Staff publications (AIRS)

Browse

Now showing 1 - 20 of 43

Access status: Open Access ,
Integrated UAS platform with 5G technology and non-terrestrial networks: Orkney Islands scenario
(Institute of Electrical and Electronics Engineers (IEEE), 2024-10-15) Mohanta, Krishnakanth; Al-Rubaye, Saba; Tsourdos, Antonios
The integration of fifth-generation (5G) technology with Non-Terrestrial Networks (NTN) holds transformative potential for Beyond Visual Line of Sight (BVLOS) operations of Uncrewed Aerial Systems (UAS) in rural regions. This paper presents a comprehensive architectural design that leverages satellite-enabled 5G networks to enhance connectivity in the Orkney Islands, Scotland, thereby improving the reliability and operational efficiency of UAS missions. By addressing the limitations of terrestrial networks, particularly in remote and underserved areas, the proposed flowchart ensures seamless data communication and transfer, facilitating real-time control and monitoring within the UAS platform. Simulations are conducted to validate the scenario for remote area connectivity. This work underscores the crucial role of NTN in advancing UAS operations, paving the way for innovative services and broader adoption of UAS technologies in rural settings.
Access status: Restricted ,
Echo-Robot: Semi-autonomous cardiac ultrasound image acquisition using AI and robotics
(Institute of Electrical and Electronics Engineers (IEEE), 2025-12-31) Laurent, Eliott; Soemantoro, Raska; Jenner, Kathryn; Kardos, Attila; Tang, Gilbert; Zhao, Yifan
Echocardiography is a critical tool for diagnosing cardiovascular diseases, offering detailed insights into heart functions. However, its accessibility is currently limited by a shortage of trained sonographers, specific skill requirements, and the physical strain imposed on professionals during repetitive procedures. This article introduces a new robotic system designed to automate the acquisition of transthoracic echocardiography (TTE) images. The system autonomously adjusts the position and orientation of the ultrasound transducer based on analysing realtime ultrasound images, without relying on tomographic data or depth sensors. Initially, the transducer is manually placed on the subjects skin, and the system uses a deep learning approach to grade the quality of ultrasound images captured at each position. The robot then adjusts its position by spiralling outwards from the starting point, moving to the location with the highest image quality score. Next, the system fine-tunes the transducers orientation in 5-degree increments along all three axes of rotation, informed by another deep learning module to identify the field of view. The robotic system was tested using a cardiac simulator, achieving approximately 80 view when the probe was initially positioned randomly in a 6 by 6 cm area beneath the left nipple. The impact of this work would be rapid diagnostics in the Emergency Departments to reduce the length of stay in hospitals, a reduction of hospital admissions related to heart disease by accessing local healthcare communities, acceleration of clearing the post-Covid backlog, and improved quality of life and longevity of patients.
Access status: Open Access ,
Have prospects for product life-spans improved?
(Aalborg University, 2025-07-02) Cooper, Tim; Watkins, Matthew; Bathaei Javareshk, Maryam; Baguley, Thom
Access status: Open Access ,
Thermal analysis and modelling of cryogenic coolant flow in an aerospike engine additively manufactured cooling channel
(Elsevier, 2025-11-01) Monokrousos, Nikos; Könözsy, László Z.; Pachidis, Vassilios; Sozio, Ernesto; Rossi, Federico
Cryogenic propellants play a crucial role in regenerative cooling systems of liquid rocket engines, particularly in high-heat flux applications such as aerospike engines. The present study is conducted within the framework of the DemoP1 demonstrator, a 20 [kN] LOx/LNG Additively Manufactured (AM) aerospike engine developed by Pangea Aerospace. This work aims to present a numerical characterisation of the cryogenic liquid oxygen flow within an AM cooling channel of the DemoP1 demonstrator. To analyse the development of the fluid primitive variables, the objective of this study is to provide a detailed assessment of the thermophysical properties and dimensionless numbers governing the cryogenic flow. The numerical findings are compared against experimental data obtained from the full-scale, single-injector hot-fire testing campaign of the demonstrator. The results highlight the enhanced heat transfer performance of AM cooling channels with high process-inherited roughness compared to conventional smooth-surface channels. Finally, a modified Dittus–Boelter correlation is introduced to characterise the heat transfer behaviour of the cryogenic flow in the AM channel. The case study presented here consists one of the first attempts to provide a comprehensive analysis on the cryogenic flow characteristics in the novel dual regenerative cooling system of an aerospike engine.
Access status: Open Access ,
Data-driven vehicle modeling for path tracking based on the Combination of a Neural Network and Kinematics Model
(Springer, 2025) Gao, Zhenhai; Wen, Wenhao; Chen, Guoying; Xing, Yang; Sun, Tianjun
Autonomous driving systems must safely navigate in increasingly diverse and challenging conditions, which necessitate the incorporation of vehicle dynamic models capable of accurately capturing a vehicle's behavior in diverse conditions. Moreover, these models need to be easily and rapidly developed to meet the needs of rapid autonomous driving software updates. Currently used models have limited accuracy, require extensive parameter tuning, and cannot meet these demands. This paper introduces the Combination of Neural Network and Kinematics Model (CNKM). A neural network is utilized to model the nonlinear characteristics of vehicle subsystems (powertrain, braking, steering, tires) and various unknown factors. It ultimately outputs accelerations that are fed into a planar kinematics model to derive the vehicle states. The neural network is trained using a dataset collected from natural driving. A weighting formula suitable for natural driving data is proposed to mitigate the impact of an uneven dataset distribution. This model is compared with commonly used models under typical and high lateral acceleration scenarios, and the position and heading errors of CNKM are 15.34% and 14.71% of those of the nonlinear dynamic model, respectively.
Access status: Open Access ,
Intelligent 5G-aided UAV positioning in high-density environments using neural networks for NLOS mitigation
(MDPI, 2025-06-01) Mousa, Morad; Al-Rubaye, Saba
The accurate and reliable positioning of unmanned aerial vehicles (UAVs) in urban environments is crucial for urban air mobility (UAM) application, such as logistics, surveillance, and disaster management. However, global navigation satellite systems (GNSSs) often fail in densely populated areas due to signal reflections (multipath propagation) and obstructions non-line-of-sight (NLOS), causing significant positioning errors. To address this, we propose a machine learning (ML) framework that integrates 5G position reference signals (PRSs) to correct UAV position estimates. A dataset was generated using MATLAB’s UAV simulation environment, including estimated coordinates derived from 5G time of arrival (TOA) measurements and corresponding actual positions (ground truth). This dataset was used to train a fully connected feedforward neural network (FNN), which improves the positioning accuracy by learning patterns between predicted and actual coordinates. The model achieved significant accuracy improvements, with a mean absolute error (MAE) of 1.3 m in line-of-sight (LOS) conditions and 1.7 m in NLOS conditions, and a root mean squared error (RMSE) of approximately 2.3 m. The proposed framework enables real-time correction capabilities for dynamic UAV tracking systems, highlighting the potential of combining 5G positioning data with deep learning to enhance UAV navigation in urban settings. This study addresses the limitations of traditional GNSS-based methods in dense urban environments and offers a robust solution for future UAV advancements.
Access status: Open Access ,
Proposal of a new category of lunar regolith simulants: reduced particle-density simulants that exhibit equivalent self-weight in Earth gravity to native regolith in lunar gravity
(Elsevier, 2025-10) Pratnekar, Marko; Garg, Vivek; Kaur, Baldeep; Bradley, Michael S. A.; Cullen, David C.
Current “normal density” lunar regolith simulants used in Earth gravity can be viewed as a poor replication of bulk material handling behaviour of lunar regolith in lunar gravity. The six-times greater self-weight of such normal simulants on Earth compared to the Moon can be the viewed as the underlying cause. The use of such normal simulants in Earth gravity as part of technology development for lunar use may fail to adequately predict lunar behaviour and result in sub-optimal outcomes. This paper proposes a new class of reduced self-weight lunar regolith simulants to minimise this issue. The current work elaborates the case for this new class of lunar regolith simulants with reduced particle density of one-sixth native lunar regolith resulting in reduced self-weight. To justify further this approach a series of studies are reported to highlight the expected differences between the current and proposed simulant uses. First, analytical arguments are used based around Jenike theory and the concept of Bond Number to highlight expected differences. Second, Discrete Element Method simulation is used show the expected difference in behaviour between the two simulants classes. Third, a laboratory breadboarded discharge hopper is used to demonstrate behaviour differences between normal and reduced self-weight stimulants. Additionally, a list of requirements for such reduced self-weight simulants is proposed. The work concludes that the proposed new class of reduced particle density lunar simulants appears to have value and should be further pursued by the relevant communities.
Access status: Open Access ,
Development of the hydrogen market and local green hydrogen offtake in Africa
(MDPI, 2025-06-24) Uzoagba, Chidiebele E. J.; Ikpeka, Princewill M.; Nnabuife, Somtochukwu Godfrey; Onwualu, Peter Azikiwe; Ngasoh, Fayen Odette; Kuang, Boyu
Creating a hydrogen market in Africa is a great opportunity to assist in the promotion of sustainable energy solutions and economic growth. This article addresses the legislation and regulations that need to be developed to facilitate growth in the hydrogen market and allow local green hydrogen offtake across the continent. By reviewing current policy and strategy within particular African countries and best practices globally from key hydrogen economies, the review establishes compelling issues, challenges, and opportunities unique to Africa. The study identifies the immense potential in Africa for renewable energy, and, in particular, for solar and wind, as the foundation for the production of green hydrogen. It examines how effective policy frameworks can establish a vibrant hydrogen economy by bridging infrastructural gaps, cost hurdles, and regulatory barriers. The paper also addresses how local offtake contracts for green hydrogen can be used to stimulate economic diversification, energy security, and sustainable development. Policy advice is provided to assist African authorities and stakeholders in the deployment of enabling regulatory frameworks and the mobilization of funds. The paper contributes to global hydrogen energy discussions by introducing Africa as an eligible stakeholder in the emerging hydrogen economy and outlining prospects for its inclusion into regional and global energy supply chains.
Access status: Open Access ,
Robust aeronautical communications enabled by UAV operations and LEO satellites
(IEEE, 2025-04-08) Subasu, Stefan; Al-Rubaye, Saba; Tsourdos, Antonios
In the realm of modern aerospace communications, the integration of Unmanned Aerial Vehicles (UAVs) with Low Earth Orbit (LEO) satellite constellations can offer a transformative solution for enabling Beyond Visual Line of Sight (BVLOS) operations. Due to initial safety operation demand of UAV BVLOS communication new metrics, this paper proposes a new quality of service (QoS) framework for uplink communication between IRIDIUM satellite constellation and UAV. The objective is to benchmark key QoS metrics for UAVLEO communications using a Non-Terrestrial Network (NTN) narrowband (NB) channel. However, this study performs metrics such as latency and throughput across various elevation angles and environments. Different sample rates are evaluated to assess their impact on communication performance. Simulation analysis indicate that lower sample rates provide reduced latency and stable throughput suitable for telemetry, while higher sample rates increase throughput at the cost of higher latency. This study can be a road map for QoS metrics for optimizing satellite communication systems in UAV operations and demonstrates optimal communication for BVLOS missions in rural, suburban and underserved areas where ground infrastructure is limited. The findings are compared against current standards and regulatory benchmarks for validation.
Access status: Open Access ,
Causal reinforcement learning for optimisation of robot dynamics in unknown environments
(IEEE, 2024-10-29) Dcruz, Julian Gerald; Mahoney, Sam; Chua, Jia Yun; Soukhabandith, Adoundeth; Mugabe, John; Guo, Weisi; Arana-Catania, Miguel
Autonomous operations of robots in unknown environments are challenging due to the lack of knowledge of the dynamics of the interactions, such as the objects' movability. This work introduces a novel Causal Reinforcement Learning approach to enhancing robotics operations and applies it to an urban search and rescue (SAR) scenario. Our proposed machine learning architecture enables robots to learn the causal relationships between the visual characteristics of the objects, such as texture and shape, and the objects’ dynamics upon interaction, such as their movability, significantly improving their decision-making processes. We conducted causal discovery and RL experiments demonstrating the Causal RL’s superior performance, showing a notable reduction in learning times by over 24.5% in complex situations, compared to non-causal models.
Access status: Open Access ,
Automating emergency landing in cities with cognitive stress reducing explanations to pilot-in-the-loop
(IEEE, 2024-10-29) Balakrishnan, Hamsa; Lechardoy, Bastien; Collignon, Maxime; Sen, Anwesha; Ali, Ahmed; Verma, Ankit; Wisniewski, Mariusz; Chatzithanos, Paris; Tsourdos, Antonios; Xing, Yang; Guo, Weisi
Future smart cities will integrate urban air mobility (UAM) where electric vertical take-off and landing aircrafts (eVTOL) will improve labour and logistic mobility. One of the challenges in urban flight is emergency landing, where an eVTOL needs to land in an unofficial roof top or clear area safely within a time frame. In semi-autonomous eVTOLs, artificial intelligence (AI) is expected to assist in identifying emergency landing locations and navigation vectors, whilst the pilot flies and lands the eVTOL. Autonomously searching and correctly identifying safe candidate locations is important for safety of both the eVTOL and ground stakeholders. Furthermore, the processes of using AI to identify such locations should ideally be explainable to the pilot to reduce cognitive stress and aid the preparation of the emergency landing procedure. Here, we have developed a simulated emergency urban landing platform, whereby an eVTOL rotorcraft is scanning the ground for suitable emergency landing locations and actively explaining the navigation vectors to the pilot-in-the-loop. Cognitive stress is measured using real experiments using heart rate monitor, and an actor-critic deep reinforcement learning is used to learn what explanations are useful to reduce cognitive stress. The end result is that the eVTOL can identify emergency landing candidates, navigate to the safe landing zone (SLZ) whilst performing obstacle avoidance, and explain its decision making to the pilot-in-the-loop whilst minimizing its cognitive stress. We show through 3 scenarios that we can indeed reduce cognitive load significantly and also reduce the average time to reach the SLZ.
Access status: Open Access ,
Machine Learning Technology in Biomedical Engineering
(MDPI, 2024-04-29) Yu, Hongqing; Alzoubi, Alaa; Zhao, Yifan; Du Hongbo
"Machine Learning Technology in Biomedical Engineering" aims to provide a platform for researchers to showcase their latest research and findings on the application of machine learning technology in the field of biomedical engineering. The use of machine learning technology in healthcare has been growing rapidly in recent years and has the potential to revolutionize multiple aspects of healthcare, including disease diagnosis, treatment, and personalized medicine. This Special Issue covers a wide range of topics related to the application of machine learning in biomedical engineering, including predictive modelling, image and signal processing, deep learning, drug discovery, biomarker discovery, and medical decision making. By applying machine learning algorithms to large datasets of biomedical information, researchers and healthcare professionals can gain new insights into disease mechanisms, identify new biomarkers for disease, and develop more effective treatments. Machine learning algorithms can also be used to improve medical imaging analysis, automate medical diagnosis and decision making, and optimize drug-discovery processes. This Special Issue is significant because it encourages interdisciplinary collaboration between machine learning and biomedical-engineering researchers
Access status: Open Access ,
Parametric study of adaptive reinforcement learning for battery operations in microgrids
(Elsevier, 2025-09-01) Panda, Deepak Kumar; Das, Saptarshi; Abusara, Mohammad
Reinforcement learning (RL) has been increasingly used for efficient energy management systems (EMSs) in microgrids. The battery storage system in the microgrid can be controlled using efficient policies derived from RL. However, little attention has been paid so far to the parametric study, which is a fundamental step for efficient implementation of such RL algorithms. Unlike previous works which focused on the implementation of different RL algorithms, this paper mainly demonstrates the parametric sensitivity study of the RL algorithms. It involves investigating the effects of (1) controllable state discretization, (2) exogenous state discretization, (3) action discretization, (4) exploration and exploitation parameters, and (5) decision intervals. Moreover, the performance of the ε-greedy randomized RL algorithm is compared against the adaptive Q-learning, derived from the adaptive approximate dynamic programming (ADP). In many microgrids utilizing solar energy and battery storage, energy management still relies on manually tuned and inefficient algorithms. This is largely due to the sensitivity of RL algorithm parameters to factors such as the specific EMS problem, environment, action-state discretization, exploration parameter and time step. We show the univariate and multivariate kernel density estimate (KDE) plots to study the RL algorithms’ performance concerning the rewards and variation of the battery state of charge (SoC) and the net power imported from the grid. Overall, the deterministic adaptive RL performs better as compared to the randomized ε-greedy algorithms in terms of rewards and simulation time. Higher discretization levels in the action space affect the convergence rate while lower discretization levels in the state space influence the performance of the algorithm. The proposed parametric analysis can be easily adapted to other EMS in more complex microgrids.
Access status: Open Access ,
Opportunities and challenges for monitoring terrestrial biodiversity in the robotics age
(Springer Nature, 2025-06) Pringle, Stephen; Dallimer, Martin; Goddard, Mark A.; Le Goff, Léni K.; Hart, Emma; Langdale, Simon J.; Fisher, Jessica C.; Abad, Sara-Adela; Ancrenaz, Marc; Angeoletto, Fabio; Auat Cheein, Fernando; Austen, Gail E.; Bailey, Joseph J.; Baldock, Katherine C. R.; Banin, Lindsay F.; Banks-Leite, Cristina; Barau, Aliyu S.; Bashyal, Reshu; Bates, Adam J.; Bicknell, Jake E.; Bielby, Jon; Bosilj, Petra; Bush, Emma R.; Butler, Simon J.; Carpenter, Daniel; Clements, Christopher F.; Cully, Antoine; Davies, Kendi F.; Deere, Nicolas J.; Dodd, Michael; Drinkwater, Rosie; Driscoll, Don A.; Dutilleux, Guillaume; Dyrmann, Mads; Edwards, David P.; Farhadinia, Mohammad S.; Faruk, Aisyah; Field, Richard; Fletcher, Robert J.; Foster, Chris W.; Fox, Richard; Francksen, Richard M.; Franco, Aldina M. A.; Gainsbury, Alison M.; Gardner, Charlie J.; Giorgi, Ioanna; Griffiths, Richard A.; Hamaza, Salua; Hanheide, Marc; Hayward, Matt W.; Hedblom, Marcus; Helgason, Thorunn; Heon, Sui P.; Hughes, Kevin A.; Hunt, Edmund R.; Ingram, Daniel J.; Jackson-Mills, George; Jowett, Kelly; Keitt, Timothy H.; Kloepper, Laura N.; Kramer-Schadt, Stephanie; Labisko, Jim; Labrosse, Frédéric; Lawson, Jenna; Lecomte, Nicolas; de Lima, Ricardo F.; Littlewood, Nick A.; Marshall, Harry H.; Masala, Giovanni L.; Maskell, Lindsay C.; Matechou, Eleni; Mazzolai, Barbara; McConnell, Alistair; Melbourne, Brett A.; Miriyev, Aslan; Nana, Eric Djomo; Ossola, Alessandro; Papworth, Sarah; Parr, Catherine L.; Payo-Payo, Ana; Perry, Gad; Pettorelli, Nathalie; Pillay, Rajeev; Potts, Simon G.; Prendergast-Miller, Miranda T.; Qie, Lan; Rolley-Parnell, Persie; Rossiter, Stephen J.; Rowcliffe, Marcus; Rumble, Heather; Sadler, Jon P.; Sandom, Christopher J.; Sanyal, Asiem; Schrodt, Franziska; Sethi, Sarab S.; Shabrani, Adi; Siddall, Robert; Smith, Simón C.; Snep, Robbert P. H.; Soulsbury, Carl D.; Stanley, Margaret C.; Stephens, Philip A.; Stephenson, P. J.; Struebig, Matthew J.; Studley, Matthew; Svátek, Martin; Tang, Gilbert; Taylor, Nicholas K.; Umbers, Kate D. L.; Ward, Robert J.; White, Patrick J. C.; Whittingham, Mark J.; Wich, Serge; Williams, Christopher D.; Yakubu, Ibrahim B.; Yoh, Natalie; Zaidi, Syed A. R.; Zmarz, Anna; Zwerts, Joeri A.; Davies, Zoe G.
With biodiversity loss escalating globally, a step change is needed in our capacity to accurately monitor species populations across ecosystems. Robotic and autonomous systems (RAS) offer technological solutions that may substantially advance terrestrial biodiversity monitoring, but this potential is yet to be considered systematically. We used a modified Delphi technique to synthesize knowledge from 98 biodiversity experts and 31 RAS experts, who identified the major methodological barriers that currently hinder monitoring, and explored the opportunities and challenges that RAS offer in overcoming these barriers. Biodiversity experts identified four barrier categories: site access, species and individual identification, data handling and storage, and power and network availability. Robotics experts highlighted technologies that could overcome these barriers and identified the developments needed to facilitate RAS-based autonomous biodiversity monitoring. Some existing RAS could be optimized relatively easily to survey species but would require development to be suitable for monitoring of more ‘difficult’ taxa and robust enough to work under uncontrolled conditions within ecosystems. Other nascent technologies (for instance, new sensors and biodegradable robots) need accelerated research. Overall, it was felt that RAS could lead to major progress in monitoring of terrestrial biodiversity by supplementing rather than supplanting existing methods. Transdisciplinarity needs to be fostered between biodiversity and RAS experts so that future ideas and technologies can be codeveloped effectively.
Access status: Open Access ,
Machine Learning driven complex network analysis of transport systems
(Elsevier, 2025-07) Xia, Yuqin; Wang, Kewei; Tanirat, Purin; Lee, Bryan; Moulitsas, Irene; Li, Jun
A complex network is a system of interconnected nodes linked by edges, exhibiting non-trivial structural features such as community structure or scale-free distributions. This study develops a novel and generic Machine Learning-driven framework that integrates Complex Network Theory and Machine Learning methods for a comprehensive and multifaceted analysis of transport systems. Specifically, four key functional development and analysis are undertaken: 1) Network analysis, using complex network indicators to study the static properties of the transport systems; 2) Network clustering, employing K-means and hierarchical clustering methods to identify underlying community structures; 3) Network resilience, examining the networks' dynamic characteristics and structural evolution under escalating node attacks to evaluate their robustness; 4) Link and feature prediction, developing Graph Convolutional Networks (GCNs) and Multi-Layer Perceptron (MLP) models to predict hidden links and features. The proposed framework is subsequently applied to two distinct transport systems, namely, the China railway network and the Paris multi-modal transport system. The complex network analysis reveals distinct complex network features in network scale, density, and efficiency, yet both demonstrate a power-law distribution. The clustering analysis based on various node and edge properties exhibits a pattern of concentric circles, radiating outward from the urban to peripheral cities in China railway network, while a high density of short-distance connections within central Paris and a prevalence of long-distance connections in the outskirts. The network attack simulations show fine resilience of the Parisian multi-modal system and low resilience of the China railway network. For link prediction, an encoder-decoder model based on GCN and multiple MLPs are developed for various scenarios. The results for the China railway network reveal critical interregional links, emphasizing the need to strengthen regional connectivity, such as expanding the high-speed railway between Hainan Island and the mainland, and establishing a major transportation artery running from south to north. In the Paris transport system, this study predicts an interesting link extending from southern Paris eastward toward northern Seine-et-Marne, indicating a demand for a direct connection. For both networks, the hidden links are largely concentrated in more developed areas, likely driven by strong economic and social interaction demands, highlighting the need for more balanced transport network development. Overall, the results of this study align closely with existing literature and official transport development plans. This research contributes to the theoretical development in Complex Network Analysis using Machine Learning and offers valuable insight to improve the two transport systems.
Access status: Open Access ,
Distributed optimal nonlinear dynamic inversion for multi-agents consensus
(Elsevier, 2025-07) Mondal, Sabyasachi; Tsourdos, Antonios
In this paper, we propose an optimal distributed controller based on Nonlinear Dynamic Inversion (NDI) theory and apply it to solve the consensus of nonlinear multi-agent systems (MASs). Our proposed method addresses the limitations of existing Distributed Nonlinear Dynamic Inversion (DNDI) techniques, which only apply to agents with square output. We formulated an optimal control problem to minimize a quadratic cost function while satisfying a set of linear constraints derived by simplifying the enforced consensus error dynamics. By relaxing the previous limitation, we introduced a distributed optimal framework called Distributed Optimal NDI (DONDI). This framework achieves consensus and incorporates additional objectives, such as minimizing control energy. The design of Optimal DNDI inherits all the advantages of NDI and provides an optimized allocation of control for achieving consensus in MAS. Also, we have shown how the controller handles the communication noise. This approach represents a significant advancement in multi-agent control, and our experimental results demonstrate its satisfactory performance and effectiveness.
Access status: Open Access ,
Novel hybrid prognostics of aircraft systems
(MDPI, 2025-05-28) Fu, Shuai; Avdelidis, Nicolas P.; Plastropoulos, Angelos
Accurate forecasting of the remaining useful life (RUL) of aviation equipment is crucial for enhancing safety and reducing maintenance costs. This study presents a novel hybrid prognostic methodology that integrates physics-based and data-driven models to improve RUL estimations for critical aircraft components. The physics-based approach simulates long-term degradation patterns using fundamental principles such as mass conservation and Bernoulli’s equation, while the data-driven model employs a hyper tangent boosted neural network (HTBNN) to detect short-term anomalies and deviations in real-time sensor data. The integration of various models enhances accuracy, adaptability, and reliability in prognostics. The proposed methodology is assessed using NASA’s N-CMAPSS dataset for gas turbines and a fuel system test rig, demonstrating a 15% improvement in prediction accuracy and a 20% reduction in uncertainty compared to traditional methods. These findings highlight the potential for widespread application of this hybrid methodology in predictive maintenance and prognostic and health management (PHM) of aircraft systems.
Access status: Open Access ,
Fire detection automation in search drones using a modified DeepLabv3+ approach
(Institute of Electrical and Electronics Engineers (IEEE), 2024-10-29) Choudhary, Abhinav; Perrusquía, Adolfo; Al-Rubaye, Saba; Guo, Weisi
Drones have become a key component in current search and rescue applications such as wildfire detection. The accurate detection of fire in forests plays a crucial global factor to reduce environmental damage and the preservation of wildlife. Current fire detection systems combine the merits of expert-learning systems and light-weight deep learning architectures. The key idea is to introduce color-based rules to identify potential fire pixels and create the associated mask that feeds a light-weight convolutional neural network (CNN) for image segmentation. However, expert learning systems are not robust and suffer of cognitive bias that induce a high number of false positives. In addition, CNN-based architectures cannot capture long-range dependencies reducing the segmentation fidelity. To overcome these gaps, this paper proposes a light weight deep learning (DL) architecture for fire segmentation. The approach is inspired in the Deeplabv3+ architecture for image segmentation. The novelty lies in the incorporation of vision transformers that heavily reduces the model complexity and avoid the usage of color-based rules. Experiments are conducted using open-access fire datasets. The results demonstrate competitive performance and highlight its potential use in drones applications.
Access status: Open Access ,
Drone pollution tracking in cities using recurrent proximal policy optimization learning
(Institute of Electrical and Electronics Engineers (IEEE), 2024-10-29) Eliades, Andreas; Thellier, Elie; Tian, Haitao; Mehta, Shivam; Almesafri, Nouf; Chen, Hongqian; Wei, Zhuangkun; Perrusquía, Adolfo; Liu, Cunjia; Guo, Weisi
Future smart cities will need to monitor polluters that periodically or burst emit illegal gases that is harmful to the environment. Tracking these sources in cities that have building obstacles and variation wind vector fields is challenging. Traditional methods using gradient kernels and partial-swarm-optimisation may not be suitable when the emissions are intermittent and pollution concentrations maybe trapped in local pockets. As such, step size tuning becomes difficult to generalise in these variational dynamic pollution environments. Here, in this paper, we have developed a simulated urban pollution propagation environment, whereby a drone is scanning the environment for gradients to search and localise the source. We consider both proximal policy optimisation (PPO)-based reinforcement learning and its recurrent PPO (R-PPO) alternative to achieve stable and reliable improvement of policy without the need to fine tune step sizes. We show localisation results across a range of wind, obstacle, and emission scenarios with success rate of 76-79% and high path efficiency of 95-96% in ideal conditions. When we examine alternative city structures and burst emissions, we can achieve success rate of 34% and path efficiency of 52%, showing that there is some generalisation in capability.
Access status: Open Access ,
Distributed Spaceborne SAR: a review of systems, applications, and the road ahead
(IEEE, 2025-12-31) Hu, Cheng; Li, Yuanhao; Chen, Zhiyang; Liu, Feifeng; Zhang, Qingjun; Monti-Guarnieri, Andrea V.; Hobbs, Stephen E.; Anghel, Andrei; Datcu, Mihai
As a crucial sensor for wide-area Earth observation, spaceborne synthetic aperture radar (SAR) plays a pivotal role in large-scale terrain mapping, ocean observation, disaster monitoring, and so forth. Driven by the increasing demands for diverse applications, enhanced performance, and the continuous advancement of satellite and radar technologies, the distributed configuration has emerged as a key developmental trend for spaceborne SAR. This review comprehensively summarizes the systems and typical applications of distributed spaceborne SAR. The system configurations encompass homogenous distributed SAR, formed by multiple identical or similar platforms, and heterogeneous distributed SAR, characterized by significant differences between the transmitting and receiving platforms. Typical applications of distributed SAR include intelligent target recognition, terrain mapping, deformation retrieval, atmosphere measurement, and ocean observation, among others. Finally, the review offers a prospective outlook on the future development of distributed spaceborne SAR.

Browse

Recent Submissions