基于改进蚁群算法的焦炉推焦计划编排

Coke Oven Pushing Plan Based on Improved Ant Colony Algorithm

针对实际焦炉推焦作业计划过程中的多炉号乱笺问题,提出一种基于改进蚁群算法的焦炉推焦计划编排方法。首先,给出以恢复推焦串序过程中总惩罚最小为优化目标的焦炉推焦优化调度模型;其次,为了避免蚁群算法进入搜索停滞状态,设置信息素值域来加强算法的搜索能力,并采用具有自适应性的全局更新规则来加快算法后期的收敛速度,进而利用改进的蚁群算法对焦炉优化调度问题进行求解;最后,通过某焦炉厂实际生产数据仿真结果证明,该方法在解决焦炉推焦计划编制问题时具有更好的求解精度和更高的搜索成功率。

In efforts to address the problem that many oven numbers out of sequence in the actual pushing process, a coke oven pushing plan method based on improved ant colony algorithm is put forward. First, a coke oven pushing optimization model is established to achieve the target of least punishment in the process of restoring the normal order; Then, to avoid the stagnation of the search in ant colony algorithm, the paper sets the pheromone domain to strengthen the searching ability of the algorithm, and uses the global adaptive updating rule to accelerate the convergence rate in the late algorithm, in order to use the improved ant colony algorithm to solve the coke oven pushing optimization scheduling problem; Finally, through actual production data, the simulation results show that the proposed algorithm has better accuracy and higher success rate in the coke oven pushing optimization scheduling problem.