Intelligent Optimization Based on a Virtual Marine Diesel Engine Using GA-ICSO Hybrid Algorithm

Considering the trade-off relationship between brake specific fuel consumption (BSFC), combustion noise (CN) and NOx emission, it is a difficult task to optimize them simultaneously in marine diesel engine. In order overcome this problem, novel genetic algorithm improved chicken swarm optimization (GA-ICSO) hybrid was proposed, where enhanced Levy flight adaptive self-learning factor were introduced algorithm. Computational comparisons GA-ICSO other effective algorithms performed using four standard test functions, validating improvements both accuracy stability for GA-ICSO. Furthermore, predictive engine model based on phenomenological approach developed validated. This coupled proposed of process, five control parameters selected as design variables, including injection timing (IT), intake cam phasing (ICP), valve closing (IVC), temperature pressure. Results show that, lower objective value can be obtained by than widely used all operating conditions. Besides, comparing results optimal generations baselines, could found under condition 50%, 75% 100%load, CN reduced 10.7%, 4.9% 3.9%, decreased 15%, 31% 33%, BSFC suppressed 10.8%, 13.3% 9.5%, respectively. Finally, heat release rates, spectrums, cylinder pressures temperatures employed discuss different working