基于遗传算法的板坯连铸二冷配水优化方法

Using a genetic algorithm to optimize secondary cooling water distribution in slab casting

为提高板坯高效连铸二冷水的动态控制水平,在满足生产实时性要求的传热模型基础上,引入遗传算法对二冷区各段水量进行编码,并根据板坯连铸配水所遵循的冶金准则确定多目标优化的适应度函数,该遗传算法与冶金准则、传热模型集成的优化配水方法避免了经验方法的适应性不足,改进了传统优化方法在解决多目标优化非线性求解时搜索效率低下的问题。从攀钢炼钢厂板坯连铸过程的仿真计算和现场测试结果可以看出,优化后的配水方案较优化前相比,水量可节约2%,同时配水沿着拉坯方向水量逐渐递减,符合铸坯质量控制的要求。

A genetic algorithm was used for coding the volume of cooling water in the secondary cooling zone based on the heat transfer model in real-time production. This was done to improve the dynamic control of the secondary cooling water in high-efficiency continuous casting. The fitness function of multi-objective optimization in the algorithm is in accordance with the distribution of metallurgical criteria. The genetic algorithm was integrated with the metallurgical criteria and the heat transferring model to optimize the water distribution. These steps increase the distribution adaptability and improve its efficiency compared to the traditional optimization methods of solving multi-objective optimization and other non-linear problems. Simulation using the process data of the No. 2 slab caster in the Steelmaking Plant of Panzhihua Iron and Steel and on-site testing were carried out. The results show that the optimized distribution saves 2% of water than without optimization, while water distribution along the slab to the water gradually decreases in accordance with requirements for slab quality control.