改进的PSO算法在重油热解模型参数估计中的应用
Parameter Estimation of Heavy Oil Thermal Cracking Model Using an Improved Particle Swarm Algorithm
-
摘要: 针对传统的粒子群算法(PSO)在解决复杂的优化问题时易陷入局部最优这一情况,提出了一种改进的粒子群算法(EPSO),该算法在传统的粒子群算法陷入局部最优的情况下引入了单个粒子的"Hooke-Jeeves模式搜索"操作和粒子之间的"启发式交叉"操作。仿真结果表明:EPSO算法的全局搜索性能和收敛速度比传统的PSO算法有明显的提高。采用EPSO算法进行非线性参数估计所得到的重油热解模型,其预报的平均相对误差比传统的PSO算法得到的模型提高了11.98%,比遗传算法(GA)得到的模型提高了38.76%。Abstract: The traditional particle swarm optimization(PSO) algorithm easily runs into local optimi-(zation) point when it is used to solve complex optimi-(zation) problems.An improved particle swarm optimization(EPSO) algorithm is proposed by introducing Hooke-Jeeves pattern search method and heuristic across method to the basic PSO algorithm.The simulation results show EPSO algorithm has greater efficiency and better performance.The EPSO method is applied successfully to nonlinear parameter estimation of heavy oil t...