Method of raw materials selection for production of the MgO‐C bricks of comparable properties using PCA and K‐medoids

Abstract

MgO‐C refractories are zonally installed in most of the key heat devices of steel and iron metallurgy with the exposure to various corrosive factors. One of the most significant factors is low‐temperature decarburization resulting in the oxidation of carbon in MgO‐C refractories and loss of its properties. Moreover MgO‐C materials are exposed for direct attack of liquid slag or steel melt which easily infiltrate the porous, decarburized hot face of the bricks. Cost of MgO‐C materials of high quality is important for refractories user. For this reason researches try to develop materials of high quality but with lower cost by substituting fused raw materials with sintered ones or with recycled MgO‐C. In this article method of selecting the raw materials for production of MgO‐C bricks with comparable properties is shown. 20 different variants of MgO‐C materials were prepared with the use of various quality raw materials. Basic properties of the industrially produced MgO‐C bricks were measured. To select recipes with similar quality PCA method and K‐medoids algorithm were applied. To verify the results corrosion resistance of selected MgO‐C materials were tested with the use of induction furnace of medium frequency.This article is protected by copyright. All rights reserved

Current State of Application of Machine Learning for Investigation of MgO-C Refractories: A Review

“…Optimization of MgO-C refractories' composition for improved corrosion resistance was studied with unsupervised learning techniques using clustering algorithms [68]. A total of 20 different variants of MgO-C materials were prepared based on four different main raw materials.…”

“…The described research [68] reveals an extremely important issue in terms of sustainable development, as the production of fused magnesia demands 15 times more energy than the production of sintered aggregates [69]. Even if the corrosion of MgO-C refractories is widely described in the literature [27][28][29][30][31][32][36][37][38][39][70][71][72], scarce information can be found regarding the comparison of high-temperature properties of MgO-C materials based on different magnesia raw materials.…”

“…Although the number of publications on the application of machine learning is rapidly growing, with a 56% increase over the last 2 years, it is still very low when it comes to ML application in the refractory industry. Based on reviewed works [63,64,67,68,73,[77][78][79][81][82][83][84][85], the most commonly used ML algorithm, and simultaneously the one giving the most accurate predictions, is an artificial neural network. One exception is given in [85], which shows boosted trees are the best-fitting algorithm.…”

The Current State of Application of Machine Learning for Development of MgO-C Refractories: A Review

“…Although the number of publications on the application of machine learning is rapidly growing, with a 56% increase over the last 2 years, it is still very low when it comes to ML application in the refractory industry. Based on reviewed works [63,64,67,68,73,[77][78][79][81][82][83][84][85], the most commonly used ML algorithm, and simultaneously the one giving the most accurate predictions, is an artificial neural network. One exception is given in [85], which shows boosted trees are the best-fitting algorithm.…”