基于改进多目标遗传算法的连铸二冷过程优化

采用一种改进的多目标遗传算法对二冷工艺进行优化.改进的多目标遗传算法应用概率法选取选择算子，根据适应度值来动态计算交叉和变异概率，能够得到更好的全局最优解，提高算法精度和整体性能.在基于凝固传热模型的二冷优化过程中，采用变间距差分法离散求解传热方程，对比粒子群算法、多目标遗传算法，改进的多目标遗传算法搜索效率高，得到的价值函数最小.在实际生产中，采用优化后的二冷工艺，使得总用水量减少约10%，提高了铸坯质量，达到了节能降耗的要求.

Optimization of Continuous Casting Secondary Cooling Based on An Enhanced Multi-objective Genetic Algorithm

An enhanced multi-objective genetic algorithm is adopted to optimize secondary cooling process， which uses the probability method to select the operator and calculates crossover and mutation probability dynamically according to the fitness value. A better global optimal solution is achieved and the algorithm precision and overall performance improve greatly. In the secondary cooling optimization process， the model based on solidification heat transfer is solved by the variable spacing difference method. Compared to particle swarm algorithm and the traditional multi-objective genetic algorithm， the enhanced multi-objective genetic algorithm has the highest search efficiency and the minimum value function. In industrial applications， the optimized secondary cooling process can reduce the total consumption of water by 10% and improve the quality of casting billet， which meet the requirements of energy saving and consumption reduction.