论文部分内容阅读
为了克服粒子群优化算法(Particle Swarm Optimization,PSO)早熟收敛,利用混沌变异机制和粒子群算法融合的基础上提出一种改进的粒子群优化算法。该算法改进了粒子自身探索行为,以保证全局搜索的有效性,同时为了让种群保持多样性和跳出局部最优解引入混沌变异机制,提高了算法的寻优性能。将改进粒子群算法训练的神经网络应用于热连轧厚度控制,仿真结果表明与遗传算法及粒子群算法相比较,该算法在提高误差精度的同时可加快训练收敛的速度,提高了热连轧厚度控制精度。
In order to overcome the premature convergence of Particle Swarm Optimization (PSO), an improved Particle Swarm Optimization (PSO) algorithm is proposed based on the fusion of chaotic mutation mechanism and particle swarm optimization algorithm. The algorithm improves the particle self-exploration behavior to ensure the validity of the global search, and introduces the chaotic mutation mechanism to keep the population diversity and jump out of the local optimal solution, which improves the performance of the algorithm. The neural network trained by improved particle swarm optimization algorithm is applied to the thickness control of hot strip mill. Simulation results show that compared with genetic algorithm and particle swarm optimization algorithm, this algorithm can improve the accuracy of error and speed up the convergence of training, Thickness control accuracy.