Abstract:
The ship’s electricity load changes dynamically with the operating conditions. Compared with the fixed-speed diesel generator set, the variable speed diesel generator set...Show MoreMetadata
Abstract:
The ship’s electricity load changes dynamically with the operating conditions. Compared with the fixed-speed diesel generator set, the variable speed diesel generator set can change the diesel engine speed according to the load condition, so that the diesel engine can operate in a higher efficiency range and achieve the purpose of fuel saving. Taking the lowest fuel consumption rate as the optimization objective, combined with the diesel engine average model of the thermal efficiency neural network model as the basis of fuel consumption rate calculation, the upper and lower limit of diesel speed and power limit line as the limit conditions of speed range, the acquisition of fuel saving speed under different load conditions as an optimization problem. The simulation results show that the diesel engine model has high precision with maximum error 1.62% and can be used for optimization calculation. The characteristics of particle swarm optimization algorithm and Grey Wolf algorithm are analyzed, and a hybrid algorithm (GWPSO) is proposed by combining the advantages of both, and the advantages of the combined algorithm are verified by standard function. The optimization results show that the lower the power load, the more obvious the fuel saving effect; The fuel saving rate can reach more than 30% when the load is 10%, and the comprehensive fuel saving rate can reach 11.9%. The optimized speed can effectively reduce the fuel consumption rate of the variable speed generator set. Grey Wolfparticle swarm optimization algorithm can improve the accuracy of optimization algorithm. The GWPSO algorithm has more balanced global and local optimization characteristics and is more suitable for the optimization of the lowest fuel consumption rate.
Published in: 2023 4th International Conference on Computer Engineering and Intelligent Control (ICCEIC)
Date of Conference: 20-22 October 2023
Date Added to IEEE Xplore: 13 February 2024
ISBN Information: