The study of students from Yekaterinburg was published in the scientific collection of the CASE-IN championship

The Organizing Committee of the International Engineering Championship "CASE-IN" and the Reliable Change Foundation have prepared a collection of articles based on the strongest case solutions of the participants of the championship. The authors include a research team of students from Ural Federal University. In total, the collection, published jointly with Kuzbass State Technical University named after T. F. Gorbachev, includes 21 articles by the strongest participants of the Student League "CASE-IN". Young people from 16 universities reworked the engineering case solutions presented during the championship and submitted them for compilation.

"Over the 13 years of the CASE-IN, our participants have proposed many promising solutions relevant to industrial companies and the country's economy," said Artem Korolev, founder and co—chairman of the organizing committee of the CASE-IN championship. — So that the industry community could get acquainted with bright ideas, and the developments themselves found practical application on production sites, we decided to create this collection. I am sure it will be of interest to both current specialists and company executives, as well as students who plan to link their careers with engineering."

UrFU students Natalia Bushueva and Igor Tetkin have prepared an article on the use of neural network analysis of acoustic emission data to assess the condition of equipment. The paper explores an innovative approach to monitoring the condition of technical equipment in the heat and power industry.

"The article discusses the basics of acoustic emission, the use of neural networks in data analysis, and their training on defect models. The proposed approach can significantly improve the accuracy and speed of defect detection, which, in turn, helps optimize maintenance processes and extend the life of equipment at thermal power plants," the authors of the article say.

This method provides more accurate results, allowing potential problems to be detected and equipment failures to be prevented at earlier stages, according to UrFU students.

"The neural network approach has the ability to adapt to different operating conditions, making it a versatile tool for monitoring and managing maintenance. Further development and integration of the method into industrial processes will provide an opportunity to increase the efficiency of equipment, reduce maintenance costs and improve the overall reliability of technical systems," emphasized UrFU students.

The collection of articles by the participants of the championship will be registered in The Russian Science Citation Index. This means that all authors will receive additional privileges upon admission to master's and postgraduate studies and the opportunity to receive additional scholarships.

You can view the collection of articles at the link. The CASE-IN Organizing Committee will continue to work on the collection and is planning new editions of the publication.

A source