20505 research outputs found
Sort by
Scientific machine learning based pursuit-evasion strategy in unmanned surface vessel defense tactics
Get PDFIn this work we develop an AI-aided tactics generator for uncrewed surface vessels (USVs) for protection of critical national infrastructure and maritime assets in face of surface vehicle attacks. Our scientific machine learning (SciML) based methodology incorporates physical principles into the learning process, enhancing the model's ability to generalize and perform accurately in scenarios not encountered during training. This innovation addresses a critical gap in existing AI applications for maritime defense: the ability to operate effectively in novel or changing conditions without the need for retraining.Engineering and Physical Sciences Research CouncilUgurcan Celik is co-funded by the EPSRC and the BAE Systems under 220124 numbered Industrial CASE award:Towards AI-driven Intelligent Decision Making in Warfare.2024 AIAA DATC/IEEE 43rd Digital Avionics Systems Conference (DASC
Machine learning application to disaster damage repair cost modelling of residential buildings
Get PDFData used for this research is publicly available in the following portal. https://openricostruzione.regione.emilia-romagna.it/ricostruzione-privataRestoring residential buildings following earthquake damage requires a significant level of resources. Being able to predict these resource requirements in advance and accurately improves the effectiveness of disaster preparedness and subsequent recovery activities. This research explored how the latest ML algorithms could be used for antecedent earthquake loss modelling. A cost database for repairing residential buildings damaged by the Emilia Romagna earthquake in Italy was analysed using six state-of-the-art ML models to explore their ability to predict repair cost rates(cost per floor area) for a domestic building damaged by earthquakes. A Gradient Boost Regression model outperformed five other models in predicting earthquake damage repair cost rate. The performance of this model was significantly accurate and covers about 76% of the cases. A further SHAP analysis revealed that operational level, damage level and non-housing area of the buildings as top 3 important features when predicting the resultant damage repair cost rate. Overall this research advanced antecedent earthquake loss modelling approaches to increase the accuracy of estimates by incorporating more variables than the widely used damage level based simple methodology.European CommissionThis work was supported by the European Unionโs Horizon 2020 under Grant No 700748Construction Management and Economic
Moving target defence in 6G UAV networks
Get PDFThis paper focuses on enhancing the resilience of Unmanned Aerial Vehicle (UAV) networks against reconnaissance cyber-attacks. We introduce a novel algorithmic framework for IP and Port hopping, specifically tailored for UAV networks, to implement Moving Target Defense (MTD). The algorithm dynamically changes IP addresses and communication ports, increasing network unpredictability and thwarting reconnaissance attempts. Furthermore, we combine Network-based Moving Target Defense with sixth generation (6G) Software-Defined Networking (SDN) to enable real-time reconfiguration of network policies, providing proactive defense capabilities. Additionally, we integrate honeypots as a cyber deception strategy to divert potential attackers and gather valuable insights into their tactics. Extensive simulations demonstrate the effectiveness of our approach in reducing reconnaissance success rates and enhancing UAV network security.Engineering and Physical Sciences Research CouncilThis work has been partially funded by the EPSRC CHEDDAR Project - Communications Hub for Empowering Distributed Cloud Computing Applications and Research under grant numbers EP/X040518/1 and EP/Y037421/1.2024 AIAA DATC/IEEE 43rd Digital Avionics Systems Conference (DASC
Participatory AI: a method for integrating inclusive and ethical design considerations into autonomous system development
Get PDFThere has been significant work in the field of AI Ethics pertaining to how it might offer guidelines for developers to design, develop and deploy AI in an ethical way. Recently, the European Unionโs AI Act has introduced a risk-based regulation approach for AI system development. However, despite the additional requirements the AI Act places on developers to ensure that their systems are created with transparency, fairness, and accountability etc., there is no formalised methodology for how this might be achieved. Drawing on the history of collaborative and emancipatory technology design in Scandinavia, this paper proposes a software development methodology founded on the ethics and praxis-based principles of Participatory Design. Integrating this approach into the established โWaterfall Methodโ, it offers developers a practical way of embedding ethics in AI development, and to thereby satisfy the requirements imposed by the new regulations.Wellcome TrustThis work is part of Research for the Imagining Technologies for Disability Futures project, and this project was funded by The Wellcome Trust (214963/Z/18/Z, 214963/B/18/Z, and 214963/C/18/Z).Towards Autonomous Robotic Systems 2024Lecture Notes in Computer Scienc
A conceptual assessment framework for sustainability in the foundation industries
Get PDFFoundation industries in the UK are in constant pursuit of better technological solutions to enhance materials conversion efficiency and supply chain economies of scale. However, sustainable materials and strategies to conserve resources and better utilize waste streams tend to be ever more challenging to achieve when technological advances fall short in being widely adoptable by companies. Knowledge and technology transfer across multiple companies within the same sector (for example, construction materials production) or across seemingly common core processes (such as size reduction or furnaces) must be achieved for sustainability efforts to achieve economies of scale. Part of the reason why this is a difficult endeavor is the lack of visibility of the steps and drivers involved in a circular economy context with a view to achieve scale. Materials and technologies that could help foundation industries become more sustainable are being examined through the introduction of a novel framework that could help companies and policy makers understand where the opportunities exist. In this paper, the authors describe the design and development of the framework and offer examples drawn from an ongoing research and innovation project in foundation industries.This article was possible thanks to funding from Engineering and Physical Sciences Research Council (project reference: EP/V054627/1).34th CIRP Design Conference 2024Procedia CIR
Enabling net-zero GHG emissions in the UK metals and transport industries through a circular supply chain framework
Get PDFThe UK metals industry is indispensable in achieving the countryโs net-zero greenhouse gas (GHG) emissions target by 2050, especially considering the heavy reliance of the transport sector on metals. This paper proposes strategies based on recycling and refining locally sourced scrap metals to build a robust circular supply chain. Findings revealed that 16% of global crude steel is used in transport and this accounts for 8% of the worldโs GHG emissions. Domestically, iron and steel account for 14% of the UK industrial emissions, with over 8 million metric tons of scrap metals exported annually. Insights from stakeholders revealed export dependency and infrastructure gaps impeding circularity. Collaborative efforts between industry, government, and recyclers are vital. Investing in electric arc furnaces and storage can enable the processing of domestic metal scrap for high-quality yield. A closed-loop flow of battery-critical metals will also support sustainable manufacturing of electric vehicles. Ultimately, this paper advocates systemic efforts across policy, technology, infrastructure, and partnerships to realise a sustainable supply chain in the metals industry aligned with the decarbonisation and circular economy goals.The authors acknowledge the Circular Economy Network+ in Transport System (CENTS) project team for the grant award received to conduct this research.57th CIRP Conference on Manufacturing Systems 2024 (CMS 2024)Procedia CIR
Wind tunnel installation effects on the base flow for a high-speed exhaust system
Get PDFIt is envisaged that future propulsion concepts will enable high-speed flight and improve space access. However, their aerodynamic behavior is not yet well understood, especially at the base where severe flow separation occurs, requiring further analyses using both numerical and experimental techniques. This paper presents a numerical investigation of the wind tunnel installation effects on a representative, sub-scale, high-speed exhaust system. The analysis facilitates an ongoing design of experiments and de-risking activity. The apparatus features a truncated, ideal-contoured nozzle and an axially symmetric cavity region embedded at the base. The viable design space owing to high blockage is identified in terms of maximum approach Mach number. A systematic jet vectoring effect is observed in all cases examined. The origins of this effect are investigated and attributed solely to the pressure distribution asymmetry caused by the existence of the wing-pylon. Additionally, local flow similarity at the base of the tunnel-installed model with respect to unconstrained flow is investigated and presented, along with a proposed methodology to establish comparability. This analysis is of increased practical importance, due to the size range of most closed transonic tunnels found in academic research facilities. Results show that the pressure distribution at pre-choking tunnel conditions agrees within less than 1.5% and 0.1% for the base and cavity wall surfaces, respectively. At post-choking tunnel operation, the base pressure distribution of the model exhibits increased deviations in the azimuthal direction of up to 7.5%. The base pressure distribution in the corresponding unconstrained flow case falls within the observed pressure range of the tunnel-installed model, while the pressure distribution along the cavity wall agrees within less 1%. The findings of this study suggest that a jet vectoring effect could potentially manifest to wingtip mounted nacelles, usually incorporated in future, high-speed vehicles. Finally, it is demonstrated, that local flow similarity exists at the base with respect to unbounded flow, even for post-choking tunnel conditions, which is critical in base flows and base drag reduction analyses.AIAA SCITECH 2024 Foru
Effect of struts and central tower on aerodynamics and aeroacoustics of vertical axis wind turbines using mid-fidelity and high-fidelity methods
Get PDFThis study investigates the impact of struts and a central tower on the aerodynamics and aeroacoustics of Darrieus Vertical Axis Wind Turbines (VAWTs) at chord-based Reynolds numbers of 8.12e4. A 2-bladed H-Darrieus VAWT is used, featuring a 1.5m diameter, a solidity of 0.1 and a blade cross-section of symmetrical NACA 0021. The turbine design is kept simple and straight-bladed which is essential for isolating and analyzing the specific effects of struts and a tower. The high-fidelity Lattice Boltzmann Method (LBM) in PowerFLOW 6-2020 and the mid-fidelity Lifting Line Free Vortex Wake (LLFVW) method in QBlade 2.0 are employed, with the mid-fidelity method providing a faster analytical tool for insights into the turbine performance. Firstly, both the LLFVW (mid-fidelity) and LBM (high-fidelity) methods effectively capture the general trends observed in VAWT power performance. However, the former predicts mean thrust values that are approximately 10% higher, and mean torque values that are approximately 19% higher, in comparison to the latter. Subsequently, the former predicts lower streamwise wake velocities relative to those predicted by the latter. These differences increase in configurations that include struts and a tower (to 30% - 31%). Secondly, the presence of struts and a tower leads to a reduction in both mean power (by 15% to 55%) and thrust (by 3% to 3.6%), with a further small decrease observed when doubling the tower diameter (power and thrust both by 0.5% to 3%). The struts predominantly affect the spanwise distribution of blade loading, while the tower impacts the azimuthal variation of blade loading. Additionally, the addition of struts and a tower reduces low-frequency noise (50-200 Hz) while increasing high-frequency noise (> 300 Hz). The observed decrease in mean blade loading results in reduced low-frequency noise, while the increase in high-frequency noise is ascribed to the increased intensity of BWI/BVI leading to higher unsteady loading fluctuations on blades.This project has received funding from the European Unionโs Horizon 2020 Marie Curie zEPHYR research and innovation programme under grant agreement No EC grant 860101 (https://www.h2020-zephyr.eu/).AIAA SCITECH 2024 Foru
Augmented Reality Training for Improved Learnability: data
No full textSurvey used Relevant images from the demonstrationDigital Toolkit for optimisation of operators and technology in manufacturing partnerships (DigiTOP
Borophene: a 2D wonder shaping the future of nanotechnology and materials science
Get PDFTwo-dimensional (2D) materials have attracted considerable research interest due to their precisely defined properties and versatile applications. In this realm, borophene - a single atomic sheet of boron atoms arranged in a honeycomb lattice - has emerged as a promising candidate. While borophenes were theoretically predicted to have unique structural, optical, and electronic properties, the experimental synthesis of crystalline borophene sheets was first demonstrated on metal substrates in 2015, marking a crucial milestone. Since then, research efforts have focused on controlling the synthesis of semiconducting borophene polymorphs and exploring their novel physical characteristics. This review aims to explore the potential of 2D materials, specifically borophene, in various technological fields such as batteries, supercapacitors, fuel cells, and more. The analysis emphasises meticulous scrutiny of synthesis techniques due to their fundamental importance in realising borophene's properties. Specifically, the high carrier mobilities, tuneable bandgaps, and exceptional thermal conductivity of borophene are highlighted. By providing a comprehensive outlook on the significance of borophene in advancing materials science and technologies, this review contributes to shaping the landscape of 2D material research.Nano Materials Scienc