Unmanned aerial vehicle automatic positioning and navigation system based on AI

Abstract

The invention discloses an AI-based unmanned aerial vehicle automatic positioning and navigation system, and the system comprises an unmanned aerial vehicle body which obtains a starting point coordinate through a navigation module by manually inputting a terminal point coordinate and a planned flight time length value t, flies to the terminal point coordinate at a flight speed value V1 and a flight height value H1 from the starting point coordinate, automatically completes a flight task, and automatically judges a return flight; and the monitoring unit is used for acquiring an initial electric quantity value Q of the unmanned aerial vehicle body, transmitting the initial electric quantity value to the coordinate unit, monitoring the output power of the storage battery in real time during flight, and generating a feedback signal and transmitting the feedback signal to the correction unit when abnormal output power is generated during flight. The problems that when an existing unmanned aerial vehicle automatic positioning navigation system is used, the endurance problem of the unmanned aerial vehicle is not considered, and the unmanned aerial vehicle cannot return or even falls in the flight process in the actual flight process are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and specifically to an AI-based automatic positioning and navigation system for unmanned aerial vehicles. Background Art

[0002] In the prior art, common civilian unmanned aerial vehicles often require users to cooperate with cameras and fly and move them manually through remote control. When approaching the flight end point, fine-tuning is required to make it reach the appropriate position. At the same time, when retrieving the unmanned aerial vehicle, remote control is required again for retrieval. The operation is relatively cumbersome and not flexible enough, and it takes a relatively long time.

[0003] In the invention patent with the application number CN202311243088.5, an automatic positioning and navigation method and system for an AI unmanned aerial vehicle are disclosed, including: a vision module, a GPS positioning module, a data storage module, a command input module, a main control module, and a flight control module; the designed automatic positioning and navigation system facilitates the automatic positioning and navigation of the unmanned aerial vehicle. At the same time, after the unmanned aerial vehicle completes its work, it can return to the flight starting point by itself, realizing the functions of automatic navigation flight and return of the unmanned aerial vehicle, so that the unmanned aerial vehicle can perform flight operations conveniently and flexibly.

[0004] Although the automatic positioning and navigation method and system of the unmanned aerial vehicle have the above advantages, in actual use, there are still certain drawbacks: since the system only identifies and judges the position of the unmanned aerial vehicle itself, but does not consider the endurance problem of the unmanned aerial vehicle, and the unmanned aerial vehicle is autonomously controlled by the system during use. If the endurance is insufficient and the system continues to execute the flight, it is easy to cause the unmanned aerial vehicle to be unable to return autonomously, and even cause the problem of the unmanned aerial vehicle crashing during flight. Therefore, it is necessary to improve the deficiencies of the prior art. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides an AI-based automatic positioning and navigation system for unmanned aerial vehicles, which solves the problem that when the existing automatic positioning and navigation system of unmanned aerial vehicles is used, the endurance problem of the unmanned aerial vehicle is not considered, resulting in the unmanned aerial vehicle being unable to return during actual flight, and even crashing during flight.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: An AI-based automatic positioning and navigation system for unmanned aerial vehicles, including: An unmanned aerial vehicle body, by manually inputting the end point coordinates and the planned flight duration value t, obtaining the starting point coordinates through the navigation module, and then flying from the starting point coordinates to the end point coordinates at a flight speed value V1 and a flight height value H1, and automatically completing the flight task and automatically judging the return flight; The monitoring unit obtains the initial power value Q of the UAV body, transmits the initial power value to the coordinate unit, and monitors the output power of the battery in real time during flight. When an abnormal output power occurs during flight, a feedback signal is generated and transmitted to the correction unit. Then, the abnormal output power is analyzed, and the abnormal output data Yi in the abnormal output power is transmitted to the verification unit; The coordinate unit forms a three-dimensional space coordinate system based on the longitude and latitude coordinates, dimensions, and the height of the sea level. Taking the coordinates of the UAV body itself as the starting coordinates, and planning a flight route that satisfies the power consumption value less than Q3 according to the starting coordinates and the input end coordinates, obtaining the distance value D of the flight route and transmitting it to the monitoring unit; The verification unit is used to receive the abnormal output data Yi transmitted by the monitoring unit and analyze the abnormal output data Yi; The correction unit receives the feedback signal transmitted by the monitoring unit, obtains the current coordinate value of the UAV body, and obtains the information of the test parameter chart to adjust the current flight height value H1 and flight speed value V1 of the UAV body.

[0007] Preferably, the specific determination method for whether there is an abnormal output power is as follows: Obtain the actual output power value P1 corresponding to the flown distance value D1 of the UAV body at the flight speed value V1 and flight height value H1; Obtain the historical data of the output power P of the UAV body at different flight speeds V and flight heights H, and obtain the standard output power value P2 corresponding to the flight speed V1 and flight height H1 of the UAV body according to the historical data; Judge whether P2 - 0.3P2 ≤ P1 ≤ P2 + 0.3P2 is satisfied; If it is satisfied, it indicates that the power consumption of the UAV body is normal.

[0008] Preferably, when P1 < P2 - 0.3P2, there is an abnormal power monitoring. When P1 > P2 + 0.3P2, then P1 is marked as an abnormal output power, and at the same time, a feedback signal is generated and transmitted to the correction unit. Then, the abnormal output power is analyzed, and an analysis signal is generated based on the analysis result and transmitted to the UAV body and the verification unit.

[0009] Preferably, the specific acquisition method of the standard output power value P2 is as follows: Obtain the flight data that meets the flight height value of H1 at different times of the historical data; Then, based on the flight data with the flight height value of H1, obtain the flight data with the flight speed meeting V1, and generate a historical set (V1, H1); Based on the historical set (V1, H1), obtain its corresponding historical output power set, generate a coordinate graph according to the historical output power set, and then obtain the standard output power value P2 through linear fitting. The standard output power value P2 represents the typical value of the output power at the flight speed value V1 and the flight height value H1.

[0010] Preferably, the specific analysis method for abnormal output power is as follows: Based on equal time differences, obtain j time periods for the flight duration corresponding to flying at a constant speed with the flight speed value V1 during the flown distance, where j = 1, 2, 3,......m, and obtain n time nodes based on equal time differences within each time period, and count the node output power values Ki within two adjacent time nodes, where i = 1, 2, 3,......n - 1; Calculate the mean C of the node output power values Ki within each time period by the mean formula, and then by , calculate the variance E of the node output power values Ki within each time period. If it does not meet E ≤ Z1, where Z1 is a preset deviation ratio, then Delete the values of from largest to smallest in sequence until E ≤ Z1 is met. Then mark the deleted node output power values Ki as abnormal output data Yi and transmit them to the verification unit for verification, and perform secondary analysis on the remaining node output power values Ki. If E ≤ Z1 is met, no processing is performed on the node output power values Ki.

[0011] Preferably, the specific method for secondary analysis is as follows: Generate a curve graph with the remaining node output power values Ki as the vertical axis and the values of i as the horizontal axis, and calculate the line segment slope within each time period to obtain the power consumption efficiency value Xj within each time period; Calculate the mean α of the power consumption efficiency values Xj according to the mean formula, and calculate the standard deviation β of the power consumption efficiency values Xj according to the standard deviation formula; Judge β ≤ γ, where γ is a preset deviation coefficient value; If the above formula is satisfied, it means that the abnormal power consumption is caused by the increase in the circuit resistance of the UAV body due to its own factors and external environmental factors, resulting in abnormal power consumption, and generate an analysis signal to transmit to the UAV body; If the above formula is not satisfied, it means that there is a short circuit in the internal circuit of the UAV body, or capacitors, resistors, and diodes are damaged, causing the circuit current of the UAV body to increase abnormally, resulting in too fast battery discharge speed and abnormal power consumption, and generate an analysis signal to transmit to the UAV body.

[0012] Preferably, the specific analysis method for the abnormal output data Yi is as follows: Obtain the values of the two adjacent time nodes corresponding to the abnormal output data Yi, then obtain the external data monitored by the sensor, substitute the value of the time node corresponding to the abnormal output data Yi into the external data, and determine whether the external data within the corresponding time node has undergone abnormal changes; If an abnormal change occurs, it means that the abnormal output data Yi is caused by an abnormal change in external data.

[0013] Preferably, if there is no abnormal change in the external data, it indicates that the battery has a problem of large instantaneous discharge power; according to , calculate the frequency value T of the abnormal output data Yi in each time period, where g is the number of abnormal output data Yi, and analyze according to T≥Z2, where Z2 is the preset frequency comparison value; If it is satisfied, the frequency of abnormal output data Yi is too high, and the drone needs to return to the home position and perform maintenance or repair and replacement on the internal circuit and battery, and generate a return signal to transmit to the drone. If it is not satisfied, the internal circuit and battery of the drone body must be maintained or repaired and replaced after returning to the flight according to the actual situation, and a signal to be inspected must be generated and transmitted to the drone body.

[0014] Preferably, the method for adjusting the flight altitude and flight speed of the drone body is: Obtain a graph A1 of horizontal flight speed and wind resistance, and obtain horizontal output power based on the wind resistance and horizontal flight speed, generating a graph A2 of horizontal output power and horizontal flight speed, and obtain a graph A3 of vertical height and vertical power. Based on graphs A2 and A3, obtain a graph A4 of the relationship between the horizontal flight speed of the UAV and the total output power; Get the flight time t1 corresponding to the distance already flown D1, get the remaining distance for a one-way flight D2 = D-D1, get the available flight time t2 = t-t1, calculate the minimum flight speed V2 = D2 / t2 for the remaining distance, get the maximum set flight speed V3 of the drone, and use V2 and V3 to form a flight speed range; Get the maximum flight altitude value H2 and the minimum flight altitude value H3 set by the drone body, and form a flight altitude range with H2 and H3; Get the value of available power consumption for the current remaining distance: Q2 = Q3 - Q1, where Q1 is the power consumption value corresponding to the distance already flown D1; Arbitrarily select a horizontal flight speed V4, where V2 ≤ V4 ≤ V3, and obtain the numerical value t3 of the flight time corresponding to the horizontal flight speed of V4, and t3 ≤ t2. Arbitrarily select a flight altitude H4, where H3 ≤ H4 ≤ H2, obtain the output power P3 for overcoming wind resistance during horizontal flight at the flight speed value of V4, and obtain the longitudinal output power P4 for maintaining suspension during horizontal flight at the flight altitude value of H4; And by satisfying P3 + P4 ≤ Q2 / t3, obtain multiple sets of adjustment sets of (V4, H4, t3); and select the corresponding flight speed value V4 and flight altitude value H4 within different adjustment sets as the optimal solutions according to different flight requirements, and adjust the flight speed value and flight altitude value of the UAV body to the corresponding flight speed value V4 and flight altitude value of the optimal solutions.

[0015] Preferably, when the flight speed and flight altitude are adjusted by selecting the optimal solutions and still do not meet the requirement that the UAV body flies to the end coordinate with the output power value of Q2 / t3, obtain information on whether there is a UAV body charging device at the end coordinate; If it exists, the UAV body will continue to fly to the end for charging; If it does not exist, the UAV body will return for charging.

[0016] Beneficial Effects The present invention provides an AI-based automatic positioning and navigation system for UAVs. Compared with the prior art, it has the following beneficial effects: (1) By obtaining the power of the UAV body at takeoff, the flight route can be planned according to the power. During flight, the actual output power is monitored in real time, and by comparing it with the standard output power of historical data, it can be monitored whether there is an abnormal power consumption problem during flight of the UAV body, so as to judge whether the UAV body can fly and return normally, avoiding the problem of the UAV being unable to return or falling.

[0017] (2) By gradually analyzing the data of the abnormal output power generated by the UAV body, the reason for the generation of the abnormal output power is judged, and for different reasons, different instructions are generated to control the flight of the UAV body, ensuring that the UAV body can fly and return normally, avoiding the problem of the UAV body being unable to return or falling.

[0018] (3) After receiving the feedback signal of the abnormal output power and based on the monitored flight data of the UAV body, the flight route and flight attitude of the UAV body are adjusted according to the output power corresponding to the remaining available power consumption, so as to ensure that the UAV body can fly or return normally, avoiding the problem of the UAV body being unable to return or falling. Description of the Drawings

[0019] Figure 1 It is the automatic positioning and navigation system diagram of the present invention; Figure 2 It is the working flow chart of the verification unit of the present invention. Specific embodiments

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] Please refer to Figure 1-2 , the present invention provides a technical solution: an AI-based automatic positioning and navigation system for drones: As the first embodiment of this application, it specifically includes: a drone body, a monitoring unit, a verification unit, a coordinate unit, and a calibration unit; Among them, the drone body, the monitoring unit, and the coordinate unit are bidirectionally connected to each other. The output nodes of the monitoring unit are electrically connected to the input nodes of the verification unit and the calibration unit respectively. The output node of the coordinate unit is electrically connected to the input node of the calibration unit. The output nodes of the calibration unit and the verification unit are both electrically connected to the input node of the drone body; The drone body includes a frame and a built-in battery, a navigation module, sensors, and an internal control system carried therein. The internal control system is a control circuit board. The battery, the navigation module, and the sensors are all electrically connected to the control circuit board. By manually inputting the end coordinates and the planned flight duration value t, the starting coordinates are obtained through the navigation module, and then the starting coordinates fly to the end coordinates at the flight speed value V1 and the flight height value H1. When the drone body flies at the flight speed value V1, it is satisfied that it reaches the end coordinates within the planned flight duration value t, and automatically completes the flight tasks (surveying and mapping, shooting) and automatically judges the return flight; Among them, the navigation module is used to obtain the real-time coordinates of the drone body, and adopts a Beidou positioning module or a GPS positioning module. The sensors are used to obtain external data such as the temperature, air pressure, humidity of the external environment of the drone body and the flight attitude of the drone body, and it includes components such as a temperature sensor, a humidity sensor, a barometer, and a gyroscope; The monitoring unit obtains the starting power value Q of the drone body, transmits the starting power value to the coordinate unit, and monitors the output power of the battery in real time during flight. When an abnormal output power occurs during flight, a feedback signal is generated and transmitted to the calibration unit, and then the abnormal output power is analyzed, and the data of the abnormal output power is transmitted to the verification unit; The coordinate unit forms a three-dimensional space coordinate system based on the longitude and latitude coordinates, dimensions, and the height of the sea level. Taking the coordinates of the UAV body itself as the starting coordinates, and according to the starting coordinates and the input end coordinates, it plans the flight route that satisfies the power consumption value less than Q3, obtains the distance value D of the flight route and transmits it to the monitoring unit, where Q3 is the rated power consumption for a one-way flight, and Q3 is less than half of the starting power value Q, that is, the rated power consumption Q3 is the maximum power consumption for the UAV body to fly one-way from the starting coordinates to the end coordinates.

[0022] The specific determination method for whether there is an abnormal output power is as follows: Obtain the actual output power value P1 corresponding to the flown distance value D1 of the UAV body at the flight speed value V1 and the flight height value H1; Obtain the historical data of the output power P of the UAV body at different flight speeds V and flight heights H, and obtain the standard output power value P2 corresponding to the flight speed V1 and the flight height H1 according to the historical data; The specific acquisition method is as follows: Obtain the flight data that meets the flight height value of H1 at different times in the historical data. The flight data includes flight speed value data, flight height value data, and flight output power value data; Among the flight data with the flight height value of H1 of the UAV body, obtain the flight data with the flight speed meeting V1, and generate a historical set (V1, H1); And based on the historical set (V1, H1), obtain its corresponding historical output power set, and according to the set of historical output powers, generate a coordinate graph with the historical output power value as the ordinate and the number of historical output power values as the abscissa, and then obtain the standard output power value P2 through linear fitting. The standard output power value P2 represents the typical value of the output power at the flight speed value V1 and the flight height value H1; Judge whether P2 - 0.3P2 ≤ P1 ≤ P2 + 0.3P2 is satisfied; If it is satisfied, it indicates that the power consumption of the UAV body is normal, and it can fly to the end coordinates at the flight speed value V1 and the flight height value H1; If it is not satisfied, when P1 < P2 - 0.3P2, there is a sensor damage resulting in abnormal power monitoring. When P1 > P2 + 0.3P2, then mark P1 as an abnormal output power, and at the same time generate a feedback signal and transmit it to the correction unit, and analyze the abnormal output power. Then, based on the analysis result, generate an analysis signal and transmit it to the UAV body and the verification unit. The specific analysis method is as follows: Based on equal time differences, the flight duration corresponding to the uniform flight at the flight speed value V1 in the flown distance is obtained as j time periods, where j = 1, 2, 3,......m. And within each time period, n time nodes are obtained based on equal time differences, and the node output power values Ki between two adjacent time nodes are statistically analyzed, where i = 1, 2, 3,......n - 1; From , the mean value C of the node output power value Ki within each time period is calculated. Then from , the variance value E of the node output power value Ki within each time period is calculated. If it does not meet E ≤ Z1, where Z1 is a preset deviation ratio obtained from test parameter data and pre - entered into the built - in control system of the UAV body by the tester, then the values are deleted in descending order until E ≤ Z1. Then the deleted node output power values Ki are marked as abnormal output data Yi and transmitted to the verification unit for verification, and the remaining node output power values Ki are analyzed again. If E ≤ Z1 is met, the node output power values Ki are not processed; The specific method of the secondary analysis is as follows: For the remaining node output power values Ki, a curve graph is generated with the Ki value as the vertical axis and the value of i as the horizontal axis, and the line segment slope within each time period is calculated to obtain the power consumption efficiency value Xj of each time period, According to , the average value α of the power consumption efficiency value Xj is obtained; According to , the standard deviation value β of the power consumption efficiency value Xj is obtained; Then it is judged whether β ≤ γ, where γ is a preset deviation coefficient value; If the above formula is satisfied, it means that the abnormal power consumption is caused by factors such as the UAV body's own factors (component aging, connection wire aging, electronic component heating, battery raw material aging) and external environmental factors (temperature change, humid environment), which lead to an increase in the circuit resistance of the UAV body and cause abnormal power consumption, and an analysis signal is generated and transmitted to the UAV body; If the above formula is not satisfied, it means that there is a short - circuit in the internal circuit of the UAV body, or problems such as damage to electrical components such as capacitors, resistors, and diodes, which cause an abnormal increase in the circuit current of the UAV body, resulting in an excessive battery discharge speed and abnormal power consumption, and an analysis signal is generated and transmitted to the UAV body.

[0023] As the second embodiment of the present application, it specifically includes: a verification unit for receiving the abnormal output data Yi in the data transmitted by the monitoring unit and analyzing the abnormal output data Yi. The specific analysis method is as follows: Obtain the numerical values of the two adjacent time nodes corresponding to the abnormal output data Yi, and then obtain the external data monitored by the sensor. Substitute the numerical value of the time node corresponding to the abnormal output data Yi into the external data to determine whether there is an abnormal change in the external data within the corresponding time node; If there is an abnormal change in the external data, it indicates that the abnormal output data Yi is caused by the abnormal change in the external data; When one or more of the following conditions occur in the external data: the temperature difference before and after is 5°C or more, the relative air pressure difference and relative humidity difference are 10% or more, and the flight attitude of the UAV itself changes, it indicates that the external data has an abnormal change. The UAV attitude change includes one or more changes in roll, pitch, and yaw angles; If there is no change, it indicates that there is a problem with the instantaneous discharge power of the battery. According to , calculate the frequency value T of the abnormal output data Yi in each time period, where g is the number of abnormal output data Yi. Analyze according to T≥Z2, where Z2 is a preset frequency comparison value, which is pre-entered into the built-in control system of the UAV body by the tester; If it is satisfied, the frequency of the abnormal output data Yi is too high, which is likely to cause the battery to age rapidly, heat severely, and lead to battery expansion, leakage, short circuit, resulting in battery spontaneous combustion, reduction of battery storage capacity, and degradation of the performance of electrical components. The UAV body needs to return and maintain or repair and replace the internal circuit and battery, and generate a return signal to transmit to the UAV body; If it is not satisfied, according to the actual situation, maintain or repair and replace the internal circuit and battery of the UAV body after returning, and generate a signal to be inspected and transmit it to the UAV body.

[0024] As the third embodiment of the present application, it specifically includes: a correction unit that receives the feedback signal transmitted by the monitoring unit, obtains the current coordinate value of the UAV body, and obtains the test parameter chart information. The test parameter chart is generated from test data after the tester tests the UAV body, and the test parameter chart is pre-entered into the built-in control system of the UAV body to adjust the current flight altitude value H1 and flight speed value V1 of the UAV body. The specific method is: The test parameter chart includes a curve graph A1 of the horizontal flight speed and wind resistance, and obtains the horizontal output power according to the wind resistance and the horizontal flight speed, generates a curve graph A2 of the horizontal output power and the horizontal flight speed, obtains a curve graph A3 of the vertical height and the vertical power, and according to the curve graph A2 and the curve graph A3, obtains a relationship curve graph A4 of the UAV horizontal flight speed and the total output power (power consumption / time); Obtain the flight duration t1 corresponding to the flown distance value D1, obtain the remaining distance value D2 = D - D1 for the one-way flight, obtain the value t2 of the available flight duration, where t2 = t - t1, calculate the value V2 of the minimum flight speed in the remaining distance, where V2 = D2 / t2, obtain the maximum set flight speed V3 of the UAV body, and form a flight speed range with V2 and V3; Obtain the maximum flight altitude value H2 and the minimum flight altitude value H3 set for the UAV body, and form a flight altitude range with H2 and H3; Obtain the value Q2 of the available power consumption in the current remaining distance, where Q2 = Q3 - Q1, and Q1 is the power consumption value corresponding to the flown distance value D1; Arbitrarily select a horizontal flight speed V4, where V2 ≤ V4 ≤ V3, and obtain the value t3 of the flight time corresponding to the horizontal flight speed of V4, and t3 ≤ t2. Arbitrarily select a flight altitude H4, where H3 ≤ H4 ≤ H2, obtain the output power P3 to overcome the wind resistance when flying horizontally at the flight speed value of V4, and obtain the longitudinal output power P4 to maintain hovering when flying horizontally at the flight altitude value of H4; And by satisfying P3 + P4 ≤ Q2 / t3, obtain multiple sets of adjustment sets (V4, H4, t3); and select the corresponding flight speed value V4 and flight altitude value H4 in different adjustment sets as the optimal solutions according to different flight requirements, and adjust the flight speed value and flight altitude value of the UAV body to the corresponding flight speed value V4 and flight altitude value H4 of the optimal solutions; The specific selection method is as follows: When the flight requirement is to ensure flight safety, select the maximum flight altitude value H4max and the corresponding flight speed value V4 for adjustment, and H4max is the maximum value of the flight altitude value H4 in multiple sets of adjustment sets (V4, H4, t3); When the flight requirement is the shortest flight duration, select the maximum flight speed value V4max and the corresponding flight altitude value H4 for adjustment, and V4max is the maximum value of the flight speed value V4 in multiple sets of adjustment sets (V4, H4); When the flight requirement is the minimum output power, sum up the total output power corresponding to (V4, H4, t3) in multiple sets of adjustment sets, obtain the minimum value in the sum of the output power summation values, and select the corresponding flight speed value V4 and flight altitude value H4 for adjustment.

[0025] After adjusting the flight speed and flight altitude by selecting the optimal solutions, when it still does not meet the requirement that the UAV body flies to the end coordinate with the output power value Q2 / t3, obtain the information on whether there is a UAV body charging device at the end coordinate; If it exists, the UAV body will continue to fly to the end for charging; If not, the UAV body will return for charging.

[0026] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An AI-based automatic positioning and navigation system for drones, characterized in that Including: The UAV body, which inputs the end coordinates and the planned flight duration value t manually, obtains the starting coordinates through the navigation module, and then flies from the starting coordinates to the end coordinates at the flight speed value V1 and the flight altitude value H1, and automatically completes the flight mission and automatically judges the return flight. The monitoring unit obtains the initial battery power value Q of the UAV body, transmits the initial battery power value to the coordinate unit, and monitors the output power of the battery in real time during flight. When an abnormal output power occurs during flight, a feedback signal is generated and transmitted to the correction unit, and then the abnormal output power is analyzed, and the abnormal output data Yi in the abnormal output power is transmitted to the verification unit. The coordinate unit forms a three-dimensional space coordinate system based on the longitude and latitude coordinates, size, and altitude of the sea level, takes the coordinates of the UAV body itself as the starting coordinates, and plans a flight route that satisfies the power consumption value less than Q3 according to the starting coordinates and the input end coordinates, obtains the distance value D of the flight route and transmits it to the monitoring unit. The verification unit is used to receive the abnormal output data Yi transmitted by the monitoring unit and analyze the abnormal output data Yi. The correction unit receives the feedback signal transmitted by the monitoring unit, obtains the current coordinate value of the UAV body, and obtains the information of the test parameter chart, and adjusts the current flight altitude value H1 and flight speed value V1 of the UAV body.

2. The AI-based automatic positioning and navigation system for drones according to claim 1, wherein: The specific determination method for whether there is abnormal output power is as follows: Obtain the actual output power value P1 corresponding to the flown distance value D1 of the UAV body at the flight speed value V1 and the flight altitude value H1. Obtain the historical data of the output power P of the UAV body at different flight speeds V and flight altitudes H, and obtain the standard output power value P2 corresponding to the flight speed V1 and the flight altitude H1 of the UAV body according to the historical data. Judge whether P2 - 0.3P2 ≤ P1 ≤ P2 + 0.3P2 is satisfied. If satisfied, it indicates that the power consumption of the UAV body is normal.

3. The AI-based UAV automatic positioning and navigation system according to claim 2, wherein: When P1 < P2 - 0.3P2, there is an abnormal power monitoring. When P1 > P2 + 0.3P2, then P1 is marked as abnormal output power, and at the same time, a feedback signal is generated and transmitted to the correction unit, and the abnormal output power is analyzed, and then an analysis signal is generated based on the analysis result and transmitted to the UAV body and the verification unit.

4. The AI-based UAV automatic positioning and navigation system according to claim 2, wherein: The specific acquisition method of the standard output power value P2 is as follows: Obtain the flight data that meets the flight altitude value of H1 at different times of the historical data. Then, based on the flight data with the flight altitude value of H1, obtain the flight data with the flight speed meeting V1, and generate a historical set (V1, H1). And based on the historical set (V1, H1), obtain the corresponding historical output power set, generate a coordinate graph according to the historical output power set, and then obtain the standard output power value P2 through linear fitting. The standard output power value P2 represents the typical value of the output power at the flight speed value V1 and the flight altitude value H1.

5. The AI-based UAV automatic positioning and navigation system according to claim 3, characterized in that: The specific analysis method for abnormal output power is as follows: The flight duration corresponding to the uniform flight at the flight speed value V1 in the flown distance is obtained as j time periods based on equal time differences, where j = 1, 2, 3,......m. And n time nodes are obtained based on equal time differences within each time period, and the node output power values Ki between two adjacent time nodes are statistically analyzed, where i = 1, 2, 3,......n - 1; Calculate the mean value C of the node output power value Ki in each time period by the mean value formula, and then , calculate the variance value E of the node output power value Ki in each time period. If it does not meet E ≤ Z1, where Z1 is a preset deviation ratio, then the values are deleted in descending order until E ≤ Z1 is met. Then, mark the deleted node output power value Ki as abnormal output data Yi and transmit it to the verification unit for verification, and perform secondary analysis on the remaining node output power value Ki. If E ≤ Z1 is met, no processing is performed on the node output power value Ki.

6. The AI-based automatic positioning and navigation system for drones according to claim 5, characterized in that: The specific method of secondary analysis is as follows: The remaining node output power values Ki are used to generate a curve graph with the Ki value as the vertical axis and the value of i as the horizontal axis, and the line segment slope within each time period is calculated to obtain the power consumption efficiency value Xj within each time period; According to the average value formula, the average value α of the power consumption efficiency value Xj is obtained, and then according to the standard deviation formula, the standard deviation value β of the power consumption efficiency value Xj is obtained; Judge β ≤ γ, where γ is a preset deviation coefficient value; If the above formula is satisfied, it means that the abnormal power consumption is caused by the increase in the circuit resistance of the UAV body due to the factors of the UAV body itself and the external environment, resulting in abnormal power consumption, and an analysis signal is generated and transmitted to the UAV body; If the above formula is not satisfied, it means that there is a short circuit in the internal circuit of the UAV body, or the capacitor, resistor, and diode are damaged, resulting in an abnormal increase in the circuit current of the UAV body, leading to an excessive battery discharge speed and abnormal power consumption, and an analysis signal is generated and transmitted to the UAV body.

7. The AI-based UAV automatic positioning and navigation system according to claim 1, characterized in that: The specific analysis method for the abnormal output data Yi is as follows: Obtain the values of two adjacent time nodes corresponding to the abnormal output data Yi, and then obtain the external data monitored by the sensor. Substitute the values of the time nodes corresponding to the abnormal output data Yi into the external data to find out whether there is an abnormal change in the external data within the corresponding time node; If there is an abnormal change, it means that the abnormal output data Yi is caused by the abnormal change in the external data.

8. The AI-based automatic positioning and navigation system for drones according to claim 7, characterized in that: If the external data does not change abnormally, it indicates that there is a problem with the large instantaneous discharge power of the storage battery; According to , calculate the frequency value T of the abnormal output data Yi in each time period, where g is the number of abnormal output data Yi, and analyze according to T≥Z2, where Z2 is a preset frequency comparison value; If it is satisfied, the frequency of the abnormal output data Yi is too high, and the UAV body needs to return and maintain or repair and replace the internal circuit and the storage battery, and a return signal is generated and transmitted to the UAV body; If it is not satisfied, it is necessary to maintain or repair and replace the internal circuit and the storage battery of the UAV body according to the actual situation after returning, and a signal to be inspected is generated and transmitted to the UAV body.

9. The AI-based automatic positioning and navigation system for unmanned aerial vehicles according to claim 1, wherein: The adjustment method for the flight height and flight speed of the UAV body is as follows: Obtain the curve graph A1 of the horizontal flight speed and the wind resistance, and obtain the horizontal output power according to the wind resistance and the horizontal flight speed, generate the curve graph A2 of the horizontal output power and the horizontal flight speed, obtain the curve graph A3 of the vertical height and the vertical power, and according to the curve graph A2 and the curve graph A3, obtain the relationship curve graph A4 between the horizontal flight speed of the UAV and the total output power; Obtain the flight duration t1 corresponding to the flown distance value D1, obtain the remaining distance value D2 = D - D1 for the one-way flight, obtain the value of the available flight duration t2 = t - t1, calculate the value of the minimum flight speed V2 in the remaining distance as V2 = D2 / t2, obtain the maximum set flight speed V3 of the UAV body, and form a flight speed interval with V2 and V3; Obtain the maximum flight altitude value H2 and the minimum flight altitude value H3 set for the UAV body, and form a flight altitude interval with H2 and H3; Obtain the value of the available power consumption Q2 = Q3 - Q1 in the current remaining distance, where Q1 is the power consumption value corresponding to the flown distance value D1; Arbitrarily select a horizontal flight speed V4, and V2 ≤ V4 ≤ V3, and obtain the value of the flight time t3 corresponding to the horizontal flight speed of V4, and t3 ≤ t2. Arbitrarily select a flight altitude H4, and H3 ≤ H4 ≤ H2, obtain the output power P3 to overcome wind resistance when flying horizontally at the flight speed value of V4, and obtain the longitudinal output power P4 to maintain suspension when flying horizontally at the flight altitude value of H4; And by satisfying P3 + P4 ≤ Q2 / t3, obtain multiple sets of adjustment sets of (V4, H4, t3); and select the corresponding flight speed value V4 and flight altitude value H4 in different adjustment sets as the optimal solutions according to different flight requirements, and adjust the flight speed value and flight altitude value of the UAV body to the corresponding flight speed value V4 and flight altitude value of the optimal solutions.

10. The AI-based UAV automatic positioning and navigation system according to claim 9, characterized in that: When the flight speed and flight altitude are adjusted by selecting the optimal solutions and still do not meet the requirement that the UAV body flies to the end coordinate with the output power value Q2 / t3, obtain the information on whether there is a UAV body charging device at the end coordinate; If it exists, the UAV body will continue to fly to the end for charging; If it does not exist, the UAV body will return for charging.

Images