Repetitive loads on metal parts cause fatigue failure. Each loading cycle leads to cracks that grow 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. Russian RUDN professors and their colleagues from Ontario Tech University Canada, Politecnico di Milano Italy & Karabuk University Turkey have created 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.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.RUDN University’s Department of Transport Professor Reza Kashy Zadeh Kazem said “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.”RUDN University’s Department of Transport Professor Dr Igor Danilov added “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.”
Repetitive loads on metal parts cause fatigue failure. Each loading cycle leads to cracks that grow 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. Russian RUDN professors and their colleagues from Ontario Tech University Canada, Politecnico di Milano Italy & Karabuk University Turkey have created 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.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.RUDN University’s Department of Transport Professor Reza Kashy Zadeh Kazem said “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.”RUDN University’s Department of Transport Professor Dr Igor Danilov added “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.”
