Disclosure of Invention
The invention provides a remote real-time monitoring system and method for an unmanned aerial vehicle, which are used for solving the defects that in the prior art, the traditional remote real-time monitoring of the unmanned aerial vehicle needs to be manually performed with monitoring data, so that the flight state, the environmental parameters and the task state of the unmanned aerial vehicle are not accurately monitored, and meanwhile, the unmanned aerial vehicle cannot be monitored and managed in real time, so that the intelligent, real-time and high-efficiency of the unmanned aerial vehicle are not realized, and the safety and high-efficiency of the unmanned aerial vehicle during working are reduced.
In one aspect, the present invention provides an unmanned aerial vehicle remote real-time monitoring system, comprising:
the selection module is used for acquiring specific application and task requirements of the unmanned aerial vehicle and selecting a corresponding unmanned aerial vehicle model according to the specific application and task requirements of the unmanned aerial vehicle;
The integration module is used for determining a plurality of factors influencing the flight of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle, configuring different sensors for the unmanned aerial vehicle according to the factors, integrating real-time detection data of the different sensors based on a data fusion technology, and acquiring real-time state information of the unmanned aerial vehicle according to the integrated data;
the identification module is used for acquiring each key parameter of the unmanned aerial vehicle, establishing a state evaluation model by combining the integrated data, determining the real-time health state of the unmanned aerial vehicle, and identifying the real-time abnormal behavior and potential faults of the unmanned aerial vehicle according to the real-time health state;
The construction module is used for analyzing historical fault data of the unmanned aerial vehicle, real-time abnormal behaviors of the unmanned aerial vehicle and potential faults by utilizing a machine learning algorithm, determining a real-time fault mode and characteristics and constructing a fault prediction model;
And the positioning module is used for acquiring a fault diagnosis algorithm based on pattern recognition and fault tree analysis, rapidly positioning fault reasons based on a fault prediction model, acquiring a fault isolation strategy according to the fault reasons and realizing remote real-time monitoring of the unmanned aerial vehicle.
According to the unmanned aerial vehicle remote real-time monitoring system provided by the invention, the selection module comprises:
The first acquisition unit is used for acquiring a use scene and a purpose of the unmanned aerial vehicle, and determining the specific purpose and task requirement of the unmanned aerial vehicle based on the use instruction of the unmanned aerial vehicle according to the use scene and the purpose;
the first determining unit is used for determining the function requirement and cost factor of the unmanned aerial vehicle according to the specific application and task requirement of the unmanned aerial vehicle;
And the selection unit is used for selecting the corresponding unmanned aerial vehicle model number according to the function requirement and the cost factor.
According to the unmanned aerial vehicle remote real-time monitoring system provided by the invention, the integration module comprises:
the second acquisition unit acquires flight characteristics and performance data of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle;
The second determining unit is used for determining flight data of the unmanned aerial vehicle in different environments according to the flight characteristics and the performance data;
a third determining unit that determines a plurality of factors affecting the flight of the unmanned aerial vehicle based on the flight data;
The configuration unit is used for acquiring specific description characteristics of a plurality of factors and configuring corresponding sensors for the unmanned aerial vehicle according to the specific description characteristics;
The integration unit is used for integrating the related information of the unmanned aerial vehicle acquired by the sensor based on a multi-source data fusion technology of the Bayesian network;
And the fourth determining unit is used for acquiring the surrounding environment and the self-motion information of the unmanned aerial vehicle according to the integrated data and determining the real-time state information of the unmanned aerial vehicle according to the surrounding environment and the self-motion information.
According to the unmanned aerial vehicle remote real-time monitoring system provided by the invention, the identification module comprises:
The third acquisition unit acquires each key parameter of the unmanned aerial vehicle through the flight control system and the communication protocol;
the extraction unit is used for preprocessing the key parameters and extracting engineering extraction speed and position characteristics based on the characteristics from the preprocessed data;
the establishing unit is used for training the speed and position characteristics and the integrated data based on a machine learning algorithm and establishing a state evaluation model according to a training result;
The fifth determining unit is used for carrying out real-time analysis and prediction on the real-time state information of the unmanned aerial vehicle according to the state evaluation model of the unmanned aerial vehicle, and determining the current health state of the unmanned aerial vehicle;
And the identification unit is used for comparing the current health state and the historical health state of the unmanned aerial vehicle and identifying the real-time abnormal behavior and potential faults of the unmanned aerial vehicle.
According to the unmanned aerial vehicle remote real-time monitoring system provided by the invention, a building module comprises:
The fourth acquisition unit acquires historical fault data, abnormal behaviors and time sequence features and frequency domain features of potential faults;
The classification and clustering unit is used for determining a corresponding machine learning algorithm according to the time sequence features and the frequency domain features, and classifying and clustering faults according to the machine learning algorithm;
A sixth determining unit, for determining fault mode and feature according to classification and clustering result combining actual condition;
and the construction unit is used for constructing a fault prediction model by taking the determined fault mode and the determined characteristics as input characteristics of the model.
According to the unmanned aerial vehicle remote real-time monitoring system provided by the invention, the positioning module comprises:
a definition unit for constructing a fault tree according to the structure and fault phenomenon of the system and defining the possibility and influence of each branch;
the classification matching unit is used for identifying the corresponding symptoms of each fault and classifying and matching the faults through a pattern identification technology;
A fifth acquisition unit for acquiring a corresponding fault diagnosis algorithm through the branch of the fault tree and the result of pattern recognition;
And the positioning unit is used for rapidly positioning fault reasons based on a fault prediction model according to the fault diagnosis algorithm, determining a fault isolation range according to the fault reasons, acquiring a fault isolation strategy according to the fault isolation range and realizing remote real-time monitoring of the unmanned aerial vehicle.
According to the unmanned aerial vehicle remote real-time monitoring system provided by the invention, the second acquisition unit comprises:
the first determination subunit acquires the design parameters of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle, and determines the flying height quantitative range and the flying speed quantitative range of the unmanned aerial vehicle according to the design parameters;
The second determination subunit is used for determining X-axis force deviation between different flying speeds of the unmanned aerial vehicle under the same flying height and Y-axis force deviation between different flying speeds of the unmanned aerial vehicle under the same flying speed according to the flying height quantitative range and the flying speed quantitative range;
The third determination subunit is used for determining the distribution parameters of the surrounding air flow field of the unmanned aerial vehicle in flight according to the X-axial force deviation and the Y-axial force deviation;
A fourth determination subunit for respectively determining aerodynamic loads of the unmanned aerial vehicle at the head, the wings at two sides and the tail of the flight time based on the air flow field distribution parameters and the structural parameters of the unmanned aerial vehicle;
the construction subunit is used for constructing a flight dynamics model of the unmanned aerial vehicle according to the pneumatic load and determining power distribution parameters of each position of the unmanned aerial vehicle in flight according to the flight dynamics model;
a fifth determination subunit, for determining aerodynamic moment of the unmanned aerial vehicle during flight according to the power distribution parameter, and determining state space linear parameter required by the unmanned aerial vehicle flight according to the aerodynamic moment;
the first acquisition subunit is used for determining a reference motion condition of the unmanned aerial vehicle flight based on the state space linear parameter and acquiring a condition parameter corresponding to the reference motion condition;
A sixth determining subunit for determining the full-dimensional motion state of the unmanned aerial vehicle in flight according to the condition parameters and the power transmission parameters of the unmanned aerial vehicle in flight;
A seventh determination subunit, determining flight characteristics of the unmanned aerial vehicle according to the full-dimensional motion state, and determining flight dynamic gain of the unmanned aerial vehicle based on the flight characteristics;
and the eighth determination subunit is used for determining the performance data of the unmanned aerial vehicle according to the flight dynamic gain and the initialized flight performance parameters of the unmanned aerial vehicle.
The invention provides a remote real-time monitoring method for an unmanned aerial vehicle, which comprises the following steps:
step 1, acquiring specific application and task requirements of an unmanned aerial vehicle, and selecting a corresponding unmanned aerial vehicle model according to the specific application and task requirements of the unmanned aerial vehicle;
Step 2, determining a plurality of influence factors of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle, configuring different sensors for the unmanned aerial vehicle according to parameters, acquiring real-time state information of the unmanned aerial vehicle according to the sensors, and integrating data of the different sensors by combining a data fusion technology;
Step 3, acquiring each key parameter of the unmanned aerial vehicle, combining the integrated data to establish a state evaluation model, determining the health state of the unmanned aerial vehicle, and identifying the abnormal behavior and potential faults of the unmanned aerial vehicle according to the health state;
Step 4, analyzing historical fault data, abnormal behaviors and potential faults by using a machine learning algorithm, determining fault modes and characteristics, and constructing a fault prediction model;
And 5, acquiring a fault diagnosis algorithm based on pattern recognition and fault tree analysis, rapidly positioning fault reasons based on a fault prediction model, and acquiring a fault isolation strategy according to the fault reasons to realize remote real-time monitoring of the unmanned aerial vehicle.
Compared with the prior art, the application has the following beneficial effects:
The unmanned aerial vehicle is configured with different sensors through the model of the unmanned aerial vehicle, acquired data are fused, a state evaluation model of the unmanned aerial vehicle is established by combining key parameters of the unmanned aerial vehicle to evaluate the health state of the unmanned aerial vehicle, potential faults are acquired, a fault isolation strategy is acquired according to fault reasons, accuracy of the flight state, environment parameters and task state monitoring data of the unmanned aerial vehicle can be guaranteed, meanwhile, real-time state monitoring and management of the unmanned aerial vehicle can be carried out, intelligent, real-time and efficient operation of the unmanned aerial vehicle is achieved, and safety and efficiency of the unmanned aerial vehicle during operation are improved.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
The embodiment of the invention provides an unmanned aerial vehicle remote real-time monitoring system, which mainly comprises the following modules as shown in fig. 1:
the selection module is used for acquiring specific application and task requirements of the unmanned aerial vehicle and selecting a corresponding unmanned aerial vehicle model according to the specific application and task requirements of the unmanned aerial vehicle;
The integration module is used for determining a plurality of factors influencing the flight of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle, configuring different sensors for the unmanned aerial vehicle according to the factors, integrating real-time detection data of the different sensors based on a data fusion technology, and acquiring real-time state information of the unmanned aerial vehicle according to the integrated data;
the identification module is used for acquiring each key parameter of the unmanned aerial vehicle, establishing a state evaluation model by combining the integrated data, determining the real-time health state of the unmanned aerial vehicle, and identifying the real-time abnormal behavior and potential faults of the unmanned aerial vehicle according to the real-time health state;
The construction module is used for analyzing historical fault data of the unmanned aerial vehicle, real-time abnormal behaviors of the unmanned aerial vehicle and potential faults by utilizing a machine learning algorithm, determining a real-time fault mode and characteristics and constructing a fault prediction model;
And the positioning module is used for acquiring a fault diagnosis algorithm based on pattern recognition and fault tree analysis, rapidly positioning fault reasons based on a fault prediction model, acquiring a fault isolation strategy according to the fault reasons and realizing remote real-time monitoring of the unmanned aerial vehicle.
In this embodiment, specific uses of the unmanned aerial vehicle include:
The unmanned aerial vehicle can rapidly conduct surveying and mapping, crop pest detection and irrigation management on farmlands.
Mapping, namely, the unmanned aerial vehicle can carry out high-precision map making and data acquisition in the fields of building sites, environment monitoring, urban planning and the like.
The unmanned aerial vehicle can provide high-quality aerial photography service for industries such as film and television production, news report, advertisement shooting and the like.
In this embodiment, the plurality of factors affecting the flight of the drone include meteorological conditions, ground obstructions, electromagnetic interference.
In this embodiment, the different sensors include an Inertial Measurement Unit (IMU), a Global Positioning System (GPS), barometer, temperature sensor, humidity sensor, vibration sensor.
In this embodiment, the data fusion technique is a 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.
In this embodiment, the real-time status information includes position, velocity, attitude, environmental parameters.
In this embodiment, the state evaluation model refers to a model that evaluates the real-time state of the unmanned aerial vehicle.
In this embodiment, the real-time health status of the unmanned aerial vehicle refers to the technical status and performance of the unmanned aerial vehicle itself.
In this embodiment, the fault tree is a graphical tool for describing potential causal relationships among system components, which can help us analyze and identify root causes that may lead to the failure of the whole system, and is mainly composed of four parts, namely trigger conditions, branch probabilities, leaf results and root nodes, which represent various combinations that may lead to the final failure.
In this embodiment, the fault isolation policy refers to that when a fault of a certain system or component is detected, a fault part can be automatically isolated, and the system or component is switched to a standby system or component, so as to maintain the basic function of the unmanned aerial vehicle.
The technical scheme has the beneficial effects that different sensors are configured on the unmanned aerial vehicle through the model of the unmanned aerial vehicle, acquired data are fused, a state evaluation model of the unmanned aerial vehicle is established by combining key parameters of the unmanned aerial vehicle to evaluate the health state of the unmanned aerial vehicle, potential faults are acquired, a fault isolation strategy is acquired according to fault reasons, accuracy of flight state, environment parameters and task state monitoring data of the unmanned aerial vehicle can be guaranteed, and meanwhile, real-time state monitoring and management can be carried out on the unmanned aerial vehicle, so that the intelligent, real-time and efficient performance of the unmanned aerial vehicle are realized, and the safety and the high efficiency of the unmanned aerial vehicle during working are improved.
Example 2:
Based on embodiment 1, the embodiment selection module of the present invention includes:
The first acquisition unit is used for acquiring a use scene and a purpose of the unmanned aerial vehicle, and determining the specific purpose and task requirement of the unmanned aerial vehicle based on the use instruction of the unmanned aerial vehicle according to the use scene and the purpose;
the first determining unit is used for determining the function requirement and cost factor of the unmanned aerial vehicle according to the specific application and task requirement of the unmanned aerial vehicle;
And the selection unit is used for selecting the corresponding unmanned aerial vehicle model number according to the function requirement and the cost factor.
In the embodiment, the unmanned aerial vehicle has the use occasions of agricultural field, logistics transportation, photogrammetry and search and rescue.
In this embodiment, the unmanned aerial vehicle is used for purposes including mapping on farmlands, spraying pesticides or seeding, and rapidly transporting goods from the production site to the desired site, topography and photographing and mapping work of buildings.
In this embodiment, the unmanned plane use guide refers to a guide for guiding a user how to use the unmanned plane, a suitable scene, and a specific use.
In this embodiment, functional requirements refer to time of flight, load capacity, radius of operation, tamper resistance, ease of operation.
The technical scheme has the beneficial effects that the function requirements and cost factors of the unmanned aerial vehicle are determined according to the specific application and task requirements of the unmanned aerial vehicle, so that the corresponding unmanned aerial vehicle model number is selected, the specific requirements can be met, and the use cost of the unmanned aerial vehicle is reduced.
Example 3:
based on embodiment 2, the integration module of the embodiment of the present invention includes:
the second acquisition unit acquires flight characteristics and performance data of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle;
The second determining unit is used for determining flight data of the unmanned aerial vehicle in different environments according to the flight characteristics and the performance data;
a third determining unit that determines a plurality of factors affecting the flight of the unmanned aerial vehicle based on the flight data;
The configuration unit is used for acquiring specific description characteristics of a plurality of factors and configuring corresponding sensors for the unmanned aerial vehicle according to the specific description characteristics;
The integration unit is used for integrating the related information of the unmanned aerial vehicle acquired by the sensor based on a multi-source data fusion technology of the Bayesian network;
And the fourth determining unit is used for acquiring the surrounding environment and the self-motion information of the unmanned aerial vehicle according to the integrated data and determining the real-time state information of the unmanned aerial vehicle according to the surrounding environment and the self-motion information.
In this embodiment, the flight characteristics of the unmanned aerial vehicle refer to the performance of the unmanned aerial vehicle in the air, including stability and controllability, fuel efficiency and safety.
In this embodiment, the key performance data of the unmanned aerial vehicle includes flight speed, range, wind resistance.
In this embodiment, different environments refer to different temperatures, pressures, wind speeds and wind directions.
In this embodiment, the flight data includes altitude, speed, course, fuel consumption.
In this embodiment, the plurality of factors affecting the flight of the drone include meteorological conditions, ground obstructions, electromagnetic interference.
In this embodiment, the specific descriptive characteristics of the plurality of factors affecting the flight of the drone include:
Meteorological conditions:
Temperature affects the dynamics and fuel consumption of the aircraft. Too low or too high an air temperature may cause problems such as reduced engine efficiency or icing of the fuel.
Humidity-relative humidity affects the moisture content of the air, which can have a corrosive effect on the engine intake and body surfaces of the aircraft.
Air pressure-variations in air pressure affect the rate of rise and fall of the aircraft, as well as fuel consumption.
In this embodiment, the bayesian network-based multi-source data fusion technique is a method for comprehensively processing data from different sensors or sources by utilizing the strong probabilistic reasoning capability of the bayesian network and the distributed network structure.
In this embodiment, the self-movement information of the unmanned aerial vehicle includes:
location information including longitude, latitude, and altitude.
Speed information-speed information of the unmanned aerial vehicle includes average speed, maximum speed and instantaneous speed.
And the gesture information of the unmanned aerial vehicle comprises a pitch angle, a roll angle and a yaw angle.
The technical scheme has the beneficial effects that the flight data of the unmanned aerial vehicle under different environments is determined according to the flight characteristics and the performance data of the unmanned aerial vehicle, a plurality of factors influencing the flight of the unmanned aerial vehicle are determined, corresponding sensors are configured for the unmanned aerial vehicle, the data of the sensors are integrated, the real-time state information of the unmanned aerial vehicle is determined, abnormal conditions can be found in time, the safety of the unmanned aerial vehicle is improved, meanwhile, the actions of the unmanned aerial vehicle can be planned and controlled more accurately according to the real-time speed and the position of the unmanned aerial vehicle, and the flight efficiency is improved.
Example 4:
based on embodiment 3, the identification module of the embodiment of the present invention includes:
The third acquisition unit acquires each key parameter of the unmanned aerial vehicle through the flight control system and the communication protocol;
the extraction unit is used for preprocessing the key parameters and extracting engineering extraction speed and position characteristics based on the characteristics from the preprocessed data;
the establishing unit is used for training the speed and position characteristics and the integrated data based on a machine learning algorithm and establishing a state evaluation model according to a training result;
The fifth determining unit is used for carrying out real-time analysis and prediction on the real-time state information of the unmanned aerial vehicle according to the state evaluation model of the unmanned aerial vehicle, and determining the current health state of the unmanned aerial vehicle;
And the identification unit is used for comparing the current health state and the historical health state of the unmanned aerial vehicle and identifying the real-time abnormal behavior and potential faults of the unmanned aerial vehicle.
In this embodiment, the flight control system is responsible for controlling and monitoring the flight status of the drone.
In this embodiment, the communication protocol is the way data is exchanged between the different components in the drone system, defining how the data is sent from the ground station to the drone, and how the data is exchanged between the drones or with other devices.
In this embodiment, the key parameters include time of flight, distance of flight, battery power.
In this embodiment, feature extraction engineering is a computer vision technique aimed at extracting useful information from images or videos.
In this embodiment, the speed and position features include linear acceleration, angular velocity, and position information.
In this embodiment, the state estimation model estimates the flight state of the unmanned aerial vehicle in each case, and generates control instructions to enable the unmanned aerial vehicle to fly along a predetermined trajectory.
The technical scheme has the beneficial effects that the current health state of the unmanned aerial vehicle is determined by preprocessing key parameters of the unmanned aerial vehicle, extracting speed and position characteristics and combining integrated data to establish a state evaluation model, so that the accurate determination of the state of the unmanned aerial vehicle can be ensured, and the safety of the unmanned aerial vehicle and the reliability of a remote real-time monitoring system of the unmanned aerial vehicle are improved.
Example 5:
Based on embodiment 4, the embodiment of the invention constructs a module, which includes:
The fourth acquisition unit acquires historical fault data, abnormal behaviors and time sequence features and frequency domain features of potential faults;
The classification and clustering unit is used for determining a corresponding machine learning algorithm according to the time sequence features and the frequency domain features, and classifying and clustering faults according to the machine learning algorithm;
A sixth determining unit, for determining fault mode and feature according to classification and clustering result combining actual condition;
and the construction unit is used for constructing a fault prediction model by taking the determined fault mode and the determined characteristics as input characteristics of the model.
In this embodiment, the unmanned plane historical fault data includes fault type, fault frequency, fault time and place, and fault impact range.
In this embodiment, the abnormal behavior of the drone includes deviations from the planned flight path, battery life anomalies.
In this embodiment, the time series characteristic of the potential fault refers to a series of time and sequence rules such as time intervals, ascending trend, descending trend, where the fault may occur in the unmanned system.
In this embodiment, the frequency domain characteristics of the potential fault are a set of characteristics reflecting the distribution and intensity of the fault over the frequency domain, including:
The failure frequency, the number of times of failure or the number of events, reflects the operation condition of the system in a specific time period. A higher failure frequency may indicate that the system is severely failing.
The duration of the fault, the duration from the occurrence of the fault to the repair, reflects the extent of the impact of the fault and the instability of the system. A longer failure duration may indicate that the system is severely malfunctioning or inherently defective.
Spectral density-distribution of failure frequencies in frequency domain analysis. The high frequency component may indicate that the fault is mainly concentrated in certain specific frequency ranges, while the low frequency component may be related to the root cause of structural damage, etc.
Resonance frequency-in some cases, the fault may amplify at a particular natural frequency. This is called the resonant frequency, and may be due to matching of the natural vibration mode of the system with the external driving force.
In this embodiment, the failure mode refers to the type of failure that may occur to the device or system, such as a battery failure, a motor failure, a remote control failure, a sensor failure.
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.
The technical scheme has the advantages that the corresponding machine learning algorithm is determined through the time sequence features and the frequency domain features, faults are classified and clustered, the fault mode and the features are determined, the fault prediction model is built, components with potential fault risks can be accurately and rapidly identified, and therefore downtime and maintenance cost are reduced, and reliability and safety of equipment are guaranteed.
Example 6:
Based on embodiment 5, the positioning module of the embodiment of the present invention includes:
a definition unit for constructing a fault tree according to the structure and fault phenomenon of the system and defining the possibility and influence of each branch;
the classification matching unit is used for identifying the corresponding symptoms of each fault and classifying and matching the faults through a pattern identification technology;
A fifth acquisition unit for acquiring a corresponding fault diagnosis algorithm through the branch of the fault tree and the result of pattern recognition;
And the positioning unit is used for rapidly positioning fault reasons based on a fault prediction model according to the fault diagnosis algorithm, determining a fault isolation range according to the fault reasons, acquiring a fault isolation strategy according to the fault isolation range and realizing remote real-time monitoring of the unmanned aerial vehicle.
In this embodiment, unmanned aerial vehicle failure phenomena include runaway, battery failure, failure of the fuselage structure, failure of the engine or other mechanical components, communication failure.
In this embodiment, the fault tree is a graphical tool for identifying and analyzing potential fault causes, which decomposes various possible fault causes into several sub-trees that are independent of each other, and derives the final fault point from the combined relationship of these sub-trees.
In this embodiment, the symptoms corresponding to each fault include:
and (3) engine faults, namely that the unmanned aerial vehicle loses power or runs abnormally.
Communication failure-communication interruption or signal loss between the drone and other devices.
And the navigation system is in fault, namely the unmanned aerial vehicle is positioned and the course control is in error.
And the sensor has faults that the readings of key sensors such as an unmanned aerial vehicle altimeter, a barometer, a thermometer and the like are abnormal.
In this embodiment, pattern recognition techniques are used to analyze and process the input data to extract hidden meaningful information and patterns therefrom.
In this embodiment, the fault diagnosis algorithm is used for detecting and predicting potential faults of the equipment or the system, such as regression analysis, cluster analysis and principal component analysis.
In this embodiment, the fault prediction model is a mathematical model for predicting the type and time of faults that may occur in a device or system, and such model typically uses historical data analysis to identify abnormal behavior of the device, such as K-nearest neighbor algorithms, random forests.
In this embodiment, the fault isolation range refers to a range in which, when one system fails, measures are required to ensure that the normal operation of the entire system is not affected, and that the fault needs to be removed.
In this embodiment, the fault isolation policy is an action taken upon a fault, in order to ensure that the entire system or business process can continue to operate and to reduce the impact of the fault.
The technical scheme has the advantages that the corresponding fault diagnosis algorithm is obtained through the branch and mode identification results of the fault tree, the fault reason is located based on the fault prediction model, the fault isolation strategy is obtained, the faults can be rapidly identified and isolated, the downtime and maintenance work can be reduced, and the flight efficiency and safety of the unmanned aerial vehicle are improved.
Example 7:
based on embodiment 6, a second obtaining unit according to an embodiment of the present invention includes:
the first determination subunit acquires the design parameters of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle, and determines the flying height quantitative range and the flying speed quantitative range of the unmanned aerial vehicle according to the design parameters;
The second determination subunit is used for determining X-axis force deviation between different flying speeds of the unmanned aerial vehicle under the same flying height and Y-axis force deviation between different flying speeds of the unmanned aerial vehicle under the same flying speed according to the flying height quantitative range and the flying speed quantitative range;
The third determination subunit is used for determining the distribution parameters of the surrounding air flow field of the unmanned aerial vehicle in flight according to the X-axial force deviation and the Y-axial force deviation;
A fourth determination subunit for respectively determining aerodynamic loads of the unmanned aerial vehicle at the head, the wings at two sides and the tail of the flight time based on the air flow field distribution parameters and the structural parameters of the unmanned aerial vehicle;
the construction subunit is used for constructing a flight dynamics model of the unmanned aerial vehicle according to the pneumatic load and determining power distribution parameters of each position of the unmanned aerial vehicle in flight according to the flight dynamics model;
a fifth determination subunit, for determining aerodynamic moment of the unmanned aerial vehicle during flight according to the power distribution parameter, and determining state space linear parameter required by the unmanned aerial vehicle flight according to the aerodynamic moment;
the first acquisition subunit is used for determining a reference motion condition of the unmanned aerial vehicle flight based on the state space linear parameter and acquiring a condition parameter corresponding to the reference motion condition;
A sixth determining subunit for determining the full-dimensional motion state of the unmanned aerial vehicle in flight according to the condition parameters and the power transmission parameters of the unmanned aerial vehicle in flight;
A seventh determination subunit, determining flight characteristics of the unmanned aerial vehicle according to the full-dimensional motion state, and determining flight dynamic gain of the unmanned aerial vehicle based on the flight characteristics;
and the eighth determination subunit is used for determining the performance data of the unmanned aerial vehicle according to the flight dynamic gain and the initialized flight performance parameters of the unmanned aerial vehicle.
In this embodiment, the design parameters of the drone include speed of flight, load capacity, battery life, range of flight, and stability performance.
In this embodiment, the quantitative range of the flying height of the unmanned aerial vehicle refers to the vertical distance of the unmanned aerial vehicle moving in the atmosphere, and in general, the flying height of the unmanned aerial vehicle can range from several meters to tens of kilometers.
In this embodiment, the quantitative range of the flight speed of the unmanned aerial vehicle refers to the horizontal movement speed of the unmanned aerial vehicle in the atmosphere, and in general, the flight speed of the unmanned aerial vehicle may range from several meters per second to several tens of meters per second.
In this embodiment, the X-axis force deviation refers to a phenomenon that the unmanned aerial vehicle yaw-moves along the X-axis due to aerodynamic effects between different flight speeds, and when the unmanned aerial vehicle flies at a high speed, its flight resistance is reduced, while the thrust is unchanged, which may cause the aircraft to generate a head-up motion, i.e., rise along the Y-axis direction. At this time, without a suitable control system to counteract this head-up motion, the drone would produce a yaw motion along the X-axis, whereas when the drone is flying at low speed, its flight resistance would increase, but the thrust would be unchanged, which could cause the aircraft to dive down.
In this embodiment, the Y-axis force deviation refers to a phenomenon that the unmanned aerial vehicle moves along the Y-axis in a yaw due to aerodynamic effects between different flying heights of the unmanned aerial vehicle, and when the unmanned aerial vehicle flies at high altitude, its aerodynamic force changes, so that the machine body generates additional rolling inertia. If the drone does not have sufficient stability to counteract this variation, it will produce roll motion along the Y axis, whereas if the drone flies at low altitude, its aerodynamic drag will increase, causing the machine body to produce additional dive inertia, if the drone does not have sufficient pitch stability to counteract this variation, the drone will produce roll motion along the Y axis.
In this embodiment, the distribution parameters of the surrounding air flow field of the unmanned aerial vehicle during flight include speed, pressure, temperature, turbulence and resistance.
In this embodiment, structural parameters of the unmanned aerial vehicle include the size, shape, angle and material of the wing, the strength and stiffness of the fuselage, the size, shape and material of the tail wing, the hover motor and the propeller.
In this embodiment, aerodynamic loading of the nose, wings and tail refers to the airflow pressure distribution experienced at these locations, such as:
Nose since it is the front of the unmanned aerial vehicle, the nose is mainly subjected to the airflow load along the advancing direction. In addition, the nose is the point of forward movement of the centre of gravity of the unmanned aerial vehicle, and therefore is also subjected to the main roll pneumatic load.
Aerodynamic loads on two sides of the wing are commonly referred to as "symmetrical aerodynamic loads" because the airflow pressure profiles they are subjected to are symmetrical. The wings on both sides are also subjected to the reactive forces of the air flow generated by the main rotor.
Tail, which is typically controlled by a pair or multiple vertical tails, the aerodynamic loading of the tails mainly includes the reaction of the airflow generated by the main rotor and the vortices generated by the tail itself.
In this embodiment, the unmanned aerial vehicle's flight dynamics model describes the unmanned aerial vehicle's law of motion under aerodynamic effects, and how to control the unmanned aerial vehicle's flight according to the desired pose and position.
In this embodiment, the power distribution parameters of each position of the unmanned aerial vehicle during flight include:
Main rotor the main rotor is responsible for providing vertical thrust and controlling the direction of flight, they should be able to generate sufficient lift and thrust to maintain hovering and stable flight of the unmanned aerial vehicle, and typically the rotational speed, pitch diameter and arrangement of the main rotor will affect the thrust and lift that it generates.
The auxiliary rotor is used for providing additional thrust and stability, and the rotation speed, the pitch diameter and the layout of the auxiliary rotor influence the thrust and the additional stability generated by the auxiliary rotor.
And the battery pack is responsible for providing power for the unmanned aerial vehicle. The location and size of the battery pack can affect the payload capacity and range of the drone.
In this embodiment, aerodynamic moment refers to the rotational effect of aerodynamic forces generated when the unmanned aerial vehicle is flying, and when the unmanned aerial vehicle is flying forward, the upper surface of the wing generates a rearward airflow, which exerts a force on the upper surface of the wing, causing the aircraft to roll about its longitudinal axis.
In this embodiment, the state space linear parameters required for unmanned aerial vehicle flight include position tracking error, speed tracking error, attitude tracking error, fuel management error
In the embodiment, the reference motion condition of the unmanned aerial vehicle is a basic motion rule which the unmanned aerial vehicle needs to meet under the action of no external force, such as mass balance, energy conservation, angular momentum conservation and linear momentum conservation.
In this embodiment, the condition parameters corresponding to the reference motion condition include:
And under the mass balance condition, the gravity center of the unmanned aerial vehicle is required to be in the geometric center of the aircraft, so that the mass distribution of the aircraft is ensured to be uniform, and the situation of gravity center deviation is avoided.
The energy conservation condition is that the mechanical energy of the unmanned aerial vehicle is ensured to be unchanged all the time in the flight process.
Angular momentum conservation conditions-angular momentum conservation is for a rotor-driven drone where the rotor torque generated by the rotor must be balanced or otherwise the drone may be out of control.
The linear momentum conservation condition is that the linear momentum conservation is aimed at the unmanned aerial vehicle taking the propeller as power, and under the linear momentum conservation condition, the combined external force generated by the propeller and the resistance is required to counteract the centrifugal force of the rotor wing, so that the unmanned aerial vehicle keeps straight line flight.
In this embodiment, the power transmission parameters of the unmanned aerial vehicle during flight include:
The power type comprises an electric motor and an internal combustion engine.
Power structure different types of power systems have different structural features, for example, the rotor of the motor consists of an inductive winding, while the pistons and crankshaft of the internal combustion engine are the main moving parts thereof.
The power transmission mode is that a transmission belt or a hydraulic system and the like can be adopted for power transmission besides a direct connection power transmission mode.
The power control parameter refers to a parameter required for adjusting and balancing the power of the unmanned aerial vehicle.
In this embodiment, the full dimensional motion state of the drone while flying includes ascent, descent, roll, pitch, yaw.
In this embodiment, the initialized flight performance parameters of the unmanned aerial vehicle include empty weight, maximum takeoff weight, and maximum load weight.
The technical scheme has the advantages that design parameters are obtained through the model number of the unmanned aerial vehicle, the range of the flying height and the speed is set, X, Y axial force deviations under different heights and speeds are calculated, reference movement conditions and corresponding condition parameters are obtained, the full-dimensional movement state of the unmanned aerial vehicle is determined according to the condition parameters and the power transmission parameters, so that performance data of the unmanned aerial vehicle are obtained, the unmanned aerial vehicle can be ensured to be always in a safe state through accurate control of the flying parameters, possible dangerous situations are avoided, and flying safety and flying efficiency of the unmanned aerial vehicle are improved.
Example 8:
A method for remote real-time monitoring of an unmanned aerial vehicle, as shown in fig. 2, comprising:
step 1, acquiring specific application and task requirements of an unmanned aerial vehicle, and selecting a corresponding unmanned aerial vehicle model according to the specific application and task requirements of the unmanned aerial vehicle;
Step 2, determining a plurality of influence factors of the unmanned aerial vehicle according to the model number of the unmanned aerial vehicle, configuring different sensors for the unmanned aerial vehicle according to parameters, acquiring real-time state information of the unmanned aerial vehicle according to the sensors, and integrating data of the different sensors by combining a data fusion technology;
Step 3, acquiring each key parameter of the unmanned aerial vehicle, combining the integrated data to establish a state evaluation model, determining the health state of the unmanned aerial vehicle, and identifying the abnormal behavior and potential faults of the unmanned aerial vehicle according to the health state;
Step 4, analyzing historical fault data, abnormal behaviors and potential faults by using a machine learning algorithm, determining fault modes and characteristics, and constructing a fault prediction model;
And 5, acquiring a fault diagnosis algorithm based on pattern recognition and fault tree analysis, rapidly positioning fault reasons based on a fault prediction model, and acquiring a fault isolation strategy according to the fault reasons to realize remote real-time monitoring of the unmanned aerial vehicle.
The technical scheme has the beneficial effects that different sensors are configured on the unmanned aerial vehicle through the model of the unmanned aerial vehicle, acquired data are fused, a state evaluation model of the unmanned aerial vehicle is established by combining key parameters of the unmanned aerial vehicle to evaluate the health state of the unmanned aerial vehicle, potential faults are acquired, a fault isolation strategy is acquired according to fault reasons, accuracy of flight state, environment parameters and task state monitoring data of the unmanned aerial vehicle can be guaranteed, and meanwhile, real-time state monitoring and management can be carried out on the unmanned aerial vehicle, so that the intelligent, real-time and efficient performance of the unmanned aerial vehicle are realized, and the safety and the high efficiency of the unmanned aerial vehicle during working are improved.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present invention.