3
RUDN University professors increased the “lifetime” of steel parts using a neural network

RUDN University professors increased the “lifetime” of steel parts using a neural network

Scientists from RUDN University, Italy, Canada and Turkey, using an artificial neural network, were able to predict the stability of steel parts and find the optimal protective coating.

Repeated stress on metal parts causes “fatigue failure.” Each stress leads to microcracks that accumulate over time. Larger damage appears, and finally the part fails. Fatigue failure inevitably occurs in almost all mechanisms, this applies to all areas of industry, so technologists and scientists are looking for ways to strengthen the metal using various coatings and processing methods. RUDN University professors, together with colleagues from Italy, Canada and Turkey, built an artificial neural network that is able to predict the life of a part made of AISI 1045 steel, which makes up half of the mechanical engineering products, and select the optimal coating.

“Most machine components in the marine, oil and gas, and wind power industries are subject to repeated applied loads that cause fatigue failure. Since the phenomenon of fatigue failure is very sensitive to various parameters, including material, load, temperature, humidity, vibration, and so on, it is convenient to use neural networks for its analysis,” Reza Kashi Zadeh Kazem, professor of the Department of Transport of RUDN University.

Engineers have created a neural network that can estimate the “lifetime” of AISI 1045 carbon steel with different types of coatings under repeated loads. Nickel, hardened chrome and zinc were used as protective coatings in the model. RUDN University researchers have achieved 99% accuracy in neural network predictions. Moreover, the authors were able to select the optimal protective coating — a layer of nickel or zinc 10–15 micrometers thick. Hardened chromium has been shown to reduce the steel’s resistance to fatigue failure.

First, RUDN scientists conducted a series of experiments with real steel parts. 23% of the obtained data was used to train the neural network, and the rest was used to test the resulting predictions. The scientists tested several neural networks, with different numbers of internal layers and neurons in each layer.

“We investigated the effect of various traditional industrial coatings, including nickel, chromium and zinc, which are commonly used to improve corrosion resistance, on the fatigue life of AISI 1045 carbon steel. The experimental results showed that nickel and hot-dip galvanized coatings with a thickness of 13 microns improved fatigue life. On the contrary, hardened chromium reduces the fatigue life of AISI 1045 steel,” Igor Danilov, Doctor of Technical Sciences, Director of the Department of Transport of the RUDN University.

The results were published in the journal JMSE.

Scientific Conferences View all
16 Oct
The collection consists of two volumes and includes biographical information about Russian demographers and their scientific research. The first volume is devoted to the research of the Pre-Revolutionary period, the second to the works of the Soviet era and the present.
76
30 Jan 2018
The conference on international arbitration, where law students from European universities simulate court proceedings and alternately defend the interests of the respondent and the orator.
1292
Similar newsletter View all
16 Oct
Green Diplomacy Center opened in RUDN

A Center for Green Diplomacy was created based on the RUDN Institute of Environmental Engineering. Among the goals is the integration of the results of scientific and practical activities into the development of international relations in the environmental sphere. The center's specialists will also accompany the corporate sector in solving various environmental problems.

92
19 Apr
A huge pizza and a jug of water, why should 5G networks be sliced? The winners of RUDN science competition explain

RUDN summarized the results of the scientific competition "Project Start: work of the science club ". Students of the Faculty of Physics, Mathematics and Natural Sciences have created a project for a managed queuing system using a neural network to redistribute resources between 5G segments. How to increase flexibility, make the network fast and inexpensive and reach more users — tell Gebrial Ibram Esam Zekri ("Fundamental Computer Science and Information Technology", Master's degree, II course) and Ksenia Leontieva ("Applied Mathematics and Computer Science", Master's degree, I course).

166
19 Apr
Lyricists and physicists are now on equal terms: the first humanitarian laboratory opened in RUDN

What is your first association with the word “laboratory”? Flasks and beakers? Microscopes and centrifuges? Yes, many of us would answer the same way.

210
Similar newsletter View all