Search Results (16,921)

Bridge health monitoring and machine learning are increasingly intertwined for civil engineers and artificial intelligence experts. Bridges’ poor health can result in severe outcomes if not addressed in time. Therefore, continuous monitoring is required to detect any anomaly or damage. Sensors, such as accelerometers, inclinometers, thermistors, etc., can help actively monitor these bridges. The signals from these sensors help record physiological activities. Such activities are helpful for anomaly detection, damage localization, and bridge health predictions with the help of machine learning algorithms. The proposed method extracts features from the dynamic response of a bridge to ambient excitation. It focuses on processing the signal received from different accelerometers installed on a steel railway bridge to determine the location of the damage and the level of the damage predictions. Initially, features are extracted from time-series data; then, they are fed to a deep neural network after some pre-processing. Normal and augmented data are used with different parameter tuning for results. Original data is also subdivided, and the effect of data slicing on the predictions is investigated. The results show that one-fourth of the slicing of the original data gives the best results for training and testing accuracy with a deep neural network. The results show that the reduced matrix representation, particularly the 40 × 40 feature slicing, improved the classification performance for the predefined bridge scenario classes under the considered experimental settings. For bridge scenario classification, the best reported accuracy was 93.54%, while for damage intensity classification the best reported accuracy was 98.21%. In the DNN-based optimizer comparison, the Adam optimizer achieved higher and more stable performance than Stochastic Gradient Descent (SGD), with test accuracies of 92.3% and 93.7% compared with 75.2% and 86.4%, respectively. It is also observed that the Adam optimizer outperformed Stochastic Gradient Descent (SGD) in terms of both damage localization and damage intensity estimation. Full article

In this paper, we propose a novel generative adversarial network (GAN)-based joint localization and mapping (JLAM) method using angle difference of arrival (ADOA) measurements for millimeter-wave (mmWave) communication systems. The proposed method adopts a deep auto-encoder neural network as the discriminator of the GAN and models the generator as an explicit geometric ADOA function of the access point (AP) positions and the mobile terminal (MT) position, rather than as a conventional black-box neural network. By exploiting the two-dimensional distribution characteristics of high-dimensional ADOA vectors collected at a large number of random and unknown MT positions, the proposed method learns the ADOA data distribution and transforms it into the AP geometric topology. Then, the MT positions and the indoor map are estimated based on the recovered physical and virtual AP topology. The simulation results show that, under the representative setting with $N=2000$ measured ADOA vectors and $\sigma =2^{\circ }$ AOA measurement noise, the proposed method achieves an average localization error of about 0.25 m, compared with about 0.60 m for the JADE algorithm, corresponding to an error reduction of approximately $58\%$. The proposed method also provides more accurate room boundary estimation than JADE, confirming its effectiveness for mmWave JLAM. Full article

The safe disposal of spent fuel and high-level radioactive waste has become a critical bottleneck restricting the sustainable development of nuclear energy, and 3D geological modeling serves as a core technology for repository siting and safety assessment. Taking the upper member of the Lower Cretaceous Bayingobi Formation in the Tamusu area as the research object, this study focuses on sedimentary facies identification, lithofacies prediction, 3D geological modeling, and candidate site optimization. A convolutional neural network (CNN) + attention algorithm is proposed for high-precision lithofacies identification, and a Geo-CVAE-GAN model is constructed to address data sparsity and reconstruct 3D geological models. Following the workflow of single-well fine analysis, multi-method fusion prediction, and 3D geological modeling, the Sequential Indicator Simulation (SIS) algorithm is improved to build a 3D lithofacies model, and four-property parameter modeling is completed under facies control. Optimal sites are delineated via 3D spatial superimposition based on parameter thresholds. The results show that favorable mudstone layers display a dual-layer structure: stable thick layers in deep strata and thin superimposed layers in shallow strata. A preliminary total area of approximately 165 km² is identified in Preselected Sections I and II, with target intervals at a 400–800 m depth, mud content exceeding 75%, and excellent physical properties, including low porosity, low permeability, and low water saturation. This study reveals the spatial distribution of favorable mudstone in the Tamusu area, and the preferred zones fully meet the siting criteria for high-level radioactive waste repositories, providing a reliable geological basis and technical support for subsequent exploration and engineering design. Full article

Fixed-bottom or floating offshore structures are the foundations, platforms, and associated infrastructure that allow for oil and gas production systems, offshore wind turbines, and cabling. The remote nature of these structures and the harsh environment with high variability in wind, waves, currents, and weather make construction activity very difficult and unpredictable; the cost of variation in the schedule can lead to high construction vessel and personnel costs. The adoption of artificial intelligence using trends observed in historical data can help achieve more accurate construction costs and schedule predictions, reducing the capital expenditure cost of installation. A resource-significant activity, sometimes called a resource-critical activity or high-resource-demand activity, is an activity on a construction or project schedule that consumes a disproportionately large share of one or more resources compared with others. Plant Design Modelling (PDM) is a digital process that creates and manages a detailed 3D model of a building’s physical and functional characteristics and semantic information, such as cost and schedule. PDM serves as a single source of truth for multidisciplinary activities and, therefore, serves as a rich data source for various construction applications, including project scheduling and cost estimation. Neural networks (NNs), a subset of machine learning algorithms inspired by the human brain, excel at identifying patterns in complex datasets and making predictions, such as forecasting costs based on non-linear relationships and historical trends. Data from an offshore structure modification project were extracted from Aveva’s Everything PDM, focusing on installation activities to create a dataset for machine learning model training. The structured data extracted exhibit non-linear patterns; therefore, linear, regularised linear, robust linear, and the ensemble (tree-based) models and supervised neural network models with varied architecture and hyperparameter values were evaluated and compared. The best performance was obtained using the deep-optimised ANN model. The result obtained is consistent with previous studies. The neural network models show a superior ability to predict the non-linear nature of offshore construction activities’ time. Full article

Aluminum alloy hot rolling features diverse varieties, large variations in incoming strip thickness, and strong process nonlinearity. Traditional rolling force prediction models rely on simplified physical assumptions and poor adaptability, making it hard to satisfy high-precision production requirements. This paper presents a mechanism–data dual-driven PSO-BP neural network method for rolling force prediction which is applicable to the rolling temperature range of 320 °C to 520 °C. The SIMS mechanism model is employed as a physical constraint, and a hybrid PSO-GD algorithm optimizes the initial weights and thresholds of the BP network, avoiding the local optimum issue of conventional BP. The rolling mechanism model is embedded into the loss function to deeply integrate physical laws and data-driven learning. Validation using 508 sets of field data from 5083 aluminum alloy hot rolling shows that the model achieves a M_APE of 5.0794% and R² of 0.9254, significantly outperforming the traditional mechanism model (8.91%) and standard BP (8.77%). The proposed model preserves physical interpretability while utilizing data-driven adaptability, offering an effective approach for high-precision rolling force prediction and improving the dimensional accuracy of hot-rolled aluminum alloy sheets. Full article

Grasslands represent one of the most extensive terrestrial biomes globally, covering approximately one-third of the Earth’s land surface, yet they are increasingly threatened by land-use change and overgrazing, underscoring the need for reliable monitoring approaches. This study compares the performance of machine learning and deep learning algorithms for grassland mapping using multi-source remote sensing data derived from Sentinel-1, Sentinel-2, and terrain variables. The research was conducted in Mpumalanga Province, South Africa, a heterogeneous landscape comprising lowland savannas, high-altitude grasslands, escarpments, and riverine wetlands. Random Forest (RF) and Support Vector Machine (SVM) classifiers were implemented in Google Earth Engine using fused satellite and terrain datasets with field-collected samples for training and validation, while a One-Dimensional Convolutional Neural Network (1D-CNN) was developed in Python 3.13.5 using the same inputs. Results demonstrate that integrating multi-source data improves classification accuracy, with radar-based features contributing the most. RF achieved the highest performance, with an overall accuracy of 97.7% and grass-class precision, recall, and F1-score exceeding 0.97, closely followed by the 1D-CNN with 91% overall accuracy and complete grass detection. In contrast, SVM performed notably lower with an overall accuracy of 80,8%. These findings highlight the effectiveness of advanced learning approaches for grassland mapping and support their application in ecological restoration and environmental management. Full article

This paper proposes a trajectory-tracking algorithm for reentry vehicles based on KalmanNet with a time-varying observation matrix. First, a nonlinear state evolution model of the reentry vehicle and a radar measurement model are developed in the radar measurement coordinate system. Then, inspired by the computation process of the Kalman gain (KG) in the extended Kalman filter (EKF), the recurrent neural network (RNN) architecture of KalmanNet is improved. The gated recurrent unit (GRU) originally used to track process noise statistics is removed. Instead, the input features are redesigned to directly estimate the prior state covariance. Furthermore, another GRU is introduced to estimate the time-varying observation matrix, considering the nonlinear characteristics of radar measurements. The calculated observation matrix is fed into both the GRU responsible for estimating the covariance of the difference between the predicted observation and the observed value and the fully connected layer that computes the KG. Finally, the proposed method is compared with six representative algorithms, including EKF, particle filter (PF), unscented Kalman filter (UKF), convolutional neural network (CNN), Long Short-Term Memory (LSTM), and the original KalmanNet. Simulation results demonstrate that the proposed method achieves the highest estimation accuracy, while its computational time remains nearly the same as that of the original KalmanNet. Monte Carlo simulations under three model-mismatch conditions are conducted to validate the robustness of the proposed method. Full article

Effective condition monitoring (CM) in the mining industry is crucial for operational excellence, given the harsh environments, continuous operation, and high-value nature of assets. Traditional fault diagnosis methods like vibration analysis often prove inadequate due to signal noise, logistical challenges for sensor placement, and limitations in detecting subtle failures. This paper addresses these challenges by proposing an advanced contactless diagnostic system that integrates Infrared Thermography (IRT) with an optimized Convolutional Neural Network (CNN) for detecting machinery faults in mining operations. The core of the approach involves a customized ResNet-50 architecture, chosen for its inherent ability to extract hierarchical features directly from raw thermal image data, thereby circumventing the laborious and error-prone process of manual feature engineering. Recognizing the profound impact of hyperparameters on model performance, a novel optimization strategy is developed. This strategy utilizes an amended Salp Swarm Algorithm (SSA), which incorporates a Levy flight mutation strategy and improved position update mechanisms to enhance its exploration capabilities and prevent premature convergence, ensuring a thorough search of the complex hyperparameter space. The proposed methodology is rigorously evaluated using thermal images acquired from a heavy-duty belt conveyor system at the JARO S.A. mine. The optimized ResNet-50 model achieved a remarkable validation accuracy of 97.22%, demonstrating superior performance. Comparative analysis showed that our model significantly outperformed other state-of-the-art deep learning architectures, such as InceptionV3 and ResNet-18, as well as other metaheuristic optimization algorithms, yielding a 15.6% improvement over the basic SSA. This robust performance, combined with efficient convergence, underscores the model’s capacity for accurate and timely fault identification, paving the way for proactive maintenance, reduced downtime, and enhanced safety in demanding mining environments. Full article

The roughness coefficient is a vital parameter in river dynamics calculations, and its accuracy is crucial for simulating water flow. Various factors contribute to channel roughness, and the underlying mechanisms are quite complex. There is a strong spatiotemporal correlation, which complicates the calculations, particularly when hydrological data is lacking or insufficient. In this study, we solved the two-dimensional shallow-water equations using the Population Simplex Evolution (PSE) with the Finite Volume Method (FVM). This approach allowed us to obtain samples for calibrating channel roughness coefficients. To enhance the analysis, we introduced a Convolutional Neural Network (CNN) to reduce the dimensionality of input parameters and extract the temporal characteristics of the flow series. Notably, we integrated a Transformer to capture the spatial characteristics of the time series. By combining the PSE-FVM with the CNN-Transformer, we effectively calibrated the roughness coefficients. Our findings indicated that the integrated PSE-FVM and CNN-Transformer model achieved high accuracy and efficiency in this calibration process. Specifically, the cross-correlation coefficients exceeded 0.90 for calibration results from September to December 2020. We recorded an average absolute deviation of 7 cm between the calculated and measured maximum water levels, and the average calibration runtime ratio was approximately 0.19% when comparing the CNN-Transformer to the PSE-FVM. Importantly, this approach could be used for rivers with incomplete hydrological data. Our work highlighted spatiotemporal correlations between roughness coefficients and their influencing factors, thereby facilitating the integration of river dynamics models with intelligent algorithms. Therefore, these findings may serve as a valuable reference for river numerical analysis, flood impact assessment, and the development of digital twins and information systems for water-related engineering projects. Full article

Plate–fin heat exchangers (PFHEs) are widely used in petrochemical, energy and electric power, aerospace, and other industries with large heat transfer requirements. The development of performance prediction and optimization methods for PFHEs has become increasingly important in the design and operation of such heat exchangers (HEs). This paper establishes a database of flow and heat transfer characteristics for four types of PFHEs with different structural parameters. Based on this database, the back-propagation artificial neural network (BP-ANN) model was optimized using the particle swarm optimization (PSO) algorithm to form the PSO-BP-ANN model for the performance prediction of these four types of PFHEs. This combination has been found to improve the prediction accuracy and generalization ability of the BP-ANN model. Additionally, the non-dominated sorting genetic algorithm II (NSGA-II) method was used to characterize the relationship between four structural parameters to be optimized (the length, height, spacing, and thickness of the HE fin) and the two objective functions (j and f) of the serrated PFHE in laminar flow. This enables the Pareto optimal solution to be obtained. The results show that, under laminar flow conditions (Re = 800), the serrated fin HE achieves the best heat transfer performance when the fin height, spacing, thickness, and length are 9.29, 1.22, 0.16, and 3.06, respectively. Full article

The marine capture fisheries sector of the Philippines employs approximately 2.3 million Filipinos, yet recent declines (including a 15.3% drop in Q1 2026 production relative to Q1 2025) underscore the need for forecasting systems resolved at the regional and sectoral level. Existing Philippine approaches rely on univariate classical time-series methods and seldom integrate multivariate oceanographic predictors. This study addresses three questions: (RQ1) How do nine candidate machine learning algorithms compare in forecasting regional fish production from environmental predictors? (RQ2) Which environmental predictors most strongly drive model output, as quantified by explainable AI (XAI) SHAP-based feature attribution? (RQ3) To what extent do model performance and predictor importance vary across regions? Across 32 region–sector panels spanning 2002–2025, kernel and neural network models were selected as the best-performing architecture in 26 of 32 panels (81.3%), achieving a mean composite score 12.7% higher than tree-based ensembles, a gap attributable to extrapolation along trending physical predictors. Feature attribution identified the partial pressure of CO${}_2$ as the leading driver in both sectors, exceeding the second-ranked variable by factors of 2.5 (commercial) and 3.4 (marine municipal). Regional heterogeneity in retained predictors, winning algorithms, and SHAP attribution rankings supports region-specific forecasting as a necessary design choice. Mean absolute percentage error of 22–25% and directional accuracy of 0.62–0.66 indicate operational utility for early-warning applications, establishing a basis for evidence-driven priority-setting in Philippine fisheries governance. Full article

Hellenic Open University has developed Onlabs, a virtual biology laboratory for its students to be trained before they use its on-site lab. The evaluation of the user’s performance in the virtual lab with respect to a particular experimental procedure is done with a scoring algorithm specifically designed for this purpose. For the calculation of the user’s overall progress score, an Artificial Neural Network (ANN) is used. The ANN, trained with data from random plays evaluated by biology experts, achieves significant convergence. Yet, when the trained ANN is used for the real-time evaluation of the user’s performance, it produces unrealistic scores, that is, incompatible with human experience, such as unscaled score values as well as a high increase in score with the execution of secondary actions. To overcome this problem, the ANN’s weights are fine-tuned with the use of a Genetic Algorithm (GA) and two algorithms of Swarm Intelligence (SI), Whale Optimization Algorithm (WOA) and Firefly Algorithm (FA). Among those, GA achieves successful optimization of the ANN’s weights, resulting in a more realistic score mechanism. Full article

Deep learning (DL)-based percussion methods in concrete-filled steel-tube (CFST) void detection have gained much attention. However, the detection signal contains a large amount of noise, which affects the accuracy of qualitative and quantitative analyses of the subsequent detection results. To improve the signal-to-noise ratio (SNR) during percussion detection, this study proposes a CFST void detection method using the good point set and vibrational snow ablation optimizer (GVSAO) algorithm and dual-channel parallel convolutional neural networks (CNNs). The proposed method employs the gram angle field (GAF) to transform percussive sound signals into images. It then constructs a dual-channel parallel CNN structure, where the GAF is decomposed into the following two maps: the gram angle sum field (GASF) and the gram angle difference field (GADF). These maps are simultaneously fed into the CNN for training. The outputs from the two channels are concatenated and fused. Finally, the GVSAO algorithm was used for model optimization to improve convergence speed and recognition accuracy. Both the temporal and spatial characteristics of the knocking sound signal are fully preserved, while the interference of different construction noises is effectively avoided. Validation experiments were conducted on CFST specimens with different heights of voids (0, 50, 100, and 150 mm) under different pressure loads. The original sample dataset and the signal-enhanced dataset were obtained by adding background noise with different SNRs. The test results show that the prediction accuracies on the original signal dataset are consistently above 98.74%. Among them, the accuracy achieves 100% at pressure loads of 0 and 50 tons. Additionally, the prediction accuracies on the signal-enhanced dataset are all above 97.2%, indicating that the model maintains a high level of classification performance. This suggests that the model can effectively suppress noise and exhibits excellent robustness. Full article

The sustainable valorization of spontaneous flora biomass for the recovery of high value-added phytochemicals represents a key opportunity within the circular bioeconomy, yet it remains constrained by the environmental limitations of conventional extraction solvents and the lack of data-driven optimization frameworks. In this study, Natural Deep Eutectic Solvents (NADES) composed of betaine and 1,3-propanediol were designed and applied as bio-based extraction media for the recovery of bioactive metabolites from Artemisia annua L. spontaneous biomass in the context of green extraction and sustainable resource utilization. Two liquid–solid extraction techniques, namely vortex-assisted extraction and ultrasound-assisted extraction, were evaluated. The influence of key process parameters, including the eutectic component molar ratio, water content, solid-to-liquid (S/L) ratio, extraction temperature, and extraction time, was systematically investigated. Results demonstrated that extraction efficiency was strongly dependent on both solvent composition and process conditions, with distinct optimum parameters for different phytochemical classes. Maximum total polyphenol content (52.08 mg GAE/mL) was achieved via ultrasound-assisted extraction at 20 °C for 15 min, using a 1:3 NADES ratio with 40% water dilution and S/L = 1:5, while the highest flavonoid yield (17.34 mg QE/mL) was obtained by vortex-assisted extraction for 45 min using a 1:6 NADES ratio under the same dilution and S/L conditions. To identify extraction conditions associated with improved process efficiency, a hybrid modeling approach combining deep neural networks with the Success-History-based Adaptive Differential Evolution (SHADE) algorithm was employed, enabling high-accuracy prediction of extraction performance across a broad parameter space. The proposed framework demonstrates the feasibility of integrating green solvent design with machine learning-driven process modeling for the efficient valorization of underutilized plant biomass, contributing to the development of resource-efficient, sustainable extraction protocols, consistent with principles of process intensification and resource-efficient extraction strategies. Full article

This paper presents an adaptive neural-network-based algorithm for chattering mitigation in sliding mode control (SMC) of parallel multicellular DC/AC power converters. Although conventional SMC provides strong robustness against parameter uncertainties, external disturbances, and load variations, its discontinuous control action often generates chattering, resulting in excessive switching activity and reduced converter performance. To address this limitation, a computationally efficient adaptive neural network is integrated into the SMC framework to approximate the discontinuous switching term and generate a smooth control signal. The proposed algorithm updates neural network parameters online through an adaptive learning mechanism, enabling real-time compensation of modeling uncertainties while preserving the inherent robustness of SMC. The resulting adaptive neural network sliding mode control (ANN-SMC) algorithm is formulated to ensure accurate output voltage tracking, balanced operation of converter cells, and reduced switching oscillations. Extensive simulation studies are conducted under different operating scenarios, including load variations and system disturbances. The performance of the proposed method is evaluated against classical SMC using quantitative indicators related to tracking accuracy, dynamic response, robustness, and chattering suppression. The results demonstrate that the ANN-SMC algorithm significantly reduces high-frequency oscillations while improving transient behavior and maintaining robust operation. These findings indicate that the proposed adaptive learning-based control algorithm constitutes an effective and scalable solution for advanced power conversion systems operating under uncertain conditions. Full article