CN111740796A - Method and device for predicting electromagnetic interference situation of UAV data link - Google Patents

Abstract

The invention is suitable for the technical field of unmanned aerial vehicle communication, and provides a method and a device for predicting the electromagnetic interference situation of an unmanned aerial vehicle data link, wherein the method comprises the following steps: acquiring electromagnetic parameters and environmental interference data of the unmanned aerial vehicle; inputting the electromagnetic parameters and the environmental interference data of the unmanned aerial vehicle into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold; and determining the electromagnetic interference situation of the unmanned aerial vehicle data chain according to the environmental interference data and the electromagnetic interference effect threshold value. This application establishes the relevant of developments with the unmanned aerial vehicle electromagnetic parameter that obtains electromagnetic interference effect threshold value and detection and environmental interference data through gaussian process regression prediction model, and prediction unmanned aerial vehicle that can be dynamic electromagnetic interference effect threshold value under different operating condition improves unmanned aerial vehicle electromagnetic interference situation and judges the accuracy to improve unmanned aerial vehicle's initiative interference killing feature.

Description

Method and device for predicting electromagnetic interference situation of UAV data link

technical field

The invention belongs to the technical field of unmanned aerial vehicle communication, and in particular relates to a method and a device for predicting the electromagnetic interference situation of an unmanned aerial vehicle data link.

Background technique

UAV is a kind of unmanned aerial vehicle controlled by radio remote control equipment or its own preset program. UAV relies heavily on information links. The safety and reliability of UAV equipment in complex electromagnetic interference environment is UAV communication. a major problem in the field. At present, the anti-electromagnetic interference capability of UAV equipment is weak, which is prominently reflected in the fact that the uplink data link is easily interfered by external electromagnetic radiation, resulting in interruption of ground-air communication and a serious threat to the flight safety of UAVs.

In the prior art, the electromagnetic interference effect threshold obtained by experiment is usually used to judge the current electromagnetic interference situation of the UAV information link. The power of the working signal is constantly changing, and the frequency of the external interference signal appears randomly. This results in the problem of low accuracy of UAV electromagnetic interference situation judgment and weak UAV anti-jamming ability.

SUMMARY OF THE INVENTION

In view of this, the embodiments of the present invention provide a method and device for predicting the electromagnetic interference situation of the UAV data link, so as to solve the problem of low accuracy in judging the electromagnetic interference situation of the UAV in the prior art.

A first aspect of the embodiments of the present invention provides a method for predicting the electromagnetic interference situation of a UAV data link, including:

Obtain the electromagnetic parameters and environmental interference data of the UAV;

Inputting the electromagnetic parameters of the UAV and the environmental interference data into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold;

Determine the electromagnetic interference situation in which the UAV data link is located according to the environmental interference data and the electromagnetic interference effect threshold.

A second aspect of the embodiments of the present invention provides a device for predicting the electromagnetic interference situation of a UAV data link, including:

The electromagnetic data acquisition module is used to acquire the electromagnetic parameters and environmental interference data of the UAV;

a threshold value acquisition module, configured to input the electromagnetic parameters of the UAV and the environmental interference data into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold;

An electromagnetic interference situation determination module, configured to determine the electromagnetic interference situation in which the UAV data link is located according to the environmental interference data and the electromagnetic interference effect threshold.

A third aspect of the embodiments of the present invention provides an adaptive prediction terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer In the program, the steps of the above-mentioned method for predicting the electromagnetic interference situation of the UAV data link are realized.

A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, realizes the above-mentioned electromagnetic interference of the UAV data link The steps of the situation prediction method.

Compared with the prior art, the embodiments of the present invention have the following beneficial effects: the present application first obtains the electromagnetic parameters and environmental interference data of the UAV; and then inputs the electromagnetic parameters and the environmental interference data of the UAV. The Gaussian process regression prediction model is used to obtain the electromagnetic interference effect threshold; finally, the electromagnetic interference situation in which the UAV data link is located is determined according to the environmental interference data and the electromagnetic interference effect threshold. The present application establishes a dynamic correlation between the electromagnetic interference effect threshold and the detected UAV electromagnetic parameters and environmental interference data through the Gaussian process regression prediction model, which can dynamically predict the electromagnetic interference effect threshold of the UAV under different working states, and improve the UAV electromagnetic interference situation judgment accuracy, so as to improve the UAV's active anti-jamming ability.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only for the present invention. In some embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

FIG. 1 is a schematic structural diagram of a UAV data link system provided by an embodiment of the present invention.

2 is a schematic flowchart of a method for predicting an electromagnetic interference situation of a UAV data link provided by an embodiment of the present invention;

3 is a schematic flowchart of another implementation of the method for predicting the electromagnetic interference situation of the UAV data link provided by the embodiment of the present invention;

FIG. 4 is a schematic flowchart of S102 in FIG. 2 according to an embodiment of the present invention;

5 is a schematic diagram of a relationship curve between input data and output data when an error occurs in a UAV data link provided by an embodiment of the present invention;

6 is a schematic diagram of a relationship curve between input data and output data when the UAV data link is out of lock according to an embodiment of the present invention;

7 is a schematic diagram of a Gaussian process regression training error of an electromagnetic interference effect threshold when a bit error occurs in a data link provided by an embodiment of the present invention;

8 is a schematic diagram of a Gaussian process regression training error of an electromagnetic interference effect threshold when a data link loses lock provided by an embodiment of the present invention;

FIG. 9 is a schematic structural diagram of a device for predicting an electromagnetic interference situation of a UAV data link provided by an embodiment of the present invention.

Detailed ways

In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are set forth in order to provide a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In order to illustrate the technical solutions of the present invention, the following specific embodiments are used for description.

As shown in FIG. 1, FIG. 1 shows the structure of the UAV data link system provided in this embodiment, including a ground subsystem and an airborne subsystem 92; wherein the ground subsystem includes a ground terminal 911, a first duplexer 912 and a first antenna 913 , the airborne subsystem 92 includes a second duplexer 921 , an airborne data link 922 , electromagnetic interference environment monitoring hardware 923 , an adaptive prediction terminal 924 and a second antenna 925 .

In this embodiment, the ground subsystem is used for drone ground remote control, drone electromagnetic environment monitoring and display, and telemetry display, and the ground subsystem communicates with the airborne subsystem through the first duplexer 912 and the second duplexer 921 92 Communications.

Specifically, the airborne data link 922 is an existing airborne data link, including an airborne transmitting end, an airborne receiving end and a data terminal; the method for predicting the electromagnetic interference situation of the UAV data link provided in this embodiment is applied to adaptive in the prediction terminal 924. The adaptive prediction terminal 924 is connected to the UAV flight control system, and is used for sending the anti-jamming response measures generated by itself to the UAV flight control system.

Further, the electromagnetic interference environment monitoring hardware 923 is used to obtain electromagnetic parameters and environmental interference data of the UAV. The electromagnetic interference environment monitoring hardware 923 includes a power divider, a compensation circuit, a monitoring platform and a memory, wherein the power divider is connected with the compensation circuit, the compensation circuit is connected with the monitoring platform, the monitoring platform is connected with the memory, and the power divider receives the data sent by the duplexer. The signal is sent to the monitoring platform and the onboard receiving end of the onboard data link 922 through the compensation circuit, and the monitoring platform stores the acquired signal in the memory.

As shown in FIG. 2, FIG. 2 shows the process of the method for predicting the electromagnetic interference situation of the UAV data link provided by the embodiment of the present invention, and the process is described in detail as follows:

S101: Obtain the electromagnetic parameters and environmental interference data of the UAV.

The main body of the process in this embodiment is the adaptive prediction terminal 924 of the airborne data link. The adaptive prediction terminal 924 first obtains the electromagnetic parameters and environmental interference data of the drone sent by the electromagnetic interference environment monitoring hardware. The electromagnetic parameters of the UAV include working signal power, working signal frequency and current AGC voltage. Environmental interference data includes EMI power and EMI frequency.

Specifically, the AGC voltage is the attenuation amplitude of the conducted signal controlled by the ESC in the automatic gain control circuit in the receiver intermediate frequency amplifier unit. This circuit structure can control the output intermediate frequency signal power to stabilize at a fixed value, and the voltage value reflects the received signal. , that is, the stronger the received signal, the greater the required ESC attenuation, and the higher the AGC voltage.

S102: Input the electromagnetic parameters of the UAV and the environmental interference data into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold.

In this embodiment, during the flight of the UAV, the state of the data link continues to change dynamically, and the power of the working signal received by the airborne antenna changes constantly. In addition, the frequency of the external interference signal appears randomly, so it is impossible to obtain all the working states of the data link through experiments. The threshold of electromagnetic interference effect caused by any potential interference frequency signal. Therefore, it is necessary to find the correlation between the threshold value of electromagnetic interference effect and the power of the working signal and the frequency of the interference signal.

This embodiment adopts the Gaussian process regression method for modeling to establish the correlation between the electromagnetic interference effect threshold and the power of the working signal and the frequency of the interference signal. Features.

S103: Determine the electromagnetic interference situation in which the UAV data link is located according to the environmental interference data and the electromagnetic interference effect threshold.

It can be seen from the above embodiments that the present application first obtains the electromagnetic parameters and environmental interference data of the UAV; and then inputs the electromagnetic parameters and the environmental interference data of the UAV into the Gaussian process regression prediction model to obtain the electromagnetic interference effect. threshold; finally, according to the environmental interference data and the electromagnetic interference effect threshold, determine the electromagnetic interference situation in which the UAV data link is located. The present application establishes a dynamic correlation between the electromagnetic interference effect threshold and the detected UAV electromagnetic parameters and environmental interference data through the Gaussian process regression prediction model, which can dynamically predict the electromagnetic interference effect threshold of the UAV under different working states, and improve the UAV electromagnetic interference situation judgment accuracy, so as to improve the UAV's active anti-jamming ability.

In an embodiment of the present invention, as shown in FIG. 3 , FIG. 3 shows another implementation process of the method for predicting the electromagnetic interference situation of the UAV data link. The process is described in detail as follows:

S201: Acquire a training sample, where the training sample includes observation data and input data; the observation data includes an interference-to-signal ratio and an AGC voltage variation, and the input data includes electromagnetic parameters and environmental interference data.

In this embodiment, the signal-to-interference ratio is the ratio of the power of the interference signal to the power of the working signal. The standard AGC voltage is the AGC voltage monitored by the drone under normal interference-free conditions. The AGC voltage change includes the AGC voltage change corresponding to the loss of lock effect and the AGC voltage change corresponding to the bit error effect, and the AGC voltage change corresponding to the loss of lock effect is the AGC voltage when the UAV data link has a loss of lock effect. The difference of the standard AGC voltage; the AGC voltage change corresponding to the bit error effect is the difference between the AGC voltage when the bit error effect occurs in the UAV data link minus the standard AGC voltage.

S202: Standardize the observed data in the training sample and the input data to obtain a standardized training sample;

S203: Create an initial prediction model based on the Gaussian process regression method;

S204: Input the standardized training samples into the initial prediction model, and train the initial prediction model to obtain the Gaussian process regression prediction model.

In this example, the working signal high power -45dBm and low power -80dBm data link states are used as examples. Through the experimental analysis of the electromagnetic interference injection effect of the dynamic data link of the drone, it is concluded that the working signal power and the interference frequency affect the electromagnetic interference of the data link. effect threshold.

Specifically, this application takes channel 1 as an example, selects typical working signal power {-100,-95,-90,...,-45,-40,-35}dBm and interference frequency offset {-5,-4,- 3,-2,-1,0,1,2,3,4,5}MHz, the standard CW interference effect thresholds under different data link working conditions were obtained by carrying out injection experiments, including the data link beginning to experience bit errors and loss. Interference-to-signal ratio and AGC voltage variation when the two effects are locked. Since the interference signal power and AGC voltage cannot directly reflect the effect of electromagnetic interference on the UAV data link, the above values are converted into the interference signal ratio and the AGC voltage variation respectively. Determine the relationship between input data (interference signal frequency, working signal power) and output data (interference signal ratio and AGC voltage variation), as shown in Figure 5 and Figure 6.

Figure 5 shows the relationship between input data (interference signal frequency, working signal power) and output data (interference-to-signal ratio and AGC voltage variation) when bit errors occur in the UAV data link. Among them, Figure 5a shows the relationship between the SIR and the interference frequency offset corresponding to different working signal powers under the bit error effect, and Figure 5b shows the SIR and the interference corresponding to different interference frequency offsets under the bit error effect. The relationship curve between signal powers, Figure 5c shows the relationship curve between the AGC voltage variation corresponding to different working signal powers and the interference frequency offset under the bit error effect, Figure 5d shows the AGC voltage corresponding to different interference frequency offsets under the bit error effect The relationship curve between the amount of change and the power of the interfering signal.

Specifically, the interference frequency offset represents a difference obtained by subtracting the frequency of the interference signal from the frequency of the working signal.

Figure 6 shows the relationship between input data (interference signal frequency, working signal power) and output data (interference signal ratio and AGC voltage variation) when the UAV data link loses lock. Among them, Figure 6a shows the relationship between the SIR and the interference frequency offset corresponding to different working signal powers under the loss of lock effect, and Figure 6b shows the SIR and the interference corresponding to different interference frequency offsets under the loss of lock effect. The relationship curve between signal powers, Figure 6c shows the relationship curve between the AGC voltage variation corresponding to different working signal powers and the interference frequency offset under the loss-of-lock effect, and Figure 6d shows the AGC voltage corresponding to different interference frequency offsets under the loss-of-lock effect The relationship curve between the amount of change and the power of the interfering signal.

It can be seen from Figure 5a and Figure 6a that the interference signal ratio and the interference frequency offset have a nonlinear relationship when the data link has bit error and lock loss effects in different working states, and the interference signal ratio corresponding to co-channel interference is relatively small, that is, The ability of the data link to resist co-channel interference is relatively weak. As the interference frequency deviates farther from the operating frequency, the interference signal ratio increases relatively. In Figures 5b and 6b, for different interference frequencies, the signal-to-interference ratio and the power of the working signal also show a nonlinear change trend when the data link has bit errors and lock-loss effects. This is due to the blocking effect phenomenon caused by the gradual saturation of the active circuit inside the receiver of the drone. Similarly, it can be seen from Figures 5c, 5d and 6c, 6d that when the data link has bit error and lock loss effects, the AGC voltage variation has a nonlinear relationship with the interference frequency offset and the working signal power. Therefore, it is difficult to predict the electromagnetic environmental effects of nonlinear systems from the perspective of system principle or effect mechanism using traditional deterministic modeling methods. .

Specifically, it can be seen from the data link electromagnetic interference injection effect test that the working signal power P _s and the interference frequency f _j affect the interference signal power {P _j1 , P j2 } and AGC voltage { P j1 , P _j2 } and AGC voltage { V _j1 , V _j2 }. In this embodiment, the interference-to-signal ratio {ISR ₁ , ISR ₂ } and the variation of the AGC voltage {V ₁ , V ₂ } are taken as the observed values of the training samples, which is convenient to observe and measure the disturbed change degree of the data link state. Among them, ISR ₁ represents the interference-to-signal ratio when the bit error occurs, and ISR ₂ represents the interference-to-signal ratio when the lock is lost. V ₁ represents the variation of the AGC voltage before and after the application of the interference signal corresponding to the bit error effect, and V ₂ represents the variation of the AGC voltage before and after the application of the interference signal corresponding to the loss of lock effect.

In addition, using the electromagnetic interference frequency f _j and the working signal power P _s as the input data of the training samples, the Gaussian process regression modeling is carried out.

In this embodiment, the method for predicting the electromagnetic interference effect threshold value of dynamic data link based on Gaussian process regression can be summarized as:

(1) Determine the sample data. Determine the training samples according to the test results of the electromagnetic interference injection effect of the dynamic data link;

(2) Set the initial value of the hyperparameter. Using the double exponential covariance function as the kernel function, the prior distribution function is determined by setting the initial value of the hyperparameter.

观测值的协方差函数为

I表示单位矩阵。此外，n_*个样本X_*作为测试集，其输出f_*同样服从高斯分布N(μ(x_*),K(x_*,x_*))，此时观测值和测试样本的预测值服从联合高斯先验分布函数：Specifically, let the observed value be y=f'(x)=f(x)+ε, where ε is Gaussian noise and obeys Gaussian distribution

The covariance function of the observations is

I represents the identity matrix. In addition, n _* samples X _* are used as the test set, and the output f _* also obeys the Gaussian distribution N(μ(x _* ), K(x _* , x _* )), at this time, the predicted value of the observed value and the test sample obey the joint Gaussian prior distribution function:

In formula (1), the covariance K(X,X) is an n×n-dimensional matrix, K(X,X _* ) is an n×n _* -dimensional matrix, and K(X _* ,X) is an n _* ×n-dimensional matrix , K(X _* ,X _* ) is an n _* ×n _* dimensional matrix

(3) Training the model. Input the training sample data, convert the prior distribution function into the posterior distribution function, optimize the hyperparameter value of the kernel function, and obtain the Gaussian process regression prediction model.

In this embodiment, from the Bayesian principle and the prior distribution function of the joint Gaussian distribution, the conditional posterior distribution function of the output f _* can be obtained as shown in formula (2):

In this embodiment, the predicted output value of the test sample can be obtained according to the mean value and covariance of the posterior distribution.

Further, the optimization process of hyperparameters specifically includes:

Since zero mean is usually used in the calculation process, the prediction error is generally greatly affected by the covariance, so the optimal hyperparameter of the covariance function must be determined to reduce the prediction error. The square exponential function is selected as the covariance function of the Gaussian kernel function, and the function expression is shown in formula (3).

In formula (3), l represents the feature length scale, δ represents the sample standard deviation, θ={l,δ}={θ ₁ ,θ ₂ ,...,θ _n } is the set of all hyperparameters, which can be known from Bayesian theory p(A|B,C)p(B|C)=p(B|A,C)p(A|C)=P(A,B|C), the posterior distribution function of the hyperparameter can be obtained:

样本方差

和协方差K(X,X)取决于超参数集θ，因此In formula (4), p(θ|X) represents the hyperparameter prior. Since its likelihood function value is independent of the sample X, p(θ|X)=p(θ), which is set as a constant; p( y|X) represents the likelihood function of the sample observation value, and its function value is independent of θ, and the value can also be set as a constant; p(y|θ, X) represents the edge likelihood function, and y obeys the Gaussian distribution

sample variance

and covariance K(X,X) depends on the hyperparameter set θ, so

Finally, the optimal hyperparameters are calculated and converted into the maximum value of equation (5). For the convenience of solving, the logarithm of equation (5) is obtained,

In formula (6), the log-likelihood function contains three terms: the first term is the complex penalty term, which is used to prevent the training model from overfitting; the second term is the data fitting term, which is used to characterize the hyperparameters to the training samples. the degree of fit; the third term is a constant term. In the process of solving the maximum value of the log-likelihood function, the conjugate gradient method is usually used, that is, the negative direction of the gradient is obtained by calculating the derivatives of each parameter several times, and then the optimal hyperparameters are obtained after many iterations until convergence.

In an embodiment of the present invention, for the observation data and input data in this embodiment, since the Gaussian process regression method generally adopts the zero mean assumption, when predicting the non-stationary training sample data, the predicted value will quickly tend to zero. , resulting in a large prediction error of the model. In order to eliminate the influence of physical dimensions, the input sample data {P _s , f _j } and the observed sample data {ISR ₁ , ISR ₂ , V ₁ , V ₂ } must be standardized, and then model training and prediction are carried out. For any array Z={z ₁ , z ₂ , . . . , z _n }, the normalization processing formula is shown in formula (7).

表示原始数据的平均值，stdZ表示原始数据的标准差，即式(8)：In formula (7), Z′ represents the normalized array,

Represents the mean value of the original data, and stdZ represents the standard deviation of the original data, that is, formula (8):

After the original data is normalized, the mean of the training samples becomes 0 and the variance is 1. On the contrary, the predicted value obtained by using the Gaussian process regression prediction model is also the standardized data, which needs to be solved inversely according to equation (7) to restore the dimension of the predicted value.

In this embodiment, the Gaussian process regression model is trained by using the normalized input sample data {P _s , f _j } and the observed sample data {ISR ₁ , ISR ₂ , V ₁ , V ₂ }, and the square exponential kernel function is set. The initial value of the hyperparameter θ = {1, 1}, and the standard deviation of the Gaussian noise likelihood estimate is set to 0.37. Through experiments, it can be seen that the signal-to-interference ratio and AGC voltage variation of the predicted output of the training sample can fit the variation trend of the measured data. In addition, the Gaussian process regression method can give the probabilistic uncertainty of the predicted output. The smaller the 95% confidence interval, the higher the reliability of the corresponding predicted output value; on the contrary, the larger the interval, the lower the corresponding predicted output value.

In this embodiment, Fig. 7 shows the Gaussian process regression training error of the electromagnetic interference effect threshold when a bit error occurs in the data link, wherein Fig. 7a shows the interference signal ratio prediction error when a bit error occurs in the data link, and Fig. 7b shows the data link Prediction error of AGC voltage change when bit error occurs. Figure 8 shows the Gaussian process regression training error of the EMI effect threshold when the data link loses lock, wherein Figure 8a shows the interference signal ratio prediction error when the data link loses lock, and Figure 8b shows the AGC when the data link loses lock. Voltage variation prediction error.

As shown in Figures 7 and 8, compared with the observed sample values obtained from the actual test, the predicted output value deviation of the co-frequency interference effect threshold is relatively large. Caused by inaccuracy; the larger the interference frequency offset, the more stable the data link is when the electromagnetic interference effect occurs, the measurement timing is relatively accurate, the data fitting effect is better, and the overall prediction error is less than 1.5dB. Through the above sample learning and training, a Gaussian process regression prediction model is obtained.

In an embodiment of the present invention, the electromagnetic parameters of the UAV include working signal power, the environmental interference data includes electromagnetic interference frequency; the electromagnetic interference effect threshold includes the interference signal power threshold and the AGC voltage threshold; as shown in the figure 4, FIG. 4 shows the specific duration process of S102 in FIG. 2, and the details of the process are as follows:

S301: Input the working signal power and the electromagnetic interference frequency into the Gaussian process regression prediction model, and output the corresponding interference signal ratio and AGC voltage variation when different effects occur in the UAV data link;

S302: Determine the interference signal power thresholds of the UAV data link under different working states according to the corresponding interference signal ratio and the working signal power when the UAV data link has different effects;

S303: Determine the AGC voltage thresholds of the drone data link in different working states according to the corresponding AGC voltage variation and the standard AGC voltage when the drone data link has different effects.

In this embodiment, the interference signal power in the current environment of the drone is compared with the interference signal power threshold in different working states to determine the electromagnetic interference situation in which the data link of the drone is located.

In this embodiment, the current AGC voltage of the drone can also be compared with the AGC voltage thresholds in different working states to determine the electromagnetic interference situation in which the data link of the drone is located.

Further, the electromagnetic interference situation in which the UAV data link is located is determined by judging the comprehensive interference signal power and the current AGC voltage.

In an embodiment of the present invention, the data link effect includes loss of lock and bit error, and the interference signal power threshold includes a first interference signal power threshold, a second interference signal power threshold, a third interference signal power threshold, and a first interference signal power threshold. Four interference signal power thresholds; the specific implementation process of S302 in Figure 4 also includes:

Calculate the product of the corresponding interference signal ratio and the working signal power when the unmanned aerial vehicle data link has an out-of-lock effect, and obtain a first interference signal power threshold; the first interference signal power threshold is the unmanned aerial vehicle data. Interfering signal power threshold for the chain to enter the out-of-lock state;

Calculate the product of the corresponding interference signal ratio and the working signal power when the UAV data link has a bit error effect to obtain a second interference signal power threshold, where the second interference signal power threshold is the UAV data The interfering signal power threshold for the chain to enter a critical loss-of-lock state from an unstable state;

Subtract the first preset buffer value from the second interference signal power threshold to obtain a third interference signal power threshold, where the third interference signal power threshold is the UAV data link from a relatively stable state to an unstable state The interfering signal power threshold;

Subtract the second preset buffer value from the third interference signal power threshold to obtain a fourth interference signal power threshold, where the fourth interference signal power threshold corresponds to the UAV data link entering a relatively stable state from a stable state The interfering signal power threshold.

In this embodiment, the working states of the data link are defined as loss of lock, critical loss of lock, unstable, relatively stable and stable. Among them, stable and relatively stable states are states that are not affected by external electromagnetic interference; unstable means that the data link is affected by external electromagnetic interference, and the link stability becomes worse, and the aircraft state parameters are at risk of fluctuation; critical loss of lock means that the data link is affected by external electromagnetic interference. After the interference, the data link is unstable, and the aircraft state parameters fluctuate greatly; loss of lock means that the communication is interrupted after the data link is affected by external electromagnetic interference, and the drone is out of control.

In this embodiment, both the first preset buffer value and the second preset buffer value may be set to 6dB.

In this embodiment, if the current jamming signal power of the drone is greater than the first jamming signal power threshold, it is predicted that the drone is in an out-of-lock state; if the current jamming signal power of the drone is greater than the second jamming signal power threshold and If it is less than or equal to the first jamming signal power threshold, it is predicted that the UAV is in a critical loss-of-lock state; if the current jamming signal power of the UAV is greater than the third jamming signal power threshold and less than or equal to the second jamming signal power threshold, it is predicted that The drone is in an unstable state; if the current jamming signal power of the drone is greater than the fourth jamming signal power threshold and less than or equal to the third jamming signal power threshold, it is predicted that the drone is in a relatively stable state; if the drone is currently in a relatively stable state The jamming signal power is less than or equal to the fourth jamming signal power threshold, and the UAV is predicted to be in a stable state.

In this embodiment, the first interference signal power threshold is greater than the second interference signal power threshold, the second interference signal power threshold is greater than the third interference signal power threshold, and the third interference signal power threshold is greater than the fourth interference signal power threshold.

In one embodiment of the present invention, the data link effect includes loss of lock and bit error, and the AGC voltage threshold includes a first AGC voltage threshold, a second AGC voltage threshold, a third AGC voltage threshold and a fourth AGC voltage threshold ; The concrete realization flow of S303 in Fig. 4 includes:

The AGC voltage change corresponding to the unmanned aerial vehicle data link under the loss of lock effect is added to the standard AGC voltage to obtain the first AGC voltage threshold, and the first AGC voltage threshold is the unmanned aerial vehicle data link. AGC voltage threshold in lock state;

The AGC voltage variation corresponding to the UAV data link under the bit error effect is added to the standard AGC voltage to obtain a second AGC voltage threshold, and the second AGC voltage threshold is the UAV data link from which it is not determined. The AGC voltage threshold for the steady state to enter the critical loss-of-lock state;

Subtract the third preset buffer value from the second AGC voltage threshold to obtain a third AGC voltage threshold, where the third AGC voltage threshold is the AGC voltage of the drone data link from a relatively stable state to an unstable state threshold;

Subtract the fourth preset buffer value from the third AGC voltage threshold to obtain a fourth AGC voltage threshold, where the fourth AGC voltage threshold is the AGC voltage threshold at which the drone data link enters a relatively stable state from a stable state .

In this embodiment, both the third preset buffer value and the fourth preset buffer value may be set to 5V. The first AGC voltage threshold is greater than the second AGC voltage threshold, the second AGC voltage threshold is greater than the third AGC voltage threshold, and the third AGC voltage threshold is greater than the third AGC voltage threshold.

In this embodiment, if the current AGC voltage of the drone is greater than the first AGC voltage threshold, it is predicted that the data link of the drone is in an out-of-lock state; if the current AGC voltage of the drone is greater than the second AGC voltage threshold and less than or is equal to the first AGC voltage threshold, it is predicted that the drone data link is in a critical loss-of-lock state, and if the current AGC voltage of the drone is greater than the third AGC voltage threshold and less than or equal to the second AGC voltage threshold, it is predicted that the The drone data link is in an unstable state. If the current AGC voltage of the drone is greater than the fourth AGC voltage threshold and less than or equal to the third AGC voltage threshold, it is predicted that the drone data link is in a relatively stable state. If the current AGC voltage of the man-machine is less than or equal to the fourth AGC voltage threshold, it is predicted that the UAV data link is in a stable state.

In an embodiment of the present invention, the method for predicting the electromagnetic interference situation of the UAV data link provided by this embodiment further includes:

Corresponding anti-jamming response measures are determined according to the electromagnetic interference situation in which the UAV data link is located.

In an embodiment of the present invention, the electromagnetic interference situation includes a loss-of-lock state, a critical loss-of-lock state, an unstable state, a relatively stable state, and a stable state, and the above-mentioned specific process for determining the anti-interference response measures includes:

If the UAV data link is in the relatively stable state, an abnormal alarm signal of the UAV data link is generated;

If the UAV data link is in the unstable state and the critical loss-of-lock state, the UAV is controlled to perform electromagnetic interference adaptive behavior; the electromagnetic interference adaptive behavior includes but is not limited to changing the flight flight track, adjust the direction of the airborne antenna, switch the working channel and control the ground transmit power.

In this embodiment, the stable state does not require any operation on the UAV. According to the level of electromagnetic interference, the relatively stable state is determined as the primary warning interval. At this time, an alarm signal is generated, and the alarm signal is used to mark the data of the UAV. chain. The unstable and critical loss-of-lock state is determined as the early warning interval. When the UAV data link is in the early warning interval, the electromagnetic interference adaptive behavior is performed. The electromagnetic interference adaptive behavior includes changing the flight route, adjusting the antenna direction, switching the working channel and Controls the ground transmit power. Among them, changing the flight route is used to stay away from the interference source, adjusting the antenna direction and switching the working channel are used to reduce the coupling efficiency, and controlling the ground transmission power is used to improve the anti-jamming capability of the equipment.

In this embodiment, if the drone is in an unstable state, the anti-jamming method of switching the working channel can be preferentially selected. If the UAV is in a critical loss-of-lock state, the purity of the space spectrum is poor, and the channel switching can no longer meet the anti-jamming requirements. The signal can make the data link achieve the purpose of anti-interference.

Specifically, since the electromagnetic interference signal has already posed a serious threat to the data link, it is necessary to increase the electromagnetic interference margin a for the data link, so that the electromagnetic interference threat level of the UAV data link is reduced to an unstable state, that is, the second interference signal power threshold S _j =P _j +a. P _j represents the jamming signal power currently monitored by the UAV. Using the Gaussian process regression prediction model, the working signal power P _s under the condition of S _j is obtained reversely.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

In one embodiment, as shown in FIG. 9 , FIG. 9 shows a schematic structural diagram of the apparatus 100 for predicting the electromagnetic interference situation of the UAV data link provided in this embodiment, which includes:

The electromagnetic data acquisition module 110 is used to acquire the electromagnetic parameters and environmental interference data of the UAV;

a threshold value acquisition module 120, configured to input the electromagnetic parameters of the UAV and the environmental interference data into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold;

The electromagnetic interference situation determination module 130 is configured to determine the electromagnetic interference situation in which the UAV data link is located according to the environmental interference data and the electromagnetic interference effect threshold.

In one embodiment, the apparatus 100 for predicting the electromagnetic interference situation of the UAV data link provided in this embodiment further includes:

a training sample acquisition module, configured to acquire a training sample, the training sample includes observation data and input data; the observation data includes interference signal ratio and AGC voltage variation, and the input data includes electromagnetic parameters and environmental interference data;

a sample data standardization module, which is used to standardize the observation data in the training sample and the input data to obtain a standardized training sample;

The initial model creation module is used to create an initial prediction model based on the Gaussian process regression method;

A model training module, configured to input the standardized training samples into the initial prediction model, train the initial prediction model, and obtain the Gaussian process regression prediction model.

In one embodiment, the electromagnetic parameters of the drone include working signal power, and the environmental interference data includes electromagnetic interference frequency; the electromagnetic interference effect threshold includes an interference signal power threshold and an AGC voltage threshold;

The threshold acquisition module 120 includes:

An output value acquisition unit, configured to input the working signal power and the electromagnetic interference frequency into the Gaussian process regression prediction model, and output the corresponding interference signal ratio and AGC voltage variation when different effects occur in the UAV data link ;

The interference signal power threshold acquisition unit is used to determine the interference signal power of the drone data link in different working states according to the corresponding interference signal ratio and the working signal power when the drone data link has different effects threshold;

The voltage threshold acquisition unit is configured to determine the AGC voltage threshold of the drone data link in different working states according to the corresponding AGC voltage variation and the standard AGC voltage when different effects occur on the drone data link.

In one embodiment, the data link effect includes loss of lock and bit error, and the interference signal power threshold includes a first interference signal power threshold, a second interference signal power threshold, a third interference signal power threshold, and a fourth interference signal power threshold power threshold;

The interference signal power threshold obtaining unit includes:

The first interference signal power threshold calculation subunit is used to calculate the product of the corresponding interference signal ratio and the working signal power when the unmanned aerial vehicle data link has an out-of-lock effect, so as to obtain the first interference signal power threshold; the first interference signal power threshold; A jamming signal power threshold is the jamming signal power threshold at which the UAV data link enters an out-of-lock state;

The second interference signal power threshold calculation subunit is used to calculate the product of the corresponding interference signal ratio and the working signal power when the UAV data link has a bit error effect, to obtain the second interference signal power threshold, and the first The second jamming signal power threshold is the jamming signal power threshold at which the UAV data link enters a critical loss-of-lock state from an unstable state;

A third interference signal power threshold calculation subunit, configured to subtract the first preset buffer value from the second interference signal power threshold to obtain a third interference signal power threshold, where the third interference signal power threshold is the no The threshold value of the interference signal power for the human-machine data link to enter an unstable state from a relatively stable state;

A fourth interference signal power threshold calculation subunit, configured to subtract the second preset buffer value from the third interference signal power threshold to obtain a fourth interference signal power threshold, where the fourth interference signal power threshold is the no The threshold value of the interference signal power corresponding to the HMI data link from a stable state to a relatively stable state.

In one embodiment, the data link effects include loss of lock and bit errors, and the AGC voltage thresholds include a first AGC voltage threshold, a second AGC voltage threshold, a third AGC voltage threshold, and a fourth AGC voltage threshold; voltage thresholds The acquisition unit includes:

The first AGC voltage threshold acquisition sub-unit is used to add the corresponding AGC voltage variation of the UAV data link under the loss-of-lock effect to the standard AGC voltage to obtain a first AGC voltage threshold, the first AGC voltage The threshold is the AGC voltage threshold at which the UAV data link enters an out-of-lock state;

The second AGC voltage threshold acquisition subunit is used to add the corresponding AGC voltage variation of the UAV data link under the bit error effect to the standard AGC voltage to obtain a second AGC voltage threshold, the second AGC voltage The threshold is the AGC voltage threshold at which the UAV data link enters a critical unlocked state from an unstable state;

A third AGC voltage threshold obtaining subunit, configured to subtract a third preset buffer value from the second AGC voltage threshold to obtain a third AGC voltage threshold, where the third AGC voltage threshold is the UAV data link AGC voltage threshold from a relatively stable state to an unstable state;

The fourth AGC voltage threshold acquisition subunit is used to subtract the fourth preset buffer value from the third AGC voltage threshold to obtain a fourth AGC voltage threshold, where the fourth AGC voltage threshold is the UAV data link AGC voltage threshold from steady state to relatively steady state.

In one embodiment, the apparatus 100 for predicting the electromagnetic interference situation of the UAV data link provided in this embodiment further includes:

The interference measure determination module is used for determining corresponding anti-interference response measures according to the electromagnetic interference situation in which the UAV data link is located.

In one embodiment, the interference measure determination module includes:

an abnormal alarm unit, configured to generate an abnormal alarm signal of the UAV data link if the UAV data link is in the relatively stable state;

The interference adaptive behavior execution unit is configured to control the UAV to perform the electromagnetic interference adaptive behavior if the UAV data link is in the unstable state and the critical loss-of-lock state; the electromagnetic interference automatic Adaptive behaviors include, but are not limited to, changing flight paths, adjusting the direction of onboard antennas, switching operating channels, and controlling ground transmit power.

An embodiment of the present invention provides an adaptive prediction terminal 924, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in each of the above embodiments of the method for predicting the electromagnetic interference situation of the UAV data link are implemented, for example, steps 101 to 103 shown in FIG. 2 . Alternatively, when the processor executes the computer program, the functions of the modules/units in the foregoing device embodiments, for example, the functions of the modules 110 to 130 shown in FIG. 9 , are implemented.

The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the adaptive prediction terminal 924 .

The adaptive prediction terminal 924 may be a computing device such as a desktop computer, a notebook computer, a palmtop computer, and a cloud server. The drone may include, but is not limited to, a processor, memory. Those skilled in the art can understand that the components of the adaptive prediction terminal 924 given above do not constitute a limitation on the adaptive prediction terminal 924, and may include more or less components than the above structure, or combine some components, or Different components, such as the UAV, may also include input and output devices, network access devices, buses, and the like.

The processor may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf processors Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory may be an internal storage unit of the adaptive prediction terminal 924 , such as a hard disk or a memory of the adaptive prediction terminal 924 . The memory may also be an external storage device of the adaptive prediction terminal 924, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the adaptive prediction terminal 924. , SD) card, flash memory card (Flash Card) and so on. Further, the memory may also include both an internal storage unit of the adaptive prediction terminal 924 and an external storage device. The memory is used to store the computer program and other programs and data required by the drone. The memory may also be used to temporarily store data that has been output or is to be output.

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned system, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

In the embodiments provided by the present invention, it should be understood that the disclosed apparatus/unmanned aerial vehicle and method may be implemented in other manners. For example, the device/unmanned aerial vehicle embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple divisions. Units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated modules/units, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. . Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable media Electric carrier signals and telecommunication signals are not included.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it is still possible to implement the foregoing implementations. The technical solutions described in the examples are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the within the protection scope of the present invention.

Claims (10)

1. The method for predicting the electromagnetic interference situation of the data link of the unmanned aerial vehicle is characterized by comprising the following steps of:

acquiring electromagnetic parameters and environmental interference data of the unmanned aerial vehicle;

inputting the electromagnetic parameters and the environmental interference data of the unmanned aerial vehicle into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold;

and determining the electromagnetic interference situation of the unmanned aerial vehicle data chain according to the environmental interference data and the electromagnetic interference effect threshold value.

2. The drone data link electromagnetic interference situation prediction method of claim 1, wherein prior to the obtaining the drone's electromagnetic parameters and environmental interference data, the method further comprises:

acquiring a training sample, wherein the training sample comprises observation data and input data; the observation data comprises an interference-signal ratio and AGC voltage variation, and the input data comprises electromagnetic parameters and environmental interference data;

standardizing the observation data and the input data in the training sample to obtain a standardized training sample;

establishing an initial prediction model based on a Gaussian process regression method;

and inputting the normalized training samples into the initial prediction model, and training the initial prediction model to obtain the Gaussian process regression prediction model.

3. The method of predicting drone data link electromagnetic interference posture of claim 1, wherein the electromagnetic parameters of the drone include operating signal power, the environmental interference data includes electromagnetic interference frequency; the electromagnetic interference effect threshold comprises an interference signal power threshold and an AGC voltage threshold;

inputting the electromagnetic parameters and the environmental interference data of the unmanned aerial vehicle into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold, wherein the electromagnetic interference effect threshold comprises the following steps:

inputting the working signal power and the electromagnetic interference frequency into the Gaussian process regression prediction model, and outputting corresponding interference-signal ratio and AGC voltage variation when different effects occur in the unmanned aerial vehicle data chain;

determining interference signal power thresholds of the unmanned aerial vehicle data chain in different working states according to corresponding interference-signal ratios and the working signal power when different effects occur in the unmanned aerial vehicle data chain;

and determining AGC voltage threshold values of the unmanned aerial vehicle data chain in different working states according to the AGC voltage variation and the standard AGC voltage corresponding to the unmanned aerial vehicle data chain with different effects.

4. The method of claim 3, wherein the datalink effects include loss of lock and bit errors, and wherein the jamming signal power thresholds include a first jamming signal power threshold, a second jamming signal power threshold, a third jamming signal power threshold, and a fourth jamming signal power threshold;

the determining the interference signal power threshold of the data link of the unmanned aerial vehicle in different working states according to the corresponding interference-to-signal ratio and the working signal power when different effects occur in the data link of the unmanned aerial vehicle comprises:

calculating the product of the corresponding interference-signal ratio and the working signal power when the unmanned aerial vehicle data link has the out-of-lock effect to obtain a first interference signal power threshold; the first interference signal power threshold is an interference signal power threshold when the unmanned aerial vehicle data link enters an out-of-lock state;

calculating the product of the corresponding interference-signal ratio and the working signal power when the error code effect occurs to the data chain of the unmanned aerial vehicle to obtain a second interference signal power threshold value, wherein the second interference signal power threshold value is the interference signal power threshold value when the data chain of the unmanned aerial vehicle enters a critical out-of-lock state from an unstable state;

subtracting a first preset buffer value from the second interference signal power threshold value to obtain a third interference signal power threshold value, wherein the third interference signal power threshold value is an interference signal power threshold value when the unmanned aerial vehicle data chain enters an unstable state from a relatively stable state;

and subtracting a second preset buffer value from the third interference signal power threshold value to obtain a fourth interference signal power threshold value, wherein the fourth interference signal power threshold value is an interference signal power threshold value corresponding to the fact that the unmanned aerial vehicle data chain enters a relatively stable state from a stable state.

5. The method of claim 3, wherein the datalink effects include loss of lock and bit errors, and wherein the AGC voltage thresholds include a first AGC voltage threshold, a second AGC voltage threshold, a third AGC voltage threshold, and a fourth AGC voltage threshold;

according to AGC voltage variation and standard AGC voltage that correspond when different effects appear in the unmanned aerial vehicle data link, confirm the AGC voltage threshold value of unmanned aerial vehicle data link under different operating condition, include:

adding the AGC voltage variation corresponding to the unmanned aerial vehicle data link under the unlocking effect to a standard AGC voltage to obtain a first AGC voltage threshold value, wherein the first AGC voltage threshold value is the AGC voltage threshold value when the unmanned aerial vehicle data link enters the unlocking state;

adding the AGC voltage variation corresponding to the data chain of the unmanned aerial vehicle under the error code effect to a standard AGC voltage to obtain a second AGC voltage threshold value, wherein the second AGC voltage threshold value is the AGC voltage threshold value when the data chain of the unmanned aerial vehicle enters a critical unlocking state from an unstable state;

subtracting a third preset buffer value from the second AGC voltage threshold value to obtain a third AGC voltage threshold value, wherein the third AGC voltage threshold value is an AGC voltage threshold value when the unmanned aerial vehicle data chain enters an unstable state from a relatively stable state;

and subtracting a fourth preset buffer value from the third AGC voltage threshold value to obtain a fourth AGC voltage threshold value, wherein the fourth AGC voltage threshold value is the AGC voltage threshold value when the unmanned aerial vehicle data chain enters a relatively stable state from the stable state.

6. The unmanned aerial vehicle data link electromagnetic interference situation prediction method of any one of claims 1 to 5, the method further comprising:

and determining corresponding anti-interference response measures according to the electromagnetic interference situation of the unmanned aerial vehicle data chain.

7. The unmanned aerial vehicle data link electromagnetic interference situation prediction method of claim 6, wherein the electromagnetic interference situation includes an out-of-lock state, a critical out-of-lock state, an unstable state, a relatively stable state, and a stable state;

the determining of the corresponding anti-interference response measures according to the electromagnetic interference situation where the unmanned aerial vehicle data chain is located includes:

if the unmanned aerial vehicle data chain is in the relatively stable state, generating an abnormal alarm signal of the unmanned aerial vehicle data chain;

if the data link of the unmanned aerial vehicle is in the unstable state and the critical unlocking state, controlling the unmanned aerial vehicle to execute an electromagnetic interference adaptive behavior; the electromagnetic interference adaptive behavior includes, but is not limited to, changing flight path, adjusting airborne antenna direction, switching operating channels, and controlling ground transmit power.

8. The utility model provides an unmanned aerial vehicle data link electromagnetic interference situation prediction device which characterized in that includes:

the electromagnetic data acquisition module is used for acquiring electromagnetic parameters and environmental interference data of the unmanned aerial vehicle;

the threshold value obtaining module is used for inputting the electromagnetic parameters and the environmental interference data of the unmanned aerial vehicle into a Gaussian process regression prediction model to obtain an electromagnetic interference effect threshold value;

and the electromagnetic interference situation determination module is used for determining the electromagnetic interference situation of the unmanned aerial vehicle data chain according to the environmental interference data and the electromagnetic interference effect threshold.

9. An adaptive predictive terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the computer program is executed by the processor.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.

Images