您的位置：首页 > 论文页面
从变分自编码器隐空间中生成新桥型的尝试
发表时间：2024-06-28 浏览量：62 下载量：9
| 全部作者： | 张洪俊 |
| 作者单位： | 万世先行数智交通科技有限公司 |
| 摘 要： | 尝试利用生成式人工智能技术生成新桥型。采用3ds MAX动画软件渲染构件宽度变化的桥梁立面灰度图片，接着用OpenCV模块对图片进行适量的几何变换（旋转、水平缩放、竖向缩放），获得三跨梁式桥、拱式桥、斜拉桥、悬索桥图像数据集。基于Python编程语言、TensorFlow及Keras深度学习平台框架，构建和训练变分自编码器，得到便于向量运算的低维桥型隐空间，实践发现从隐空间中采样能够生成新的组合桥型。变分自编码器能够在人类原创桥型的基础上，将两种桥型合为一体，组合创造。生成式人工智能技术能够协助桥梁设计师进行桥型创新，可以作为虚拟助手。 |
| 关 键 词： | 人工智能；桥型创新；变分自编码器；隐空间；深度学习 |
| Title： | An attempt to generate new bridge types from latent space of variational autoencoder |
| Author： | ZHANG Hongjun |
| Organization： | Wanshi Antecedence Digital Intelligence Traffic Technology Co., Ltd. |
| Abstract： | We try to generate new bridge types using generative artificial intelligence technology. The grayscale images of the bridge facade with the change of component width were rendered by 3ds MAX animation software, and then the OpenCV module performed an appropriate amount of geometric transformation (rotation, horizontal scale, vertical scale) to obtain the image dataset of the three-span beam bridge, arch bridge, cable-stayed bridge, and suspension bridge. Based on Python programming language, TensorFlow, and Keras deep learning platform framework, a 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 based on the original human into one that is a new bridge-type. Generative artificial intelligence technology can assist bridge designers in bridge-type innovation and can be used as the copilot. |
| Key words： | artificial intelligence; bridge-type innovation; variational autoencoder; latent space; deep learning |
| 发表期数： | 2024年6月第2期 |
| 引用格式： | 张洪俊. 从变分自编码器隐空间中生成新桥型的尝试[J]. 中国科技论文在线精品论文，2024，17（2）：196-204. |
0
评论数 0请您登录
暂无评论
下载全文
多维论文