Environmental Effects of Exhaust Emission from Spark Ignition Engine Fuelled with 4% HDPE Pyrolysis Oil-Gasoline Blend: Artificial Neural Network Modelling
Manickavelan Kolandasami1, Kumaradhas Paulian2, Venkatesan Tharanipathy3, Mithun V.Kulkarni4
1Dr. Manickavelan Kolandasami, Department of Mechanical Engineering, University of Technology and Applied Sciences, Salalah (Dhofar), Oman.
2Dr. Kumaradhas Paulian, Department of Mechanical Engineering, University of Technology and Applied Sciences, Salalah (Dhofar), Oman.
3Er. Venkatesan Tharanipathy, Department of Mechanical Engineering, University of Technology and Applied Sciences, Salalah (Dhofar), Oman.
4Dr. Mithun. V. Kulkarni, Department of Mechanical Engineering, University of Technology and Applied Sciences, Salalah (Dhofar), Oman.
Manuscript received on 02 November 2024 | Revised Manuscript received on 13 April 2026 | Manuscript Accepted on 15 April 2026 | Manuscript published on 30 April 2026 | PP: 4-10 | Volume-13 Issue-4, April 2026 | Retrieval Number: 100.1/ijies.E818513050125 | DOI: 10.35940/ijies.E8185.13040426
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The present study investigates the environmental impacts of exhaust emissions from a spark-ignition (SI) engine fueled with a 4% High-Density Polyethene (HDPE) pyrolysis oil gasoline blend. Using Artificial Neural Network (ANN) modelling, the research focuses on predicting and analysing key emissions parameters, including carbon monoxide (CO), nitrogen oxides (NOx), oxygen (O2), hydrocarbons (HC), and carbon dioxide (CO2). A comprehensive dataset, encompassing various operational conditions, load, and speed, is collected from experiments. The analysis involves feature selection, data preprocessing, and the design of a feedforward backpropagation neural network architecture. The model is trained, tested, and validated on the dataset, with performance evaluated against environmental standards and regulations. Results from the trained ANN are then utilized to assess the environmental impact of the fuel blend under different scenarios. Sensitivity analysis identifies influential factors affecting emissions, providing insights into the complex relationship between input features and environmental effects. The study concludes with a detailed interpretation of findings, highlighting potential future considerations for mitigating environmental impacts associated with the use of HDPE pyrolysis oil-gasoline blends in SI engines. This research contributes to a deeper understanding of the interplay between fuel composition and environmental sustainability.
Keywords: Spark-ignition, Comprehensive Dataset, Load Encompassing, Various Operational Conditions
Scope of the Article: Civil Engineering