CAJ | 학술논문

针对粒子群优化算法易于陷入局部最优解的不足,提出了改进的粒子群算法,以克服粒子群算法的早熟现象。引入免疫算法中浓度的概念对粒子的更新进行有选择的指导,增强了粒子群算法全局搜索的能力。通过5种典型的标准函数对改进的算法进行测试和比较,验证了改进算法的有效性.
침대입자군우화산법역우함입국부최우해적불족,제출료개진적입자군산법,이극복입자군산법적조숙현상。인입면역산법중농도적개념대입자적경신진행유선택적지도,증강료입자군산법전국수색적능력。통과5충전형적표준함수대개진적산법진행측시화비교,험증료개진산법적유효성.
In order to solve premature convergence to local minimum problem of PSO,a new method is introduced to improve PSO performance on global optimization problem.Through introducing the density from immune algorithm,the particle can update effectively and improve the global search capability for finding the global optimum.A comparison is made with the standard PSO by five benchmark functions.The experimental results illustrate that the proposed algorithm has evident superiorities in search precision and convergence speed.