Aerospace Systems最新文献

Underwater target detection is a critical and rapidly evolving research area with significant applications in both military and civilian fields. Multi-Beam Forward-Looking Sonar (MFLS) operates reliably in low-visibility conditions and is one of the most widely used technologies for underwater detection. However, the complex and dynamic underwater environment, signal attenuation and distortion, along with the high cost of signal acquisition and transmission, make MFLS images detection one of the most challenging tasks in computer vision and image processing. To address these challenges, this paper proposes a target detection model based on MFLS, named AGD-YOLO. First, the ADNet attention mechanism is introduced to enhance performance by focusing on relevant features while suppressing unrelated noise. This denoising mechanism balances efficiency and further improves the model’s detection performance. Second, MPDIoU is adopted as the boundary regression loss, which considers the overlapping region, center point distance, and deviations in width and height, thereby enhancing the efficiency and accuracy of bounding box regression. Third, a new dataset based on MFLS is constructed to facilitate the detection of Unmanned Underwater Vehicle (UUV). Experimental results show that the proposed model improves ({mAP}_{0.5:0.95}) by 2.6% compared to the second-best detection algorithm, significantly enhancing detection performance on MFLS images.

This paper investigates the evolution properties of the flow field structure for axial descent rotor based on the unsteady momentum source method combined with the Computational Fluid Dynamics (CFD). The study focuses on analyzing the speed critical value during the onset of or exit from the Vortex Ring State (VRS), and its changing characteristics of the flow field structure. Results from the Lagrangian Coherent Structure (LCS) analysis reveal the switch particularity between the tubular slipstream and the annular vortex, suggesting the criticality change character on flow field structure which occurs in the evolution process of VRS. These criticality features, that is the VRS boundaries described by the flow structure change, as determined by this method, are consistent with the existing theoretical and experimental results, verifying the feasibility of the established analysis method in the study of such boundaries. This work provides a robust framework for studying VRS boundaries and offers insights for further research on the underlying flow mechanism.

Predicting hard landings is crucial for aiding pilots’ decisions and ensuring flight safety. This paper addresses the limitations of current hard landing prediction models, specifically in terms of long-term forecasting accuracy and explainability. To overcome these challenges, it introduces the Informer hard landing prediction model, developed using QAR data, and performs an in-depth explainability analysis of the model’s output. Following the principles of learning assurance, the data processing and model training phases are standardized. This involves the application of forward–backward filtering and Granger causality testing to refine the QAR data, thus creating a dataset that aligns with essential prediction standards. The Informer model addresses the challenges of multivariate time series discontinuities by localizing its network to enhance data adaptability. During model training and testing, hyperparameters are finely tuned to maximize prediction accuracy and generalizability. To improve transparency, the model employs an attention weight matrix and a feature reset-based explainability method. Tests show that models trained on datasets developed through a defined data management process deliver favorable predictive performance. The localized enhanced network improved prediction accuracy by 23.5% and increased its capacity to learn from discontinuous multivariate time series. Compared to the LSTM network, the Informer network achieved an 18.83% improvement in prediction accuracy and demonstrated superior long-time series prediction capabilities.

There are about 1,900 electrical measuring equipment in the aircraft assembly workshop and aircraft production line, which is directly related to the manufacturing quality of the aircraft. This paper evaluates the health status of electrical measuring equipment based on Analytical Hierarchy Process. The bottom-up health status evaluation system of electrical measuring equipment is established by selecting an appropriate number of health indicators. According to the failure mode summary of electrical measuring equipment, the evaluation indexes at all levels are determined, the health assessment and judgment matrix of electrical measuring equipment is constructed. The 1–9 scale method is used for quantitative analysis of the indexes of electrical measuring equipment. The health level of the electrical measuring equipment is divided into 5 levels, and the corresponding relationship between the score of the measuring equipment and the health status is formulated. The 0–1 method and fuzzy distribution method are used to score each quantitative index. The historical data of a company electrical measuring equipment is used for example analysis, and the example results show that the calculation results of the health status score of the general measuring equipment is 0.951. The health status of the general measuring equipment is health. The health status score of the special measurement equipment is 0.877. The health status of the aviation specific measuring equipment is available.

The paper develops and investigates various options for separating the first and second stages of a promising launch vehicle without using pyrotechnic elements (such as the “Clamp Band” type, “petal” and “ball” types). A review and analysis of the applicability of pyrotechnic elements as part of separation devices of existing and promising launch vehicles was carried out, as a result, it was revealed that their use is difficult for technological reasons related to the need for specialized devices and equipment for accurate control of the detonation process and the likelihood of a large number of fragments and shock loads during operation, which negatively affects the provision of specified structural and operational characteristics of launch vehicles. The basic requirements for ensuring the rational operation of the proposed separation devices, taking into account the possibility of their multiple use, are considered. Experimental and mathematical modeling of relative motion of the stages separating according to the “cold” scheme under the influence of static and dynamic loads has been carried out, and rational technical solutions and design and technological approaches for the proposed separation devices have been selected. The results of the research on assessment of the stress–strain state of structural elements of the proposed separation devices without using pyrotechnic elements in various configurations, as well as their novelty, are presented.

Acoustic field reconstruction for aircraft engine fans is essential for effective noise reduction. However, the use of a limited number of far-field measurement points in the reconstruction process exacerbates the ill-posedness issues, which necessitates the adoption of regularization techniques. The hierarchical Bayesian-based regularisation method has recently been applied to solve the equivalent source intensity distribution and reconstruct the sound field. However, previous methods have failed to accurately obtain the acoustic modal coefficients of the sound source, which are essential for determining the radiation type and directivity. This paper proposes a sound field reconstruction method that applies the hierarchical Bayesian algorithm to the source modal coefficient solution. Firstly, the deconvolution beamforming method obtains the sound source position. Subsequently, the hierarchical Bayesian algorithm is employed to obtain the source modal coefficients of the sound field, thereby completing the reconstruction of the sound field in the far-field region. Experimental results indicate that the proposed algorithm is highly effective in reconstructing far-field sound fields. Under free-field conditions and in mid-high frequency ranges, the average reconstruction error can be significantly reduced by using a few far-field microphones compared to traditional methods.

The article analyzes the main options for design solutions of separation devices of promising launch vehicles and payloads without using pyrotechnic elements, such as the “Clamp Band” type, “ball” and “petal” types, as well as the bandage-based separation device. Parametric redundancy has been performed to achieve the required level of the reliability, providing the necessary coefficient of parametric margin. Engineering Critical Assessment of structural elements of the proposed separation devices by using the scorecard method is analyzed and considered. The reliability requirements are considered, which must be confirmed during complex experimental processing, including laboratory debugging, control developing, control sampling, control finishing and manufacturing tests of individual large-sized elements and subsystems included in the proposed separation devices, as well as recommendations for ensuring the reliability of their operation at the design development stage.

Unmanned aerial vehicles (UAVs) propelled by electricity have emerged as a prominent concept in aviation due to their eco-friendly and stealth characteristics. To address the limitations of Polymer Membrane Fuel Cell (PMFC), which serve as the primary power source but exhibit sluggish responses to sudden load changes, this research proposes a novel hybrid power system incorporating a Li-Ion battery. This hybrid setup ensures superior dynamic response while maintaining high power-to-weight efficiency. This paper presents an intelligent energy management system (EMS), which effectively regulates power flow between the PMFC and Li-Ion battery through a multi-input multi-output (MIMO) control framework. The uniqueness of this study lies in the comparative evaluation of two advanced EMS control strategies: Fuzzy Logic Control and the Adaptive Neuro-Fuzzy Inference System (ANFIS), under multiple flight modes. By thoroughly analyzing system transients and dynamic behaviors using MATLAB/SIMULINK, this work provides a detailed insight into optimizing UAV power efficiency. Unlike previous studies, this research highlights the distinct advantages and limitations of each control strategy for different flight phases, providing a comprehensive benchmark for future EMS designs in UAV applications.

This study investigates the potential of Fish Bone Morphing (FBM) technology for enhancing the aerodynamic performance of aerofoils. FBM is a bio-inspired concept that incorporates flexible structural elements to facilitate morphing of the aerofoil shape in response to varying flight conditions. The NACA 2412 aerofoil is chosen for its camber adaptability, and CFD simulations are employed to assess the efficacy of FBM integration. The k–ω SST turbulence model is adopted for its ability to combine the strengths of the k–ω and k–ε models. The investigation encompasses a systematic exploration of geometric configurations, including trailing edge deflection at various chord lengths (0.6c, 0.65c, 0.70c, 0.75c, and 0.80c) and deflection angles (4°, 8°, and 12°). The results reveal that FBM aerofoils exhibit a consistent increase in maximum lift coefficient compared to conventional aerofoils across all deflection points and angles. Additionally, improvements in lift-to-drag ratio are observed. Furthermore, the stalling angle remains unaffected by deflection point variations, while deflection angle increments lead to corresponding increases in maximum lift coefficient. The morphing aerofoil with a 0.60c deflection point demonstrates the most significant enhancement in maximum lift coefficient, achieving a 13% increase at a 12° deflection angle. These findings establish the aerodynamic efficiency of FBM aerofoils, characterized by superior lift-to-drag ratios and increased maximum lift coefficients.

Dynamic multi-robot task allocation (MRTA) requires real-time responsiveness and adaptability to rapidly changing conditions. Existing methods, primarily based on static data and centralized architectures, often fail in dynamic environments that require decentralized, context-aware decisions. To address these challenges, this paper proposes a novel graph reinforcement learning (GRL) architecture, named Spatial-Temporal Fusing Reinforcement Learning (STFRL), to address real-time distributed target allocation problems in search and rescue scenarios. The proposed policy network includes an encoder, which employs a Temporal-Spatial Fusing Encoder (TSFE) to extract input features and a decoder uses multi-head attention (MHA) to perform distributed allocation based on the encoder’s output and context. The policy network is trained with the REINFORCE algorithm. Experimental comparisons with state-of-the-art baselines demonstrate that STFRL achieves superior performance in path cost, inference speed, and scalability, highlighting its robustness and efficiency in complex, dynamic environments.