Search

This paper proposes a data-driven model for predicting the code-based seismic vulnerability index calibrated on a dataset comprising almost 300 buildings. The vulnerability index, estimated following the Italian Seismic Code, involved rigorous investigations, including geometric surveys, experimental tests, and numerical modelling. Leveraging data from these investigations, encompassing approximately 15 categorical and numerical explanatory variables, the authors developed several regression and classification predictive models, such as Logistic Regression and Artificial Neural Networks (ANN). The optimal models perform binary classification to determine the categorization into two macro-classes, defined by an arbitrary vulnerability threshold. The ANN model stands out as the best performer. When adjusting the vulnerability threshold to obtain a balanced dataset, such a model achieves an accuracy higher than 85%. The paper also discusses the importance of each feature by calculating the SHapley Additive exPlanations (SHAP) values. The proposed model can aid decision-makers in allocating resources effectively to mitigate seismic risks of built environments. • Data-driven model for code-based seismic vulnerability assessment. • 15 explanatory variables are considered. • Regression models perform poorly. • Binary classification is the only reliable approach. • The ANN model has an 85% accuracy on binary classification with balanced dataset. [ABSTRACT FROM AUTHOR]

Cold-Formed Steel Lipped (CFSL) channels are susceptible to a localized failure mechanism known as web crippling, triggered by concentrated loads or reactions applied to the web of the section. These loads induce buckling and distortion in the web, ultimately leading to the member's collapse. It is a challenging task to accurately determine the web crippling capacity of a CFSL channel due to its complexity and various influencing factors. This paper presents hybrid soft computing techniques for accurately predicting the web crippling capacity of CFSL channels subjected to two flange load cases. The developed soft computing techniques combine Artificial Neural Networks (ANN) with either Genetic Algorithms (GA) or Particle Swarm Optimization (PSO) to improve computational efficiency and accuracy. The finite element models of CFSL channels are developed and validated by experimental results and then employed to generate a database, which is used to train machine learning models, including ANN, GA-ANN, and PSO-ANN. Analysis is undertaken on the reliability of existing design formulas for determining the web crippling capacity of CFSL channels. It is shown that the PSO-ANN model outperforms the other models in terms of prediction accuracy. The existing design codes and formulas are not reliable in estimating the web crippling capacity of CFSL channels. However, the proposed model yields good correlation with finite element analysis results. A user- friendly graphical interface tool is developed for the practical design of cold-formed steel lipped channels. • FE model is developed that simulates the web crippling behavior of CFSL channels. • Hybrid ML models are developed for predicting web crippling capacity of CFSL channels. • Reliability of existing formulas for estimating web crippling capacity is investigated. • A user-friendly graphical interface tool is developed for design purpose. [ABSTRACT FROM AUTHOR]

This paper aims to develop a unique artificial neural network (ANN)-based equation as well as MATLAB- and Python-based graphical user interfaces (GUIs) using the most comprehensive and up-to-date database for predicting the behaviour of axially loaded concrete-filled double skin tubular (CFDST) short and slender columns with normal- and high-strength materials. Two machine learning (ML) methods, which are ANN and extreme gradient boosting (XGBoost), are trained and tested using 1721 sets of data, with 129 of them collected from experimental studies and 1592 generated by finite element (FE) simulations. The accuracy of the developed ML models is assessed through comparing their predictions with the experimental and FE results. To demonstrate the effect of each parameter on the predicted results, the SHapley Additive exPlanations (SHAP) method is used. The developed ML models are also used to conduct parametric studies to examine the effect of geometric and material parameters on the predicted results. The accuracy of the ML models and the proposed ANN-based equation in predicting the ultimate axial capacity of CFDST columns is compared with that of six design methods including two design code provisions and four design equations proposed by researchers. A numerical example is presented to illustrate the design procedure of the CFDST column using the proposed ANN-based equation. The results indicate that the ANN model performs better on unseen data than the XGBoost model with lower root mean square error for the test set. The results also show that the ML models and the proposed ANN-based equation are superior to the other design models in prediction accuracy. • 1721 data samples of CFDST columns are used to train and test the ML models. • Optimized ANN and XGBoost models are used to predict the behaviour of CFDST columns. • ANN-based equation, MATLAB- and Python-based GUIs are developed. • Parametric studies are conducted using the trained ML models. • The superiority of the proposed design models over six design equations is shown. [ABSTRACT FROM AUTHOR]

Dynamic analysis of forced-vibration systems in civil engineering could be computationally inefficient or even hard to converge if the systems are stiff or highly complicated. Rapid advances in machine learning make it possible to formulate surrogate models for forced-vibration systems using neural networks. The widely used neural networks such as the convolutional neural network (CNN), recurrent neural network (RNN), etc., usually require a constant sampling rate and data length, thus they are difficult to be implemented for real-time calculation of the dynamic system with varying sampling rates. Recently, the continuous-time state-space neural network (CSNN) has shown the capability to lift these restrictions and has been drawing growing attention from the community. In this paper, we propose a generalized CSNN model for various forced-vibration systems (linear and nonlinear). The CSNN model comprises two sets of independent neural networks aiming to compute the state derivative and system response, respectively. Both neural networks adopt linear and nonlinear layers in parallel, instead of only fully connected nonlinear layers as adopted in the literature. This configuration is aimed to enhance the CSNN model with its capability to recognize the linear and nonlinear behaviors of systems. Additionally, the bias options in the CSNN model are all turned off to improve the stability of the model in the long-term time-series forecast, premised on the assumption that the forced-vibration systems are dissipative systems without drift, which is the most common case in civil engineering. Integration on the state derivative at the current time step is executed to obtain the state at the next time step using the explicit 4th-order Runge–Kutta method. Both numerical and experimental illustrative examples are provided, demonstrating that the CSNN model can achieve high performance and training efficiency with a few hyper-parameters, and thus is highly promising for engineering applications. • A novel continuous-time state-space neural network (CSNN) model is proposed for data-driven modeling of forced-vibration linear/nonlinear systems. • The CSNN model does not require any prior knowledge of the system, and is not restricted to the pre-designated sampling rate and input data length. • The CSNN model has much fewer hyper-parameters than traditional neural network models and is unlikely to induce overfitting. • Numerical and experimental studies demonstrate that the CSNN model is superior to LSTM and PhyCNN in modeling both linear and nonlinear systems. [ABSTRACT FROM AUTHOR]

[Display omitted] • An innovative two-stage machine learning framework (TMLF) was proposed. • The uncertainties of material and geometrics were considered. • The strengths of the RHS-CHS T-joint follow the gamma distribution. • ANN model shows the highest accuracy in predicting the RHS-CHS T-joints' strength. • The TMLF can accurately predict the distribution of structural component strength. Machine learning technics have been extensively used in the strength prediction of structural components in recent years, nevertheless, these established strength prediction models usually can not address the inherent uncertainties introduced by the material and geometrics of structural components. This paper intends to propose an innovative two-stage machine learning framework for developing probabilistic strength prediction models of structural components with the consideration of uncertainties of material and geometrics based on limited test results. Rectangular hollow section to circular hollow section (RHS-CHS) T-joints are used as an example for evaluating the proposed framework. To this end, 58,744 training and 19,870 validation datasets are first generated through numerical simulation. Three machine learning algorithms are used and evaluated in this paper to develop the best model for predicting the strength of the RHS-CHS T-joints. The analysis results show that the artificial neural networks (ANN) showed the best generalization performance. The combination of the uncertainties of material and geometrics is considered through the Latin hypercube sampling method. Then, a new strength database considering the randomness of the structural parameters (e.g., material and geometrics) are developed through the trained ANN model and the probabilistic distribution of the strength of the RHS-CHS T-joints is analyzed through the Anderson-Darling test method. The analysis results indicate that the random strengths of the RHS-CHS T-joints follow a gamma distribution while the material and geometrics follow the normal distribution. Finally, the machine learning models for probabilistic strength prediction of the RHS-CHS T-joints are developed and validated. The analysis results indicate that the developed machine learning model can accurately capture the distribution of the strength of RHS-CHS T-joints, confirming the efficiency of the proposed two-stage machine learning framework for developing probabilistic strength prediction models of structural components. A software named "Probabilistic strength prediction of RHS-CHS T-joint" is proposed based on the developed probabilistic strength prediction model for practical application. [ABSTRACT FROM AUTHOR]

The estimation of the maximum displacements of RC beams subjected to impact loads is of pivotal importance to define demand models to be employed in structural design. The dynamic behavior is quite complex and the maximum displacements can be obtained through experimental tests or high-fidelity FEM models, while simplified analytical models accounting for few degrees of freedom have generally low accuracy. In this context, this paper presents a study on the training and interpretation of a machine-learning model that strategically combines several algorithms for the said purpose. To train the model, a comprehensive database of 342 samples of rectangular simply supported beams under rigid impact loads is adopted. Seven ML regression algorithms are adopted in this study to develop a predictive model: (1) Support Vector Regression (SV R), (2) Gaussian Process Regression (GPR), (3) Random Forest Regressor (RFR), (4) XGBoost , (5) CatBoost , (6) LightGBM , and (7) Artificial Neural Networks (ANN). Finally, a stacking model combining SV R , GPR , RFR , XGBoost , CatBoost and ANN is built to improve accuracy, wherein 75% and 25% of the data are used for training and validation, respectively, in combination with the 5 cross-validation technique. This effort resulted in approximately 90% validation accuracy exceeding current mechanics-based/semi-empirical models. Finally, the SHapley Additive exPlanations (SHAP) algorithm is used to estimate the relative importance of the input features; the most influential factors are impact velocity and impactor mass which are representing the initial kinetic energy. Moreover, a full parametric analysis of the proposed model is provided and the influence of each input is discussed. The model is finally applied to perform a structural check for three damage levels. The proposed model can be used in practical applications where a reliable estimation of the maximum displacements of RC beams under impact loading is required. • Dataset of 342 samples of rectangular RC beams subjected to impact loads. • Seven ML regression algorithms are compared to predict maximum displacements. • Stacking model combining SV R , GPR , RFR , XGBoost , CatBoost and ANN. • SHapley Additive exPlanations (SHAP) algorithm to estimate importance of the inputs. • A full parametric analysis of the proposed model is provided. [ABSTRACT FROM AUTHOR]

• Innovation application of arterial neural network (ANN) on predicting thermal behavior of concrete, steel reinforcement and fiber reinforced polymers exposed to fire. • The predicted and experimental results were in good agreement. • This paper presents developed software tool that implements proposed ANN for parametric study and designing purposes. • Unique parametric studies have been carried out on reinforced concrete columns through the proposed ANN. This paper presents a novel application of artificial neural networks (ANNs) for predicting complete temperature profiles with varying time for circular reinforced concrete (RC) columns exposed to fire. The application is valid for un-strengthened columns or columns strengthened with fibre reinforced polymers (FRP) and isolated with different types and thicknesses of insulation materials under varying fire exposure condition. In addition, prediction of the temperature variation with time for constituent materials of the column such as concrete, reinforcement steel and FRP sheets is conducted. To reach this end, extensive nonlinear finite element analysis was conducted using ANSYS software to build database of 1200 training samples with different column diameters, concrete cover thicknesses, thermal conductivity curves, specific heat curves, insulation types and thicknesses. The prediction results of ANN model is validated against published full-scale experimental studies which reveal good agreement between experimental and predicted results. The novelty of this technique is the ability of ANN model to predict rapidly and efficiently the temperature–time for any part of continent materials of reinforced concrete column many in case scenarios of parameters; this is especially useful in avoiding the time-consuming and costly full-scale experimental fire tests. Moreover, this study encourages designers to use FRP in design applications in spite of the threat of fire conditions, by utilizing ANN as backend calculation provider for software design tool with graphical user interface presented in this paper. [ABSTRACT FROM AUTHOR]

Bond strength estimation plays an important role in structure engineering. This paper proposes to adopt machine learning approaches to conduct a data-driven analysis of bond strength between ultra-high performance concrete (UHPC) and reinforcing bars. To make up for the lack of experimental data, a new database is established by integrating 557 instances from several published works. A total of nine machine learning models which can be divided into three types are implemented to train the bond strength estimators based on the database, including linear models, tree models, and artificial neural networks. Four strong metrics, i.e. Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R 2), and Ratio of Accurate Estimation (RACC), are used to evaluate the performance of models. Among them, Artificial Neural Network and Random Forest achieve great estimation performances in the top two, which far exceed the empirical formulas. They have 74% and 73% of estimated data to keep the relative error within 10%, respectively. The statistical relative importance of different factors from tree models consistently shows that the ratio of embedded depth to the diameter of reinforcing bars has a significant impact on the bond strength of UHPC, which is conformable with the observations in experiments. • The largest database of bond strength between UHPC and reinforcing bars was built. • Nine machine learning models were used to train the bond strength estimator. • The ratio of the embedded depth had a significant effect on the bond strength. [ABSTRACT FROM AUTHOR]

• Machine learning (ML)-based approach is developed for seismic failure mode and maximum bearing capacity prediction for corroded RC columns. • The best models for seismic failure model prediction is the RF and CatBoost model which has an accuracy of 89%. • The best model for bearing capacity prediction is the CatBoost model which has a R2 of 0.92. • The ML-based models can conveniently predict the life-cycle seismic performance of RC columns. Corrosion of steel reinforcements is a major factor that will adversely affect the seismic performance of the reinforced concrete (RC) columns. This paper investigates the application of machine learning (ML)-based approach for seismic failure mode and maximum bearing capacity prediction for corroded RC columns. A comprehensive database consisting of 180 cyclic tests of corroded RC columns are collected. Six ML algorithms including three single learning methods (k -Nearest neighbors, Decision tree, Artificial neural network) and three ensemble learning methods (Random forest, AdaBoost, CatBoost) are selected to develop the predictive model. The performance of the six models are evaluated and the application of ML-based approaches for life-cycle seismic performance assessment of RC column is demonstrated with a case-study column. The results show that the Random forest and CatBoost models have the best performance for seismic failure mode prediction with an accuracy of 89%. The best model for bearing capacity prediction is the CatBoost model which has a R2 of 0.92, and the CatBoost model is superior to the traditional mechanism-based code models for bearing capacity prediction. The ML-based models can conveniently predict the seismic failure mode and bearing capacity of RC columns in its life-cycle context without complicated numerical simulations or theoretical calculations. [ABSTRACT FROM AUTHOR]

• Two soft computing models are developed for the estimation of masonry compressive strength. • The unit and mortar strengths and the height to thickness ratio have been found as main influencing parameters. • Proposed ANN model proves quite more accurate compared to existing codes and literature models. • A database of 410 individual specimens has been compiled for the development and evaluation of the models. Masonry is a building material that has been used in the last 10.000 years and remains competitive today for the building industry. The compressive strength of masonry is used in modern design not only for gravitational and lateral loading, but also for quality control of materials and execution. Given the large variations of geometry of units and joint thickness, materials and building practices, it is not feasible to test all possible combinations. Many researchers tried to provide relations to estimate the compressive strength of masonry from the constituents, which remains a challenge. Similarly, modern design codes provide lower bound solutions, which have been demonstrated to be weakly correlated to observed test results in many cases. The present paper adopts soft-computing techniques to address this problem and a dataset with 401 specimens is considered. The obtained results allow to identify the most relevant parameters affecting masonry compressive strength, areas in which more experimental research is needed and expressions providing better estimates when compared to formulas existing in codes or literature. [ABSTRACT FROM AUTHOR]

• 497 experimental data of reinforced concrete (R/C) interior slab–column connections were collected for the development of machine learning (ML) models. • Extreme gradient boosting (XGBoost) was employed to predict the punching shear resistance of R/C interior slabs without shear reinforcement. • The developed XGBoost model was compared with two other ML models, four design codes, and three empirical models. • The XGBoost model presented the best accuracy. • A graphical user interface was developed based on the XGBoost model for the estimation of punching shear strength. This paper aims to present the application of extreme gradient boosting (XGBoost) to the prediction of the punching shear resistance of reinforced concrete (R/C) interior slabs without shear reinforcement. For the training and testing of the XGBoost model, which was developed using the XGBoost 1.1.1 package, 497 experimental data of interior slab–column connections were collected from the literature. The input variables were the column section dimension, slab effective depth, concrete compressive strength, steel yield strength, and reinforcement ratio at the top and bottom of the slab. The targeted output variable was the punching shear strength. First, the developed XGBoost model was compared with two other machine learning (ML) models that incorporate artificial neural network (ANN) and random forest (RF). All three ML models could reliably estimate the punching shear resistance of the considered type of R/C slabs, but the XGBoost model generally achieved the best prediction. Second, the performance of the developed XGBoost model was compared to various design codes and empirical models. The XGBoost model presented the most accurate prediction among them with the coefficient of determination ( R 2) for the testing dataset being equal to 0.9578. Third, the relative significance of input variables in the prediction of punching shear resistance was examined. The effective depth was shown to have the most significant role in the punching shear prediction. Finally, a graphical user interface based on the XGBoost model was created for preliminary estimation of the punching shear resistance of R/C interior slabs without shear reinforcement. [ABSTRACT FROM AUTHOR]

• Data-driven 11 machine learning methods are employed to predict the shear capacity of SFRC beams. • 10-fold cross-validations are performed on a data of 507 experimental results. • The XGBoost outperformed other models in terms of high coefficient of determination and low error. • The most important feature in shear capacity prediction is the ratio of shear span to effective depth. • Volume fraction and the type of fiber are found to have a significant influence on the shear capacity of SFRC beams. The incorporation of steel fibers in a concrete mix enhances the shear capacity of reinforced concrete beams and a comprehensive understanding of this phenomenon is imperative to have an accurate estimation in engineering designs. Although significant studies have been carried out on shear capacity estimation, mechanics-based models are not yet available due to the complex underlying phenomenon. This paper presents a data-driven approach to the shear strength of SFRC beams and incorporates the largest database compilation of 507 experimental data. Input features considered in this study are the ratio of shear span to effective depth, concrete compressive strength, longitudinal reinforcement ratio, volume fraction, aspect ratio, and type of fiber. Eleven machine learning (ML) models, namely linear regression, ridge regression, lasso regression, decision tree, random forest, support vector machine, k-nearest neighbors, artificial neural network, XGBoost, AdaBoost, and CatBoost, are evaluated to examine their shear strength estimation of SFRC beams. The XGBoost is resulting in the most accurate predictions (85%) with the lowest root mean squared error and low mean absolute error. A study on the importance of the input parameters reveals that shear span to effective depth ratio, longitudinal reinforcement ratio, concrete strength, and volume fraction of fiber are the most influential parameters of shear strength of SFRC. [ABSTRACT FROM AUTHOR]

• A new algorithm is proposed and validated for the model updating of structures. • The algorithm takes advantage of the virtues of different mathematical techniques. • The algorithm allows reducing the simulation time for the updating process. • The algorithm allows obtaining a robust selection of the best updated model. • The performance of this algorithm has been validated via a real case study. Finite element model updating has become a key tool to improve the numerical modelling of existing civil engineering structures, by adjusting the numerical response to the observed experimental behaviour of the structure. At present, model updating is mostly conducted using the maximum likelihood method. Following this approach, the updating problem can be transformed into a multi-objective optimization problem. Due to the complex nonlinear behaviour of the resulting objective functions, metaheuristic optimization algorithms are normally employed to solve such optimization problem. However, and although this is nowadays a well-established technique, there are still two main drawbacks that need to be addressed for practical engineering applications, namely: (i) the high simulation time required to compute the problem; and (ii) the uncertainty associated with the selection of the best updated model among all the Pareto optimal solutions. In order to overcome these limitations, a new collaborative algorithm is proposed herein, which takes advantage of the collaborative coupling among two optimization algorithms (harmony search and active-set algorithms), a machine learning technique (artificial neural networks) and a statistical tool (principal component analysis). The implementation details of our proposal are discussed in detail throughout the paper and its performance is illustrated with a case study addressing the model updating of a real steel footbridge. Two are the main advantages of the newly proposed algorithm: (i) it leads to a clear reduction of the simulation time; and (ii) it further permits a robust selection of the best updated model. [ABSTRACT FROM AUTHOR]

• A machine learning framework is developed to predict failure mode of UHPC beams. • Genetic programing algorithms is applied for predicting shear capacity of UHPC beams. • The proposed expressions can be utilized in practice for design of UHPC beams. This paper presents a data-driven machine learning (ML) framework for predicting failure mode and shear capacity of Ultra High Performance Concrete (UHPC) beams. To this end, a comprehensive database on 360 reported tests on UHPC beams with different geometric, fiber properties, loading and material characteristics was collected. This database was then analyzed utilizing different ML algorithms including, support vector machine (SVM), artificial neural networks (ANN), k -nearest neighbor (k -NN), and genetic programing (GP), to identify key parameters governing failure pattern and shear capacity of UHPC beams. The outcome of this analysis is a computational-based ML framework that is capable of identifying failure mode of UHPC beams and simplified expressions for predicting shear capacity of UHPC beams. Predictions obtained from the proposed framework was compared against the values obtained from design equations in codes, and also results from full-scale tests to show the reliability of the proposed approach. The results clearly infer that the proposed data-driven ML framework can effectively predict failure mode and shear capacity of prestressed and non-prestressed UHPC beams with varying reinforcement detailing and configurations. [ABSTRACT FROM AUTHOR]