Search Results (34)

This work introduces a new initialization scheme for complex-valued layers in physics-informed neural networks that use holomorphic activation functions. The proposed method is derived empirically by estimating the activation and gradient gains specific to complex-valued tanh and sigmoid functions through Monte Carlo simulations. These estimates are then used to formulate variance-preserving initialization rules. The effectiveness of these formulas is evaluated on several second-order complex-valued ordinary differential equations derived from the Helmholtz equation, a fundamental model in wave theory and theoretical physics. Comparative experiments show that complex-valued neural solvers initialized with the proposed method outperform traditional real-valued physics-informed neural networks in terms of both accuracy and training dynamics. Full article

Sub-meter-resolution Polarimetric Synthetic Aperture Radar (PolSAR) imagery enables precise building footprint extraction but introduces complex scattering correlated with fine spatial structures. This change renders both traditional methods, which rely on simplified scattering models, and existing deep learning approaches, which sacrifice spatial detail through multi-looking, inadequate for high-precision extraction tasks. To address this, we propose an Orthogonal Dual-Resolution Network (ODRNet) for end-to-end, precise segmentation directly from single-look complex (SLC) data. Unlike complex-valued neural networks that suffer from high computational cost and optimization difficulties, our approach decomposes complex-valued data into its orthogonal real and imaginary components, which are then concurrently fed into a Dual-Resolution Branch (DRB) with Bilateral Information Fusion (BIF) to effectively balance the trade-off between semantic and spatial details. Crucially, we introduce an auxiliary Polarization Orientation Angle (POA) regression task to enforce physical consistency between the orthogonal branches. To tackle the challenge of diverse building scales, we designed a Multi-scale Aggregation Pyramid Pooling Module (MAPPM) to enhance contextual awareness and a Pixel-attention Fusion (PAF) module to adaptively fuse dual-branch features. Furthermore, we have constructed a VHR PolSAR building footprint segmentation dataset to support related research. Experimental results demonstrate that ODRNet achieves 64.3% IoU and 78.27% F1-score on our dataset, and 73.61% IoU with 84.8% F1-score on a large-scale SLC scene, confirming the method’s significant potential and effectiveness in high-precision building extraction directly from SLC. Full article

The rapid integration of renewable energy sources and increasing complexity of modern power grids demand advanced forecasting tools capable of simultaneously predicting multiple interconnected variables. While time series foundation models (TSFMs) have demonstrated remarkable zero-shot forecasting capabilities across diverse domains, their application in power grid operations remains limited due to complex coupling relationships between load, price, emissions, and renewable generation. This paper proposes GridFM, a novel physics-informed foundation model specifically designed for multi-task energy forecasting in power systems. GridFM introduces four key innovations: (1) a FreqMixer adaptation layer that transforms pre-trained foundation model representations to power-grid-specific patterns through frequency domain mixing without modifying base weights; (2) a physics-informed constraint module embedding power balance equations and zonal grid topology using graph neural networks; (3) a multi-task learning framework enabling joint forecasting of load demand, locational-based marginal prices (LBMP), carbon emissions, and renewable generation with uncertainty-weighted loss functions; and (4) an explainability module utilizing SHAP values and attention visualization for interpretable predictions. We validate GridFM using over 10 years of real-time data from the New York Independent System Operator (NYISO) at 5 min resolution, comprising more than 10 million data points across 11 load zones. Comprehensive experiments demonstrate that GridFM achieves state-of-the-art performance with an 18.5% improvement in load forecasting MAPE (achieving 2.14%), a 23.2% improvement in price forecasting (achieving 7.8% MAPE), and a 21.7% improvement in emission prediction compared to existing TSFMs including Chronos, TimesFM, and Moirai-MoE. Ablation studies confirm the contribution of each proposed component. The physics-informed constraints reduce physically inconsistent predictions by 67%, while the multi-task framework improves individual task performance by exploiting inter-variable correlations. The proposed model provides interpretable predictions supporting the Climate Leadership and Community Protection Act (CLCPA) 2030/2040 compliance objectives, enabling grid operators to make informed decisions for sustainable energy transition and carbon reduction strategies. Full article

Engineering education is based on experiential learning, but the problem is that in laboratory conditions, it is difficult to give feedback to the students in real time and personalize this feedback. The paper introduces the proposal of an innovative approach to the laboratories, called Adaptive Lab Mentor (ALM), which combines the technologies of Artificial Intelligence (AI), Internet of Things (IoT), and sensor technology to facilitate intelligent and customized laboratory setting. ALM is supported by a new real-time multimodal sensor fusion model in which a sensor-instrumented laboratory is used to record real-time electrical measurements (voltage and current) which are used in parallel with symbolic component measurements (target resistance) with a lightweight, dual-input Convolutional Neural Network (1D-CNN) running on an edge device. In this initial validation, visual context is presented as a symbolic target value, which establishes a pathway for the future integration of full computer vision. The architecture will enable monitoring of the student progress, making error diagnoses within a short time period, and provision of adaptive feedback based on information available in the context. To test this strategy, a high-fidelity model of an Ohm Laboratory was developed. LTspice was used to generate a huge amount of current and voltage time series of various circuit states. The trained model achieved 93.3% test accuracy and demonstrated that the proposed system could be applied. The ALM model, compared to the current Intelligent Tutoring Systems, is based on physical sensing and edge AI inference in real-time, as well as adaptive and safety-sensitive feedback throughout hands-on engineering demonstrations. The ALM framework serves as a blueprint for the new smart laboratory assistant. Full article

This study introduces the Graph-Structured Physics-Informed DeepONet (GS-PI-DeepONet), a novel neural network framework designed to address the challenges of solving parametric Partial Differential Equations (PDEs) in structural analysis, particularly for problems with complex geometries and dynamic boundary conditions. By integrating Graph Neural Networks (GNNs), Deep Operator Networks (DeepONets), and Physics-Informed Neural Networks (PINNs), the proposed method employs graph-structured representations to model unstructured Finite Element (FE) meshes. In this framework, nodes encode physical quantities such as displacements and loads, while edges represent geometric or topological relationships. The framework embeds PDE constraints as soft penalties within the loss function, ensuring adherence to physical laws while reducing reliance on large datasets. Extensive experiments have demonstrated the GS-PI-DeepONet’s superiority over traditional Finite Element Methods (FEMs) and standard DeepONets. For benchmark problems, including cantilever beam bending and Hertz contact, the model achieves high accuracy. In practical applications, such as stiffness analysis of a recliner mechanism and strength analysis of a support bracket, the framework achieves a 7–8 speed-up compared to FEMs, while maintaining fidelity comparable to FEM, with R² values reaching up to 0.9999 for displacement fields. Consequently, the GS-PI-DeepONet offers a resolution-independent, data-efficient, and physics-consistent approach for real-time simulations, making it ideal for rapid parameter sweeps and design optimizations in engineering applications. Full article

The advancement of smart grid technologies necessitates the integration of cutting-edge computational methods to enhance predictive energy optimization. This study proposes a multi-faceted approach by incorporating (1) Deep Reinforcement Learning (DRL) agents trained using data from digital twins (DTs) to optimize energy consumption in real time, (2) Physics-Informed Neural Networks (PINNs) to seamlessly embed physical laws within the optimization process, ensuring model accuracy and interpretability, and (3) blockchain (BC) technology to facilitate secure and transparent communication across the smart grid infrastructure. The model was trained and validated using comprehensive datasets, including smart meter energy consumption data, renewable energy outputs, dynamic pricing, and user preferences collected from IoT devices. The proposed framework achieved superior predictive performance with a Mean Absolute Error (MAE) of 0.237 kWh, Root Mean Square Error (RMSE) of 0.298 kWh, and an R-squared (R²) value of 0.978, indicating a 97.8% explanation of data variance. Classification metrics further demonstrated the model’s robustness, achieving 97.7% accuracy, 97.8% precision, 97.6% recall, and an F1 Score of 97.7%. Comparative analysis with traditional models like Linear Regression, Random Forest, SVM, LSTM, and XGBoost revealed the superior accuracy and real-time adaptability of the proposed method. In addition to enhancing energy efficiency, the model reduced energy costs by 35%, maintained a 96% user comfort index, and increased renewable energy utilization to 40%. This study demonstrates the transformative potential of integrating PINNs, DT, and blockchain technologies to optimize energy consumption in smart grids, paving the way for sustainable, secure, and efficient energy management systems. Full article

Time series models are widely used to examine temporal dynamics and uncover patterns across diverse fields. A commonly employed approach for modeling such data is the (Vector) Autoregressive (AR/VAR) model, in which each variable is represented as a linear combination of its own and others’ lagged values. However, the traditional (V)AR framework relies on the key assumption of stationarity, that autoregressive coefficients remain constant over time, which is often violated in practice, especially in systems affected by structural breaks, seasonal fluctuations, or evolving causal mechanisms. To overcome this limitation, Time-Varying (Vector) Autoregressive (TV-AR/TV-VAR) models have been developed, enabling model parameters to evolve over time and thus better capturing non-stationary behavior. Conventional approaches to estimating such models, including generalized additive modeling and kernel smoothing techniques, often require strong assumptions about basis functions, which can restrict their flexibility and applicability. To address these challenges, we introduce a novel framework that leverages physics-informed neural networks (PINN) to model TV-AR/TV-VAR processes. The proposed method extends the PINN framework to time series analysis by reducing reliance on explicitly defined physical structures, thereby broadening its applicability. Its effectiveness is validated through simulations on synthetic data and an empirical study of real-world health-related time series. Full article

The prestressed concrete-filled double skin steel tube (CFDST) lattice tower has emerged as a promising structural solution for large-capacity wind turbine systems due to its superior load-bearing capacity and economic efficiency. The steel–concrete composite adapter (SCCA) is a key component that connects the upper tubular steel tower to the lower lattice segment, transferring axial loads. However, the compressive behaviour of the SCCA remains underexplored due to its complex multi-shell configuration and steel–concrete interaction. This study investigates the axial compression behaviour of SCCAs through refined finite element simulations, identifying diagonal extrusion as the typical failure mode. The analysis clarifies the distinct roles of the outer and inner shells in confinement, highlighting the dominant influence of outer shell thickness and concrete strength. A sensitivity-based parametric study highlights the significant roles of outer shell thickness and concrete strength. To address the high cost of FE simulations, a 400-sample database was built using Latin Hypercube Sampling and engineering-grade material inputs. Using this dataset, five neural networks were trained to predict SCCA capacity. The Dropout model exhibited the best accuracy and generalization, confirming the feasibility of physics-informed, data-driven prediction for SCCAs and outperforming traditional empirical approaches. A graphical prediction tool was also developed, enabling rapid capacity estimation and design optimization for wind turbine structures. This tool supports real-time prediction and multi-objective optimization, offering practical value for the early-stage design of composite adapters in lattice turbine towers. Full article

Accurate and real-time environmental perception is essential for the safe and efficient execution of deep-sea mining operations. Semantic segmentation of forward-looking sonar (FLS) images plays a pivotal role in enabling environmental awareness for deep-sea mining vehicles (DSMVs), but remains challenging due to strong acoustic noise, blurred object boundaries, and long-range semantic dependencies. To address these issues, this study proposes DSM-Seg, a novel hybrid segmentation architecture combining Convolutional Neural Networks (CNNs) and Receptance Weighted Key-Value (RWKV) modeling. The architecture integrates a Physical Prior-Based Semantic Guidance Module (PSGM), which utilizes sonar-specific physical priors to produce high-confidence semantic guidance maps, thereby enhancing the delineation of target boundaries. In addition, a RWKV-Based Global Fusion with Semantic Constraints (RGFSC) module is introduced to suppress cross-regional interference in long-range dependency modeling and achieve the effective fusion of local and global semantic information. Extensive experiments on both a self-collected seabed terrain dataset and a public marine debris dataset demonstrate that DSM-Seg significantly improves segmentation accuracy under complex conditions while satisfying real-time performance requirements. These results highlight the potential of the proposed method to support intelligent environmental perception in DSMV applications. Full article

The increasing application of plain bearings in various industries, especially under challenging conditions like thin lubricating films and high temperatures, necessitates effective monitoring to prevent failures and ensure reliable performance. While sensor-based monitoring incurs significant costs and complex installation due to physical sensors and data acquisition systems, model-based tracking offers a more cost-effective alternative. Model-based monitoring relies on mathematical or physics-based models to estimate system behaviour, reducing the need for extensive sensor data. However, reliable results depend on real-time capable and precise simulation models. Conventional real-time modelling techniques, including analytical calculations, empirical formulas, and data-driven methods, exhibit significant limitations in real-world applications. Analytical methods often have a restricted range of applicability and do not match the accuracy of numerical methods. Meanwhile, data-driven approaches rely heavily on the quality and quantity of training data and are inherently constrained to their training domain. Recently, Physics-Informed Neural Networks (PINNs) have emerged as a promising solution for model-based monitoring to capture complex system behaviour. This approach combines physical modelling with data-driven learning, allowing for better generalisation beyond the training domain while reducing reliance on extensive data. Thus, this study presents an approach for load monitoring in radial plain bearings using PINNs. It extends the application of PINNs by relying solely on simple sensor inputs, such as radial load and rotational speed, to predict the hydrodynamic pressure and oil film thickness distribution under varying stationary conditions. The real-time model is trained, validated, and evaluated within and beyond the training domain using elastohydrodynamic simulation results. The developed real-time model enables load monitoring in plain bearings by identifying critical hydrodynamic pressure and oil film thickness values using readily available speed and load sensor data under varying stationary conditions. Full article

Urban building energy prediction is a critical challenge for sustainable city planning and large-scale retrofit prioritization. However, traditional data-driven models struggle to capture real urban environments’ spatial and morphological complexity. In this study, we systematically benchmark a range of graph-based neural networks (GNNs)—including graph convolutional network (GCN), GraphSAGE, and several physics-informed graph attention network (GAT) variants—against conventional artificial neural network (ANN) baselines, using both shape coefficient and energy use intensity (EUI) stratification across three distinct residential districts. Extensive ablation and cross-district generalization experiments reveal that models explicitly incorporating interpretable physical edge features, such as inter-building distance and angular relation, achieve significantly improved prediction accuracy and robustness over standard approaches. Among all models, GraphSAGE demonstrates the best overall performance and generalization capability. At the same time, the effectiveness of specific GAT edge features is found to be district-dependent, reflecting variations in local morphology and spatial logic. Furthermore, explainability analysis shows that the integration of domain-relevant spatial features enhances model interpretability and provides actionable insight for urban retrofit and policy intervention. The results highlight the value of physics-informed GNNs (PINN) as a scalable, transferable, and transparent tool for urban energy modeling, supporting evidence-based decision making in the context of aging residential building upgrades and sustainable urban transformation. Full article

Gas turbine (GT) modeling and optimization have been widely studied at the design level but still lacks focus on real-world operational cases. The concept of a digital twin (DT) allows for the interaction between operation data and the system dynamic performance. Among many DT studies, only a few focus on GT for thermal power plants. This study proposes a digital twin prototype framework including the following modules: process modeling, parameter estimation, and performance optimization. Provided with real-world power plant operational data, key performance parameters such as turbine inlet temperature (TIT) and specific fuel consumption (SFC) were initially unavailable, therefore necessitating further calculation using thermodynamic analysis. These parameters are then used as a target label for developing artificial neural networks (ANNs). Three ANN models with different structures are developed to predict TIT, SFC, and turbine power output (GTPO), achieving high R² scores of 94.03%, 82.27%, and 97.59%, respectively. Physics-informed neural networks (PINNs) are then employed to estimate the values of the air–fuel ratio and combustion efficiency for each time index. The PINN-based estimation resulted in estimated values that align with the literature. Subsequently, an unconventional method of detecting alarms by using conformal prediction were also proposed, resulting in a significantly reduced number of alarms. The developed ANNs are then combined with particle swarm optimization (PSO) to carry out performance optimization in real time. GTPO and SFC are selected as the primary metrics for the optimization, with controllable parameters such as AFR and a fine-tuned inlet guide vane position. The results demonstrated that GTPO could be optimized with the application of conformal prediction when the true GTPO is detected to be higher than the upper range of GTPO obtained from the ANN model with a conformal prediction of a 95% confidence level. Multiple PSO variants were also compared and benchmarked to ensure an enhanced performance. The proposed PSO in this study has a lower mean loss compared to GEP. Furthermore, PSO has a lower computational cost compared to RS for hyperparameter tuning, as shown in this study. Ultimately, the proposed methods aim to enhance GT operations via a data-driven digital twin concept combination of deep learning and optimization algorithms. Full article

Accurate real-time icing grid fields are critical for preventing ice-related disasters during winter and protecting property. These fields are essential for both mapping ice distribution and predicting icing using physical models combined with numerical weather prediction systems. However, developing precise real-time icing grids is challenging due to the uneven distribution of monitoring stations, data confidentiality restrictions, and the limitations of existing interpolation methods. In this study, we propose a new approach for constructing real-time icing grid fields using 1339 online terminal monitoring datasets provided by the China Southern Power Grid Research Institute Co., Ltd. (CSPGRI) during the winter of 2023. Our method integrates static geographic information, dynamic meteorological factors, and ice_kriging values derived from parameter-optimized Empirical Bayesian Kriging Interpolation (EBKI) to create a spatiotemporally matched, multi-source fused icing thickness grid dataset. We applied five machine learning algorithms—Random Forest, XGBoost, LightGBM, Stacking, and Convolutional Neural Network Transformers (CNNT)—and evaluated their performance using six metrics: R, RMSE, CSI, MAR, FAR, and fbias, on both validation and testing sets. The stacking model performed best, achieving an R-value of 0.634 (0.893), RMSE of 3.424 mm (2.834 mm), CSI of 0.514 (0.774), MAR of 0.309 (0.091), FAR of 0.332 (0.161), and fbias of 1.034 (1.084), respectively, when comparing predicted icing values with actual measurements on pylons. Additionally, we employed the SHAP model to provide a physical interpretation of the stacking model, confirming the independence of selected features. Meteorological factors such as relative humidity (RH), 10 m wind speed (WS₁₀), 2 m temperature (T₂), and precipitation (PRE) demonstrated a range of positive and negative contributions consistent with the observed growth of icing. Thus, our multi-source remote-sensing data-fusion approach, combined with the stacking model, offers a highly accurate and interpretable solution for generating real-time icing grid fields. Full article

Concrete dams are prone to various hidden dangers after long-term operation and may lead to significant risk if failed to be detected in time. However, the existing hollowing detection techniques are few as well as inefficient when facing the demands of comprehensive coverage and intelligent management for regular inspections. Hence, we proposed an innovative, non-destructive infrared inspection method via constructed dataset and proposed deep learning algorithms. We first modeled the surface temperature field variation of concrete dams as a one-dimensional, non-stationary partial differential equation with Robin boundary. We also designed physics-informed neural networks (PINNs) with multi-subnets to compute the temperature value automatically. Secondly, we obtained the time-domain features in one-dimensional space and used the diffusion techniques to obtain the synthetic infrared images with dam hollowing by converting the one-dimensional temperatures into two-dimensional ones. Finally, we employed adaptive joint learning to obtain the spatio-temporal features. We designed the experiments on the dataset we constructed, and we demonstrated that the method proposed in this paper can handle the low-data (few shots real images) issue. Our method achieved 94.7% of recognition accuracy based on few shots real images, which is 17.9% and 5.8% higher than maximum entropy and classical OTSU methods, respectively. Furthermore, it attained a sub-10% cross-sectional calculation error for hollowing dimensions, outperforming maximum entropy (70.5% error reduction) and OTSU (7.4% error reduction) methods, which shows our method being one novel method for automated intelligent hollowing detection. Full article

Inundation maps that show water depths that occur in the event of a flood are essential for protection. Especially information on timings is crucial. Creating a dynamic inundation map with depth data in temporal resolution is a major challenge and is not possible with physical models, as these are too slow for real-time predictions. To provide a dynamic inundation map in real-time, we developed a data-driven multi-step inundation forecast system for fluvial flood events. The forecast system is based on a convolutional neural network (CNN), feature-informed dense layers, and a recursive connection from the predicted inundation at timestep t as a new input for timestep t + 1. The forecast system takes a hydrograph as input, cuts it at desired timesteps (t), and outputs the respective inundation for each timestep, concluding in a dynamic inundation map with a temporal resolution (t). The prediction shows a Critical Success Index (CSI) of over 90%, an average Root Mean Square Error (RMSE) of 0.07, 0.12, and 0.15 for the next 6 h, 12 h, and 24 h, respectively, and an individual RMSE value below 0.3 m, for all test datasets when compared with the results from a physically based model. Full article