SummaryPrecise estimation of the shear strength of concrete‐filled steel tubes (CFSTs) is a crucial requirement for the design of these members. The existing design codes and empirical equations are inconsistent in predicting the shear strength of these members. This paper provides a data‐driven approach for the shear strength estimation of circular CFSTs. For this purpose, the authors evaluated and compared the performance of nine machine learning (ML) methods, namely linear regression, decision tree (DT), k‐nearest neighbors (KNN), support vector regression (SVR), random forest (RF), bagging regression (BR), adaptive boosting (AdaBoost), gradient boosting regression tree (GBRT), and extreme gradient boosting (XGBoost) in estimating the shear strength of CFSTs on an experimental database compiled from the results of 230 shear tests on CFSTs in the literature. For each model, hyperparameter tuning was performed by conducting a grid search in combination with k‐fold cross‐validation (CV). Comparing the nine methods in terms of several performance measures showed that the XGBoost model was the most accurate in predicting the shear strength of CFSTs. This model also showed superior accuracy in predicting the shear strength of CFSTs when compared to the formulas provided in design codes and the existing empirical equations. The Shapley Additive exPlanations (SHAP) technique was also used to interpret the results of the XGBoost model. Using SHAP, the features with the greatest impact on the shear strength of CFSTs were found to be the cross‐sectional area of the steel tube, the axial load ratio, and the shear span ratio, in that order.
{"title":"Interpretable machine learning model for shear strength estimation of circular concrete‐filled steel tubes","authors":"Ali Mansouri, Maryam Mansouri, Sujith Mangalathu","doi":"10.1002/tal.2111","DOIUrl":"https://doi.org/10.1002/tal.2111","url":null,"abstract":"SummaryPrecise estimation of the shear strength of concrete‐filled steel tubes (CFSTs) is a crucial requirement for the design of these members. The existing design codes and empirical equations are inconsistent in predicting the shear strength of these members. This paper provides a data‐driven approach for the shear strength estimation of circular CFSTs. For this purpose, the authors evaluated and compared the performance of nine machine learning (ML) methods, namely linear regression, decision tree (DT), k‐nearest neighbors (KNN), support vector regression (SVR), random forest (RF), bagging regression (BR), adaptive boosting (AdaBoost), gradient boosting regression tree (GBRT), and extreme gradient boosting (XGBoost) in estimating the shear strength of CFSTs on an experimental database compiled from the results of 230 shear tests on CFSTs in the literature. For each model, hyperparameter tuning was performed by conducting a grid search in combination with k‐fold cross‐validation (CV). Comparing the nine methods in terms of several performance measures showed that the XGBoost model was the most accurate in predicting the shear strength of CFSTs. This model also showed superior accuracy in predicting the shear strength of CFSTs when compared to the formulas provided in design codes and the existing empirical equations. The Shapley Additive exPlanations (SHAP) technique was also used to interpret the results of the XGBoost model. Using SHAP, the features with the greatest impact on the shear strength of CFSTs were found to be the cross‐sectional area of the steel tube, the axial load ratio, and the shear span ratio, in that order.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140886282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SummaryThis study investigates the impact of different positions of two limbs on the structural response of a rectangular building model to wind forces. The building's geometry assumes Z and + shapes based on specific limb configurations. Computational fluid dynamics (CFD) simulations are performed to quantify wind‐induced pressures, resulting in wind force coefficients. These coefficients are used to develop predictive machine learning models through Gene Expression Programming, Group Method of Data Handling‐combinatorial (GMDH‐Combi), Model Tree, and Artificial Neural Network (ANN) techniques. The ANN analysis explores various combinations of training algorithms, adaptation functions, activation functions, and performance functions to enhance model accuracy. Among these, the Levenberg–Marquardt (LM) with gradient descent with momentum (GDM) adaptation function and sigmoid activation function exhibit superior performance with high R‐squared values. These predictive models are then employed for a comprehensive comparative assessment of the maximum wind force coefficient (CF, max) concerning different limb positions and angles of attack (AOA). For CF, max vs Limb position, variations of limb position are examined for most critical cases of AOA. Similarly, the study of CF, max vs AOA involves an exhaustive investigation into the variation of AOA for the building with the worst limb position. The analysis reveals that changes in AOA have a more pronounced effect on CF, max compared to alterations in limb position. Interestingly, within the AOA range of 1.5 to 2.5, the CF, max consistently reaches a minimum across all models. However, the relationship between CF, max and the critical structural parameter ‘S' (representing limb position) remains less conclusive for the most significant AOAs.
{"title":"Machine learning‐based wind‐induced response analysis in rectangular building models with limbs","authors":"Prasenjit Sanyal, Rajdip Paul, Sujit Kumar Dalui","doi":"10.1002/tal.2116","DOIUrl":"https://doi.org/10.1002/tal.2116","url":null,"abstract":"SummaryThis study investigates the impact of different positions of two limbs on the structural response of a rectangular building model to wind forces. The building's geometry assumes Z and + shapes based on specific limb configurations. Computational fluid dynamics (CFD) simulations are performed to quantify wind‐induced pressures, resulting in wind force coefficients. These coefficients are used to develop predictive machine learning models through Gene Expression Programming, Group Method of Data Handling‐combinatorial (GMDH‐Combi), Model Tree, and Artificial Neural Network (ANN) techniques. The ANN analysis explores various combinations of training algorithms, adaptation functions, activation functions, and performance functions to enhance model accuracy. Among these, the Levenberg–Marquardt (LM) with gradient descent with momentum (GDM) adaptation function and sigmoid activation function exhibit superior performance with high R‐squared values. These predictive models are then employed for a comprehensive comparative assessment of the maximum wind force coefficient (C<jats:sub>F, max</jats:sub>) concerning different limb positions and angles of attack (AOA). For C<jats:sub>F, max</jats:sub> vs Limb position, variations of limb position are examined for most critical cases of AOA. Similarly, the study of C<jats:sub>F, max</jats:sub> vs AOA involves an exhaustive investigation into the variation of AOA for the building with the worst limb position. The analysis reveals that changes in AOA have a more pronounced effect on C<jats:sub>F, max</jats:sub> compared to alterations in limb position. Interestingly, within the AOA range of 1.5 to 2.5, the C<jats:sub>F, max</jats:sub> consistently reaches a minimum across all models. However, the relationship between C<jats:sub>F, max</jats:sub> and the critical structural parameter ‘S' (representing limb position) remains less conclusive for the most significant AOAs.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140840048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ziluo Yao, Sheng Jiang, Shuo Wang, Jingjing Wang, Hai Liu, Yasutaka Narazaki, Jie Cui, Billie F. Spencer
SummaryCracks can develop in high‐rise buildings because of long‐term environmental changes and extreme loading events such as strong winds or earthquakes. Although deep learning‐based identification methods can efficiently identify cracks, the accuracy of crack identification in high‐rise buildings needs to be improved due to the lack of crack datasets specifically related to high‐rise structures. Moreover, the number of available images of cracks in high‐rise is limited. To this end, this paper establishes an intelligent crack identification method based on a photorealistic synthetic modeling technique. First, a computer graphics (CG) model of a high‐rise building with assumed damage is constructed. Subsequently, the CG model is utilized to generate a dataset that includes photorealistic images of the high‐rise building as well as corresponding labels for various components and types of damage. The generated dataset is then used to train a DeepLabv3 + neural network for structural component and damage identification, followed by validation by employing images of both synthetic and full‐scale high‐rise buildings. The trained network can accurately identify different components in images of the full‐scale, high‐rise building and identify cracks that are intentionally synthesized in those images. The results show that the synthetic dataset generated by the CG model not only allows for fast and efficient labeling for the purpose of neural network training but also outperforms methods that do not consider any application‐specific context in crack identification.
{"title":"Intelligent crack identification method for high‐rise buildings aided by synthetic environments","authors":"Ziluo Yao, Sheng Jiang, Shuo Wang, Jingjing Wang, Hai Liu, Yasutaka Narazaki, Jie Cui, Billie F. Spencer","doi":"10.1002/tal.2117","DOIUrl":"https://doi.org/10.1002/tal.2117","url":null,"abstract":"SummaryCracks can develop in high‐rise buildings because of long‐term environmental changes and extreme loading events such as strong winds or earthquakes. Although deep learning‐based identification methods can efficiently identify cracks, the accuracy of crack identification in high‐rise buildings needs to be improved due to the lack of crack datasets specifically related to high‐rise structures. Moreover, the number of available images of cracks in high‐rise is limited. To this end, this paper establishes an intelligent crack identification method based on a photorealistic synthetic modeling technique. First, a computer graphics (CG) model of a high‐rise building with assumed damage is constructed. Subsequently, the CG model is utilized to generate a dataset that includes photorealistic images of the high‐rise building as well as corresponding labels for various components and types of damage. The generated dataset is then used to train a DeepLabv3 + neural network for structural component and damage identification, followed by validation by employing images of both synthetic and full‐scale high‐rise buildings. The trained network can accurately identify different components in images of the full‐scale, high‐rise building and identify cracks that are intentionally synthesized in those images. The results show that the synthetic dataset generated by the CG model not only allows for fast and efficient labeling for the purpose of neural network training but also outperforms methods that do not consider any application‐specific context in crack identification.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140839973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SummaryThe columned‐supported reinforced concrete silo models with different filling conditions considering soil‐structure dynamic interaction (SSI) are established based on the finite element program ANSYS to thoroughly investigate the complex interaction mechanism of the soil–pile–silo structure with granular solid. The dynamic characteristics and seismic responses of the SSI system and fixed‐base condition are analyzed and compared when the filling conditions are empty‐filled state, half‐filled state and full‐filled state. The numerical results reveal that the SSI effect reduces the seismic acceleration response of columned‐supported silos effectively. However, in terms of displacement, the SSI effect often amplifies the relative deformation of the supporting column and the cylindrical silos. Furthermore, the SSI effect often increases the relative dynamic lateral pressure of the storage material in the half‐filled silo condition. In the full‐filled silo condition, the relative dynamic lateral pressure at the top and bottom of the storage material is increased by the SSI effect; while it is decreased in the middle part of the granular solid, demonstrating that the SSI effect could change and increase the seismic responses of the silo structure in certain areas. Therefore, the investigation provides a comprehensive insight into the interaction mechanism of the pile–soil–silo structure with different filling conditions.
{"title":"Dynamic responses of reinforced concrete silo considering pile–soil‐structure–granular solid interaction","authors":"Jinping Yang, Kaixin Sun, Meng Gao, Peizhen Li","doi":"10.1002/tal.2118","DOIUrl":"https://doi.org/10.1002/tal.2118","url":null,"abstract":"SummaryThe columned‐supported reinforced concrete silo models with different filling conditions considering soil‐structure dynamic interaction (SSI) are established based on the finite element program ANSYS to thoroughly investigate the complex interaction mechanism of the soil–pile–silo structure with granular solid. The dynamic characteristics and seismic responses of the SSI system and fixed‐base condition are analyzed and compared when the filling conditions are empty‐filled state, half‐filled state and full‐filled state. The numerical results reveal that the SSI effect reduces the seismic acceleration response of columned‐supported silos effectively. However, in terms of displacement, the SSI effect often amplifies the relative deformation of the supporting column and the cylindrical silos. Furthermore, the SSI effect often increases the relative dynamic lateral pressure of the storage material in the half‐filled silo condition. In the full‐filled silo condition, the relative dynamic lateral pressure at the top and bottom of the storage material is increased by the SSI effect; while it is decreased in the middle part of the granular solid, demonstrating that the SSI effect could change and increase the seismic responses of the silo structure in certain areas. Therefore, the investigation provides a comprehensive insight into the interaction mechanism of the pile–soil–silo structure with different filling conditions.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140840599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SummaryThe regular operation of the subway negatively impacts the occupants of super high‐rise multi‐tower buildings located on over‐depot (MBLO), causing undesirable vibrations. To save engineers time and computational cost, an improved one‐dimensional impedance model of super high‐rise MBLO is established to predict undesirable vibration in the design phase and devise measures to enhance human comfort. The stiffness factor of the thick plate of a large chassis is introduced, and the impedance relationships of coupled beam and floor based on the equivalence of mass and bending stiffness are considered for an improved one‐dimensional impedance model. The vibration response of multi‐story buildings and super high‐rise MBLO is predicted by an improved one‐dimensional impedance model and compared with field measurements and experimental results, respectively. The results show that the vibration transmission law of super high‐rise MBLO can be more accurately predicted when the stiffness factor of thick plates and the impedance relationships of coupled beam and floor are adopted in an improved one‐dimensional impedance model of super high‐rise MBLO.
{"title":"Subway‐induced floor vibration predictions in super high‐rise multi‐tower building located on over‐depot based on one‐dimensional impedance model","authors":"Can Mei, Dayang Wang, Yongshan Zhang","doi":"10.1002/tal.2126","DOIUrl":"https://doi.org/10.1002/tal.2126","url":null,"abstract":"SummaryThe regular operation of the subway negatively impacts the occupants of super high‐rise multi‐tower buildings located on over‐depot (MBLO), causing undesirable vibrations. To save engineers time and computational cost, an improved one‐dimensional impedance model of super high‐rise MBLO is established to predict undesirable vibration in the design phase and devise measures to enhance human comfort. The stiffness factor of the thick plate of a large chassis is introduced, and the impedance relationships of coupled beam and floor based on the equivalence of mass and bending stiffness are considered for an improved one‐dimensional impedance model. The vibration response of multi‐story buildings and super high‐rise MBLO is predicted by an improved one‐dimensional impedance model and compared with field measurements and experimental results, respectively. The results show that the vibration transmission law of super high‐rise MBLO can be more accurately predicted when the stiffness factor of thick plates and the impedance relationships of coupled beam and floor are adopted in an improved one‐dimensional impedance model of super high‐rise MBLO.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140839688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Acceleration measurements are often used for model updating of civil engineering structures, especially in the case of seismic monitoring. It is yet unclear if accelerations alone would generate an accurate and robust finite‐element (FE) model. This study examines this notion and analyzes the possibility of using other vibration monitoring data for model updating of shear‐wall tall buildings. This study compares the accuracy and robustness of the FE models being optimized via accelerations, roof displacement, wall rotations, interstory drift ratios, and the linear combination of these measurements. A numerical case study is analyzed using Timoshenko beams for modeling the lateral vibration of a benchmark 42‐story building under seismic excitations. Results show that the acceleration response of the examined building is mostly governed by its higher vibration modes. Depending on the characteristics of ground motions, using accelerations alone may generate an FE model biased towards higher‐order modes without effectively capturing the lower‐order modes. For instance, the first modal frequency of the updated FE model could be 12.0% lower than the true value, and the reconstructed displacement and rotation responses are noticeably inaccurate. Employing multi‐source monitoring data for model updating, for example, the combinations of roof displacement and acceleration measurements, could reduce the normalized root‐mean‐square errors in displacements by more than 70%. This study also quantifies the robustness of the FE model under various measurement noise levels and 50 pairs of earthquake records. Finally, the effects of multi‐source data on FE model updating are validated via experiments on a 7‐story shear wall building. Analysis reveals that a more accurate and robust FE model can be determined via a combination of accelerations and top displacement than via acceleration alone.
加速度测量通常用于土木工程结构的模型更新，尤其是在地震监测情况下。但目前还不清楚仅靠加速度是否就能生成准确、稳健的有限元（FE）模型。本研究探讨了这一概念，并分析了使用其他振动监测数据更新剪力墙高层建筑模型的可能性。本研究比较了通过加速度、屋顶位移、墙体旋转、层间漂移比以及这些测量数据的线性组合进行优化的有限元模型的准确性和稳健性。一项数值案例研究使用 Timoshenko 梁对地震激励下 42 层基准建筑的横向振动进行了建模分析。结果表明，受测建筑的加速度响应主要由其较高的振动模式控制。根据地面运动的特点，仅使用加速度可能会生成偏向高阶模态的有限元模型，而无法有效捕捉低阶模态。例如，更新后的 FE 模型的第一模态频率可能比真实值低 12.0%，重建的位移和旋转响应也明显不准确。采用多源监测数据进行模型更新，例如屋顶位移和加速度测量组合，可将位移的归一化均方根误差降低 70% 以上。本研究还量化了 FE 模型在不同测量噪声水平和 50 对地震记录下的稳健性。最后，通过对一栋 7 层剪力墙建筑的实验，验证了多源数据对 FE 模型更新的影响。分析表明，通过加速度和顶部位移的组合确定的 FE 模型比仅通过加速度确定的模型更准确、更稳健。
{"title":"Model updating of a shear‐wall tall building using various vibration monitoring data: Accuracy and robustness","authors":"Jiazeng Shan, Changhao Zhuang, Xi Chao, C. Loong","doi":"10.1002/tal.2114","DOIUrl":"https://doi.org/10.1002/tal.2114","url":null,"abstract":"Acceleration measurements are often used for model updating of civil engineering structures, especially in the case of seismic monitoring. It is yet unclear if accelerations alone would generate an accurate and robust finite‐element (FE) model. This study examines this notion and analyzes the possibility of using other vibration monitoring data for model updating of shear‐wall tall buildings. This study compares the accuracy and robustness of the FE models being optimized via accelerations, roof displacement, wall rotations, interstory drift ratios, and the linear combination of these measurements. A numerical case study is analyzed using Timoshenko beams for modeling the lateral vibration of a benchmark 42‐story building under seismic excitations. Results show that the acceleration response of the examined building is mostly governed by its higher vibration modes. Depending on the characteristics of ground motions, using accelerations alone may generate an FE model biased towards higher‐order modes without effectively capturing the lower‐order modes. For instance, the first modal frequency of the updated FE model could be 12.0% lower than the true value, and the reconstructed displacement and rotation responses are noticeably inaccurate. Employing multi‐source monitoring data for model updating, for example, the combinations of roof displacement and acceleration measurements, could reduce the normalized root‐mean‐square errors in displacements by more than 70%. This study also quantifies the robustness of the FE model under various measurement noise levels and 50 pairs of earthquake records. Finally, the effects of multi‐source data on FE model updating are validated via experiments on a 7‐story shear wall building. Analysis reveals that a more accurate and robust FE model can be determined via a combination of accelerations and top displacement than via acceleration alone.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140661617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A three‐dimensional refined numerical simulation model of a corrugated steel–concrete slab composite structure under contact explosion load was established by the finite element model and smoothed particle hydrodynamics(FEM‐SPH) coupling method to explore the anti‐knock properties of corrugated steel reinforced concrete slabs with different angles. The effects of corrugated steel angle on the dynamic response, damage evolution characteristics, damage mode, anti‐knock property, and propagation mechanism of the shock wave in the composite structure were investigated, and the damage prediction and anti‐knock property evaluation of the composite structure were carried out. The results show that the simulation results of the mid‐span displacement of the corrugated steel are consistent with the experimental results, and the maximum error is 2.3%, which verifies the effectiveness of the contact explosion simulation process. The mid‐span displacement, peak stress, acceleration at the center point, and energy absorption value of 90° corrugated steel are 17.9%, 70.5%, 88.6%, and 59.4% lower than those of 30° corrugated steel. The damage range of the composite structure gradually decreases with increasing angle of the corrugated steel. The failure volume of the concrete slab reinforced by corrugated steel with different angles decreases with increasing angle of the corrugated steel, and the energy absorption value of the composite structure increases with increasing of angle of the corrugated steel, mainly because the corrugated steel increases the number of reflections of the stress wave. The research results can provide a theoretical basis for the application of composite structures in the field of structural anti‐explosion protection.
{"title":"Effect of corrugated steel angle on the damage characteristics and anti‐explosion performance of corrugated steel–concrete composite structures","authors":"Kelei Cao, Qiaofeng Fu, Jianwei Zhang, Changxing Tang, Jinlin Huang, Chao Wang, Weifeng Bai","doi":"10.1002/tal.2112","DOIUrl":"https://doi.org/10.1002/tal.2112","url":null,"abstract":"A three‐dimensional refined numerical simulation model of a corrugated steel–concrete slab composite structure under contact explosion load was established by the finite element model and smoothed particle hydrodynamics(FEM‐SPH) coupling method to explore the anti‐knock properties of corrugated steel reinforced concrete slabs with different angles. The effects of corrugated steel angle on the dynamic response, damage evolution characteristics, damage mode, anti‐knock property, and propagation mechanism of the shock wave in the composite structure were investigated, and the damage prediction and anti‐knock property evaluation of the composite structure were carried out. The results show that the simulation results of the mid‐span displacement of the corrugated steel are consistent with the experimental results, and the maximum error is 2.3%, which verifies the effectiveness of the contact explosion simulation process. The mid‐span displacement, peak stress, acceleration at the center point, and energy absorption value of 90° corrugated steel are 17.9%, 70.5%, 88.6%, and 59.4% lower than those of 30° corrugated steel. The damage range of the composite structure gradually decreases with increasing angle of the corrugated steel. The failure volume of the concrete slab reinforced by corrugated steel with different angles decreases with increasing angle of the corrugated steel, and the energy absorption value of the composite structure increases with increasing of angle of the corrugated steel, mainly because the corrugated steel increases the number of reflections of the stress wave. The research results can provide a theoretical basis for the application of composite structures in the field of structural anti‐explosion protection.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140660062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xianwen Zhang, Zifa Wang, Dengke Zhao, Jianming Wang, Zhaoyan Li
Structural damage identification is a major task in structural health monitoring. Machine learning and deep learning algorithms have been widely applied in the research of structural damage identification. Supervised algorithms require expert labeling, making it difficult to implement in engineering applications. Unsupervised structural damage identification algorithms are generally divided into two parts: damage‐sensitive factor extraction and damage determination. Existing algorithms all perform these two steps separately. This paper proposes a damage identification method combining covariance matrix and improved deep embedding clustering network (IDEC). IDEC can perform damage‐sensitive factor extraction and damage determination operations at the same time. The covariance matrix that introduces delay information contains rich damage features, and the combination of the two has been proven to effectively mine the damage‐sensitive feature space. After network hyperparameter optimization via Bayesian optimization, the proposed method is applied to the damage identification and quantification using real bridge acceleration response data under vehicle load. The results show that this method can identify structural damage with an accuracy of up to 97% with better performance than existing technologies, and it also has great performance in identifying small damages. The proposed method is expected to increase the damage identification accuracy if applied in engineering practice.
{"title":"Unsupervised structural damage identification based on covariance matrix and deep clustering","authors":"Xianwen Zhang, Zifa Wang, Dengke Zhao, Jianming Wang, Zhaoyan Li","doi":"10.1002/tal.2115","DOIUrl":"https://doi.org/10.1002/tal.2115","url":null,"abstract":"Structural damage identification is a major task in structural health monitoring. Machine learning and deep learning algorithms have been widely applied in the research of structural damage identification. Supervised algorithms require expert labeling, making it difficult to implement in engineering applications. Unsupervised structural damage identification algorithms are generally divided into two parts: damage‐sensitive factor extraction and damage determination. Existing algorithms all perform these two steps separately. This paper proposes a damage identification method combining covariance matrix and improved deep embedding clustering network (IDEC). IDEC can perform damage‐sensitive factor extraction and damage determination operations at the same time. The covariance matrix that introduces delay information contains rich damage features, and the combination of the two has been proven to effectively mine the damage‐sensitive feature space. After network hyperparameter optimization via Bayesian optimization, the proposed method is applied to the damage identification and quantification using real bridge acceleration response data under vehicle load. The results show that this method can identify structural damage with an accuracy of up to 97% with better performance than existing technologies, and it also has great performance in identifying small damages. The proposed method is expected to increase the damage identification accuracy if applied in engineering practice.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140670995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SummaryIn this study, a viscoelastic damper (VED) employing an additional amplification device is proposed to enhance the stiffness as well as energy dissipation. The mechanical model of the amplified viscoelastic damper (AVED) is developed and the amplification efficiency is explored. The mechanical behaviors of AVED and the traditional VED are experimentally investigated. By adopting a leverage system, the stiffness and the dissipated energy of AVED are significantly improved and the amplification factors are confirmed. Meanwhile, the seismic responses and structural damages are addressed through a numerical study on a frame attached to the AVEDs and VEDs. The AVED reinforced building employing fewer dampers has close seismic responses compared with VED reinforced building. Furthermore, the installation of AVEDs significantly reduces the risk of structural damage.
摘要 在本研究中，提出了一种采用附加放大装置的粘弹性阻尼器（VED），以增强刚度和能量耗散。建立了放大粘弹性阻尼器（AVED）的机械模型，并探讨了放大效率。实验研究了 AVED 和传统 VED 的力学行为。通过采用杠杆系统，AVED 的刚度和耗能得到了显著改善，放大系数也得到了证实。同时，通过对连接 AVED 和 VED 的框架进行数值研究，探讨了地震响应和结构破坏问题。与 VED 加固建筑相比，采用较少阻尼器的 AVED 加固建筑具有接近的地震响应。此外，AVED 的安装大大降低了结构损坏的风险。
{"title":"Experimental study on viscoelastic damper with amplified mechanism and seismic mitigation evaluation","authors":"Hao Xu, Sufan Jia, Feng Shang, Wenfu He","doi":"10.1002/tal.2113","DOIUrl":"https://doi.org/10.1002/tal.2113","url":null,"abstract":"SummaryIn this study, a viscoelastic damper (VED) employing an additional amplification device is proposed to enhance the stiffness as well as energy dissipation. The mechanical model of the amplified viscoelastic damper (AVED) is developed and the amplification efficiency is explored. The mechanical behaviors of AVED and the traditional VED are experimentally investigated. By adopting a leverage system, the stiffness and the dissipated energy of AVED are significantly improved and the amplification factors are confirmed. Meanwhile, the seismic responses and structural damages are addressed through a numerical study on a frame attached to the AVEDs and VEDs. The AVED reinforced building employing fewer dampers has close seismic responses compared with VED reinforced building. Furthermore, the installation of AVEDs significantly reduces the risk of structural damage.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140613385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
SummaryCurved structural elements can extensively be employed in engineering applications, to which structural designers and architects can resort in order to cope with the existing structural limitations and architectural challenges. In this regard, the current study is an attempt to provide insight into the overall performance of curved reinforced concrete (RC) shear walls (CRCSWs) due to the gaps existing in the literature. In order to fulfill this purpose, a CRCSW with general cross‐section has been considered subjected to the applied bi‐lateral and axial loadings. Equivalent non‐rectangular T‐, U‐, and L‐shaped sections are then introduced in lieu of a curved section. Thereafter, the stress and displacement distributions of CRCSWs have been analytically established. In order to highlight the structural merits of CRCSWs, a comparative study is performed based on the six non‐dimensional parameters defined in this study. According to the comparative study conducted between the CRCSWs and the equivalent non‐rectangular flanged walls, unlike latter wall types, the shear‐lag effects do not make serious issues for the performance of CRCSWs. Furthermore, to make a more realistic judgment on the response of CRCSWs, a numerical investigation has been carried out utilizing the finite element (FE) software Abaqus. On the strength of the data obtained from the FE simulation of 90 CRCSWs in three categories of short, squat, and slender walls, a regression model has been established, which is advantageous in that it can supply a means for the initial estimation of the shear strength of CRCSWs. The average R‐factor of 0.88 indicates that the established formulations can potentially well predict the shear strength of CRCSWs. The findings of this study divulge that, in addition to the inherent aesthetical advantages of CRCSWs, these structural elements can effectively resist against bi‐directional loadings as compared with the equivalent RC walls with flanged sections.
{"title":"An analytical investigation into the lateral load response of curved RC shear walls","authors":"Hatef Abdoos, Alireza Khaloo, Mohammad Tabiee","doi":"10.1002/tal.2097","DOIUrl":"https://doi.org/10.1002/tal.2097","url":null,"abstract":"SummaryCurved structural elements can extensively be employed in engineering applications, to which structural designers and architects can resort in order to cope with the existing structural limitations and architectural challenges. In this regard, the current study is an attempt to provide insight into the overall performance of curved reinforced concrete (RC) shear walls (CRCSWs) due to the gaps existing in the literature. In order to fulfill this purpose, a CRCSW with general cross‐section has been considered subjected to the applied bi‐lateral and axial loadings. Equivalent non‐rectangular T‐, U‐, and L‐shaped sections are then introduced in lieu of a curved section. Thereafter, the stress and displacement distributions of CRCSWs have been analytically established. In order to highlight the structural merits of CRCSWs, a comparative study is performed based on the six non‐dimensional parameters defined in this study. According to the comparative study conducted between the CRCSWs and the equivalent non‐rectangular flanged walls, unlike latter wall types, the shear‐lag effects do not make serious issues for the performance of CRCSWs. Furthermore, to make a more realistic judgment on the response of CRCSWs, a numerical investigation has been carried out utilizing the finite element (FE) software Abaqus. On the strength of the data obtained from the FE simulation of 90 CRCSWs in three categories of short, squat, and slender walls, a regression model has been established, which is advantageous in that it can supply a means for the initial estimation of the shear strength of CRCSWs. The average R‐factor of 0.88 indicates that the established formulations can potentially well predict the shear strength of CRCSWs. The findings of this study divulge that, in addition to the inherent aesthetical advantages of CRCSWs, these structural elements can effectively resist against bi‐directional loadings as compared with the equivalent RC walls with flanged sections.","PeriodicalId":501238,"journal":{"name":"The Structural Design of Tall and Special Buildings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140303061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：