Modelling and artificial intelligence technologies in modern approaches to automation of metallurgical industries

Abstract

The article examines modern approaches to the automation of metallurgical production, focusing on increasing productivity, improving product quality, and minimizing costs. The main methodologies and implemented technologies are described, with particular emphasis on modeling and simulation techniques. The study highlights the application of industrial control systems, big data analytics, and artificial intelligence technologies in metallurgical processes. A key aspect of the research is the use of advanced modeling tools, such as digital twins and process simulation software, to optimize various stages of metallurgical production. The paper presents a detailed analysis of casting process modeling using ESI Group ProCast software, demonstrating how virtual experiments can predict temperature distribution, metal flow vectors, and potential defect formation in castings. The research also explores the integration of machine learning models for process control and quality assurance in real-world metallurgical operations. An analysis of the practical application of these technologies is conducted, discussing both the advantages and challenges of implementing such advanced systems in the metallurgical industry. The study concludes by emphasizing the transformative potential of modeling and AI technologies in modernizing traditional metallurgical processes and improving overall operational efficiency.