Unmanned aerial vehicles (UAVs) are becoming more widely used in various industries, raising growing concerns about their safety and reliability. The flight data of UAVs can directly reflect their flight health status; however, the rarity of abnormal flight data and the spatiotemporal characteristics of these data represent a significant challenge for constructing accurate and reliable anomaly detectors. To address this, this study proposes an anomaly detection framework that fully considers the temporal correlations and distribution characteristics of flight data. This framework first combines a one-dimensional convolutional neural network (1DCNN) with an autoencoder (AE) to establish a feature extraction model. This model leverages the feature extraction capabilities of the 1DCNN and the reconstruction capabilities of the AE to thoroughly extract the spatiotemporal features from UAV flight data. Then, to address the challenge of adaptive anomaly detection thresholds, this research proposes a nonlinear model of support vector data description (SVDD) utilizing a 0/1 soft-margin loss, referred to as L0/1-SVDD. This model replaces the traditional hinge loss function in SVDD with a 0/1 loss function, with the goal of enhancing the accuracy and robustness of anomaly detection. Since the 0/1 loss function is a bounded, non-convex, and non-continuous function, this paper proposes the Bregman ADMM algorithm to solve the L0/1-SVDD. Finally, the difference between the reconstructed and the actual value is employed to train the L0/1-SVDD, resulting in a hypersphere classifier that is capable of detecting UAV anomaly data. The experimental results using real flight data show that, compared with methods such as AE, LSTM, and LSTM-AE, the proposed method exhibits superior performance across five evaluation metrics.

With recent advances in airborne weapons, air combat tends to occur in the form of beyond-visual-range (BVR) combat and multi-aircraft cooperation. Target assignment is critical in multi-aircraft BVR air combat decision-making. Most previous research on target assignment for multi-aircraft cooperative BVR air combat has focused on centralized algorithms, which can be time-consuming and unreliable. This paper proposes an efficient distributed target assignment algorithm called the multi-target consensus-based auction algorithm (MTCBAA). First, by analyzing the main geometric aspects of BVR air combat, a target assignment model for cooperative BVR air combat was established. Next, based on a consensus-based auction algorithm (CBAA), the MTCBAA was developed to solve the target assignment problem by introducing a cooperative decision-making variable. Although the MTCBAA is based on a greedy mechanism, it can guarantee at least 50% global optimization performance, which was proven through a demonstration of the minimum optimization performance of a centralized target assignment algorithm, since the centralized algorithm is equivalent to the MTCBAA. Finally, experiments were conducted, including an experiment that illustrates the operation of the proposed algorithm, Monte Carlo comparisons with a centralized target assignment method based on the immune algorithm, and deployment experiments on a semi-physical simulation platform. Compared with the heuristic target assignment algorithm, the proposed algorithm significantly improved the target assignment efficiency. The practicality of the proposed algorithm was further verified through a distributed semi-physical simulation experiment.

Interval-valued linguistic neutrosophic sets (IVLNSs), Z-numbers, and the trapezium cloud model are powerful tools for expressing uncertainty and randomness. This paper aims to combine these methodologies. First, we review relevant concepts and operators, introducing a novel combination of IVLNSs and Z-numbers, which establishes a new form of expression. Subsequently, we propose the Z-interval-valued linguistic neutrosophic set-trapezium–trapezium cloud (Z-IVLNS-TTC) model, designed to minimize information loss and distortion during quantification. A novel method for calculating the objective weight vector is then developed using multi-objective programming (MOP). Drawing inspiration from the TOPSIS method, we propose a new approach for calculating the distance between Z-IVLNS-TTCs based on the p-norm. Finally, a group decision-making problem is presented to demonstrate the practical application of the proposed method. To validate the effectiveness and feasibility of the method, sensitivity analysis and comparisons with existing approaches are conducted.

Aiming at the difficulty of post-stall maneuvering control modeling and control of advanced aircraft under unsteady aerodynamics, a control method with high control accuracy and fast computation speed is proposed based on Radial Basis Function (RBF) network with minimum parameters learning (MPL) and dynamic surface control (DSC) method. Firstly, the aerodynamic characteristics of post-stall maneuvers are analyzed based on the experimental data of large-scale oscillation wind tunnels, and the key factors affecting the unsteady aerodynamic forces are obtained. Then, an accurate unsteady aerodynamic model is established based on the improved extreme learning machine (ELM) method. Secondly, the influence of unsteady aerodynamic forces on the control of post-stall maneuvers is considered. For the uncertainty of advanced aircraft model, high angle of attack flight control laws based on RBF-DSC are designed. In order to improve the calculation speed of the above control law and optimize the parameters, a post-stall maneuver control law method based on MPL-RBF-DSC is designed, and the stability of the method is proved. The coordinated allocation of the conventional aerodynamic surfaces and thrust vectors is realized based on the daisy chain method. Finally, the typical maneuver simulation of “Cobra” is carried out, which highlights the advantages of the design method in this paper, such as high control accuracy, short calculation time and strong robustness.

In the avionics industry, Integrated Modular Avionics (IMA) which introduces the concept of partition has been widely adopted for its isolating capability. However, the real-time performance of the IMA system mainly depends on the partition parameters. This leads to the question of how to design the partition parameters for satisfying the timing requirements of real-time applications. In this paper, the problem of partition parameter design for multiprocessors system is investigated. Firstly, the hierarchical scheduling strategy of IMA is analyzed, and a new schedulability analysis method is proposed to judge the schedulability of the partitions according to the partition period and execution time. Then, an approximation algorithm is developed to minimize the allocated bandwidth of the partitions while simultaneously guaranteeing tasks schedulability within the partitions. The harmonic period partitions, which are used as the constraint of partition parameter design, are realized by considering the scheduling mechanism of intra-partition and inter-partition. The total required bandwidth and the system overhead caused by partition scheduling are regarded as the optimization objective functions. Moreover, Multi-objective Evolutionary Algorithm Based on Decomposition (MOEA/D) method is improved by applying the Adjustment for the Direction Vectors (ADV) algorithm. Constrained Dominance Principle (CDP) is embedded into the improved algorithm to solve the constrained optimization problem. Consequently, simulation results show that the presented algorithm can achieve better coverage and uniformity than the compared algorithms while obtaining the partition parameters, and the system overhead and total required bandwidth can also be reduced.

Aiming at the requirement of attitude information module with high precision, small size and low power consumption for the control of miniature UAV, a practical attitude estimation algorithm based on the micro-electro-mechanical sensor is proposed in this paper, which realizes the accurate estimation of the attitude of the UAV under the condition of low acceleration. A low-cost MEMS gyroscope, accelerometer, and magnetometer are used in the system. The Euler angle is obtained by the state observer method based on Direction Cosine Matrix (DCM) which can be got by fusing the sensor data. Firstly, based on the basic idea of TRIAD algorithm, a method to determine the attitude rotation matrix by accelerometer and magnetometric measurement is proposed. Compared with the traditional method, this method does not have to calculate the inverse of the matrix. Secondly, a state observer is intended to estimate the attitude of the system. The state observer doesn't have to observe the bias of the gyroscope, but still ensures the convergence of the Euler angle. Finally, the simulation based on the actual sampling data of the MEMS sensor shows that the output of the state observer designed in this paper still has high accuracy and good dynamic characteristics under the condition of gyroscope noise and bias. 针对微小型无人飞行器的控制对高精度、小体积、低功耗的姿态信息的需求，提出了一种实用的基于MEMS传感器的姿态解算算法，实现了在低加速度状态下对飞行器姿态的精准估计。该算法将MEMS陀螺仪、加速度计和磁力计的数据作为输入，采用一种全局渐进稳定的状态观测器方法对3种传感器数据进行融合，进而得到欧拉角输出。首先，针对实际航姿参考系统（AHRS）设计的需求，改进了TRIAD算法，使用加速度计和磁力计的量测向量来估计姿态旋转矩阵。与传统方法相比，该方法避免了矩阵的求逆过程。其次，在获得了量测向量确定的姿态旋转矩阵的基础上，设计了无需观测陀螺仪零偏的状态观测器，并证明了姿态角的收敛性。最后，基于实际MEMS传感器采样数据的仿真结果表明，在存在陀螺仪噪声和零偏的情况下，文中设计的状态观测器输出依然具有较高的精度和较好的动态特性。