基于粒子群优化算法的船舶柴油机故障诊断

Marine Diesel Fault Diagnosis Based on Particle Swarm Optimization

为了提高模糊神经网络收敛速度,克服容易陷入局部极值的不足,提出利用改进的动态加速常数协同惯性权重的WCPSO算法对网络参数进行优化。该算法通过对标准粒子群算法WPSO的改进,实现动态加速常数随进化代数线性变化,使被优化的网络收敛速度加快,不易陷入局部极值。将其应用于船舶柴油机模糊神经网络故障诊断模型中,仿真结果表明经过优化的故障诊断模型更为准确,提高了诊断速度。

To improve the convergence rate of neural networks and overcome the shortcoming of easily falling into local extreme,the coordination of dynamic acceleration constant and inertia weight called WCPSO algorithm is proposed to optimize network parameters.This algorithm improves the WPSO to realize linear evolution of the dynamic acceleration constant.WCPSO was applied to marine diesel fault diagnosis model,and the simulation results show that the optimized diagnosis model is more prepared and the diagnosis speed is faster.