... 06 2026 © 2026 Emerald Publishing Limited 2026 Emerald Publishing Limited Licensed re-use rights only aerodynamic force aerodynamic torque artificial intelligence bogie data high-velocity locomotive neural networks tunnel N–S Navier–Stokes k − ϵ turbulence...

... in various fields, and some scholars applied wavelet analysis to image decomposition and reconstruction. The backpropagation algorithm was proposed by an American biophysicist, and the research on neural networks also gradually matured (Lawal and Zhao, 2021). From the 1990s to now, with the rapid development...

..., a deep convolutional neural network is used to determine flood depth through the analysis of crowdsourced images of submerged stop signs. Model performance in pole length estimation is tested on a test set, achieving a root mean squared error of 10.200 in. (1 in. = 1 inch = 2.54 cm) on pre-flood...

... and depth of cracks in a beam structure, a genetic algorithm (GA) and a damage identification model are combined. This method optimises the back-propagation neural network by using the ability of the GA to find the global optimal solution. The natural frequency (NF) of the cracked beam is obtained through...

... study of neural networks, embedding neural networks in predictive models can improve model performance. A genetic algorithm combined with a feed-forward back-propagation (BP) neural network can be applied to metallisation rate prediction in the actual production process (Zhang et al., 2021...