In recent decades, deep learning (DL) has become a rapidly growing research direction, redefining the state-of-the-art performances in wide range of techniques, such as object detection and speech recognition. aircraft design, dynamics, control field, many works hinge on information-rich data-driven approach, which includes fusion-based prognostic health management, airliner's flight safety monitoring, intelligent sensing, systems development. While DL provides great potentials to solve...

Compared with traditional model-based fault detection and classification (FDC) methods, deep neural networks (DNNs) prove to be more accurate for aerospace sensors. An emerging approach, called image-based intelligent FDC, converts sensor data into images, treating FDC as abnormal region problem on the image. Although promising advances have been claimed, due small size of stacked image, diminutive convolutional kernels shallow DNN layers were used, which hinders performances. In this paper,...

In recent years, unmanned aerial vehicles (UAV) have been increasingly used in power line inspections. Birds often nest on transmission towers, which threatens safe operation. The existing research bird’s inspection using UAVs mainly stays at the level of image postprocessing detection, has poor real-time performance and cannot obtain timely detection results. Considering above shortcomings, we designed a UAV system based deep learning technology for autonomous flight, positioning...

Space infrared dim target recognition is an important applications of space situational awareness (SSA). Due to the weak observability and lack geometric texture target, it may be unreliable rely only on grayscale features for recognition. In this paper, intelligent information decision-level fusion method which takes full advantage ensemble classifier Dempster–Shafer (DS) theory proposed. To deal with problem that DS produces counterintuitive results when evidence conflicts, a...

This article proposes a stabilizing control scheme based on partial-state decomposition to exponentially stabilize multi-input and multioutput nonminimum phase nonlinear systems in general normal form with relative degree. The reveals that variables can play an essential role the whole system. Specifically, are decomposed into sum of two vector signals <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math...

In within-visual-range (WVR) air combat, basic fighter maneuvers (BFMs) are widely used. Air combat engagement database (ACED) is a dedicated for researching WVR combat. Utilizing the data in ACED, Transformer-based BFM decision support scheme developed to enhance pilot’s making The proposed model significantly outperforms baseline long short-term memory (LSTM)-based accuracy. To augment interpretability of this approach, Shapley Additive Explanation (SHAP) analysis employed, exhibiting...

Aircraft sensors are crucial for ensuring the safe and efficient operation of aircraft. However, these vulnerable to external factors that can lead malfunctions, making fault diagnosis essential. Traditional deep learning-based methods often face challenges, such as limited data representation insufficient feature extraction. To address problems, this paper proposes an enhanced GraphSage-based method incorporates attention mechanisms. First, signal representing coupling characteristics...

Carrier-based aircraft (CBA) landing involves complex system engineering characterized by strong non-linearity, significant coupling and susceptibility to environmental disturbances. To address uncertainties in parameters, carrier air-wake disturbances other challenges inherent CBA landing, this paper presents a longitudinal automatic based on adaptive fuzzy sliding-mode control. This was developed improve control accuracy stability during the critical phase. Furthermore, analyzes components...

This paper presents the experimental test of an unmanned ground vehicle delivering goods. Configuration and motion equations are illustrated, drivers for control introduced. In presence obstacles, collision-free path connecting from start to goal position is planned using Rapidly-exploring Random Tree (RRT) algorithm; collision detection, nodes selection, tree expansion, generation RRT presented, optimization approach discussed. To grip goods, mechanical arms manipulated based on inversed...

Morphing aircraft are able to keep optimal performance in diverse flight conditions. However, the change geometry always leads challenges design of controllers. In this paper, a new method for designing controller variable-sweep morphing is presented—dynamic inversion combined with L1 adaptive control. Firstly, dynamics vehicle analyzed and six degrees freedom (6DOF) nonlinear model based on multibody theory established. Secondly, dynamic (NDI) incremental (INDI) then employed realize...

Fault detection (FD) is important for health monitoring and safe operation of dynamical systems. Previous studies use model-based approaches which are sensitive to system specifics, attenuating the robustness. Data-driven methods have claimed accurate performances scale well different cases, but algorithmic structures enclosed operations “black,” jeopardizing its To address these issues, exemplifying FD problem aircraft air data sensors, we explore develop a robust (accurate, scalable,...

This paper presents a valley path planning algorithm based on the Hybrid A* algorithm. is aimed at finding for aircraft considering dynamics constraints and terrain limitations. The preliminaries involve establishment of 3D workspace digital elevation map (DEM) data addressing methods detection. Following this comprehensive groundwork, A*-based algorithm, employed to determine within while accommodating dynamic limitations, then introduced. In experimental test, validate effectiveness...

This paper introduces a framework that is constructed for target aircraft movement prediction the autonomous air combat technique. work inspired by common experience human pilots could foresee future moves of opponent in based on visual check target. Movement depicted body coordinates own aircraft; an infrared/optical image adopted; orientation estimated moment-invariants analysis neural networks; and position extrapolated current orientation. also includes test report proposed classic...

In the past few decades, in-flight icing has become a common problem for many missions, potentially leading to reduction in control effectiveness and flight stability, which would threaten safety. One of most popular methods address this is adaptive control. This paper establishes dynamic model an iced high-altitude long-endurance unmanned aerial vehicle (HALE-UAV) with disturbance measurement noise. Then, by combining multilayer perceptrons (MLP) nonlinear inversion (NDI) controller, we...