149544 research outputs found
Sort by
Enhancing Offshore Infrastructure Monitoring: Synthetic Data Generation for Deep Learning-Based Object Detection on Sentinel-1 Radar Imagery
Get PDFThe recent and ongoing expansion of marine infrastructure, including offshore wind farms, oil and gas platforms, artificial islands, and aquaculture facilities, highlights the need for effective monitoring systems. Precise quantification in space and time is crucial to planning the future expansion, usage, management, and impact of marine offshore infrastructure. In the past decade, numerous studies have explored the detection and monitoring of offshore infrastructure using space-borne data and remote sensing techniques. Recently, deep learning-based approaches have emerged as a powerful tool for these tasks. However, the development of robust and reliable object detection models depends on the availability of comprehensive, balanced training datasets. Manual annotation of existing objects is the standard method for dataset creation, but it falls short when samples are scarce, particularly for underrepresented object classes, shapes, and sizes. To address this limitation, we propose a deep learning-based approach for generating synthetic training data by modifying and retraining a stable diffusion model. The goal of this approach lies within the augmentation of manual image-label pairs and the enhancement of the dataset quality and diversity. We validate this approach by applying the object detector YOLOv10 to efficiently detect and classify offshore infrastructure objects (specifically offshore oil and gas platforms) on Sentinel-1 radar imagery in three diverse test regions: the Gulf of Mexico, the North Sea, and the Persian Gulf. We will present an analysis of the impact of our synthetic data generation approach on training results with a focus on how unbalanced classes can be better represented and model performance improved. This study underscores the critical importance of balanced datasets and highlights synthetic data generation as an effective strategy to address common challenges in remote sensing. Furthermore, it reaffirms the pivotal role of Earth observation in advancing offshore infrastructure monitoring by demonstrating the first test results of our model on unseen data
COMPARATIVE EVALUATION OF MACHINE LEARNING MODELS AND SUPER ELLIPSE CRITERION FOR FATIGUE LIFE PREDICTION OF WELDED JOINTS UNDER MULTIAXIAL LOADING
No full textEvaluating the fatigue life of welded joints under multiaxial loading is a key challenge in structural engineering. This study explores machine learning (ML) methods for predicting fatigue life and compares their performance against the novel super ellipse criterion, which is an analytical approach that aims to improve current design standard methods (e.g., Eurocode 3, IIW). Using a dataset of uniaxial and multiaxial fatigue tests with varying phase angles, ML models-including artificial neural networks and XGBoost-are trained on features like stress amplitudes, phase differences, and material properties. Artificial neural networks provide high accuracy, while tree-based models like XGBoost offer better interpretability via model agnostic interpretation using Explainable AI. Results show ML models can outperform traditional criteria, especially under non-proportional loading, but face limitations near the edges of the training data. This work highlights the potential and challenges of ML in fatigue rediction and highlights their value for enhancing the safety and reliability of welded structures
DEVELOPMENT OF ENVIRONMENTAL BARRIER COATINGS VIA PVD TECHNIQUES: EVALUATION UNDER HIGH TEMPERATURE WATER VAPOR
Get PDFEnvironmental barrier coatings (EBCs) are proven to protect SiC-based materials against water vapor in gas turbine environments. The straightforward EBCs are typically comprised of two layers, ytterbium disilicates (YbDS) and a Si bond coat, and are applied by atmospherically plasma spraying (APS) method. YbDS offers high-temperature phase stability. However, it still experiences a detrimental volatilization rate under a high-velocity steam environment. Yttrium disilicate (YDS), on the other hand, exhibits better water vapor and CMAS resistance but lacks the high-temperature phase stability. While the use of RE-mono silicates, RE-disilicates, or multi-component for EBC or T/EBC (thermal environmental barrier coatings) is still under debate, efforts are required to produce dense, uniform, crack-free layers that have good adherence through complex geometries components. Physical vapor deposition, e.g., magnetron sputtering or electron beam physical vapor deposition (EB-PVD), can provide good adhesion through sharper-edged and improve the accommodation of CTE by columnar and/or dense microstructure.
This study presents a comparative analysis of two advanced deposition techniques—magnetron sputtering and EB-PVD—for the fabrication of EBCs and their performance under a water vapor environment at high temperatures. Successfully, two different double-layer EBC systems were deposited by PVD techniques, the first based on Y silicates and the second (Y,Yb) silicates. The water vapor parameters consist of 30% H2O/70%O2, at 1300°C. The results showed, in coated conditions, dense EB-PVD layers while magnetron sputtering a columnar microstructure both with in amorphous states. After crystallization, the monoclinic X2-monosilicates and β-disilicates phases constituted the final EBCs. The changes after the crystallization and water vapor test will be discussed in terms of morphology, crystalline phase, and chemistry of the coatings
AI-Based Vehicle State Estimation Using Multi-Sensor Perception and Real-World Data
Get PDFWith the rise of vehicle automation, accurate estimation of driving dynamics has become crucial for ensuring safe and efficient operation. Vehicle dynamics control systems rely on these estimates to provide necessary control variables for stabilizing vehicles in various scenarios. Traditional model-based methods use wheel-related measurements, such as steering angle or wheel speed, as inputs. However, under low-traction conditions, e.g., on icy surfaces, these measurements often fail to deliver trustworthy information about the vehicle states. In such critical situations, precise estimation is essential for effective system intervention. This work introduces an AI-based approach that leverages perception sensor data, specifically camera images and lidar point clouds. By using relative kinematic relationships, it bypasses the complexities of vehicle and tire dynamics and enables robust estimation across all scenarios. Optical and scene flow are extracted from the sensor data and processed by a recurrent neural network to infer vehicle states. The proposed method is vehicle-agnostic, allowing trained models to be deployed across different platforms without additional calibration. Experimental results based on real-world data demonstrate that the AI-based estimator presented in this work achieves accurate and robust results under various conditions. Particularly in low-friction scenarios, it significantly outperforms conventional model-based approaches
Instroduction to thermophysical properties of liquid metals V
No full textThe teaching activities of Dr. Jürgen Brillo in our Department will be 10 hours and take place for 5 days from Monday 26 May 2025 to 30 May 2025.
The indicative titles of his lectures are:
(a) Thermophysical Properties of Liquid Metals I (2 hours)
(b) Thermophysical Properties of Liquid Metals II (2 hours)
(c) Thermophysical Properties of Liquid Metals III (2 hours)
(d) Thermophysical Properties of Liquid Metals IV (2 hours)
(e) Thermophysical Properties of Liquid Metals V (2 hours
Improving flood detection in arid regions using Sentinel-1 interferometric coherence and machine learning
No full textFloods are among the most devastating natural disasters, affecting about 1-in-4 people globally. The increasing frequency and intensity of extreme weather events have led to unprecedented flooding impacts, particularly in arid regions. The low soil permeability in arid regions means that short periods of heavy rain can cause rapid surface runoff, erosion, and infrastructure damage. Moreover, arid regions often lack the infrastructure and resources to cope with such disasters. Satellite-based remote sensing has become crucial for near real-time flood mapping and monitoring and rapid response and rescue operations. While optical satellites are limited by cloud cover, Synthetic Aperture Radar (SAR) satellites are increasingly utilized due to their relatively longer wavelengths which penetrate clouds, and their ability to collect information in different modes of polarization. However, current SAR-based flood detection methods struggle to differentiate between water and dry sandy surfaces, as both exhibit similar low-amplitude backscatter characteristics. This creates a critical gap in our ability to monitor and respond to floods in arid regions. We present a methodology that combines SAR amplitude and interferometric coherence data for flood detection in arid regions. We leverage ESA Copernicus Sentinel-1 data and employ a Random Forest classifier to integrate multiple SAR features, including temporal coherence and backscatter information. The predicted flood map is validated against reference flood maps derived using cloud-free Sentinel-2 optical imagery. The methodology is tested through three real-world flood events in Iran, Turkmenistan, and Pakistan. Our analysis reveals that combining coherence information with amplitude-based methods improves flood detection accuracy from 12% to 25% across the three test cases, with strong performance in areas where traditional methods typically fail. Using permutation feature importance analysis, we identified three key parameters: coherence and pre/post-flood amplitude changes all in vertically transmit and vertically receive. By focusing on these features, our model maintains the same accuracy while reducing processing time by 33%, making it more suitable for emergency response. The model also demonstrates robust performance across different geographical regions: successfully detecting floods in previously unseen locations without retraining the model. This geographical transferability of the model suggests the potential for a standardized flood detection system including arid regions. The increasing availability of open-access SAR data and advances in cloud computing have made handling and computing calculations of SAR data more feasible. With multiple space agencies launching new SAR missions, there are opportunities to test and adapt this methodology across different sensors and integrate it into operational flood mapping systems
Concept and design aspects of High Temperature Heat Pumps in the EU-PROJECT SOLINDARITY
Get PDFThe EU-Project SOLINDARITY will develop, demonstrate and validate the feasibility of an integrated Solar Energy-based Heat Upgrade System (SEHUS) comprising solar energy resources (High Vacuum Flat Solar Panels and Photovoltaic), innovative High Temperature Heat Pumps (HTHP), Thermal Energy Storage and Waste Heat Recovery for the deep decarbonization of industrial processes with temperatures up to 280°C. The pilot system to be developed will demonstrate its effectiveness, robustness, sustainability and cost-efficiency in three industrial sites, belonging to different industrial sectors (Food, Paper, Rubber industries) and climatic regions (Germany, Greece, Italy). This publication presents initial results from the development of a reversed Brayton HTHP regarding the SEHUS, while considering different industrial applications. The integration concept and a preliminary dimensioning, based on steady-state simulations, cover the configuration of the HTHP and serve as the starting point for the design phase, particularly regarding the turbo machinery and the drive system. Results from the system’s initial design iterations are also presented, allowing conclusions to be drawn about the process integration of HTHP and its components into different industrial applications
Thermophysical properties of Al-Mg and Al-Cr based additive manufacturing alloys
No full textThis study focuses on investigation the thermophysical properties of two aluminium additive manufacturing alloys, Al-Mg-based Scalmalloy (Al-Mg-3.18-Sc0.73-Mn0.39-Zr0.3) and Al-Cr based Scancromal (Al-Cr2.6-Sc0.72-Zr0.25). Viscosity and surface tension play critical roles in determining the performance of the welding process. Spatter formation and welding plumes cause defects like gas pores, process pores, lack of fusion etc. Of particular importance are understanding and controlling the formation of these manufacturing defects. Accurate measurement of the thermophysical properties is essential for optimization the manufacturing processes and imroving numerical simulations. The oscillating droplet method is employed to determine the thermophysical properties of the molten aluminium alloys. Ground-based experiments were conducted using the DLR electromagnetic levitator which showed contrasting behaviors between the two alloys. Scalmalloy demonstrated lower surface tension and significant magnesium evaporation; the additive manufacturing process using Laser Powder Bed Fusion showed unstable melt dynamics with significant spatter formation. In contrast Scancromal exhibited higher surface tension and stable melt behavior during the LPB-F process. Parabolic flight experiments using SUPOS EML were carried out to offer reduced gravity conditions. The influence of evaporation effects and composition changes on the thermophysical properties of the two aluminium alloys is adressed
Temperature and pressure reconstruction in turbulent Rayleigh-Bénard convection by Lagrangian velocities using PINN
Get PDFVelocity, pressure, and temperature are the key variables for understand-
ing thermal convection, and measuring them all is a complex task. In this paper, we demonstrate a method to reconstruct temperature and pressure fields based on given Lagrangian velocity data. A physics-informed neural network (PINN) based on a multilayer perceptron architecture and a periodic sine activation function is used to reconstruct both the temperature and the pressure for two cases of turbulent Rayleigh-B´enard convection (Pr = 6.9, Ra = 109). The first dataset is generated with DNS and it includes Lagrangian velocity data of 150000 tracer particles. The second contains a PTV experiment with the same system parameters in a water-filled cubic cell, and we observed about 50000 active particle tracks per time step with the open-source framework proPTV. A realistic temperature and pressure field could be reconstructed in both cases, which underlines the importance of PINNs also in the context of experimental data. In the case of the DNS, the reconstructed temperature and pressure fields show a 90% correlation over all particles when directly validated against the ground truth. Thus, the proposed method, in combination with particle tracking velocimetry, is able to provide velocity, temperature, and pressure fields in convective flows even in the hard turbulence regime. The PINN used in this paper is compatible with proPTV and is part of an open source project. It is available at https://github.com/DLR-AS-BOA/RBC-PIN
