针对水工闸门损伤识别过程中存在的识别流程复杂、实时性较差、可视化程度低的问题,提出一种数字孪生驱动的水工闸门损伤在线识别与监测方法。首先阐述闸门孪生数据的获取方法,并采用融合注意力模块的卷积神经网络对其进行特征提取,构建实时数据驱动的闸门损伤识别模型;然后利用数字孪生技术搭建水工闸门虚拟现实场景,并将损伤识别结果映射至闸门虚拟几何模型,实现闸门损伤的实时可视化监测;最后将该方法应用于水工闸门试验平台,并借助Unity3D平台实现闸门数字孪生损伤识别系统的开发。结果表明,构建的水工闸门损伤识别模型对损伤状态的识别准确率达到了95%以上,系统运行每帧平均用时为136.68 ms
Department of Cold Regions Kitami Institute of Technology Hokkaido,Department of Civil and Environmental Engineering Kitami Institute of Technology Hokkaido,Department of Civil and Environmental Engineering Kitami Institute of Technology Hokkaido,Department of Civil and Environmental Engineering Kitami Institute of Technology Hokkaido.Vibration‐based structural state identification by a 1‐dimensional convolutional neural network[J].Computer‐Aided Civil and Infrastructure Engineering,2019.
Osama Abdeljaber,Onur Avci,Mustafa Serkan Kiranyaz,Boualem Boashash,Henry Sodano,Daniel J. Inman.1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data[J].Neurocomputing,2018.