A mathematical model to determine the optimal production lot size for a deteriorating production system under an extended product inspection policy is developed. The last-K product inspection policy is considered so that the nonconforming items can be reduced, under which the last K products in a production lot are inspected and the nonconforming items from those inspected are reworked. Consider that the products produced towards the end of a production lot are more likely to be nonconforming, is proposed an extended product inspection policy for a deteriorating production system. That is, in a production lot, product inspections are performed among the middle K1 items and after inspections, all of the last K2 products are directly reworked without inspections. Our objective here is the joint optimization of the production lot size and the corresponding extended inspection policy such that the expected total cost per unit time is minimized. Since there is no closed form expression for our optimal policy, the existence for the optimal production inspection policy and an upper bound for the optimal lot size are obtained. Furthermore, an efficient solution procedure is provided to search for the optimal policy. Finally, numerical examples are given to illustrate the proposed model and indicate that the expected total cost per unit time of our product inspection model is less than that of the last-K inspection policy.

The rapid evolution of unmanned aerial vehicle (UAV) technology and autonomous capabilities has positioned UAV as promising last-mile delivery means. Vehicle and onboard UAV collaborative delivery is introduced as a novel delivery mode. Spatiotemporal collaboration, along with energy consumption with payload and wind conditions play important roles in delivery route planning. This paper introduces the traveling salesman problem with time window and onboard UAV (TSP-TWOUAV) and emphasizes the consideration of real-world scenarios, focusing on time collaboration and energy consumption with wind and payload. To address this, a mixed integer linear programming (MILP) model is formulated to minimize the energy consumption costs of vehicle and UAV. Furthermore, an adaptive large neighborhood search (ALNS) algorithm is applied to identify high-quality solutions efficiently. The effectiveness of the proposed model and algorithm is validated through numerical tests on real geographic instances and sensitivity analysis of key parameters is conducted.

The earth observation satellites (EOSs) scheduling problem for emergency tasks often presents many challenges. For example, the scheduling calculation should be completed in seconds, the scheduled task rate is supposed to be as high as possible, the disturbance measure of the scheme should be as low as possible, which may lead to the loss of important observation opportunities and data transmission delays. Existing scheduling algorithms are not designed for these requirements. Consequently, we propose a rolling horizon strategy (RHS) based on event triggering as well as a heuristic algorithm based on direct insertion, shifting, backtracking, deletion, and reinsertion (ISBDR). In the RHS, the driven scheduling mode based on the emergency task arrival and control station time window events are designed to transform the long-term, large-scale problem into a short-term, small-scale problem, which can improve the schedulability of the original scheduling scheme and emergency response sensiti-vity. In the ISBDR algorithm, the shifting rule with breadth search capability and backtracking rule with depth search capability are established to realize the rapid adjustment of the original plan and improve the overall benefit of the plan and early completion of emergency tasks. Simultaneously, two heuristic factors, namely the emergency task urgency degree and task conflict degree, are constructed to improve the emergency task scheduling guidance and algorithm efficiency. Finally, we conduct extensive experiments by means of simulations to compare the algorithms based on ISBDR and direct insertion, shifting, deletion, and reinsertion (ISDR). The results demonstrate that the proposed algorithm can improve the timeliness of emergency tasks and scheduling performance, and decrease the disturbance measure of the scheme, therefore, it is more suitable for emergency task scheduling.

A novel multi-view 3D face registration method based on principal axis analysis and labeled regions orientation called local orientation registration is proposed. The pre-registration is achieved by transforming the multi-pose models to the standard frontal model’s reference frame using the principal axis analysis algorithm. Some significant feature regions, such as inner and outer canthus, nose tip vertices, are then located by using geometrical distribution characteristics. These regions are subsequently employed to compute the conversion parameters using the improved iterative closest point algorithm, and the optimal parameters are applied to complete the final registration. Experimental results implemented on the proper database demonstrate that the proposed method significantly outperforms others by achieving 1.249 and 1.910 mean root-mean-square measure with slight and large view variation models, respectively.

This paper considers multi-frequency passive radar and develops a multi-frequency joint direction of arrival (DOA) estimation algorithm to improve estimation accuracy and resolution. The developed algorithm exploits the sparsity of targets in the spatial domain. Specifically, we first extract the required frequency channel data and acquire the snapshot data through a series of preprocessing such as clutter suppression, coherent integration, beamforming, and constant false alarm rate (CFAR) detection. Then, based on the framework of sparse Bayesian learning, the target’s DOA is estimated by jointly extracting the multi-frequency data via evidence maximization. Simulation results show that the developed algorithm has better estimation accuracy and resolution than other existing multi-frequency DOA estimation algorithms, especially under the scenarios of low signal-to-noise ratio (SNR) and small snapshots. Furthermore, the effectiveness is verified by the field experimental data of a multi-frequency FM-based passive radar.

Autonomous umanned aerial vehicle (UAV) manipulation is necessary for the defense department to execute tactical missions given by commanders in the future unmanned battlefield. A large amount of research has been devoted to improving the autonomous decision-making ability of UAV in an interactive environment, where finding the optimal maneuvering decision-making policy became one of the key issues for enabling the intelligence of UAV. In this paper, we propose a maneuvering decision-making algorithm for autonomous air-delivery based on deep reinforcement learning under the guidance of expert experience. Specifically, we refine the guidance towards area and guidance towards specific point tasks for the air-delivery process based on the traditional air-to-surface fire control methods. Moreover, we construct the UAV maneuvering decision-making model based on Markov decision processes (MDPs). Specifically, we present a reward shaping method for the guidance towards area and guidance towards specific point tasks using potential-based function and expert-guided advice. The proposed algorithm could accelerate the convergence of the maneuvering decision-making policy and increase the stability of the policy in terms of the output during the later stage of training process. The effectiveness of the proposed maneuvering decision-making policy is illustrated by the curves of training parameters and extensive experimental results for testing the trained policy.

In a cloud-native era, the Kubernetes-based workflow engine enables workflow containerized execution through the inherent abilities of Kubernetes. However, when encountering continuous workflow requests and unexpected resource request spikes, the engine is limited to the current workflow load information for resource allocation, which lacks the agility and predictability of resource allocation, resulting in over and under-provisioning resources. This mechanism seriously hinders workflow execution efficiency and leads to high resource waste. To overcome these drawbacks, we propose an adaptive resource allocation scheme named adaptive resource allocation scheme (ARAS) for the Kubernetes-based workflow engines. Considering potential future workflow task requests within the current task pod’s lifecycle, the ARAS uses a resource scaling strategy to allocate resources in response to high-concurrency workflow scenarios. The ARAS offers resource discovery, resource evaluation, and allocation functionalities and serves as a key component for our tailored workflow engine (KubeAdaptor). By integrating the ARAS into KubeAdaptor for workflow containerized execution, we demonstrate the practical abilities of KubeAdaptor and the advantages of our ARAS. Compared with the baseline algorithm, experimental evaluation under three distinct workflow arrival patterns shows that ARAS gains time-saving of 9.8% to 40.92% in the average total duration of all workflows, time-saving of 26.4% to 79.86% in the average duration of individual workflow, and an increase of 1% to 16% in centrol processing unit (CPU) and memory resource usage rate.

To deal with the problem that the block sparse Bayesian algorithm exists in grid estimation, an off-grid weighted block sparse Bayesian algorithm is proposed based on coherent accumulation. The algorithm first uses the signal characteristics to coherently accumulate the polarization-sensitive array received data to enhance the signal-to-noise ratio (SNR); then the first-order Taylor expansion of the steering vector is performed, and an off-grid real-valued model is introduced by improving the block structure; then the weighting vectors are introduced to accelerate the iteration of the algorithm and reduce the number of iterations; and finally, the solution of the off-grid parameters is achieved by iterative optimization of the parameters. Compared with the traditional block sparse Bayesian learning (BSBL) algorithm, the method iterates faster and achieves efficient joint off-grid polarization-DOA estimation. Simulation results show the effectiveness of the algorithm.

In order to improve the autonomous ability of unmanned aerial vehicles (UAV) to implement air combat mission, many artificial intelligence-based autonomous air combat maneuver decision-making studies have been carried out, but these studies are often aimed at individual decision-making in 1v1 scenarios which rarely happen in actual air combat. Based on the research of the 1v1 autonomous air combat maneuver decision, this paper builds a multi-UAV cooperative air combat maneuver decision model based on multi-agent reinforcement learning. Firstly, a bidirectional recurrent neural network (BRNN) is used to achieve communication between UAV individuals, and the multi-UAV cooperative air combat maneuver decision model under the actor-critic architecture is established. Secondly, through combining with target allocation and air combat situation assessment, the tactical goal of the formation is merged with the reinforcement learning goal of every UAV, and a cooperative tactical maneuver policy is generated. The simulation results prove that the multi-UAV cooperative air combat maneuver decision model established in this paper can obtain the cooperative maneuver policy through reinforcement learning, the cooperative maneuver policy can guide UAVs to obtain the overall situational advantage and defeat the opponents under tactical cooperation.

The existing recognition algorithms of space-time block code (STBC) for multi-antenna (MA) orthogonal frequency-division multiplexing (OFDM) systems use feature extraction and hypothesis testing to identify the signal types in a complex communication environment. However, owing to the restrictions on the prior information and channel conditions, these existing algorithms cannot perform well under strong interference and non-cooperative communication conditions. To overcome these defects, this study introduces deep learning into the STBC-OFDM signal recognition field and proposes a recognition method based on the fourth-order lag moment spectrum (FOLMS) and attention-guided multi-scale dilated convolution network (AMDCNet). The fourth-order lag moment vectors of the received signals are calculated, and vectors are stitched to form two-dimensional FOLMS, which is used as the input of the deep learning-based model. Then, the multi-scale dilated convolution is used to extract the details of images at different scales, and a convolutional block attention module (CBAM) is introduced to construct the attention-guided multi-scale dilated convolution module (AMDCM) to make the network be more focused on the target area and obtian the multi-scale guided features. Finally, the concatenate fusion, residual block and fully-connected layers are applied to acquire the STBC-OFDM signal types. Simulation experiments show that the average recognition probability of the proposed method at ?12 dB is higher than 98%. Compared with the existing algorithms, the recognition performance of the proposed method is significantly improved and has good adaptability to environments with strong disturbances. In addition, the proposed deep learning-based model can directly identify the pre-processed FOLMS samples without a priori information on channel and noise, which is more suitable for non-cooperative communication systems than the existing algorithms.

A terahertz (THz) wave transmitted through vegetation experiences both absorption and scattering caused by the air molecules and leaves. This paper presents the scattering attenuation characteristics of vegetation in a THz range. The theoretical path loss model near the vegetation yields the average attenuation of THz waves in a mixed channel composed of air and vegetation leaves. Furthermore, a simplified model of the vegetation structure is obtained for generic vegetation types based on a variety of parameters, such as leaf size, distribution, and moisture content. Finally, based on specific vegetation species and different levels of air humidity, the attenuation characteristics under different conditions are calculated, and the influence of different model parameters on the attenuation characteristics is obtained.

The accuracy of target threat estimation has a great impact on command decision-making. The Bayesian network, as an effective way to deal with the problem of uncertainty, can be used to track the change of the target threat level. Unfortunately, the traditional discrete dynamic Bayesian network (DDBN) has the problems of poor parameter learning and poor reasoning accuracy in a small sample environment with partial prior information missing. Considering the finiteness and discreteness of DDBN parameters, a fuzzy k-nearest neighbor (KNN) algorithm based on correlation of feature quantities (CF-FKNN) is proposed for DDBN parameter learning. Firstly, the correlation between feature quantities is calculated, and then the KNN algorithm with fuzzy weight is introduced to fill the missing data. On this basis, a reasonable DDBN structure is constructed by using expert experience to complete DDBN parameter learning and reasoning. Simulation results show that the CF-FKNN algorithm can accurately fill in the data when the samples are seriously missing, and improve the effect of DDBN parameter learning in the case of serious sample missing. With the proposed method, the final target threat assessment results are reasonable, which meets the needs of engineering applications.

Frequency planning is of great significance which can effectively dispatch the battlefield resources of radio equipment. To enhance the efficiency of scheduling, this paper investigates the frequency planning problem (FPP) and puts forward a multi-objective approach. The proposed multi-objective model considers the coordination constraints of radio equipment alongside diverse resources, defining key points to delineate the cooperative interactions among radio equipment. The model integrates considerations of time, space, and energy, focusing on electromagnetic interference, frequency demand satisfaction and frequency occupancy as its primary optimization objectives. To improve the accuracy of the solution, this study proposes a multi-population multi-objective memetic algorithm (MPMA). This algorithm employs a segment-based coding strategy and a specialized genetic operator to facilitate the integration of global and local search techniques. Additionally, chaos initialization and a multi-population-based scheduling approach are incorporated to enhance global search performance. The experimental results demonstrate the superiority of the proposed model and MPMA in meeting the diverse scheduling needs of radio equipment across various scenarios.

This paper tackles the formation-containment control problem of fixed-wing unmanned aerial vehicle (UAV) swarm with model uncertainties for dynamic target tracking in three-dimensional space in the faulty case of UAVs ’ actuator and sensor. The fixed-wing UAV swarm under consideration is organized as a “multi-leader-multi-follower” structure, in which only several leaders can obtain the dynamic target information while others only receive the neighbors’ information through the communication network. To simultaneously realize the formation, containment, and dynamic target tracking, a two-layer control framework is adopted to decouple the problem into two subproblems: reference trajectory generation and trajectory tracking. In the upper layer, a distributed finite-time estimator (DFTE) is proposed to generate each UAV ’s reference trajectory in accordance with the control objective. Subsequently, a distributed composite robust fault-tolerant trajectory tracking controller is developed in the lower layer, where a novel adaptive extended super-twisting (AESTW) algorithm with a finite-time extended state observer (FTESO) is involved in solving the robust trajectory tracking control problem under model uncertainties, actuator, and sensor faults. The proposed controller simultaneously guarantees rapidness and enhances the system ’s robustness with fewer chattering effects. Finally, corresponding simulations are carried out to demonstrate the effectiveness and competitiveness of the proposed two-layer fault-tolerant cooperative control scheme.

Recognition of pulse repetition interval (PRI) modulation is a fundamental task in the interpretation of radar intentions. However, the existing PRI modulation recognition methods mainly focus on single-label classification of PRI sequences. The prerequisite for the effectiveness of these methods is that the PRI sequences are perfectly divided according to different modulation types before identification, while the actual situation is that radar pulses reach the receiver continuously, and there is no completely reliable method to achieve this division in the case of non-cooperative reception. Based on the above actual needs, this paper implements an algorithm based on the recurrence plot technique and the multi-target detection model, which does not need to divide the PRI sequence in advance. Compared with the sliding window method, it can more effectively realize the recognition of the dynamically varying PRI modulation.

In this paper, we propose an effective full array and sparse array adaptive beamforming scheme that can be applied for multiple desired signals based on the branch-and-bound algorithm. Adaptive beamforming for the multiple desired signals is realized by the improved Capon method. At the same time, the sidelobe constraint is added to reduce the sidelobe level. To reduce the pointing errors of multiple desired signals, the array response phase of the desired signal is firstly optimized by using auxilary variables while keeping the response amplitude unchanged. The whole design is formulated as a convex optimization problem solved by the branch-and-bound algorithm. In addition, the beamformer weight vector is penalized with the modified reweighted ${l_1}$-norm to achieve sparsity. Theoretical analysis and simulation results show that the proposed algorithm has lower sidelobe level, higher SINR, and less pointing error than the state-of-the-art methods in the case of a single expected signal and multiple desired signals.

Taking the real part and the imaginary part of complex sound pressure of the sound field as features, a transfer learning model is constructed. Based on the pre-training of a large amount of underwater acoustic data in the preselected sea area using the convolutional neural network (CNN), the few-shot underwater acoustic data in the test sea area are retrained to study the underwater sound source ranging problem. The S5 voyage data of SWellEX-96 experiment is used to verify the proposed method, realize the range estimation for the shallow source in the experiment, and compare the range estimation performance of the underwater target sound source of four methods: matched field processing (MFP), generalized regression neural network (GRNN), traditional CNN, and transfer learning. Experimental data processing results show that the transfer learning model based on residual CNN can effectively realize range estimation in few-shot scenes, and the estimation performance is remarkably better than that of other methods.

Global Navigation Satellite System (GNSS)-based passive radar (GBPR) has been widely used in remote sensing applications. However, for moving target detection (MTD), the quadratic phase error (QPE) introduced by the non-cooperative target motion is usually difficult to be compensated, as the low power level of the GBPR echo signal renders the estimation of the Doppler rate less effective. Consequently, the moving target in GBPR image is usually defocused, which aggravates the difficulty of target detection even further. In this paper, a spawning particle filter (SPF) is proposed for defocused MTD. Firstly, the measurement model and the likelihood ratio function (LRF) of the defocused point-like target image are deduced. Then, a spawning particle set is generated for subsequent target detection, with reference to traditional particles in particle filter (PF) as their parent. After that, based on the PF estimator, the SPF algorithm and its sequential Monte Carlo (SMC) implementation are proposed with a novel amplitude estimation method to decrease the target state dimension. Finally, the effectiveness of the proposed SPF is demonstrated by numerical simulations and preliminary experimental results, showing that the target range and Doppler can be estimated accurately.

Considering the problem that the scattering echo images of airborne Doppler weather radar are often reduced by ground clutters, the accuracy and confidence of meteorology target detection are reduced. In this paper, a deep convolutional neural network (DCNN) is proposed for meteorology target detection and ground clutter suppression with a large collection of airborne weather radar images as network input. For each weather radar image, the corresponding digital elevation model (DEM) image is extracted on basis of the radar antenna scanning parameters and plane position, and is further fed to the network as a supplement for ground clutter suppression. The features of actual meteorology targets are learned in each bottleneck module of the proposed network and convolved into deeper iterations in the forward propagation process. Then the network parameters are updated by the back propagation iteration of the training error. Experimental results on the real measured images show that our proposed DCNN outperforms the counterparts in terms of six evaluation factors. Meanwhile, the network outputs are in good agreement with the expected meteorology detection results (labels). It is demonstrated that the proposed network would have a promising meteorology observation application with minimal effort on network variables or parameter changes.

In this paper, we first propose a memristive chaotic system and implement it by circuit simulation. The chaotic dynamics and various attractors are analysed by using phase portrait, bifurcation diagram, and Lyapunov exponents. In particular, the system has robust chaos in a wide parameter range and the initial value space, which is favourable to the security communication application. Consequently, we further explore its application in image encryption and present a new scheme. Before image processing, the external key is protected by the Grain-128a algorithm and the initial values of the memristive system are updated with the plain image. We not only perform random pixel extraction and masking with the chaotic cipher, but also use them as control parameters for Brownian motion to obtain the permutation matrix. In addition, multiplication on the finite field GF(2⁸) is added to further enhance the cryptography. Finally, the simulation results verify that the proposed image encryption scheme has better performance and higher security, which can effectively resist various attacks.

This paper presents an approach for mitigating the cross-eye jamming using a dual-polarization array. By transmitting a sum beam and a difference beam in two orthogonal polarimetric channels, a synthesized transmitted beam with spatially varying polarization is produced, such that the polarization of the transmitted radar wave varies in azimuth or elevation. Thus, the phases of the signals received on the two antennas of a cross-eye jammer become unequal, and an additional phase difference is introduced to disrupt the 180° phase shifting in the retrodirective loop of the jammer. By means of beam scanning in a small angular range, the optimal beam steering configuration can be found to maximize the phase error for the mitigation of cross-eye jamming. As a result, the jamming performance of the cross-eye jammer degrades largely. Theoretical analysis and simulation results indicate that the proposed method is valid and feasible.

To improve the ability of detecting underwater targets under strong wideband interference environment, an efficient method of line spectrum extraction is proposed, which fully utilizes the feature of the target spectrum that the high intense and stable line spectrum is superimposed on the wide continuous spectrum. This method modifies the traditional beam forming algorithm by calculating and fusing the beam forming results at multi-frequency band and multi-azimuth interval, showing an excellent way to extract the line spectrum when the interference and the target are not in the same azimuth interval simultaneously. Statistical efficiency of the estimated azimuth variance and corresponding power of the line spectrum band depends on the line spectra ratio (LSR) of the line spectrum. The change laws of the output signal to noise ratio (SNR) with the LSR, the input SNR, the integration time and the filtering bandwidth of different algorithms bring the selection principle of the critical LSR. As the basis, the detection gain of wideband energy integration and the narrowband line spectrum algorithm are theoretically analyzed. The simulation detection gain demonstrates a good match with the theoretical model. The application conditions of all methods are verified by the receiver operating characteristic (ROC) curve and experimental data from Qiandao Lake. In fact, combining the two methods for target detection reduces the missed detection rate. The proposed post-processing method in 2-dimension with the Kalman filter in the time dimension and the background equalization algorithm in the azimuth dimension makes use of the strong correlation between adjacent frames, could further remove background fluctuation and improve the display effect.

Developing intelligent unmanned swarm systems (IUSSs) is a highly intricate process. Although current simulators and toolchains have made a notable contribution to the development of algorithms for IUSSs, they tend to concentrate on isolated technical elements and are deficient in addressing the full spectrum of critical technologies and development needs in a systematic and integrative manner. Furthermore, the current suite of tools has not adequately addressed the challenge of bridging the gap between simulation and real-world deployment of algorithms. Therefore, a comprehensive solution must be developed that encompasses the entire IUSS development lifecycle. In this study, we present the RflySim ToolChain, which has been developed with the specific aim of facilitating the rapid development and validation of IUSSs. The RflySim ToolChain employs a model-based design (MBD) approach, integrating a modeling and simulation module, a lower reliable control module, and an upper swarm decision-making module. This comprehensive integration encompasses the entire process, from modeling and simulation to testing and deployment, thereby enabling users to rapidly construct and validate IUSSs. The principal advantages of the RflySim ToolChain are as follows: it provides a comprehensive solution that meets the full-stack development needs of IUSSs; the highly modular architecture and comprehensive software development kit (SDK) facilitate the automation of the entire IUSS development process. Furthermore, the high-fidelity model design and reliable architecture solution ensure a seamless transition from simulation to real-world deployment, which is known as the simulation to reality (Sim2Real) process. This paper presents a series of case studies that illustrate the effectiveness of the RflySim ToolChain in supporting the research and application of IUSSs.

This work explores an alternative 3D geometry measurement method for non-cooperative spacecraft guiding navigation and proximity operations. From one snapshot of an unfocused light-field camera, the 3D point cloud of a non-cooperative spacecraft can be calculated from sub-aperture images with the epipolar plane image (EPI) based light-field rendering algorithm. A Chang’e?3 model (7.2 cm×5.6 cm×7.0 cm) is tested to validate the proposed technique. Three measurement distances (1.0 m, 1.2 m, 1.5 m) are considered to simulate different approaching stages. Measuring errors are quantified by comparing the light-field camera data with a high precision commercial laser scanner. The mean error distance for the three cases are 0.837 mm, 0.743 mm, and 0.973 mm respectively, indicating that the method can well reconstruct 3D geometry of a non-coope-rative spacecraft with a densely distributed 3D point cloud and is thus promising in space-related missions.

Cloud manufacturing is a specific implementation form of the "Internet + manufacturing" strategy. Why and how to develop cloud manufacturing platform (CMP), however, remains the key concern of both platform operators and users. A microscopic model is proposed to investigate advantages and diffusion forces of CMP through exploration of its diffusion process and mechanism. Specifically, a three-stage basic evolution process of CMP is innovatively proposed. Then, based on this basic process, a more complex CMP evolution model has been established in virtue of complex network theory, with five diffusion forces identified. Thereafter, simulations on CMP diffusion have been conducted. The results indicate that, CMP possesses better resource utilization, user satisfaction, and enterprise utility. Results of simulation on impacts of different diffusion forces show that both the time required for CMP to reach an equilibrium state and the final network size are affected simultaneously by the five diffusion forces. All these analyses indicate that CMP could create an open online cooperation environment and turns out to be an effective implementation of the "Internet + manufacturing" strategy.

Neuromorphic computing simulates the operation of biological brain function for information processing and can potentially solve the bottleneck of the Von Neumann architecture. Inspired by the real characteristics of physical memristive devices, we propose a threshold-type nonlinear voltage-controlled memristor mathematical model which is used to design a novel memristor-based crossbar array. The presented crossbar array can simulate the synaptic weight in real number field rather than only positive number field. Theoretical analysis and simulation results of a 2×2 image inversion operation validate the feasibility of the proposed crossbar array and the necessary training and inference functions. Finally, the presented crossbar array is used to construct the neural network and then applied in the handwritten digit recognition. The Mixed National Institute of Standards and Technology (MNIST) database is adopted to train this neural network and it achieves a satisfactory accuracy.

Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recognition. To solve this problem, an optimized cooperative semi-supervised learning radar emitter recognition method based on a small amount of labeled data is developed. First, a small amount of labeled data are randomly sampled by using the bootstrap method, loss functions for three common deep learning networks are improved, the uniform distribution and cross-entropy function are combined to reduce the overconfidence of softmax classification. Subsequently, the dataset obtained after sampling is adopted to train three improved networks so as to build the initial model. In addition, the unlabeled data are preliminarily screened through dynamic time warping (DTW) and then input into the initial model trained previously for judgment. If the judgment results of two or more networks are consistent, the unlabeled data are labeled and put into the labeled data set. Lastly, the three network models are input into the labeled dataset for training, and the final model is built. As revealed by the simulation results, the semi-supervised learning method adopted in this paper is capable of exploiting a small amount of labeled data and basically achieving the accuracy of labeled data recognition.

A compensation implementation scheme of the advanced targeting process based on the fine tracking system is proposed in this paper. Based on the working process of the quantum positioning system (QPS) and its acquisition, tracking and pointing (ATP) system, the advanced targeting subsystem of the ATP system is designed. Based on six orbital parameters of the quantum satellite Mozi, the advanced targeting azimuth angle and pitch angle are transformed into the dynamic tracking center of the fine tracking system in the ATP system. The deviation of the advanced targeting process is analyzed. In the Simulink, the simulation experiment of the ATP system considering the deviation compensation of the advanced targeting is carried out, and the results are analyzed.

To solve the problem of providing the best initial situation for terminal guidance when multiple missiles intercept multiple targets, a group cooperative midcourse guidance law (GCMGL) considering time-to-go is proposed. Firstly, a three-dimensional (3D) guidance model is established and a cooperative trajectory shaping guidance law is given. Secondly, for estimating the unknown target maneuvering acceleration, an adaptive disturbance observer (ADO) is designed, combining finite-time theory with a radial basis function (RBF) neural network, and the convergence of the estimation error is proven using Lyapunov stability theory. Then, to ensure time-to-go cooperation among missiles within the same group and across different groups, the group consensus protocols of virtual collision point mean and the inter-group cooperative consensus protocol are designed respectively. Based on the group consensus protocols, the virtual collision point cooperative guidance law is given, and the finite-time convergence is proved by Lyapunov stability theory. Simultaneously, combined with trajectory shaping guidance law, virtual collision point cooperative guidance law and the inter-group cooperative consensus protocol, the design of GCMGL considering time-to-go is given. Finally, numerical simulation results show the effectiveness and the superiority of the proposed GCMGL.

Rich semantic information in natural language increases team efficiency in human collaboration, reduces dependence on high precision data information, and improves adaptability to dynamic environment. We propose a semantic centered cloud control framework for cooperative multi-unmanned ground vehicle (UGV) system. Firstly, semantic modeling of task and environment is implemented by ontology to build a unified conceptual architecture, and secondly, a scene semantic information extraction method combining deep learning and semantic web rule language (SWRL) rules is used to realize the scene understanding and task-level cloud task cooperation. Finally, simulation results show that the framework is a feasible way to enable autonomous unmanned systems to conduct cooperative tasks.

Some attributes are uncertain for evaluation work because of incomplete or limited information and knowledge. It leads to uncertainty in evaluation results. To that end, an evaluation method, uncertainty entropy-based exploratory evaluation (UEEE), is proposed to guide the evaluation activities, which can iteratively and gradually reduce uncertainty in evaluation results. Uncertainty entropy (UE) is proposed to measure the extent of uncertainty. First, the belief degree distributions are assumed to characterize the uncertainty in attributes. Then the belief degree distribution of the evaluation result can be calculated by using uncertainty theory. The obtained result is then checked based on UE to see if it could meet the requirements of decision-making. If its uncertainty level is high, more information needs to be introduced to reduce uncertainty. An algorithm based on the UE is proposed to find which attribute can mostly affect the uncertainty in results. Thus, efforts can be invested in key attribute(s), and the evaluation results can be updated accordingly. This update should be repeated until the evaluation result meets the requirements. Finally, as a case study, the effectiveness of ballistic missiles with uncertain attributes is evaluated by UEEE. The evaluation results show that the target is believed to be destroyed.

The conventional two dimensional (2D) inverse synthetic aperture radar (ISAR) imaging fails to provide the targets’ three dimensional (3D) information. In this paper, a 3D ISAR imaging method for the space target is proposed based on mutli-orbit observation data and an improved orthogonal matching pursuit (OMP) algorithm. Firstly, the 3D scattered field data is converted into a set of 2D matrix by stacking slices of the 3D data along the elevation direction dimension. Then, an improved OMP algorithm is applied to recover the space target’s amplitude information via the 2D matrix data. Finally, scattering centers can be reconstructed with specific three dimensional locations. Numerical simulations are provided to demonstrate the effectiveness and superiority of the proposed 3D imaging method.

Small video satellites have unique advantages of short development cycle, agile attitude maneuver, real-time video imaging. They have broad application prospects in space debris, faulty spacecraft, and other space target detection and tracking. However, when a space target first enters the camera’s visual field, it has a relatively large angular velocity relative to the satellite, which makes it easy to deviate from the visual field and cause off-target problems. This paper proposes a novel visual tracking control method based on potential function preventing missed targets in space. Firstly, a circular area in the image plane is designed as a mandatory restricted projection area of the target and a visual tracking controller based on image error. Then, a potential function is designed to ensure continuous and stable tracking of the target after entering the visual field. Finally, the stability of the control is proved using Barbarat’s lemma. By setting the same conditions and comparing with the simulation results of the proportion-derivative (PD) control method, the results show that when there is a large relative attitude motion angular velocity between the target and the satellite, the tracking method based on potential function can ensure that the target does not deviate from the field-of-view during the tracking control process, and the projection of target is controlled to the desired position. The proposed control method is effective in eliminating tracking error and preventing off-target simultaneously.

This paper presents a path planning approach for rotary unmanned aerial vehicles (R-UAVs) in a known static rough terrain environment. This approach aims to find collision-free and feasible paths with minimum altitude, length and angle variable rate. First, a three-dimensional (3D) modeling method is proposed to reduce the computation burden of the dynamic models of R-UAVs. Considering the length, height and tuning angle of a path, the path planning of R-UAVs is described as a tri-objective optimization problem. Then, an improved multi-objective particle swarm optimization algorithm is developed. To render the algorithm more effective in dealing with this problem, a vibration function is introduced into the collided solutions to improve the algorithm efficiency. Meanwhile, the selection of the global best position is taken into account by the reference point method. Finally, the experimental environment is built with the help of the Google map and the 3D terrain generator World Machine. Experimental results under two different rough terrains from Guilin and Lanzhou of China demonstrate the capabilities of the proposed algorithm in finding Pareto optimal paths.

In the field of calculating the attack area of air-to-air missiles in modern air combat scenarios, the limitations of existing research, including real-time calculation, accuracy efficiency trade-off, and the absence of the three-dimensional attack area model, restrict their practical applications. To address these issues, an improved backtracking algorithm is proposed to improve calculation efficiency. A significant reduction in solution time and maintenance of accuracy in the three-dimensional attack area are achieved by using the proposed algorithm. Furthermore, the age-layered population structure genetic programming (ALPS-GP ) algorithm is introduced to determine an analytical polynomial model of the three-dimensional attack area, considering real-time requirements. The accuracy of the polynomial model is enhanced through the coefficient correction using an improved gradient descent algorithm. The study reveals a remarkable combination of high accuracy and efficient real-time computation, with a mean error of 91.89 m using the analytical polynomial model of the three-dimensional attack area solved in just 10^?4 s, thus meeting the requirements of real-time combat scenarios.

Synthetic aperture radar (SAR) is able to detect surface changes in urban areas with a short revisit time, showing its capability in disaster assessment and urbanization monitoring. Most presented change detection methods are conducted using couples of SAR amplitude images. However, a prior date of surface change is required to select a feasible image pair. We propose an automatic spatio-temporal change detection method by identifying the temporary coherent scatterers. Based on amplitude time series, ${\chi ^2} $ -test and iterative single pixel change detection are proposed to identify all step-times: the moments of the surface change. Then the parameters, e.g., deformation velocity and relative height, are estimated and corresponding coherent periods are identified by using interferometric phase time series. With identified temporary coherent scatterers, different types of temporal surface changes can be classified using the location of the coherent periods and spatial significant changes are identified combining point density and F values. The main advantage of our method is automatically detecting spatio-temporal surface changes without prior information. Experimental results by the proposed method show that both appearing and disappearing buildings with their step-times are successfully identified and results by ascending and descending SAR images show a good agreement.

In the complex countermeasure environment, the pulse description words (PDWs) of the same type of multi-function radar emitters are similar in multiple dimensions. Therefore, it is difficult for conventional methods to deinterleave such emitters. In order to solve this problem, a pulse deinterleaving method based on implicit features is proposed in this paper. The proposed method introduces long short-term memory (LSTM) neural networks and statistical analysis to mine new features from similar PDW features, that is, the variation law (implicit features) of pulse sequences of different radiation sources over time. The multi-function radar emitter is deinterleaved based on the pulse sequence variation law. Statistical results show that the proposed method not only achieves satisfactory performance, but also has good robustness.

This paper deals with subspace detection for range-spread target in non-homogeneous clutter with unknown covariance matrix where structured interference is presented in the received data. Through exploiting the persymmetry of the clutter covariance matrix, we propose two adaptive target detectors, which are referred to as persymmetric subspace Rao to suppress interference and persymmetric subspace Wald to suppress interference (“PS-Rao-I” and “PS-Wald-I”), respectively. The persymmetry-based design brings in the advantage of easy implementation for small training sample support. The signal flow analysis of the two detectors shows that the PS-Rao-I rejects interference and integrates signals successively through separated matrix projection, while the PS-Wald-I jointly achieves interference elimination and signal combination via oblique projection. In addition, both detectors are shown to be constant false alarm rate detectors, significantly improving the detection performance with other competing detectors under the condition of limited training.

Aiming at the terminal defense problem of aircraft, this paper proposes a method to simultaneously achieve terminal defense and seize the dominant position. The method employs a λ-return based reinforcement learning algorithm, which can be applied to the flight assistance decision-making system to improve the pilot’s survivability. First, we model the environment to simulate the interaction between air-to-air missiles and aircraft. Subsequently, we propose a λ-return based approach to improve the deep Q learning network (DQN), deep advantageous actor criticism (A2C), and proximity policy optimization (PPO) algorithms used to train manoeuvre strategies. The method employs an action space containing nine manoeuvres and defines the off-target distance at the end of the scene as a sparse reward for algorithm training. Simulation results show that the convergence speed of the three improved algorithms is significantly improved when using the λ-return method. Moreover, the effect of the fetch value on the convergence speed is verified by ablation experiments. In order to solve the illegal behavior problem in the training process, we also design a backtracking-based illegal behavior masking mechanism, which improves the data generation efficiency of the environment model and promotes effective algorithm training.