The carbon footprint from the iron, steel and other metal sectors has become a problem both environmentally and economically. The purpose of this report is to propose a concept of an electrified reheat furnace for the steel industry in the making of sheet metal. The aim is to reduce the environmental impact from the steel industry. The approach in this report has been to analyse relevant facts to propose a fully electrified concept. The concept is divided into two sections. The first section of the concept consists of a preheating furnace with the purpose to heat the slabs to 850 °C before it enters the second section. The preheating furnace contains 1447 – 2412 MoSi2 heating elements due to considering different efficiencies. The second section consists of 13 induction heating modules heating the slabs to a homogenous temperature of 1250 °C. By applying electrical heating in a walking beam furnace approximately 100 000 tonne carbon dioxide can be reduced annually. In conclusion, the proposed concept could be a feasible solution in order to avoid carbon emission and obtain the same production rate as the existing reheating furnaces. However, it is suggested that further investigations and analysis are performed regarding this concept to verify the total efficiency of the reheating furnace and to theoretically determine the required power input / Koldioxidutsläppen från järn, stål och andra metallindustrier har blivit ett problem både urmiljö och ekonomisk synpunkt. Syftet med denna rapport är att föreslå ett koncept av en heltelektrifierad uppvärmningsugn för stålindustrin i processen för att skapa plåt. Målet meddenna studie är att reducera stålindustrins påverkan på växthuseffekten. Metoden i denna rapport har varit att analysera relevant fakta för att sedan kunna föreslå ettkoncept av en helt elektrifierad ugn. Det föreslagna konceptet är uppdelad i två delar. Denförsta delen består av en förvärmningsugn med målet att värma stålet till 850 °C innan ståletgår in i den andra delen. Förvärmningsugnen består av 1447 – 2412 stycken MoSi2värmeelement med hänsyn till ugnens verkningsgrad. Den andra delen består utav 13 styckeninduktionsvärmemoduler som värmen stålet till en homogentemperatur på 1250 °C. Genomatt använda elektricitet för att värma ugnen minskar koldioxidutsläppen med 66 kg per tontillverkas stål. Sammanfattningsvis, det föreslagna konceptet kan vara en möjlig lösning för att minskakoldioxidutsläpp och samtidigt bibehålla samma produktionshastighet som existerandeuppvärmningsugnar. Däremot är det förslaget att vidare studier och analyser görs påkonceptet för att verifiera den totala verkningsgraden av ugnen och för att bestämma denexakta energiförbrukningen.

Surface defects in steel slabs during continuous casting pose significant challengesfor quality control and product integrity in the steel industry. Predicting and classifyingthese defects accurately is crucial for ensuring product quality and minimizing productionlosses. This thesis investigates the effectiveness of machine learning models in predictingsurface defects of varying severity levels (ordinal classes) during the primary coolingstage of continuous casting. The study evaluates four machine learning algorithms,namely, XGBoost (main and baseline models), Decision Tree, and One-vs.-Rest SupportVector Machine (O-SVM), all trained with imbalanced defect class data. Model evaluationis conducted using a set of performance metrics, including precision, recall, F1-score,accuracy, macro-averaged Mean Absolute Error (MAE), Receiver Operating Characteristic(ROC) curves, Weighted Kappa and Ordinal Classification Index (OCI). Results indicatethat the XGBoost main model demonstrates robust performance across most evaluationmetrics, with high accuracy, precision, recall, and F1-score. Furthermore, incorporatingtemperature data from the primary cooling process inside the mold significantly enhancesthe predictive capabilities of machine learning models for defect prediction in continuouscasting. Key process parameters associated with defect formation, such as tundish temperature,casting speed, stopper rod argon pressure, and submerged entry nozzle (SEN) argonflow, are identified as significant contributors to defect severity. Feature importance andSHAP (SHapley Additive exPlanations) analysis reveal insights into the relationship betweenprocess variables and defect formation. Challenges and trade-offs, including modelcomplexity, interpretability, and computational efficiency, are discussed. Future researchdirections include further optimization and refinement of machine learning models andcollaboration with industry stakeholders to develop tailored solutions for defect predictionand quality control in continuous casting processes.