Prediction model for mechanical properties of hot-rolled strips by deep learning
- PDF / 1,016,088 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 26 Downloads / 253 Views
ORIGINAL PAPER
Prediction model for mechanical properties of hot‑rolled strips by deep learning Wei‑gang Li1 · Lu Xie1 · Yun‑tao Zhao1 · Zi‑xiang Li2 · Wen‑bo Wang3 Received: 23 July 2019 / Revised: 6 September 2019 / Accepted: 11 September 2019 © China Iron and Steel Research Institute Group 2020
Abstract The prediction of the mechanical properties of hot-rolled strips is a very complex, highly dimensional and nonlinear problem, and the published models might lack reliability, practicability and generalization. Thus, a new model was proposed for predicting the mechanical properties of hot-rolled strips by deep learning. First, the one-dimensional numerical data were transformed into two-dimensional data for expressing the complex interaction between the influencing factors. Subsequently, a new convolutional network was proposed to establish the prediction model of tensile strength of hot-rolled strips, and an improved inception module was introduced into this network to abstract features from different scales. Many comparative experiments were carried out to find the optimal network structure and its hyperparameters. Finally, the prediction experiments were carried out on different models to evaluate the performance of the new convolutional network, which includes the stepwise regression, ridge regression, support vector machine, random forest, shallow neural network, Bayesian neural network, deep feed-forward network and improved LeNet-5 convolutional neural network. The results show that the proposed convolutional network has better prediction accuracy of the mechanical properties of hot-rolled strips compared with other models. Keywords Deep learning · Convolutional neural network · Mechanical property · Hot-rolled strip
1 Introduction Steels are characterized by stable quality, low price, abundant resources and high recovery rate. Compared with other materials, steel is still the most widely used material in many fields [1], such as construction, automobiles, ships and railways. The mechanical properties of steel strips are important performance parameters related to the quality of steel products. The accurate prediction of the mechanical
* Wei‑gang Li [email protected] 1
Engineering Research Center of Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, Hubei, China
2
Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, Hubei, China
3
Hubei Province Key Laboratory of Systems Science in Metallurgical Process, Wuhan University of Science and Technology, Wuhan 430081, Hubei, China
properties of hot-rolled strips can help reduce the strip sampling frequency, control the mechanical properties of the products, optimize the components of steel and design new products [2]. The prediction of the mechanical properties of hot-rolled strips has always been a difficult problem, which has greatly affected the further
Data Loading...
