Multi-objective optimization of diesel engine using back propagation neural network and metaheuristic methods

Air pollution is a serious problem encountered by most Indonesian people. The world air quality report published in 2018 by IQAir listed Indonesia to be in the 11th rank as one of the countries with the worst air quality in the world as indicated by the average pollution concentration of 42 (μg/m3). A straightforward solution to overcome this problem is to reduce the harmful gas emission content released into the air by an internal combustion engine. This research then aimed to optimise the performance of CAT 3401 internal combustion diesel engine using two sequential stages. The first stage was Backpropagation Neural Network (BPNN) method. Then, the effect of various input parameters (compression ratio, start of injection angle, fuel injection pressure, and exhaust gas recirculation) on the diesel engine performance was examined in the first stage. The resulting analytical modelling produced by the Backpropagation Neural Network (BPNN) method was further used to optimise the diesel engine's performance. Next, in the second stage, two well-known metaheuristic methods, namely Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), were used to achieve the highest peak pressure and minimal NOx gas emission and soot content.