Prediction Model of Yield Strength of V-N Steel Hot-rolled Plate Based on Machine Learning Algorithm

Mechanical properties are an essential standard for V-N steel hot-rolled plates used in steel structures such as ship hulls, paint pipelines and offshore platforms. To solve the problems of low production efficiency and low applicability of the traditional physical metallurgy (PM) model, this study proposed an adequate model, namely eXtreme Gradient Boosting based on Bayesian optimization (BO-XGBoost). First, composition-process-yield strength data of V-N steel hot-rolled plate with steel grade Q550D were collected, and K nearest neighbor (KNN), support vector machine (SVR), multi-layer perception (MLP), random forest regression (RFR), gradient boosting regression (GBR) and XGBoost machine learning (ML) models were established using preprocessed data sets. Then, the Bayesian optimization method was used to optimize the hyperparameters of the RFR and XGBoost models with better performance. Therefore, the mechanical properties prediction model was established, and the impact of feature processing and PM parameters on the model was discussed. The results show that the BO-XGBoost model can effectively predict the mechanical properties of high-dimensional industrial big data and has excellent generalization ability (testing set Er = 93.52%, MAE = 13.56 MPa, RMSE = 20.19 MPa), which is suitable for large-scale and industrial production of V-N steel hot-rolled plate.