Genetic Algorithm-Based Optimization Of Engine Parameters For Enhanced Efficiency

Abstract

The growing demand for sustainable fuels has accelerated research into optimizing engine performance when using biodiesel. This study explores the application of Genetic Algorithms (GA) to optimize key engine parameters such as injection timing, compression ratio, and biodiesel blend ratio for improved performance and reduced emissions in a compression ignition (CI) engine. Biodiesel derived from waste cooking oil was used to formulate blends (B20–B100), and experimental tests were conducted to evaluate performance metrics including brake thermal efficiency (BTE), brake specific fuel consumption (BSFC), and nitrogen oxide (NOx) emissions. A GA model was developed in MATLAB to identify the optimal combination of parameters that maximized engine efficiency while minimizing emissions. The GA-based optimization results showed significant improvements over baseline values, with enhanced thermal efficiency and notable reductions in NOx. The findings highlight the potential of genetic algorithms as a robust tool for multi-objective optimization in biodiesel-fueled engines, offering a path toward cleaner and more efficient engine operation.