基于振动信号深度表征学习的高层建筑结构振动识别.pdfVIP

第

41

卷第

9

期Vol.41

No.9工程力学

2024年9

月Sep.2024ENGINEERING

MECHANICS134

文章编号：1000-4750(2024)09-0134-10

基于振动信号深度表征学习的

高层建筑结构振动识别

熊青松，熊海贝，孔庆钊，陈

琳，丁叶蔚，袁

程

(同济大学土木工程防灾国家重点实验室，上海

200092)

摘

要：振动识别对于实现结构振动控制、性态监测评估具有重要作用。“智慧城市”背景下的高层建筑结构

对其振动响应识别提出了更高的要求，传统基于时频域转换与图神经网络的振动识别方法在计算成本和工程适

用性上的局限性愈发显著。该文提出了一种基于振动信号深度表征学习的振动识别方法。在该方法中通过搭建

自编码网络对一维频域信号进行自监督学习用以获取振动表征信息，然后基于原始信号和重构信号进行振动敏

感参数定义和计算，其结果作为特征工程输入到线性分类器模型中进行训练，进而实现对振动的快速识别。该

文以某超高层建筑在不同环境激励下的振动响应识别为例，验证了所提出方法的可靠性。同时为证明提出方法

的优越性，引入了目前普遍认为最优的MFCC+CNN振动识别方法进行对比，结果表明，该文提出的方法在计

算时间上节省了近20倍，并且整体识别精度从0.74提高到0.95以上。

关键词：振动识别；表征学习；高层建筑结构；自编码器；深度学习

中图分类号：TP183；TU312+.1

文献标志码：A

doi:

10.6052/j.issn.1000-4750.2022.07.0650

VIBRATION

RECOGNITION

OF

HIGH-RISE

BUILDING

STRUCTURES

BASED

ON

DEEP

REPRESENTATION

LEARNING

ON

VIBRATIONAL

SIGNALS

XIONG

Qing-song

,

XIONG

Hai-bei

,

KONG

Qing-zhao

,

CHEN

Lin

,

DING

Ye-wei

,

YUAN

Cheng

(State

Key

Laboratory

for

Disaster

Reduction

in

Civil

Engineering,

Tongji

University,

Shanghai

200092,

China)

Abstract:

Vibration

recognition

plays

an

important

role

in

realizing

structural

vibration

control

and

health

monitoring

and

evaluation.

Under

the

background

of

smart

city,

high-rise

building

structures

have

appealed

for

higher

requirements

in

their

vibrational

response

recognition.

Traditional

vibration

recognition

methods

based

on

time-frequency

domain

transformation

and

graph

neural

network

reveal

more

significant

limitations

in

terms

of

computational

cost

and

engineering

applicability.

In

this

study,

a

novel

vibration

recognition

method

based

on

deep

representation

learning

of

vibration

signals

is

proposed.

In

present

method,

self-supervised

lea