The deep deterministic policy gradient (DDPG) algorithm is an off-policy method that combines two mainstream reinforcement learning methods based on value iteration and policy iteration. Using the DDPG algorithm, agents can explore and summarize the environment to achieve autonomous decisions in the continuous state space and action space. In this paper, a cooperative defense with DDPG via swarms of unmanned aerial vehicle (UAV) is developed and validated, which has shown promising practical value in the effect of defending. We solve the sparse rewards problem of reinforcement learning pair in a long-term task by building the reward function of UAV swarms and optimizing the learning process of artificial neural network based on the DDPG algorithm to reduce the vibration in the learning process. The experimental results show that the DDPG algorithm can guide the UAVs swarm to perform the defense task efficiently, meeting the requirements of a UAV swarm for non-centralization, autonomy, and promoting the intelligent development of UAVs swarm as well as the decision-making process.

The dynamic weapon target assignment (DWTA) problem is of great significance in modern air combat. However, DWTA is a highly complex constrained multi-objective combinatorial optimization problem. An improved elitist non-dominated sorting genetic algorithm-II (NSGA-II) called the non-dominated shuffled frog leaping algorithm (NSFLA) is proposed to maximize damage to enemy targets and minimize the self-threat in air combat constraints. In NSFLA, the shuffled frog leaping algorithm (SFLA) is introduced to NSGA-II to replace the inside evolutionary scheme of the genetic algorithm (GA), displaying low optimization speed and heterogeneous space search defects. Two improvements have also been raised to promote the internal optimization performance of SFLA. Firstly, the local evolution scheme, a novel crossover mechanism, ensures that each individual participates in updating instead of only the worst ones, which can expand the diversity of the population. Secondly, a discrete adaptive mutation algorithm based on the function change rate is applied to balance the global and local search. Finally, the scheme is verified in various air combat scenarios. The results show that the proposed NSFLA has apparent advantages in solution quality and efficiency, especially in many aircraft and the dynamic air combat environment.

Deep neural networks (DNNs) have achieved great success in many data processing applications. However, high computational complexity and storage cost make deep learning difficult to be used on resource-constrained devices, and it is not environmental-friendly with much power cost. In this paper, we focus on low-rank optimization for efficient deep learning techniques. In the space domain, DNNs are compressed by low rank approximation of the network parameters, which directly reduces the storage requirement with a smaller number of network parameters. In the time domain, the network parameters can be trained in a few subspaces, which enables efficient training for fast convergence. The model compression in the spatial domain is summarized into three categories as pre-train, pre-set, and compression-aware methods, respectively. With a series of integrable techniques discussed, such as sparse pruning, quantization, and entropy coding, we can ensemble them in an integration framework with lower computational complexity and storage. In addition to summary of recent technical advances, we have two findings for motivating future works. One is that the effective rank, derived from the Shannon entropy of the normalized singular values, outperforms other conventional sparse measures such as the $ \ell_1 $ norm for network compression. The other is a spatial and temporal balance for tensorized neural networks. For accelerating the training of tensorized neural networks, it is crucial to leverage redundancy for both model compression and subspace training.

In the process of performing a task, autonomous unmanned systems face the problem of scene changing, which requires the ability of real-time decision-making under dynamically changing scenes. Therefore, taking the unmanned system coordinative region control operation as an example, this paper combines knowledge representation with probabilistic decision-making and proposes a role-based Bayesian decision model for autonomous unmanned systems that integrates scene cognition and individual preferences. Firstly, according to utility value decision theory, the role-based utility value decision model is proposed to realize task coordination according to the preference of the role that individual is assigned. Then, multi-entity Bayesian network is introduced for situation assessment, by which scenes and their uncertainty related to the operation are semantically described, so that the unmanned systems can conduct situation awareness in a set of scenes with uncertainty. Finally, the effectiveness of the proposed method is verified in a virtual task scenario. This research has important reference value for realizing scene cognition, improving cooperative decision-making ability under dynamic scenes, and achieving swarm level autonomy of unmanned systems.

To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle (UAV) real-time path planning problem, a real-time UAV path planning algorithm based on long short-term memory (RPP-LSTM) network is proposed, which combines the memory characteristics of recurrent neural network (RNN) and the deep reinforcement learning algorithm. LSTM networks are used in this algorithm as Q-value networks for the deep Q network (DQN) algorithm, which makes the decision of the Q-value network has some memory. Thanks to LSTM network, the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment. Besides, the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning, so that the UAV can more reasonably perform path planning. Simulation verification shows that compared with the traditional feed-forward neural network (FNN) based UAV autonomous path planning algorithm, the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.

Effective bearing fault diagnosis is vital for the safe and reliable operation of rotating machinery. In practical applications, bearings often work at various rotational speeds as well as load conditions. Yet, the bearing fault diagnosis under multiple conditions is a new subject, which needs to be further explored. Therefore, a multi-scale deep belief network (DBN) method integrated with attention mechanism is proposed for the purpose of extracting the multi-scale core features from vibration signals, containing four primary steps: preprocessing of multi-scale data, feature extraction, feature fusion, and fault classification. The key novelties include multi-scale feature extraction using multi-scale DBN algorithm, and feature fusion using attention mechanism. The benchmark dataset from University of Ottawa is applied to validate the effectiveness as well as advantages of this method. Furthermore, the aforementioned method is compared with four classical fault diagnosis methods reported in the literature, and the comparison results show that our proposed method has higher diagnostic accuracy and better robustness.

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.

The angular resolution of radar is of crucial significance to its tracking performance. In this paper, a super-resolution parameter estimation algorithm based on wide-narrowband joint processing is proposed to improve the angular resolution of wideband monopulse radar. The range cells containing resolvable scattering points are detected in the wideband mode, and these range cells are adopted to estimate part of the target parameters by algorithms of low computational requirement. Then, the likelihood function of the echo is constructed in the narrow-band mode to estimate the rest of the parameters, and the parameters estimated in the wideband mode are employed to reduce computation and enhance estimation accuracy. Simulation results demonstrate that the proposed algorithm has higher estimation accuracy and lower computational complexity than the current algorithm and can avoid the risk of model mismatch.

The dynamic wireless communication network is a complex network that needs to consider various influence factors including communication devices, radio propagation, network topology, and dynamic behaviors. Existing works focus on suggesting simplified reliability analysis methods for these dynamic networks. As one of the most popular modeling methodologies, the dynamic Bayesian network (DBN) is proposed. However, it is insufficient for the wireless communication network which contains temporal and non-temporal events. To this end, we present a modeling methodology for a generalized continuous time Bayesian network (CTBN) with a 2-state conditional probability table (CPT). Moreover, a comprehensive reliability analysis method for communication devices and radio propagation is suggested. The proposed methodology is verified by a reliability analysis of a real wireless communication network.

In this paper, a flexible modular “Tetris” microsatellite platform is studied to implement the rapid integration and assembly of microsatellites. The proposed microsatellite platform is fulfilled based on a sandwich assembly mode which consists of the isomorphic module structure and the standard mechanical-electric-data-thermal interfaces. The advantages of the sandwich assembly mode include flexible reconfiguration and efficient assembly. The prototype of the sandwich assembly mode is built for verifying the performance and the feasibility of the proposed mechanical-electric-data-thermal interfaces. Finally, an assembly case is accomplished to demonstrate the validity and advantages of the proposed “Tetris” microsatellite platform.

Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit (SA-GRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform (FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced features. Subsequently, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.

To ensure safe flight of multiple fixed-wing unmanned aerial vehicles (UAVs) formation, considering trajectory planning and formation control together, a leader trajectory planning method based on the sparse A* algorithm is introduced. Firstly, a formation controller based on prescribed performance theory is designed to control the transient and steady formation configuration, as well as the formation forming time, which not only can form the designated formation configuration but also can guarantee collision avoidance and terrain avoidance theoretically. Next, considering the constraints caused by formation controller on trajectory planning such as the safe distance, turn angle and step length, as well as the constraint of formation shape, a leader trajectory planning method based on sparse A* algorithm is proposed. Simulation results show that the UAV formation can arrive at the destination safely with a short trajectory no matter keeping the formation or encountering formation transformation.

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.

Space emergency launching is to send a satellite into space by using a rapid responsive solid rocket in the bounded time to implement the emergency Earth observation mission. The key and difficult points mainly include the business process construction of launching mission planning, validation of the effectiveness of the launching scheme, etc. This paper proposes the agile space emergency launching mission planning simulation and verification method, which systematically constructs the overall technical framework of space emergency launching mission planning with multi-field area, multi-platform and multi-task parallel under the constraint of resource scheduling for the first time. It supports flexible reconstruction of mission planning processes such as launching target planning, trajectory planning, path planning, action planning and launching time analysis, and can realize on-demand assembly of operation links under different mission scenarios and different plan conditions, so as to quickly modify and generate launching schemes. It supports the fast solution of rocket trajectory data and the accurate analysis of multi-point salvo time window recheck and can realize the fast conflict resolution of launching missions in the dimensions of launching position and launching window sequence. It supports lightweight scenario design, modular flexible simulation, based on launching style, launching platform, launching rules, etc., can realize the independent mapping of mission planning results to two-dimensional and three-dimensional visual simulation models, so as to achieve a smooth connection between mission planning and simulation.

In order to solve the problem that the performance of traditional localization methods for mixed near-field sources (NFSs) and far-field sources (FFSs) degrades under impulsive noise, a robust and novel localization method is proposed. After eliminating the impacts of impulsive noise by the weighted outlier filter, the direction of arrivals (DOAs) of FFSs can be estimated by multiple signal classification (MUSIC) spectral peaks search. Based on the DOAs information of FFSs, the separation of mixed sources can be performed. Finally, the estimation of localizing parameters of NFSs can avoid two-dimension spectral peaks search by decomposing steering vectors. The Cramer-Rao bounds (CRB) for the unbiased estimations of DOA and range under impulsive noise have been drawn. Simulation experiments verify that the proposed method has advantages in probability of successful estimation (PSE) and root mean square error (RMSE) compared with existing localization methods. It can be concluded that the proposed method is effective and reliable in the environment with low generalized signal to noise ratio (GSNR), few snapshots, and strong impulse.

The unmanned combat aerial vehicle (UCAV) is a research hot issue in the world, and the situation assessment is an important part of it. To overcome shortcomings of the existing situation assessment methods, such as low accuracy and strong dependence on prior knowledge, a data-driven situation assessment method is proposed. The clustering and classification are combined, the former is used to mine situational knowledge, and the latter is used to realize rapid assessment. Angle evaluation factor and distance evaluation factor are proposed to transform multi-dimensional air combat information into two-dimensional features. A convolution success-history based adaptive differential evolution with linear population size reduction-means (C-LSHADE-Means) algorithm is proposed. The convolutional pooling layer is used to compress the size of data and preserve the distribution characteristics. The LSHADE algorithm is used to initialize the center of the mean clustering, which overcomes the defect of initialization sensitivity. Comparing experiment with the seven clustering algorithms is done on the UCI data set, through four clustering indexes, and it proves that the method proposed in this paper has better clustering performance. A situation assessment model based on stacked autoencoder and learning vector quantization (SAE-LVQ) network is constructed, and it uses SAE to reconstruct air combat data features, and uses the self-competition layer of the LVQ to achieve efficient classification. Compared with the five kinds of assessments models, the SAE-LVQ model has the highest accuracy. Finally, three kinds of confrontation processes from air combat maneuvering instrumentation (ACMI) are selected, and the model in this paper is used for situation assessment. The assessment results are in line with the actual situation.

Strategic management of equipment system development must attach importance to effective strategic risk management. Aiming at the identification of strategic risk of equipment system development, firstly, the source of strategic risk of equipment system development is analyzed and classified. Based on this, a causal loop diagram of strategic risk of equipment system development based on system dynamics is established. The system dynamics analysis software Vensim PLE is used to carry out the risk influencing factors analysis, risk consequences analysis, risk feedback loop identification and corresponding pre-control measures, and achieves a good risk identification effect.

Aiming at evaluating and predicting rapidly and accurately a high sensitivity receiver’s adaptability in complex electromagnetic environments, a novel testing and prediction method based on dual-channel multi-frequency is proposed to improve the traditional two-tone test. Firstly, two signal generators are used to generate signals at the radio frequency (RF) by frequency scanning, and then a rapid measurement at the intermediate frequency (IF) output port is carried out to obtain a huge amount of sample data for the subsequent analysis. Secondly, the IF output response data are modeled and analyzed to construct the linear and nonlinear response constraint equations in the frequency domain and prediction models in the power domain, which provide the theoretical criteria for interpreting and predicting electromagnetic susceptibility (EMS) of the receiver. An experiment performed on a radar receiver confirms the reliability of the method proposed in this paper. It shows that the interference of each harmonic frequency and each order to the receiver can be identified and predicted with the sensitivity model. Based on this, fast and comprehensive evaluation and prediction of the receiver’s EMS in complex environment can be efficiently realized.

To solve the path following control problem for unmanned surface vehicles (USVs), a control method based on deep reinforcement learning (DRL) with long short-term memory (LSTM) networks is proposed. A distributed proximal policy optimization (DPPO) algorithm, which is a modified actor-critic-based type of reinforcement learning algorithm, is adapted to improve the controller performance in repeated trials. The LSTM network structure is introduced to solve the strong temporal correlation USV control problem. In addition, a specially designed path dataset, including straight and curved paths, is established to simulate various sailing scenarios so that the reinforcement learning controller can obtain as much handling experience as possible. Extensive numerical simulation results demonstrate that the proposed method has better control performance under missions involving complex maneuvers than trained with limited scenarios and can potentially be applied in practice.

For the underwater long baseline (LBL) positioning systems, the traditional distance intersection algorithm simplifies the sound speed to a constant, and calculates the underwater target position parameters with a nonlinear iteration. However, due to the complex underwater environment, the sound speed changes with time and space, and then the acoustic propagation path is actually a curve, which inevitably causes some errors to the traditional distance intersection positioning algorithm. To reduce the position error caused by the uncertain underwater sound speed, a new time of arrival (TOA) intersection underwater positioning algorithm of LBL system is proposed. Firstly, combined with the vertical layered model of the underwater sound speed, an implicit positioning model of TOA intersection is constructed through the constant gradient acoustic ray tracing. And then an optimization function based on the overall TOA residual square sum is advanced to solve the position parameters for the underwater target. Moreover, the particle swarm optimization (PSO) algorithm is replaced with the traditional nonlinear least square method to optimize the implicit positioning model of TOA intersection. Compared with the traditional distance intersection positioning model, the TOA intersection positioning model is more suitable for the engineering practice and the optimization algorithm is more effective. Simulation results show that the proposed methods in this paper can effectively improve the positioning accuracy for the underwater target.

This paper presents an operational framework of unstructured decision-making approach involving quality function deployment (QFD) in an uncertain linguistic context. Firstly, QFD is extended to the multi-enterprise paradigm in a real-world manufacturing environment. Secondly, hesitant fuzzy linguistic term sets (HFLTSs), which facilitate the management and handling of information equivocality, are designed to construct a house of quality (HoQ) in the product planning process. The technique of computing with words is applied to bridge the gap between mechanisms of the human brain and machine processes with fuzzy linguistic term sets. Thirdly, a multi-enterprise QFD pattern is formulated as an unstructured decision-making problem for alternative infrastructure project selection in a manufacturing organization. The inter-relationships of cooperative partners are directly matched with a back propagation neural network (BPNN) to construct the multi-enterprise manufacturing network. The resilience of the manufacturing organization is considered by formulating an outranking method on the basis of HFLTSs to decide on infrastructure project alternatives. Finally, a real-world example, namely, the prototype manufacturing of an automatic transmission for a vehicle, is provided to illustrate the effectiveness of the proposed decision-making approach.

In this paper, we study scene image recognition with knowledge transfer for drone navigation. We divide navigation scenes into three macro-classes, namely outdoor special scenes (OSSs), the space from indoors to outdoors or from outdoors to indoors transitional scenes (TSs), and others. However, there are difficulties in how to recognize the TSs, to this end, we employ deep convolutional neural network (CNN) based on knowledge transfer, techniques for image augmentation, and fine tuning to solve the issue. Moreover, there is still a novelty detection problem in the classifier, and we use global navigation satellite systems (GNSS) to solve it in the prediction stage. Experiment results show our method, with a pre-trained model and fine tuning, can achieve 91.3196% top-1 accuracy on Scenes21 dataset, paving the way for drones to learn to understand the scenes around them autonomously.

With the extensive application of large-scale array antennas, the increasing number of array elements leads to the increasing dimension of received signals, making it difficult to meet the real-time requirement of direction of arrival (DOA) estimation due to the computational complexity of algorithms. Traditional subspace algorithms require estimation of the covariance matrix, which has high computational complexity and is prone to producing spurious peaks. In order to reduce the computational complexity of DOA estimation algorithms and improve their estimation accuracy under large array elements, this paper proposes a DOA estimation method based on Krylov subspace and weighted $ {l}_{1} $-norm. The method uses the multistage Wiener filter (MSWF) iteration to solve the basis of the Krylov subspace as an estimate of the signal subspace, further uses the measurement matrix to reduce the dimensionality of the signal subspace observation, constructs a weighted matrix, and combines the sparse reconstruction to establish a convex optimization function based on the residual sum of squares and weighted $ {l}_{1} $-norm to solve the target DOA. Simulation results show that the proposed method has high resolution under large array conditions, effectively suppresses spurious peaks, reduces computational complexity, and has good robustness for low signal to noise ratio (SNR) environment.

Satellites with altitudes below 400 km are called super low altitude satellites (SLAS), often used to achieve responsive imaging tasks. Therefore, it is important for the manipulation of its ground track. Aiming at the problem of ground track manipulation of SLAS, a control method based on tangential impulse thrust is proposed. First, the equation of the longitude difference between SLAS and the target point on the target latitude is derived based on Gauss’s variational equations. On this basis, the influence of the tangential impulse thrust on the ground track’s longitude is derived. Finally, the method for ground track manipulation of SLAS under the tangential impulse thrust is proposed. The simulation results verify the effectiveness of the method, after manipulation, the satellite can visit the target point and revisit it for multiple days.

The key advantage of unmanned swarm operation is its autonomous cooperation. How to improve the proportion of cooperators is one of the key issues of autonomous collaboration in unmanned swarm operations. This work proposes a strategy dominance mechanism of autonomous collaboration in unmanned swarm within the framework of public goods game. It starts with the requirement analysis of autonomous collaboration in unmanned swarm; and an aspiration-driven multiplayer evolutionary game model is established based on the requirement. Then the average abundance function and strategy dominance condition of the model are constructed by theoretical derivation. Furthermore, the evolutionary mechanism of parameter adjustment in swarm cooperation is revealed via simulation, and the influences of the multiplication factor $ r $ , aspiration level $ \alpha $ , threshold $ m $ and other parameters on the strategy dominance conditions were simulated for both linear and threshold public goods games (PGGs) to determine the strategy dominance characteristics; Finally, deliberate proposals are suggested to provide a meaningful exploration in the actual control of unmanned swarm cooperation.

The warhead of a ballistic missile may precess due to lateral moments during release. The resulting micro-Doppler effect is determined by parameters such as the target’s motion state and size. A three-dimensional reconstruction method for the precession warhead via the micro-Doppler analysis and inverse Radon transform (IRT) is proposed in this paper. The precession parameters are extracted by the micro-Doppler analysis from three radars, and the IRT is used to estimate the size of targe. The scatterers of the target can be reconstructed based on the above parameters. Simulation experimental results illustrate the effectiveness of the proposed method in this paper.

This paper considers the non-line-of-sight (NLOS) vehicle localization problem by using millimeter-wave (MMW) automotive radar. Several preliminary attempts for NLOS vehicle detection are carried out and achieve good results. Firstly, an electromagnetic (EM) wave NLOS multipath propagation model for vehicle scene is established. Subsequently, with the help of available multipath echoes, a complete NLOS vehicle localization algorithm is proposed. Finally, simulation and experimental results validate the effectiveness of the established EM wave propagation model and the proposed NLOS vehicle localization algorithm.

Degradation and overstress failures occur in many electronic systems in which the operation load and environmental conditions are complex. The dependency of them called dependent competing failure process (DCFP), has been widely studied. Electronic system may experience mutual effects of degradation and shocks, they are considered to be interdependent. Both the degradation and the shock processes will decrease the limit of system and cause cumulative effect. Finally, the competition of hard and soft failure will cause the system failure. Based on the failure mechanism accumulation theory, this paper constructs the shock-degradation acceleration and the threshold descent model, and a system reliability model established by using these two models. The mutually DCFP effect of electronic system interaction has been decomposed into physical correlation of failure, including acceleration, accumulation and competition. As a case, a reliability of electronic system in aeronautical system has been analyzed with the proposed method. The method proposed is based on failure physical evaluation, and could provide important reference for quantitative evaluation and design improvement of the newly designed system in case of data deficiency.

Existing specific emitter identification (SEI) methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages, which reduce the identification accuracy of emitters and complicate the procedures of identification. In this paper, we propose a deep SEI approach via multidimensional feature extraction for radio frequency fingerprints (RFFs), namely, RFFsNet-SEI. Particularly, we extract multidimensional physical RFFs from the received signal by virtue of variational mode decomposition (VMD) and Hilbert transform (HT). The physical RFFs and I-Q data are formed into the balanced-RFFs, which are then used to train RFFsNet-SEI. As introducing model-aided RFFs into neural network, the hybrid-driven scheme including physical features and I-Q data is constructed. It improves physical interpretability of RFFsNet-SEI. Meanwhile, since RFFsNet-SEI identifies individual of emitters from received raw data in end-to-end, it accelerates SEI implementation and simplifies procedures of identification. Moreover, as the temporal features and spectral features of the received signal are both extracted by RFFsNet-SEI, identification accuracy is improved. Finally, we compare RFFsNet-SEI with the counterparts in terms of identification accuracy, computational complexity, and prediction speed. Experimental results illustrate that the proposed method outperforms the counterparts on the basis of simulation dataset and real dataset collected in the anechoic chamber.

How to mine valuable information from massive multi-source heterogeneous data and identify the intention of aerial targets is a major research focus at present. Aiming at the long-term dependence of air target intention recognition, this paper deeply explores the potential attribute features from the spatiotemporal sequence data of the target. First, we build an intelligent dynamic intention recognition framework, including a series of specific processes such as data source, data preprocessing, target space-time, convolutional neural networks-bidirectional gated recurrent unit-atteneion (CBA) model and intention recognition. Then, we analyze and reason the designed CBA model in detail. Finally, through comparison and analysis with other recognition model experiments, our proposed method can effectively improve the accuracy of air target intention recognition, and is of significance to the commanders’ operational command and situation prediction.

Aiming at the problem of detecting a distributed target when signal mismatch occurs, this paper proposes a tunable detector parameterized by an adjustable parameter. By adjusting the parameter, the tunable detector can achieve robust or selective detection of mismatched signals. Moreover, the proposed tunable detector, with a proper tunable parameter, can provide higher detection probability compared with existing detectors in the case of no signal mismatch. In addition, the proposed tunable detector possesses the constant false alarm rate property with the unknown noise covariance matrix.

The performance of a strapdown inertial navigation system (SINS) largely depends on the accuracy and rapidness of the initial alignment. A novel anti-interference self-alignment algorithm by attitude optimization estimation for SINS on a rocking base is presented in this paper. The algorithm transforms the initial alignment into the initial attitude determination problem by using infinite vector observations to remove the angular motions, the SINS alignment is heuristically established as an optimization problem of finding the minimum eigenvector. In order to further improve the alignment precision, an adaptive recursive weighted least squares (ARWLS) curve fitting algorithm is used to fit the translational motion interference-contaminated reference vectors according to their time domain characteristics. Simulation studies and experimental results favorably demonstrate its rapidness, accuracy and robustness.

Convolutional neural networks (CNNs) are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns. However, gathering sufficient cases of faulty conditions in real-world engineering scenarios to train an intelligent diagnosis system is challenging. This paper proposes a fault diagnosis method combining several augmentation schemes to alleviate the problem of limited fault data. We begin by identifying relevant parameters that influence the construction of a spectrogram. We leverage the uncertainty principle in processing time-frequency domain signals, making it impossible to simultaneously achieve good time and frequency resolutions. A key determinant of this phenomenon is the window function’s choice and length used in implementing the short-time Fourier transform. The Gaussian, Kaiser, and rectangular windows are selected in the experimentation due to their diverse characteristics. The overlap parameter ’s size also influences the outcome and resolution of the spectrogram. A 50% overlap is used in the original data transformation, and ±25% is used in implementing an effective augmentation policy to which two-stage regular CNN can be applied to achieve improved performance. The best model reaches an accuracy of 99.98% and a cross-domain accuracy of 92.54%. When combined with data augmentation, the proposed model yields cutting-edge results.

Link16 data link is the communication standard of the joint tactical information distribution system (JTIDS) used by the U.S. military and North Atlantic Treaty Organization, which is applied as the opportunistic illuminator for passive radar in this paper. The time-domain expression of the Link16 signal is established, and its ambiguity function expression is derived. The time-delay dimension and Doppler dimension side peaks of which lead to the appearance of the false target during target detection. To solve the problem, the time-delay dimension and Doppler dimension side peaks suppression methods are proposed. For the problem that the conventional mismatched filter (MMF) cannot suppress the time-delay dimension side peaks, a neighborhood MMF (NMMF) is proposed. Experimental results demonstrate the effectiveness of the proposed methods.

Aviation accidents are currently one of the leading causes of significant injuries and deaths worldwide. This entices researchers to investigate aircraft safety using data analysis approaches based on an advanced machine learning algorithm. To assess aviation safety and identify the causes of incidents, a classification model with light gradient boosting machine (LGBM) based on the aviation safety reporting system (ASRS) has been developed. It is improved by k-fold cross-validation with hybrid sampling model (HSCV), which may boost classification performance and maintain data balance. The results show that employing the LGBM-HSCV model can significantly improve accuracy while alleviating data imbalance. Vertical comparison with other cross-validation (CV) methods and lateral comparison with different fold times comprise the comparative approach. Aside from the comparison, two further CV approaches based on the improved method in this study are discussed: one with a different sampling and folding order, and the other with more CV. According to the assessment indices with different methods, the LGBM-HSCV model proposed here is effective at detecting incident causes. The improved model for imbalanced data categorization proposed may serve as a point of reference for similar data processing, and the model’s accurate identification of civil aviation incident causes can assist to improve civil aviation safety.

In electromagnetic countermeasures circumstances, synthetic aperture radar (SAR) imagery usually suffers from severe quality degradation from modulated interrupt sampling repeater jamming (MISRJ), which usually owes considerable coherence with the SAR transmission waveform together with periodical modulation patterns. This paper develops an MISRJ suppression algorithm for SAR imagery with online dictionary learning. In the algorithm, the jamming modulation temporal properties are exploited with extracting and sorting MISRJ slices using fast-time autocorrelation. Online dictionary learning is followed to separate real signals from jamming slices. Under the learned representation, time-varying MISRJs are suppressed effectively. Both simulated and real-measured SAR data are also used to confirm advantages in suppressing time-varying MISRJs over traditional methods.

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.