Search Results (31)

This paper is devoted to a novel formal analysis, optimizing the learning models for feedforward multilayer neural networks with hybrid structures. The proposed mathematical description replicates a specific switched-type optimal control problem (OCP). We have developed an equivalent, optimal control-based formulation of the given problem of training a hybrid feedforward multilayer neural network, to train the target mapping function constrained by the training samples. This novel formal approach makes it possible to apply some well-established optimal control techniques to design a versatile type of full connection neural networks. We next discuss the irrelevance of the necessity of Pontryagin-type optimality conditions for the construction of the obtained switched-type OCP. This fact motivated us to consider the so-called direct-solution approaches to the switched OCPs, which can be associated with the learning of hybrid neural networks. Concretely, we consider the generalized reduced-gradient algorithm in the framework of the auxiliary switched OCP. Full article

In modern architecture, the structural safety of buildings largely depends on the compressive strength of high-performance concrete (HPC), which is determined by the complex nonlinear relationships between its components. In order to more accurately forecast HPC’s compressive strength, this paper proposes a prediction model based on an improved dung beetle optimization algorithm (OTDBO)-optimized backpropagation neural network (BPNN). Extreme Gradient Boosting (XGBoost) is employed to determine the inputs for the BPNN, enhancing the computational efficiency under high-dimensional data feature conditions. To address the issues of local optima entrapment and slow convergence in the dung beetle optimization algorithm (DBO), four improvements were made to enhance its performance. In the initial population generation stage, the optimal Latin hypercube method was used to increase the population diversity. In the rolling stage, the osprey optimization algorithm’s global exploration strategy was introduced to improve the global search capability. The variable spiral search strategy was employed in the reproduction stage, and an adaptive t-distribution perturbation strategy was combined in the foraging stage to enhance the algorithm’s adaptability and search efficiency. The improved dung beetle optimization algorithm (OTDBO) outperformed other algorithms in performance tests on the CEC2017 benchmark functions. In terms of predicting the compressive strength of HPC, the XG-OTDBO-BP model developed in this study outperformed models optimized by other algorithms in terms of fitting outcomes and prediction accuracy. These findings support the XG-OTDBO-BP model’s superiority in the compressive strength of HPC prediction. Full article

In recent years, the use of recycled aggregate (RA) in roller-compacted concrete (RCC) for pavement construction has been increasingly attractive due to various environmental and economic benefits. Early determination of the compressive strength (CS) is crucial for the construction and maintenance of pavement. This paper presents the idea of combining metaheuristics and an advanced gradient boosting regressor for estimating the compressive strength of roller-compacted concrete containing RA. A dataset, including 270 samples, has been collected from previous experimental works. Recycled aggregates of construction demolition waste, reclaimed asphalt pavement, and industrial slag waste are considered in this dataset. The extreme gradient boosting machine (XGBoost) is employed to generalize a functional mapping between the CS and its influencing factors. A recently proposed gradient-based optimizer (GBO) is used to fine-tune the training phase of XGBoost in a data-driven manner. Experimental results show that the hybrid GBO-XGBoost model achieves outstanding prediction accuracy with a root mean square error of 2.64 and a mean absolute percentage error less than 8%. The proposed method is capable of explaining up to 94% of the variation in the CS. Additionally, an asymmetric loss function is implemented with GBO-XGBoost to mitigate the overestimation of CS values. It was found that the proposed model trained with the asymmetric loss function helped reduce overestimated cases by 17%. Hence, the newly developed GBO-XGBoost can be a robust and reliable approach for predicting the CS of RCC using RA. Full article

The expeditious and precise prediction of stress variations in nonlinear boom structures is paramount for ensuring the safe, dependable, and effective operation of pump trucks. Nonetheless, balancing prediction accuracy and efficiency by constructing a suitable machine-learning model remains a challenge in engineering practice. To this end, this paper introduces an interpretable fusion model named RS–XGBoost–RF (Random Search–Extreme Gradient Boosting Tree–Random Forest) and develops an intelligent algorithm for the stress prediction of the nonlinear boom structure of concrete pump trucks. Firstly, an information acquisition system is deployed to collect relevant data from the boom systems of ZLJ5440THBBF 56X-6RZ concrete pump trucks during its operational phase. Data pre-processing is conducted on the 2.4 million sets of acquired data. Then, a sample dataset of typical working conditions is obtained. Secondly, the RS algorithm, RF model, and XGBoost model are selected based on their complementary strengths to construct the fusion model. The model fusion condition is established with a focus on prediction efficiency. By leveraging the synergy between search and prediction mechanisms, the RS–XGBoost model is constructed for the prediction of the master hyperparameters of the RF model. This model uses the random search (RS) process to obtain the mapping between the loss function and the hyperparameters. This mapping relationship is then learned using the XGBoost model, and the hyperparameter value with the smallest loss value is predicted. Finally, the RS–XGBoost–RF model with optimized hyperparameters is employed to achieve rapid stress prediction at various detection points of the nonlinear boom structure. The findings demonstrate that, within the acceptable prediction efficiency for engineering practice, the fitting accuracy (R²) of the RS–XGBoost–RF model consistently exceeds 0.955 across all measurement points, with only a few exceptions. Concerning the stress magnitudes themselves, the mean absolute error (MAE) and root mean square error (RMSE) are maintained within the ranges of 2.22% to 3.91% and 4.79% to 7.85%, respectively. In comparison with RS–RF–RF, RS–RF–XGBoost, and RS–XGBoost–XGBoost, the proposed model exhibits the optimal prediction performance. The method delineated in this paper offers valuable insights for expeditious structural stress prediction in the realm of inherent safety within construction machinery. Full article

The theoretical calculation formula for the temperature effect of composite box beams with corrugated steel webs and arbitrary temperature gradient distribution is derived based on the structural characteristics of such beams. This is achieved by considering the deformation coordination condition of the steel and concrete interface, as well as taking into account the longitudinal constraint effect of the web. An analysis is conducted to compare the results obtained from a fine finite element numerical example with those from the theoretical formula. This study also investigates the height of the common flexural zone of corrugated steel web and concrete, confirming the correctness of the theoretical formula. The findings indicate that, when 10% of the height of the corrugated steel web is considered as the common flexural area, there is optimal agreement between the theoretical values and finite element values, resulting in calculated results that are more consistent with actual stress states in this type of box girder bridge. Furthermore, it is observed that the interfacial shear force and interface slip between the steel and concrete in composite beams are not uniformly distributed along their longitudinal axis. Specifically, the interfacial shear force follows a hyperbolic cosine function along this axis, reaching its maximum value at mid-span while being zero at both ends. On the other hand, the interface slip follows a hyperbolic sine function along this axis, reaching its maximum value at the beam end while being zero within the span. It should be noted that factors such as the interface slip stiffness, temperature difference, and linear expansion coefficient have a significant influence on the temperature effects in composite beams. In addition to these factors, a reasonable arrangement of shear nails on steel plates has been identified as an effective method for mitigating adverse effects. Full article

As deep learning has evolved, larger and deeper neural networks are currently a popular trend in both natural language processing tasks and computer vision tasks. With the increasing parameter size and model complexity in deep neural networks, it is also necessary to have more data available for training to avoid overfitting and to achieve better results. These facts demonstrate that training deep neural networks takes more and more time. In this paper, we propose a training acceleration method based on gradually freezing the parameters during the training process. Specifically, by observing the convergence trend during the training of deep neural networks, we freeze part of the parameters so that they are no longer involved in subsequent training and reduce the time cost of training. Furthermore, an adaptive freezing algorithm for the control of freezing speed is proposed in accordance with the information reflected by the gradient of the parameters. Concretely, a larger gradient indicates that the loss function changes more drastically at that position, implying that there is more room for improvement with the parameter involved; a smaller gradient indicates that the loss function changes less and the learning of that part is close to saturation, with less benefit from further training. We use ViTDet as our baseline and conduct experiments on three remote sensing target detection datasets to verify the effectiveness of the method. Our method provides a minimum speedup ratio of 1.38×, while maintaining a maximum accuracy loss of only 2.5%. Full article

This study proposes a novel integration of the Extreme Gradient Boosting Machine (XGBoost) and Differential Flower Pollination (DFP) for constructing an intelligent method to predict the compressive strength (CS) of high-performance concrete (HPC) mixes. The former is employed to generalize a mapping function between the mechanical property of concrete and its influencing factors. DFP, as a metaheuristic algorithm, is employed to optimize the learning phase of XGBoost and reach a fine balance between the two goals of model building: reducing the prediction error and maximizing the generalization capability. To construct the proposed method, a historical dataset consisting of 400 samples was collected from previous studies. The model’s performance is reliably assessed via multiple experiments and Wilcoxon signed-rank tests. The hybrid DFP-XGBoost is able to achieve good predictive outcomes with a root mean square error of 5.27, a mean absolute percentage error of 6.74%, and a coefficient of determination of 0.94. Additionally, quantile regression based on XGBoost is performed to construct interval predictions of the CS of HPC. Notably, an asymmetric error loss is used to diminish overestimations committed by the model. It was found that this loss function successfully reduced the percentage of overestimated CS values from 47.1% to 27.5%. Hence, DFP-XGBoost can be a promising approach for accurately and reliably estimating the CS of untested HPC mixes. Full article

Engineered cementitious composite (ECC) functional gradient concrete has a promising application future, and its mechanical features are piquing the interest of researchers. The impacts of this strength class of concrete, interface reinforcement technique, ECC thickness (i.e., fiber dosage), and other factors on the splitting tensile strength qualities are explored using an experimental investigation of functional gradient concrete. The splitting tensile tests of 150 mm × 150 mm × 150 mm functional gradient concrete specimens were used to explore the link between concrete strength grade, interface reinforcing technique, and ECC thickness with polyvinyl alcohol (PVA) fiber additive and functional gradient concrete. The test results show that the splitting tensile strength of functional gradient concrete increases as the concrete strength grade increases; different interfacial treatments have a significant effect on the splitting tensile strength of functional gradient concrete; and the effect of ECC thickness change on the splitting tensile strength of functional gradient concrete shows different trends, which research can be used as an experimental reference for functional gradient concrete engineering applications. Full article

3D printing of ceramics has started gaining traction in architecture over the past decades. However, many existing paste-based extrusion techniques have not yet been adapted or made feasible in ceramics. A notable example is coextrusion, a common approach to extruding multiple materials simultaneously when 3D-printing thermoplastics or concrete. In this study, coextrusion was utilized to enable multi-material 3D printing of ceramic elements, aiming to achieve functionally graded porosities at an architectural scale. The research presented in this paper was carried out in two consecutive phases: (1) The development of hardware components, such as distinct material mixtures and a dual extruder setup including a custom nozzle, along with software environments suitable for printing gradient materials. (2) Material experiments including material testing and the production of exemplary prototypes. Among the various potential applications discussed, the developed coextrusion method for clay-based composites was utilized to fabricate ceramic objects with varying material properties. This was achieved by introducing a combustible as a variable additive while printing, resulting in a gradient porosity in the object after firing. The research’s originality can be summarized as the development of clay-based material mixtures encompassing porosity agents for 3D printing, along with comprehensive material-specific printing parameter settings for various compositions, which collectively enable the successful creation of functionally graded architectural building elements. These studies are expected to broaden the scope of 3D-printed clay in architecture, as it allows for performance optimization in terms of structural performance, insulation, humidity regulation, water absorption and acoustics. Full article

During the operational phase of the expressway, a significant challenge arises concerning substantial differential settlement in the transition zone connecting the culvert and the general subgrade, affecting its smoothness. In order to address the issue of abrupt stiffness variations within the transition section and to mitigate the occurrence of differential settlement, a gradient pile–reinforced-concrete slab composite foundation was implemented for the first time within an expressway culvert–subgrade transition section. At the same time, an in situ vibration test was conducted through the SBZ30 vibration exciter to comprehensively understand the vertical dynamic responses in the culvert–subgrade transition section under various axle loads and speed conditions. Furthermore, continuous monitoring was conducted to track the long-term settlement of the roadbed. The findings indicate that the utilization of gradient pile–reinforced-concrete slab composite foundations can significantly mitigate the amplitude of the dynamic response parameters. Moreover, dynamic parameters and attenuation coefficients exhibit a gradual reduction as the depth increases. Dynamic stresses, acceleration, and displacements on the roadbed surface exhibited positive correlations with both the axle weight and vehicle speed. However, at deeper depths, the load weight exerted a more pronounced influence. As the speed rose, acceleration decayed faster, affecting a shallower depth. Conversely, the increased load slowed the acceleration decay. The cumulative deformation of the roadbed and the number of excitations followed exponential function characteristics. Settlement values progressively increased while the settlement rate gradually diminished, eventually reaching a stable state, ultimately stabilizing within 4.7 mm. These research outcomes offer valuable guidance and serve as a reference for the implementation of gradient pile–reinforced-concrete slab composite foundations within the culvert–subgrade transition section. Full article

Piezoelectric (PZT) sensors employed in the electro-mechanical impedance/admittance (EMI/EMA) technique are vulnerable to temperature variations when applied to concrete structural health monitoring (SHM). However, in practice, the ambient temperature transmitted from the air or surface to the concrete inner part is time-dependent during its monitoring process, which inflicts a critical challenge to ensure accurate signal processing for PZT sensors embedded inside the concrete. This paper numerically and experimentally investigated the thermal hysteresis effect on EMA-based concrete structure monitoring via an embedded PZT sensor. In the numerical modeling, a 3D finite element model of a concrete cube embedded with a PZT sensor was generated, where thermal hysteresis in the concrete, adhesive coat, and sensor was fully incorporated by introducing a temperature gradient. In the experiment, an equal-sized concrete cube installed with a cement-embedded PZT (CEP) sensor was cast and heated for 180 min at four temperature regimes for EMA monitoring. Experimental results, as a cogent validation of the simulation, indicated that EMA characteristics were functionally correlated to the dual effect of both heat transfer and the temperature regime. Moreover, a new approach relying on the frequency/magnitude of the maximum resonance peak in the EMA spectrum was proposed to effectively compensate for the thermal hysteresis effect, which could be regarded as a promising alternative for future applications. Full article

To ensure the safety of buildings, accurate and robust prediction of a reinforced concrete deep beam’s shear capacity is necessary to avoid unpredictable accidents caused by brittle failure. However, the failure mechanism of reinforced concrete deep beams is very complicated, has not been fully elucidated, and cannot be accurately described by simple equations. To solve this issue, machine learning techniques have been utilized and corresponding prediction models have been developed. Nevertheless, these models can only provide deterministic prediction results of the scalar type, and the confidence level is uncertain. Thus, these prediction results cannot be used for the design and assessment of deep beams. Therefore, in this paper, a probabilistic prediction approach of the shear strength of reinforced concrete deep beams is proposed based on the natural gradient boosting algorithm trained on a collected database. A database of 267 deep beam experiments was utilized, with 14 key parameters identified as the inputs related to the beam geometry, material properties, and reinforcement details. The proposed NGBoost model was compared to empirical formulas from design codes and other machine learning methods. The results showed that the NGBoost model achieved higher accuracy in mean shear strength prediction, with an R² of 0.9045 and an RMSE of 38.8 kN, outperforming existing formulas by over 50%. Additionally, the NGBoost model provided probabilistic predictions of shear strength as probability density functions, enabling reliable confidence intervals. This demonstrated the capability of the data-driven NGBoost approach for robust shear strength evaluation of RC deep beams. Overall, the results illustrated that the proposed probabilistic prediction approach dramatically surpassed the current formulas adopted in design codes and machine learning models in both prediction accuracy and robustness. Full article

The main goal of the present study is to investigate the capability of hybridizing the imperialist competitive algorithm (ICA) with an intelligent, robust, and data-driven technique named the light gradient boosting machine (LightGBM) to estimate the compressive strength of geo-polymer concrete (CSGCo). The hyper-parameters of the LightGBM algorithm have been optimized based on ICA and its accuracy improved. The obtained results from the proposed hybrid ICA-LightGBM are compared with the traditional LightGBM model as well as four different topologies of artificial neural networks (ANN) comprising a multi-layer perceptron neural network (MLP), radial basis function (RBF), generalized feed-forward neural network (GFFNN), and Bayesian regularized neural network (BRNN). The results of these models were compared based on three evaluation indices of R², RMSE, and VAF for providing an objective evaluation of the performance and capability of the predictive models. Concerning the outcomes, the ICA-LightGBM with the R² of (0.9871 and 0.9805), RMSE of (0.4703 and 1.3137), and VAF of (98.5773 and 98.0397) for training and testing phases, respectively, was a superior predictor to estimate the CSGCo compared to the LightGBM with the R² of (0.9488 and 0.9478), RMSE of (0.9532 and 2.1631), and VAF of (94.3613 and 94.5173); the MLP with the R² of (0.9067 and 0.8959), RMSE of (1.3093 and 3.3648), and VAF of (88.9888 and 84.9125); the RBF with the R² of (0.8694 and 0.8055), RMSE of (1.4703 and 5.0309), and VAF of (86.3122 and 66.1888); the BRNN with the R² of (0.9212 and 0.9107), RMSE of (1.1510 and 2.6569), and VAF of (91.4168 and 90.5854); and the GFFNN with the R² of (0.9144 and 0.8925), RMSE of (1.1525 and 2.9415), and VAF of (91.4092 and 88.9088). Hence, the proposed ICA-LightGBM algorithm can be efficiently used in anticipating the CSGCo. Full article

This paper forms a set of three-dimensional temperature field simulation methods considering the influence of sunshine shadow based on the DFLUX subroutine and FILM subroutine interface provided by the Abaqus platform to simulate the three-dimensional temperature field of concrete bridge towers and study its distribution law. The results show that the method has high accuracy for shadow recognition and temperature field calculation. The maximum difference between the shadow recognition results and the theoretical calculation value was only 19.1 mm, and the maximum difference between the simulated temperature and the measured temperature was 3.3 °C. The results of analyzing the temperature field of the concrete bridge tower using this algorithm show that the temperature difference between the opposite external surface of the tower column can reach 11.6 °C, which is significantly greater than the recommended temperature difference value of 5 °C in the specifications. For the concrete bridge tower, in the thickness direction of the tower wall, the temperature change was obvious only at a range of 0.3 m from the external surface of the tower wall, and the temperature change in the remaining range was small. In addition, the temperature gradient distribution of the sunshine temperature field in the direction of wall thickness conformed to the exponential function T(x) = T₀e^−αx + C. Additionally, the data fitting results indicate that using the temperature data at a distance of 0.8 m from the external surface as the calculation parameter in the function can achieve the ideal fitting result. Full article

The real temperature distribution within 24 h of the main beam in a single-tower hybrid beam cable-stayed bridge is analysed according to its actual section and material parameters, as well as other factors of local atmospheric temperature, geographical environment, and solar intensity. The results show that the internal temperature distribution in the steel–concrete composite beam is uneven, and the temperature of the steel is higher than that at the surface of the concrete slab. Then, a finite element model of the whole bridge is established using the thermal–mechanical sequential coupling function in ABAQUS to acquire the structural response under the action of a 24-h temperature field. The results show that the vertical temperature gradients have a great influence on the longitudinal stress in the lower flange of the steel I-beam, with a maximum compressive stress of 11.9 MPa in the daytime and a maximum tensile stress of 13.36 MPa at midnight. The temperature rise leads to a downward deflection of the main span, and the maximum deflection occurs at the 1/4 main span. There was an obvious temperature gradient in the concrete slab, with a difference between the maximum and minimum value of 14 °C. Similarly, the longitudinal compressive stress of the concrete slab increases with increasing temperature in the daytime, but the peak time is obviously inconsistent with that of the steel beam. Full article