结构工程师2024，Vol.40Issue(2)：184-191,8.
龙门吊轨道交叉下连续箱梁移位工序AI识别模型
AI identification Model for Continuous Box Girder Displacement Process of Cross-Sea Channel Project under Gantry Crane Track Crossing
黄华1
作者信息
- 1. 广东盛翔交通工程检测有限公司,广州 511400
- 折叠
摘要
Abstract
In order to improve the quality of continuous box girder displacement and ensure the orderly and smooth progress of the project,an AI identification model for the continuous box girder displacement process of cross-sea channel project under the crossing of a gantry crane track is designed.The process flow of continuous box girder displacement is analyzed,and it is divided into five processes:reinforcement processing,formwork installation,and concrete steam curing.The AI recognition model of the continuous box girder shift process is built using threshold Boltzmann machine and support vector machine in artificial intelligence technology.Continuous box girder shift working images are collected,and these collected images are taken as the model input.The convolution layer and pooling layer in the convolutional neural network are utilized to optimize the threshold Boltzmann machine model.The optimized model is then used to collect the characteristics of the continuous box girder shift working images.Based on different image features,support vector machine is used to classify image categories and complete process recognition.The experimental results show that the model can accurately identify the displacement process of continuous box girder and effectively improve the construction performance and economic benefits of the project.关键词
龙门吊轨道/跨海通道工程/连续箱梁移位/工序识别/深度学习/支持向量机Key words
gantry crane track/cross-sea channel project/displacement of continuous box girder/process identification/deep learning/support vector machine引用本文复制引用
黄华..龙门吊轨道交叉下连续箱梁移位工序AI识别模型[J].结构工程师,2024,40(2):184-191,8.
