Zihang Weng, Chenglong Liu, Yuchuan Du, Difei Wu, Zhen Leng
The pavement skid resistance is crucial for ensuring driving safety. However, the reproducibility and comparability of field measurements are constrained by various influencing factors. One solution to these constraints is utilizing laser‐based 3D pavement data, which are notably stable and can be employed to estimate pavement skid resistance indirectly. However, the integration of tire–road friction mechanisms and deep neural networks has not been fully studied. This study employed spatial‐channel attention mechanisms to integrate frictional domain knowledge and convolutional neural networks (CNNs) that predict the friction coefficient as the output. The models’ inputs include 3D texture data, corresponding finite element (FE) simulation outcomes, and 2D wavelet decomposition outcomes. An additional spatial attention (ASA) mechanism guided the CNNs to focus on the tire–road contact region, using tire–road contact stress from FE simulation as domain knowledge. Multi‐scale channel attention (MSCA) mechanisms enabled the CNNs to learn the channel weights of 2D‐wavelet‐based multi‐scale inputs, thereby assessing the contribution of different texture scales to tire–road friction. A multi‐attention and feature fusion mechanism was designed, and the performances of various combinations were compared. The results showed that the fusion of ASA and MSCA achieved the best performance, with a regression R2 of 0.8470, which was a 20.25% improvement over the baseline model.
{"title":"Integrating spatial and channel attention mechanisms with domain knowledge in convolutional neural networks for friction coefficient prediction","authors":"Zihang Weng, Chenglong Liu, Yuchuan Du, Difei Wu, Zhen Leng","doi":"10.1111/mice.13391","DOIUrl":"https://doi.org/10.1111/mice.13391","url":null,"abstract":"The pavement skid resistance is crucial for ensuring driving safety. However, the reproducibility and comparability of field measurements are constrained by various influencing factors. One solution to these constraints is utilizing laser‐based 3D pavement data, which are notably stable and can be employed to estimate pavement skid resistance indirectly. However, the integration of tire–road friction mechanisms and deep neural networks has not been fully studied. This study employed spatial‐channel attention mechanisms to integrate frictional domain knowledge and convolutional neural networks (CNNs) that predict the friction coefficient as the output. The models’ inputs include 3D texture data, corresponding finite element (FE) simulation outcomes, and 2D wavelet decomposition outcomes. An additional spatial attention (ASA) mechanism guided the CNNs to focus on the tire–road contact region, using tire–road contact stress from FE simulation as domain knowledge. Multi‐scale channel attention (MSCA) mechanisms enabled the CNNs to learn the channel weights of 2D‐wavelet‐based multi‐scale inputs, thereby assessing the contribution of different texture scales to tire–road friction. A multi‐attention and feature fusion mechanism was designed, and the performances of various combinations were compared. The results showed that the fusion of ASA and MSCA achieved the best performance, with a regression <jats:italic>R</jats:italic><jats:sup>2</jats:sup> of 0.8470, which was a 20.25% improvement over the baseline model.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"36 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142797166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rock quality designation (RQD) plays a crucial role in the design and analysis of rock engineering. The traditional method of measuring RQD relies on manual logging by geologists, which is often labor‐intensive and time‐consuming. Thus, this study presents an autonomous framework for expeditious RQD estimation based on two‐dimensional corebox photographs. The scale‐invariant feature transform (SIFT) algorithm is employed for rapid image calibration. A K‐Net‐based model with dynamic semantic kernels, conditional on their actual activations, is proposed for rock core segmentation. It surpasses other prevalent models with a mean intersection over union of 95.43%. The automatic RQD estimation error of our proposed framework is only 1.46% compared to manual logging results, demonstrating its exceptional reliability and effectiveness. The robustness of the framework is then validated on an additional test set, proving its potential for widespread adoption in geotechnical engineering practice.
{"title":"A K‐Net‐based deep learning framework for automatic rock quality designation estimation","authors":"Sihao Yu, Louis Ngai Yuen Wong","doi":"10.1111/mice.13386","DOIUrl":"https://doi.org/10.1111/mice.13386","url":null,"abstract":"Rock quality designation (RQD) plays a crucial role in the design and analysis of rock engineering. The traditional method of measuring RQD relies on manual logging by geologists, which is often labor‐intensive and time‐consuming. Thus, this study presents an autonomous framework for expeditious RQD estimation based on two‐dimensional corebox photographs. The scale‐invariant feature transform (SIFT) algorithm is employed for rapid image calibration. A K‐Net‐based model with dynamic semantic kernels, conditional on their actual activations, is proposed for rock core segmentation. It surpasses other prevalent models with a mean intersection over union of 95.43%. The automatic RQD estimation error of our proposed framework is only 1.46% compared to manual logging results, demonstrating its exceptional reliability and effectiveness. The robustness of the framework is then validated on an additional test set, proving its potential for widespread adoption in geotechnical engineering practice.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"95 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142797167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. G. Fragkoulis, F. N. Koumboulis, M. P. Tzamtzi, P. G. Totomis
An event-based supervisory control scheme, in the Ramdage–Wonham framework, will be proposed for the cyber-physical Waterway Lock system, known as Lock III, in Tilburg, the Netherlands. The proposed control scheme imposes desired behavior, by appropriately disabling controllable events, so as to avoid activation of actuator commands that may lead to undesired and potentially hazardous operating states. The discrete event model of the total Waterway Lock system, comprising 54 actuator and sensor automata, will be presented in analytic 6-tuple forms of its subsystems. The system's desired behavior, which is expressed using six rules, will be formulated as 84 regular and prefix closed languages that will be realized as appropriate supervisor automata. All supervisors are developed by a general two-state supervisor form, which facilitates their implementation. A distributed control architecture will be proposed, which organizes all supervisors in distinct groups, each of which controls one and only one distinct command event. The complexity of the proposed control scheme will be computed to be equal to (168,324,564), being reasonable, as compared to the large number of subsystems and the restrictive design requirements. The physical realizability of the 84 supervisors, with respect to the 54 subsystems of the waterway lock system, will be proved analytically. Also, it will be proved analytically that the proposed supervisor architecture guarantees the nonblocking property of the controlled automaton, including all subsystems. The establishment of these analytic proofs supports the extendibility of the results to other applications. To demonstrate the resulting large-scale controlled automaton's good performance, its marked behavior and simulation results will be presented.
{"title":"Event-based supervisor control for a cyber-physical waterway lock system","authors":"D. G. Fragkoulis, F. N. Koumboulis, M. P. Tzamtzi, P. G. Totomis","doi":"10.1111/mice.13393","DOIUrl":"https://doi.org/10.1111/mice.13393","url":null,"abstract":"An event-based supervisory control scheme, in the Ramdage–Wonham framework, will be proposed for the cyber-physical Waterway Lock system, known as Lock III, in Tilburg, the Netherlands. The proposed control scheme imposes desired behavior, by appropriately disabling controllable events, so as to avoid activation of actuator commands that may lead to undesired and potentially hazardous operating states. The discrete event model of the total Waterway Lock system, comprising 54 actuator and sensor automata, will be presented in analytic 6-tuple forms of its subsystems. The system's desired behavior, which is expressed using six rules, will be formulated as 84 regular and prefix closed languages that will be realized as appropriate supervisor automata. All supervisors are developed by a general two-state supervisor form, which facilitates their implementation. A distributed control architecture will be proposed, which organizes all supervisors in distinct groups, each of which controls one and only one distinct command event. The complexity of the proposed control scheme will be computed to be equal to (168,324,564), being reasonable, as compared to the large number of subsystems and the restrictive design requirements. The physical realizability of the 84 supervisors, with respect to the 54 subsystems of the waterway lock system, will be proved analytically. Also, it will be proved analytically that the proposed supervisor architecture guarantees the nonblocking property of the controlled automaton, including all subsystems. The establishment of these analytic proofs supports the extendibility of the results to other applications. To demonstrate the resulting large-scale controlled automaton's good performance, its marked behavior and simulation results will be presented.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"14 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142793159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate soil stratification is essential for geotechnical engineering design. Owing to its effectiveness and efficiency, the cone penetration test (CPT) has been widely applied for subsurface stratigraphy, which relies heavily on empiricism for correlations to soil type. Recently, deep learning techniques have shown great promise in learning the relationship between CPT data and soil boundaries automatically. However, the segmentation of soil boundaries is fraught with model and measurement uncertainty. This paper introduces an uncertainty-guided U((-Net (UGU-Net) for improved soil boundary segmentation. The UGU-Net consists of three parts: (a) a Bayesian U-Net to predict a pixel-level uncertainty map, (b) reinforcement of original labels on the basis of the predicted uncertainty map, and (c) a traditional deterministic U-Net, which is applied to the reinforced labels for final soil boundary segmentation. The results show that the proposed UGU-Net outperforms the existing methods in terms of both high accuracy and low uncertainty. A sensitivity study is also conducted to explore the influence of key model parameters on model performance. The proposed method is validated by comparing the predicted subsurface profile with benchmark profiles. The code for this project is available at github.com/Xiaoqi-Zhou-suda/UGU-Net.
{"title":"Uncertainty-guided U-Net for soil boundary segmentation using Monte Carlo dropout","authors":"X. Zhou, B. Sheil, S. Suryasentana, P. Shi","doi":"10.1111/mice.13396","DOIUrl":"https://doi.org/10.1111/mice.13396","url":null,"abstract":"Accurate soil stratification is essential for geotechnical engineering design. Owing to its effectiveness and efficiency, the cone penetration test (CPT) has been widely applied for subsurface stratigraphy, which relies heavily on empiricism for correlations to soil type. Recently, deep learning techniques have shown great promise in learning the relationship between CPT data and soil boundaries automatically. However, the segmentation of soil boundaries is fraught with model and measurement uncertainty. This paper introduces an uncertainty-guided U((-Net (UGU-Net) for improved soil boundary segmentation. The UGU-Net consists of three parts: (a) a Bayesian U-Net to predict a pixel-level uncertainty map, (b) reinforcement of original labels on the basis of the predicted uncertainty map, and (c) a traditional deterministic U-Net, which is applied to the reinforced labels for final soil boundary segmentation. The results show that the proposed UGU-Net outperforms the existing methods in terms of both high accuracy and low uncertainty. A sensitivity study is also conducted to explore the influence of key model parameters on model performance. The proposed method is validated by comparing the predicted subsurface profile with benchmark profiles. The code for this project is available at github.com/Xiaoqi-Zhou-suda/UGU-Net.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"52 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142793160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Danilo D'Angela, Gennaro Magliulo, Chiara Di Salvatore, Edoardo Cosenza
The structural response of reinforced concrete dapped-end beams is simulated through finite element analysis. The case study consists in experimental tests performed in the framework of an Italian research project on bridges. The study assesses both the local and global behavior of the beam and characterizes the damage patterns. A blind prediction is initially performed inputting the main basic material and geometrical properties of the specimen. Further models are developed by varying several structural parameters and modeling/analysis features, assessing their influence on the structural capacity and response of the beams. The blind model yielded relatively accurate behavior and capacity estimations. Additionally, the modeling is enhanced by accounting for experimental data. Technical and operative guidelines for implementing the numerical analysis of dapped-end beams are finally provided, in light of the critical assessment of the modeling and analysis results.
{"title":"Computational modeling of reinforced concrete dapped-end beams","authors":"Danilo D'Angela, Gennaro Magliulo, Chiara Di Salvatore, Edoardo Cosenza","doi":"10.1111/mice.13390","DOIUrl":"https://doi.org/10.1111/mice.13390","url":null,"abstract":"The structural response of reinforced concrete dapped-end beams is simulated through finite element analysis. The case study consists in experimental tests performed in the framework of an Italian research project on bridges. The study assesses both the local and global behavior of the beam and characterizes the damage patterns. A blind prediction is initially performed inputting the main basic material and geometrical properties of the specimen. Further models are developed by varying several structural parameters and modeling/analysis features, assessing their influence on the structural capacity and response of the beams. The blind model yielded relatively accurate behavior and capacity estimations. Additionally, the modeling is enhanced by accounting for experimental data. Technical and operative guidelines for implementing the numerical analysis of dapped-end beams are finally provided, in light of the critical assessment of the modeling and analysis results.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"66 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142763340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The cover image is based on the Article Crack pattern-based machine learning prediction of residual drift capacity in damaged masonry walls by Mauricio Pereira et al., https://doi.org/10.1111/mice.13212.
{"title":"Cover Image, Volume 39, Issue 24","authors":"","doi":"10.1111/mice.13388","DOIUrl":"https://doi.org/10.1111/mice.13388","url":null,"abstract":"<p><b>The cover image</b> is based on the Article <i>Crack pattern-based machine learning prediction of residual drift capacity in damaged masonry\u0000walls</i> by Mauricio Pereira et al., https://doi.org/10.1111/mice.13212.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure>\u0000 </p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"39 24","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.13388","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142762255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The cover image is based on the Article Smartphone-based high durable strain sensor with sub-pixel-level accuracy and adjustable camera position by Pengfei Wu et al., https://doi.org/10.1111/mice.13383.
{"title":"Cover Image, Volume 39, Issue 24","authors":"","doi":"10.1111/mice.13389","DOIUrl":"https://doi.org/10.1111/mice.13389","url":null,"abstract":"<p><b>The cover image</b> is based on the Article <i>Smartphone-based high durable strain sensor with sub-pixel-level accuracy and adjustable camera position</i> by Pengfei Wu et al., https://doi.org/10.1111/mice.13383.\u0000\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure>\u0000 </p>","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"39 24","pages":""},"PeriodicalIF":8.5,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.13389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142762256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yingbo Zhu, Dongge Jia, John C. Brigham, Alessandro Fascetti
A novel coupled mechanical and mass transport lattice discrete particle model is developed to quantitatively assess the impact of cracks on the mass transport properties in concrete members subjected to short‐ and long‐term loading conditions. In the developed approach, two sets of dual lattice networks are generated: one to resolve the mechanical response and another for mass transport analysis. The cracks simulated by the mechanical lattice are mapped onto the transport elements to investigate the effect of cracks on the global transport properties in concrete members. A new quantitative relationship is proposed for the estimation of the diffusion coefficient based on local crack information, and the developed model is capable of describing both convection and diffusion mechanisms. Moreover, creep behavior is incorporated to account for the influence of cracks induced by long‐term loading conditions. Numerical results, in the form of dynamic changes in cumulative water and chloride contents in concrete members under tension, compression, and bending with various stress levels show remarkable accuracy when compared to available experimental observations. The developed model provides an effective means for incorporating mesoscale information in simulations of water and chloride transport in concrete members under varying short‐ and long‐term loading conditions.
{"title":"Coupled lattice discrete particle model for the simulation of water and chloride transport in cracked concrete members","authors":"Yingbo Zhu, Dongge Jia, John C. Brigham, Alessandro Fascetti","doi":"10.1111/mice.13385","DOIUrl":"https://doi.org/10.1111/mice.13385","url":null,"abstract":"A novel coupled mechanical and mass transport lattice discrete particle model is developed to quantitatively assess the impact of cracks on the mass transport properties in concrete members subjected to short‐ and long‐term loading conditions. In the developed approach, two sets of dual lattice networks are generated: one to resolve the mechanical response and another for mass transport analysis. The cracks simulated by the mechanical lattice are mapped onto the transport elements to investigate the effect of cracks on the global transport properties in concrete members. A new quantitative relationship is proposed for the estimation of the diffusion coefficient based on local crack information, and the developed model is capable of describing both convection and diffusion mechanisms. Moreover, creep behavior is incorporated to account for the influence of cracks induced by long‐term loading conditions. Numerical results, in the form of dynamic changes in cumulative water and chloride contents in concrete members under tension, compression, and bending with various stress levels show remarkable accuracy when compared to available experimental observations. The developed model provides an effective means for incorporating mesoscale information in simulations of water and chloride transport in concrete members under varying short‐ and long‐term loading conditions.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"3 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142756118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Miguel Cid Montoya, Ashutosh Mishra, Sumit Verma, Omar A. Mures, Carlos E. Rubio‐Medrano
Aero‐structural shape design and optimization of bridge decks rely on accurately estimating their self‐excited aeroelastic forces within the design domain. The inherent nonlinear features of bluff body aerodynamics and the high cost of wind tunnel tests and computational fluid dynamics (CFD) simulations make their emulation as a function of deck shape and reduced velocity challenging. State‐of‐the‐art methods address deck shape tailoring by interpolating discrete values of integrated flutter derivatives (FDs) in the frequency domain. Nevertheless, more sophisticated strategies can improve surrogate accuracy and potentially reduce the required number of samples. We propose a time domain emulation strategy harnessing temporal fusion transformers (TFTs) to predict the self‐excited forces time series before their integration into FDs. Emulating aeroelastic forces in the time domain permits the inclusion of time‐series amplitudes, frequencies, phases, and other properties in the training process, enabling a more solid learning strategy that is independent of the self‐excited forces modeling order and the inherent loss of information during the identification of FDs. TFTs' long‐ and short‐term context awareness, combined with their interpretability and enhanced ability to deal with static and time‐dependent covariates, make them an ideal choice for predicting unseen aeroelastic forces time series. The proposed TFT‐based metamodel offers a powerful technique for drastically improving the accuracy and versatility of wind‐resistant design optimization frameworks.
{"title":"Aeroelastic force prediction via temporal fusion transformers","authors":"Miguel Cid Montoya, Ashutosh Mishra, Sumit Verma, Omar A. Mures, Carlos E. Rubio‐Medrano","doi":"10.1111/mice.13381","DOIUrl":"https://doi.org/10.1111/mice.13381","url":null,"abstract":"Aero‐structural shape design and optimization of bridge decks rely on accurately estimating their self‐excited aeroelastic forces within the design domain. The inherent nonlinear features of bluff body aerodynamics and the high cost of wind tunnel tests and computational fluid dynamics (CFD) simulations make their emulation as a function of deck shape and reduced velocity challenging. State‐of‐the‐art methods address deck shape tailoring by interpolating discrete values of integrated flutter derivatives (FDs) in the frequency domain. Nevertheless, more sophisticated strategies can improve surrogate accuracy and potentially reduce the required number of samples. We propose a time domain emulation strategy harnessing temporal fusion transformers (TFTs) to predict the self‐excited forces time series before their integration into FDs. Emulating aeroelastic forces in the time domain permits the inclusion of time‐series amplitudes, frequencies, phases, and other properties in the training process, enabling a more solid learning strategy that is independent of the self‐excited forces modeling order and the inherent loss of information during the identification of FDs. TFTs' long‐ and short‐term context awareness, combined with their interpretability and enhanced ability to deal with static and time‐dependent covariates, make them an ideal choice for predicting unseen aeroelastic forces time series. The proposed TFT‐based metamodel offers a powerful technique for drastically improving the accuracy and versatility of wind‐resistant design optimization frameworks.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"12 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142753007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Long‐span suspension bridges are significantly susceptible to windstorm‐induced vibrations, leading to critical challenges of field measurements along with multicollinearity and nonlinearity between wind features and bridge dynamic responses. To address these issues, this article proposes an innovative machine learning‐assisted predictive method by integrating a predictor selector developed from regularized neighborhood components analysis and kernel regression modeling through a regularized support vector machine adjusted by Bayesian hyperparameter optimization. The crux of the proposed method lies in advanced machine learning algorithms including metric learning, kernel learning, and hybrid learning integrated in a regularized framework. Utilizing the Hardanger Bridge subjected to different windstorms, the performance of the proposed method is validated and then compared with state‐of‐the‐art regression techniques. Results highlight the effectiveness and practicality of the proposed method with the minimum and maximum R‐squared rates of 89% and 98%, respectively. It also surpasses the state‐of‐the‐art regression techniques in predicting bridge dynamics under different windstorms.
大跨度悬索桥非常容易受到暴风引起的振动的影响，导致现场测量面临严峻挑战，同时风力特征与桥梁动态响应之间存在多重共线性和非线性。为解决这些问题，本文提出了一种创新的机器学习辅助预测方法，即通过贝叶斯超参数优化调整的正则化支持向量机，将正则化邻域成分分析和核回归建模开发的预测选择器整合在一起。所提方法的关键在于先进的机器学习算法，包括集成在正则化框架中的度量学习、核学习和混合学习。利用哈当厄尔大桥遭受的不同风灾，对所提方法的性能进行了验证，然后与最先进的回归技术进行了比较。结果凸显了所提方法的有效性和实用性，最小和最大 R 平方率分别为 89% 和 98%。在预测不同风灾下的桥梁动态方面，该方法也超越了最先进的回归技术。
{"title":"Machine learning‐aided prediction of windstorm‐induced vibration responses of long‐span suspension bridges","authors":"Alireza Entezami, Hassan Sarmadi","doi":"10.1111/mice.13387","DOIUrl":"https://doi.org/10.1111/mice.13387","url":null,"abstract":"Long‐span suspension bridges are significantly susceptible to windstorm‐induced vibrations, leading to critical challenges of field measurements along with multicollinearity and nonlinearity between wind features and bridge dynamic responses. To address these issues, this article proposes an innovative machine learning‐assisted predictive method by integrating a predictor selector developed from regularized neighborhood components analysis and kernel regression modeling through a regularized support vector machine adjusted by Bayesian hyperparameter optimization. The crux of the proposed method lies in advanced machine learning algorithms including metric learning, kernel learning, and hybrid learning integrated in a regularized framework. Utilizing the Hardanger Bridge subjected to different windstorms, the performance of the proposed method is validated and then compared with state‐of‐the‐art regression techniques. Results highlight the effectiveness and practicality of the proposed method with the minimum and maximum R‐squared rates of 89% and 98%, respectively. It also surpasses the state‐of‐the‐art regression techniques in predicting bridge dynamics under different windstorms.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"8 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：