Try to generate new bridge types using generative artificial intelligence technology. Symmetric structured image dataset of three-span beam bridge, arch bridge, cable-stayed bridge and suspension bridge are used . Based on Python programming language, TensorFlow and Keras deep learning platform framework , as well as Wasserstein loss function and Lipschitz constraints, generative adversarial network is constructed and trained. From the obtained low dimensional bridge-type latent space sampling, new bridge types with asymmetric structures can be generated. Generative adversarial network can create new bridge types by organically combining different structural components on the basis of human original bridge types. It has a certain degree of human original ability. Generative artificial intelligence technology can open up imagination space and inspire humanity.

使用生成人工智能技术尝试生成新的桥梁类型。利用三跨梁桥、拱桥、斜拉桥和悬索桥的对称结构图像数据集。基于Python编程语言，TensorFlow和Keras深度学习平台框架，以及Wasserstein损失函数和Lipschitz约束，构建并训练了生成对抗网络。可以通过获取的低维桥类型潜空间采样生成具有非对称结构的新桥梁类型。生成对抗网络能够通过有机地结合不同的结构组件，基于人类原始桥梁类型创造新的桥梁类型，具有一定的人类原创能力。生成人工智能技术能够拓展想象空间并启发人类。

从生成对抗网络的潜空间中尝试生成新的桥梁类型