论文部分内容阅读
为改善粒子群优化算法的寻优性能,提出了一种新的算法——混沌粒子群算法。该算法将混沌搜索机制引入到粒子群算法中来增加粒子的多样性,同时采用增加粒子交互性策略及先增后减的惯性权重因子模型来设置惯性权重因子,改善了递减策略中存在的缺陷。将改进后的算法与PID型单神经元相结合,并将其用于热连轧活套解耦控制系统。仿真试验表明:该算法较好地克服了粒子群算法易早熟和陷入局部最优的缺点,为解决活套系统高度张力耦合问题提供了一种新的有效途径。
In order to improve the optimization performance of particle swarm optimization algorithm, a new algorithm - chaos particle swarm optimization algorithm is proposed. The algorithm introduced the chaos search mechanism into particle swarm optimization algorithm to increase the diversity of particles. At the same time, the inertia weighting factor was set by increasing the particle interactive strategy and the inertia weighting factor model firstly increasing and then decreasing, which improved the defects in the decreasing strategy . The improved algorithm is combined with a PID single neuron and used in hot rolling looper decoupling control system. The simulation results show that this algorithm overcomes the shortcoming that PSO is easy to get premature and falls into local optimum, which provides a new effective way to solve the coupling problem of the high tension of the looper system.