基于混沌粒子群的铝热连轧多目标轧制规程优化

Optimization of multi-objective rolling schedules for hot rolling aluminum mill based on chaotic particle swarm algorithm

针对铝热连轧轧制规程制定过程中的多目标问题,提出一种基于混沌粒子群算法的多目标轧制规程优化方法。选取预防打滑和等功率裕度为多目标优化函数;为了提高粒子群算法的收敛性和分布性,提出一种基于混沌序列的动态加权法选择全局最优粒子,并改进了拥挤距离计算方法;提出一种基于模糊偏好的选择策略用以从最优解集中选择最终采用的轧制规程。基于该方法对某铝热连精轧机组轧制规程进行了优化,验证了该方法的有效性。

For the multi-objective problem in the rolling schedules for hot rolling aluminum mill,an optimization method was proposed based on chaotic particle swarm for the multi-objective rolling schedule.Firstly,both preventing slippage and equal margin were chosen as the multi-objective optimizing function;Then,to improve the convergence and the distribution of the particle swarm optimization algorithm,a dynamic weighting method was proposed based on chaotic sequence to select the global optimum particle,also a calculation method of crowding distance was improved;Finally,a selection strategy was proposed based on the fuzzy preference to choose the finally adopted rolling schedule from the optimal solution set.The method was applied to the rolling schedule optimization of an aluminum hot strip finishing mill group and the result shows the effectiveness.