基于改进粒子群-BP神经网络算法的PSC选船模型

PSC ship-selecting model based on improved particle swarm and BP neural network algorithms

以2009/16/EC巴黎备忘录目标船选船机制NIR为研究对象,提出基于改进的粒子群-BP神经网络算法的PSC新选船模型.该算法可针对BP神经网络收敛速度慢、易陷入局部极小值等问题,根据群体早熟收敛度及个体适应值调整惯性权重,更新粒子速度和位置.将改进的粒子群算法训练BP网络用于PSC选船,实验结果表明,较常规BP网络,改进的自适应粒子群优化神经网络算法能够有效改善神经网络的训练效率,提高训练精度.

This paper researched Paris MOU NIR（New Inspection Regime）of latest PSC rules of 2009/16/EC,and put forward an algorithm of PSC ship-selecting model based on improved particle swarm optimization（PSO） and BP neural network algorithm.The algorithm can adaptively adjust inertia weight and update speed and position according to premature convergence degree and individual fitness value and aiming to the problems of BP,such as slower convergence speed and easy to fall into local minimum value.The improved PSO algorithm was used to train BP network,and was applied to PSC ship-selecting.Test results show that this algorithm improves the performance on speed of convergence and precision of convergence.