中文摘要：

为了充分发挥钢中析出相的晶内形核细晶作用,以便优化热模拟工艺,对合金钢热模拟试验组织中的析出相进行了分析及预测。研究了合金钢热模拟试验工艺参数,包括化学成分、变形温度、变形量以及保温时间等与析出相粒径、形态与分布之间关系,并建立了相应的映射关系,在此基础上建立了合金钢析出相分析及预测模型。应用L-M算法对该神经网络模型的权值进行了优化,从而克服了神经网络训练速度慢、容易陷入极小局域和全局搜索能力弱等缺点,提高了神经网络的预测精度。通过实例验证表明,改进后的神经网络对合金钢析出相粒径的预测精度达到93%以上,对合金钢析出相形态的预测精度达到90%以上。

英文摘要：

The grain size and shape of precipitated phase in alloyed steel were analyzed and predicted for the purpose of promoting the refinement effect of intercrystalline nucleation adequately and optimizing the thermal simulation technique. The mapping relationship between thermal simulation parameters （ including chemical composition, deformation temperature, degree of deformation and holding time ） and precipitated phase state including its grain size, shape and distribution was studied. The BP neural network prediction model improved by L-M algorithm was established. The shortage of conventional B-P algorithm such as the slow speed of training, easily come to a local minimum and weak of global search was overcome. By the means of the simulation and practice, the prediction precision of improved BP neural network on the grain size of precipitated phase is more than 93% ,and the precision of the shape of precipitated phase is more than 90%.