Online prediction of mechanical properties of hot rolled steel plate using machine learning

TLDR

In industrial steel plate production, process parameters and steel grade composition significantly influence microstructure and mechanical properties, yet determining their exact relationship remains challenging. The study aimed to develop a deep learning model to predict yield strength, ultimate tensile strength, elongation, and impact energy of industrial steel plates from process parameters and raw steel composition, and deploy it online in a real plant. An optimal deep neural network with 27 inputs, two hidden layers of 200 nodes each, and four outputs was trained using Adam optimizer and Z‑preprocessing, achieving R² = 0.907, while local linear models were also constructed to interpret parameter–property relationships. The tuned DNN achieved RMSE of 21.06 MPa for YS, 16.67 MPa for UTS, 2.36 % for EL, and 39.33 J for Akv, with RPEs of 4.7 %, 2.9 %, 7.7 %, and 16.2 %, outperforming classic machine‑learning algorithms, and was successfully deployed for online monitoring and control of steel mechanical properties.

Abstract

In industrial steel plate production, process parameters and steel grade composition significantly influence the microstructure and mechanical properties of the steel produced. But determining the exact relationship between process parameters and mechanical properties is a challenging process. This work aimed to devise a deep learning model, to predict mechanical properties of industrial steel plate including yield strength (YS), ultimate tensile strength (UTS), elongation (EL), and impact energy (Akv); based on the process parameters as well as composition of raw steel, and apply it online to a real steel manufacturing plant. An optimal deep neural network (DNN) model was formulated with 27 inputs parameters, 2 hidden layers each having 200 nodes and 4 output parameters (27 × 200 × 200 × 4) with an initial learning rate 0.0001, using Adam optimizer and subjected to Z pre-processing method, to yield an accurate model with R2 = 0.907. The tuned DNN model, had a root mean square error of 21.06 MPa, 16.67 MPa, 2.36%, and 39.33 J, and root mean square percentage error of 4.7%, 2.9%, 7.7%, and 16.2%, for YS, UTS, EL and Akv respectively. Through comparative analysis, it was found that the accuracy of DNN model was higher than other classic machine learning algorithms. To interpret the model assumptions and findings, several local linear models were devised and analyzed to establish the link between process parameters and mechanical properties. Finally the tuned DNN model was deployed in the real-steel plant for online monitoring and control of steel mechanical properties, and to guide the production of targeted steel plates with tailored mechanical properties.