Application of neural networks to forecast changes in the technical condition of critical production facilities. (July 2021)

• Record Type: Journal Article
• Authors: Yemelyanov, Vitaliy; Chernyi, Sergei; Yemelyanova, Nataliya; Varadarajan, Vijayakumar
• Is Part Of: Computers & electrical engineering. Volume 93(2021)
• Publication Date: 2021-07
• Subjects: Production facilities -- Neural networks -- Diagnostic -- Forecasting methods -- Parameter; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107225
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: The relevance of research in the field of diagnostics and forecasting the technical condition of critical production facilities at metallurgical works is substantiated. An approach to the analysis of time series of the main parameters of the critical production facilities at the metallurgical works based on a neural network forecasting of the state of diagnostic objects is proposed. The neural network structure for predicting changes in the basic parameters of torpedo ladle car in the metallurgical industry is described and justified. The results of predicting the torpedo ladle cars lining condition by classical methods and by means of a neural network are compared. This comparison has shown a higher forecasting efficiency using the neural network method.