Synthesis of Near-Fault Ground Motions Based on the Wavelet Packet Transform and BP Neural Network.
Saved in:
| Title: | Synthesis of Near-Fault Ground Motions Based on the Wavelet Packet Transform and BP Neural Network. |
|---|---|
| Authors: | Lin, Guobin1 (AUTHOR), Hu, Xiaobin1,2 (AUTHOR) newhxb@whu.edu.cn |
| Source: | Journal of Earthquake Engineering. Jul2025, Vol. 29 Issue 9, p1839-1869. 31p. |
| Subjects: | Ground motion, Back propagation, Earthquake engineering, Wavelet transforms, Acceleration (Mechanics) |
| Abstract: | Synthesis of near-fault (NF) ground motions is an important task in earthquake engineering since they are rarely recorded in historical events. This paper mainly focuses on proposing a novel method of generating NF ground motions in the direction of the strongest pulse under given seismological parameters while appropriately considering the non-stationarity especially in the frequency domain. The synthesis model consists of two parts: a low-frequency velocity pulse component constructed using the modified Gabor wavelet function and a high-frequency acceleration component generated utilizing the wavelet packet transform (WPT). Based on the collected NF records, the parameters involved in the synthesis model are recognized and related to the seismological parameters pertaining to NF ground motions using the BP network. In the process, random errors induced by different seismic events and different records within the same event are appropriately taken into account. Thereby, the whole procedure is proposed and successfully applied to generate the NF ground motions under given seismological parameters. Finally, a comparative study is carried out to further demonstrate the advantage of the method proposed in this study. The results reveal that the WPT utilized in the method can more effectively simulate the non-stationarity of NF ground motions in the frequency domain compared to existing methods. Moreover, the use of BP neural networks not only enhances the accuracy but also significantly reduces the uncertainty. The method proposed in this study can be well applicable for related studies in performance-based earthquake engineering. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Earthquake Engineering is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 186283591 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Synthesis of Near-Fault Ground Motions Based on the Wavelet Packet Transform and BP Neural Network. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Lin%2C+Guobin%22">Lin, Guobin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hu%2C+Xiaobin%22">Hu, Xiaobin</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> newhxb@whu.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Journal+of+Earthquake+Engineering%22">Journal of Earthquake Engineering</searchLink>. Jul2025, Vol. 29 Issue 9, p1839-1869. 31p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Ground+motion%22">Ground motion</searchLink><br /><searchLink fieldCode="DE" term="%22Back+propagation%22">Back propagation</searchLink><br /><searchLink fieldCode="DE" term="%22Earthquake+engineering%22">Earthquake engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Wavelet+transforms%22">Wavelet transforms</searchLink><br /><searchLink fieldCode="DE" term="%22Acceleration+%28Mechanics%29%22">Acceleration (Mechanics)</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Synthesis of near-fault (NF) ground motions is an important task in earthquake engineering since they are rarely recorded in historical events. This paper mainly focuses on proposing a novel method of generating NF ground motions in the direction of the strongest pulse under given seismological parameters while appropriately considering the non-stationarity especially in the frequency domain. The synthesis model consists of two parts: a low-frequency velocity pulse component constructed using the modified Gabor wavelet function and a high-frequency acceleration component generated utilizing the wavelet packet transform (WPT). Based on the collected NF records, the parameters involved in the synthesis model are recognized and related to the seismological parameters pertaining to NF ground motions using the BP network. In the process, random errors induced by different seismic events and different records within the same event are appropriately taken into account. Thereby, the whole procedure is proposed and successfully applied to generate the NF ground motions under given seismological parameters. Finally, a comparative study is carried out to further demonstrate the advantage of the method proposed in this study. The results reveal that the WPT utilized in the method can more effectively simulate the non-stationarity of NF ground motions in the frequency domain compared to existing methods. Moreover, the use of BP neural networks not only enhances the accuracy but also significantly reduces the uncertainty. The method proposed in this study can be well applicable for related studies in performance-based earthquake engineering. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Journal of Earthquake Engineering is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=186283591 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1080/13632469.2025.2484585 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 31 StartPage: 1839 Subjects: – SubjectFull: Ground motion Type: general – SubjectFull: Back propagation Type: general – SubjectFull: Earthquake engineering Type: general – SubjectFull: Wavelet transforms Type: general – SubjectFull: Acceleration (Mechanics) Type: general Titles: – TitleFull: Synthesis of Near-Fault Ground Motions Based on the Wavelet Packet Transform and BP Neural Network. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Lin, Guobin – PersonEntity: Name: NameFull: Hu, Xiaobin IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 07 Text: Jul2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 13632469 Numbering: – Type: volume Value: 29 – Type: issue Value: 9 Titles: – TitleFull: Journal of Earthquake Engineering Type: main |
| ResultId | 1 |
