The empirical modeling methods are widely used in corrosion behavior analysis. But due to the limited regression ability of conventional algorithms, modeling objects are often limited to individual factors and specific environments. This study proposed a modeling method based on machine learning to simulate the marine atmospheric corrosion behavior of low-alloy steels. The correlations between material, environmental factors and corrosion rate were evaluated, and their influences on the corrosion behavior of steels were analyzed intuitively. By using the selected dominating factors as input variables, an optimized random forest model was established with a high prediction accuracy of corrosion rate (R 2 values, 0.94 and 0.73 to the training set and testing set) to different low-alloy steel samples in several typical marine atmospheric environments. The results demonstrated that machine learning was efficient in corrosion behavior analysis, which usually involves a regression analysis of multiple factors.

This article uses powder metallurgy technology to prepare foamed aluminum and carbon nanotubes (CNTs) / foamed aluminum composites. The laser thermal diffusion analyzer, thermal analyzer, and transfer function sound absorption coefficient test system were used to study the thermal conductivity and sound absorption properties of aluminum foam and its composites, respectively. The results show that the thermal conductivity of aluminum foam with 79% porosity is only 5W · m−1·K−1, which is much smaller than the thermal conductivity of aluminum. So it can be used as an ideal thermal insulation material; The thermal conductivity of carbon nanotubes (CNTs) / foamed aluminum-based composites increases first and then decreases with the increase in the mass fraction of CNTs. As the test temperature increases, the thermal conductivity of the material gradually increases. When the mass fraction of CNTs is 0.75%, the thermal conductivity of foamed aluminum-based composites reaches the maximum. As the test frequency increases, the sound absorption performance of foamed aluminum first increases, then decreases, and then gradually increases, reaching a maximum value around 1000 Hz. The sound absorption performance of CNTs / foam aluminum matrix composites decreases at lower test frequencies as the mass fraction of CNTs increases. At higher frequencies, as the mass fraction of CNTs increases, the sound absorption coefficient of foamed aluminum decreases first and then increases.

The material model was established by the finite element analysis software ABAQUS. The temperature field and stress field of iron-based powder metallurgy friction pairs under the brake pressure of 0.44Mpa and 0.8MPa were calculated respectively. The variation laws of temperature and stress under two pressure conditions were compared and analyzed. The results show that with the increase of braking pressure, the stress of the friction pairs increases, but the distribution of temperature and stress fields changes little.

No abstract

For the iron-based powder metallurgical friction pair under high-speed braking conditions, the structural model and physical model of the friction pair were established, and the finite element software ABAQUS was used to calculate and analyze the temperature field and distribution law of the friction pair during friction braking. The results show that during friction braking, the temperature at the outer diameter of the contact surface of the friction pair is the highest, and the temperature at the inner diameter of the edge of the chip removal tank is the lowest. During braking, the temperature of friction pair increases first and then decreases with time.