Impact of machine learning approach using ANN and RSM to evaluated the engine characteristics of a dual-fuel CI engine

Abstract

Surge in fossil fuels consumption has severely impacted the environment, namely in terms of climate change, due to the influence of extensive pollution. The current study assesses and contrasts the ability of Artificial Neural Networks (ANN), a machine learning technique, and Response Surface Methodology (RSM) derived model to predict the important engine characteristics such as performance and emissions. The effect of parameters such as load (25%, 50%, 75%, and 100%), speed (1500 RPM and 1800 RPM), compression ratio (17.5 and 18.5), and six different blends of diesel-biodiesel fuels (Diesel, SM20, SM40, SM60, SM80, and SM100) were investigated on test engine (4-S single-cylinder DI diesel engine). Box Behnken Design (BBD) of Response Surface Methodology (RSM) and a Multi-Layer Perceptron (MLP) neural network with a topology of 4-10-6 was employed to study the principal engine performance (brake thermal efficiency, brake-specific fuel consumption, and indicated mean effective pressure) and emission (carbon dioxide, nitrogen oxides, and smoke) parameters. Using statistical analysis on both RSM and ANN, the projected outcomes were then compared with experimental results. The outcomes of present study reveals that RSM (Response Surface Methodology) and ANN (Artificial Neural Networks) can be employed to model processes that exhibit high predictability. Optimization can be performed utilizing diverse strategies, which rely on the specific process or problem.