实船训练系统中柴油机转速的粒子群优化RBF神经网络预测

摘要

针对柴油机是一个具有不确定性因素的强非线性系统，首先将 RBF网络的参数编码成粒子群优化算法中的粒子个体进行优化；然后，利用粒子群算法的全局寻优能力优化 RBF神经网络的关键参数；最后，建立了柴油机转速的预测模型。仿真结果表明：该算法使得柴油机转速的预测速度和精度都得到了提高。%In view of the diesel engine with uncertainty and strong nonlinearity,a model based on par-ticle swarm optimization and radial basis function neural network algorithm is proposed.The central position,the width of the basis function and the network weight in the RBF network are encoded and optimized by the PSO algorithm.Finally the prediction model of diesel engine rotate speed is estab-lished.The results show that the PSO-RBF neural network model is improved in the prediction accu-racy and the convergence speed.