论文部分内容阅读
针对混沌粒子群运算初期的无目的性、固定的控制参量在运算后期不利于跳出局部最优等进行了分析和改进,利用混沌运动的随机性、遍历性和规律性特点对粒子群体中的最优粒子进行混沌寻优,根据给水管网管径选取的离散化特殊性,对混沌粒子群的混沌参量μ进行公式化规定,提出一种改进型混沌粒子群算法(HMCPSO),提高粒子群算法摆脱局部极优的能力。通过引入混沌算法启动机制,有效提高种群初期的收敛能力,通过引入粒子群位置的历史数据判断机制,减少多余的混沌运算,有效缩短算法运行时间。将本改进算法应用于给水管网的模型中,仿真效果表明文中提出的改进算法与PSO和CPSO算法相比,找到的结果更优且稳定性较好,运算时间得到有效减少。
In the early stage of chaos particle swarm optimization, the fixed control parameters are not conducive to jump out of the local optimum after the operation is analyzed and improved. Based on the randomness, ergodicity and regularity of chaotic motion, According to the particularity of the discretization of pipe diameter selection of water supply network, the chaos parameter μ of chaotic particle swarm is formulated. An improved chaos particle swarm optimization algorithm (HMCPSO) is proposed to improve the performance of particle swarm optimization Excellent ability. By introducing the chaos algorithm start-up mechanism, the initial convergence ability of the population can be effectively improved. By introducing the historical data of the particle swarm to determine the mechanism, the redundant chaos operation can be reduced and the algorithm running time can be shortened effectively. The improved algorithm is applied to the water supply network model. The simulation results show that the improved algorithm proposed in this paper is better than PSO and CPSO algorithm, and the result is better and the stability is better and the computing time is reduced effectively.