An attempt to generate new bridge types from latent space of variational autoencoder

• 1、Wanshi Xianxing Digital Intelligence Traffic Technology Co., Ltd, Nanjing, 210016, China

Abstract：Try to generate new bridge types using generative artificial intelligence technology. The grayscale pictures of the bridge fa?ade with the change of component width was rendered by 3dsMax animation software, and then the OpenCV module performed an appropriate amount of geometric transformation (rotation, horizontal scale, vertical scaling) to obtain the image dataset of three-span beam bridge, arch bridge, cable-stayed bridge and suspension bridge. Based on Python programming language, TensorFlow and Keras deep learning platform framework, variational autoencoder was constructed and trained, and low-dimensional bridge-type latent space that is convenient for vector operations was obtained. Variational autoencoder can combine two bridge types into one on the basis of the original human bridge type. Generative artificial intelligence technology can assist bridge designers in bridge-type innovation, and can be used as copilot.

Keywords： variational autoencoder latent space bridge-type innovation generative artificial intelligence deep learning