为改善热轧厚板的强度和屈强比,结合粒子群优化算法,利用神经元网络建立了粗轧开轧温度、中间坯厚度、终轧温度、终冷温度及冷却速率等生产工艺参数与钢板强度的关系模型,并进行了优化。优化结果与实验室热轧实验及工业试生产结果的对比表明,本模型能有效地优化厚板生产过程的工艺参数,从而为最优工艺或柔性化生产工艺的设计提供依据。
A model for processing and properties optimization based on artificial neural network and PSO (Particle Swarm Optimization) algorithm was proposed. In order to obtain the desired strength and lower yield/ strength ratio, the relationship of plate strength and parameters, such as rough rolling temperature, temperature-holding thickness, finish rolling temperature, finish cooling temperature and cooling rate were establised and optimized. The experimental results and industrial trials showed that the optimized results were in good agreements with the experimental ones, The model can be applied to the optimal design for processing parameters in plate rolling.