RUDN Professors Increase the Lifetime of Steel Parts by using Neural Network

RUDN Professors Increase the Lifetime of Steel Parts by using Neural Network

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

Repetitive loads on metal parts cause fatigue failure. Each loading cycle leads to cracks that grows 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, engineers and scientists are looking for different ways to strengthen the metal using various coated and processing methods. RUDN professors and their colleagues from Canada, Italy, and Turkey create an artificial neural network that is able to predict the lifetime of a component made of AISI 1045 steel and choose the optimal coating and its thickness.

“Most machine components in the offshore oil and gas, and the offshore wind energy industries are affected by the repeated applied loadings that make fatigue failure. Since the destruction fatigue phenomenon is very sensitive to various parameters, including material, load, temperature, humidity, vibration, and so on, it is appropriate to use neural networks for its analysis”, said Reza Kashy Zadeh Kazem, Professor, Department of Transport, RUDN University.

Scholars have created a neural network that is able to estimate the lifetime of carbon steel AISI 1045 with different types of coatings under the influence of cyclic loadings. They used nickel, hardened chromium, and galvanization as protective coatings in the model. RUDN researchers have achieved 99% accuracy of neural network predictions. Moreover, the authors were able to choose the optimal protective coating — a 10-15 micrometers layer of nickel or zinc. Also, hardened chromium, as it turned out, reduces the fatigue lifetime of steel.

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

“We investigated the impact of various traditional industrial coatings, including nickel, chromium and zinc, which are commonly used to improve corrosion resistance, on the fatigue longevity of AISI 1045 carbon steel. The results of the experiments showed that coatings of nickel and galvanization with a thickness of 13 μm increase fatigue durability. On the contrary, hardened chromium reduces the fatigue durability of AISI 1045 steel”, said Igor Danilov, Doctor of Technical Sciences, Director of the Department of Transport of RUDN University.

The results are published in JMSE.

News
All news
Science
23 Oct
RUDN University Space Week 2024: Outcomes

On October 7–10, 2024 RUDN University Space Week traditionally took place. This event was dedicated to the World Space Week, which is celebrated annually in accordance with the UN General Assembly Resolution 54/68 (December 6, 1999) from October 4 to 10 to commemorate the launch of the first artificial satellite Sputnik-1 on October 4, 1957, and the signing of the Outer Space Treaty on October 10, 1967 – the fundamental international treaty in the field of international space law.

Science
18 Jan
RUDN University agronomist found wheat genetically resistant to fungus

A RUDN agrotechnologist has identified wheat genotypes that are resistant to a dangerous fungal pathogen that infects plants even before the snow melts and reduces yields.

Science
10 Jan
RUDN Engineers Have Calculated the Parameters of the Heat Rejection System for a Lunar Power Plant

RUDN University engineers have calculated the parameters of a system that can prevent lunar power plants from overheating. These developments will be needed when planning for long-term lunar missions and colonizing the satellite.