Search Results (130)

This paper proposes an integrated, stress-based framework for fatigue diagnosis of wind turbine blades that is tailored to field deployments where detailed structural design information is unavailable. The approach combines a data-driven reduced-order model (ROM) for directional damage equivalent loads (DELs) with a physics-based Soderberg index and a one-class support vector machine (SVM) anomaly detector. The framework is implemented and evaluated using measurements from a 2 MW onshore turbine equipped with blade-root strain gauges and standard SCADA monitoring. Ten-minute operating windows are formed by synchronizing SCADA records with high-frequency strain data, converting strain to stress, and computing DELs via Rainflow counting for flapwise, edgewise, and torsional blade root directions. SCADA inputs are summarized by their 10 min statistics and augmented with yaw misalignment features; these are used to train LightGBM-based ROMs that map operating conditions to directional DELs. On an independent test set, the DEL-ROM achieves coefficients of determination of approximately 0.87, 0.99, and 0.99 for flapwise, edgewise, and torsional directions, respectively, with small absolute errors relative to the measured DELs. The Soderberg index is then used to define conservative Normal/Alert/Alarm classes based on representative material parameters, while a one-class SVM is trained on DEL- and stress-based fatigue features to learn the distribution of normal operation. A simple AND-normal/OR-abnormal rule combines the Soderberg class and SVM label into a hybrid diagnostic decision. Application to the field dataset shows that the proposed framework provides interpretable fatigue-safety margins and reliably highlights operating periods with elevated flapwise fatigue usage, demonstrating its suitability as a scalable building block for digital-twin-enabled condition monitoring and life-extension assessment of wind turbine blades. Full article

Establishing a reduced-order model (ROM) of the wind turbine generator system (WTGS) preserving transient characteristics is a fundamental requirement for the transient stability analysis of power systems. This study introduces a novel dimension reduction framework based on trajectory eigenvalues, integrated with virtual inertia control (VIC). The framework facilitates multi-timescale state variable partitioning through a reversible mapping, which is derived from eigenvalue dominance and participation metrics. Based on this, dimension reduction is performed using singular perturbation theory (SPT). Taking a direct-drive wind turbine generator as an example, this paper establishes a ROM of the WTGS with VIC preserving transient characteristics, based on the proposed reduction method. Comprehensive time-domain simulations in MATLAB/Simulink validate the model’s accuracy and computational efficacy. Full article

This study addresses the system identification of a small autonomous surface vehicle (ASV) under moored conditions using Hankel dynamic mode decomposition with control (HDMDc) and its Bayesian extension (BHDMDc). Experiments were carried out on a Codevintec CK-14e ASV in the CNR-INM towing tank, under both irregular and regular head wave conditions. The ASV under investigation features a recessed moon pool, which induces nonlinear responses due to sloshing, thereby increasing the modeling challenge. Data-driven reduced-order models were built from measurements of vessel motions and mooring loads. The HDMDc framework provided accurate deterministic predictions of vessel dynamics, while the Bayesian formulation enabled uncertainty-aware characterization of the model response by accounting for variability in hyperparameter selection. Validation against experimental data demonstrated that both HDMDc and BHDMDc can predict the vessel’s response under unseen regular and irregular wave excitations. In conclusion, this study shows that HDMDc-based ROMs are a viable data-driven alternative for system identification, demonstrating for the first time their generalization capability for an unseen sea condition different from the training set, achieving high accuracy in reproducing the vessel dynamics. Full article

Flight safety is central to the certification process and relies on assessment methods that provide evidence acceptable to regulators. For drones operating as Advanced Air Mobility (AAM) platforms, this requires an accurate representation of the complex wind fields in urban areas. Large-eddy simulations (LES) of such environments generate datasets from hundreds of gigabytes to several terabytes, imposing heavy storage demands and limiting real-time use in simulation frameworks. To address this challenge, we apply a Convolutional Autoencoder (CAE) to compress a 40 m-deep section of an LES wind field. The dataset size was reduced from 7.5 GB to 651 MB, corresponding to a 91% compression ratio, while maintaining maximum magnitude errors within a few tenths of the spatio-temporal wind velocity. Predicted vehicle responses showed only marginal differences, with close agreement between the full LES and CAE reconstructions. These findings demonstrate that CAEs can significantly reduce the computational cost of urban wind field integration without compromising fidelity, thereby enabling the use of larger domains in real-time and supporting efficient sharing of disturbance models in collaborative studies. Full article

This study presents a reduced-order modeling framework for the shape optimization of a centrifugal pump. A database of CFD solutions is generated using Latin Hypercube Sampling over five design parameters to construct a reduced-order model based on proper orthogonal decomposition with radial basis function interpolation. The model predicts the flow field at the impeller–diffuser interface and pump outlet, enabling the estimation of impeller torque and total pressure rise. The active subspaces method is applied to reduce the dimensionality of the input space from five to four modified parameters. The sensitivity of the ROM is assessed with respect to further dimensionality reductions in the parameter space, POD mode truncation, and adaptive sampling. The model is then used to perform pump shape optimization via a quasi-Newton method, identifying the combination of the parameters that minimizes the impeller torque while satisfying a constraint on the head. The optimal result is validated through CFD analysis and compared against the Pareto front generated by a genetic algorithm. The work highlights the potential of model-order reduction techniques in centrifugal pump optimization. Full article

In this paper, the optimization of a harmonic-excited synchronous machine (HESM) is carried out. A two-phase harmonic exciter winding of the HESM provides brushless excitation and sufficient starting torque at any rotor position. The HESM under consideration is intended to be used for applications requiring speed control, especially in the field-weakening region. The novelty of the proposed approach is that a two-level optimization based on a two-stage model is used to reduce the computational burden. It includes a finite-element model that takes into account only the fundamental current harmonic (basic model). Using the output of the basic model, a reduced-order model (ROM) is parametrized. The ROM considers pulse-width-modulated components of the inverter output current, zero-sequence current injected into the stator winding, and harmonic excitation winding currents. A two-level optimization technique is developed based on the Nelder–Mead method, taking into account the significantly different computational complexity of the basic and reduced-order models. Optimization is performed considering two operating points: base and maximum speed. The results show that an optimized design provides significantly higher efficiency and reduced inverter power requirements. This allows the use of more compact and cheaper power switches. Therefore, the advantage of the presented approach lies in the computationally effective optimization of HESMs (optimization time is reduced by approximately three orders of magnitude compared to calculations using FEA alone), which enhances HESMs’ performance in various applications. Full article

This paper proposes a comprehensive numerical methodology for predicting Sound Transmission Loss (STL) in acoustic metamaterials. It integrates a high-fidelity model (HFM), using Thermoviscous Acoustics for detailed characterization, with a reduced-order model (ROM), employing Pressure Acoustics in COMSOL Multiphysics. The goal is a hierarchical approach balancing computational cost with predictive accuracy for metamaterial designs. The results show that HFM is crucial for understanding complex dissipative mechanisms, especially viscous and thermal losses in sub-wavelength features. The ROM offers rapid predictions for broader design exploration. The case studies compare these models against each other and to experimental results in the low-to-mid frequency range. The average STL values for both models diverged by a marginal 6 dB. Full article

Digital twins (DTs) offer significant promise for condition-based maintenance of floating offshore wind turbines (FOWTs); however, existing solutions typically compromise either on physical rigor or real-time computational performance. This paper presents a real-time DT framework that resolves this trade-off by embedding a hydro-elastic reduced-order model (ROM) that accurately captures structural dynamics and fluid–structure interaction. Integrated in a cloud-ready Internet of Things architecture, the ROM reconstructs full-field displacements, von Mises stresses, and fatigue metrics with near real-time responsiveness. Validation on the 5 MW OC4-DeepCWind semi-submersible platform shows that the ROM reproduces finite-element (FEM) displacements and stresses with relative errors below 1%. A three-hour load case is solved in 0.69 min for displacements and 3.81 min for stresses on a consumer-grade NVIDIA RTX 4070 Ti GPU—over two orders of magnitude faster than the full FEM model—while one million fatigue stress histories (1000 hotspots × 1000 operating scenarios) are processed in 37 min. This efficiency enables continuous structural monitoring, rapid *what-if* assessments and timely decision-making for targeted inspections and adaptive control. By effectively combining physics-based reduced-order modeling with high-throughput computation, the proposed framework overcomes key barriers to DT deployment: computational overhead, physical fidelity and scalability. Although demonstrated on a steel platform, the approach is readily extensible to composite structures and multi-turbine arrays, providing a robust foundation for cost-effective and reliable deep-water wind-energy operations. Full article

Effective real-time control systems require fast and accurate models. The roll bending models presented in this paper are proposed for a real-time control system for the design of the rolling schedule. The roll bending, with other factors, defines the shape of the roll surface, its convexity, and finally the shape of the final product of the flat rolling, its convexity, and its flatness. This paper presents accurate finite element (FE) models for a four-high mill. The models serve to obtain accurate solutions to the problem of roll bending, taking into account the rolling force, width of the rolling sheet (strip), initial shape of the roll surface, and the anti-bending force. The results of the FE simulation are used to train three models developed on the basis of the neural network (NN) for the solution of one direct and two inverse tasks. The pre-trained NN model gives accurate results and is faster than the FE model (FEM). The calculation time on a personal computer for one case of 3D FEM is 1 to 2 min, for 2D FEM it is 1 s, and for NN it is less than 1 ms. The results can be immediately used by other models of the real-time control system. A novelty of the research presented in the paper is the creation of complex applications of the FE method and an NN as a reduced-order model (ROM) for prediction of roll bending and calculation of sheet (strip) convexity, rolling, and anti-bending forces to obtain the required convexity. Full article

Effective real-time control systems require fast and accurate models. The thermal profile models of the rolls presented in this paper are proposed for a real-time control system for the design of the rolling schedule. The thermal profile of the roll defines the shape of the roll surface, its convexity, and, finally, the shape of the final product of the flat rolling, its convexity, and flatness. This paper presents accurate semi-analytical and finite element (FE) models, which serve to obtain an accurate solution of the joint thermal and mechanical problem, that is, heat transfer and thermal expansion. The results of the FE simulation are used for training the developed thermal model based on the neural network (NN) and for the creation of a dynamic reduced order model (ROM) of the roll surface profile. The pre-trained NN model gives accurate results and is faster than the FE model, but the model is not very useful for fast calculations in a real-time control system, mainly because the temperature distribution inside the rolls is not explicitly used in further calculations. In contrast, the ROM is fast and accurate and provides surface-shaped results that can be immediately used by other models of the real-time control system. The results of the simulation of the real process are also shown. Calculations of the roll campaign (more than 9 h) by the FEM model last several hours, while by the ROM less than 20 s. Full article

This study developed a novel data-driven indentation computation framework to characterize the indentation response and behavior by combining the reduced-order model (ROM), optimal technology, and indentation response curve. ROM was utilized to build a surrogated model to approximate the accuracy of the indentation response. The dataset was generated using the indentation test or physical model for ROM. Simplicial Homology Global Optimization (SHGO) was considered an optimal technology for searching for mechanical properties in inverse analysis. The developed framework was illustrated and verified using a numerical example. The results were compared with the actual value obtained by an indentation test. The results show that the developed framework characterizes the material mechanical property and indentation response well and agrees with the engineering practice. The proposed framework provides a feasible, scientific, helpful, and promising way to capture the material mechanical behavior and indentation response. Meanwhile, it also has essential reference significance for another engineering field. Full article

Model order reduction (MOR) is crucial for efficiently simulating large-scale RLCk models extracted from modern integrated circuits. Among MOR methods, balanced truncation offers strong theoretical error bounds but is computationally intensive and does not preserve passivity. In contrast, moment matching (MM) techniques are widely adopted in industrial tools due to their computational efficiency and ability to preserve passivity in RLCk models. Typically, MM approaches based on the rational Krylov subspace (RKS) are employed to produce reduced-order models (ROMs). However, the quality of the reduction is influenced by the selection of the number of moments and expansion points, which can be challenging to determine. This underlines the need for advanced strategies and reliable convergence criteria to adaptively control the reduction process and ensure accurate ROMs. This article introduces a frequency-aware multi-point MM (MPMM) method that adaptively constructs an RKS by closely monitoring the ROM transfer function. The proposed approach features automatic expansion point selection, local and global convergence criteria, and efficient implementation techniques. Compared to an established MM technique, MPMM achieves up to 16.3× smaller ROMs for the same accuracy, over 99.18% reduction in large-scale benchmarks, and up to 4× faster runtime. These advantages establish MPMM as a strong candidate for integration into industrial parasitic extraction tools. Full article

High production costs and extended development timelines pose significant challenges to the manufacturing of bearingless permanent magnet synchronous motors (BPMSMs). Moreover, uncertainties regarding the motor’s ability to generate suspension and torque often persist even after prototyping, primarily due to the limitations of lumped parameter models in capturing the system’s complex dynamics. Since this technology is not yet fully consolidated, there is a clear need for a solution that enables the effective evaluation of BPMSMs prior to physical production. To address this, a reduced-order model (ROM) was developed for BPMSMs with combined windings, capturing the cross-coupling effects associated with rotor eccentricity, magnetic saturation, and topological complexity. The model was constructed using the parametric interpolation method (PIM), enabling efficient and accurate representations of nonlinear electromechanical behavior as ferromagnetic materials and spatial harmonics are addressed through finite element modeling. Additionally, hardware-in-the-loop (HIL) techniques were used for gain tuning, and active disturbance rejection control (ADRC) was applied to enhance performance. This combined approach offers a comprehensive solution for the design and control of BPMSMs. Full article

Lamb waves offer a series of desirable features for Structural Health Monitoring (SHM) applications, such as the ability to detect small defects, allowing to detect damage at early stages of its evolution. On the downside, their propagation through media with multiple geometrical features results in complicated patterns, which complicate the task of damage detection, thus hindering the realization of their full potential. This is exacerbated by the fact that numerical models for Lamb waves, which could aid in both the prediction and interpretation of such patterns, are computationally expensive. The present paper provides a flexible surrogate to rapidly evaluate the sensor response in scenarios where Lamb waves propagate in plates that include multiple features or defects. To this end, an offline–online ray tracing approach is combined with Frequency Response Functions (FRFs) and transmissibility functions. Each ray is thereby represented either by a parametrized FRFs, if the origin of the ray lies in the actuator, or by a parametrized transmissibility function, if the origin of the ray lies in a feature. By exploiting the mechanical properties of propagating waves, it is possible to minimize the number of training simulations needed for the surrogate, thus avoiding the repeated evaluation of large models. The efficiency of the surrogate is demonstrated numerically, through an example, including different types of features, in particular through holes and notches, which result in both reflection and conversion of incident waves. For most sensor locations, the surrogate achieves an error between 1% and 4%, while providing a computational speedup of three to four orders of magnitude. Full article

Kolmogorov–Arnold Networks (KANs) are a recent development in machine learning, offering strong functional representation capabilities, enhanced interpretability, and reduced parameter complexity. Leveraging these advantages, this paper proposes a KAN-based reduced-order model (ROM) for unsteady aerodynamics and aeroelasticity. To effectively capture temporal dependencies inherent in nonlinear unsteady flow phenomena, an architecture termed Kolmogorov–Arnold Gated Recurrent Network (KAGRN) is introduced. By incorporating a recurrent structure and a gating mechanism, the proposed model effectively captures time-delay effects and enables the selective control and preservation of long-term temporal dependencies. This architecture provides high predictive accuracy, good generalization capability, and fast prediction speed. The performance of the model is evaluated using simulations of the NACA (National Advisory Committee for Aeronautics) 64A010 airfoil undergoing harmonic motion and limit cycle oscillations in transonic flow conditions. Results demonstrate that the proposed model can not only accurately and efficiently predict unsteady aerodynamic coefficients, but also effectively capture nonlinear aeroelastic responses. Full article