基于曲率模态和神经网络的施工桁架梁损伤识别研究  被引量:2

Damage Identification of Construction Truss Beam Based onCurvature Mode and Neural Network

在线阅读下载全文

作  者:黄莺[1,2] 宋睿 屈如意 梁江涛 HUANG Ying;SONG Rui;QU Ruyi;LIANG Jiangtao(School of Civil Engineering,Xi’an University of Architecture&Technology,Xi’an,Shaanxi 710055,China;National Experimental Teaching Center for Civil Engineering Virtual Simulation(XAUAT),Xi’an University of Architecture&Technology,Xi’an,Shaanxi 710055,China;China Construction Installation Group Co.,Ltd.,Huaxi Co.,Xi’an,Shaanxi 710055,China;SCEGC No􀆰6 Construction Engineering Group Co.,Ltd.,Xianyang,Shaanxi 712000,China)

机构地区:[1]西安建筑科技大学土木工程学院,陕西西安710055 [2]西安建筑科技大学国家级土木工程虚拟仿真实验教学中心,陕西西安710055 [3]中建安装集团有限公司华西公司,陕西西安710055 [4]陕西建工第六建设集团有限公司,陕西咸阳712000

出  处:《施工技术(中英文)》2023年第5期41-48,共8页Construction Technology

基  金:陕西省自然科学基础研究基金面上项目(2020JM-494)。

摘  要:桁架梁在大跨施工中作为组装式承重结构,代替高支模体系作施工平台,关系到人员生命财产安全,需要进行损伤检测。在人工观察法检测基础上,为提高识别准确率和效率,提出基于曲率模态和神经网络的损伤识别两步法。结合西安某产业研发基地在役施工桁架梁,通过ABAQUS分析模态参数,使用小波变换对数据进行处理,实现损伤定位,并构造BP神经网络,以识别损伤程度。研究表明,基于曲率模态及小波系数和BP神经网络的损伤识别两步法可较好实现对桁架梁的损伤识别。Truss beam is used as assembled load⁃bearing structure in long⁃span construction,replacing high formwork system as construction platform.It is related to the safety of human life and property,so it is necessary to detect its damage.Based on the existing manual observation method,a two⁃step damage identification method based on curvature mode and neural network is proposed to improve the identification accuracy and efficiency.Taking the in⁃service construction truss beam of an industrial research and development base in Xi’an as an example,the model parameters are analyzed by ABAQUS,and the wavelet transform is used to process data to realize the damage location,and the BP neural network is constructed to realize the damage degree recognition.The research shows that the two⁃step damage identification method based on curvature mode,wavelet coefficient and BP neural network can better realize the damage identification of truss beam.

关 键 词:曲率模态 神经网络 小波变换 桁架梁 损伤识别 

分 类 号:TU758[建筑科学—建筑技术科学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象