Artificial intelligence based drone telemetry link jamming and suppression system

Abstract

The application provides an unmanned aerial vehicle remote telemetry link interference and suppression system based on artificial intelligence, relates to the unmanned aerial vehicle attitude control technical field, and is characterized in that: the speed disturbance and ionized density disturbance are preprocessed in the measurement module, the normalized disturbance index is output in real time in the prediction module, the multivariate nonlinear optimization algorithm is adopted in the calculation and solving module to synchronously determine the transmission power increment, the key time slot proportion and the link switching strategy, finally, the three types of instructions are issued in parallel in the execution module and the backup takeover is rapidly completed; the multi-factor coupling suppression is realized, and the application requirement of the high-reliability remote telemetry of the canyon unmanned aerial vehicle formation under the high-voltage transmission line is met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle attitude control, in particular to an unmanned aerial vehicle remote telemetry link interference and suppression system based on artificial intelligence. BACKGROUND

[0002] In the canyon terrain under the high-voltage transmission line, the complex terrain shielding, electromagnetic interference and the Doppler effect caused by high-speed motion make the link quality present strong time-varying and nonlinear attenuation characteristics. For this reason, researchers gradually introduce predictive control, Kalman filtering and other algorithms to realize dynamic estimation of environmental interference, and realize real-time adjustment in transmission power and time slot allocation. However, these studies are mostly limited to single parameter optimization or separate consideration of measurement, solution and execution, lacking a full-link coupling suppression idea, making it difficult to balance link robustness and resource utilization efficiency under the dual influence of high ion cluster group distribution change and relative speed disturbance of formation. In addition, the existing scheme often only relies on static threshold prediction or coarse-grained switching strategy when triggering link switching, resulting in high misjudgment rate and long switching delay, which cannot meet the simultaneous optimization requirements of available rate improvement, error rate reduction and recovery time shortening and other multiple indicators.

[0003] In the prior art, a unmanned aerial vehicle interference system and a unmanned aerial vehicle with interference function are disclosed in CN111694371A, which are used to simultaneously control the flight of the host unmanned aerial vehicle and interfere with the non-host unmanned aerial vehicle, so as to realize the flight of the unmanned aerial vehicle while interfering with other unmanned aerial vehicles. The interference module in the unmanned aerial vehicle interference system is used to generate an interference signal; the flight control mainboard is used to receive a control signal and control the flight of the unmanned aerial vehicle; and the radio frequency module is used to switch the wireless channel of the interference signal and the wireless channel of the control signal according to a preset time interval, so that in the same time period, the interference signal can be transmitted through a first wireless channel by using an interference transmitting antenna, and the control signal can be received through a second wireless channel by using a communication receiving antenna, and the control signal is sent to the flight control mainboard, and the frequency bands corresponding to the first wireless channel and the second wireless channel are non-overlapping.

[0004] Although existing researches have proposed various optimization schemes for transmission power adaptive adjustment, time slot resource dynamic allocation and link switching mechanism respectively, an integrated system that integrates the "measurement-prediction-computation-solution-execution" closed-loop link full process has not yet been formed:

[0005] 1. First, traditional measurement modules mostly focus on signal strength (RSSI) or instantaneous bit error rate (BER) monitoring, ignoring the influence of relative speed difference in unmanned aerial vehicle formation on Doppler frequency offset and dynamic link quality decay;

[0006] 2、Secondly, although algorithms such as Kalman filtering can predict the ion cluster group density change online, the prediction value is often lacking in preprocessing and normalization in conventional applications, making it difficult to quantify the synergistic effect of the two types of disturbance indicators in subsequent link scoring and bit error rate prediction; Thirdly, existing nonlinear optimization is limited to single-objective or double-objective fields, and it is difficult to achieve multi-variable and multi-constraint joint solution among the three types of control instructions: transmit power increment, key time slot ratio and backup switching command;

[0007] 3、Finally, the execution module usually only triggers a single radio frequency backup or time slot switching when the threshold is exceeded, and the switching trigger and switching confirmation processes are separated, resulting in a long link recovery time and an imbalance between availability and bit error rate.

[0008] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0009] In view of the deficiencies in the prior art, the present application provides an unmanned aerial vehicle telemetry link interference and suppression system based on artificial intelligence to solve the problems raised in the background art.

[0010] The purpose of the present application is achieved by an unmanned aerial vehicle telemetry link interference and suppression system based on artificial intelligence, applied to a canyon unmanned aerial vehicle formation cruising scene under a high-voltage transmission line, specifically comprising:

[0011] A measurement module for measuring the relative speed difference between each node unmanned aerial vehicle in the unmanned aerial vehicle formation and its adjacent unmanned aerial vehicles, and preprocessing the relative speed difference to generate a normalized speed disturbance indicator;

[0012] A prediction module for real-time acquisition of the ion cluster group density of the node unmanned aerial vehicle at the current time, and online prediction of the ion cluster group density prediction value in the future short time window through the Kalman filtering algorithm, and preprocessing the ion cluster group density prediction value to generate a normalized density disturbance indicator;

[0013] A calculation module for calculating the link score of each node unmanned aerial vehicle according to the speed disturbance indicator, and calculating the bit error rate prediction value according to the density disturbance indicator of each node unmanned aerial vehicle at the current time;

[0014] A solution module for taking the link score and the bit error rate prediction value as input, and using a multivariate nonlinear optimization algorithm to solve the optimal values of the transmit power increment and the key time slot ratio of each node unmanned aerial vehicle to minimize the link quality degradation and the bit error rate;

[0015] The execution module is configured to adjust the transmission power and the key time slot ratio of each node unmanned aerial vehicle in real time according to the transmission power increment and the key time slot ratio parameter output by the solving module, and trigger the adjacent unmanned aerial vehicle link backup takeover when the link score or the error code rate prediction value exceeds the preset threshold.

[0016] Further, the measurement module comprises a measurement unit and a fusion calculation unit.

[0017] The measurement unit comprises a GNSS receiver and a three-axis inertial measurement unit, which are configured to acquire the GNSS speed and the body acceleration vector of the node unmanned aerial vehicle, respectively.

[0018] The fusion calculation unit adopts a first-order Kalman filtering algorithm to fuse the GNSS speed , the body acceleration vector and the IMU integrated speed , and obtain the instantaneous speed of the node unmanned aerial vehicle i.

[0019] The measurement module is further configured to calculate the relative speed difference between any adjacent node unmanned aerial vehicles i and j, and express it through a two-norm operation.

[0020] The relative speed difference is normalized to generate a normalized speed disturbance index , the value range of which is limited in the interval [0, 1].

[0021] The closer to 0, the smaller the relative disturbance between the adjacent node unmanned aerial vehicles i and j, and the lower the redundant link resource allocation.

[0022] The closer to 1, the stronger the relative disturbance between the adjacent node unmanned aerial vehicles i and j, and the power and time slot compensation should be triggered preferentially.

[0023] Further, a threshold of the speed disturbance index is set, which is used for decision-making of subsequent link scheduling.

[0024] When , it indicates that the relative motion disturbance between the adjacent node unmanned aerial vehicles i and j is serious.

[0025] When , it indicates that the existing link parameters are maintained.

[0026] Further, the prediction module comprises an on-board micro electrochemical cluster sensor, which is configured to collect the ion cluster density around the node unmanned aerial vehicle in real time.

[0027] The prediction module will measure the ionized cluster group density at the current time As a prediction initial value ;

[0028] The prediction module calculates the ionized cluster group density prediction value in the future short time window By Kalman filtering algorithm ;

[0029] The prediction module normalizes the ionized cluster group density prediction value Generate normalized density disturbance index The value range is limited in the interval [0,1];

[0030] The prediction threshold is set to , used to determine whether to trigger subsequent link intervention; When

[0031] , output the intervention signal; When

[0032] , maintain the current link parameters. Further: the calculation module includes link score calculation unit and bit error rate prediction calculation unit, for generating quantitative evaluation value according to speed disturbance index

[0033] And density disturbance index ;

[0034] The link score calculation unit inputs the speed disturbance index of adjacent unmanned aerial vehicles ; the bit error rate prediction calculation unit inputs the density disturbance index ;

[0035] The link score calculation unit is used to calculate the link score of each node unmanned aerial vehicle , wherein The speed disturbance index of adjacent unmanned aerial vehicles Is averaged and linearly mapped to the interval (0,1).

[0036] Further: the bit error rate prediction calculation unit performs secondary mapping based on the density disturbance index Generate bit error rate prediction value Of node unmanned aerial vehicle i in the future short time window ;

[0037] The link score And the bit error rate prediction value Characterized as a vector . ​

[0038] Further, the solving module includes an optimization calculation unit and a result output unit, configured to perform nonlinear optimization based on the input link score and the error rate prediction value and output an optimal solution; specifically including:

[0039] The optimization calculation unit receives vector input through shared memory , and outputs which is then issued to the power control and time slot scheduling module by the result output unit;

[0040] is the transmission power increment of the node UAV i; is the key time slot proportion of the node UAV i;

[0041] The optimization calculation unit performs joint optimization on the transmission power increment and the key time slot proportion of all node UAVs based on nonlinear target optimization, to finally obtain the optimal solution of and ; ;

[0042] The result output unit issues the optimal solution of the solving to the communication controller of each node UAV i.

[0043] Further, the execution module includes a configuration issuing unit and a backup switching unit, configured to respectively issue the transmission power increment and the key time slot proportion and perform link backup switching when the trigger condition is met;

[0044] The configuration issuing unit reads the optimal solution from the shared memory of the solving module , and the backup switching unit listens to the link quality and error rate alarm.

[0045] Further, the configuration issuing unit calls the radio frequency front-end firmware API to set the actual transmission power and the key time slot proportion of the node UAV i;

[0046] When the link score or the error rate prediction value exceeds the preset threshold, the backup switching unit generates a link switching command;

[0047] The preset thresholds of the link score and the error rate prediction value are respectively and ;

[0048] If or , the switching event flag is set; otherwise, the event flag is cleared;

[0049] The backup switching unit instructs the adjacent unmanned aerial vehicle j to take over the link in relay mode after the event flag is set.

[0050] Further, the response delay of the backup switching unit is inversely proportional to the trigger threshold strictness;

[0051] The trigger threshold strictness is the sum of the relative difference of the link score below the minimum allowed level and the relative difference of the error rate prediction value exceeding the maximum allowed value.

[0052] The greater the trigger threshold strictness, the more serious the over-standard degree of the link score or the error rate, and the smaller the required response delay.

[0053] Compared with the prior art, the beneficial effects of the present application are:

[0054] The present application preprocesses the speed disturbance and ionized density disturbance in the measurement module, outputs the normalized disturbance index in real time in the prediction module, and synchronously determines the transmission power increment, key time slot proportion and link switching strategy in the calculation and solving module by using a multivariate nonlinear optimization algorithm, finally parallelly issues the three types of instructions in the execution module and quickly completes the backup takeover; multi-factor coupling suppression is realized, and the application requirements of high-reliability telemetry of canyon unmanned aerial vehicle formation under high-voltage transmission lines are met. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0056] Figure 1 It is a schematic diagram of the overall system module of the present application.

[0057] Figure 2 It is a schematic diagram of the application of the present application to canyon unmanned aerial vehicle formation cruising under high-voltage transmission lines. DETAILED DESCRIPTION

[0058] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0059] Embodiment one:

[0060] Please refer to Figure 1 and Figure 2 , the present application provides a technical solution:

[0061] The unmanned aerial vehicle remote telemetry link interference and suppression system based on artificial intelligence is applied to the canyon unmanned aerial vehicle formation cruising scene under the high-voltage transmission line, and specifically includes:

[0062] The measurement module is used to measure the relative speed difference between each node unmanned aerial vehicle in the unmanned aerial vehicle formation and its adjacent unmanned aerial vehicle, and to preprocess the relative speed difference to generate a normalized speed disturbance index.

[0063] Further description: the measurement module includes a measurement unit and a fusion calculation unit.

[0064] 1.1) The measurement unit includes a GNSS receiver and a three-axis inertial measurement unit (IMU) for acquiring the GNSS speed and body acceleration vector of the node unmanned aerial vehicle, respectively; specifically including:

[0065] GNSS receiver: collect the longitude and latitude and ground speed of the node unmanned aerial vehicle after differential correction , update frequency 1Hz, positioning accuracy ±0.5m.

[0066] Three-axis inertial measurement unit IMU: measure the body acceleration vector , sampling frequency 200Hz, acceleration accuracy ±0.02m / s².

[0067] The GNSS and IMU are connected to the flight control mainboard through the SPI bus, and the data synchronization error is ≤1ms, which ensures the data consistency of the subsequent fusion calculation.

[0068] 1.2) The fusion calculation unit adopts a first-order Kalman filter algorithm to fuse the GNSS speed , the body acceleration vector and the IMU integral speed to obtain the instantaneous speed of the node unmanned aerial vehicle i; the specific calculation logic includes:

[0069] The integral speed is calculated by the formula:

[0070]

[0071] In the formula, is the acceleration amplitude measured by the IMU;

[0072] is the IMU sampling period; in this embodiment second;

[0073] The Kalman filter fusion step is as follows:

[0074]

[0075] wherein, is the filter gain, which depends on the covariance ratio of GNSS and IMU; is the instantaneous speed of the node UAV i;

[0076] When increases, the GNSS speed is more trusted; when decreases, the IMU data is more trusted;

[0077] The least square method is used online to estimate the covariance matrix, so that the fusion speed mean square error is minimized, and .

[0078] 1.3) The measurement module is further used to calculate the relative speed difference of any adjacent node UAV i, j , expressed by the two norm operation; the specific expression logic includes:

[0079]

[0080] wherein, , is the instantaneous speed fused by step 1.2); is the two norm operation;

[0081] When the relative speed difference increases from 0 to the maximum theoretical speed difference , it indicates that the relative motion disturbance of the two UAVs is from nothing to strong;

[0082] When the relative speed difference increases by 1 m / s, it causes the link score to decrease , which is used for subsequent link optimization.

[0083] 1.4) The relative speed difference is normalized to generate a normalized speed disturbance index , whose value range is limited in the interval [0, 1]; the specific normalization step is as follows:

[0084]

[0085] wherein, is the maximum theoretical speed difference preset by the system, and in the embodiment , the value is 20 m / s;

[0086] When , ; when Time, ;

[0087] The closer to 0, the smaller the relative disturbance of adjacent node drones i, j, which can reduce the allocation of redundant link resources;

[0088] The closer to 1, the stronger the relative disturbance of adjacent node drones i, j, which should trigger power and time slot compensation first; the higher the demand for "double compensation" of link backup and power time slot;

[0089] 1.5) Set the speed disturbance index Threshold for subsequent link scheduling decision; the specific implementation steps are as follows:

[0090] This embodiment sets It should be noted that Based on fuzzy analytic hierarchy process (FAHP) or using the average median of historical data to determine, not described in detail;

[0091] When , it indicates that the relative motion disturbance of adjacent node drones i, j is serious;

[0092] When , it indicates that the existing link parameters are maintained.

[0093] Prediction module: for real-time collection of ion cluster group density of node drone at current time, and online prediction of ion cluster group density prediction value in future short time window through Kalman filtering algorithm, and preprocessing of ion cluster group density prediction value to generate normalized density disturbance index;

[0094] Further explanation: 2.1) The prediction module includes an onboard micro electrochemical cluster group sensor for real-time collection of ion cluster group density around the node drone ; the specific implementation steps are as follows:

[0095] A micro electrochemical cluster group sensor with a range of 0-10 6 ions / cm³, typical measurement error ±5%.

[0096] The micro electrochemical cluster group sensor is fixed on the top front edge of the node drone to ensure stable sampling airflow and avoid the influence of body disturbance.

[0097] Connected to the flight control mainboard through I²C bus, sampling frequency 1Hz, data frame synchronization delay ≤10ms.

[0098] The original measured ion cluster group density Denoising is performed by using 3-point moving average filter to ensure that the data jitter amplitude is less than or equal to 2%.

[0099] 2.2) The prediction module measures the ion cluster group density at the current time as the initial value of prediction The specific implementation includes:

[0100]

[0101] In the formula, is the initial value of the predicted state for Kalman filtering;

[0102] After receiving each new sampling data, the prediction state is updated immediately to ensure that the prediction state is consistent with the latest environmental conditions.

[0103] 2.3) The prediction module calculates the ion cluster group density prediction value in the future short time window by using Kalman filtering algorithm; the specific implementation steps are as follows:

[0104]

[0105] In the formula, is the Kalman gain, which is adjusted online according to the sensor noise covariance R and the process noise covariance Q;

[0106] When tends to 1, the prediction result is closer to the real-time measurement; when tends to 0, the prediction result is smoother;

[0107] is the prediction time delay, which is taken as 0.5 s in the embodiment ;

[0108] 2.4) The standard Kalman gain update formula is used:

[0109]

[0110]

[0111] wherein is the prior error covariance, and the posterior error covariance is

[0112] After each is obtained, the Kalman gain is updated according to , and is calculated again;

[0113] 2.5) The prediction module updates the ion cluster group density prediction value The normalized density disturbance index is generated by normalization processing , whose value range is limited in the interval [0, 1]; the implementation is as follows:

[0114]

[0115] In the formula, is the upper limit of the sensor range; in this embodiment , The closer to 0, the lower the environmental interference; The closer to 1, the closer the interference density to the upper limit of the range.

[0116] The prediction threshold of is set to , which is used to determine whether to trigger subsequent link intervention; in this embodiment ; it should be noted that is determined based on fuzzy analytic hierarchy process (FAHP), or the average median of historical data, which is not described here;

[0117] When , the intervention signal is output;

[0118] When , the current link parameters are maintained.

[0119] The calculation module is used to calculate the link score of each node UAV according to the speed disturbance index, and calculate the error rate prediction value according to the density disturbance index of each node UAV at the current time;

[0120] Further description: the calculation module includes a link score calculation unit and an error rate prediction calculation unit, which are used to respectively generate a quantitative evaluation value according to the speed disturbance index and the density disturbance index ;

[0121] In this embodiment, a dual-core ARM Cortex-A53 microprocessor is used, the main core is responsible for link score calculation, the auxiliary core is responsible for error rate prediction calculation, and the two cores exchange intermediate data through shared memory, and the calculation delay is ≤5ms.

[0122] Two independent tasks are deployed in the flight control real-time operating system (RTOS), and the task priority is link score > error rate prediction, so as to ensure that the score is given priority when the speed disturbance is severe.

[0123] The link score calculation unit inputs the speed disturbance index of the adjacent UAV ; the error rate prediction calculation unit inputs the density disturbance index ;

[0124] The link score calculation unit is configured to calculate a link score of each node UAV wherein by the speed disturbance index of the adjacent UAV averaging and linearly mapping to the interval (0, 1) to obtain; the specific acquisition steps are as follows:

[0125]

[0126] wherein, is a set of adjacent UAVs of the node UAV i, and the total number of UAVs in the set of adjacent UAVs is N;

[0127]

[0128] wherein, when tends to 0, tends to 1;

[0129] when tends to 1, tends to 0;

[0130] The bit error rate prediction calculation unit is configured to calculate a bit error rate prediction value of the node UAV i in a future short time window based on the density disturbance index ; the specific implementation steps are as follows:

[0131] The secondary mapping formula is defined as ; wherein, the output ;

[0132] when tends to 0, the bit error rate prediction value tends to 0;

[0133] when tends to 1, the bit error rate prediction value tends to 1; and the secondary mapping has greater sensitivity to high interference.

[0134] The secondary mapping of the embodiment is simple and feasible, highlights the trend of sharp rise of the bit error rate under high-density interference, and has low operation resource consumption on hardware.

[0135] The link score and the bit error rate prediction value are represented in vector form as .

[0136] ​Solving module: for link score and bit error rate prediction value as input, using multivariate nonlinear optimization algorithm, solving each node unmanned aerial vehicle transmission power increment and the optimal value of key time slot ratio, to minimize the link quality degradation and bit error rate;

[0137] Further description: the solving module includes an optimization calculation unit and a result output unit, for performing nonlinear optimization based on the input link score and bit error rate prediction value and outputting the optimal solution; specifically including:

[0138] The optimization calculation unit of the embodiment adopts a DSP processor with a main frequency of 1.2GHz, and integrates a floating point operation unit to ensure that the optimization iteration delay is ≤50ms;

[0139] An optimization task and an output task are deployed in the flight control RTOS, and the optimization task has a higher priority than the output task;

[0140] The optimization calculation unit receives vector input through shared memory , and outputs to the power control and time slot scheduling module by the result output unit;

[0141] is the transmission power increment of the node unmanned aerial vehicle i; is the key time slot ratio of the node unmanned aerial vehicle i;

[0142] The optimization calculation unit performs joint optimization on the transmission power increment and the key time slot ratio of all node unmanned aerial vehicles based on nonlinear objective optimization, to finally obtain the optimal solution of and ; the specific logic includes:

[0143] The nonlinear objective optimization function is:

[0144]

[0145] In the formula: is the maximum transmission power increment allowed by the system; in the embodiment ; , , , is the non-negative weight coefficient of the corresponding parameter, and the example value is =0.5、 =0.3、 =0.1、 =0.1.

[0146] If the link score decreases, then increases, driving or​ increase;

[0147] If increases, the driving resource is also increased; increases, the driving resource is also increased;

[0148] If or increases, the respective penalty term , increases, which restricts excessive allocation.

[0149] The optimization calculation unit adopts a sequential quadratic programming (SQP) algorithm to solve the above-mentioned nonlinear programming problem to balance the solution accuracy and real-time performance; the specific implementation steps include:

[0150] Set all and initial values to 0.1x the maximum value;

[0151] The SQP iteration content is as follows:

[0152] Linearize the objective and constraints at the current point; solve the quadratic subproblem to obtain the step size and direction;

[0153] Update the variables until the objective function converges or the iteration number reaches the maximum value of 20 times;

[0154] When the objective function decreases , early convergence is achieved;

[0155] The optimization calculation unit imposes the following constraints on each variable during the solution process:

[0156]

[0157]

[0158]

[0159] For the transmit power increment constraint: through the projection operation, ensure that is maintained in [0, 20] dBm after each iteration;

[0160] For the key time slot proportion constraint: add a linear inequality to the quadratic subproblem;

[0161] The result output unit sends the solved optimal solution to the communication controller of each node UAV i. The implementation is: convert to a floating-point number, to a percentage;

[0162] Sent by CAN bus in a 10Hz rate loop, each frame contains single-node UAV i's ;

[0163] Each node UAV receives the backward optimization calculation unit returns the confirmation message, if the communication fails, keep the last parameter.

[0164] The execution module: for according to the solving module output of the transmission power increment and key time slot ratio parameters, real-time adjustment of each node UAV's transmission power and key time slot ratio, and in the link score or error rate prediction value exceeds the preset threshold, trigger adjacent UAV link backup takeover.

[0165] Further explanation: the execution module includes configuration unit and backup switching unit, for respectively issuing transmission power increment and key time slot ratio and in the trigger condition is met when the execution link backup switching; implementation includes:

[0166] Configuration unit and backup switching unit are running in ARM Cortex-M4 real-time controller;

[0167] In the flight control RTOS is divided into two task chain-configuration task and switching task, task through the event flag communication;

[0168] Configuration unit reads the optimal solution from the solving module shared memory , backup switching unit listens to the link quality and error rate alarm;

[0169] Further, the configuration unit calls the radio frequency front-end firmware API to set the actual transmission power of node UAV i And key time slot ratio ; Implementation is:

[0170]

[0171] In the formula, Baseline transmission power, the value of the embodiment 10dBm;

[0172] Directly pass into the firmware API, converted to percentage duty cycle;

[0173] Immediately after each optimization is completed, API is called, and is issued repeatedly at a rate of 100Hz, to ensure that the firmware parameters and algorithm output are synchronized.

[0174] Further, the backup switching unit generates a link switching command when the link score Or error rate prediction value Exceeds the preset threshold; Implementation is: ​

[0175] Setting link score with the preset threshold value of the error rate prediction value respectively and ; the embodiment ;

[0176] If or , set the switching event flag; otherwise, clear the event flag; use the event group API of the RTOS to detect the flag, and ensure that the detection period is less than or equal to 10 ms.

[0177] Further, the backup switching unit instructs the adjacent unmanned aerial vehicle j to take over the link in the relay mode after the event flag is set, and completes the switching within 50 ms; the implementation is as follows:

[0178] The switching command format is ;

[0179] Send within 0-10 ms after receiving the switching event flag;

[0180] Start the relay firmware module of the adjacent unmanned aerial vehicle j within 10-40 ms; confirm the link access and switch the control signal routing within 40-50 ms;

[0181] The adjacent unmanned aerial vehicle j sends within 50 ms, otherwise retry once.

[0182] Further, the response delay of the backup switching unit is inversely proportional to the strictness of the trigger threshold value.

[0183] The strictness of the trigger threshold value is the sum of the relative difference of the link score being lower than the minimum allowed level and the relative difference of the error rate prediction value exceeding the maximum allowed value.

[0184] The greater the strictness of the trigger threshold value, the more serious the exceeding degree of the link score or the error rate, and the smaller the required response delay.

[0185] The specific implementation is as follows:

[0186] The strictness of the trigger threshold value is defined as follows:

[0187]

[0188] In the formula, if , the first term >0;

[0189] If , the second term >0;

[0190] Trigger threshold strictness ;

[0191] The response time delay function is as follows:

[0192]

[0193] In the formula: is the backup switching response time delay; is the maximum allowed response time delay; is the response sensitivity adjustment coefficient; is the trigger threshold over-standard degree;

[0194] The embodiment is valued at 50 ms; is initially valued at 1;

[0195] When is closer to 0, is closer to ; when is larger, is smaller; embodying a more rapid link switching;

[0196] Through response time delay function mapping, the system can adaptively adjust the backup switching time delay according to the over-standard severity, guaranteeing minimal resource consumption in light over-standard and prioritizing communication reliability in severe over-standard; the response sensitivity adjustment coefficient controls the steepness of the mapping curve, which can be optimized according to hardware switching capacity and energy consumption budget.

[0197] Embodiment two:

[0198] In a certain canyon transmission line area, six drones of the same model (aircraft A-F) are arranged, each aircraft integrating a measurement module, a solving module, and an execution module firmware. The measurement module collects link scores and error rate prediction values in real time; the solving module outputs:

[0199] transmit power increment ; key time slot proportion ;

[0200] backup switching command : or .

[0201] The execution module includes a configuration issuing unit and a backup switching unit, and is run on an ARM Cortex-M4 controller, and parallel processing is achieved by using a flight control RTOS task chain. The radio frequency front-end API is called, and is repeatedly issued through the CAN bus at 100 Hz, the API response delay is ≤1 ms, and the synchronization error is ≤2 ms. The switching process can be completed within 50 ms through joint debugging → relay starts → handshake.

[0202] Before flight, six aircrafts are vertically patrolled at a distance of 50 m in formation, at a height of 30 m, and cross a 200 m cliff to simulate a high ionization and motion disturbance environment. A detection system is set up on the ground, and .

[0203] Joint command issuing verification:

[0204] A randomly generated dBm and is sequentially issued to each node unmanned aerial vehicle, and is issued when the trigger condition is met.

[0205] Verify the correctness of API calling, CAN frame synchronization and switching command.

[0206] In normal cruising, the ground equipment is used to dynamically reduce the signal or inject ionization interference, so that or tends to or exceeds the limit, respectively.

[0207] Record the time when each trigger occurs, the relay starts and acknowledgement time of the adjacent unmanned aerial vehicle j, and calculate the overall backup switching response delay .

[0208] Repeat the whole process 10 times, take the average value, and observe the response delay distribution under different over-limit degrees; at the same time, monitor the coupling changes of , and : when increases by 10%, the average increases by 0.05; when it decreases by 5%, the switching probability increases by 15%. In order to speed up the response, the response sensitivity adjustment coefficient is adjusted to 1.2.

[0209] Table 1 Feasibility study of the execution module:

[0210]

[0211] Through comparison with the traditional single radio frequency switching scheme, the following average indicators are obtained:

[0212] For link availability:

[0213] Traditional scheme: 98.7%; the present scheme: 99.3%, increase 0.6%.

[0214] For the bit error rate:

[0215] Traditional scheme: 0.0021; the present scheme: 0.00087, decrease 59%.

[0216] For the backup switching corresponding delay:

[0217] Traditional scheme: 60ms; the present scheme: 41.2ms, shorten 31%.

[0218] The above-mentioned increase all exceed the design target of available rate ≥0.5%, BER decrease ≥50%, recovery time shorten ≥30%, fully prove that the present application has significant innovation and practicality by the linkage optimization of power, time slot and switching instruction, compared with the existing scheme.

[0219] The "link backup and power / time slot adaptive scheduling based on formation relative speed coupling and atmospheric ion cluster density prediction" technical route is selected, which has the following advantages:

[0220] Dual compensation of motion disturbance and environmental disturbance: considering the formation speed difference and ion cluster density as two major interference sources;

[0221] Predictive pre-backup: using Kalman filter to predict short-time ion density to realize second-level pre-backup link;

[0222] Linkage power + time slot + link switching: an optimization model simultaneously generates three types of control instructions to ensure link stability.

[0223] It should be noted that: the label "1" in the attached Figure 2 indicates the schematic of the three types of control instructions; the label "2" indicates the node unmanned aerial vehicle.

[0224] It should be noted that: all the calculation formulas in the present application file use regression analysis including but not limited to machine learning algorithms to deeply analyze the collected relevant parameters, identify their natural trend and mutual relationship. Professional software such as Python's Scikit-learn library or R language is used to automatically generate mathematical models matching the data. Then, the model performance is objectively evaluated through cross-validation and other methods, and combined with continuous feedback and optimization to ensure that the created formula truly reflects the inherent law of the data, thereby ensuring its effectiveness and accuracy. In all the calculation formulas in the present application, the parameters in each formula are processed by consistent range of dimensionless to ensure that different physical quantities are compared on the same scale; the dimensionless technology means include but are not limited to Min-Max Normalization, Z-Score standardization;

[0225] The technical solution of the present application can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a ROM, a RAM, a FLASH, a hard disk, or an optical disc, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method of various embodiments of the present application.

[0226] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be specifically embodied in any computer readable medium for use by or in connection with an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch instructions from the instruction execution system, apparatus or device and execute the instructions, or in conjunction with such an instruction execution system, apparatus or device. For the purpose of this specification, a "computer readable medium" can be any device that can contain, store, communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device, or in conjunction with such an instruction execution system, apparatus or device.

[0227] The above description of the embodiments is only for the purpose of helping to understand the method of the present application and its core idea. It should be noted that for those skilled in the art, without departing from the principles of the present application, a number of improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. An artificial intelligence-based unmanned aerial vehicle telemetry link interference and suppression system applied to a canyon unmanned aerial vehicle formation cruising scene under a high-voltage transmission line, characterized in that, Specifically comprising: a measurement module for measuring the relative speed difference between each node UAV in the UAV formation and its adjacent UAV, and preprocessing the relative speed difference to generate a normalized speed disturbance index; the measurement module comprises a measurement unit and a fusion calculation unit; The measurement unit includes a GNSS receiver and a three-axis inertial measurement unit for acquiring a GNSS velocity and a body acceleration vector of the node drone, respectively The fusion calculation unit adopts a first-order Kalman filtering algorithm to fuse GNSS speed , body acceleration vector and IMU integrated speed to obtain the instantaneous speed of the node unmanned aerial vehicle i ; The measurement module is further configured to calculate a relative speed difference of any adjacent nodes, unmanned aerial vehicles i, j and express it through a two-norm operation. to the relative speed difference is normalized to generate a normalized speed disturbance index whose value range is limited in the interval [0, 1]; The closer to 0, the smaller the relative disturbance of adjacent nodes UAV i, j, which can reduce the allocation of redundant link resources; The closer to 1, the stronger the relative disturbance of the adjacent nodes UAV i, j, and the power and time slot compensation should be triggered in priority. a prediction module for collecting the ionized ion cluster group density of the node UAV at the current time in real time, and predicting the ionized ion cluster group density prediction value in the future short time window through the Kalman filtering algorithm, and preprocessing the ionized ion cluster group density prediction value to generate a normalized density disturbance index; a calculation module for calculating the link score of each node UAV according to the speed disturbance index, and calculating the bit error rate prediction value according to the density disturbance index of each node UAV at the current time; a solving module for taking the link score and the bit error rate prediction value as input, using a multivariate nonlinear optimization algorithm to solve the optimal value of the transmission power increment and the key time slot ratio of each node UAV to minimize the link quality degradation and the bit error rate; the solving module comprises an optimization calculation unit and a result output unit for performing nonlinear optimization based on the input link score and bit error rate prediction value and outputting the optimal solution; specifically comprising: The optimization computing unit receives vector input through shared memory , output Then the result output unit issues to the power control and time slot scheduling module is the link score of node drone i; N is the total number of node drones; is the bit error rate prediction value for the node drone i in the future short time window of future. is the transmit power increment of the node drone i; is the key time slot ratio of the node drone i; The optimization calculation unit jointly optimizes the transmission power increment of all nodes of the unmanned aerial vehicle and the key time slot proportion based on nonlinear target optimization, to finally obtain and optimal solution ; The result output unit outputs the optimal solution The communication controller of each node UAV i is issued. an execution module for adjusting the transmission power and key time slot ratio of each node UAV in real time according to the transmission power increment and key time slot ratio parameters output by the solving module, and triggering the adjacent UAV link backup takeover when the link score or the bit error rate prediction value exceeds the preset threshold.

2. The artificial intelligence based unmanned vehicle telemetry link jamming and suppression system of claim 1, wherein: Setting a speed perturbation indicator threshold value for deciding subsequent link scheduling; When , it indicates that the relative motion disturbance of adjacent nodes UAV i, j is serious; When maintain the existing link parameters.

3. The artificial intelligence-based unmanned aerial vehicle telemetry link jamming and mitigation system of claim 2, wherein: The prediction module comprises an on-board micro-electrochemical cluster sensor for real-time acquisition of the density of ionized clusters around the node drone ; The prediction module will predict the ion cluster group density at the next time point based on the ion cluster group density measured at the current time point As the prediction initial value ; The prediction module calculates the ion cluster group density prediction value in a future short time window through a Kalman filtering algorithm ;​ The prediction module predicts the ion cluster group density value The normalized density disturbance index is generated by normalization processing The value range is limited in the interval [0, 1]. Setting the prediction threshold to for determining whether to trigger a subsequent link intervention; When an intervention signal is output; When the current link parameters are maintained.

4. The artificial intelligence-based UAV telemetry link jamming and mitigation system of claim 3, wherein: The computing module comprises a link score computing unit and a bit error rate prediction computing unit, which are used for respectively generating a quantified evaluation value according to the speed disturbance index and the density disturbance index . The link score calculation unit inputs the speed perturbation index of the adjacent drone The bit error rate prediction calculation unit inputs the density perturbation index The bit error rate prediction calculation unit inputs the density perturbation index The link score calculation unit is configured to calculate a link score of each node drone wherein by averaging the speed perturbation indicators of the neighboring drones and linearly mapping to the interval (0, 1) gives 5. The artificial intelligence-based unmanned aerial vehicle telemetry link jamming and mitigation system of claim 4, wherein: The error rate prediction calculation unit is based on a density perturbation index Performing secondary mapping, generating node drone i in the future short time window Error rate prediction value ; Link scores are calculated with a bit error rate prediction value characterized in vector form as .

6. The artificial intelligence-based unmanned aerial vehicle telemetry link jamming and mitigation system of claim 5, wherein: the execution module comprises a configuration issuing unit and a backup switching unit for issuing the transmission power increment and key time slot ratio respectively and executing link backup switching when the trigger condition is met; The configuration issuing unit reads the optimal solution from the solving module shared memory The backup switching unit monitors the link quality and the bit error rate alarm.

7. The artificial intelligence-based unmanned aerial vehicle telemetry link jamming and mitigation system of claim 6, wherein: The configuration issuing unit calls a radio frequency front-end firmware API to set the actual transmission power of the node unmanned aerial vehicle i And key time slot proportion ; The backup switching unit performs link scoring. Or predicted bit error rate When the preset threshold is exceeded, a link switching command is generated; Setting link score with the preset threshold values of the error rate prediction values are and respectively; If or then set the switch event flag; otherwise clear the event flag; the backup switching unit instructs the adjacent UAV j to take over the link in relay mode after the event flag is set.

8. The artificial intelligence-based unmanned aerial vehicle telemetry link jamming and mitigation system of claim 7, wherein: The response delay of the backup switching unit is inversely proportional to the severity of the trigger threshold value; The severity of the trigger threshold value is the sum of "the relative difference of the link score below the minimum allowed level" and "the relative difference of the bit error rate prediction value exceeding the maximum allowed value"; The greater the severity of the trigger threshold value, the more serious the link score or bit error rate exceeds the standard, and the smaller the required response delay.

Images