Asian Journal of Civil Engineering最新文献_第8页

Analysis of irregular RC buildings using probabilistic seismic vulnerability assessment 基于概率地震易损性评价的不规则钢筋混凝土建筑分析

Asian Journal of Civil Engineering Pub Date : 2025-06-20 DOI: 10.1007/s42107-025-01397-6

Anuj Kumar Sharma, Saraswati Setia

{"title":"Analysis of irregular RC buildings using probabilistic seismic vulnerability assessment","authors":"Anuj Kumar Sharma, Saraswati Setia","doi":"10.1007/s42107-025-01397-6","DOIUrl":"10.1007/s42107-025-01397-6","url":null,"abstract":"<div><p>For the assessment of vulnerability of reinforced concrete (RC) buildings, particularly irregular ones, requires robust methodologies due to increasing frequency and intensity of seismic events. Irregularities in building design such as plan or vertical irregularities, often leads to complex dynamic behaviour during seismic events, which may result in severe structural damage or failure. In this study, the performance of irregular RC buildings, which are usually more prone to damage during earthquakes because of their geometrical shape and slenderness ratio are assessed using probabilistic seismic vulnerability assessment (PSVA). With the objective to develop fragility curves which gauge the probability of multiple damage states under various seismic intensity levels, the analysis takes into consideration the non-parallel lateral force system (NPLFS) type of plan irregularity along with different height models that significantly influences their seismic performance. The results suggest that NPLFS irregularity in reinforced concrete buildings are significantly performing good than as compared to regular models. Additionally, it emphasizes areas where design changes or retrofitting could enhance resilience and illustrates the effectiveness of probabilistic approaches in improving the precision of seismic hazard evaluations for irregular RC buildings. Due to the assessment being probabilistic, it helps stakeholders in understanding risk and make informed choices regarding disaster preparedness and safety of buildings. The PSVA framework can assist engineers and policymakers in implementing effective strategies for risk reduction by offering a quantitative foundation for assessing vulnerability. This ultimately contributes to creating a safer urban environment in regions prone to seismic activity.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 9","pages":"3785 - 3796"},"PeriodicalIF":0.0,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145167782","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}

引用次数: 0

Enhanced ResNet50 deep learning algorithm for classification of crack images in RCC structures 增强的ResNet50深度学习算法用于RCC结构的裂纹图像分类

Asian Journal of Civil Engineering Pub Date : 2025-06-17 DOI: 10.1007/s42107-025-01396-7

Shashi Kumar Bussa, Narendra Kumar Boppana

{"title":"Enhanced ResNet50 deep learning algorithm for classification of crack images in RCC structures","authors":"Shashi Kumar Bussa, Narendra Kumar Boppana","doi":"10.1007/s42107-025-01396-7","DOIUrl":"10.1007/s42107-025-01396-7","url":null,"abstract":"<div><p>The assessment of concrete crack conditions stands as a basic requirement to protect the sustainability and security of civil construction elements. Hand-based damage assessment methods prove both too slow and too variable to conduct on big structural elements. The authors propose a deep learning system which applies transfer learning using ResNet50 architecture to perform binary classification on concrete surface cracks. The training and validation processes for model development relied on the METU concrete surface dataset through its 20,000-image subset that equally divided between crack and non-crack categories. Changing the classification end of ResNet50 and freezing the pretrained convolutional layers during training enabled efficient feature learning and minimization of overfitting problems. My training process used data augmentation combined with 80/20 stratified train-valid split distribution. Furthermore, 100 cross-domain crack pictures were created during flexural testing of RC beams in a laboratory setting using a servo-controlled loading frame and utilized to verify model generalization. The experimental results showed 97.00% validation accuracy together with an F1-Score rate of 97.0% better than multiple CNN-based techniques executed on the same dataset. The model demonstrated outstanding performance based on confusion matrix results and sample predictions while remaining effective across different surface textures and crack patterns. The evaluation showed the proposed ResNet50-based model yielded better performance than conventional CNNs and both LeNet variants and VGG-based models as per previous studies. Transfer learning and deep residual networks demonstrate their effectiveness for detecting cracks in a robust and scalable manner according to the obtained results. The proposed model will receive future development which aims to enhance the severity measurement ability alongside real-time deployment technology for autonomous infrastructure surveillance systems.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 9","pages":"3773 - 3784"},"PeriodicalIF":0.0,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145166733","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}

引用次数: 0

TabNet-based prediction of residual compressive and flexural strengths in hybrid fiber-reinforced self-compacting concrete (HFR-SCC) exposed to elevated temperatures 高温下混杂纤维增强自密结混凝土（HFR-SCC）残余抗压和抗弯强度基于表网的预测

Asian Journal of Civil Engineering Pub Date : 2025-06-16 DOI: 10.1007/s42107-025-01392-x

Amel Ali Aichouba, Ali Benzaamia, Mohammed Ezziane, Mohamed Ghrici, Mohamed Mouli

{"title":"TabNet-based prediction of residual compressive and flexural strengths in hybrid fiber-reinforced self-compacting concrete (HFR-SCC) exposed to elevated temperatures","authors":"Amel Ali Aichouba, Ali Benzaamia, Mohammed Ezziane, Mohamed Ghrici, Mohamed Mouli","doi":"10.1007/s42107-025-01392-x","DOIUrl":"10.1007/s42107-025-01392-x","url":null,"abstract":"<div><p>Hybrid fiber-reinforced self-compacting concrete (HFR-SCC) is increasingly employed in structural applications requiring enhanced ductility and durability. However, its performance under elevated temperatures remains difficult to predict due to the complex interactions between mixture constituents, fiber degradation, and thermal damage mechanisms. This study proposes a novel data-driven framework based on the TabNet deep learning architecture to forecast the residual compressive and flexural strengths of HFR-SCC exposed to high temperatures. A diverse experimental dataset comprising 114 samples was compiled from the literature, incorporating eight key input parameters including binder composition, aggregate content, fiber dosage, and thermal exposure conditions. The TabNet model, optimized via Bayesian hyperparameter tuning, demonstrated excellent predictive accuracy and generalization capability, achieving R<sup>2</sup> values exceeding 0.98 and low error metrics across both training and testing sets. Comparative evaluations against seven conventional machine learning models—including ensemble and kernel-based approaches—highlighted TabNet’s superior performance, particularly in balancing accuracy and robustness. Importantly, TabNet’s intrinsic interpretability revealed that exposure temperature, slag content, and fiber volume were the most influential factors governing residual mechanical behavior. These findings affirm the potential of attention-based deep learning models to support reliable, interpretable, and efficient evaluation of fire-exposed concrete structures, advancing the integration of machine learning in materials engineering practice.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 9","pages":"3705 - 3724"},"PeriodicalIF":0.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145165695","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}

引用次数: 0

Fire-damaged recycled brick and concrete aggregates: enhancing early strength and reducing costs 火灾损坏的再生砖和混凝土集料：提高早期强度和降低成本

Asian Journal of Civil Engineering Pub Date : 2025-06-14 DOI: 10.1007/s42107-025-01389-6

Md. Tushar Ali

{"title":"Fire-damaged recycled brick and concrete aggregates: enhancing early strength and reducing costs","authors":"Md. Tushar Ali","doi":"10.1007/s42107-025-01389-6","DOIUrl":"10.1007/s42107-025-01389-6","url":null,"abstract":"<div><p>Fire-damaged construction debris poses both a challenge and an opportunity for sustainable material recovery. This study investigates the use of 14-year-old, fire-damaged recycled brick aggregates (RBA) and recycled concrete aggregates (RCA) as partial replacements for natural coarse aggregates (NCA) in concrete up to 70%, utilizing a two-step mixing (TSM) method. Results indicate that Concrete mixes incorporating 20% and 40% fire-damaged RCA and RBA demonstrated notable improvements in mechanical performance. Tensile strength increased by approximately 20%, while compressive strength improved slightly by 2–3% compared to conventional NCA concrete. Early strength development was also enhanced, with 7-day compressive strengths reaching over 73% of the 28-day values, around 10% higher than the control mix. Microstructural analysis confirmed the development of a denser ITZ and reduced porosity at lower replacement levels, which helped restrain crack propagation. However, at higher replacements (55% and 70%), a notable increase in pore size (from 1–5 to 8–15 µm) and ITZ width (~ 5–7 to ~ 12–18 µm) indicated a decline in matrix compactness and structural integrity. Furthermore, the aggregate cost analysis indicated that 20% and 40% replacements could reduce overall material costs by 15% and 28%, respectively, while maintaining structural integrity. These results highlight the feasibility of incorporating fire-damaged recycled aggregates for sustainable, cost-effective concrete production without compromising performance.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 9","pages":"3657 - 3670"},"PeriodicalIF":0.0,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145165068","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}

引用次数: 0

Hybrid ANN-GPR machine learning surrogate for dynamic behavior of functional materials 混合ANN-GPR机器学习替代功能材料的动态行为

Asian Journal of Civil Engineering Pub Date : 2025-06-12 DOI: 10.1007/s42107-025-01393-w

Mallikarjun Muttappa Gadikar, Aman Garg, Vaishali Sahu

{"title":"Hybrid ANN-GPR machine learning surrogate for dynamic behavior of functional materials","authors":"Mallikarjun Muttappa Gadikar, Aman Garg, Vaishali Sahu","doi":"10.1007/s42107-025-01393-w","DOIUrl":"10.1007/s42107-025-01393-w","url":null,"abstract":"<div><p>Modeling bidirectional functionally graded (BDFG) plates is challenging due to the continuous spatial variation of material properties. This study presents a novel machine learning (ML)-assisted isogeometric analysis (IGA) framework to predict the free vibration response of BDFG plates efficiently. The training dataset is generated using zigzag theory within an IGA framework, capturing high-fidelity structural behavior. Three regression-based ML algorithms—Gaussian Process Regression (GPR), Artificial Neural Network (ANN), and hybrid models (GA-optimized ANN and Bayesian-optimized GPR)—are employed. Additionally, a novel hybrid ANN-GPR model is proposed, where ANN extracts high-level features from raw input data, and GPR performs regression with uncertainty quantification. Further, an ANN-learned kernel replaces the conventional GPR kernel, enabling latent-space transformation for enhanced predictive performance. The proposed hybrid approach demonstrates superior computational efficiency and accuracy compared to standalone and optimized ML models, making it a robust tool for the analysis of BDFG structures.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 9","pages":"3725 - 3742"},"PeriodicalIF":0.0,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145164219","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}

引用次数: 0

Seismic response prediction of irregular buildings using machine learning: a comparative analysis of parametric and non-parametric models 使用机器学习的不规则建筑物地震反应预测：参数模型和非参数模型的比较分析

Asian Journal of Civil Engineering Pub Date : 2025-06-11 DOI: 10.1007/s42107-025-01388-7

Anurag Wahane, Pradeep Kumar Ghosh, Sri Ram Krishna Mishra

{"title":"Seismic response prediction of irregular buildings using machine learning: a comparative analysis of parametric and non-parametric models","authors":"Anurag Wahane, Pradeep Kumar Ghosh, Sri Ram Krishna Mishra","doi":"10.1007/s42107-025-01388-7","DOIUrl":"10.1007/s42107-025-01388-7","url":null,"abstract":"<div><p>The increasing demand for aesthetic designs, coupled with limited land availability, has resulted in irregular building configurations that compromise seismic performance. These irregularities can lead to stress concentrations caused by torsional effects and variations in stiffness. This study aims to predict key seismic responses such as natural time period, displacement, and storey drift for geometrically irregular reinforced concrete (RC) buildings. A total of 630 building models were developed and analyzed using ETABS, incorporating input parameters like the structural coefficient (r), building height (H), and irregularity index (β). We applied various machine learning (ML) algorithms, including parametric models such as Multiple Linear Regression, Ridge, and Bayesian Ridge, as well as non-parametric models like Decision Tree, Random Forest, AdaBoost, XGBoost, and Gaussian Regressor. Model performance was evaluated using metrics such as R<sup>2</sup>, Mean Absolute Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and K-fold cross-validation to ensure robustness. Among the models assessed, Gaussian Boosting demonstrated superior performance with an R<sup>2</sup> value of 0.99347, while Ridge Regression exhibited the lowest accuracy. This study highlights the effectiveness of machine learning techniques, particularly Gaussian and multi-linear models, as accurate, fast, and cost-effective alternatives to traditional methods of predicting seismic response. In addition, we introduced a graphical user interface (GUI) as a user-friendly tool designed to assist researchers in estimating the seismic capacity of reinforced concrete buildings. This GUI aims to minimize computational demands and reduce the complexity of analytical procedures.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 9","pages":"3627 - 3655"},"PeriodicalIF":0.0,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145164552","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}

引用次数: 0

Predicting split tensile strength of hollow concrete blocks using PCA-enhanced machine learning models 使用pca增强的机器学习模型预测空心混凝土块的劈裂拉伸强度

Asian Journal of Civil Engineering Pub Date : 2025-06-10 DOI: 10.1007/s42107-025-01386-9

S. Hetaish Subramanya, S. Deepak Raj, Rakesh Kumar, Sathvik Sharath Chandra

{"title":"Predicting split tensile strength of hollow concrete blocks using PCA-enhanced machine learning models","authors":"S. Hetaish Subramanya, S. Deepak Raj, Rakesh Kumar, Sathvik Sharath Chandra","doi":"10.1007/s42107-025-01386-9","DOIUrl":"10.1007/s42107-025-01386-9","url":null,"abstract":"<div><p>Concrete's split tensile strength (STS) is a crucial metric when assessing the material's structural integrity and longevity. The split tensile strength (STS) of concrete is a critical parameter for assessing its structural integrity and durability. Traditional methods for predicting STS involve labour-intensive testing procedures. This study applies advanced machine learning models, Gradient Boosting (GB), Random Forest (RF), and Adaptive Boosting (AdaBoost) to predict the STS of hollow concrete blocks (HCBs) based on the rod position during ASTM C-1006-13 split tensile testing. A dataset comprising 90 observations with 22 input parameters, including geometrical properties (block dimensions, cavity sizes, thicknesses) and experimental conditions (net area, applied load, block length, and height), was used for model training and evaluation. It enhanced predictive accuracy and address multicollinearity, Principal Component Analysis (PCA) was employed as a dimensionality reduction technique. The model’s performance was assessed using Root Mean Square Error (RMSE) and the coefficient of determination (R<sup>2</sup>). The Random Forest model demonstrated the highest accuracy, achieving RMSE = 0.118 and R<sup>2</sup> = 0.920 in the testing phase. Compared to conventional testing methods, the findings highlight the effectiveness of feature selection and machine learning techniques in developing reliable predictive models for concrete performance.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 8","pages":"3533 - 3551"},"PeriodicalIF":0.0,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145163667","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}

引用次数: 0

Resource-constrained discrete time-cost trade-off optimization in construction projects using nature-inspired algorithms 基于自然启发算法的建设项目资源约束离散时间成本权衡优化

Asian Journal of Civil Engineering Pub Date : 2025-06-10 DOI: 10.1007/s42107-025-01394-9

Aditi Tiwari, Manoj Kumar Trivedi

{"title":"Resource-constrained discrete time-cost trade-off optimization in construction projects using nature-inspired algorithms","authors":"Aditi Tiwari, Manoj Kumar Trivedi","doi":"10.1007/s42107-025-01394-9","DOIUrl":"10.1007/s42107-025-01394-9","url":null,"abstract":"<div><p>Efficient management of time and cost in construction projects is often hindered by limited resource availability and the discrete nature of execution alternatives. This study addresses the resource-constrained discrete time-cost trade-off problem (RC-DTCTP) by proposing a multi-algorithmic optimization framework using six nature-inspired algorithms: NSGA-III, MOPSO, MOACO, MOTLBO, MOWOA, and SPEA2. Each algorithm is rigorously evaluated based on 13 performance metrics, including convergence, diversity, and computational efficiency. A benchmark case study comprising 18 multi-mode construction activities is used for comparative validation. Among all, the multi-objective teaching-learning-based optimization (MOTLBO) algorithm demonstrated superior performance, achieving the most balanced trade-off between project duration and cost. Additionally, post-Pareto analysis using multi-criteria decision-making (MCDM) techniques—TOPSIS and the entropy weight method—was employed to identify the best compromise solution under varying stakeholder preferences. Sensitivity analysis further confirmed the robustness of MOTLBO across different resource availability scenarios. The proposed framework not only enhances algorithmic benchmarking for RC-DTCTP but also bridges the gap between computational optimization and practical decision-making in construction planning. This study provides a valuable decision-support tool for project managers seeking cost-effective and time-efficient scheduling solutions under realistic constraints.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 9","pages":"3743 - 3759"},"PeriodicalIF":0.0,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145163911","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}

引用次数: 0

An advanced machine learning framework for predicting climate warming from greenhouse gas emissions 一个先进的机器学习框架，用于预测温室气体排放导致的气候变暖

Asian Journal of Civil Engineering Pub Date : 2025-06-09 DOI: 10.1007/s42107-025-01378-9

Gokulan Ravindiran, K. Karthick, H. K. Ramaraju, Deepshikha Datta, Valisher Sapayev, Mirjalol Ismoilov

{"title":"An advanced machine learning framework for predicting climate warming from greenhouse gas emissions","authors":"Gokulan Ravindiran, K. Karthick, H. K. Ramaraju, Deepshikha Datta, Valisher Sapayev, Mirjalol Ismoilov","doi":"10.1007/s42107-025-01378-9","DOIUrl":"10.1007/s42107-025-01378-9","url":null,"abstract":"<div><p>The present research investigated the emissions of greenhouse gases (GHGs), namely carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O), and their impact on the global mean surface temperature rise in India from 1851 to 2020. The emission data were derived from a combination of fossil fuel source emissions and emissions related to land use, land-use change, and forestry (LULUCF). Machine learning models including XGBoost, Random Forest (RF), LightGBM, and Nu Support Vector Regression (NuSVR) were employed to develop a regression models for predicting the total change in temperature based on GHG emissions data. A strong correlation was observed between these emissions and the global temperature rise, with CO₂ exerting the greatest impact. Fossil fuels constituted the primary source of CO₂ emissions, while LUCUCF was the major contributor to CH₄ and N₂O emissions. The results also indicated that these emission sources increased after 1950, possibly due to rapid industrialization, intensified agricultural practices, urbanization, and the greater use of fossil fuels as a major energy source. The Box–Cox transformation was applied to reduce skewness and kurtosis of the datasets. Model performance was evaluated using the correlation coefficient, mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE) on an 80:20 training-to-testing split. The results revealed that although all models performed well, the Random Forest and NuSVR models outperformed XGBoost and LightGBM. This work highlights the potential of machine learning for climate modeling and informs policy decisions aimed at mitigating climate change impacts in developing regions such as India.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 8","pages":"3379 - 3400"},"PeriodicalIF":0.0,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145163527","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}

引用次数: 0

Prediction of inelastic displacement ratios in soil-structure interaction on very soft soils using neural architecture search-based ML hybrid technique 基于神经结构搜索的ML混合预测超软土土-结构相互作用的非弹性位移比

Asian Journal of Civil Engineering Pub Date : 2025-06-08 DOI: 10.1007/s42107-025-01371-2

Adnane Brahma, Mohamed Beneldjouzi, Mohamed Hadid, Mohammed Amin Benbouras

{"title":"Prediction of inelastic displacement ratios in soil-structure interaction on very soft soils using neural architecture search-based ML hybrid technique","authors":"Adnane Brahma, Mohamed Beneldjouzi, Mohamed Hadid, Mohammed Amin Benbouras","doi":"10.1007/s42107-025-01371-2","DOIUrl":"10.1007/s42107-025-01371-2","url":null,"abstract":"<div><p>Performance-based seismic design focuses on limiting building lateral inelastic displacements to control potential structural damage during earthquakes. In this study, advanced machine learning methods are used to carry out a new model for predicting inelastic displacement ratios (IDR) in multistorey buildings built on very soft soils, considering soil-structure interaction (SSI) effects. The proposed model enhances prediction accuracy, reduces computational cost, and facilitates real-world seismic response assessments. A comprehensive dataset was generated, encompassing various dynamic characteristics and key SSI parameters of soil-structure systems. Nonlinear time history analyses (NLTHA) were conducted using a set of 20 ground motions recorded on very soft soil sites. The research utilizes artificial neural networks (ANN), random forest (RF) algorithms, and hybrid models optimized via neural architecture search (NAS-ANN and -RF). A practical and user-friendly graphical interface, named \"IDRs_SSI2025\", has been developed to support the application of the model proposed by engineers and researchers. Results indicate that the proposed methodology improves prediction accuracy, reduces computational cost, and facilitates real-world seismic response assessments.</p></div>","PeriodicalId":8513,"journal":{"name":"Asian Journal of Civil Engineering","volume":"26 8","pages":"3257 - 3278"},"PeriodicalIF":0.0,"publicationDate":"2025-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145163519","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}

引用次数: 0