论文部分内容阅读
低碳贝氏体钢经控轧控冷后,在不同温度下进行回火处理,获得了不同冷却速度、终冷温度和回火温度下的贝氏体室温组织。结合实验数据和神经网络知识,建立了具有BP算法的人工神经网络,训练结束后的神经网络即成为低碳贝氏体钢回火组织预测模型。误差分析表明,该神经网络模型具有较高的精度,可用于指导低碳贝氏体钢热加工工艺的制定。
Low-carbon bainitic steels were controlled by rolling and controlled cooling, and were tempered at different temperatures to obtain bainite room temperature microstructure at different cooling rates, final cooling temperature and tempering temperature. Combined with the experimental data and neural network knowledge, an artificial neural network with BP algorithm is established. After the training, the neural network becomes the tempering tissue prediction model of low carbon bainitic steel. Error analysis shows that the neural network model has high accuracy and can be used to guide the development of low carbon bainitic steel thermal processing technology.