CAJ | 학술논문

针对粒子群算法收敛速度慢和易陷入局部最优的问题，提出了基于惯性权重对数递减的粒子群算法，并引入对数调整因子，对数调整因子的不同取值保证了算法搜索成功率。选取八种典型函数分别进行给定迭代次数和给定精度的仿真实验，并与标准PSO算法、惯性权重线性递减PSO算法、惯性权重高斯函数递减PSO算法进行比较。测试结果表明，该策略可以简便高效地提高算法的全局收敛性和收敛速度，并且具有较好的稳定性。求解大多数优化问题时，即使不引入对数调整因子新算法就可以获得较好的效果。
침대입자군산법수렴속도만화역함입국부최우적문제，제출료기우관성권중대수체감적입자군산법，병인입대수조정인자，대수조정인자적불동취치보증료산법수색성공솔。선취팔충전형함수분별진행급정질대차수화급정정도적방진실험，병여표준PSO산법、관성권중선성체감PSO산법、관성권중고사함수체감PSO산법진행비교。측시결과표명，해책략가이간편고효지제고산법적전국수렴성화수렴속도，병차구유교호적은정성。구해대다수우화문제시，즉사불인입대수조정인자신산법취가이획득교호적효과。
In the light of the problems of slow convergence rate and falling into the local optimization easily for the Particle Swarm Optimization(PSO)algorithm, the algorithm which based on the inertia weight logarithmic decreasing is pro-posed and the logarithmic adjustment factor is introduced. Changes of logarithmic adjustment factor ensure the success rate. The simulation experiment for eight kinds of typical function in the given number of iterations and precision and the comparison with standard, inertia weight linearly decreasing PSO algorithm and inertia weight decreasing based on Gaussian function are made. The test results show that, the strategy can improve the algorithm’s global convergence and conver-gence speed easily and efficiently and has a better stability. The better performances can be obtained even without intro-ducing the logarithmic adjustment factor while solving the most optimization problems.