论文部分内容阅读
建立了神经网络预测热轧管线钢力学性能的网络模型。在此基础上 ,利用神经网络对热轧管线钢力学性能进行了预测 ,并将预测结果与生产数据进行了比较。同时 ,还利用神经网络对生产工艺参数进行了优化。计算结果表明 ,神经网络预测值与实测值之间接相对误差可以控制在 11.6 %以内 ,这对现场进行力学性能预测和工艺参数优化具有较强的现实意义。
A neural network model for predicting the mechanical properties of hot rolled pipeline steel was established. On this basis, neural network is used to predict the mechanical properties of hot rolled steel, and the predicted results are compared with the production data. At the same time, neural network is also used to optimize the production process parameters. The calculation results show that the relative error between the predicted value of the neural network and the measured value can be controlled within 11.6%, which is of great practical significance to predict the mechanical properties and optimize the process parameters in the field.