UAV adaptive scheduling analysis method and system based on fuzzy artificial intelligence

Abstract

The present invention discloses a method and system for self-adaptive scheduling analysis of unmanned aerial vehicles based on fuzzy artificial intelligence, and relates to the field of unmanned aerial vehicle control technology. The method comprises the following steps: obtaining unmanned aerial vehicle flight parameter data through an unmanned aerial vehicle flight control system; the unmanned aerial vehicle flight control system transmits the unmanned aerial vehicle flight parameter data to an unmanned aerial vehicle ground control station; the unmanned aerial vehicle ground control station receives the unmanned aerial vehicle flight parameter data; analyzing the unmanned aerial vehicle flight parameter data to obtain the unmanned aerial vehicle fault degree value; analyzing the first-level fault severity of the unmanned aerial vehicle according to the unmanned aerial vehicle fault degree value; analyzing the second-level fault severity of the unmanned aerial vehicle according to the unmanned aerial vehicle flight parameter data; and scheduling the unmanned aerial vehicle in combination with the first-level fault severity and the second-level fault severity. The present invention achieves the effect of accurately scheduling the unmanned aerial vehicle by scheduling the unmanned aerial vehicle in combination with the first-level fault severity and the second-level fault severity, and solves the problem of difficulty in accurately scheduling the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle control, and in particular to a method and system for self-adaptive scheduling analysis of unmanned aerial vehicles based on fuzzy artificial intelligence. Background Art

[0002] With the development of science and technology, drones have been widely used due to their flexibility and versatility, from military reconnaissance and surveillance to civilian logistics and agricultural monitoring. As drone technology advances, they are required to operate in more complex, dynamic and uncertain environments. Therefore, drones are required to perform tasks autonomously in complex and changing environments, which requires drones to have a high degree of adaptability. Artificial intelligence technology, especially fuzzy logic, provides the possibility to deal with uncertainty and ambiguity in scheduling. Fuzzy logic can simulate human intuitive judgment and decision-making process, and is suitable for dealing with complex problems in drone scheduling.

[0003] The existing UAV adaptive scheduling system establishes a deterministic mathematical model, inputs UAV related data into the mathematical model to obtain scheduling instructions, and the UAV is scheduled according to the scheduling instructions to realize the UAV adaptive scheduling function.

[0004] For example, the invention patent application with publication number: CN113379172A discloses a multi-UAV automatic operation scheduling system and scheduling method, including: a scheduling server, several regional scheduling centers, multiple UAVs, a UAV airport and a communication station; the scheduling server accepts the demand input of the terminal user and forwards it to the regional scheduling center through a public or private network; the regional scheduling center generates a task plan and sends it to the UAV airport through a public or private network and 4G / 5G, and the UAV airport then sends it to the UAV through the 4G / 5G network or a dedicated microwave data link to perform specific flight missions. The UAV airport includes a UAV automatic airport and an alternate landing field; the communication station is a dedicated microwave data link relay device within a certain area, which is used to supplement the communication blind spots in urban obstruction environments.

[0005] For example, the patent application with publication number: CN108830450A discloses a drone cluster scheduling method and system, including: the drone cluster includes at least one master drone, and multiple slave drones that are communicatively connected to the master drone; the drone cluster scheduling method includes: generating a cluster waypoint task; sending the cluster waypoint task to the master drone in the drone cluster; the master drone receives the cluster waypoint task; the master drone decomposes the cluster waypoint task into multiple sub-waypoint tasks according to the cluster waypoint task; the sub-waypoint tasks are allocated and sent to the corresponding drones; the drones receive the sub-waypoint tasks to execute the task content; wherein the cluster waypoint task includes one or more of the following information: drone quantity information, drone type requirement information, macro action content information, location airspace information, and time content information.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the prior art, existing drone scheduling methods perform poorly when dealing with uncertainty and ambiguity in the environment, especially when environmental conditions change rapidly, and there is a problem of difficulty in accurately scheduling drones. Summary of the invention

[0008] The embodiments of the present application solve the problem in the prior art that it is difficult to accurately schedule drones by providing a drone adaptive scheduling analysis method and system based on fuzzy artificial intelligence, thereby achieving accurate drone scheduling.

[0009] An embodiment of the present application provides a UAV adaptive scheduling analysis method based on fuzzy artificial intelligence, comprising the following steps: obtaining UAV flight parameter data through a UAV flight control system; the UAV flight control system transmits the UAV flight parameter data to a UAV ground control station; the UAV ground control station receives the UAV flight parameter data; analyzing the UAV flight parameter data to obtain a UAV fault degree value; analyzing the first-level fault severity of the UAV according to the UAV fault degree value; analyzing the second-level fault severity of the UAV according to the UAV flight parameter data; and scheduling the UAV in combination with the first-level fault severity and the second-level fault severity.

[0010] Furthermore, the specific analysis process of analyzing the UAV flight parameter data to obtain the UAV fault degree value is: obtaining the UAV system temperature and the UAV battery voltage in the UAV flight parameter data, setting the UAV fault degree value, taking the UAV system temperature and the UAV battery voltage as input and substituting the UAV fault degree value as output into the fuzzy calculation process preset in the database to obtain the UAV fault degree value.

[0011] Furthermore, the specific analysis process of analyzing the first-level fault severity of the drone based on the drone fault degree value is: obtain the drone fault degree value, obtain a preset first threshold from the database, when the drone fault degree value is below the first threshold, it indicates that the first-level fault severity of the drone is that no fault has occurred; when the drone fault degree value is greater than the first threshold, it indicates that the first-level fault severity of the drone is that a fault has occurred.

[0012] Furthermore, the specific analysis process of analyzing the severity of the secondary fault of the drone based on the drone flight parameter data is as follows: the drone flight parameter data includes drone battery fault parameter data and drone flight fault parameter data; the drone battery fault degree assessment coefficient is obtained based on the analysis of the drone battery fault parameter data, and the drone battery fault degree assessment coefficient is used to reflect the degree of fault in the battery of the drone; the drone battery fault degree is analyzed based on the drone battery fault degree assessment coefficient; the drone flight fault degree assessment index is obtained based on the analysis of the drone flight fault parameter data, and the drone flight fault degree assessment index is used to reflect the degree of fault in flight of the drone; the drone flight fault degree is analyzed based on the drone flight fault degree assessment index; the drone fault assessment index is obtained based on the analysis of the drone battery fault degree assessment coefficient and the drone flight fault degree assessment index, and the drone fault assessment index is used to reflect the severity of the drone fault; the drone fault degree is analyzed based on the drone fault assessment index; the severity of the secondary fault of the drone is analyzed by comprehensively analyzing the drone battery fault degree, the drone flight fault degree and the drone fault degree.

[0013] Furthermore, the specific analysis process of analyzing the degree of drone battery failure according to the drone battery failure degree assessment coefficient is as follows: obtaining the drone battery failure degree assessment coefficient, obtaining a preset drone battery failure threshold from a database, comparing the drone battery failure degree assessment coefficient with the drone battery failure threshold, when the drone battery failure degree assessment coefficient is below the drone battery failure threshold, it indicates that the drone battery has not failed; when the drone battery failure degree assessment coefficient is greater than the drone battery failure threshold, it indicates that the drone battery has failed; the specific analysis process of analyzing the degree of drone flight failure according to the drone flight failure degree assessment index is as follows: obtaining the drone flight failure degree assessment index, obtaining the drone battery failure threshold from a database A preset UAV flight fault threshold is used, and the UAV flight fault degree assessment index is compared with the UAV flight fault threshold. When the UAV flight fault degree assessment index is below the UAV flight fault threshold, it indicates that the UAV flight has not failed; when the UAV flight fault degree assessment index is greater than the UAV flight fault threshold, it indicates that the UAV flight has failed; the specific analysis process of analyzing the UAV fault degree according to the UAV fault assessment index is as follows: obtaining the UAV fault assessment index, obtaining the preset UAV fault threshold from the database, when the UAV fault assessment index is below the UAV fault threshold, it indicates that the UAV has not failed; when the UAV fault assessment index is greater than the UAV fault threshold, it indicates that the UAV has failed.

[0014] Furthermore, the specific analysis process of comprehensively analyzing the secondary fault severity of the drone by combining the drone battery failure degree, the drone flight failure degree and the drone failure degree is as follows: when the drone battery failure degree, the drone flight failure degree and the drone failure degree of the drone battery failure, the drone flight failure and the drone failure occur at the same time, it indicates that the secondary fault severity of the drone is a serious fault, and the drone is subject to primary scheduling; when any two of the drone battery failure, the drone flight failure and the drone failure occur, it indicates that the secondary fault severity of the drone is a medium fault, and the drone is subject to secondary scheduling; when one of the drone battery failure, the drone flight failure and the drone failure occurs, it indicates that the secondary fault severity of the drone is a minor fault, and the drone is subject to tertiary scheduling; when none of the drone battery failure, the drone flight failure and the drone failure occurs, it indicates that the secondary fault severity of the drone is no fault, and the drone is not scheduled.

[0015] Furthermore, the specific analysis process for scheduling UAVs in combination with the first-level fault severity and the second-level fault severity is: obtaining the first-level fault severity of the UAV, extracting UAVs with faults at the first-level fault severity and performing an analysis process and a scheduling process for the second-level fault severity; after the scheduling of UAVs with faults at the first-level fault severity is completed, performing a second-level fault severity analysis and scheduling on UAVs with no faults at the first-level fault severity.

[0016] Furthermore, the specific process of the first-level scheduling is: fly the drone to a safe area for emergency landing, terminate the mission of the drone, and start the backup drone to continue the mission; the specific process of the second-level scheduling is: fly the drone to a safe area, suspend mission execution, and check the faulty part. If it can be repaired within the specified time, continue to perform the mission. If it cannot be repaired, start the backup drone to replace it and continue to perform the mission; the specific process of the third-level scheduling is: the drone continues to perform the mission, and at the same time strengthens the monitoring of the drone to ensure that the drone's failure will not worsen.

[0017] Furthermore, the specific method for obtaining the drone fault assessment index is as follows: obtaining the number of drones and numbering the drones; setting multiple time monitoring points; obtaining the preset drone battery fault degree assessment coefficient and the weight ratio of the drone flight fault degree assessment index from the database; constructing a drone fault assessment index calculation formula; the specific drone fault assessment index calculation formula is:

[0018] ;

[0019] In the formula, Expressed as The drone The UAV fault assessment index at each time monitoring point, , Indicates the number of the drone. Expressed as the total number of drones, , It is the number of the time monitoring point. Expressed as the total number of time monitoring points, Expressed as The drone The evaluation coefficient of the drone battery failure degree at each time monitoring point is: Expressed as The drone The UAV flight failure degree assessment index at each time monitoring point, It is expressed as the weight ratio of the drone battery failure assessment coefficient in the drone failure assessment index. It is expressed as the weight ratio of the UAV flight failure degree assessment index in the UAV failure assessment index.

[0020] An embodiment of the present application provides a UAV adaptive scheduling and analysis system based on fuzzy artificial intelligence, including: a data acquisition module, a data transmission module, a data receiving module, a fuzzy calculation module, a primary fault analysis module, a secondary fault analysis module and a scheduling analysis module; wherein, the data acquisition module is used to acquire UAV flight parameter data through the UAV flight control system; the data transmission module is used for the UAV flight control system to transmit the UAV flight parameter data to the UAV ground control station; the data receiving module is used for the UAV ground control station to receive the UAV flight parameter data; the fuzzy calculation module is used to analyze the UAV flight parameter data to obtain the UAV fault degree value; the primary fault analysis module is used to analyze the primary fault severity of the UAV according to the UAV fault degree value; the secondary fault analysis module is used to analyze the secondary fault severity of the UAV according to the UAV flight parameter data; the scheduling analysis module is used to schedule the UAV in combination with the primary fault severity and the secondary fault severity.

[0021] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0022] 1. The fault degree value of the drone is obtained by analyzing the drone flight parameter data, and the first-level fault severity of the drone is analyzed according to the drone fault degree value. The second-level fault severity of the drone is analyzed according to the drone flight parameter data, so that the drone is dispatched in combination with the first-level fault severity and the second-level fault severity, thereby realizing accurate and efficient dispatch of drones, effectively solving the problem of difficulty in accurate drone dispatch in the existing technology.

[0023] 2. By analyzing the drone battery failure parameter data, the drone battery failure degree assessment coefficient is obtained, and then the drone battery failure degree is analyzed according to the drone battery failure degree assessment coefficient, thereby accurately analyzing whether the drone has a battery failure.

[0024] 3. By analyzing the UAV flight fault parameter data, the UAV flight fault degree assessment index is obtained, and then the UAV flight fault degree is analyzed according to the UAV flight fault degree assessment index, thereby accurately analyzing whether the UAV has a fault in flight. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flow chart of a method for analyzing the adaptive scheduling of unmanned aerial vehicles based on fuzzy artificial intelligence provided in an embodiment of the present application;

[0026] Figure 2 A graph of the drone fault assessment index provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of the structure of a UAV adaptive scheduling and analysis system based on fuzzy artificial intelligence provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The embodiments of the present application solve the problem in the prior art that it is difficult to accurately schedule drones by providing a drone adaptive scheduling analysis method and system based on fuzzy artificial intelligence. The drone flight parameter data is analyzed to obtain the drone fault degree value, and the first-level fault severity of the drone is analyzed according to the drone fault degree value. The second-level fault severity of the drone is analyzed according to the drone flight parameter data, and the drone is scheduled in combination with the first-level fault severity and the second-level fault severity, thereby achieving accurate and efficient scheduling of drones.

[0029] The technical solution in the embodiment of the present application is to solve the above-mentioned problem of difficulty in accurately dispatching drones. The overall idea is as follows:

[0030] The UAV flight parameter data such as the UAV battery fault parameter data and the UAV flight fault parameter data are obtained through the UAV flight control system; the UAV flight control system transmits the UAV flight parameter data to the UAV ground control station; the UAV ground control station receives the UAV flight parameter data; the UAV flight parameter data is analyzed to obtain the UAV fault degree value; the primary fault severity of the UAV is analyzed according to the UAV fault degree value; the secondary fault severity of the UAV is analyzed according to the UAV flight parameter data, including: obtaining the UAV battery fault degree assessment coefficient according to the UAV battery fault degree assessment coefficient, and analyzing the UAV battery fault degree according to the UAV battery fault degree assessment coefficient; obtaining the UAV flight fault degree assessment index according to the UAV flight fault parameter data, and analyzing the UAV flight fault degree according to the UAV flight fault degree assessment index; obtaining the UAV fault assessment index according to the UAV battery fault degree assessment coefficient and the UAV flight fault degree assessment index, and analyzing the UAV fault degree according to the UAV fault assessment index; analyzing the secondary fault severity of the UAV by comprehensively analyzing the UAV battery fault degree, the UAV flight fault degree and the UAV fault degree; dispatching the UAV in combination with the primary fault severity and the secondary fault severity; achieving the effect of accurately and efficiently dispatching the UAV.

[0031] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0032] like Figure 1 As shown, it is a flow chart of the UAV adaptive scheduling analysis method based on fuzzy artificial intelligence provided in an embodiment of the present application, and the method includes the following steps: obtaining UAV flight parameter data through the UAV flight control system; the UAV flight control system transmits the UAV flight parameter data to the UAV ground control station; the UAV ground control station receives the UAV flight parameter data; analyzing the UAV flight parameter data to obtain the UAV fault degree value; analyzing the first-level fault severity of the UAV according to the UAV fault degree value; analyzing the second-level fault severity of the UAV according to the UAV flight parameter data; and scheduling the UAV in combination with the first-level fault severity and the second-level fault severity.

[0033] Furthermore, the specific analysis process of analyzing the UAV flight parameter data to obtain the UAV fault degree value is as follows: obtaining the UAV system temperature and the UAV battery voltage in the UAV flight parameter data, setting the UAV fault degree value, taking the UAV system temperature and the UAV battery voltage as input and substituting the UAV fault degree value as output into the fuzzy calculation process preset in the database to obtain the UAV fault degree value.

[0034] In this embodiment, the drone system temperature and drone battery voltage of the drone are substituted as inputs into the fuzzy calculation process of the artificial intelligence preset in the database, and the obtained drone fault degree value is the output. The drone fault degree value is used to quantify the possibility of possible failure of the drone.

[0035] Furthermore, the specific analysis process of analyzing the first-level fault severity of the drone based on the drone fault degree value is: obtain the drone fault degree value, obtain a preset first threshold value from the database, when the drone fault degree value is below the first threshold value, it indicates that the first-level fault severity of the drone is that no fault has occurred; when the drone fault degree value is greater than the first threshold value, it indicates that the first-level fault severity of the drone is that a fault has occurred.

[0036] In this embodiment, the value range of the drone fault degree value is the domain, which is a preset value range in the fuzzy calculation process preset in the database. The larger the drone fault degree value, the greater the possibility that the drone may fail, and the smaller the drone fault degree value, the smaller the possibility that the drone may fail.

[0037] Furthermore, the specific analysis process of analyzing the severity of the secondary fault of the drone based on the drone flight parameter data is as follows: the drone flight parameter data includes the drone battery fault parameter data and the drone flight fault parameter data; the drone battery fault degree assessment coefficient is obtained based on the analysis of the drone battery fault parameter data, and the drone battery fault degree assessment coefficient is used to reflect the degree of fault in the battery of the drone; the drone battery fault degree is analyzed based on the drone battery fault degree assessment coefficient; the drone flight fault degree assessment index is obtained based on the analysis of the drone flight fault parameter data, and the drone flight fault degree assessment index is used to reflect the degree of fault in flight of the drone; the drone flight fault degree is analyzed based on the drone flight fault degree assessment index; the drone fault assessment index is obtained based on the analysis of the drone battery fault degree assessment coefficient and the drone flight fault degree assessment index, and the drone fault assessment index is used to reflect the severity of the drone fault; the drone fault degree is analyzed based on the drone fault assessment index; the severity of the drone secondary fault is analyzed by comprehensively analyzing the drone battery fault degree, the drone flight fault degree and the drone fault degree.

[0038] In this embodiment, the specific method for obtaining the drone battery failure degree assessment coefficient is as follows: obtain the number of drones and number the drones; set multiple time monitoring points and number the time monitoring points; obtain data multiple times at each time monitoring point and number the number of data acquisitions; obtain the preset drone system temperature, drone battery temperature and drone battery voltage weight ratio from the database; construct a drone battery failure degree assessment coefficient calculation formula; the specific drone battery failure degree assessment coefficient calculation formula is:

[0039] ;

[0040] In the formula, Expressed as The drone The evaluation coefficient of the drone battery failure degree at each time monitoring point is: , Indicates the number of the drone. Expressed as the total number of drones, , It is the number of the time monitoring point. Expressed as the total number of time monitoring points, Expressed as The drone The first time monitoring point The temperature of the UAV system at the time of data acquisition, Expressed as The drone The first time monitoring point The drone battery temperature at the time of data acquisition, , Indicates the number of times data is obtained. Represents the total number of data acquisitions, Expressed as The drone The first time monitoring point The battery voltage of the drone when the data was acquired. Expressed as The standard value of the drone system temperature of the drone, Expressed as The standard value of drone battery temperature for a drone, Expressed as The standard value of drone battery voltage for a drone, It is expressed as the weight ratio of the drone system temperature in the drone battery failure degree assessment coefficient, It is expressed as the weight ratio of the drone battery temperature in the drone battery failure degree assessment coefficient, It is expressed as the weight ratio of the drone battery voltage in the drone battery fault degree assessment coefficient.

[0041] It is represented by the weight ratio corresponding to the preset UAV system temperature obtained from the database, which represents the numerical value of the influence of the UAV system temperature on the UAV battery fault degree assessment coefficient. When used, the weight ratio corresponding to the UAV system temperature can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the UAV system temperature and the weight ratio corresponding to the preset UAV system temperature in the database form a mapping set, and the weight ratio corresponding to the UAV system temperature is obtained according to the UAV system temperature input mapping set, and the mapping relationship can be one-to-one or many-to-one.

[0042] It is represented by the weight ratio corresponding to the preset drone battery temperature obtained from the database, which represents the numerical value of the influence of the drone battery temperature on the drone battery fault degree assessment coefficient. When used, the weight ratio corresponding to the drone battery temperature can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the drone battery temperature and the weight ratio corresponding to the drone battery temperature preset in the database form a mapping set, and the weight ratio corresponding to the drone battery temperature is obtained according to the drone battery temperature input mapping set, and the mapping relationship can be one-to-one or many-to-one.

[0043] It is represented by the weight ratio corresponding to the preset UAV battery voltage obtained from the database, which represents the numerical value of the influence of the UAV battery voltage on the UAV battery fault degree assessment coefficient. When used, the weight ratio corresponding to the UAV battery voltage can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the UAV battery voltage and the weight ratio corresponding to the UAV battery voltage preset in the database form a mapping set, and the weight ratio corresponding to the UAV battery voltage is obtained according to the UAV battery voltage input mapping set, and the mapping relationship can be one-to-one or many-to-one.

[0044] The temperature data of the drone flight control board is obtained by monitoring the built-in temperature sensor of the drone flight control board, and can be read by the flight control system, that is, the drone system temperature. The temperature of each battery is monitored by the built-in temperature sensor of the smart battery and transmitted to the flight control board through the battery management system, and can be read by the flight control system. The temperature of each battery is arranged in descending order, and the temperature of the battery in the first place is used as the drone battery temperature. The battery management system monitors each battery to obtain the voltage of each battery, and sends the data to the flight control board. The flight control system reads and arranges the voltage of each battery in descending order, and the voltage of the last battery is used as the drone battery voltage. The standard value of the drone system temperature refers to the maximum temperature of the drone flight control board within the safe use range indicated in the drone instructions, the standard value of the drone battery temperature refers to the temperature value of the first place after the maximum temperature of each drone battery within the safe use range indicated in the drone instructions is arranged in descending order, and the standard value of the drone battery voltage refers to the voltage value of the last place after the minimum voltage of each drone battery within the safe use range indicated in the drone instructions is arranged in descending order.

[0045] The overheating of the drone battery may be caused by internal battery failure, long-term high-load operation or poor heat dissipation. When the drone battery is overheated, it may cause the drone system temperature to rise, which in turn causes the battery voltage to drop. Therefore, the higher the drone system temperature, the higher the drone battery temperature and the lower the drone battery voltage, the more serious the drone battery failure. In the algorithm of this embodiment, the drone battery failure degree assessment coefficient is obtained by comprehensively analyzing the drone system temperature, drone battery temperature and drone battery voltage and using the hyperbolic tangent function to smooth the influence of abnormal values. The drone battery failure degree assessment coefficient can be used to more accurately analyze whether the drone has a battery failure.

[0046] The specific method for obtaining the UAV flight fault degree evaluation index is as follows: obtaining the preset weight ratios of the UAV battery voltage, the UAV flight speed, and the UAV engine speed from the database; constructing a calculation formula for the UAV flight fault degree evaluation index; the specific calculation formula for the UAV flight fault degree evaluation index is:

[0047] ;

[0048] In the formula, Expressed as The drone The UAV flight failure degree assessment index at each time monitoring point, Expressed as The drone The first time monitoring point The battery voltage of the drone when the data was acquired. Expressed as The drone The first time monitoring point The flight speed of the drone when the data was acquired. Expressed as The drone The first time monitoring point The engine speed of the drone at the time of data acquisition, Expressed as The standard value of drone battery voltage for a drone, Expressed as The reference value of the flight speed of the drone. Expressed as The reference value of the engine speed of the UAV of the UAV, It is expressed as the weight ratio of the drone battery voltage in the drone flight fault degree assessment index, It is expressed as the weight ratio of the UAV flight speed in the UAV flight failure degree assessment index. It is expressed as the weight ratio of the UAV engine speed in the UAV flight fault degree assessment index, Expressed as a natural constant.

[0049] It is represented by the weight ratio corresponding to the preset UAV battery voltage obtained from the database, which represents the numerical value of the influence of the UAV battery voltage on the UAV flight fault degree assessment index. When used, the weight ratio corresponding to the UAV battery voltage can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the UAV battery voltage and the weight ratio corresponding to the UAV battery voltage preset in the database form a mapping set, and the weight ratio corresponding to the UAV battery voltage is obtained according to the UAV battery voltage input mapping set, and the mapping relationship can be one-to-one or many-to-one.

[0050] It is represented by the weight ratio corresponding to the preset UAV flight speed obtained from the database, which represents the numerical value of the influence of the UAV flight speed on the UAV flight fault degree assessment index. When used, the weight ratio corresponding to the UAV flight speed can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the UAV flight speed and the weight ratio corresponding to the UAV flight speed preset in the database form a mapping set, and the weight ratio corresponding to the UAV flight speed is obtained according to the UAV flight speed input mapping set, wherein the mapping relationship can be one-to-one or many-to-one.

[0051] It is represented by the weight ratio corresponding to the preset UAV engine speed obtained from the database, which represents the numerical value of the influence of the UAV engine speed on the UAV flight fault degree assessment index. When used, the weight ratio corresponding to the UAV engine speed can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the UAV engine speed and the weight ratio corresponding to the UAV engine speed preset in the database form a mapping set, and the weight ratio corresponding to the UAV engine speed is obtained according to the UAV engine speed input mapping set, and the mapping relationship can be one-to-one or many-to-one.

[0052] The drone's horizontal flight speed is obtained through the drone's built-in speed sensor and transmitted to the flight control board. The flight control system reads the speed of the drone. The speed of each motor is monitored by the drone's built-in electronic speed controller, and the speed of each motor is sent to the flight control board. The flight control system reads the speed of each motor and accumulates and averages the speed to get the average value, which is the engine speed of the drone. The drone's flight speed reference value refers to the horizontal flight speed of the drone when it performs a flight mission without any faults. The drone's engine speed reference value refers to the average value obtained by accumulating and averaging the speed of each motor when the drone performs a flight mission without any faults.

[0053] A drop in battery voltage will directly affect the flight performance of the drone, because the battery is the power source of the drone. A drop in voltage may cause the flight speed to slow down, the engine speed to drop, and may even cause the drone to land suddenly. Therefore, the smaller the drone battery voltage, the slower the drone flight speed, and the smaller the drone engine speed, the more serious the drone's flight failure. In the algorithm of this embodiment, the drone flight fault degree assessment index is obtained by comprehensively analyzing the impact of the drone battery voltage, the drone flight speed, and the drone engine speed, and smoothing the extreme values ​​through a logarithmic function, so that the drone flight fault degree assessment index is more accurate, and the drone's flight fault degree can be more accurately analyzed based on the drone flight fault degree assessment index.

[0054] Furthermore, the specific method for obtaining the drone fault assessment index is as follows: obtain the number of drones and number the drones; set multiple time monitoring points; obtain the preset drone battery fault degree assessment coefficient and the weight ratio of the drone flight fault degree assessment index from the database; construct a drone fault assessment index calculation formula; the specific drone fault assessment index calculation formula is:

[0055] ;

[0056] In the formula, Expressed as The drone The UAV fault assessment index at each time monitoring point, , Indicates the number of the drone. Expressed as the total number of drones, , It is the number of the time monitoring point. Expressed as the total number of time monitoring points, Expressed as The drone The evaluation coefficient of the drone battery failure degree at each time monitoring point is: Expressed as The drone The UAV flight failure degree assessment index at each time monitoring point, It is expressed as the weight ratio of the drone battery failure assessment coefficient in the drone failure assessment index. It is expressed as the weight ratio of the UAV flight failure degree assessment index in the UAV failure assessment index.

[0057] In this embodiment, It is represented by the weight ratio corresponding to the preset UAV battery fault degree assessment coefficient obtained from the database, which represents the numerical value of the influence degree of the UAV battery fault degree assessment coefficient on the UAV fault assessment index. When used, the weight ratio corresponding to the UAV battery fault degree assessment coefficient can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the UAV battery fault degree assessment coefficient and the weight ratio corresponding to the UAV battery fault degree assessment coefficient preset in the database form a mapping set, and the weight ratio corresponding to the UAV battery fault degree assessment coefficient is obtained by inputting the mapping set according to the UAV battery fault degree assessment coefficient, and the mapping relationship can be one-to-one or many-to-one.

[0058] It is represented by the weight ratio corresponding to the preset UAV flight fault degree assessment index obtained from the database, which represents the numerical value of the influence degree of the UAV flight fault degree assessment index on the UAV fault assessment index. When used, the weight ratio corresponding to the UAV flight fault degree assessment index can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the UAV flight fault degree assessment index and the weight ratio corresponding to the UAV flight fault degree assessment index preset in the database form a mapping set, and the weight ratio corresponding to the UAV flight fault degree assessment index is obtained according to the UAV flight fault degree assessment index input mapping set, wherein the mapping relationship can be one-to-one or many-to-one.

[0059] In the algorithm of this embodiment, the drone fault assessment index is obtained by comprehensively analyzing the drone battery fault degree assessment coefficient and the drone flight fault degree assessment index, so that the drone fault assessment index is more comprehensive and specific, and the influence of outliers is smoothed by nonlinear transformation through the inverse tangent function, making the drone fault assessment index more accurate, which is conducive to more accurate analysis of the severity of drone faults according to the drone fault assessment index.

[0060] In a specific embodiment, Figure 2 As shown, it is a UAV fault assessment index curve provided by an embodiment of the present application, with the UAV battery fault degree assessment coefficient as the independent variable and the UAV fault assessment index as the dependent variable. For example, for the second UAV at the fourth time monitoring point, through the increase and decrease analysis of curves one, two and three, it can be seen that when the UAV battery fault degree assessment coefficient is larger, the UAV fault assessment index is larger; when the UAV battery fault degree assessment coefficient is smaller, the UAV fault assessment index is smaller. The statistical table of relevant data of the UAV fault assessment index is shown in Table 1:

[0061] Table 1 Statistics of relevant data of UAV fault assessment index

[0062]

[0063] When the UAV flight fault degree assessment indexes of curve 1, curve 2 and curve 3 are 1.26, 1.37 and 1.46 respectively, and other parameters are consistent, the UAV fault assessment indexes of curve 1, curve 2 and curve 3 are 1.31, 1.34 and 1.37 respectively. It can be seen that when the UAV battery fault degree assessment coefficient is consistent with other parameters, the larger the UAV flight fault degree assessment index, the larger the UAV fault assessment index.

[0064] Furthermore, the specific analysis process of analyzing the degree of drone battery failure according to the drone battery failure degree assessment coefficient is as follows: obtaining the drone battery failure degree assessment coefficient, obtaining the preset drone battery failure threshold from the database, comparing the drone battery failure degree assessment coefficient with the drone battery failure threshold, when the drone battery failure degree assessment coefficient is below the drone battery failure threshold, it indicates that the drone battery has not failed; when the drone battery failure degree assessment coefficient is greater than the drone battery failure threshold, it indicates that the drone battery has failed; the specific analysis process of analyzing the degree of drone flight failure according to the drone flight failure degree assessment index is as follows: obtaining the drone flight failure degree assessment index, obtaining the preset drone battery failure threshold from the database A drone flight fault threshold is set, and the drone flight fault degree assessment index is compared with the drone flight fault threshold. When the drone flight fault degree assessment index is below the drone flight fault threshold, it indicates that the drone flight has not failed; when the drone flight fault degree assessment index is greater than the drone flight fault threshold, it indicates that the drone flight has failed. The specific analysis process of analyzing the drone fault degree according to the drone fault assessment index is as follows: obtain the drone fault assessment index, obtain the preset drone fault threshold from the database, when the drone fault assessment index is below the drone fault threshold, it indicates that the drone has not failed; when the drone fault assessment index is greater than the drone fault threshold, it indicates that the drone has failed.

[0065] In this embodiment, a preset drone battery fault threshold is obtained from a database. When the drone battery fault degree evaluation coefficient exceeds the drone battery fault threshold, it indicates that the drone battery fault degree is higher. A preset drone flight fault threshold is obtained from a database. When the drone flight fault degree evaluation index is greater than the drone flight fault threshold, it indicates that the severity of the drone flight fault is higher. A preset drone fault threshold is obtained from a database. When the drone fault evaluation index is greater than the drone fault threshold, it indicates that the severity of the drone fault is higher.

[0066] Furthermore, the specific analysis process of comprehensively analyzing the secondary fault severity of the drone by comprehensively analyzing the drone battery failure degree, the drone flight failure degree and the drone failure degree is as follows: when the drone battery failure degree, the drone flight failure degree and the drone failure degree include drone battery failure, drone flight failure and drone failure at the same time, it means that the secondary fault severity of the drone is a serious fault, and the drone is subject to first-level scheduling; when any two of the drone battery failure, drone flight failure and drone failure occur, it means that the secondary fault severity of the drone is a medium fault, and the drone is subject to second-level scheduling; when one of the drone battery failure, drone flight failure and drone failure occurs, it means that the secondary fault severity of the drone is a minor fault, and the drone is subject to third-level scheduling; when none of the drone battery failure, drone flight failure and drone failure occurs, it means that the secondary fault severity of the drone is no fault, and the drone is not scheduled.

[0067] In this embodiment, the drone battery failure degree, the drone flight failure degree and the number of drone battery failures, drone flight failures and drone failures in the drone failure degree are greater, indicating that the drone failure degree is more serious. Different levels of scheduling are performed according to the severity of the drone failure, so that the drone can be scheduled more reasonably.

[0068] Furthermore, the specific analysis process for scheduling UAVs in combination with the first-level fault severity and the second-level fault severity is as follows: obtaining the first-level fault severity of the UAV, extracting UAVs with faults at the first-level fault severity and performing an analysis process and a scheduling process for the second-level fault severity; after the scheduling of UAVs with faults at the first-level fault severity is completed, performing a second-level fault severity analysis and scheduling on UAVs with no faults at the first-level fault severity.

[0069] In this embodiment, a first-level fault severity of a fault indicates that the UAV is more likely to fail, and priority is given to the subsequent second-level fault severity analysis process and scheduling process for the UAV; a first-level fault severity of a non-faulted UAV is less likely to fail, and after the subsequent second-level fault severity analysis process and scheduling process are performed on the UAVs with a higher possibility of failure, relevant analysis is performed on the UAVs with a lower possibility of failure, so that subsequent analysis and scheduling can be more accurately prioritized for the UAVs that may fail.

[0070] Furthermore, the specific process of the first-level dispatch is: fly the UAV to a safe area for emergency landing, terminate the mission of the UAV, and start the backup UAV to continue the mission; the specific process of the second-level dispatch is: fly the UAV to a safe area, suspend the mission execution, and check the faulty part. If it can be repaired within the specified time, continue to perform the mission. If it cannot be repaired, start the backup UAV to replace it and continue to perform the mission; the specific process of the third-level dispatch is: the UAV continues to perform the mission, and at the same time strengthens the monitoring of the UAV to ensure that the failure of the UAV does not worsen.

[0071] In this embodiment, the severity of the failure of the drone that needs to be dispatched at the first level is extremely high, and it is difficult to use the drone for subsequent tasks. The drone is flown to a safe area for emergency landing, the mission of the drone is terminated, and the backup drone is started to continue the mission. The degree of failure of the drone that needs to be dispatched at the second level is relatively high. The drone is flown to a safe area, the mission is suspended, and the faulty part is checked. If it can be repaired within the specified time, the mission will continue. If it cannot be repaired, the backup drone is started to replace it and continue the mission. The degree of failure of the drone that needs to be dispatched at the third level is relatively low. The drone continues to perform the mission, and the monitoring of the drone is strengthened to ensure that the failure of the drone does not worsen.

[0072] like Figure 3 As shown, it is a structural schematic diagram of the UAV adaptive scheduling and analysis system based on fuzzy artificial intelligence provided in an embodiment of the present application. The UAV adaptive scheduling and analysis system based on fuzzy artificial intelligence provided in an embodiment of the present application includes: a data acquisition module, a data transmission module, a data receiving module, a fuzzy calculation module, a primary fault analysis module, a secondary fault analysis module and a scheduling analysis module; wherein, the data acquisition module is used to obtain the flight parameter data of the UAV through the UAV flight control system; the data transmission module is used for the UAV flight control system to transmit the flight parameter data of the UAV to the UAV ground control station; the data receiving module is used for the UAV ground control station to receive the flight parameter data of the UAV; the fuzzy calculation module is used to analyze the flight parameter data of the UAV to obtain the fault degree value of the UAV; the primary fault analysis module is used to analyze the primary fault severity of the UAV according to the fault degree value of the UAV; the secondary fault analysis module is used to analyze the secondary fault severity of the UAV according to the flight parameter data of the UAV; the scheduling analysis module is used to schedule the UAV in combination with the primary fault severity and the secondary fault severity.

[0073] The technical solution in the above-mentioned embodiment of the present application obtains the UAV fault degree value by analyzing the UAV flight parameter data, analyzes the first-level fault severity of the UAV according to the UAV fault degree value, and analyzes the second-level fault severity of the UAV according to the UAV flight parameter data, thereby scheduling the UAV in combination with the first-level fault severity and the second-level fault severity, thereby realizing accurate and efficient scheduling of UAVs, and effectively solving the problem of difficulty in accurately scheduling UAVs in the prior art.

[0074] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0079] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The adaptive scheduling analysis method of UAV based on fuzzy artificial intelligence is characterized by: The following steps are involved: Obtain UAV flight parameter data through the UAV flight control system; The UAV flight control system transmits the UAV flight parameter data to the UAV ground control station; The UAV ground control station receives the UAV flight parameter data; Analyze the UAV flight parameter data to obtain the UAV fault degree value; Analyze the severity of the first-level fault of the drone based on the drone fault degree value; Analyze the severity of the drone's secondary faults based on the drone's flight parameter data; The drone is dispatched based on the first-level fault severity and the second-level fault severity; The specific analysis process of analyzing the UAV flight parameter data to obtain the UAV fault degree value is as follows: Obtain the drone system temperature and drone battery voltage in the drone flight parameter data, set the drone fault degree value, use the drone system temperature and drone battery voltage as input and substitute the drone fault degree value as output into the fuzzy calculation process preset in the database to obtain the drone fault degree value; The specific analysis process of analyzing the severity of the secondary fault of the drone based on the drone flight parameter data is as follows: The UAV flight parameter data includes UAV battery fault parameter data and UAV flight fault parameter data; According to the analysis of the drone battery failure parameter data, a drone battery failure degree assessment coefficient is obtained, wherein the drone battery failure degree assessment coefficient is used to reflect the failure degree of the drone battery; Analyze the degree of drone battery failure based on the drone battery failure degree assessment coefficient; Obtaining a UAV flight fault degree evaluation index according to the UAV flight fault parameter data analysis, wherein the UAV flight fault degree evaluation index is used to reflect the degree of UAV flight fault; Analyze the degree of UAV flight failure based on the UAV flight failure degree assessment index; The drone fault assessment index is obtained by analyzing the drone battery fault degree assessment coefficient and the drone flight fault degree assessment index, and the drone fault assessment index is used to reflect the severity of the drone fault; Analyze the degree of drone failure based on the drone failure assessment index; The severity of the secondary fault of the drone is analyzed by comprehensively analyzing the degree of drone battery fault, drone flight fault and drone fault; The specific method for obtaining the drone battery failure degree assessment coefficient is as follows: obtaining the number of drones and numbering the drones; setting multiple time monitoring points and numbering the time monitoring points; performing multiple data acquisitions at each time monitoring point and numbering the number of data acquisitions; obtaining the preset drone system temperature, drone battery temperature and drone battery voltage weight ratio from the database; constructing a drone battery failure degree assessment coefficient calculation formula; the specific drone battery failure degree assessment coefficient calculation formula is: ； In the formula, Expressed as The drone The evaluation coefficient of the drone battery failure degree at each time monitoring point is: , Indicates the number of the drone. Expressed as the total number of drones, , It is the number of the time monitoring point. Expressed as the total number of time monitoring points, Expressed as The drone The first time monitoring point The temperature of the UAV system at the time of data acquisition, Expressed as The drone The first time monitoring point The drone battery temperature at the time of data acquisition, , Indicates the number of times data is obtained. Represents the total number of data acquisitions, Expressed as The drone The first time monitoring point The battery voltage of the drone when the data was acquired. Expressed as The standard value of the drone system temperature of the drone, Expressed as The standard value of drone battery temperature for a drone, Expressed as The standard value of drone battery voltage for a drone, It is expressed as the weight ratio of the drone system temperature in the drone battery failure degree assessment coefficient, It is expressed as the weight ratio of the drone battery temperature in the drone battery failure degree assessment coefficient, It is expressed as the weight ratio of the drone battery voltage in the drone battery fault degree assessment coefficient; The specific method for obtaining the UAV flight fault degree evaluation index is as follows: obtaining the preset weight ratios of the UAV battery voltage, the UAV flight speed and the UAV engine speed from the database; constructing a calculation formula for the UAV flight fault degree evaluation index; the specific calculation formula for the UAV flight fault degree evaluation index is: ； In the formula, Expressed as The drone The UAV flight failure degree assessment index at each time monitoring point, Expressed as The drone The first time monitoring point The battery voltage of the drone when the data was acquired. Expressed as The drone The first time monitoring point The flight speed of the drone when the data was acquired. Expressed as The drone The first time monitoring point The engine speed of the drone at the time of data acquisition, Expressed as The standard value of drone battery voltage for a drone, Expressed as The reference value of the flight speed of the drone. Expressed as The reference value of the engine speed of the UAV of the UAV, It is expressed as the weight ratio of the drone battery voltage in the drone flight fault degree assessment index, It is expressed as the weight ratio of the UAV flight speed in the UAV flight failure degree assessment index. It is expressed as the weight ratio of the UAV engine speed in the UAV flight fault degree assessment index, Expressed as a natural constant; The specific method for obtaining the drone fault assessment index is as follows: Get the number of drones and number them; Set up multiple time monitoring points; Obtaining the preset UAV battery fault degree assessment coefficient and the weight ratio of the UAV flight fault degree assessment index from the database; Construct the calculation formula of drone fault assessment index; The specific calculation formula for the drone fault assessment index is: ； In the formula, Expressed as The drone The UAV fault assessment index at each time monitoring point, , Indicates the number of the drone. Expressed as the total number of drones, , It is the number of the time monitoring point. It is expressed as the total number of time monitoring points, Expressed as The drone The evaluation coefficient of the drone battery failure degree at each time monitoring point is: Expressed as The drone The UAV flight failure degree assessment index at each time monitoring point, It is expressed as the weight ratio of the drone battery failure assessment coefficient in the drone failure assessment index. It is expressed as the weight ratio of the UAV flight failure degree assessment index in the UAV failure assessment index.

2. The method for adaptive scheduling analysis of unmanned aerial vehicles based on fuzzy artificial intelligence as claimed in claim 1, characterized in that: The specific analysis process of analyzing the severity of the first-level fault of the drone according to the drone fault degree value is as follows: Obtaining the drone fault level value, obtaining a preset first threshold value from a database, and when the drone fault level value is below the first threshold value, it indicates that the first-level fault severity of the drone is that no fault has occurred; When the drone fault level value is greater than the first threshold, it indicates that the first-level fault severity of the drone is a fault.

3. The method for adaptive scheduling analysis of unmanned aerial vehicles based on fuzzy artificial intelligence as claimed in claim 1, characterized in that: The specific analysis process of analyzing the degree of failure of the drone battery according to the drone battery failure degree assessment coefficient is as follows: Obtaining a drone battery failure degree assessment coefficient, obtaining a preset drone battery failure threshold from a database, and comparing the drone battery failure degree assessment coefficient with the drone battery failure threshold. When the drone battery failure degree assessment coefficient is below the drone battery failure threshold, it indicates that the drone battery is not faulty. When the drone battery failure degree assessment coefficient is greater than the drone battery failure threshold, it means that the drone battery has failed; The specific analysis process of analyzing the degree of UAV flight failure according to the UAV flight failure degree evaluation index is as follows: Obtaining a UAV flight fault degree assessment index, obtaining a preset UAV flight fault threshold from a database, comparing the UAV flight fault degree assessment index with the UAV flight fault threshold, and when the UAV flight fault degree assessment index is below the UAV flight fault threshold, it indicates that no UAV flight fault occurs; When the drone flight fault degree assessment index is greater than the drone flight fault threshold, it means that the drone flight has a fault; The specific analysis process of analyzing the degree of drone failure according to the drone failure assessment index is as follows: Obtaining a drone fault assessment index, obtaining a preset drone fault threshold from a database, and when the drone fault assessment index is below the drone fault threshold, it indicates that the drone has not failed; When the drone fault assessment index is greater than the drone fault threshold, it means that the drone has a fault.

4. The method for adaptive scheduling analysis of unmanned aerial vehicles based on fuzzy artificial intelligence as claimed in claim 3 is characterized in that: The specific analysis process of analyzing the severity of the secondary fault of the drone by integrating the drone battery fault degree, the drone flight fault degree and the drone fault degree is as follows: When the drone battery failure degree, drone flight failure degree, and drone battery failure, drone flight failure, and drone failure in the drone failure degree occur simultaneously, the drone is dispatched to the first level; When any two of the UAV battery failure, UAV flight failure, and UAV failure occur, the UAV will be dispatched at the second level; When the drone battery fails, the drone flight fails, or the drone fails, the drone will be dispatched at level three; When the drone battery fails, the drone flight fails, or none of the drone failures occur, the drone will not be dispatched.

5. The method for adaptive scheduling analysis of unmanned aerial vehicles based on fuzzy artificial intelligence as claimed in claim 1, characterized in that: The specific analysis process of dispatching the drone based on the first-level fault severity and the second-level fault severity is as follows: Obtain the first-level fault severity of the drone, extract the drones with the first-level fault severity that have failed, and perform the analysis process and scheduling process of the second-level fault severity; After the dispatch of the UAVs with the first-level fault severity level being faulty is completed, the UAVs with the first-level fault severity level being non-faulty are analyzed and dispatched with the second-level fault severity level.

6. The method for adaptive scheduling analysis of unmanned aerial vehicles based on fuzzy artificial intelligence as claimed in claim 4 is characterized in that: The specific process of the first-level dispatch is: fly the drone to a safe area for emergency landing, terminate the mission of the drone, and start the backup drone to continue the mission; The specific process of the secondary dispatch is: fly the drone to a safe area, suspend the mission execution, check the faulty part, and if it can be repaired within the specified time, continue to perform the mission; if it cannot be repaired, start the backup drone to replace it and continue to perform the mission; The specific process of the three-level dispatch is: the drone continues to perform the mission, and at the same time, the monitoring of the drone is strengthened to ensure that the failure of the drone will not worsen.

7. The UAV adaptive scheduling analysis system based on fuzzy artificial intelligence is characterized by: include: Data acquisition module, data transmission module, data receiving module, fuzzy calculation module, primary fault analysis module, secondary fault analysis module and scheduling analysis module; The data acquisition module is used to acquire the flight parameter data of the UAV through the UAV flight control system; The data transmission module is used for the UAV flight control system to transmit the UAV flight parameter data to the UAV ground control station; The data receiving module is used for the UAV ground control station to receive the UAV flight parameter data; The fuzzy calculation module is used to analyze the UAV flight parameter data to obtain the UAV fault degree value; The first-level fault analysis module is used to analyze the severity of the first-level fault of the drone according to the drone fault degree value; The secondary fault analysis module is used to analyze the severity of the secondary fault of the UAV according to the flight parameter data of the UAV; The scheduling analysis module is used to schedule the drone based on the first-level fault severity and the second-level fault severity; The specific analysis process of analyzing the UAV flight parameter data to obtain the UAV fault degree value is as follows: Obtain the drone system temperature and drone battery voltage in the drone flight parameter data, set the drone fault degree value, use the drone system temperature and drone battery voltage as input and substitute the drone fault degree value as output into the fuzzy calculation process preset in the database to obtain the drone fault degree value; The specific analysis process of analyzing the severity of the secondary fault of the drone based on the drone flight parameter data is as follows: The UAV flight parameter data includes UAV battery fault parameter data and UAV flight fault parameter data; According to the analysis of the drone battery failure parameter data, a drone battery failure degree assessment coefficient is obtained, wherein the drone battery failure degree assessment coefficient is used to reflect the failure degree of the drone battery; Analyze the degree of drone battery failure based on the drone battery failure degree assessment coefficient; Obtaining a UAV flight fault degree evaluation index according to the UAV flight fault parameter data analysis, wherein the UAV flight fault degree evaluation index is used to reflect the degree of UAV flight fault; Analyze the degree of UAV flight failure based on the UAV flight failure degree assessment index; The drone fault assessment index is obtained by analyzing the drone battery fault degree assessment coefficient and the drone flight fault degree assessment index, and the drone fault assessment index is used to reflect the severity of the drone fault; Analyze the degree of drone failure based on the drone failure assessment index; The severity of the secondary fault of the drone is analyzed by comprehensively analyzing the degree of drone battery fault, drone flight fault and drone fault; The specific method for obtaining the drone battery failure degree assessment coefficient is as follows: obtaining the number of drones and numbering the drones; setting multiple time monitoring points and numbering the time monitoring points; performing multiple data acquisitions at each time monitoring point and numbering the number of data acquisitions; obtaining the preset drone system temperature, drone battery temperature and drone battery voltage weight ratio from the database; constructing a drone battery failure degree assessment coefficient calculation formula; the specific drone battery failure degree assessment coefficient calculation formula is: ； In the formula, Expressed as The drone The evaluation coefficient of the drone battery failure degree at each time monitoring point is: , Indicates the number of the drone. Expressed as the total number of drones, , It is the number of the time monitoring point. Expressed as the total number of time monitoring points, Expressed as The drone The first time monitoring point The temperature of the UAV system at the time of data acquisition, Expressed as The drone The first time monitoring point The drone battery temperature at the time of data acquisition, , Indicates the number of times data is obtained. Represents the total number of data acquisitions, Expressed as The drone The first time monitoring point The battery voltage of the drone when the data was acquired. Expressed as The standard value of the drone system temperature of the drone, Expressed as The standard value of drone battery temperature for a drone, Expressed as The standard value of drone battery voltage for a drone, It is expressed as the weight ratio of the drone system temperature in the drone battery failure degree assessment coefficient, It is expressed as the weight ratio of the drone battery temperature in the drone battery failure degree assessment coefficient, It is expressed as the weight ratio of the drone battery voltage in the drone battery fault degree assessment coefficient; The specific method for obtaining the UAV flight fault degree evaluation index is as follows: obtaining the preset weight ratios of the UAV battery voltage, the UAV flight speed and the UAV engine speed from the database; constructing a calculation formula for the UAV flight fault degree evaluation index; the specific calculation formula for the UAV flight fault degree evaluation index is: ； In the formula, Expressed as The drone The UAV flight failure degree assessment index at each time monitoring point, Expressed as The drone The first time monitoring point The battery voltage of the drone when the data was acquired. Expressed as The drone The first time monitoring point The flight speed of the drone when the data was acquired. Expressed as The drone The first time monitoring point The engine speed of the drone at the time of data acquisition, Expressed as The standard value of drone battery voltage for a drone, Expressed as The reference value of the flight speed of the drone. Expressed as The reference value of the engine speed of the UAV of the UAV, It is expressed as the weight ratio of the drone battery voltage in the drone flight fault degree assessment index, It is expressed as the weight ratio of the UAV flight speed in the UAV flight failure degree assessment index. It is expressed as the weight ratio of the UAV engine speed in the UAV flight fault degree assessment index, Expressed as a natural constant; The specific method for obtaining the drone fault assessment index is as follows: Get the number of drones and number them; Set up multiple time monitoring points; Obtaining the preset UAV battery fault degree assessment coefficient and the weight ratio of the UAV flight fault degree assessment index from the database; Construct the calculation formula of drone fault assessment index; The specific calculation formula for the drone fault assessment index is: ； In the formula, Expressed as The drone The UAV fault assessment index at each time monitoring point, , Indicates the number of the drone. Expressed as the total number of drones, , It is the number of the time monitoring point. It is expressed as the total number of time monitoring points, Expressed as The drone The evaluation coefficient of the drone battery failure degree at each time monitoring point is: Expressed as The drone The UAV flight failure degree assessment index at each time monitoring point, It is expressed as the weight ratio of the drone battery failure assessment coefficient in the drone failure assessment index. It is expressed as the weight ratio of the UAV flight failure degree assessment index in the UAV failure assessment index.

Images