A Prediction Model of Blast Furnace Slag Viscosity Based on Principal Component Analysis and K-Nearest Neighbor Regressi
- PDF / 1,720,084 Bytes
- 9 Pages / 593.972 x 792 pts Page_size
- 13 Downloads / 193 Views
https://doi.org/10.1007/s11837-020-04360-9 Ó 2020 The Minerals, Metals & Materials Society
MACHINE LEARNING APPLICATIONS IN ADVANCED MANUFACTURING PROCESSES
A Prediction Model of Blast Furnace Slag Viscosity Based on Principal Component Analysis and K-Nearest Neighbor Regression DEWEN JIANG,1 JIANLIANG ZHANG,1,2 ZHENYANG WANG CHENFAN FENG,3 KEXIN JIAO,1 and RENZE XU1
,1,4
1.—School of Metallurgical and Ecological Engineering, University of Science and Technology Beijing, Beijing 100083, China. 2.—School of Chemical Engineering, The University of Queensland, St Lucia, QLD 4072, Australia. 3.—School of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China. 4.—e-mail: [email protected]
Viscosity is considered to be a significant indicator of the metallurgical property of blast furnace (BF) slag. However, a BF is a complicated black box so that the measurement of the viscosity has a large hysteresis. A prediction model for the viscosity based on machine learning, principal component analysis (PCA) and k-nearest neighbor (KNN) regression is presented in this article. First, the main influencing factors of the viscosity are analyzed and selected as the input of the model. Then, the two datasets are preprocessed by data normalization. In addition, the sample characteristics of the data are processed to be statistically irrelevant by PCA. Based on the above, the two datasets are applied to the PCA–KNN model and the support vector regression model, respectively. The results show that the predicted result using the PCA–KNN model is more accurate and reaching 99%.
INTRODUCTION For a long time, many companies have used blast furnaces (BF) to produce iron. A BF is one of the most complex industrial reactors. Its parameters and indicators of the internal state and product quality cannot be measured and acquired in time due to the limitations of its internal structure, reaction complexity, extreme temperature, and detecting cost. In the field of metallurgy, the solutions related to the prediction problems of parameters, such as the status of the BF and the quality of the products, can be divided into three categories: first, a geometric model based on conventional solution theory and traditional metallurgical theory (kinetics, thermodynamics, mass transfer,and chemical reaction). For example, a simple viscosity prediction model based on the Vogel–Fulcher–Tammann equation was proposed by Lei Gan;1 second, a computational simulation method of simulation software such as
(Received March 9, 2020; accepted August 26, 2020)
ANSYS. For instance, a computational fluid dynamics numerical simulation model of the cooling stave of a BF based on a 1-dimensional heat transfer mechanism was established. The model can reduce the influence of frequent forming and shedding of the slag crusts on the BF by analyzing the effects of the cooling stave material, the volume distribution of the cooling water pipes, and the nano-polymer in the cooling stave;2 and third, a regression model on the basis of data-dri
Data Loading...
