改进粒子群算法及其在电力变压器优化设计中的应用

Improved PSO Algorithm and Its Application in Optimal Design of Power Transformer

针对基本粒子群算法易陷入局部最优解的缺陷,本文提出了一种带有惩罚量的改进粒子群算法。用标准测试函数对改进算法做了仿真分析,结果表明改进算法在寻优精度和收敛性能上均有所提高。将改进算法应用于电力变压器SF9-630/10的优化设计中,分析了优化变量和约束条件的选取,建立了带有惩罚函数的优化设计目标函数,给出了改进粒子群算法的具体实施方法。将传统计算数据与优化数据做了对比,证明了该方法的正确性和有效性。

To overcome the disadvantage of being trapped in local optimum in the basic particle swarm optimization （PSO）, an improved particle swarm ＇optimization algorithm with punishment factor （PPSO） is proposed in this paper. The simulation analysis with standard test functions indicates that the PPSO has better optimizing efficiency and accuracy. The PPSO is applied to the optimization design of power transformer SF9-630/10, a target function with penalty functions is founded by analyzing the selection of optimization variables and constraint conditions, specific implementation methods of the PPSO are proposed. The correctness and effectiveness of the proposed method are proved by comparing the PPSO result with that of the conventional method.