【摘要】 提出了一种改进的粒子群算法,很好地解决了基本粒子群算法中易陷入局部最优的缺点。通过比较和分析几个标准测试函数的计算结果,改进的粒子群算法的优良性得到充分的证明。改进的粒子群算法被用于优化神经网络的结构和参数,结果表明:不但网络的结构得到控制,而且泛化性能有了较大的提高。同时,算法在优化神经网络上的有效性也在4-CBA含量的软测量建模中得到了很好的证实。更多还原

【Abstract】 An improved PSO(particle swarm optimization) algorithm is presented which well addresses slow convergence speed and low calculation precision in the basic PSO algorithm.By comparing and analyzing the results of several standard test functions,the excellent performance of PSO is proved.Then,the improved PSO is applied to optimization of the structure and parameters in NN(neural network).The availability of algorithm in optimizing neural network is proved by applying NN in soft sensor modeling of 4-CBA measurement.更多还原