Browsing by Author "Ignatyev, Dmitry"
Now showing 1 - 14 of 14
Results Per Page
Sort Options
Item Open Access Advancing fault diagnosis in aircraft landing gear: an innovative two-tier machine learning approach with intelligent sensor data management(AIAA, 2024-01-04) Kadripathi, K. N.; Ignatyev, Dmitry; Tsourdos, Antonios; Perrusquía, AdolfoRevolutionizing aircraft safety, this study unveils a pioneering two-tier machine learning model specifically designed for advanced fault diagnosis in aircraft landing gear systems. Addressing the critical gap in traditional diagnostic methods, our approach deftly navigates the challenges of sensor data anomalies, ensuring robust and accurate real-time health assessments. This innovation not only promises to enhance the reliability and safety of aviation but also sets a new benchmark in the application of intelligent machine-learning solutions in high-stakes environments. Our method is adept at identifying and compensating for data anomalies caused by faulty or uncalibrated sensors, ensuring uninterrupted health assessment. The model employs a simulation-based dataset reflecting complex hydraulic failures to train robust machine learning classifiers for fault detection. The primary tier focuses on fault classification, whereas the secondary tier corrects sensor data irregularities, leveraging redundant sensor inputs to bolster diagnostic precision. Such integration markedly improves classification accuracy, with empirical evidence showing an increase from 95.88% to 98.76% post-imputation. Our findings also underscore the importance of specific sensors—particularly temperature and pump speed—in evaluating the health of landing gear, advocating for their prioritized usage in monitoring systems. This approach promises to revolutionize maintenance protocols, reduce operational costs, and significantly enhance the safety measures within the aviation industry, promoting a more resilient and data-informed safety infrastructure.Item Open Access A comprehensive survey of unmanned ground vehicle terrain traversability for unstructured environments and sensor technology insights(Elsevier, 2023-09-29) Beyçimen, Semih; Ignatyev, Dmitry; Zolotas, ArgyriosThis article provides a detailed analysis of the assessment of unmanned ground vehicle terrain traversability. The analysis is categorized into terrain classification, terrain mapping, and cost-based traversability, with subcategories of appearance-based, geometry-based, and mixed-based methods. The article also explores the use of machine learning (ML), deep learning (DL) and reinforcement learning (RL) and other based end-to-end methods as crucial components for advanced terrain traversability analysis. The investigation indicates that a mixed approach, incorporating both exteroceptive and proprioceptive sensors, is more effective, optimized, and reliable for traversability analysis. Additionally, the article discusses the vehicle platforms and sensor technologies used in traversability analysis, making it a valuable resource for researchers in the field. Overall, this paper contributes significantly to the current understanding of traversability analysis in unstructured environments and provides insights for future sensor-based research on advanced traversability analysis.Item Open Access Conceptual design study based on defined parameters for next-generation Martian rotorcrafts(IEEE, 2024-05-13) Youhanna, Vishal; Felicetti, Leonard; Ignatyev, DmitryThe remarkable achievement of NASA’s Ingenuity Helicopter has opened exciting possibilities for the future exploration of Mars, suggesting that aerobots will play a crucial role alongside rovers and landers. However, Ingenuity’s capabilities are limited by its small and relatively basic design. This limitation is primarily evident in its restricted long-range endurance and limited capacity for scientific payloads. To address these shortcomings and advance the field of Martian drone technology, this paper introduces a practical approach to optimising the Martian rotorcraft concepts within the set parameters. The primary objective of these concepts is to enhance performance, endurance, and payload capacity to meet more demanding requirements for future Martian aerobot missions. The paper addresses an essential phase in the design process—an initial sizing of rotary electric vertical takeoff and landing (eVTOL) configurations. This phase is informed by a comprehensive parametric analysis, which considers various factors affecting the performance of drones during hover (stationary flight), vertical climb (ascending flight), and forward flight. The analysis is based on the principles of simplified rotorcraft momentum theory, a foundational concept in rotorcraft engineering. These Martian drone concepts are tailored to address the more challenging mission requirements that future Martian exploration missions are likely to demand. These requirements may include extended flight durations, increased payload capacity to accommodate scientific instruments, and the ability to cover larger areas on the Martian surface. Importantly, the designs are constrained by the maximum size of the spacecraft aeroshell, ensuring that they can be safely transported to Mars within the confines of the protective aeroshell. Among the various configurations considered in this study, a tandem rotorcraft configuration emerged as the most efficient option. This configuration is expected to attain a balance between performance, endurance, and payload capacity, making it a promising choice for future Martian aerobot missions. In contrast, the analysis revealed that a conventional single main rotor configuration within the defined parameters performed poorly in meeting the requirements of the mission.Item Open Access Estimation of non-symmetric and unbounded region of attraction using shifted shape function and R-composition(Elsevier, 2022-09-21) Li, Dongyang; Ignatyev, Dmitry; Tsourdos, Antonios; Wang, ZhongyuanSum-of-squares programming is widely used for region of attraction (ROA) estimations of asymptotically stable equilibrium points of nonlinear polynomial systems. However, existing methods yield conservative results, especially for non-symmetric and unbounded regions. In this study, a cost-effective approach for ROA estimation is proposed based on the Lyapunov theory and shape functions. In contrast to existing methods, the proposed method iteratively places the center of a shifted shape function (SSF) close to the boundary of the acquired invariant subset. The set of obtained SSFs yields robust ROA subsets, and R-composition is employed to express these independent sets as a single but richer-shaped level set. Several benchmark examples show that the proposed method significantly improves ROA estimations, especially for non-symmetric or unbounded ROA without a significant computational burden.Item Open Access Fault detection in aircraft flight control actuators using support vector machines(MDPI, 2023-02-02) Grehan, Julianne; Ignatyev, Dmitry; Zolotas, ArgyriosFuture generations of flight control systems, such as those for unmanned autonomous vehicles (UAVs), are likely to be more adaptive and intelligent to cope with the extra safety and reliability requirements due to pilotless operations. An efficient fault detection and isolation (FDI) system is paramount and should be capable of monitoring the health status of an aircraft. Historically, hardware redundancy techniques have been used to detect faults. However, duplicating the actuators in an UAV is not ideal due to the high cost and large mass of additional components. Fortunately, aircraft actuator faults can also be detected using analytical redundancy techniques. In this study, a data-driven algorithm using Support Vector Machine (SVM) is designed. The aircraft actuator fault investigated is the loss-of-effectiveness (LOE) fault. The aim of the fault detection algorithm is to classify the feature vector data into a nominal or faulty class based on the health of the actuator. The results show that the SVM algorithm detects the LOE fault almost instantly, with an average accuracy of 99%.Item Open Access Futuristic Martian aerobot design(2022-08-26) Youhanna, Vishal; Ignatyev, Dmitry; Felicetti, LeonardNASA’s Ingenuity Helicopter has proved that flight is possible on Mars with its ingenious yet elementary design, but it lacks long-range endurance and the capacity to carry any dedicated scientific instruments. In this paper, we propose a preliminary study for an innovative development in the series of Martian drones. The Futuristic Mars Aerobot Design (FuMAD) proposes a foldable winged drone based on Ingenuity’s rotors design for enhancing long-range endurance and payload capacity.Item Open Access Integrated compact electrically powered and signaled actuation systems(AIAA, 2022-06-20) Wang, I-Tsun; Ignatyev, Dmitry; Inalhan, Gokhan; Collins, Andrew; Cheng, Szuyu; Stephen, ShirleyOne of the key challenges in enabling More Electric Aircraft is the development of electrically powered servos that meet or exceed the performance, packaging, weight, and cost of a hydraulic fly-by-wire servo. This paper introduces an innovative Electro-Hydrostatic Actuator that outperforms the existing solutions in terms of mass, size and energy efficiency. The innovative design features hydraulic regeneration when the commanded movement is aligned with the direction of external force. This new feature helps to decrease energy consumption. The high efficiency of the actuator prototype is confirmed by simulation with a verified MATLAB/Simulink model. Simulations also manifest that the proposed actuator has improved phase and gain margins as compared to existing solutions.Item Open Access A Loewner-based system identification and structural health monitoring approach for mechanical systems(Wiley, 2023-04-18) Dessena, Gabriele; Civera, Marco; Zanotti Fragonara, Luca; Ignatyev, Dmitry; Whidborne, James F.Data-driven structural health monitoring (SHM) requires precise estimates of the target system behaviour. In this sense, SHM by means of modal parameters is strictly linked to system identifcation (SI). However, existing frequency-domain SI techniques have several theoretical and practical drawbacks. Tis paper proposes using an input-output system identifcation technique based on rational interpolation, known as the Loewner framework (LF), to estimate the modal properties of mechanical systems. Pioneeringly, the Loewner framework mode shapes and natural frequencies estimated by LF are then applied as damage-sensitive features for damage detection. To assess its capability, the Loewner framework is validated on both numerical and experimental datasets and compared to established system identification techniques. Promising results are achieved in terms of accuracy and reliability.Item Open Access Low-cost multi-object positioning system with optical sensor fusion(AIAA, 2023-01-19) Pashchapur, Ravi Ashok; Chen, Yuxi; Ignatyev, DmitryIndoor position estimation of any moving objects with the aid of integration of multiple sensors such as optical, radio, and ultrasonic is an ongoing field of research. Although, commercial companies like VICON and OptiTrack provides the higher precision indoor positioning by using custom design optical sensors, but not every teaching or research institute can afford them because of the cost metric. To overcome this problem, an affordable low-cost solution for object tracking using multiple low-cost cameras is provided in this paper. The object tracking system introduced in this paper uses cameras to track active markers such as LEDs and estimate the coordinates of these LEDs with less than 0.15 meters of error in all the axes. The VICON camera system setup is used to opt ground truth measurements which later utilized for error estimation of the low-cost object tracking system.Item Open Access Non-linear control of a quadrotor with actuator delay(AIAA, 2024-01-04) Kartal, Muhammed R.; Ignatyev, Dmitry; Zolotas, ArgyriosDuring the last decade, Unmanned Aerial Vehicles (UAVs) gained significant interest for use in various application domains such as monitoring/surveillance, freight/cargo shipping, and agriculture spraying. Developing such vehicle platforms requires the utilization of robust control approaches to maintain stable and appropriate maneuvering capabilities, as well as to address system uncertainty such as payload variation or dynamic variations (e.g., spraying drones are affected by such uncertainty). Moreover, due to the rotor-based structure, rotorcraft UAVs are quite vulnerable to UAV systems control input signal delay. In terms of maintaining a robust approach for a rotorcraft UAV, it is essential to provide stability against UAV systems control input signal delay. This paper makes an analysis throughout to improve control efficiency against UAV systems control input signal delay. Through investigation and improved fault rejection, three controlling algorithms were designed and applied. The analysis focused on three different scenarios. Insights are discussed within the remit of command tracking performance with UAV systems control input signal delay.Item Open Access Parametric analysis of battery-electric rotorcraft configurations to fly on Mars(Council of European Aerospace Societies (CEAS), 2023-07-13) Youhanna, Vishal; Felicetti, Leonard; Ignatyev, DmitryThe success of NASA’s Ingenuity Helicopter promises that the future exploration of Mars will include aerobots in line with rovers and landers. However, Ingenuity lacks long-range endurance and scientific payload capacity because of its small and elementary design. In the series of optimised Martian drone concepts development, we introduced in this paper - an initial sizing of rotary eVTOL design configurations based on the performed parametric analysis for hover and vertical climb using simplified rotorcraft momentum theory, for a set of more challenging requirements for a Martian aerobot mission and sized to fit into the maximum spacecraft aeroshell limit. A tandem rotor configuration was found to be the most efficient configuration, whereas a conventional single main rotor configuration with small diameters manifested the poorest performance.Item Open Access Predicting autonomous vehicle navigation parameters via image and image-and-point cloud fusion-based end-to-end methods(IEEE, 2022-10-13) Beycimen, Semih; Ignatyev, Dmitry; Zolotas, ArgyriosThis paper presents a study of end-to-end methods for predicting autonomous vehicle navigation parameters. Image-based and Image & Lidar points-based end-to-end models have been trained under Nvidia learning architectures as well as Densenet-169, Resnet-152 and Inception-v4. Various learning parameters for autonomous vehicle navigation, input models and pre-processing data algorithms i.e. image cropping, noise removing, semantic segmentation for image data have been investigated and tested. The best ones, from the rigorous investigation, are selected for the main framework of the study. Results reveal that the Nvidia architecture trained Image & Lidar points-based method offers the better results accuracy rate-wise for steering angle and speed.Item Open Access Semantic segmentation based mapping systems for the safe and precise landing of flying vehicles(Elsevier, 2023-04-17) Dhami, Harsimret; Ignatyev, Dmitry; Tsourdos, AntoniosUnmanned Aerial Systems (UAS) are a promising technology for many areas, including transportation, agriculture, inspection, and rescue missions. However, to enable a high level of autonomy, including Beyond Visual Line of Sight (BVLOS) filght, the drones should be able to perform safe landings in unknown areas without an operator. Hence there is a need for development of safe landing methods for autonomous drones. The autonomous UAVs can often be operated more economically than the conventional manned aircraft. As technology advances, autonomous UAVs are expected to play an increasingly important role in a variety of industries and applications. In this paper we have explored a semantic segmentation-based approach for the problem of autonomous landing.Item Open Access THE TRAM-FPV RACING Open Database. Sequences complete indoor flight tests for the study of racing drones(University of Rioja, 2022-09-09) Castiblanco, J. M.; Garcia-Nieto, S.; Ignatyev, Dmitry; Blasco, X.This paper presents the TRAM-FPV Racing open database, generated from a set of indoor flights performed with five racing drones at Cranfield University (UK), specifically at the Flight Arena, one of the largest indoor flight fields in the world for research purposes. The database incorporates the position and orientation information in the space of five racing drone models using an optical measurement system (OMS). It includes readings from accelerometers, gyroscopes, and heading angles recorded by inertial unit (IMU) sensors. These databases are frequently used to develop and adjust the sensor fusion algorithms incorporated in the drones to estimate their current state vector. However, their field of application is vast, being able to be used, for example, for the development of the nonlinear mathematical models of drones or the generation of trajectories.