Lipeng Gao

An improved dynamic kernel function Fast Fourier Transform (FFT) with variable truncation scheme (VTS) is proposed, wherein the dynamic kernel function deploys a twiddle factor fixed-point numerical representation, and substitutes simple shift-and-add operations for the FFT multipliers, accomplishing a hardware resource saving. Using Xilinx System Generator, the improved dynamic truncation function can yield at 20% average reduction on the hardware resources. The proposed VTS dynamically scales the result of every stage in FFT and maximally uses the word length in FFT without complicated design additions. The proposed VTS also can detect weak signal compared to the method of only truncating the least significant bit (LSB).

Electromagnetic warfare is the most extensive and most hidden theatre of battle in modern warfare. To enhance the jamming effectiveness of a cooperative jammer platform against the threat of a radar net, a combinatorial‐optimisation‐based threat evaluation and jamming allocation (COTEJA) system is proposed. This COTEJA system fully considers the confrontation analysis in the jammer‐radar process, including the interactions between radars, jammers, and jammer‐radar pairs, and emphasises the realisation of cooperative jamming strategies. The cooperative jamming strategies include the combination of jamming techniques and optimisation algorithms for the objective function. The performance of the COTEJA system is evaluated through a combat mission that considers a platform with four jammers attacking five threats. In addition, the extended permutation‐based differential evolution algorithm is used for the first time to optimise the jamming coding matrix, which effectively reduces the danger value of netted radar under multiple constraints. The numerical results reveal that the COTEJA system can make the optimal jamming decision within 1 s, which improves the survival ability of the platform in a complicated electromagnetic environment.

In cognitive electronic warfare, when a typical combat vehicle, such as an unmanned combat air vehicle (UCAV), uses radar sensors to explore an unknown space, the target-searching fails due to an inefficient servoing/tracking system. Thus, to solve this problem, we developed an autonomous reasoning search method that can generate efficient decision-making actions and guide the UCAV as early as possible to the target area. For high-dimensional continuous action space, the UCAV’s maneuvering strategies are subject to certain physical constraints. We first record the path histories of the UCAV as a sample set of supervised experiments and then construct a grid cell network using long short-term memory (LSTM) to generate a new displacement prediction to replace the target location estimation. Finally, we enable a variety of continuous-control-based deep reinforcement learning algorithms to output optimal/sub-optimal decision-making actions. All these tasks are performed in a three-dimensional target-searching simulator, i.e., the Explorer game. Please note that we use the behavior angle (BHA) for the first time as the main factor of the reward-shaping of the deep reinforcement learning framework and successfully make the trained UCAV achieve a 99.96% target destruction rate, i.e., the game win rate, in a 0.1 s operating cycle.

The power of Beidou satellite signals is very low, so it is vulnerable to interfering sources and in the presence of jamming. Therefore, a robust constrained inverse beamforming algorithm based on space-time adaptive processing is proposed, which can not only reduce the sidelobe level to suppress interference better, but also achieve the lower complexity, and then introducing the steering vector uncertainty set model into the algorithm to improve its stability. In the simulation, the proposed algorithm can be verified to have good beamforming capability and higher signal-to-interference noise ratio (SINR) improvement even in the case of low signal to noise ratio (SNR) and high interference to noise ratio (INR).

Radar signal recognition is an indispensable part of an electronic countermeasure system. In order to solve the problem that the current techniques have, which is a low recognition rate and a slow recognition speed for radar signals, a rapid accurate recognition system is proposed, especially for when multiple signals arrive at the receiver. The proposed system can recognize eight types of radar signals while separating signals: binary phase shift keying (BPSK), linear frequency modulation (LFM), Costas, Frank code, and P1–P4 codes. Regression variational mode decomposition (RVMD) is explored to separate the received signals, which saves time for parameter optimization of variational mode decomposition (VMD). Furthermore, signal separation and a noise removal technique based on VMD and the first component recognition technique based on a deep belief network (DBN) are proposed. In addition, in order to overcome the loss of the secondary component caused by signal separation, a fusion network is explored to increase the recognition rate of the secondary component in a short time. The simulation results show that the recognition system achieves an overall recognition rate of 99.5% and 94% at a signal-to-noise ratio (SNR) of 0 dB when receiving single signals and double signals, while spending 0.8 s and 2.23 s, respectively. The proposed system can also be used to recognize medical and mechanical signals.

In this paper, we investigate the problem of joint direction of departure (DOD) and the direction of arrival (DOA) estimation in bistatic MIMO radar. A new bistatic MIMO radar with the distributed nested array is proposed. Based on the new array, the DOD and DOA estimation algorithm called automatically paired DR-ESPRIT based on the angle disambiguation algorithm by using the range information of targets is proposed. By designing distributed nested array and using Khatri-Rao product processing, the long baseline and short baseline in the transceiver arrays are virtually extended simultaneously. The non-ambiguous and high-accuracy sine estimations of the DOD and DOA can be accomplished using DR-ESPRIT algorithm and the range information of targets and the geometry of bistatic MIMO radar. The virtual extension of array aperture and high angle estimation accuracy can be achieved for the MIMO radar with automatic pairing and without increasing the number of antennas compared with traditional uniform linear MIMO array. And, the proposed corresponding algorithm gives significant improvement in the DOD and DOA estimation performance. The simulation results validate the theoretical algorithm.

With the increase of radar signal modulations and the emergence of new system radars, the receiver will intercept radar signals at the same time. In order to accurately estimate and suppress the signals, this paper proposes an accurate recognition system for radar emitter signals. The system can effectively separate multiple signals and accurately recognize Binary Phase Shift Keying (BPSK), Linear Frequency Modulation (LFM), Continuous Wave (CW), Costas, Frank code, and P1 to P4 codes. The separation technique based on fractional Fourier transform is proposed to decompose received signals into multiple components. Furthermore, a transferable GoogleNet is explored to achieve accurate recognition of the first component with better separation effect. Meanwhile, variational mode decomposition is developed to eliminate the noise of the second component; then, the fusion features are extracted to improve the recognition rate of the second component. Finally, the improved particle swarm optimization algorithm is proposed to find best support vector machine parameters. The simulation results show that the recognition rate of single signal and double signals can reach 96.23% and 72%, respectively, when signal‐to‐noise ratio is 0 dB. The system can also bring some inspiration to medical and mechanical signal recognition.

The recent appreciation of deep reinforcement learning (DRL) arises from its successes in many domains, but the applications of DRL in practical engineering are still unsatisfactory, including optimizing control strategies in cognitive electronic warfare (CEW). CEW is a massive and challenging project, and due to the sensitivity of the data sources, there are few open studies that have investigated CEW. Moreover, the spatial sparsity, continuous action, and partially observable environment that exist in CEW have greatly limited the abilities of DRL algorithms, which strongly depend on state-value and actionvalue functions. In this work, we use Python to build a three-dimensional space game named Explorer to simulate various CEW environments in which the electronic attacker is an unmanned combat air vehicle (UCAV) and the defender is an observation station, both of which are equipped with radar as the observation sensor. In our game, the UCAV needs to accomplish the task of detecting the target as early as possible to perform follow-up tracking and guidance tasks. To allow an “infant” UCAV to understand what “target searching” is, we train the UCAV’s manoeuvring strategies by means of well-designed reward shaping, simplified constant accelerated motion control, and a deep deterministic policy gradient (DDPG) algorithm based on a generative model and variational Bayesian estimation. The experimental results show that when the operating cycle is 0.2 s, the search success rate of the trained UCAV in 10,000 episodes is improved by 33.36% compared with the benchmark, and the target destruction rate is similarly improved by 57.84%.