基于神经网络的高压蒸汽管道损伤识别
DAMAGE IDENTIFICATION OF STEAM PIPELINE UNDER HIGH PRESSURE BASED ON NEURAL NETWORK TECHMOLOGY
崔晓明 1贾浩文 2魏宗远2
作者信息
- 1. 黑龙江建筑职业技术学院,哈尔滨 150001
- 2. 哈尔滨工程大学,哈尔滨 150001
- 折叠
摘要
核电站高压蒸汽管道存在诸多问题,对他进行结构健康监测至关重要.文中以某核电站高压蒸汽管道为研究对象,建立缩比模型,结合有限元模型更新方法和BP神经网络进行损伤识别.通过管道模态采集试验获取结构特征参数,更新有限元模型,使他与实际管道结构在动态响应上相似.利用BP神经网络对损伤工况进行识别,选取合适的参数进行训练.结果表明训练后的神经网络在损伤识别中具有高准确率,证明了该方法的可靠性,为实际管道结构的损伤识别积累经验.
Abstract
In nuclear power plants,high-pressure steam pipelines are subjected to many problems,so it is very im-portant to monitor their structural health.In this paper,the scale model of a high-pressure steam pipeline is estab-lished for damage identification by the finite element model updating method and BP neural network.The character-istic parameters of the structure are obtained through the modal acquisition test of the pipeline,and the finite ele-ment model is updated to make it similar to the actual pipeline structure in dynamic response.BP neural network is used to identify the damage condition,and appropriate parameters are selected for training.The results show that the trained neural network has a high accuracy in damage identification.The reliability of the method is verified,provid-ing the reference for the actual damage identification of pipeline structures.
关键词
损伤识别/神经网络/管道结构/固有频率/模态振型/高压管道Key words
damage identification/neural network/pipeline structure/natural frequency/mode shape/high-pres-sure pipeline引用本文复制引用
出版年
2024
NETL
NSTL
万方数据