数字孪生驱动的水工闸门损伤在线识别与监测方法  

Online Identification and Monitoring Method for Damage of Hydraulic Gates Driven by Digital Twins

作　　者：朱潇 张钰奇 熊景然 陈栋[1] 李成[1] ZHU Xiao;ZHANG Yu-qi;XIONG Jing-ran;CHEN Dong;LI Cheng(School of Mechanical and Power Engineering,Zhengzhou University,Zhengzhou 450001,China)

机构地区：[1]郑州大学机械与动力工程学院,河南郑州450001

出　　处：《水电能源科学》2024年第9期143-147,共5页Water Resources and Power

基　　金：国家自然科学基金项目(52175153);河南省水下智能装备重点实验室开放基金(ZT22064U)。

摘　　要：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,具有较高的准确性和较快的分析速度,验证了该方法在水工闸门损伤识别中的可行性.A digital twin-based online identification and monitoring method for hydraulic gate damage is proposed to address issues related to complex identification processes,poor real-time performance,and limited visualization in the hydraulic gate damage identification process.Firstly,a method for acquiring twin data of the gate is introduced,and a convolutional neural network fused with attention modules is used to extract features from the twin data and construct a realtime data-driven gate damage identification model.Subsequently,digital twin technology is employed to build a virtual reality scene for hydraulic gates,with the damage identification results mapped onto the virtual geometric model of the gate,facilitating real-time visual monitoring of gate damage.Finally,this method is applied to a hydraulic gate experimental platform,and a gate damage identification system is developed using the Unity3D platform.The results demonstrate that the constructed hydraulic gate damage identification model achieves an accuracy rate of over 95%in identifying damage states,with an average system identification time for damage of 136.68 milliseconds.This method exhibits high accuracy and fast analysis speed,confirming the feasibility of its application in hydraulic gate damage identification.

关 键 词：水工闸门 损伤识别 数字孪生 可视化监测 

分 类 号：TV663[水利工程—水利水电工程]