20505 research outputs found
Sort by
Extracting data-driven insights from LiDAR and SCADA data for improved analysis of offshore wind farms
No full textOffshore wind energy is essential for the global transition to renewable energy. Wind farms, such as those at Anholt and Westermost Rough, are crucial in providing clean electricity. LiDAR (Light Detection and Ranging) and SCADA (Supervisory Control and Data Acquisition) data are particularly valuable for understanding turbine behavior and predicting energy output. Recent advancements in machine learning (ML) and artificial intelligence (AI) have opened new possibilities for analyzing complex wind farm data. This study employs data-driven techniques, specifically XGBoost and Long Short-Term Memory (LSTM) networks, to enhance the analysis of LiDAR and SCADA data from the Anholt and Westermost Rough offshore wind farms. Data-driven filters were applied to enhance the quality of input data, thereby improving the accuracy of the models and reducing noise. XGBoost demonstrated computational efficiency, training faster than Bi-LSTM while achieving an R2 of 0.97 for Anholt and 0.86 for Westermost Rough. While Bi-LSTM successfully captured temporal dependencies, it required significantly longer training times. RMSE and MSE results indicate that XGBoost outperformed Bi-LSTM at Anholt by 6.3% and 12.2%, respectively, whereas both models showed higher errors at Westermost Rough, likely due to data dependency. The residual analysis confirmed tighter error distribution for Anholt, whereas Westermost Rough exhibited higher prediction uncertainties. Wind speed loss analysis revealed that turbines in the selected rows experienced variations, highlighting the impact of local turbulence on wind flow characteristics.Journal of Physics: Conference Serie
Cognitive digital twins: enabling holistic asset management through semantic interoperability and human expertise integration
No full textAddepalli, Pavan - Associate SupervisorThe growing industrial interest in Digital Twins (DTs) has led to an expansive network of standalone DT solutions. Many of these twins operate in isolation, frequently lacking the features
that enable seamless integration and communication with other systems. Based on these facts,
this PhD project aims to propose a novel framework for creating DTs with advanced semantic
capabilities, which are increasingly being referred to as Cognitive Digital Twins (CDTs). Beyond advancements of traditional DTs, these CDTs provide a means to formalise and transfer
human expertise, which is crucial for enhancing DTs’ decision support, operational efficiency,
and adaptability in complex asset management. Moreover, CDTs also have the potential to
achieve significantly improved semantic interoperability among twins. This enhanced interoperability facilitates a consistent and efficient data flow and augments asset management procedures. Furthermore, it boosts awareness and insights regarding the operations and performance
metrics of the mirrored assets.
This comprehensive approach to DT development offers a reference frame that delineates
how assets communicate, function, and evolve in a digitally twinned environment. This PhD
thesis explores the potential of CDTs in improving the management of complex engineering
assets by enhancing the transfer of human expertise and semantic interoperability within and
among DTs.
The thesis makes several contributions, starting with a systematic literature review to identify gaps in existing academic research and an industrial review that assesses current industry
practices, highlighting the relevance of the research. A novel five-step methodology for developing CDTs is introduced, emphasising the use of top level ontologies (TLOs) and the integration of human expertise. This methodology ensures semantic consistency within the DT
framework and has been validated in a laboratory setting. A CDT framework is also presented,
prioritising flexibility, interoperability, and reusability aspects provided by this novel approach.
The study primarily focuses on the manufacturing industry and underscores the role of ontologies in enhancing CDTs, bridging the gap between human understanding and automated
systems. Future research directions are proposed, mainly aiming to optimise asset management, availability, and sustainability by integrating human knowledge into digital systems and
promoting collaborative learning among CDTs.PhD in Manufacturin
Structured AI decision-making in disaster management
No full textWith artificial intelligence (AI) being applied to bring autonomy to decision-making in safety-critical domains such as the ones typified in the aerospace and emergency-response services, there has been a call to address the ethical implications of structuring those decisions, so they remain reliable and justifiable when human lives are at stake. This paper contributes to addressing the challenge of decision-making by proposing a structured decision-making framework as a foundational step towards responsible AI. The proposed structured decision-making framework is implemented in autonomous decision-making, specifically within disaster management. By introducing concepts of Enabler agents, Levels and Scenarios, the proposed framework’s performance is evaluated against systems relying solely on judgement-based insights, as well as human operators who have disaster experience: victims, volunteers, and stakeholders. The results demonstrate that the structured decision-making framework achieves 60.94% greater stability in consistently accurate decisions across multiple Scenarios, compared to judgement-based systems. Moreover, the study shows that the proposed framework outperforms human operators with a 38.93% higher accuracy across various Scenarios. These findings demonstrate the promise of the structured decision-making framework for building more reliable autonomous AI applications in safety-critical contexts.Scientific Report
Dynamic space debris removal via deep feature extraction and trajectory prediction in robotic systems
No full textThis article belongs to the Section AI in RoboticsThis work introduces a comprehensive vision-based framework for autonomous space debris removal using robotic manipulators. A real-time debris detection module is built upon the YOLOv8 architecture, ensuring reliable target localization under varying illumination and occlusion conditions. Following detection, object motion states are estimated through a calibrated binocular vision system coupled with a physics-based collision model. Smooth interception trajectories are generated via a particle swarm optimization strategy integrated with a 5–5–5 polynomial interpolation scheme, enabling continuous and time-optimal end-effector motions. To anticipate future arm movements, a Transformer-based sequence predictor is enhanced by replacing conventional multilayer perceptrons with Kolmogorov–Arnold networks (KANs), improving both parameter efficiency and interpretability. In practice, the Transformer+KAN model compensates the manipulator’s trajectory planner to adapt to more complex scenarios. Each component is then evaluated separately in simulation, demonstrating stable tracking performance, precise trajectory execution, and robust motion prediction for intelligent on-orbit servicing.Robotic
Autonomous robotic radio source localization via a novel Gaussian Mixture Filtering approach
No full textThis study proposes a new Gaussian Mixture Filter (GMF) to improve the estimation performance for the au-tonomous robotic radio signal source search and localization problem in unknown environments. The proposed filter is first tested with a benchmark numerical problem to validate the performance with other state-of-the-practice approaches such as Particle Filter (PF) and Particle Gaussian Mixture (PGM) filters. Then the proposed approach is tested and compared against PF and PGM filters in real-world robotic field experiments to validate its impact for real-world applications. The considered real-world scenarios have partial observability with the range-only measurement and uncertainty with the measurement model. The results show that the proposed filter can handle this partial observability effectively whilst showing improved performance compared to PF, reducing the computation requirements while demonstrating improved robustness over compared techniques.The research was carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration (80NM0018D0004).2025 28th International Conference on Information Fusion (FUSION
Developing a strategic roadmap toward hydrogen energy economy for energy mix integration in Saudi Arabia
No full textLuk, Patrick Chi-Kwong - Associate SupervisorHydrogen has come to the forefront as a hopeful solution in the transition toward
cleaner, more sustainable sources of energy that will meet global decarbonization
goals. However, while it is a great potential, a few challenges are found within the
hydrogen sector, including fluctuating renewable energy costs, policy
uncertainties, and complex issues related to storage, transportation, and market
integration. These make efficient production and distribution of hydrogen hard,
hence acting as a barrier to large-scale adoption.
This research addresses these challenges through developing a strategic DSS
intended to optimize the production and distribution of hydrogen. The presented
DSS integrates multi-criteria decision-making and decision tree methodologies to
obtain a flexible tool based on data that will balance economic feasibility,
technological adaptability, environmental sustainability, and compliance with
regulations. By putting all these elements together, the DSS provides an
integrated approach to making decisions for addressing issues with hydrogen
energy systems.
This work is motivated by the fact that literature lacks integrated frameworks that
might guide decision analyses in hydrogen production. Most works have focused
on isolated issues related to the analysis of technology costs or even policy
impacts, excluding the important needs for a strategic approach that captures all
these significant factors in one fell swoop. This study fills this gap by presenting
one unified system able to support relevant, strategic decisions by any
stakeholder.
A case study undertaken in Saudi Arabia validates the DSS against practical,
real-world scenarios for completeness in aligning with the Vision 2030 energy
transition pathways of the country. It should not only promote efficiency and
costeffectiveness of hydrogen production but also meet green practices by
remaining in step with environmental targets and market demand. Besides, the
integration of machine learning techniques enhances the predictive capabilities
of DSS and hence increases its adaptability toward dynamically changing energy
markets.
These research findings pinpoint the DSS as a very important tool for furthering
hydrogen production and distribution while offering valuable insights for
policymakers, industry leaders, and investors in the same instance. Given that
this study provides a structured approach to decision-making, it will contribute
valuably to the global effort of developing a sustainable hydrogen economy and
support broader goals for energy security and environmental stewardship.PhD in Energy and Powe
An attitude coordination architecture for communications routing in LEO constellations
No full textIn this work, the challenge of using multiple satellite constellations in LEO for establishing communication links between two ground stations is investigated. Low altitude orbits and limited onboard equipment capabilities, which lead to reduced coverage areas and frequent visibility changes, create a highly dynamic problem. To address typical requirements such as maximising link uptime and/or minimising communication delay, an architecture for optimising the selection of a signal route and attitude control for the involved relay satellites’ attitude is presented herein. This architecture is deterministic and can be distributed among all the involved satellites, allowing them to operate individually towards achieving the desired goal.This work has been supported by the NATO Science for Peace and Security (SPS) programme, under the grant SPS
G6141 - "Federated laboratories for testing formations of responsive satellites".11th European Conference for AeroSpace Sciences (EUCASS 2025
Quantifying public perceptions of hydrogen adoption in the United Kingdom incorporating challenges, acceptance factors and proposed strategies
No full textThis study investigates the public acceptance of hydrogen technologies in the United Kingdom's domestic energy sector, with a focus on green and low-carbon hydrogen as a pathway to decarbonisation. The purpose is to evaluate the social, economic and perceptual factors shaping willingness to adopt hydrogen-based appliances such as boilers, hobs and complete home systems. A mixed-methods framework was employed, combining quantitative analysis including descriptive statistics, correlation matrices and regression modelling with qualitative approaches such as sentiment and thematic analysis of survey responses (n = 1213). Sentiment analysis revealed three dominant orientations: optimistic (28%), cautious (17.7%) and hopeful (16.8%). Thematic coding highlighted five central drivers and barriers: affordability, environmental impact, technological reliability, trust and broader public opinion. Regression analysis confirmed that knowledge of hydrogen strongly predicts acceptance (β = 0.28, p < 0.001 for boilers; β = 0.26, p < 0.001 for hobs), while demographic factors such as age (β = −0.099, p < 0.05) and income (β = 0.045, p < 0.05) exert smaller yet significant influences. Standard error clustering and robustness checks were applied to validate these results. The findings demonstrate that acceptance is more closely tied to attitudinal and informational factors than to demographics alone. Based on these insights, the study proposes evidence-based strategies for policymakers, including targeted public education, financial incentives and transparency-driven pilot projects. By integrating both methodological rigour and policy relevance, the paper contributes to the literature on sustainable energy transitions and outlines practical pathways for accelerating hydrogen adoption in domestic contexts.Energy Science & Engineerin
Impact of installation on the performance of a civil turbofan exhaust at wind-milling: a combined experimental and numerical approach
Get PDFThis work presents a combined experimental and numerical investigation of the effect of wing integration on the aerodynamic behaviour of a typical large civil aero-engine exhaust at wind-milling conditions. Engine performance simulations established estimates of Fan and Core Nozzle Pressure Ratios (FNPR and CNPR, respectively) for representative “engine-out” wind-milling scenarios. The experimental data and Reynolds Averaged Navier Stokes (RANS) Computational Fluid Dynamic (CFD) simulations encompassed End of Runway (EoR) take-off, diversion, and cruise wind-milling conditions for both isolated and installed configurations. The impact of FNPR, CNPR, free-stream Mach number (M∞), and high-lift surfaces on the installed suppression effect were evaluated. The measured and CFD predicted fan and core nozzle maps were implemented into the engine performance model to estimate the engine re-matching characteristics due to the impact of the installation, and the effect on engine mass flow. The effect of installation can reduce the fan and core nozzle discharge coefficients by up to 13% and 26%, respectively, relative to the isolated configuration for representative EOR wind-milling conditions. RANS CFD captures the effect of suppression on both the fan and core with an accuracy between 0.1% and 1.2%, depending on Mach number, which is sufficient for industrial design and analysis purposes. The engine performance analyses showed that the installed suppression effect can result in a 10% reduction of engine mass flow at EOR wind-milling. Within the context of nacelle design under wind-milling, this effect of exhaust suppression must be considered in determining the intake Mass Flow Capture Ratio (MFCR).This project has received funding from the Clean Sky 2 Joint Undertaking (JU) under grant agreement number 101007598.Aerospace Science and Technolog