It is economical and efficient to use existing natural gas pipelines to transport hydrogen. The fast and accurate prediction of mixing uniformity of hydrogen injection in natural gas pipelines is important for the safety of pipeline transportation and downstream end users. In this study, the computational fluid dynamics (CFD) method was used to investigate the hydrogen injection process in a T-junction natural gas pipeline. The coefficient of variation (COV) of a hydrogen concentration on a pipeline cross section was used to quantitatively characterize the mixing uniformity of hydrogen and natural gas. To quickly and accurately predict the COV, a deep neural network (DNN) model was constructed based on CFD simulation data, and the main influencing factors of the COV including flow velocity, hydrogen blending ratio, gas temperature, flow distance, and pipeline diameter ratio were taken as input nodes of the DNN model. In the model training process, the effects of various parameters on the prediction accuracy of the DNN model were studied, and an accurate DNN architecture was constructed with an average error of 4.53% for predicting the COV. The computational efficiency of the established DNN model was also at least two orders of magnitude faster than that of the CFD simulations for predicting the COV.

To improve the corrosion resistance of 6061 Al in electric vehicle battery packs, a composite coating of nano-SiO₂/Micro-Arc oxidation (MAO) ceramic structure was prepared on its surface. Electrochemical impedance spectroscopy (EIS) and potentiodynamic polarization curves (PDP) were used to evaluate the corrosion resistance of the specimens after 7 days immersion in a 3.5% NaCl solution. The corrosion resistance of the prefabricated coatings was measured via local electrochemical impedance spectroscopy (LEIS). Confocal microscopy, scanning electron microscopy (SEM), and X-ray diffraction (XRD) were used to characterize the microstructure and phase composition of the specimens. An energy dispersive spectrometer (EDS) was used to detect the elemental composition of the surface of the specimen. The results showed that the specimen with nano-SiO₂/MAO composite coating had the least amount of micropores and superior corrosion resistance. The global electrochemical impedance of nano-SiO₂/MAO composite coating was 1.1 times higher than that of the MAO coating and 8.4 times higher than that of the 6061 Al. When the coating was defective, the local electrochemical impedance of the nano-SiO₂/MAO composite coating was still two times higher than that of the MAO coating. In the presence of scratches, the nano-SiO₂/MAO composite coating still showed high corrosion resistance. The collapse corrosion mechanism of the nano-SiO₂/MAO composite coating was proposed.