A UAV flight verification management system and method based on big data

Abstract

The present invention discloses a UAV flight calibration management system and method based on big data, which belongs to the technical field of UAV flight calibration. The present invention can timely discover abnormal conditions of UAV batteries by installing power meter sensors on UAV batteries for real-time monitoring and calibration, and extract and analyze historical data of UAV batteries for predictive calculation, which can avoid damage to UAVs and mission failures caused by battery failure or performance degradation, reduce maintenance and replacement costs, ensure that each mission has sufficient power support, and improve the success rate of missions. Improve user experience, ensure stable battery performance of UAVs during flight, reduce unexpected shutdowns or performance degradation, and increase user trust in UAV performance. Users can understand battery status at any time, plan and adjust usage plans, and improve user experience. Flight calibration makes the application of UAVs in various fields more reliable, efficient and sustainable.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle flight verification, and in particular to a unmanned aerial vehicle flight verification management system and method based on big data. Background Art

[0002] Drones play an important role in many fields, from commercial and economic development to security and emergency response, from environmental protection to scientific research and education, and their applications are constantly expanding and deepening. They not only improve efficiency and safety, but also create new economic and social value, and promote technological innovation and progress. With the continuous advancement of technology and the expansion of application scenarios, the significance of drones will become more and more important, and have a profound impact on all walks of life.

[0003] However, drone batteries have shortcomings in terms of endurance, charging time, service life, safety, environmental adaptability, cost and environmental protection. During the use of drones, drone batteries are charged and reused many times, which will cause the service life of drone batteries to be affected by factors such as manufacturing process defects, electrolyte composition, stability and frequency of use, resulting in different life spans. In the current use of drones, there is a lack of drone battery calibration data. Therefore, only with the support of actual and reliable drone battery calibration data can the flight safety and flight performance of drones be further guaranteed. Summary of the invention

[0004] The purpose of the present invention is to provide a UAV flight verification management system and method based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a UAV flight verification management system and method based on big data.

[0006] The UAV flight verification management method comprises the following steps:

[0007] Step S1: Use a power meter sensor to monitor the drone battery, and record the power data of each drone battery unit monitored by the power meter sensor as battery power data. And verify and store it with the standard data of drone batteries;

[0008] Step S2: Obtain the minimum life threshold of the abnormal drone battery based on the drone battery history data and the number of abnormalities in drone battery power during each flight;

[0009] Step S3: Count the total number of abnormal battery power of the drone and record it as the battery depth value The single flight abnormality threshold is set as the data with the most abnormal battery power in the drone battery history data. , the number of abnormalities due to battery power failure in a single flight is recorded as a failure abnormality ;

[0010] Step S4: Calculate the number of abnormal battery times and battery depth value of the drone monitored and verified during the flight of the drone The sum is greater than or equal to the minimum lifespan threshold When the number of abnormal battery failures detected by the drone monitoring system during flight is greater than or equal to the abnormal failure When the drone is in flight, it is judged that there is an abnormality in the battery power output and a return signal is sent;

[0011] Step S4-1: The number of abnormal battery times of the drone monitored and verified during the flight of the drone With battery depth value to conduct and calculate;

[0012] when When the battery power output of the UAV is judged to be normal, the flight mission can continue;

[0013] when When the drone is detected to have abnormal battery power output, it sends a request to return home.

[0014] Step S4-2: The number of abnormal battery times of the drone monitored and verified during the flight of the drone Exception with fault Make comparisons;

[0015] when When the UAV battery power output is normal, it is judged that the UAV can continue to perform the flight mission;

[0016] when When the drone detects that the battery power output is abnormal and cannot continue to perform the flight mission, it sends a request to return.

[0017] Step S5: After the drone flight is over, the number of abnormal battery power generated by the drone flight is recorded, and the drone battery depth value is recorded. Single flight abnormality threshold The sum of is calculated, and the abnormal historical data of the drone battery power is used for time series prediction. The time series prediction value is ;

[0018] Furthermore, the specific process of using a power meter sensor to monitor the drone battery is as follows:

[0019] Step S1-1, confirm the drone calibration parameter standards, collect drone battery data under different batteries and different usage scenarios, confirm the standard value range, and establish a drone battery calibration standard database;

[0020] Step S1-2, setting the monitoring frequency of the power meter sensor on the drone battery;

[0021] Step S1-3: Correct the data type collected by the power meter sensor, and record the collected drone battery unit power data as battery power data , using drone battery standard data and battery power data Perform a calibration. If the calibration data is lower or higher than the standard data of the drone battery, it is defined as abnormal drone battery power;

[0022] Step S1-4: store the anomalies generated during each drone flight.

[0023] Install a power meter sensor on the drone battery and set an adaptive monitoring frequency to monitor its data. Use different battery standards to conduct big data learning, obtain the usage standards, safety standards and performance standards of individual batteries to establish a calibration benchmark standard library, and mark the abnormal power data of the drone battery monitored by the power meter sensor that is greater than the benchmark standard library as an overload abnormality, and mark the abnormal power data of the drone battery monitored by the power meter sensor that is less than the benchmark standard library as an underload abnormality.

[0024] Furthermore, based on the drone battery history data, all battery power data of the drone performing different tasks on different dates are collected. Summarize and obtain the total number of abnormalities that occur in the drone battery from the time it leaves the factory to the time it is scrapped, as well as the number of abnormalities that occur after each flight of the drone, and set the minimum value of the total number of abnormalities as the minimum life threshold of the drone battery , the number of abnormalities that occur after each flight check of the drone is recorded as .

[0025] Furthermore, the battery data of each flight of the drone obtained in step S2 is verified with the standard verification data in the drone battery verification standard library to obtain the number of abnormalities that occur each time. , accumulate the number of abnormal battery power of the drone to obtain the battery depth value , using the following formula:

[0026]

[0027] In the formula, Expressed as battery depth value, Expressed as Abnormal data, Represented as battery power data, Expressed as the maximum value of the battery power standard range, Expressed as the minimum value of the battery power standard range;

[0028] Get the single flight abnormality threshold , based on the historical data of drone battery usage Obtain the number of abnormalities caused by abnormal battery power in a single flight of the drone, and record it as a fault abnormality .

[0029] Obtain the total number of abnormalities that occur in the drone battery from the time it leaves the factory to the current flight, and perform abnormal evaluation and calculation on the battery power output.

[0030] Furthermore, the specific process of sending a signal to replace the drone battery is as follows:

[0031] Calculate the battery depth of the drone Single flight abnormality threshold The sum of , and the abnormal historical data of the drone battery power are used for time series prediction, and the time series prediction is calculated using the following formula:

[0032]

[0033] In the formula, is the time series prediction value, which means the number of times the battery will produce abnormalities during the next flight of the drone; It is expressed as a constant indicating battery abnormality during drone flight. It is expressed as the total number of abnormal data; Indicates the number of times the drone battery has abnormalities. Indicates the frequency of abnormal drone battery. Expressed as the UAV regression parameter; Expressed as a moving average parameter; It is expressed as the abnormal frequency coefficient of the drone battery; It is represented as the abnormal random error term of the drone battery;

[0034] Single flight abnormality threshold The value is the maximum number of abnormalities generated during a single drone flight. The value is obtained by bubble sorting and meets the single flight abnormality threshold. ;

[0035] The conditions for the drone to perform its flight mission are predicted to be:

[0036] ,

[0037] ,

[0038] When the conditions for the above two drones to perform flight missions are met at the same time, it is predicted that the drone can perform the flight mission, and the drone battery power output verification result is normal, and the flight mission can be performed normally; when any one or two of the conditions for the above two drones to perform flight missions are not met, it is predicted that the drone cannot perform the take-off mission, and a signal for replacing the drone battery is sent, so as to realize the real-time battery power verification of the drone flight to ensure the stability of the drone performance and reduce unexpected downtime or performance degradation;

[0039] Drone battery depth value With time series forecast value The sum is greater than or equal to the minimum lifespan threshold , or the drone battery depth value Single flight abnormality threshold The sum is greater than or equal to the minimum lifespan threshold When the drone is in flight, it is predicted whether the battery condition supports flight.

[0040] Further, a system applied to a UAV flight verification management method based on big data includes a sensor control module, a battery data acquisition module, a historical data module, a flight verification module, a battery power abnormality calculation module, a battery data recording and storage module, and an early warning module;

[0041] The sensor control module includes a sensor control unit and a data type correction unit; the sensor control unit is used to control the power meter sensor to open, close, configure parameters, initialize and transmit data; the data type correction unit is used to standardize the data format, convert the data type, verify the data, clean, normalize and handle exceptions;

[0042] The battery data acquisition module includes a sensor interface unit, a battery power data acquisition unit, a battery power data preprocessing unit, a storage unit, a sensor calibration unit and a transmission unit; the sensor interface unit is used to connect the power meter sensor and adapt to the connection of other battery power monitoring sensors; the battery power data acquisition unit is used to collect data acquired by the power meter sensor in real time; the battery power data preprocessing unit is used to filter, denoise and correct the data acquired by the power meter sensor; the storage unit is used to temporarily store the power meter sensor and the data of other battery power monitoring sensors; the sensor calibration unit is used to calibrate the power meter sensor regularly or for a set period of time; the transmission unit is used to transmit the processed data acquired by the power monitoring sensor;

[0043] The historical data module includes a single abnormality recording unit, a battery life threshold unit, a single abnormality limiting unit and a battery depth unit; the abnormality recording unit is used to obtain single aircraft abnormality records of different missions at different times from the historical data of the drone performing flight missions, and the acquired data is the number of abnormalities of a single flight of the drone; the battery life threshold unit is used to obtain the number of times the drone battery is scrapped when the number of abnormalities of the drone battery reaches a certain value based on the historical data of the drone, and record it as the minimum life threshold , when the total number of abnormalities of the drone battery is greater than or equal to the minimum life threshold When the UAV battery is used up, it is judged that the UAV battery life has been used up and the flight mission cannot be performed again; the single abnormality limiting unit is used to obtain the abnormal number of failures of the UAV due to abnormal battery power, and record it as a fault abnormality , when the number of abnormal battery power occurrences in a single drone flight is greater than or equal to the fault abnormality When the battery power output of the drone storage battery is abnormal, it is judged that the drone storage battery power output is abnormal, and a signal requesting return is immediately sent; the battery depth unit is used to count the total number of battery power abnormalities that occur in the drone battery from the factory to the current flight, which is recorded as the battery depth value , and has a battery depth value Less than the minimum lifespan threshold ;

[0044] The flight verification module includes a verification standard library unit and a verification scheduling unit; the verification standard library unit is used to match the use standards, safety standards and performance standards of various batteries to establish a benchmark standard library, and match and compare the data input by the battery data acquisition module with the data in the benchmark standard library; the verification scheduling unit is used to control the inspection standard, the inspection frequency and the inspection data type;

[0045] The battery power abnormality calculation module includes a battery power abnormality calculation unit, a life prediction calculation unit and a battery power abnormality classification unit; the battery power abnormality calculation unit is used to calculate the battery power abnormality and fault abnormality during a single flight of the drone , minimum lifespan threshold The life prediction calculation unit is used to calculate the remaining service life of the drone battery; the battery power abnormality classification unit is used to calculate and store the number of different abnormal types;

[0046] The battery data recording and storage module is used to record and store the abnormal type, abnormal number, flight date, single continuous flight time and remaining service life of the drone battery;

[0047] The early warning module includes an early warning classification unit and an early warning notification unit; the early warning classification unit is used for early warning during and after the flight of the UAV, and obtains accurate early warning instructions after calculation by the battery power abnormality calculation module; the early warning notification unit is used to send early warning information to the UAV control end, and close the early warning information when the early warning information is confirmed.

[0048] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: by installing a power meter sensor on the drone battery for real-time monitoring and calibration, the present invention can timely discover the abnormal situation of the drone battery, extract and analyze the historical data of the drone, and perform flight evaluation on the drone battery when performing a flight mission by predictive means, which can avoid damage to the drone and mission failure caused by battery failure or performance degradation, reduce maintenance and replacement costs, and optimize inventory at the same time. According to the battery status and prediction results, the battery inventory can be reasonably controlled to avoid excessive backlog of spare batteries, reduce inventory costs, and improve the mission efficiency of the drone flight. According to the prediction calculation, the flight mission of the drone can be arranged more accurately to ensure that each mission has sufficient power support and improve the success rate of the mission. Improve user experience, ensure stable battery performance of the drone during flight, reduce unexpected shutdown or performance degradation, and improve user trust in the performance of the drone. Users can understand the battery status at any time, plan and adjust the use plan, and improve the user experience. Flight calibration makes the application of drones in various fields more reliable, efficient and sustainable. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 It is a flow chart of a UAV flight verification management method based on big data of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1 The present invention provides a technical solution: a UAV flight verification management method based on big data

[0053] The UAV flight verification management method includes the following steps:

[0054] Step S1: Establish a standard library for drone battery calibration, and use a power meter sensor to monitor the drone battery. The power data of each drone battery unit monitored by the power meter sensor is recorded as battery power data. , using drone battery calibration standard library data and battery power data Verify storage;

[0055] Step S1-1, confirm the drone calibration parameter standards, collect drone battery data under different batteries and different usage scenarios, confirm the standard value range, and establish a drone battery calibration standard database;

[0056] Step S1-2, setting the monitoring frequency of the power meter sensor on the drone battery;

[0057] Step S1-3: Correct the data type collected by the power meter sensor, and record the collected drone battery unit power data as battery power data , using drone battery standard data and battery power data Perform a calibration. If the calibration data is lower or higher than the standard data of the drone battery, it is defined as abnormal drone battery power;

[0058] Step S1-4: store the anomalies generated during each drone flight.

[0059] Step S2: Obtain the minimum life threshold of the abnormal drone battery based on the drone battery history data and the number of abnormalities in drone battery power during each flight;

[0060] Step S3: Count the total number of abnormal battery power of the drone and record it as the battery depth value The single flight abnormality threshold is set as the data with the most abnormal battery power in the drone battery history data. , the number of abnormalities due to battery power failure in a single flight is recorded as a failure abnormality ;

[0061] Step S4: Calculate the number of abnormal battery times and battery depth value of the drone monitored and verified during the flight of the drone The sum is greater than or equal to the minimum lifespan threshold When the number of abnormal battery failures detected by the drone monitoring system during flight is greater than or equal to the abnormal failure When the drone is in flight, it is judged that there is an abnormality in the battery power output and a return signal is sent;

[0062] Step S4-1: The number of abnormal battery times of the drone monitored and verified during the flight of the drone With battery depth value to conduct and calculate;

[0063] when When the battery power output of the UAV is judged to be normal, the flight mission can continue;

[0064] when When the drone is detected to have abnormal battery power output, it sends a request to return home.

[0065] Step S4-2: The number of abnormal battery times of the drone monitored and verified during the flight of the drone Exception with fault Make comparisons;

[0066] when When the UAV battery power output is normal, it is judged that the UAV can continue to perform the flight mission;

[0067] when When the drone detects that the battery power output is abnormal and cannot continue to perform the flight mission, it sends a request to return.

[0068] Step S5: After the drone flight is over, the number of abnormal battery power generated by the drone flight is recorded, and the drone battery depth value is recorded. Single flight abnormality threshold The sum of is calculated, and the abnormal historical data of the drone battery power is used for time series prediction. The time series prediction value is ;

[0069] Based on the drone battery history data, all the battery power data of the drone performing different tasks on different dates are collected. Summarize and obtain the total number of abnormalities that occur in the drone battery from the time it leaves the factory to the time it is scrapped, as well as the number of abnormalities that occur after each flight of the drone, and set the minimum value of the total number of abnormalities as the minimum life threshold of the drone battery , the number of abnormalities that occur after each flight of the drone is recorded as .

[0070] The number of abnormalities that occur after each flight of the drone obtained in step S2 , accumulate the number of abnormal battery power of the drone to obtain the battery depth value , using the following formula:

[0071]

[0072] In the formula, Expressed as battery depth value, Expressed as Abnormal data, Represented as battery power data, Expressed as the maximum value of the battery power standard range, Expressed as the minimum value of the battery power standard range;

[0073] Get the single flight abnormality threshold , based on the historical data of drone battery usage Obtain the number of abnormalities caused by abnormal battery power in a single flight of the drone, and record it as a fault abnormality .

[0074] Calculate the battery depth of the drone Single flight abnormality threshold The sum of , and the abnormal historical data of the drone battery power are used for time series prediction, and the time series prediction is calculated using the following formula:

[0075]

[0076] In the formula, is the time series prediction value, which means the number of times the battery will produce abnormalities during the next flight of the drone; It is expressed as a constant indicating battery abnormality during drone flight. It is expressed as the total number of abnormal data; Indicates the number of times the drone battery has abnormalities. Indicates the frequency of abnormal drone battery. Expressed as the UAV regression parameter; Expressed as a moving average parameter; It is expressed as the abnormal frequency coefficient of the drone battery; It is represented as the abnormal random error term of the drone battery;

[0077] The conditions for the drone to perform its flight mission are predicted to be:

[0078] ,

[0079] ,

[0080] When the conditions for the above two drones to perform flight missions are met at the same time, it is predicted that the drone can perform the flight mission, the drone battery power output is normal, and the flight mission can be performed normally; when any one or two of the conditions for the above two drones to perform flight missions are not met, it is predicted that the drone cannot perform the take-off mission, and a signal for replacing the drone battery is sent to realize real-time battery power verification of the drone flight to ensure stable drone performance and reduce unexpected downtime or performance degradation;

[0081] Drone battery depth value With time series forecast value The sum is greater than or equal to the minimum lifespan threshold , or the drone battery depth value Single flight abnormality threshold The sum is greater than or equal to the minimum lifespan threshold When the drone is in flight, it is predicted whether the battery condition supports flight.

[0082] A system applied to a UAV flight verification management method based on big data includes a sensor control module, a battery data acquisition module, a historical data module, a flight verification module, a battery power abnormality calculation module, a battery data recording and storage module, and an early warning module;

[0083] The sensor control module includes a sensor control unit and a data type correction unit; the sensor control unit is used to control the power meter sensor to open, close, configure parameters, initialize and transmit data; the data type correction unit is used to standardize the data format, convert the data type, verify the data, clean, normalize and handle exceptions;

[0084] The battery data acquisition module includes a sensor interface unit, a battery power data acquisition unit, a battery power data preprocessing unit, a storage unit, a sensor calibration unit and a transmission unit; the sensor interface unit is used to connect the power meter sensor and adapt to the connection of other battery power monitoring sensors; the battery power data acquisition unit is used to collect data acquired by the power meter sensor in real time; the battery power data preprocessing unit is used to filter, denoise and correct the data acquired by the power meter sensor; the storage unit is used to temporarily store the power meter sensor and the data of other battery power monitoring sensors; the sensor calibration unit is used to calibrate the power meter sensor regularly or for a set period of time; the transmission unit is used to transmit the processed data acquired by the power monitoring sensor;

[0085] The historical data module includes a single abnormality recording unit, a battery life threshold unit, a single abnormality limiting unit and a battery depth unit; the abnormality recording unit is used to obtain single aircraft abnormality records of different missions at different times from the historical data of the drone performing flight missions, and the acquired data is the number of abnormalities of a single flight of the drone; the battery life threshold unit is used to obtain the number of times the drone battery is scrapped when the number of abnormalities of the drone battery reaches a certain value based on the historical data of the drone, and record it as the minimum life threshold , when the total number of abnormalities of the drone battery is greater than or equal to the minimum life threshold When the UAV battery is used up, it is judged that the UAV battery life has been used up and the flight mission cannot be performed again; the single abnormality limiting unit is used to obtain the abnormal number of failures of the UAV due to abnormal battery power, and record it as a fault abnormality , when the number of abnormal battery power occurrences in a single drone flight is greater than or equal to the fault abnormality When the battery power output of the drone storage battery is abnormal, it is judged that the drone storage battery power output is abnormal, and a signal requesting return is immediately sent; the battery depth unit is used to count the total number of battery power abnormalities that occur during all flights of the drone battery from the factory to the current flight, which is recorded as the battery depth value , and has a battery depth value Less than the minimum lifespan threshold ;

[0086] The flight verification module includes a verification standard library unit and a verification scheduling unit; the verification standard library unit is used to match the use standards, safety standards and performance standards of various batteries to establish a benchmark standard library, and match and compare the data input by the battery data acquisition module with the data in the benchmark standard library; the verification scheduling unit is used to control the inspection standard, the inspection frequency and the inspection data type;

[0087] The battery power abnormality calculation module includes a battery power abnormality calculation unit, a life prediction calculation unit and a battery power abnormality classification unit; the battery power abnormality calculation unit is used to calculate the battery power abnormality and fault abnormality during a single flight of the drone , minimum lifespan threshold The life prediction calculation unit is used to calculate the remaining service life of the drone battery; the battery power abnormality classification unit is used to calculate and store the number of different abnormal types;

[0088] The battery data recording and storage module is used to record and store the abnormal type, abnormal number, flight date, single continuous flight time and remaining service life of the drone battery;

[0089] The early warning module includes an early warning classification unit and an early warning notification unit; the early warning classification unit is used for early warning during and after the flight of the UAV, and obtains accurate early warning instructions after calculation by the battery power abnormality calculation module; the early warning notification unit is used to send early warning information to the UAV control end, and close the early warning information when the early warning information is confirmed.

[0090] Example 1: Sum the battery power anomalies based on historical drone battery data to obtain the battery depth value , get the battery depth value 95, the minimum life threshold of the drone battery abnormality =100, the drone single flight abnormality threshold 5, the drone is abnormal is 10; the battery voltage data monitored by the power meter sensor for this flight is: 3.7, 3.5, 4.2, 2.8, 4.5, 3.9, 4.8, 3.6, 2.5, 4.6, 3.4, 3.8, 4.1, 4.9, 2.7, taken from the drone battery calibration standard library The value of is 4.5, take The value is 3.0, using the formula:

[0091]

[0092] According to the calibration data of the drone battery calibration standard library, the number of abnormal battery occurrences during the next flight of the drone is monitored and verified. 6 times, the abnormal threshold of a single flight of a drone is 6;

[0093] The flight is predicted based on the battery voltage data of the drone’s last flight, using the time series prediction formula:

[0094]

[0095] Drone regression parameters The value is 0.5, the average moving parameter The value is -0.3, which is the constant of battery abnormality during drone flight The value is 0.2, and the value of the drone battery abnormal random error term is 1, then the calculation is:

[0096]

[0097] Then there is, ;

[0098] Then according to the abnormal threshold of a single flight of the drone Predict the next flight of the drone:

[0099] Then there is, ;

[0100] The conditions are not less than the minimum lifespan threshold , predicts that the drone battery does not support the next flight conditions, and the current battery used by the drone needs to be replaced and cannot be used again. A battery replacement signal is sent to the drone control terminal to complete the prediction.

[0101] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0102] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A UAV flight verification management method based on big data, characterized in that: The UAV flight verification management method comprises the following steps: Step S1: Establish a standard library for drone battery calibration, and use a power meter sensor to monitor the drone battery. The execution data of each parameter of each drone battery unit monitored by the power meter sensor is recorded as battery power data. , using drone battery calibration standard library data and battery power data Verify storage; Step S2: Obtain the minimum life threshold of the abnormal drone battery based on the drone battery history data and the number of abnormalities in drone battery power during each flight; Step S3: Count the total number of abnormal battery power of the drone and record it as the battery depth value The single flight abnormality threshold is set as the data with the most abnormal battery power in the drone battery history data. The number of abnormalities due to battery power failure in a single flight is recorded as a failure abnormality. ; Step S4: Calculate the number of abnormal battery times and battery depth value of the drone monitored and verified during the flight of the drone The sum is greater than or equal to the minimum lifespan threshold When the number of abnormalities of the drone battery monitored and checked during the flight is greater than or equal to the abnormal fault When the UAV is detected to have abnormal battery power output, a return signal is sent; Step S5: After the drone flight is over, the number of abnormal battery power generated by the drone flight is recorded, and the drone battery depth value is recorded. Single flight abnormality threshold The sum of is calculated, and the abnormal historical data of the drone battery power is used for time series prediction. The time series prediction value is .

2. The method for managing UAV flight verification based on big data according to claim 1, characterized in that: In step S1, the drone battery calibration standard library data and battery power data are used The specific process of verification storage is as follows: Step S1-1, confirm the drone calibration parameter standards, collect drone battery data under different batteries and different usage scenarios, confirm the standard value range, and establish a drone battery calibration standard database; Step S1-2, setting the monitoring frequency of the power meter sensor on the drone battery; Step S1-3: Correct the data type collected by the power meter sensor, and record the collected drone battery unit power data as battery power data , using drone battery standard data and battery power data Perform a calibration. If the calibration data is lower or higher than the standard data of the drone battery, it is defined as abnormal drone battery power; Step S1-4: store the battery power anomaly generated by each drone flight.

3. The method for managing UAV flight verification based on big data according to claim 1, characterized in that: In step S2, all battery power data of the drones performing different tasks on different dates are collected based on the drone battery history data. Summarize and obtain the total number of abnormalities that occur in the drone battery from the time it leaves the factory to the time it is scrapped, as well as the number of abnormalities that occur after each flight of the drone, and set the minimum value of the total number of abnormalities as the minimum life threshold of the drone battery , the number of abnormalities that occur after each flight of the drone is recorded as .

4. The method for managing UAV flight verification based on big data according to claim 3 is characterized by: In step S3, the number of abnormalities that occur in each flight of the drone obtained in step S2 is , accumulate the number of abnormal battery power of the drone to obtain the battery depth value , using the following formula: ； In the formula, Expressed as battery depth value, Expressed as Abnormal data, Represented as battery power data, Expressed as the maximum value of the battery power standard range, Expressed as the minimum value of the battery power standard range; Get the single flight abnormality threshold , based on the historical data of drone battery usage Obtain the number of abnormalities caused by abnormal battery power in a single flight of the drone, and record it as a fault abnormality .

5. The method for managing UAV flight verification based on big data according to claim 4 is characterized in that: In step S4, the specific process of sending a return request signal is as follows: Step S4-1: The number of abnormal battery times of the drone monitored and verified during the flight of the drone With battery depth value to conduct and calculate; when When the battery power output of the UAV is judged to be normal, the flight mission can continue; when When the drone is detected to have abnormal battery power output, it sends a request to return home. Step S4-2: The number of abnormal battery times of the drone monitored and verified during the flight of the drone Exception with fault Make comparisons; when When the UAV battery power output is normal, it is judged that the UAV can continue to perform the flight mission; when When the drone detects that the battery power output is abnormal and cannot continue to perform the flight mission, it sends a request to return.

6. The method for managing UAV flight verification based on big data according to claim 4 is characterized by: The specific process of step S5 is as follows: Calculate the battery depth of the drone Single flight abnormality threshold The sum of , and the abnormal historical data of the drone battery power are used for time series prediction, and the time series prediction is calculated using the following formula: ； In the formula, is the time series prediction value, which means the number of times the battery will produce abnormalities during the next flight of the drone; It is expressed as a constant indicating battery abnormality during drone flight. It is expressed as the total number of abnormal data; Indicates the number of times the drone battery has abnormalities. Indicates the frequency of abnormal drone battery. Expressed as the UAV regression parameter; Expressed as a moving average parameter; It is expressed as the abnormal frequency coefficient of the drone battery; It is represented as the abnormal random error term of the drone battery; The conditions for the drone to perform its flight mission are predicted to be: ； ； When the conditions for the above two drones to perform flight missions are met at the same time, it is predicted that the drone can perform the flight mission, the drone battery power output is normal, and the flight mission can be performed normally; when any one or two of the conditions for the above two drones to perform flight missions are not met, it is predicted that the drone cannot perform the take-off mission, and a signal to replace the drone battery is sent.

7. A UAV flight verification management system based on big data, applied to a UAV flight verification management method based on big data as claimed in any one of claims 1 to 6, characterized in that: The flight verification management system includes a sensor control module and a battery data acquisition module; The sensor control module includes a sensor control unit and a data type correction unit; the sensor control unit is used to control the power meter sensor to open, close, configure parameters, initialize and transmit data; the data type correction unit is used to standardize the data format, convert the data type, verify the data, clean, normalize and handle exceptions; The battery data acquisition module includes a sensor interface unit, a battery power data acquisition unit, a battery power data preprocessing unit, a storage unit, a sensor calibration unit and a transmission unit; the sensor interface unit is used to connect the power meter sensor and adapt to the connection of other battery power monitoring sensors; the battery power data acquisition unit is used to collect data acquired by the power meter sensor in real time; the battery power data preprocessing unit is used to filter, denoise and correct the data acquired by the power meter sensor; the storage unit is used to temporarily store the data of the power meter sensor and other adapted battery power monitoring sensors; The sensor calibration unit is used to calibrate the power meter sensor regularly or for a set period of time; The transmission unit is used to transmit the processed data acquired by the power monitoring sensor.

8. The UAV flight verification management system based on big data according to claim 7 is characterized by: The flight verification management system also includes a historical data module and a flight verification module; The historical data module includes a single abnormality recording unit, a battery life threshold unit, a single abnormality limiting unit and a battery depth unit; the abnormality recording unit is used to obtain single aircraft abnormality records of different missions at different times from the historical data of the drone performing flight missions, and the acquired data is the number of abnormalities of a single flight of the drone; the battery life threshold unit is used to obtain the number of times the drone battery is scrapped when the number of abnormalities of the drone battery reaches a certain value based on the historical data of the drone, and record it as the minimum life threshold , when the total number of abnormalities of the drone battery is greater than or equal to the minimum life threshold When the UAV battery is used up, it is judged that the UAV battery life has been used up and the flight mission cannot be performed again; the single abnormality limiting unit is used to obtain the abnormal number of failures of the UAV due to abnormal battery power, and record it as a fault abnormality , when the number of abnormal battery power occurrences in a single drone flight is greater than or equal to the fault abnormality When the battery power output of the drone storage battery is abnormal, it is judged that the drone storage battery power output is abnormal, and a signal requesting return is immediately sent; the battery depth unit is used to count the total number of battery power abnormalities that occur in the drone battery from the factory to the current flight, which is recorded as the battery depth value , and has a battery depth value Less than the minimum lifespan threshold ; The flight verification module includes a verification standard library unit and a verification scheduling unit; The verification standard library unit is used to match the usage standards, safety standards and performance standards of various batteries to establish a benchmark standard library, and match and compare the data transmitted by the battery data acquisition module with the data in the benchmark standard library; the verification scheduling unit is used to control the inspection standard, the frequency of verification and the type of verification data.

9. The UAV flight verification management system based on big data according to claim 7 is characterized by: The flight verification management system also includes a battery power abnormality calculation module and a battery data recording and storage module; The battery power abnormality calculation module includes a battery power abnormality calculation unit, a life prediction calculation unit and a battery power abnormality classification unit; the battery power abnormality calculation unit is used to calculate the battery power abnormality and fault abnormality during a single flight of the drone , minimum lifespan threshold The life prediction calculation unit is used to calculate the remaining service life of the drone battery; the battery power abnormality classification unit is used to calculate and store the number of different abnormal types; The battery data recording and storage module is used to record and store the abnormal type, abnormal number, flight date, single continuous flight time and remaining service life of the drone battery.

10. The UAV flight verification management system based on big data according to claim 7 is characterized by: The flight verification management system also includes an early warning module; The early warning module includes an early warning classification unit and an early warning notification unit; the early warning classification unit is used for early warning during and after the flight of the UAV, and obtains accurate early warning instructions after calculation by the battery power abnormality calculation module; the early warning notification unit is used to send early warning information to the UAV control end, and close the early warning information when the early warning information is confirmed.

Images