AI-based drone automatic positioning and navigation system

Abstract

This invention discloses an AI-based automatic positioning and navigation system for unmanned aerial vehicles (UAVs), comprising: a UAV body that obtains the starting coordinates through a navigation module by manually inputting the destination coordinates and the planned flight duration t, and then flies from the starting coordinates to the destination coordinates at a flight speed V1 and a flight altitude H1, automatically completing the flight mission and automatically determining the return-to-home status; and a monitoring unit that acquires the initial battery level Q of the UAV body, transmits the initial battery level to the coordinate unit, and monitors the output power of the battery in real time during flight. When abnormal output power occurs during flight, a feedback signal is generated and transmitted to the correction unit. This invention relates to the field of UAV technology and solves the problem that existing UAV automatic positioning and navigation systems do not consider the UAV's battery life, which can easily lead to the UAV being unable to return to home or even crashing during flight.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, specifically to an AI-based automatic positioning and navigation system for UAVs. Background Technology

[0002] In the existing technology, common civilian drones often require users to use a camera to remotely control the flight and move the drone. When the drone is close to the end of the flight, it needs to be fine-tuned to reach the appropriate position. At the same time, when the drone is retrieved, it needs to be remotely controlled again. The operation is relatively cumbersome, inflexible, and time-consuming.

[0003] The invention patent with application number CN202311243088.5 discloses an automatic positioning and navigation method and system for AI-based drones, 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 automatic positioning and navigation of drones, and can return to the flight starting point on its own after completing its work, realizing the automatic navigation flight and return-to-home functions of drones, enabling drones to perform flight operations conveniently and flexibly.

[0004] While the automatic positioning and navigation method and system for unmanned aerial vehicles (UAVs) possess the aforementioned advantages, they still have certain drawbacks in practical use: because the system only identifies and judges the UAV's own position, it does not consider the UAV's endurance. Furthermore, since the UAV is autonomously controlled by the system during use, if the endurance is insufficient and the system continues to fly, the UAV may be unable to return autonomously, or even crash during flight. Therefore, improvements are needed to address the shortcomings of the existing technology. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an AI-based automatic positioning and navigation system for unmanned aerial vehicles (UAVs). This system solves the problem that existing UAV automatic positioning and navigation systems do not consider the UAV's battery life, which can easily lead to the UAV being unable to return to its home location or even crashing during flight.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system, comprising:

[0007] The drone body obtains the starting coordinates through the navigation module by manually inputting the destination coordinates and the planned flight time value t. Then, it flies from the starting coordinates to the destination coordinates at a flight speed value V1 and a flight altitude value H1, and automatically completes the flight mission and automatically determines the return home.

[0008] The monitoring unit acquires the initial battery level Q of the UAV body, transmits the initial battery level to the coordinate unit, and monitors the output power of the battery in real time during flight. When abnormal output power occurs during flight, a feedback signal is generated and transmitted to the correction unit. The abnormal output power is then analyzed, and the abnormal output data Yi in the abnormal output power is transmitted to the verification unit.

[0009] The coordinate unit forms a three-dimensional spatial coordinate system based on latitude and longitude coordinates and sea level height. It takes the coordinates of the UAV itself as the starting coordinates and plans the flight route that meets the requirement of power consumption less than Q3 based on the starting coordinates and the input ending coordinates, obtains the distance value D of the flight route, and transmits it to the monitoring unit.

[0010] The verification unit is used to receive the abnormal output data Yi transmitted by the monitoring unit and analyze the abnormal output data Yi.

[0011] The calibration 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.

[0012] Preferably, the specific method for determining whether there is abnormal output power is as follows:

[0013] Obtain the actual output power value P1 corresponding to the distance traveled by the UAV body with flight speed value V1, flight altitude value H1, and flight distance value D1;

[0014] Obtain 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 of the UAV body at flight speed V1 and flight altitude H1 based on the historical data;

[0015] Determine whether the condition P2 - 0.3P2 ≤ P1 ≤ P2 + 0.3P2 is satisfied;

[0016] If the conditions are met, it indicates that the power consumption of the drone itself is normal.

[0017] Preferably, when P1 < P2 - 0.3P2, there is an abnormal power monitoring. When P1 > P2 + 0.3P2, P1 is marked as abnormal output power, and a feedback signal is generated and transmitted to the correction unit. The abnormal output power is analyzed, and an analysis signal is generated based on the analysis results and transmitted to the UAV body and the verification unit.

[0018] Preferably, the standard output power value P2 is obtained in the following way:

[0019] Acquire flight data at different times in history that match the flight altitude value H1;

[0020] Then, based on the flight data with a flight altitude value of H1, obtain the flight data with a flight speed that matches V1, and generate a history set (V1, H1).

[0021] Based on the historical set (V1, H1), the corresponding historical output power set is obtained, and a coordinate graph is generated according to the historical output power set. Then, the standard output power value P2 is obtained through linear fitting. The standard output power value P2 represents the typical value of output power at flight speed value V1 and flight altitude value H1.

[0022] Preferably, the specific analysis method for abnormal output power is as follows:

[0023] The flight time corresponding to the flight speed of V1 at a constant speed during the flight distance is obtained into j time intervals based on equal time differences, where j = 1, 2, 3, ... m. Within each time interval, n time nodes are obtained based on equal time differences. The node output power value Ki between two adjacent time nodes is statistically analyzed, where i = 1, 2, 3, ... n-1.

[0024] The mean value C of the node output power value Ki in each time period is calculated using the average value formula, and then... Calculate the square value E of the node output power value Ki in each time period. If it does not meet the condition E≤Z1, where Z1 is a preset deviation ratio, then... The values ​​are deleted sequentially from largest to smallest until E≤Z1 is met. The deleted node output power values ​​Ki are then marked as abnormal output data Yi and transmitted to the verification unit for verification. The remaining node output power values ​​Ki are then analyzed a second time. If E≤Z1 is met, the node output power values ​​Ki are not processed.

[0025] The preferred method for secondary analysis is as follows:

[0026] Generate a curve with the remaining node output power value Ki, using Ki as the vertical axis and the value of i as the horizontal axis, and calculate the slope of the line segment in each time period to obtain the power consumption efficiency value Xj in each time period.

[0027] The average value α of the power consumption efficiency value Xj is calculated using the average value formula, and the standard deviation β of the power consumption efficiency value Xj is calculated using the standard deviation formula.

[0028] The condition β≤γ is determined, where γ is a preset deviation coefficient value;

[0029] If the above formula is satisfied, it means that the abnormal power consumption is caused by factors of the drone itself and external environmental factors, which lead to an increase in the circuit resistance of the drone itself, resulting in abnormal power consumption and generating analysis signals that are transmitted to the drone itself.

[0030] If the above formula is not met, it indicates that there is a short circuit in the internal circuit of the drone, or that the capacitor, resistor, or diode is damaged, causing the circuit current of the drone to increase abnormally, resulting in the battery discharging too quickly and abnormal power consumption, generating an analysis signal that is transmitted to the drone.

[0031] The preferred method for analyzing abnormal output data Yi is as follows:

[0032] 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 values ​​of the time nodes corresponding to the abnormal output data Yi into the external data, and find out whether the external data within the corresponding time node has undergone abnormal changes.

[0033] If an abnormal change occurs, it indicates that the abnormal output data Yi is caused by an abnormal change in external data.

[0034] Preferably, if there are no abnormal changes in external data, it indicates that the battery has a problem with a large instantaneous discharge power;

[0035] according to Calculate the frequency value T of 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;

[0036] If the condition is met, then there is an abnormal output data Yi with an excessively high frequency, requiring the drone to return to base and its internal circuitry and battery to be maintained or replaced, and a return-to-base signal to be generated and transmitted to the drone.

[0037] If the requirements are not met, then the internal circuitry and battery of the drone should be maintained or repaired or replaced after returning to base, and a test signal should be generated and transmitted to the drone.

[0038] Preferably, the method for adjusting the flight altitude and speed of the drone is as follows:

[0039] Obtain the curve A1 of horizontal flight speed and wind resistance, and obtain the horizontal output power based on wind resistance and horizontal flight speed. Generate the curve A2 of horizontal output power and horizontal flight speed. Obtain the curve A3 of vertical height and vertical power. Based on curves A2 and A3, obtain the curve A4 of the relationship between the UAV's horizontal flight speed and total output power.

[0040] Get the flight time t1 corresponding to the distance already flown D1, get the remaining distance of one-way flight D2=D-D1, get the available flight time t2=t-t1, calculate the minimum flight speed V2=D2 / t2 in the remaining distance, get the maximum set flight speed V3 of the UAV body, and form a flight speed range with V2 and V3.

[0041] Obtain the maximum flight altitude value H2 and the minimum flight altitude value H3 set by the UAV body, and form a flight altitude range using H2 and H3;

[0042] Get the available power consumption value for the remaining distance: Q2 = Q3 - Q1, where Q1 is the power consumption value corresponding to the distance already flown: D1.

[0043] 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 V4, where t3≤t2. Arbitrarily select a flight altitude H4, where H3≤H4≤H2, and obtain the output power P3 for overcoming wind resistance when flying horizontally at a flight speed of V4, and obtain the longitudinal output power P4 for maintaining suspension when flying horizontally at a flight altitude of H4.

[0044] Furthermore, by satisfying P3+P4≤Q2 / t3, multiple adjustment sets (V4, H4, t3) are obtained; and according to different flight requirements, the flight speed value V4 and flight altitude value H4 corresponding to different adjustment sets are selected as the optimal solution, and the flight speed value and flight altitude value of the UAV body are adjusted to the flight speed value V4 and flight altitude value H4 corresponding to the optimal solution.

[0045] Preferably, if adjusting the flight speed and flight altitude by selecting the optimal solution still does not satisfy the requirement that the UAV body flies to the destination coordinates with the output power value Q2 / t3, information on whether there is a charging device for the UAV body at the destination coordinates is obtained;

[0046] If present, the drone will continue flying to the destination to recharge;

[0047] If it does not exist, the drone will return to its home base to recharge.

[0048] Beneficial effects

[0049] This invention provides an AI-based automatic positioning and navigation system for unmanned aerial vehicles (UAVs). Compared with existing technologies, it has the following advantages:

[0050] (1) By acquiring the power of the UAV body when it takes off, the flight route can be planned according to the power. The actual output power can be monitored in real time during flight. By comparing it with the standard output power of historical data, it can be monitored whether the UAV body has abnormal power consumption during flight. This allows for a judgment on whether the UAV body can fly normally and return home, thus avoiding the problem of the UAV being unable to return home or crashing.

[0051] (2) By analyzing the data of abnormal output power of the UAV body step by step, the cause of abnormal output power is determined, and different instructions are generated to control the flight of the UAV body for different causes, so as to ensure that the UAV body can fly normally and return home, thus avoiding the problem of the UAV body being unable to return home or crashing.

[0052] (3) After receiving the feedback signal that generates abnormal output power, and based on the flight data of the UAV body that has been monitored, 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 normally or return home, and avoid the problem that the UAV body cannot return home or crashes. Attached Figure Description

[0053] Figure 1 This is a diagram of the automatic positioning and navigation system of the present invention;

[0054] Figure 2 This is a flowchart of the verification unit of the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Please see Figure 1-2 This invention provides a technical solution: an AI-based automatic positioning and navigation system for unmanned aerial vehicles (UAVs).

[0057] As an embodiment of this application, it specifically includes: a UAV body, a monitoring unit, a verification unit, a coordinate unit, and a correction unit;

[0058] The UAV body, monitoring unit, and coordinate unit are bidirectionally connected to each other. The output node of the monitoring unit is electrically connected to the input node 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 UAV body.

[0059] The drone body includes a frame and its internal battery, navigation module, sensors, and built-in control system. The built-in control system is a control circuit board. The battery, navigation module, and sensors are all electrically connected to the control circuit board. By manually inputting the destination coordinates and the planned flight time value t, the drone obtains the starting coordinates through the navigation module. Then, it flies from the starting coordinates to the destination coordinates at a flight speed value V1 and a flight altitude value H1. When the drone body flies at a flight speed value V1, it meets the requirement of reaching the destination coordinates within the planned flight time value t and automatically completes the flight mission (surveying and shooting) and automatically determines the return.

[0060] The navigation module is used to obtain the real-time coordinates of the UAV body, using a Beidou navigation block or a GPS positioning module. The sensors are used to obtain external data such as temperature, air pressure, humidity and flight attitude of the UAV body. They include components such as temperature sensors, humidity sensors, barometers and gyroscopes.

[0061] The monitoring unit acquires the initial battery level Q of the UAV body, transmits the initial battery level to the coordinate unit, and monitors the output power of the battery in real time during flight. When abnormal output power occurs during flight, a feedback signal is generated and transmitted to the correction unit. The abnormal output power is then analyzed and transmitted to the verification unit.

[0062] The coordinate unit forms a three-dimensional spatial coordinate system based on latitude and longitude coordinates and sea level height. The coordinates of the UAV itself are used as the starting coordinates. Based on the starting coordinates and the input ending coordinates, the flight route that meets the requirement of power consumption being less than Q3 is planned, and the distance value D of the flight route is obtained and transmitted to the monitoring unit. Q3 is the rated power consumption for a one-way flight, and Q3 is less than half of the initial power value Q. That is, the rated power consumption Q3 is the maximum power consumption of the UAV for a one-way flight from the starting coordinates to the ending coordinates.

[0063] The specific method for determining whether there is abnormal output power is as follows:

[0064] Obtain the actual output power value P1 corresponding to the distance traveled by the UAV body with flight speed value V1, flight altitude value H1 and distance traveled D1;

[0065] Acquire 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 flight speed V1 and flight altitude H1 based on the historical data;

[0066] The specific method of obtaining it is as follows:

[0067] Acquire historical data for flight data at different times that match the flight altitude value H1. The flight data includes flight speed data, flight altitude data, and flight output power data.

[0068] In the flight data of the UAV at an altitude of H1, the flight data with a flight speed of V1 are obtained and a historical set (V1, H1) is generated.

[0069] Based on the historical set (V1, H1), the corresponding historical output power set is obtained. Based on the set of historical output power, a coordinate graph is generated with the historical output power value as the vertical axis and the number of historical output power values ​​as the horizontal axis. Then, the standard output power value P2 is obtained through linear fitting. The standard output power value P2 represents the typical value of output power with flight speed value V1 and flight altitude value H1.

[0070] Determine whether the condition P2 - 0.3P2 ≤ P1 ≤ P2 + 0.3P2 is satisfied;

[0071] If the conditions are met, it indicates that the power consumption of the drone is normal, and it can fly to the destination coordinates with a flight speed value V1 and a flight altitude value H1.

[0072] If the condition is not met, when P1 < P2 - 0.3P2, there is a possibility of sensor malfunction causing abnormal power monitoring. When P1 > P2 + 0.3P2, P1 is marked as abnormal output power, and a feedback signal is generated and transmitted to the correction unit. The abnormal output power is then analyzed, and an analysis signal is generated based on the analysis results and transmitted to the UAV body and the verification unit. The specific analysis method is as follows:

[0073] The flight time corresponding to the flight speed of V1 at a constant speed during the flight distance is obtained into j time intervals based on equal time differences, where j = 1, 2, 3, ... m. Within each time interval, n time nodes are obtained based on equal time differences. The node output power value Ki between two adjacent time nodes is statistically analyzed, where i = 1, 2, 3, ... n-1.

[0074] Depend on Calculate the mean C of the node output power value Ki in each time period, and then use... Calculate the variance E of the node output power value Ki in each time period. If 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 by the tester, then... The values ​​are deleted sequentially from largest to smallest until E≤Z1 is met. The deleted node output power values ​​Ki are then marked as abnormal output data Yi and transmitted to the verification unit for verification. The remaining node output power values ​​Ki are then analyzed a second time. If E≤Z1 is met, the node output power values ​​Ki are not processed.

[0075] The specific method of secondary analysis is as follows:

[0076] Generate a curve with the remaining node output power values ​​Ki on the vertical axis and the values ​​of i on the horizontal axis, and calculate the slope of the line segment for each time period to obtain the power consumption efficiency value Xj for each time period.

[0077] according to Obtain the average value α of the power consumption efficiency value Xj;

[0078] according to Obtain the standard deviation β of the power consumption efficiency value Xj;

[0079] Next, we determine whether β ≤ γ, where γ is a preset deviation coefficient value;

[0080] If the above formula is satisfied, it means that the abnormal power consumption is caused by factors such as the drone itself (component aging, connection wire aging, electronic component heating, battery raw material aging) and external environmental factors (temperature change, humid environment), which increase the circuit resistance of the drone itself, causing abnormal power consumption and generating analysis signals that are transmitted to the drone itself.

[0081] If the above formula is not met, it indicates that there is a short circuit in the internal circuit of the drone, or problems such as damage to electrical components such as capacitors, resistors, and diodes, which causes the circuit current of the drone to increase abnormally, resulting in excessively fast battery discharge and abnormal power consumption, generating analysis signals that are transmitted to the drone.

[0082] As a second embodiment of this application, it specifically includes: a verification unit, used to receive abnormal output data Yi from the data transmitted by the monitoring unit, and to analyze the abnormal output data Yi. The specific analysis method is as follows:

[0083] 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 values ​​of the time nodes corresponding to the abnormal output data Yi into the external data, and find out whether the external data within the corresponding time node has undergone abnormal changes.

[0084] If the external data changes abnormally, it means that the abnormal output data Yi is caused by the abnormal change in the external data.

[0085] When external data shows one or more of the following conditions: a temperature difference of 5°C or more, a relative pressure difference and a relative humidity difference of 10% or more, or a change in the flight attitude of the UAV itself, it indicates that the external data has changed abnormally. The change in the UAV's attitude includes one or more changes in roll, pitch and yaw angle.

[0086] If no change occurs, it indicates that the battery has a problem with excessive instantaneous discharge power. The frequency value T of abnormal output data Yi in each time period is calculated, where g is the number of abnormal output data Yi. The analysis is carried out based on T≥Z2, where Z2 is a preset frequency comparison value, which is pre-entered into the built-in control system of the UAV by the tester.

[0087] If the condition is met, the frequency of abnormal output data Yi is too high, which can easily cause the battery to age faster, overheat, and lead to battery expansion, leakage, short circuit and battery spontaneous combustion, reduced storage capacity and reduced performance of electrical components. The drone body needs to return to base and maintain or replace the internal circuit and battery, and generate a return signal to transmit to the drone body.

[0088] If the requirements are not met, then the internal circuitry and battery of the drone should be maintained or repaired or replaced after returning to base, and a test signal should be generated and transmitted to the drone.

[0089] As a third embodiment of this application, it specifically includes: a calibration unit, which receives the feedback signal transmitted by the monitoring unit, obtains the current coordinate value of the UAV body, and obtains test parameter chart information, wherein 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, and adjusts the current flight altitude value H1 and flight speed value V1 of the UAV body, specifically in the following manner:

[0090] The test parameter charts include a curve A1 of horizontal flight speed and wind resistance, and a curve A2 of horizontal output power and horizontal flight speed is generated based on wind resistance and horizontal flight speed. A curve A3 of vertical height and vertical power is also generated. Based on curves A2 and A3, a curve A4 of the relationship between the drone's horizontal flight speed and total output power (power consumption / time) is obtained.

[0091] Get the flight time t1 corresponding to the distance already flown D1, get the remaining distance of one-way flight D2=D-D1, get the available flight time t2=t-t1, calculate the minimum flight speed V2=D2 / t2 in the remaining distance, get the maximum set flight speed V3 of the UAV body, and form a flight speed range with V2 and V3.

[0092] Obtain the maximum flight altitude value H2 and the minimum flight altitude value H3 set by the UAV body, and form a flight altitude range using H2 and H3;

[0093] Get the available power consumption value for the remaining distance: Q2 = Q3 - Q1, where Q1 is the power consumption value corresponding to the distance already flown: D1.

[0094] 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 V4, where t3≤t2. Arbitrarily select a flight altitude H4, where H3≤H4≤H2, and obtain the output power P3 for overcoming wind resistance when flying horizontally at a flight speed of V4, and obtain the longitudinal output power P4 for maintaining suspension when flying horizontally at a flight altitude of H4.

[0095] Furthermore, by satisfying P3+P4≤Q2 / t3, multiple adjustment sets (V4, H4, t3) are obtained; and according to different flight requirements, the flight speed value V4 and flight altitude value H4 corresponding to different adjustment sets are selected as the optimal solution, and the flight speed value and flight altitude value of the UAV body are adjusted to the flight speed value V4 and flight altitude value H4 corresponding to the optimal solution.

[0096] The specific selection method is as follows:

[0097] When flight safety is the primary requirement, the maximum flight altitude value H4max and its corresponding flight speed value V4 are selected for adjustment, and H4max is the maximum value of flight altitude value H4 among multiple adjustment sets (V4, H4, t3);

[0098] When the shortest flight time is the flight requirement, the maximum flight speed value V4max and its corresponding flight altitude value H4 are selected for adjustment, and V4max is the maximum value of the flight speed value V4 in multiple adjustment sets (V4, H4);

[0099] When the minimum output power is the flight requirement, the total output power corresponding to (V4, H4, t3) in multiple adjustment sets is summed, the minimum value among the summed total output power is obtained, and the corresponding flight speed value V4 and flight altitude value H4 are selected for adjustment.

[0100] If, after adjusting the flight speed and altitude by selecting the optimal solution, the drone body still does not reach the destination coordinates with the output power value Q2 / t3, information on whether there is a charging device for the drone body at the destination coordinates is obtained.

[0101] If present, the drone will continue flying to the destination to recharge;

[0102] If it does not exist, the drone will return to its home base to recharge.

[0103] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An AI-based automatic positioning and navigation system for unmanned aerial vehicles, characterized in that, include: The drone body obtains the starting coordinates through the navigation module by manually inputting the destination coordinates and the planned flight time value t. Then, it flies from the starting coordinates to the destination coordinates at a flight speed value V1 and a flight altitude value H1, and automatically completes the flight mission and automatically determines the return home. The monitoring unit acquires the initial battery level Q of the UAV body, transmits the initial battery level to the coordinate unit, and monitors the output power of the battery in real time during flight. When abnormal output power occurs during flight, a feedback signal is generated and transmitted to the correction unit. The abnormal output power is then 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 spatial coordinate system based on latitude and longitude coordinates and sea level altitude. It takes the coordinates of the UAV itself as the starting coordinates and plans the flight route that meets the power consumption value of less than Q3 based on the starting coordinates and the input ending coordinates. It obtains the distance value D of the flight route and transmits it to the monitoring unit; Q3 is the rated power consumption for a one-way flight. 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 calibration 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. The test parameter charts are generated from the test data after the testers test the UAV itself. The test parameter charts include the curves of horizontal flight speed and wind resistance (A1), the curves of horizontal output power and horizontal flight speed (A2), the curves of vertical height and vertical power (A3), and the curve of the relationship between the UAV's horizontal flight speed and total output power (A4).

2. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 1, characterized in that: The specific method for determining whether there is abnormal output power is as follows: Obtain the actual output power value P1 corresponding to the distance traveled by the UAV body with flight speed value V1, flight altitude value H1, and flight distance value D1; Obtain 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 of the UAV body at flight speed V1 and flight altitude H1 based on the historical data; Determine whether the condition P2 - 0.3P2 ≤ P1 ≤ P2 + 0.3P2 is satisfied; If the conditions are met, it indicates that the power consumption of the drone itself is normal.

3. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 2, characterized in that: When P1 < P2 - 0.3P2, there is an abnormal power monitoring. When P1 > P2 + 0.3P2, P1 is marked as abnormal output power, and a feedback signal is generated and transmitted to the correction unit. The abnormal output power is analyzed, and an analysis signal is generated based on the analysis results and transmitted to the UAV body and the verification unit.

4. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 2, characterized in that: The specific method for obtaining the standard output power value P2 is as follows: Acquire flight data at different times in history that match the flight altitude value H1; Then, based on the flight data with a flight altitude value of H1, obtain the flight data with a flight speed that matches V1, and generate a history set (V1, H1). Based on the historical set (V1, H1), the corresponding historical output power set is obtained, and a coordinate graph is generated according to the historical output power set. Then, the standard output power value P2 is obtained through linear fitting. The standard output power value P2 represents the typical value of output power at flight speed value V1 and flight altitude value H1.

5. The AI-based unmanned aerial vehicle (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 time corresponding to the flight speed of V1 at a constant speed during the flight distance is obtained into j time intervals based on equal time differences, where j = 1, 2, 3, ... m. Within each time interval, n time nodes are obtained based on equal time differences. The node output power value Ki between two adjacent time nodes is statistically analyzed, where i = 1, 2, 3, ... n-1. The mean value C of the node output power Ki in each time period is calculated using the average value formula, and then... Calculate the square value E of the node output power value Ki in each time period. If E≤Z1, then no processing is required on the node output power value Ki. If E≤Z1 is not met, where Z1 is the preset deviation ratio, then... The values ​​are deleted sequentially from largest to smallest until E≤Z1 is met. The deleted node output power values ​​Ki are then marked as abnormal output data Yi and transmitted to the verification unit for verification. The remaining node output power values ​​Ki are then subjected to secondary analysis.

6. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 5, characterized in that: The specific method of secondary analysis is as follows: Generate a curve with the remaining node output power value Ki, using Ki as the vertical axis and the value of i as the horizontal axis, and calculate the slope of the line segment in each time period to obtain the power consumption efficiency value Xj in each time period. The average value α of the power consumption efficiency value Xj is calculated using the average value formula, and the standard deviation β of the power consumption efficiency value Xj is calculated using the standard deviation formula. The condition β≤γ is determined, 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 of the drone itself and external environmental factors, which lead to an increase in the circuit resistance of the drone itself, resulting in abnormal power consumption and generating analysis signals that are transmitted to the drone itself. If the above formula is not met, it indicates that there is a short circuit in the internal circuit of the drone, or that the capacitor, resistor, or diode is damaged, causing the circuit current of the drone to increase abnormally, resulting in the battery discharging too quickly and abnormal power consumption, generating an analysis signal that is transmitted to the drone.

7. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 1, characterized in that: The specific analysis method for 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 values ​​of the time nodes corresponding to the abnormal output data Yi into the external data, and find out whether the external data within the corresponding time node has undergone abnormal changes. If an abnormal change occurs, it indicates that the abnormal output data Yi is caused by an abnormal change in external data.

8. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 7, characterized in that: If there are no abnormal changes in the external data, it indicates that the battery has a problem with a large instantaneous discharge power. according to Calculate the frequency value T of 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 the condition is met, then there is an abnormal output data Yi with an excessively high frequency, requiring the drone to return to base and its internal circuitry and battery to be maintained or replaced, and a return-to-base signal to be generated and transmitted to the drone. If the requirements are not met, then the internal circuitry and battery of the drone should be maintained or repaired or replaced after returning to base, and a test signal should be generated and transmitted to the drone.

9. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 1, characterized in that: The methods for adjusting the flight altitude and speed of the drone are as follows: Obtain the curve A1 of horizontal flight speed and wind resistance, and obtain the horizontal output power based on wind resistance and horizontal flight speed. Generate the curve A2 of horizontal output power and horizontal flight speed. Obtain the curve A3 of vertical height and vertical power. Based on curves A2 and A3, obtain the curve A4 of the relationship between the UAV's horizontal flight speed and total output power. Get the flight time t1 corresponding to the distance already flown D1, get the remaining distance of one-way flight D2=D-D1, get the available flight time t2=t-t1, calculate the minimum flight speed V2=D2 / t2 in the remaining distance, get 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 by the UAV body, and form a flight altitude range using H2 and H3; Get the available power consumption value for the 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 value t3 of the flight time corresponding to the horizontal flight speed V4, where t3≤t2. Arbitrarily select a flight altitude H4, where H3≤H4≤H2, and obtain the output power P3 for overcoming wind resistance when flying horizontally at a flight speed of V4, and obtain the longitudinal output power P4 for maintaining suspension when flying horizontally at a flight altitude of H4. Furthermore, by satisfying P3+P4≤Q2 / t3, multiple adjustment sets (V4, H4, t3) are obtained; and according to different flight requirements, the flight speed value V4 and flight altitude value H4 corresponding to different adjustment sets are selected as the optimal solution, and the flight speed value and flight altitude value of the UAV body are adjusted to the flight speed value V4 and flight altitude value H4 corresponding to the optimal solution.

10. The AI-based unmanned aerial vehicle (UAV) automatic positioning and navigation system according to claim 9, characterized in that: If, after adjusting the flight speed and altitude by selecting the optimal solution, the drone body still does not reach the destination coordinates with the output power value Q2 / t3, information on whether there is a charging device for the drone body at the destination coordinates is obtained. If present, the drone will continue flying to the destination to recharge; If it does not exist, the drone will return to its home base to recharge.

Images