Unmanned aerial vehicle remote real-time monitoring system and method

Abstract

The invention provides an unmanned aerial vehicle remote real-time monitoring system and method, and belongs to the technical field of unmanned aerial vehicle monitoring, and the system comprises a selection module which obtains the specific purpose and task demands of an unmanned aerial vehicle, and selects a corresponding unmanned aerial vehicle model; the integration module is used for determining a plurality of factors influencing flight according to the model, configuring different sensors, and integrating data of the different sensors to obtain real-time state information of the unmanned aerial vehicle; the recognition module is used for acquiring key parameters of the unmanned aerial vehicle, establishing a state evaluation model, determining a real-time health state of the unmanned aerial vehicle and recognizing real-time abnormal behaviors and potential faults; the construction module is used for analyzing historical fault data, real-time abnormal behaviors and potential faults of the unmanned aerial vehicle and constructing a fault prediction model; and the positioning module obtains a fault diagnosis algorithm to position a fault reason, obtains a fault isolation strategy, and realizes remote real-time monitoring of the unmanned aerial vehicle. The problems that remote monitoring data of the unmanned aerial vehicle is inaccurate, and the safety and the efficiency of the unmanned aerial vehicle are reduced are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle monitoring, and in particular to a remote real-time monitoring system and method for unmanned aerial vehicle. Background Art

[0002] With the rapid development of drone technology in my country, its application in agriculture, forestry, environmental protection and other fields is becoming more and more extensive.

[0003] However, traditional remote real-time monitoring of drones requires manual monitoring of data, resulting in inaccurate monitoring data on the drone's flight status, environmental parameters, and mission status. At the same time, the drone cannot be monitored and managed in real time, and the drone cannot be made intelligent, real-time, and efficient, which reduces the safety and efficiency of the drone during operation.

[0004] Therefore, the present invention proposes a remote real-time monitoring system and method for an unmanned aerial vehicle. Summary of the invention

[0005] The present invention provides a remote real-time monitoring system and method for unmanned aerial vehicles, which are used to solve the problem that traditional remote real-time monitoring of unmanned aerial vehicles in the prior art requires manual monitoring of data, resulting in inaccurate monitoring data on the flight status, environmental parameters, and mission status of the unmanned aerial vehicle. At the same time, the unmanned aerial vehicle cannot be monitored and managed in real time, and the intelligence, real-time and high efficiency of the unmanned aerial vehicle cannot be realized, which reduces the safety and efficiency of the unmanned aerial vehicle during operation.

[0006] In one aspect, the present invention provides a remote real-time monitoring system for an unmanned aerial vehicle, comprising: Selection module: obtaining the specific purpose and mission requirements of the drone, and selecting a corresponding drone model according to the specific purpose and mission requirements of the drone; Integration module: determining multiple factors affecting the flight of the drone according to the drone model, configuring different sensors for the drone according to the multiple factors, integrating the real-time detection data of different sensors based on data fusion technology, and obtaining the real-time status information of the drone according to the integrated data; Identification module: obtains the key parameters of the drone, establishes a status assessment model based on the integrated data, determines the real-time health status of the drone, and identifies the real-time abnormal behavior and potential failures of the drone based on the real-time health status; Building module: Use machine learning algorithms to analyze the drone’s historical fault data, real-time abnormal behavior, and potential faults, determine real-time fault modes and characteristics, and build a fault prediction model; Positioning module: obtains a fault diagnosis algorithm based on pattern recognition and fault tree analysis, and quickly locates the cause of the fault based on the fault prediction model, obtains a fault isolation strategy based on the fault cause, and realizes remote real-time monitoring of the drone.

[0007] According to a drone remote real-time monitoring system provided by the present invention, a selection module includes: A first acquisition unit: acquires the usage scenario and purpose of the drone, and determines the specific purpose and mission requirements of the drone based on the drone usage guide according to the usage scenario and purpose; A first determination unit: determining the functional requirements and cost factors of the UAV according to the specific purpose and mission requirements of the UAV; Selection unit: selects a corresponding drone model according to the functional requirements and cost factors.

[0008] According to the present invention, a remote real-time monitoring system for unmanned aerial vehicles is provided, and the integrated module includes: A second acquisition unit: acquiring flight characteristics and performance data of the UAV according to the UAV model; A second determination unit: determining flight data of the UAV in different environments according to the flight characteristics and performance data; A third determining unit: determining multiple factors affecting the flight of the UAV according to the flight data; Configuration unit: obtaining specific description features of multiple factors, and configuring corresponding sensors for the drone according to the specific description features; Integration unit: integrates the relevant information of the UAV obtained by the sensor based on the multi-source data fusion technology of the Bayesian network; The fourth determination unit obtains the surrounding environment and self-motion information of the UAV according to the integrated data, and determines the real-time status information of the UAV according to the surrounding environment and self-motion information.

[0009] According to the present invention, a remote real-time monitoring system for unmanned aerial vehicles, an identification module, includes: The third acquisition unit: obtains the key parameters of the drone through the flight control system and communication protocol; Extraction unit: preprocessing the key parameters, and extracting speed and position features from the preprocessed data based on feature extraction engineering; Establishing unit: training the speed and position characteristics and the integrated data based on a machine learning algorithm, and establishing a state assessment model according to the training results; The fifth determination unit: performs real-time analysis and prediction of the real-time status information of the drone according to the drone status assessment model to determine the current health status of the drone; Identification unit: compares the current health status of the drone with its historical health status, and identifies abnormal behaviors and potential failures of the drone in real time.

[0010] According to the present invention, a remote real-time monitoring system for unmanned aerial vehicles is provided, and the building modules include: The fourth acquisition unit: acquires the time series characteristics and frequency domain characteristics of historical fault data, abnormal behaviors and potential faults; Classification and clustering unit: determining a corresponding machine learning algorithm according to the time series characteristics and frequency domain characteristics, and classifying and clustering faults according to the machine learning algorithm; The sixth determination unit: determines the fault mode and characteristics according to the classification and clustering results combined with the actual situation; Construction unit: The determined fault modes and features are used as input features of the model to build a fault prediction model.

[0011] According to the present invention, a remote real-time monitoring system for unmanned aerial vehicles, a positioning module, includes: Definition unit: construct a fault tree based on the system structure and fault phenomenon, and define the possibility and impact of each branch; Classification and matching unit: For each fault, identify its corresponding symptoms, and classify and match them through pattern recognition technology; The fifth acquisition unit: acquires the corresponding fault diagnosis algorithm through the branches of the fault tree and the results of pattern recognition; Positioning unit: quickly locate the cause of the fault based on the fault prediction model according to the fault diagnosis algorithm, determine the fault isolation range according to the fault cause, obtain the fault isolation strategy according to the fault isolation range, and realize remote real-time monitoring of the UAV.

[0012] According to a drone remote real-time monitoring system provided by the present invention, the second acquisition unit includes: The first determination subunit: obtains the design parameters of the UAV according to the UAV model, and determines the quantitative range of the flight altitude and the quantitative range of the flight speed of the UAV according to the design parameters; The second determination subunit determines the X-axis force deviation of the UAV at different flight speeds at the same flight altitude and the Y-axis force deviation at different flight altitudes at the same flight speed according to the flight altitude quantitative range and the flight speed quantitative range; The third determination subunit determines the surrounding air flow field distribution parameters of the UAV during flight according to the X-axis force deviation and the Y-axis force deviation; The fourth determination subunit: determines the aerodynamic loads of the nose, wings on both sides and tail of the UAV during flight based on the air flow field distribution parameters and the structural parameters of the UAV; Construct subunits: construct the flight dynamics model of the UAV according to the aerodynamic load, and determine the power distribution parameters of each position of the UAV during flight according to the flight dynamics model; The fifth determination subunit: determines the aerodynamic torque of the UAV during flight according to the power distribution parameter, and determines the state space linear parameters required for the UAV flight according to the aerodynamic torque; The first acquisition subunit is used to determine the reference motion condition of the UAV flight based on the state space linear parameter, and obtain the condition parameter corresponding to the reference motion condition; The sixth determination subunit: determines the full-dimensional motion state of the UAV during flight according to the condition parameters and the power transmission parameters of the UAV during flight; The seventh determination subunit: determines the flight characteristics of the UAV according to the full-dimensional motion state, and determines the flight dynamic gain of the UAV based on the flight characteristics; The eighth determination subunit determines the performance data of the UAV according to the flight dynamic gain and the initialization flight performance parameters of the UAV.

[0013] A method for remote real-time monitoring of an unmanned aerial vehicle provided by the present invention comprises: Step 1: Obtain the specific purpose and mission requirements of the drone, and select a corresponding drone model according to the specific purpose and mission requirements of the drone; Step 2: Determine multiple influencing factors of the drone according to the drone model, configure different sensors for the drone according to the parameters, obtain real-time status information of the drone according to the sensors, and integrate data from different sensors by combining data fusion technology; Step 3: Obtain the key parameters of the drone, establish a state assessment model based on the integrated data, determine the health status of the drone, and identify abnormal behaviors and potential failures of the drone based on the health status; Step 4: Use machine learning algorithms to analyze historical fault data, abnormal behaviors, and potential faults, determine fault modes and characteristics, and build a fault prediction model; Step 5: Obtain a fault diagnosis algorithm based on pattern recognition and fault tree analysis, and quickly locate the cause of the fault based on the fault prediction model, obtain a fault isolation strategy based on the fault cause, and realize remote real-time monitoring of the drone.

[0014] Compared with the prior art, the present invention has the following beneficial effects: Different sensors are configured for drones according to their models, and the acquired data are fused. A drone status assessment model is established in combination with the drone's key parameters to evaluate the drone's health status, obtain potential faults, and obtain fault isolation strategies based on the causes of the faults. This can ensure the accuracy of the drone's flight status, environmental parameters, and mission status monitoring data. At the same time, the drone can be monitored and managed in real time, making the drone intelligent, real-time, and efficient, and improving the safety and efficiency of the drone during operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 Schematic diagram of the structure of the remote real-time monitoring system for unmanned aerial vehicles provided by an embodiment of the present invention; Figure 2 It is a flow chart of a method for remote real-time monitoring of a UAV provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0018] Embodiment 1: An embodiment of the present invention provides a remote real-time monitoring system for unmanned aerial vehicles, such as Figure 1 As shown, the system mainly includes the following modules: Selection module: obtaining the specific purpose and mission requirements of the drone, and selecting a corresponding drone model according to the specific purpose and mission requirements of the drone; Integration module: determining multiple factors affecting the flight of the drone according to the drone model, configuring different sensors for the drone according to the multiple factors, integrating the real-time detection data of different sensors based on data fusion technology, and obtaining the real-time status information of the drone according to the integrated data; Identification module: obtains the key parameters of the drone, establishes a status assessment model based on the integrated data, determines the real-time health status of the drone, and identifies the real-time abnormal behavior and potential failures of the drone based on the real-time health status; Building module: Use machine learning algorithms to analyze the drone’s historical fault data, real-time abnormal behavior, and potential faults, determine real-time fault modes and characteristics, and build a fault prediction model; Positioning module: obtains a fault diagnosis algorithm based on pattern recognition and fault tree analysis, and quickly locates the cause of the fault based on the fault prediction model, obtains a fault isolation strategy based on the fault cause, and realizes remote real-time monitoring of the drone.

[0019] In this embodiment, the specific uses of the drone include: Agriculture: Drones can quickly conduct surveying and mapping on farmland, detect crop pests and diseases, and manage irrigation.

[0020] Mapping: Drones can be used for high-precision map production and data collection in areas such as construction sites, environmental monitoring, and urban planning.

[0021] Photography / Videography: Drones can provide high-quality aerial photography services for industries such as film and television production, news reporting, and advertising shooting.

[0022] In this embodiment, multiple factors affecting the flight of the drone include: weather conditions, ground obstacles, and electromagnetic interference.

[0023] In this embodiment, the different sensors include: an inertial measurement unit (IMU), a global positioning system (GPS), a barometer, a temperature sensor, a humidity sensor, and a vibration sensor.

[0024] In this embodiment, data fusion technology is the process of combining data sets from different sensors, sources or formats to create a larger, more comprehensive, more accurate or more reliable data set, such as: spatial fusion, spectral fusion, radar fusion.

[0025] In this embodiment, the real-time status information includes: position, speed, posture, and environmental parameters.

[0026] In this embodiment, the state assessment model refers to a model for assessing the real-time state of the drone.

[0027] In this embodiment, the real-time health status of the drone refers to the technical status and performance of the drone itself.

[0028] In this embodiment, the fault tree is a graphical tool used to describe the potential causal relationship between system components, which can help us analyze and identify the root causes that may cause the failure of the entire system. The fault tree is mainly composed of four parts: trigger conditions, branch probabilities, leaf results and root nodes. These four parts respectively represent various combinations that may lead to the final failure.

[0029] In this embodiment, the fault isolation strategy means that when a system or component failure is detected, the faulty part can be automatically isolated and switched to a backup system or component to maintain the basic functions of the drone.

[0030] The beneficial effects of the above technical solution are: different sensors are configured for drones according to the models of drones, and the acquired data are integrated, and a drone status assessment model is established in combination with the key parameters of the drone to assess the health status of the drone, obtain potential faults, and obtain fault isolation strategies based on the causes of the faults, which can ensure the accuracy of the drone's flight status, environmental parameters, and mission status monitoring data. At the same time, the drone can be monitored and managed in real time, realizing the intelligence, real-time and efficiency of the drone, and improving the safety and efficiency of the drone during operation.

[0031] Embodiment 2: Based on the first embodiment, the selection module of the embodiment of the present invention includes: A first acquisition unit: acquires the usage scenario and purpose of the drone, and determines the specific purpose and mission requirements of the drone based on the drone usage guide according to the usage scenario and purpose; A first determination unit: determining the functional requirements and cost factors of the UAV according to the specific purpose and mission requirements of the UAV; Selection unit: selects a corresponding drone model according to the functional requirements and cost factors.

[0032] In this embodiment, the use scenarios of the drone include: agriculture, logistics and transportation, photogrammetry, and search and rescue.

[0033] In this embodiment, the purpose of using the drone includes: surveying and mapping farmland, spraying pesticides or sowing, quickly transporting goods from the place of production to the place of demand, and photographing and mapping terrain, landforms and buildings.

[0034] In this embodiment, the drone usage guide refers to a guide that instructs users on how to use the drone, applicable scenarios, and specific purposes.

[0035] In this embodiment, the functional requirements refer to: flight time, load capacity, operating radius, anti-interference, and ease of operation.

[0036] The beneficial effect of the above technical solution is: the functional requirements and cost factors of the drone are determined by the specific purpose and mission requirements of the drone, so as to select the corresponding drone model, which can meet specific needs and reduce the cost of using the drone.

[0037] Embodiment 3: Based on Example 2, the integration module of this embodiment of the present invention includes: A second acquisition unit: acquiring flight characteristics and performance data of the UAV according to the UAV model; A second determination unit: determining flight data of the UAV in different environments according to the flight characteristics and performance data; A third determining unit: determining multiple factors affecting the flight of the UAV according to the flight data; Configuration unit: obtaining specific description features of multiple factors, and configuring corresponding sensors for the drone according to the specific description features; Integration unit: integrates the relevant information of the UAV obtained by the sensor based on the multi-source data fusion technology of the Bayesian network; The fourth determination unit obtains the surrounding environment and self-motion information of the UAV according to the integrated data, and determines the real-time status information of the UAV according to the surrounding environment and self-motion information.

[0038] In this embodiment, the flight characteristics of the drone refer to its performance in the air, including stability and controllability, fuel efficiency, and safety.

[0039] In this embodiment, the key performance data of the UAV include: flight speed, range, and wind resistance.

[0040] In this embodiment, different environments refer to: different temperatures, air pressures, wind speeds and wind directions.

[0041] In this embodiment, the flight data includes: flight altitude, speed, range, and fuel consumption.

[0042] In this embodiment, multiple factors affecting the flight of the drone include: weather conditions, ground obstacles, and electromagnetic interference.

[0043] In this embodiment, the specific description features of the multiple factors that affect the flight of the drone include: Weather conditions: Air temperature: Temperature affects aircraft dynamics and fuel consumption. Too low or too high temperatures may cause problems such as reduced engine efficiency or fuel freezing.

[0044] Humidity: Relative humidity affects the amount of moisture in the air, which can cause corrosion to an aircraft's engine intakes and fuselage surfaces.

[0045] Air Pressure: Changes in air pressure affect an aircraft's ascent and descent rates, as well as fuel consumption.

[0046] In this embodiment, the multi-source data fusion technology based on the Bayesian network is a method of comprehensively processing data from different sensors or sources by utilizing the powerful probabilistic reasoning ability and distributed network structure of the Bayesian network.

[0047] In this embodiment, the drone's own motion information includes: Location information: including longitude, latitude and altitude.

[0048] Speed ​​information: The speed information of the drone includes average speed, maximum speed and instantaneous speed.

[0049] Attitude information: The attitude information of the drone includes pitch angle, roll angle and yaw angle.

[0050] The beneficial effects of the above technical solution are: determining the flight data of the drone in different environments based on the flight characteristics and performance data of the drone, determining multiple factors affecting the flight of the drone and configuring corresponding sensors for the drone, integrating the sensor data, and determining the real-time status information of the drone, so as to detect abnormal situations in time and improve the safety of the drone. At the same time, the drone's actions can be planned and controlled more accurately based on the real-time speed and position of the drone, thereby improving flight efficiency.

[0051] Embodiment 4: Based on Example 3, the identification module of this embodiment of the present invention includes: The third acquisition unit: obtains the key parameters of the drone through the flight control system and communication protocol; Extraction unit: preprocessing the key parameters, and extracting speed and position features from the preprocessed data based on feature extraction engineering; Establishing unit: training the speed and position characteristics and the integrated data based on a machine learning algorithm, and establishing a state assessment model according to the training results; The fifth determination unit: performs real-time analysis and prediction of the real-time status information of the drone according to the drone status assessment model to determine the current health status of the drone; Identification unit: compares the current health status of the drone with its historical health status, and identifies abnormal behaviors and potential failures of the drone in real time.

[0052] In this embodiment, the flight control system is responsible for controlling and monitoring the flight status of the UAV.

[0053] In this embodiment, the communication protocol is the way to exchange data between different components in the drone system, defining how to send data from the ground station to the drone, and how to exchange data between drones or with other devices.

[0054] In this embodiment, the key parameters include: flight time, flight distance, and battery power.

[0055] In this embodiment, feature extraction engineering is a computer vision technique that aims to extract useful information from images or videos.

[0056] In this embodiment, the velocity and position characteristics include: linear acceleration, angular velocity, and position information.

[0057] In this embodiment, the state assessment model estimates the flight state of the UAV under various circumstances and generates control instructions to enable the UAV to fly along a predetermined trajectory.

[0058] The beneficial effects of the above technical solution are: by preprocessing the key parameters of the drone, extracting speed and position characteristics and combining the integrated data to establish a status assessment model, the current health status of the drone can be determined, which can ensure the accurate determination of the drone status, improve the safety of the drone and the reliability of the drone remote real-time monitoring system.

[0059] Embodiment 5: Based on Example 4, the embodiment of the present invention constructs a module, including: The fourth acquisition unit: acquires the time series characteristics and frequency domain characteristics of historical fault data, abnormal behaviors and potential faults; Classification and clustering unit: determining a corresponding machine learning algorithm according to the time series characteristics and frequency domain characteristics, and classifying and clustering faults according to the machine learning algorithm; The sixth determination unit: determines the fault mode and characteristics according to the classification and clustering results combined with the actual situation; Construction unit: The determined fault modes and features are used as input features of the model to build a fault prediction model.

[0060] In this embodiment, the historical fault data of the drone includes: fault type, fault frequency, fault time and location, and fault impact range.

[0061] In this embodiment, the abnormal behavior of the drone includes: deviation from the planned flight path and abnormal battery life.

[0062] In this embodiment, the time series characteristics of potential faults refer to a series of time and order patterns at which faults may occur in the UAV system, such as time interval, rising trend, and falling trend.

[0063] In this embodiment, the frequency domain characteristics of the potential fault are a set of characteristics that reflect the distribution and intensity of the fault in the frequency domain, including: Fault frequency: The number of times a fault occurs or the number of events, reflecting the operating status of the system in a specific period of time. A high fault frequency may indicate a serious fault in the system.

[0064] Fault duration: The duration from the occurrence of a fault to its repair, which reflects the impact of the fault and the instability of the system. A longer fault duration may indicate a serious fault or inherent defect in the system.

[0065] Spectral density: In frequency domain analysis, the distribution of fault frequencies. High-frequency components may indicate that the fault is mainly concentrated in certain frequency ranges, while low-frequency components may be related to root causes such as structural damage.

[0066] Resonant frequency: In some cases, a fault may be amplified at a specific natural frequency. This is called the resonant frequency and may be caused by the matching of the system's inherent vibration mode with the external driving force.

[0067] In this embodiment, the failure mode refers to the type of failure that may occur in a device or system, such as: battery failure, motor failure, remote control failure, sensor failure.

[0068] In this embodiment, the fault prediction model is an algorithm used to predict the type of fault that may occur in a device or system.

[0069] The beneficial effects of the above technical solution are: determining the corresponding machine learning algorithm through time series characteristics and frequency domain characteristics, classifying and clustering faults, determining failure modes and characteristics, and building a fault prediction model, which can accurately and quickly identify components with potential failure risks, thereby reducing downtime and maintenance costs, and ensuring the reliability and safety of equipment.

[0070] Embodiment 6: Based on Example 5, the positioning module of this embodiment of the present invention includes: Definition unit: construct a fault tree based on the system structure and fault phenomenon, and define the possibility and impact of each branch; Classification and matching unit: For each fault, identify its corresponding symptoms, and classify and match them through pattern recognition technology; The fifth acquisition unit: acquires the corresponding fault diagnosis algorithm through the branches of the fault tree and the results of pattern recognition; Positioning unit: quickly locate the cause of the fault based on the fault prediction model according to the fault diagnosis algorithm, determine the fault isolation range according to the fault cause, obtain the fault isolation strategy according to the fault isolation range, and realize remote real-time monitoring of the UAV.

[0071] In this embodiment, the failure phenomena of the drone include: loss of control, battery failure, damage to the fuselage structure, engine failure or failure of other mechanical components, and communication failure.

[0072] In this embodiment, the fault tree is a graphical tool for identifying and analyzing potential fault causes. It decomposes various possible fault causes into several independent subtrees, and derives the final fault point through the combination relationship of these subtrees.

[0073] In this embodiment, the symptoms corresponding to each fault include: Engine failure: The drone loses power or operates abnormally.

[0074] Communication failure: The communication between the drone and other equipment is interrupted or the signal is lost.

[0075] Navigation system failure: Errors occurred in the positioning and heading control of the drone.

[0076] Sensor failure: Abnormal readings from key sensors such as the drone’s altimeter, barometer, and thermometer.

[0077] In this embodiment, pattern recognition technology is used to analyze and process input data to extract hidden meaningful information and patterns therefrom.

[0078] In this embodiment, the fault diagnosis algorithm is used to detect and predict potential faults of equipment or systems, such as regression analysis, cluster analysis, and principal component analysis.

[0079] In this embodiment, the fault prediction model is a mathematical model used to predict the type and time of faults that may occur in a device or system. This model usually uses historical data analysis to identify abnormal behavior of the device, such as: K nearest neighbor algorithm, random forest.

[0080] In this embodiment, the fault isolation scope refers to the measures that need to be taken when a system fails to operate to ensure that the normal operation of the entire system is not affected, and the scope of the fault that needs to be eliminated.

[0081] In this embodiment, the fault isolation strategy is an action taken when a fault occurs, the purpose of which is to ensure that the entire system or business process can continue to run and reduce the impact of the fault.

[0082] The beneficial effects of the above technical solution are: through the results of fault tree branches and pattern recognition, the corresponding fault diagnosis algorithm is obtained, the cause of the fault is located based on the fault prediction model, and the fault isolation strategy is obtained, which can quickly identify and isolate the fault, reduce downtime and maintenance work, and improve the flight efficiency and safety of the UAV.

[0083] Embodiment 7: Based on Example 6, the second acquisition unit in this embodiment of the present invention includes: The first determination subunit: obtains the design parameters of the UAV according to the UAV model, and determines the quantitative range of the flight altitude and the quantitative range of the flight speed of the UAV according to the design parameters; The second determination subunit determines the X-axis force deviation of the UAV at different flight speeds at the same flight altitude and the Y-axis force deviation at different flight altitudes at the same flight speed according to the flight altitude quantitative range and the flight speed quantitative range; The third determination subunit determines the surrounding air flow field distribution parameters of the UAV during flight according to the X-axis force deviation and the Y-axis force deviation; The fourth determination subunit: determines the aerodynamic loads of the nose, wings on both sides and tail of the UAV during flight based on the air flow field distribution parameters and the structural parameters of the UAV; Construct subunits: construct the flight dynamics model of the UAV according to the aerodynamic load, and determine the power distribution parameters of each position of the UAV during flight according to the flight dynamics model; The fifth determination subunit: determines the aerodynamic torque of the UAV during flight according to the power distribution parameter, and determines the state space linear parameters required for the UAV flight according to the aerodynamic torque; The first acquisition subunit is used to determine the reference motion condition of the UAV flight based on the state space linear parameter, and obtain the condition parameter corresponding to the reference motion condition; The sixth determination subunit: determines the full-dimensional motion state of the UAV during flight according to the condition parameters and the power transmission parameters of the UAV during flight; The seventh determination subunit: determines the flight characteristics of the UAV according to the full-dimensional motion state, and determines the flight dynamic gain of the UAV based on the flight characteristics; The eighth determination subunit determines the performance data of the UAV according to the flight dynamic gain and the initialization flight performance parameters of the UAV.

[0084] In this embodiment, the design parameters of the drone include: flight speed, load capacity, battery life, flight range and stability performance.

[0085] In this embodiment, the quantitative range of the flight altitude of the UAV refers to the vertical distance that the UAV moves within the atmosphere. Generally, the flight altitude of the UAV can range from a few meters to tens of kilometers.

[0086] In this embodiment, the quantitative range of the flight speed of the drone refers to the horizontal moving speed of the drone in the atmosphere. Generally, the flight speed of the drone can range from a few meters per second to tens of meters per second.

[0087] In this embodiment, between different flight speeds, the X-axis force deviation refers to the phenomenon of the drone's yaw motion along the X-axis due to aerodynamic effects. When the drone is flying at high speed, its flight resistance will decrease, while the thrust will remain unchanged, which will cause the aircraft to produce a head-up motion, that is, rise along the Y-axis. At this time, if there is no appropriate control system to offset this head-up motion, the drone will produce a yaw motion along the X-axis. On the contrary, when the drone is flying at a low speed, its flight resistance will increase, but the thrust will remain unchanged, which may cause the aircraft to dive downward.

[0088] In this embodiment, between different flight altitudes of the drone, the Y-axis force deviation refers to the phenomenon of the drone's yaw motion along the Y-axis caused by aerodynamic effects. When the drone flies at high altitudes, its aerodynamic force will change, causing the body to generate additional rolling inertia. If the drone does not have sufficient stability to offset this change, it will generate rolling motion along the Y-axis. Conversely, if the drone flies at low altitudes, its aerodynamic resistance will increase, causing the body to generate additional diving inertia. If the drone does not have sufficient pitch stability to offset this change, the drone will generate pitch and roll motion along the Y-axis.

[0089] In this embodiment, the air flow field distribution parameters around the UAV during flight include: speed, pressure, temperature, turbulence, and resistance.

[0090] In this embodiment, the structural parameters of the drone include: the size, shape, angle and material of the wings, the strength and rigidity of the fuselage, the size, shape and material of the tail, the hovering motor and the propeller.

[0091] In this embodiment, the aerodynamic loads on the nose, wings on both sides and tail refer to the airflow pressure distribution on these parts, for example: Nose: Since the nose is the front part of the drone, it mainly bears the airflow load along the forward direction. In addition, since the nose is the forward point of the center of gravity of the drone, it also bears the main rolling aerodynamic load.

[0092] Wings on both sides: The aerodynamic loads on the wings on both sides are usually called "symmetrical aerodynamic loads" because the airflow pressure distribution they bear is symmetrical. The wings on both sides also bear the airflow reaction force generated by the main rotor.

[0093] Tail: The tail is usually controlled by a pair or more vertical tail fins. The aerodynamic load of the tail fin mainly includes the airflow reaction force generated by the main rotor and the vortex generated by the tail fin itself.

[0094] In this embodiment, the flight dynamics model of the UAV describes the motion law of the UAV under the aerodynamic effect, and how to control the flight of the UAV according to the desired posture and position.

[0095] In this embodiment, the power distribution parameters of the drone at various positions during flight include: Main rotor: The main rotors are responsible for providing vertical thrust and controlling the direction of flight. They should be able to generate enough lift and thrust to maintain the drone's hovering and stable flight. Normally, the main rotor's speed, blade diameter and layout will affect the thrust and lift it generates.

[0096] Aileron: The aileron is used to provide additional thrust and stability. The speed, blade diameter and layout of the aileron will affect the thrust and additional stability it generates.

[0097] Battery Pack: The battery pack is responsible for providing power to the drone. The location and size of the battery pack will affect the payload capacity and range of the drone.

[0098] In this embodiment, aerodynamic torque refers to the rotational effect produced by the aerodynamic force generated when the UAV is flying. When the UAV flies forward, a backward airflow is generated on the upper surface of the wing. This airflow generates a force on the upper surface of the wing, causing the aircraft to roll around its longitudinal axis.

[0099] In this embodiment, the state space linear parameters required for the UAV flight include: position tracking error, velocity tracking error, attitude tracking error, fuel management error In this embodiment, the reference motion conditions for the UAV flight refer to the basic motion laws that the UAV should satisfy in the absence of external forces, such as mass balance, conservation of energy, conservation of angular momentum, and conservation of linear momentum.

[0100] In this embodiment, the condition parameters corresponding to the reference motion condition include: Mass balance condition: The center of gravity of the drone must be at the geometric center of the aircraft to ensure that the mass of the aircraft is evenly distributed and avoid center of gravity deviation.

[0101] Energy conservation condition: During the flight of a drone, its mechanical energy must remain constant.

[0102] Angular momentum conservation condition: Angular momentum conservation applies to rotor-driven UAVs. Under this condition, the rotor torque generated by the rotor must be balanced, otherwise the UAV will lose control.

[0103] Conditions for conservation of linear momentum: Conservation of linear momentum applies to drones powered by thrusters. Under the conditions for conservation of linear momentum, the combined external force generated by the thrusters and the resistance must offset the centrifugal force of the rotor to keep the drone flying in a straight line.

[0104] In this embodiment, the power transmission parameters of the UAV during flight include: Power type: including electric motor and internal combustion engine.

[0105] Power structure: Different types of power systems have different structural characteristics. For example, the rotor of an electric motor is composed of an inductor winding, while the piston and crankshaft of an internal combustion engine are its main moving parts.

[0106] Power transmission method: In addition to direct connection power transmission method, power transmission can also be carried out by means of transmission belts or hydraulic systems.

[0107] Power control parameters: Power control parameters refer to the parameters required to adjust and balance the power of the UAV.

[0108] In this embodiment, the full-dimensional motion state of the drone during flight includes: ascending, descending, rolling, pitching, and yaw.

[0109] In this embodiment, the initialization flight performance parameters of the UAV include: empty weight, maximum take-off weight, and maximum load weight.

[0110] The beneficial effects of the above technical solution are: obtaining design parameters through the UAV model, setting the range of flight altitude and speed, calculating the X, Y axial force deviations at different altitudes and speeds, obtaining the reference motion conditions and corresponding conditional parameters, and determining the full-dimensional motion state of the UAV based on the conditional parameters and power transmission parameters, thereby obtaining the performance data of the UAV. Through precise control of flight parameters, it can be ensured that the UAV is always in a safe state, avoiding possible dangerous situations, and improving the flight safety and efficiency of the UAV.

[0111] Embodiment 8: A method for remote real-time monitoring of unmanned aerial vehicles, such as Figure 2 As shown, including: Step 1: Obtain the specific purpose and mission requirements of the drone, and select a corresponding drone model according to the specific purpose and mission requirements of the drone; Step 2: Determine multiple influencing factors of the drone according to the drone model, configure different sensors for the drone according to the parameters, obtain real-time status information of the drone according to the sensors, and integrate data from different sensors by combining data fusion technology; Step 3: Obtain the key parameters of the drone, establish a state assessment model based on the integrated data, determine the health status of the drone, and identify abnormal behaviors and potential failures of the drone based on the health status; Step 4: Use machine learning algorithms to analyze historical fault data, abnormal behaviors, and potential faults, determine fault modes and characteristics, and build a fault prediction model; Step 5: Obtain a fault diagnosis algorithm based on pattern recognition and fault tree analysis, and quickly locate the cause of the fault based on the fault prediction model, obtain a fault isolation strategy based on the fault cause, and realize remote real-time monitoring of the drone.

[0112] The beneficial effects of the above technical solution are: different sensors are configured for drones according to the models of drones, and the acquired data are integrated, and a drone status assessment model is established in combination with the key parameters of the drone to assess the health status of the drone, obtain potential faults, and obtain fault isolation strategies based on the causes of the faults, which can ensure the accuracy of the drone's flight status, environmental parameters, and mission status monitoring data. At the same time, the drone can be monitored and managed in real time, realizing the intelligence, real-time and efficiency of the drone, and improving the safety and efficiency of the drone during operation.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A UAV remote real-time monitoring system, characterized in that: include: Selection module: obtaining the specific purpose and mission requirements of the drone, and selecting a corresponding drone model according to the specific purpose and mission requirements of the drone; Integration module: determining multiple factors affecting the flight of the drone according to the drone model, configuring different sensors for the drone according to the multiple factors, integrating the real-time detection data of different sensors based on data fusion technology, and obtaining the real-time status information of the drone according to the integrated data; Identification module: obtains the key parameters of the drone, establishes a status assessment model based on the integrated data, determines the real-time health status of the drone, and identifies the real-time abnormal behavior and potential failures of the drone based on the real-time health status; Building module: Use machine learning algorithms to analyze the drone’s historical fault data, real-time abnormal behavior, and potential faults, determine real-time fault modes and characteristics, and build a fault prediction model; Positioning module: obtains a fault diagnosis algorithm based on pattern recognition and fault tree analysis, and quickly locates the cause of the fault based on the fault prediction model, obtains a fault isolation strategy based on the fault cause, and realizes remote real-time monitoring of the drone.

2. The UAV remote real-time monitoring system according to claim 1, characterized in that: Select modules including: A first acquisition unit: acquires the usage scenario and purpose of the drone, and determines the specific purpose and mission requirements of the drone based on the drone usage guide according to the usage scenario and purpose; A first determination unit: determining the functional requirements and cost factors of the UAV according to the specific purpose and mission requirements of the UAV; Selection unit: selects a corresponding drone model according to the functional requirements and cost factors.

3. The UAV remote real-time monitoring system according to claim 1, characterized in that: Integration modules, including: A second acquisition unit: acquiring flight characteristics and performance data of the UAV according to the UAV model; A second determination unit: determining flight data of the UAV in different environments according to the flight characteristics and performance data; A third determining unit: determining multiple factors affecting the flight of the UAV according to the flight data; Configuration unit: obtaining specific description features of multiple factors, and configuring corresponding sensors for the drone according to the specific description features; Integration unit: integrates the relevant information of the UAV obtained by the sensor based on the multi-source data fusion technology of the Bayesian network; The fourth determination unit obtains the surrounding environment and self-motion information of the UAV according to the integrated data, and determines the real-time status information of the UAV according to the surrounding environment and self-motion information.

4. The UAV remote real-time monitoring system according to claim 1, characterized in that: Identification module, including: The third acquisition unit: obtains the key parameters of the drone through the flight control system and communication protocol; Extraction unit: preprocessing the key parameters, and extracting speed and position features from the preprocessed data based on feature extraction engineering; Establishing unit: training the speed and position characteristics and the integrated data based on a machine learning algorithm, and establishing a state assessment model according to the training results; The fifth determination unit: performs real-time analysis and prediction of the real-time status information of the drone according to the drone status assessment model to determine the current health status of the drone; Identification unit: compares the current health status of the drone with its historical health status, and identifies abnormal behaviors and potential failures of the drone in real time.

5. The UAV remote real-time monitoring system according to claim 1, characterized in that: Building blocks, including: The fourth acquisition unit: acquires the time series characteristics and frequency domain characteristics of historical fault data, abnormal behaviors and potential faults; Classification and clustering unit: determining a corresponding machine learning algorithm according to the time series characteristics and frequency domain characteristics, and classifying and clustering faults according to the machine learning algorithm; The sixth determination unit: determines the fault mode and characteristics according to the classification and clustering results combined with the actual situation; Construction unit: The determined fault modes and features are used as input features of the model to build a fault prediction model.

6. The UAV remote real-time monitoring system according to claim 1, characterized in that: Positioning module, including: Definition unit: Construct a fault tree based on the structure and fault phenomenon of the UAV system, and define the possibility and impact of each branch; Classification and matching unit: For each fault, identify its corresponding symptoms, and classify and match them through pattern recognition technology; The fifth acquisition unit: acquires the corresponding fault diagnosis algorithm through the branches of the fault tree and the results of pattern recognition; Positioning unit: quickly locate the cause of the fault based on the fault prediction model according to the fault diagnosis algorithm, determine the fault isolation range according to the fault cause, obtain the fault isolation strategy according to the fault isolation range, and realize remote real-time monitoring of the UAV.

7. The UAV remote real-time monitoring system according to claim 3, characterized in that: The second acquisition unit includes: The first determination subunit: obtains the design parameters of the UAV according to the UAV model, and determines the quantitative range of the flight altitude and the quantitative range of the flight speed of the UAV according to the design parameters; The second determination subunit determines the X-axis force deviation of the UAV at different flight speeds at the same flight altitude and the Y-axis force deviation at different flight altitudes at the same flight speed according to the flight altitude quantitative range and the flight speed quantitative range; The third determination subunit determines the surrounding air flow field distribution parameters of the UAV during flight according to the X-axis force deviation and the Y-axis force deviation; The fourth determination subunit: determines the aerodynamic loads of the nose, wings on both sides and tail of the UAV during flight based on the air flow field distribution parameters and the structural parameters of the UAV; Construct subunits: construct the flight dynamics model of the UAV according to the aerodynamic load, and determine the power distribution parameters of each position of the UAV during flight according to the flight dynamics model; The fifth determination subunit: determines the aerodynamic torque of the UAV during flight according to the power distribution parameter, and determines the state space linear parameters required for the UAV flight according to the aerodynamic torque; The first acquisition subunit is used to determine the reference motion condition of the UAV flight based on the state space linear parameter, and obtain the condition parameter corresponding to the reference motion condition; The sixth determination subunit: determines the full-dimensional motion state of the UAV during flight according to the condition parameters and the power transmission parameters of the UAV during flight; The seventh determination subunit: determines the flight characteristics of the UAV according to the full-dimensional motion state, and determines the flight dynamic gain of the UAV based on the flight characteristics; The eighth determination subunit determines the performance data of the UAV according to the flight dynamic gain and the initialization flight performance parameters of the UAV.

8. A method for remote real-time monitoring of unmanned aerial vehicles, characterized in that: include: Step 1: Obtain the specific purpose and mission requirements of the drone, and select a corresponding drone model according to the specific purpose and mission requirements of the drone; Step 2: Determine multiple influencing factors of the drone according to the drone model, configure different sensors for the drone according to the parameters, obtain real-time status information of the drone according to the sensors, and integrate data from different sensors by combining data fusion technology; Step 3: Obtain the key parameters of the drone, establish a state assessment model based on the integrated data, determine the health status of the drone, and identify abnormal behaviors and potential failures of the drone based on the health status; Step 4: Use machine learning algorithms to analyze historical fault data, abnormal behaviors, and potential faults, determine fault modes and characteristics, and build a fault prediction model; Step 5: Obtain a fault diagnosis algorithm based on pattern recognition and fault tree analysis, and quickly locate the cause of the fault based on the fault prediction model, obtain a fault isolation strategy based on the fault cause, and realize remote real-time monitoring of the drone.

Images