通过具有长短期记忆和注意机制的双向递归神经网络桥接运动中称重

IF 2.1 3区 工程技术 Q2 ENGINEERING, CIVIL Smart Structures and Systems Pub Date : 2021-02-01 DOI:10.12989/SSS.2021.27.2.241
Yang Wang, Zhichao Wang
{"title":"通过具有长短期记忆和注意机制的双向递归神经网络桥接运动中称重","authors":"Yang Wang, Zhichao Wang","doi":"10.12989/SSS.2021.27.2.241","DOIUrl":null,"url":null,"abstract":"In bridge weigh-in-motion (BWIM), dynamic bridge response is measured during traffic and used to identify overloaded vehicles. Most past studies of BWIM use mechanics-based algorithms to estimate axle weights. This research instead investigates deep learning, specifically the recurrent neural network (RNN), toward BWIM. In order to acquire the large data volume to train a RNN network that uses bridge response to estimate axle weights, a finite element bridge model is built through the commercial software package LS-DYNA. To mimic everyday traffic scenarios, tens of thousands of randomized vehicle formations are simulated, with different combinations of vehicle types, spacings, speeds, axle weights, axle distances, etc. Dynamic response from each of the randomized traffic scenarios is recorded for training the RNN. In this paper we propose a 3-stage Bidirectional RNN toward BWIM. Long short-term memory (LSTM) and attention mechanism are embedded in the BRNN to further improve the network performance. Additional test data indicates that the BRNN network achieves high accuracy in estimating axle weights, in comparison with a conventional moving force identification (MFI) method.","PeriodicalId":51155,"journal":{"name":"Smart Structures and Systems","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2021-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Bridge weigh-in-motion through bidirectional Recurrent Neural Network with long short-term memory and attention mechanism\",\"authors\":\"Yang Wang, Zhichao Wang\",\"doi\":\"10.12989/SSS.2021.27.2.241\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In bridge weigh-in-motion (BWIM), dynamic bridge response is measured during traffic and used to identify overloaded vehicles. Most past studies of BWIM use mechanics-based algorithms to estimate axle weights. This research instead investigates deep learning, specifically the recurrent neural network (RNN), toward BWIM. In order to acquire the large data volume to train a RNN network that uses bridge response to estimate axle weights, a finite element bridge model is built through the commercial software package LS-DYNA. To mimic everyday traffic scenarios, tens of thousands of randomized vehicle formations are simulated, with different combinations of vehicle types, spacings, speeds, axle weights, axle distances, etc. Dynamic response from each of the randomized traffic scenarios is recorded for training the RNN. In this paper we propose a 3-stage Bidirectional RNN toward BWIM. Long short-term memory (LSTM) and attention mechanism are embedded in the BRNN to further improve the network performance. Additional test data indicates that the BRNN network achieves high accuracy in estimating axle weights, in comparison with a conventional moving force identification (MFI) method.\",\"PeriodicalId\":51155,\"journal\":{\"name\":\"Smart Structures and Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2021-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Smart Structures and Systems\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.12989/SSS.2021.27.2.241\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Smart Structures and Systems","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.12989/SSS.2021.27.2.241","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 4

摘要

在桥梁动态称重(BWIM)中,桥梁动态响应是在交通过程中测量的,用于识别超载车辆。过去对BWIM的大多数研究都使用基于力学的算法来估计轴重。相反,这项研究针对BWIM研究了深度学习,特别是递归神经网络(RNN)。为了获得大数据量来训练利用桥梁响应估计轴重的RNN网络,通过商业软件包LS-DYNA建立了桥梁有限元模型。为了模拟日常交通场景,模拟了数以万计的随机车辆编队,车辆类型、间距、速度、轴重、轴距等的不同组合。记录每个随机交通场景的动态响应,以训练RNN。在本文中,我们提出了一种针对BWIM的三阶段双向RNN。在BRNN中嵌入了长短期记忆(LSTM)和注意力机制,以进一步提高网络性能。额外的测试数据表明,与传统的移动力识别(MFI)方法相比,BRNN网络在估计轴重方面实现了高精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Bridge weigh-in-motion through bidirectional Recurrent Neural Network with long short-term memory and attention mechanism
In bridge weigh-in-motion (BWIM), dynamic bridge response is measured during traffic and used to identify overloaded vehicles. Most past studies of BWIM use mechanics-based algorithms to estimate axle weights. This research instead investigates deep learning, specifically the recurrent neural network (RNN), toward BWIM. In order to acquire the large data volume to train a RNN network that uses bridge response to estimate axle weights, a finite element bridge model is built through the commercial software package LS-DYNA. To mimic everyday traffic scenarios, tens of thousands of randomized vehicle formations are simulated, with different combinations of vehicle types, spacings, speeds, axle weights, axle distances, etc. Dynamic response from each of the randomized traffic scenarios is recorded for training the RNN. In this paper we propose a 3-stage Bidirectional RNN toward BWIM. Long short-term memory (LSTM) and attention mechanism are embedded in the BRNN to further improve the network performance. Additional test data indicates that the BRNN network achieves high accuracy in estimating axle weights, in comparison with a conventional moving force identification (MFI) method.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Smart Structures and Systems
Smart Structures and Systems 工程技术-工程:机械
CiteScore
6.50
自引率
8.60%
发文量
0
审稿时长
9 months
期刊介绍: An International Journal of Mechatronics, Sensors, Monitoring, Control, Diagnosis, and Management airns at providing a major publication channel for researchers in the general area of smart structures and systems. Typical subjects considered by the journal include: Sensors/Actuators(Materials/devices/ informatics/networking) Structural Health Monitoring and Control Diagnosis/Prognosis Life Cycle Engineering(planning/design/ maintenance/renewal) and related areas.
期刊最新文献
Analysis, optimization and control of an adaptive tuned vibration absorber featuring magnetoactive materials Numerical investigation on cyclic behaviour of superelastic shape memory alloy (SMA) dampers Hybrid fragility curve derivation of buildings based on post-earthquake reconnaissance data A corrosion threshold-controllable sensing system of Fe-C coated long period fiber gratings for life-cycle mass loss measurement of steel bars with strain and temperature compensation Steel dual-ring dampers: Micro-finite element modelling and validation of cyclic behavior
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1