongb, Dao Nam Caob , Van Vang Le c,*P aVinh University of Technology Education, 117 Nguyen Viet Xuan Street, Hung Dung Ward, Vinh City, VietNam. bInstitute of Mechanical Engineering, Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet Nam. cInstitute of Maritime, Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet Nam. Abstract. In the ongoing search for an alternative fuel for diesel engines, biogas is an attractive option. Biogas can be used in dual-fuel mode with diesel as pilot fuel. This work investigates the modeling of injecting strategies for a waste-derived biogas-powered dual-fuel engine. Engine performance and emissions were projected using supervised machine learning methods including random forest, lasso regression, and support vector machines (SVM) . Mean Squared Error (MSE), R-squared (R²), and Mean Absolute Percentage Error (MAPE) were among the criteria used in evaluations of the models. Random Forest has shown better performance for Brake Thermal Efficiency (BTE) with a test R² of 0.9938 and a low test MAPE of 3.0741% . Random Forest once more exceeded other models with a test R² of 0.9715 and a test MAPE of 4.2242% in estimating Brake Specific Energy Consumption (BSEC) . With a test R² of 0.9821 and a test MAPE of 2.5801% Random Forest emerged as the most accurate model according to carbon dioxide (CO₂) emission modeling. Analogous results for the carbon monoxide (CO) prediction model based on Random Forest obtained a test R² of 0.8339 with a test MAPE of 3.6099% . Random Forest outperformed Linear Regression with a test R² of 0.9756% and a test MAPE of 7.2056% in the case of nitrogen oxide (NOx) emissions. Random Forest showed the most constant performance overall criteria. This paper emphasizes how well machine learning models especially Random Forest can prognosticate the performance of biogas dual-fuel engines. Keywords: Biogas; Alternative fuel; Supervised machine learning; Lasso regression; Random Forest; Taylor diagram @ The author(s) . Published by CBIORE. This is an open access article under the CC BY-SA license ([http://creativecommons.org/licenses/by-sa/4.0/](http://creativecommons.org/licenses/by-sa/4.0/)). Received: 25th June 2024; Revised: 19th October 2024; Accepted: 27th October 2024; Available online: 15th November 2024 1. Introduction SDG 7 seeks to guarantee that everyone can afford modern, reasonably priced, environmentally friendly energy, these targets can be achieved through various sustainable practices (Nguyen et al., 2024; “Tracking SDG 7 – The Energy Progress Report 2022,” n.d.) . The use of biogas is one such option. Biogas is generated from organic sources like food waste, sewage, and agricultural trash (Hoang et al., 2022; Naghavi et al., 2020; TheThanh et al., 2019) . That is the reason it is termed as a sustainable substitute for fossil fuels. By lowering reliance on conventional fuels such as charcoal or firewood, the use of biogas for cooking, heating, and electricity all help to increase energy availability (Fransiscus and Simangunsong, 2021; Hidayanti et al., 2021; Sharma et al., 2023b) . Other SDGs including Zero Hunger (SDG 2), which lowers food waste and supplies fertilizer, and Climate Action (SDG 13), which lowers greenhouse gas emissions, benefit from biogas generating as well. By offering a dependable and sustainable energy source, boosting energy access, and so supporting more general sustainability goals, biogas helps to meet SDG 7 (Lohani et al. , 2021; Rocha-Meneses et al., 2023; Runyowa a

FAQs

What fuel strategy does the study focus on for biogas-powered engines?

It investigates a dual-fuel mode where biogas is the main fuel and diesel acts as the pilot fuel to initiate combustion.

Which supervised machine learning models are used to predict performance and emissions?

The study evaluates random forest, lasso regression, and support vector machines (SVM) for predicting engine performance and emissions.

How does random forest perform compared with other models in the prognostic analysis?

Random forest shows superior and more consistent performance across evaluation metrics, achieving the best accuracy for BTE, BSEC, CO₂, and NOx prediction, and strong results for CO.

Aug 6, 2026

Upload by Violet