An intelligent antenna synthesis method is proposed to automatically select suitable antenna type and provide optimal geometric parameters according to the requirement of antenna performance. The performance characteristics of different antennas are analyzed, and a smart antenna selection model is established to recommend the appropriate antenna by using support vector machine (SVM). Then, the stacking ensemble model is built by combining five primary learners to give full play to the advantages of each type of learners and, finally, the geometric parameters of the antenna are provided. Microstrip patch antenna, spiral antenna, and horn antenna are used to demonstrate the accuracy and efficiency of the model. The system shows a great ability of antenna classification with accuracy over 99% and parameter prediction with a mean absolute percentage error (MAPE) of less than 6%. Moreover, the results are compared with the traditional data-driven model, and the key parameters of the model are comprehensively discussed. The proposed method could be widely used in intelligent antenna design in practice.

Unmanned aerial vehicle (UAV), when illuminated by high-power microwave (HPM), is vulnerable to losing control and even falling to the ground with damage. To explore the mechanism of the UAV's falling and its damage caused by HPM, the HPM radiation experiments on a certain kind of UAV are carried out. It is concluded that the UAV's cable is the main energy coupling path from HPM according to the analysis of the cable connection relationships among the flight control system (FCS), the electronic speed control (ESC) board, and the motors based on the experiment. Furthermore, the coupled voltages of the cable's termination load are obtained when the UAV is radiated by HPM with different carrier frequencies or incident directions using numerical calculation and typical test verification. To facilitate the analysis of circuit level, the equivalence of radiation and injection test is analyzed, so the waveform of the control signal related to the UAV's flight is recorded by the injection test. According to the experimental results and the principle of the UAV's flight dynamics, the effect mechanisms of the UAV's falling and its damage are clarified. The experimental results show that the carrier frequency of the HPM leading to the falling and damage of the UAV mainly depends on the length of the internal cable inside the UAV. The pulsewidth and the repetition frequency of HPM resulting in the UAV's falling are related to the pulsewidth and the period of the control signal of FCS. In addition, the coupled voltages induced on the twisted three-wire cables due to the illumination of HPM are verified to enter into the control signal port through parasitic capacitance and, finally, to damage the vulnerable components, including the metal–oxide–semiconductor field-effect transistor inside the ESC and the motor of the UAV. The damage mechanism is determined to be the high-voltage breakdown and large current burning.

Unmanned aerial vehicle (UAV) is likely to be interfered by high-power microwave (HPM) pulse, especially its datalink. To investigate the effects of HPM pulse on the datalink of a UAV in a dynamic flight scenario, a tracking interference model for an HPM source toward a UAV is proposed, as well a dynamic flight model is also built to determine the HPM reception of the UAV's datalink. In order to predict the possible effects of HPM on the datalink, the tests on a certain type of UAV's datalink are carried out in the presence of HPM with its carrier frequency in L-, S- and C-band, respectively. The results show that the electromagnetic interference (EMI) can easily enter the receiver via front-door when the carrier frequency of the HPM falls into the operating frequency band of the datalink, which will lead to a permanent physical damage. However, when the carrier frequency deviates from the operating frequency band of the datalink, the EMI couples into the incomplete shielded power line via back-door and generates a high-voltage signal at the power port, resulting in a transient lost-link effect or even a functional failure of the datalink due to its abnormal electric power supply. Finally, some suggestions are put forward to improve the UAV's adaptability in the HPM environment.

The operation signal of an unmanned aerial vehicle's (UAV's) datalink will change with the flight radius and attitude, which leads to a dynamic variation of the electromagnetic susceptibility (EMS) of the datalink against the external electromagnetic interference. In order to predict the electromagnetic compatibility (EMC) for the dynamic datalink of a UAV, the operation signal of the UAV's datalink and the received interference by the UAV need to be quantified and the EMS is also necessary to be tested. In this paper, a new model of the UAV's datalink in different flight states is presented. The relationship among the airborne operation signal, the interference and the flight parameters is presented and compared in three typical flight states, i.e., the fixed angle state, dive state, and hover state. To increase the repeatability and accuracy of the test and avoid risks in a flight test, a novel EMS test method using a static test instead of a dynamic flight test is proposed. On the basis of the operation state and its corresponding EMS threshold, the EMC prediction is performed to determine the moment when the datalink will be interrupted. The new method can be used to improve the security of UAV in the severe electromagnetic environment.

In this article, a novel method is presented for electromagnetic interference (EMI) perception and electromagnetic susceptibility (EMS) assessment of an unmanned aerial vehicle (UAV) against interference. A large number of in-phase and quadrature data of the UAV's data link and their corresponding critical EMI signal were collected by the equivalent injection test method. After visualization and preprocessing of the in-phase and quadrature data, the obtained time–frequency spectrum and the data-link state parameter histogram were joined to further preprocess as the input of the model. A dual-channel convolutional neural network optimized by a sparrow search algorithm (SSA-DCNN) was proposed to predict the EMS of the data link of the UAV. The proposed method can not only avoid manual extraction of data features but also improve the intelligence level of EMI perception and safety evaluation on UAVs. The performance of the dual-channel convolutional neural network is compared with that of the SSA-DCNN method under different optimization algorithms. The results show that the SSA-DCNN model can significantly enhance the convergence speed and prediction accuracy of the training process compared with the dual-channel convolutional neural network. Besides, among the optimization algorithms, the stochastic gradient descent with momentum applied to the SSA-DCNN model shows a better performance.

The datalink of an unmanned aerial vehicle (UAV) is vulnerable to external electromagnetic interference (EMI). The characteristic parameters of the EMI signal can be definitively detected by a developed monitoring platform mounted on the UAV, but it is impossible to determine the lost-link thresholds of the datalink in any state by experiment because the state of the datalink varies dynamically with the flight distance and the UAV's attitudes. In this case, whether a certain state of the UAV's datalink will be interrupted or not by the EMI cannot be evaluated. In this article, a method of EMI prediction for the UAV's dynamic datalink based on the Gaussian process regression (GPR) is proposed, two indicators, including the interfering frequency and the operation signal power of the datalink, are taken as the training inputs, and the lost-link thresholds of the datalink obtained by the EMI injection test are taken as the training targets. The results show that this method can effectively fit the training samples and determine a 95% confidence interval of the predictive outputs, which has a low predictive error, less than 2.2 dB. Compared with the methods of the layer recurrent neural network and support vector machine, the GPR method has higher predictive accuracy and a stronger generalization ability. Therefore, the detected EMI characteristic parameters can be used as new input samples to predict the lost-link thresholds in any condition. On this basis, the EMI margin can be calculated to evaluate the degree of the anti-EMI redundancy of the UAV's datalink, which can be used for the active adaptation of the UAV's datalink to EMI in the future.