Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings

The modal frequencies of a structure are affected by continuous changes in ambient factors, such as temperature, wind speed etc. This study incorporates nonlinear principal component analysis (NLPCA) with support vector regression (SVR) to build a mathematical model to reflect the correlation betwee...

Full description

Bibliographic Details
Main Authors: Xijun Ye, Yingfeng Wu, Liwen Zhang, Liu Mei, Yunlai Zhou
Format: Article
Language:English
Published: MDPI AG 2020-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/20/4/1143
_version_ 1818002081412284416
author Xijun Ye
Yingfeng Wu
Liwen Zhang
Liu Mei
Yunlai Zhou
author_facet Xijun Ye
Yingfeng Wu
Liwen Zhang
Liu Mei
Yunlai Zhou
author_sort Xijun Ye
collection DOAJ
description The modal frequencies of a structure are affected by continuous changes in ambient factors, such as temperature, wind speed etc. This study incorporates nonlinear principal component analysis (NLPCA) with support vector regression (SVR) to build a mathematical model to reflect the correlation between ambient factors and modal frequencies. NLPCA is first used to eliminate the high correlation among different ambient factors and extract the nonlinear principal components. The extracted nonlinear principal components are input into the SVR model for training and predicting. The proposed method is verified by the measured data provided in the Guangzhou New TV Tower (GNTVT) Benchmark. The grid search method (GSM), genetic algorithm (GA) and fruit fly optimization algorithm (FOA) are applied to determine the optimal hyperparameters for the SVR model. The optimized result of FOA is most suitable for the NLPCA-SVR model. As evaluated by the hypothesis test and goodness-of-fit test, the results show that the proposed method has a high generalization performance and the correlation between the ambient factor and modal frequency can be strongly reflected. The proposed method can effectively eliminate the effects of ambient factors on modal frequencies.
first_indexed 2024-04-14T03:42:14Z
format Article
id doaj.art-56cc8da98dcb4c8d810f3d795270bab5
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-04-14T03:42:14Z
publishDate 2020-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-56cc8da98dcb4c8d810f3d795270bab52022-12-22T02:14:29ZengMDPI AGSensors1424-82202020-02-01204114310.3390/s20041143s20041143Ambient Effect Filtering Using NLPCA-SVR in High-Rise BuildingsXijun Ye0Yingfeng Wu1Liwen Zhang2Liu Mei3Yunlai Zhou4School of Civil Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Civil Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Civil Engineering, Guangzhou University, Guangzhou 510006, ChinaGuangdong Provincial Key Laboratory of Durability for Marine Civil Engineering, Shenzhen University, Shenzhen 518060, ChinaDepartment of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, SAR, ChinaThe modal frequencies of a structure are affected by continuous changes in ambient factors, such as temperature, wind speed etc. This study incorporates nonlinear principal component analysis (NLPCA) with support vector regression (SVR) to build a mathematical model to reflect the correlation between ambient factors and modal frequencies. NLPCA is first used to eliminate the high correlation among different ambient factors and extract the nonlinear principal components. The extracted nonlinear principal components are input into the SVR model for training and predicting. The proposed method is verified by the measured data provided in the Guangzhou New TV Tower (GNTVT) Benchmark. The grid search method (GSM), genetic algorithm (GA) and fruit fly optimization algorithm (FOA) are applied to determine the optimal hyperparameters for the SVR model. The optimized result of FOA is most suitable for the NLPCA-SVR model. As evaluated by the hypothesis test and goodness-of-fit test, the results show that the proposed method has a high generalization performance and the correlation between the ambient factor and modal frequency can be strongly reflected. The proposed method can effectively eliminate the effects of ambient factors on modal frequencies.https://www.mdpi.com/1424-8220/20/4/1143ambient effectsmodal frequencyguangzhou new tv towernonlinear principal component analysissupport vector regression
spellingShingle Xijun Ye
Yingfeng Wu
Liwen Zhang
Liu Mei
Yunlai Zhou
Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings
Sensors
ambient effects
modal frequency
guangzhou new tv tower
nonlinear principal component analysis
support vector regression
title Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings
title_full Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings
title_fullStr Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings
title_full_unstemmed Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings
title_short Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings
title_sort ambient effect filtering using nlpca svr in high rise buildings
topic ambient effects
modal frequency
guangzhou new tv tower
nonlinear principal component analysis
support vector regression
url https://www.mdpi.com/1424-8220/20/4/1143
work_keys_str_mv AT xijunye ambienteffectfilteringusingnlpcasvrinhighrisebuildings
AT yingfengwu ambienteffectfilteringusingnlpcasvrinhighrisebuildings
AT liwenzhang ambienteffectfilteringusingnlpcasvrinhighrisebuildings
AT liumei ambienteffectfilteringusingnlpcasvrinhighrisebuildings
AT yunlaizhou ambienteffectfilteringusingnlpcasvrinhighrisebuildings