Substation unmanned aerial vehicle flight analogue simulation method and system

Abstract

The invention discloses a substation unmanned aerial vehicle flight analogue simulation method and system. The method comprises the steps of performing digital reconstruction on acquired substation geographic data and equipment data to generate a three-dimensional terrain model; transformer substation unmanned aerial vehicle flight characteristic simulation is carried out by using the three-dimensional terrain model, and physical motion simulation analysis is carried out on unmanned aerial vehicle motion from unmanned aerial vehicle motion analysis, collision detection and unmanned aerial vehicle attitude calculation; and on the basis of the physical motion simulation analysis, unmanned aerial vehicle patrol route planning is carried out, an unmanned aerial vehicle flight route is generated, simulation flight is carried out, and transformer substation unmanned aerial vehicle flight analogue simulation is realized. According to the invention, the environment of the transformer substation is realistically restored through a high-precision three-dimensional modeling technology, real-time data return and display can be realized, and a highly real training platform is provided for operators; meanwhile, a built-in dynamic defect library supports flexible setting of common equipment defects, the diversity of training content is ensured, and full-scene simulation assessment helps operators to comprehensively improve the inspection ability of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle simulation, and in particular to a substation unmanned aerial vehicle flight simulation method and system. Background Art

[0002] With the continuous advancement of smart grid construction, the application of drone technology in the field of substation inspection is becoming more and more extensive. With its advantages of high efficiency, safety and flexibility, it has become an important supplement to traditional manual inspection. Drones can go deep into the substation, observe the equipment at close range, and find potential faults in time, which greatly improves the efficiency and quality of inspection. However, the existing substation drone inspection system still has some significant problems in practical application, especially in operator training. Due to the lack of effective training simulation tools, new operators often need a long period of actual operation to become familiar with the control skills of drones, which not only increases the training cost, but also increases the risk of accidents caused by improper operation. In addition, when facing complex equipment and special environments, operators may find it difficult to accurately identify and judge equipment defects due to lack of experience, which affects the effectiveness of inspection work.

[0003] Existing technologies are still lacking in the ability to restore high-precision three-dimensional scenes and simulate defects, which directly restricts the development of training simulation tools. On the one hand, the internal structure of the substation is complex and there are many types of equipment. It is not easy to achieve high-precision three-dimensional modeling. Existing modeling technologies often fail to achieve ideal results, especially in terms of detail presentation and dynamic change simulation. On the other hand, there are many types of equipment defects, ranging from slight rust to severe damage. The manifestation and degree of impact of each defect are different. Existing simulation technologies are difficult to fully and realistically reproduce these defects, resulting in a large difference between the experience gained by operators in the simulation environment and the actual situation, which affects the training effect.

[0004] Therefore, it is particularly important to develop a flight simulation method for substation drone inspection, which should be able to achieve high-precision 3D reconstruction of the internal and external environment of the substation, including various equipment and their layout, to ensure the high authenticity of the simulated environment. At the same time, it is also necessary to have a powerful defect simulation function that can simulate different types and degrees of equipment defects to provide operators with a rich variety of training cases. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a substation drone flight simulation method and system, which comprehensively simulates the substation drone inspection scene through three-dimensional modeling, drone real-time data feedback and defect identification functions. The system adopts the UE4 engine, which can truly reproduce the equipment structure and environment of the 110kV substation. At the same time, it has a built-in function of automatically generating inspection reports. Operators can conduct drone operation training and defect detection assessment through the simulation platform, further improving the drone inspection effect and efficiency.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] In the first aspect, the present invention provides a method for simulating substation UAV flight, including: digitally reconstructing the collected substation geographic data and equipment data to generate a three-dimensional terrain model; using the three-dimensional terrain model to simulate the flight characteristics of the substation UAV, and performing physical motion simulation analysis on the UAV motion from the perspective of UAV motion analysis, collision detection and UAV attitude calculation; based on the physical motion simulation analysis, performing UAV patrol track planning, generating a UAV flight route and performing simulated flight, thereby realizing simulation of substation UAV flight.

[0009] As a preferred solution of the substation UAV flight simulation method of the present invention, the digital reconstruction of the collected substation geographic data and equipment data to generate a three-dimensional terrain model includes:

[0010] The UAV laser radar is used to collect the original point cloud data of the precise geography and equipment of the substation, and the point cloud candidate points of different categories are marked by clustering method to separate the ground object point cloud from the non-ground object point cloud, and the original point cloud data is noise filtered and enhanced;

[0011] By analyzing the three-dimensional coordinates and morphological features of point cloud data, the direction of the terrain and the distribution of objects can be determined;

[0012] The selected point cloud data is used in combination with its spatial position to perform three-dimensional modeling of the power lines and the entire surface;

[0013] In three-dimensional terrain modeling, a three-dimensional terrain model is generated based on triangulation and Poisson reconstruction algorithm, and the three-dimensional terrain model is smoothed.

[0014] As a preferred solution of the substation UAV flight simulation method of the present invention, the substation UAV flight characteristics simulation includes:

[0015] Based on the three-dimensional terrain model, the Airsim+Pixhawk flight control semi-physical platform is used to simulate the flight characteristics, simulate the real physical state of the UAV flight, and use a real UAV remote control for control.

[0016] As a preferred solution of the substation UAV flight simulation method of the present invention, the UAV motion analysis is to perform physical motion simulation analysis on the UAV motion from the perspectives of UAV force analysis, UAV acceleration, and UAV speed, position, angular velocity and direction;

[0017] The UAV force analysis includes:

[0018] During the motion of the drone, the linear drag and angular velocity drag are important factors in changing its motion state. The direction of the linear drag is opposite to the velocity vector v.

[0019] Assuming that the partial angular velocity of the rigid surface ds is ω, ds is subject to two kinds of resistance torques, namely the friction torque, i.e. the torque generated by the tangential component of the velocity, and the torque generated by the shear stress. The linear resistance of ds is obtained according to the linear resistance equation, and the resistance torque of the drone surface is calculated by integration;

[0020] Then obtain the total force and torque F acting on the drone net for:

[0021] F net =∑ i F i +F d

[0022] Among them, F i is the thrust of the four vertices relative to the center of gravity of the drone, F d is the linear resistance;

[0023] The UAV acceleration includes: calculating the total linear acceleration and angular acceleration of the UAV according to the total force and torque acting on the UAV, synthesizing the calculated linear acceleration and angular acceleration and the gravity acceleration g, and obtaining the actual acceleration a of the UAV as:

[0024]

[0025] Among them, m represents the mass of the UAV;

[0026] The drone speed, position, angular velocity and direction include:

[0027] At time t+1, the speed V is updated by time integrating the speed at the previous time t. t+1 and position p t+1At time t+1, the angular velocity ω is updated by time-integrating the angular velocity at the previous time t t+1 ;

[0028] Calculate the angle axis pair (a dt ,u), where a dt is the angular velocity of rotation around the unit vector u, with the change in quaternion at time dt representing the change in direction.

[0029] As a preferred solution of the substation UAV flight simulation method of the present invention, the physical motion simulation analysis of the UAV motion from the perspective of collision detection includes:

[0030] In the collision detection system, each entity has a collision attribute, which determines whether the entity collides with other entities. If a collision or overlap event occurs during the rendering interval, the collision detection system calls the collision response, returns the collision position, collision type and input depth, calculates the returned data, and modifies the motion state of the drone according to the calculation results.

[0031] As a preferred solution of the substation UAV flight simulation method of the present invention, the physical motion simulation analysis of the UAV motion from the two aspects of UAV attitude estimation and attitude control includes:

[0032] Quaternions are used to save the attitude of the drone in the geographic coordinate system. When input into the drone control algorithm, they are converted into Euler angles. Pitch angle (θ), yaw angle (ψ), and roll angle (φ) are used to represent the attitude of the drone relative to the ground. The pitch angle represents the rotation of the drone around the x-axis, and the drone nose is facing up, which is positive; the yaw angle represents the rotation of the drone around the y-axis, and the drone nose is yawed to the right, which is positive; the roll angle represents the rotation of the drone around the z-axis, and the nose rolls to the right, which is positive;

[0033] The drone attitude estimation uses IMU sensor data and adopts Mahony complementary filter algorithm combined with PID feedback controller to compensate and correct gyroscope errors;

[0034] The attitude control of the UAV adopts a nested PI-PID controller to control the pitch angle, yaw angle and roll angle by adjusting the angular velocity of the propeller.

[0035] As a preferred solution of the substation UAV flight simulation method of the present invention, the UAV patrol track planning includes:

[0036] In the inspection area, the population individuals are transformed into track points, each track point is represented by its distance and direction angle;

[0037] pass Describes the path length of the track, where P i Indicates the track point, D(P i ,P i+1 ) represents the distance between two consecutive track points. Penalty design is performed by determining the safe distance from obstacles, and the smoothness of flight is measured by calculating the change in heading angle between consecutive track points.

[0038] The fitness function F is designed based on the track path length, obstacle avoidance performance and smoothness, which is expressed as:

[0039]

[0040] Among them, w i is the weight value of each reference, s represents the smoothness of flight, and p represents the obstacle avoidance of flight;

[0041] Assume that the point set that the drone needs to inspect is X = {X1, X2, ..., X n}, where X n Indicates inspection points. During the inspection process, the planning path visits all inspection points in sequence and returns to the starting point.

[0042] All inspection points are fully arranged (n-1)! , all inspection paths are listed by exhaustive method, the inspection process of each path and the total distance back to the origin are calculated, and the path with the shortest distance is selected as the optimal inspection path.

[0043] In a second aspect, the present invention provides a substation UAV flight simulation system, comprising:

[0044] A terrain model generation module is used to digitally reconstruct the collected substation geographic data and equipment data to generate a three-dimensional terrain model;

[0045] A simulation analysis module, used to simulate the flight characteristics of the substation UAV using the three-dimensional terrain model, and to perform physical motion simulation analysis on the UAV motion from the perspectives of UAV motion analysis, collision detection, and UAV attitude calculation;

[0046] The simulation flight module is used to plan the UAV patrol trajectory based on physical motion simulation analysis, generate the UAV flight route and perform simulated flight, so as to realize the simulation of substation UAV flight.

[0047] In a third aspect, the present invention provides an electronic device, comprising:

[0048] Memory and processor;

[0049] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the substation drone flight simulation method are implemented.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the substation UAV flight simulation method.

[0051] Compared with the prior art, the present invention has the following beneficial effects: the present invention provides a substation drone flight simulation method and system, which realistically restores the substation environment through high-precision three-dimensional modeling technology. The simulation system can realize real-time data feedback and display, providing operators with a highly realistic training platform; patrol reports can be automatically generated in the simulation environment, significantly improving patrol efficiency; at the same time, the built-in dynamic defect library supports flexible setting of common equipment defects and allows batch import / export, ensuring the diversity and pertinence of training content, and the full-scene simulation assessment helps operators comprehensively improve the drone inspection capabilities, ensuring that they can complete tasks efficiently and accurately in actual work. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0053] Figure 1 A schematic diagram of the overall process logic of a substation UAV flight simulation method according to an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of a geographic coordinate system and a body coordinate system of a substation UAV flight simulation method according to an embodiment of the present invention;

[0055] Figure 3 A schematic diagram of an electrical equipment model of a substation drone flight simulation method according to an embodiment of the present invention;

[0056] Figure 4 A schematic diagram of a three-dimensional scene of a substation UAV flight simulation method according to an embodiment of the present invention;

[0057] Figure 5 A schematic diagram of a drone inspection operation of a substation drone flight simulation method according to an embodiment of the present invention;

[0058] Figure 6 A schematic diagram of horizontal 8-character training of a substation UAV flight simulation method according to an embodiment of the present invention;

[0059] Figure 7 A schematic diagram of single-channel hovering training of a substation UAV flight simulation method according to an embodiment of the present invention;

[0060] Figure 8 A schematic diagram of dual-channel hovering training of a substation UAV flight simulation method according to an embodiment of the present invention;

[0061] Fig. 9 This is a schematic diagram of AOPA assessment of a substation UAV flight simulation method according to an embodiment of the present invention;

[0062] Fig.10 A schematic diagram of a substation inspection defect by a drone according to a substation drone flight simulation method described in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0064] Example 1

[0065] Reference Figure 1-Figure 10 As an embodiment of the present invention, a substation UAV flight simulation method is provided, such as Figure 1 The specific steps shown include:

[0066] S100: Digitally reconstructing the collected substation geographic data and equipment data to generate a three-dimensional terrain model;

[0067] S200: Use the 3D terrain model to simulate the flight characteristics of the substation UAV, and perform physical motion simulation analysis of the UAV motion from the perspectives of UAV motion analysis, collision detection, and UAV attitude calculation;

[0068] S300: Based on the physical motion simulation analysis, the UAV patrol trajectory is planned, the UAV flight route is generated and simulated flight is performed to realize the simulation of substation UAV flight.

[0069] It should be noted that the present invention provides a substation drone flight simulation method and system, which realistically restores the substation environment through high-precision three-dimensional modeling technology. The simulation system can realize real-time data feedback and display, providing operators with a highly realistic training platform; patrol reports can be automatically generated in the simulation environment, significantly improving patrol efficiency; at the same time, the built-in dynamic defect library supports flexible setting of common equipment defects and allows batch import / export, ensuring the diversity and pertinence of training content, and the full-scene simulation assessment helps operators to comprehensively improve the drone inspection capabilities, ensuring that they can complete tasks efficiently and accurately in actual work.

[0070] It should be noted that the precise geographic and equipment data of the substation collected in advance by the UAV LiDAR is digitally reconstructed using image processing tools (such as 3dsMax). Airborne LiDAR is to carry the LiDAR system to the flight platform, obtain the spatial information of the ground objects through laser scanning, and realize the rapid acquisition of high-density and high-precision three-dimensional spatial information of the ground objects. The series of data obtained by the LiDAR system is called "point cloud". The point cloud is a group of discrete points with spatial three-dimensional coordinate information. Based on the point cloud data, the three-dimensional model of the ground objects around the transmission line can be constructed. The processing of laser point cloud data includes point cloud classification, noise reduction filtering, target object extraction and three-dimensional model reconstruction.

[0071] In the embodiment of the present application, the above step S100 digitally reconstructs the collected substation geographic data and equipment data to generate a three-dimensional terrain model, including:

[0072] The UAV laser radar is used to collect the original point cloud data of the substation's precise geography and equipment, including all objects in the geographical environment, such as the ground surface, vegetation, buildings, roads, etc. The point cloud candidate points of different categories are marked by clustering method to separate the ground object point cloud from the non-ground object point cloud. The formula of the stratification threshold is:

[0073]

[0074] Among them, H max and H min are the maximum and minimum height values ​​in the point cloud data, respectively, and n is the number of layers, which is used to divide different types of objects;

[0075] Furthermore, geographic environment modeling must filter the point cloud for noise before data extraction. For power line extraction, the noise mainly comes from the clutter in the sky or the reflection on the ground. By filtering the noise, these irrelevant data can be excluded, thereby enhancing the clarity of the power line points. In geographic environment modeling, the noise mainly comes from the occlusion of ground objects or the error of the equipment. The noise can be processed by using a method similar to the moving least squares method (MLS):

[0076]

[0077] Among them, f(x i ,y i ) is the interpolation fitting surface, and p′ is the point after filtering;

[0078] Furthermore, by analyzing the three-dimensional coordinates and morphological features of the point cloud data, the direction of the terrain and the distribution of objects can be determined. Delaunay triangulation is a common method for processing such data. The surface can be refined and modeled through triangulation, especially for complex terrain (such as mountains, rivers, etc.):

[0079]

[0080] Furthermore, the selected point cloud data is combined with its spatial position to build a three-dimensional model of the power lines and the entire surface, and the point cloud is interpolated through the Voronoi diagram structure using the natural neighbor interpolation method:

[0081]

[0082] Among them, w i (P) is the weight of the interpolation point to its natural neighbors, z i is the height value of the known neighboring point.

[0083] Further, such as Figure 4 As shown in the 3D terrain modeling, a 3D terrain model is generated based on triangulation and Poisson reconstruction algorithm:

[0084]

[0085] Among them, Φ is the three-dimensional shape function generated by the point cloud, and V is the normal vector field;

[0086] Furthermore, the existing 3D model was optimized using 3DSMax software, mainly to reduce the roughness of the model surface, improve its visual effect and optimize the details. According to the line design drawings, 3DSMax software was used to complete the conventional typical tower modeling, and the details were restored 1:1, such as Figure 3 shown.

[0087] It should be noted that the above step S100 generates a three-dimensional terrain model by digitally reconstructing the collected substation geographic data and equipment data, which can provide a highly realistic and detailed environmental basis for the subsequent UAV flight characteristics simulation and trajectory planning, ensuring the accuracy and reliability of the simulation. At the same time, the construction of this three-dimensional model helps to fully understand and evaluate the actual situation of the substation, laying a solid foundation for the efficient and safe patrol operations of UAVs.

[0088] In the embodiment of the present application, the above step S200 includes the following sub-steps B1-B2;

[0089] In B1: Using 3D terrain model to simulate the flight characteristics of substation drones;

[0090] In B2: Physical motion simulation analysis of drone motion from drone motion analysis, collision detection and drone attitude calculation;

[0091] Specifically, the flight characteristics simulation of the substation drone in the above sub-step B1 includes using the Airsim+Pixhawk flight control semi-physical platform to simulate the flight characteristics based on the three-dimensional terrain model, simulating the real physical state of the drone flight, and using a real drone remote control for control.

[0092] It should be noted that the real drone size, CAD drawings, and prototype photos are used for real modeling, and a proportional three-dimensional model is made to restore the details of the drone. Mainstream models are supported, including Mavic 2, M210 RTK, Elf 4, M600, and M300. Based on the three-dimensional model, flight characteristics simulation is performed based on the AirSim platform. AirSim is a cross-platform simulator for drones and other automatic mobile devices built on UE4 (Unreal Engine 4). It supports the physical and visual realistic simulation of hardware in the flight controller. The simulator creates a highly restored realistic virtual environment, simulating environments that are easily disturbed in the real world such as shadows and reflections; this embodiment uses Airsim+Pixhawk flight control semi-physical flight characteristics simulation to simulate the real physical state of drone flight, and uses a real drone remote control for control, which is close to the operating feel of the real machine, and the flight control covers the currently commonly used four-rotor, six-rotor, and eight-rotor models.

[0093] It should be noted that the establishment of the drone model fully considers the force and motion analysis of the drone during movement. This embodiment selects a multi-rotor aircraft as the research and modeling object. The physical characteristics of the drone mainly involve parameters such as mass, linearity, inertia, friction coefficient, elasticity and angular resistance coefficient. These parameters are the basis for the force, motion analysis and attitude estimation of the drone. In Unreal Engine, the actuator is the source of force and torque on the drone. In order to simplify the calculation, the drone is abstracted as a cylinder with 4 vertices and a mass of m. The distance from each vertex to the center of mass is X. i , i = {1, 2, 3, 4}, the input angular velocity control signal is u i , i = {1,2,3,4}, the force and torque acting on the drone are:

[0094] F i =C T σω maxD 4 u i

[0095]

[0096] Among them, C T and C pow represents the thrust coefficient and power coefficient. These two coefficients are determined by the propeller material of the drone. σ is the air density, D is the propeller length, and ω max is the maximum angular speed of the propeller per minute;

[0097] In addition to the driving force of the drone itself, it will also be affected by various physical quantities during the movement. Gravity, air density, magnetic field, light, and visibility all have important effects on the movement of the drone, but in this module, only gravity, the earth's magnetic field, air pressure, and air density are modeled. Lighting and visibility will not have any force on the drone, so they will be set in the UE4 engine and are not part of the drone modeling;

[0098] ① Gravity

[0099] When the drone is flying at low altitude, the flying height of the drone is negligible relative to the radius of the earth, so the gravity acceleration of the drone is a constant value g when flying at low altitude. const =9.8m / s 2 When a drone flies at high altitude or at a high altitude (the flight altitude is specified to be one thousandth of the radius of the earth), the change in gravity caused by the drone's flight altitude cannot be ignored, and the gravity acceleration is:

[0100]

[0101] Among them, R e =6000km represents the radius of the earth, because In order to reduce the amount of calculation and eliminate the square term, an approximate calculation is performed on the quadratic term.

[0102] ②Magnetic field force

[0103] In real drones, the gyroscope and accelerometer alone cannot accurately calculate the drone's position, namely the yaw angle, pitch angle, and roll angle. Magnetometers are very important sensors on drones. They are used in the inertial navigation unit to determine the drone's heading vector and velocity vector relative to the earth together with accelerometers and gyroscopes. Therefore, magnetism is an important factor affecting drone flight. Because modeling the earth's magnetic field is a very complex task, only approximate values ​​of the magnetic field are used in the modeling. The magnetic field strength is determined by the longitude, latitude, and altitude of the drone's location.

[0104] Given longitude Latitude θ and altitude h, calculate the geomagnetic latitude θ m The formula is as follows. Where θ0 represents the latitude of the North Magnetic Pole in the real magnetic field, Indicates the longitude of the North Magnetic Pole.

[0105]

[0106] The total magnetic field strength |B| is calculated as follows: Where, represents the average value of the magnetic field at the magnetic equator on the surface of the earth.

[0107]

[0108] And obtain the values ​​of the horizontal, vertical, latitude and longitudinal components of the magnetic field vector respectively.

[0109] ③Air pressure and air density

[0110] Air pressure and density have a great influence on the lift and drag of the drone during movement. The air pressure and air density change significantly with the altitude, so it is very important to simulate the air pressure and air density. The pressure P and temperature T of the US standard atmospheric model at an altitude below 51km are calculated as shown in the following formula:

[0111]

[0112] The atmospheric pressure at sea level is P SL =1.033×10 4 kg / m 2 , atmospheric model pressure P and temperature T. At pressure P and temperature T, the air density calculation formula is:

[0113]

[0114] Specifically, in the above sub-step B2, physical motion simulation analysis is performed on the UAV motion from the UAV motion analysis, wherein the UAV motion analysis includes UAV force analysis, UAV acceleration, and UAV speed, position, angular velocity and direction;

[0115] Specifically, the UAV force analysis includes:

[0116] During the motion of the drone, the linear drag and angular velocity drag are important factors that change its motion state. The direction of the linear drag is opposite to the velocity vector v, and the calculation formula is:

[0117]

[0118] Among them, C lin is the linear air resistance coefficient, A is the cross-sectional area of ​​the drone, and σ is the air density;

[0119] The angle resistance arm is more complicated than the linear resistance arm. Assuming that the partial angular velocity of the rigid surface ds is ω, ds is subject to two kinds of resistance torques, namely the friction torque, which is the torque generated by the tangential component of the velocity, and the torque generated by the shear stress. Because the shear stress is an internal force on the drone and has nothing to do with the drone's motion, the friction torque is mainly analyzed. The linear velocity of ds is r ds ×ω, according to the linear resistance equation, the linear resistance of ds is:

[0120]

[0121] The direction of dF and r ds ×ωIn contrast, the drag torque on the drone surface is calculated by integration:

[0122] τ d =∫r ds ×dF

[0123] In addition to the drag and drag moment, the thrust F of the four vertices relative to the center of gravity of the drone i and thrust torque τ i It is also an important parameter for calculating the motion state of the drone, and then obtaining the total force and torque F acting on the drone. net for:

[0124] F net =∑ i F i +F d

[0125] Among them, F i is the thrust of the four vertices relative to the center of gravity of the drone, F d is the linear resistance;

[0126] Specifically, the analysis of drone acceleration includes:

[0127] The total linear acceleration and angular acceleration of the drone are calculated based on the total force and torque acting on the drone. The angular acceleration is given by the Euler rotation equation:

[0128] α=I -1 (τ net -(ω×(I·ω))

[0129] Where I is the inertia tensor;

[0130] According to Newton's second law, the linear acceleration can be calculated. The calculated linear acceleration is synthesized with the angular acceleration and the gravitational acceleration g, and the actual acceleration a of the drone is obtained as:

[0131]

[0132] Among them, m represents the mass of the UAV;

[0133] Specifically, the analysis of the drone’s speed, position, angular velocity, and direction includes:

[0134] At time t+1, the speed V is updated by time integrating the speed at the previous time t. t+1 and position p t+1 :

[0135] V t+1 =V t +dt·a t / 2

[0136] p t+1 =p t +dt·v t+1

[0137] At time t+1, the angular velocity ω is updated by time integrating the angular velocity at the previous time t t+1 :

[0138] ω t+1 =ω t +dt·a t / 2

[0139] The update of direction is different from the update of position. It is not a linear update. If the direction is updated with the rotation matrix each time, there will be a slow drift, and a lot of calculations are required to determine the real direction of the drone. The model converts the direction, that is, it uses quaternions to represent the rotation. Quaternions only need the rotation axis and the rotation angle to represent the rotation state. First, calculate the angle axis pair (a dt ,u), where a dt is the angular velocity of rotation around the unit vector u.

[0140] a t+1 =|ω·dt

[0141] u=ω / |ω

[0142] The change in direction is represented by the change in quaternion at time dt:

[0143] q t+1 =q t ·q dt

[0144] It should be noted that according to the force analysis of the UAV, the six parameters of the UAV's motion state can be obtained respectively, namely position, direction, linear velocity, linear acceleration, angular velocity and angular acceleration. Applying this physical model to the physics engine can present a motion state similar to that of a real UAV in the system.

[0145] Specifically, the physical motion simulation analysis of the UAV motion from the collision detection in the above sub-step B2 includes that each entity in the collision detection system has a collision attribute, and the collision attribute determines whether the entity collides with other entities. If a collision or overlap event occurs during the rendering interval, the collision detection system calls the collision response, returns the collision position, collision type and input depth, and calculates the returned data, and modifies the motion state of the UAV according to the calculation results.

[0146] It should be noted that the purpose of simulating the flight of drones is achieved by analyzing and calculating the flight status of drones. UnrealEngine provides a collision detection system for different types of collisions. The system is mainly composed of collision detection, collision response and trace response. During the rendering interval, if a collision or overlap event occurs, the Unreal Engine collision detection system will call the collision response, return the collision position, collision type and input depth, and calculate the returned data to modify the motion state of the drone according to the calculation results.

[0147] It should be noted that in Unreal Engine, each entity has a Collision property, which is used to determine whether the entity collides with other entities. There are three main collision properties: no collision (the entity will not collide with other entities), no physical collision (the entity can only be applied to ray casting, sweeping and overlapping), and enabled collision (the entity can be used for physical simulation and collision detection). Since the force is mutual, a collision will only occur if two or more colliding entities have the collision property. Otherwise, the entities will not collide, and the display effect is that the two entities overlap or pass through each other when moving.

[0148] It should be noted that in Unreal Engine, each entity with collision properties has its own channel type. Collisions between different entities are distinguished by collision channels. Commonly used collision object channels include WorldDynamic, Worldstatic, Pawn, character, etc. The WorldDynamic channel type is often used on "moving" objects, such as drones, birds and other movable entities; while the Worldstatic channel type is often used on "stationary" objects, such as the earth, trees and other stationary entities. Entities can use collision presets to set whether to collide with entities of other channel types. For example, if the entity channel is the ground with Worldstatic, the collision preset is BlockAll (collision with all objects), select the drone under its collision response list, then a collision will occur when the drone contacts the ground, and the drone's motion state will be changed according to the collision response, and the collision result will be returned.

[0149] Specifically, the physical motion simulation analysis of the UAV motion from the UAV attitude calculation in the above sub-step B2 includes analysis from two aspects: UAV attitude estimation and UAV attitude control;

[0150] It should be noted that quaternions are used to save the attitude of the drone in the geographic coordinate system. When input into the drone control algorithm, they are converted into Euler angles. The pitch angle (pitch, θ), yaw angle (yaw, ψ) and roll angle (roll, φ) are used to represent the attitude of the drone relative to the ground, such as Figure 2 As shown, the pitch angle indicates that the drone rotates around the x-axis, and the drone head is facing upward, which is positive; the yaw angle indicates that the drone rotates around the y-axis, and the drone head yaws to the right, which is positive; the roll angle indicates that the drone rotates around the z-axis, and the drone head rolls to the right, which is positive;

[0151] Specifically, the attitude estimation of the drone uses the IMU sensor data, the Mahony complementary filter algorithm combined with the PID feedback controller to compensate for the gyroscope error, and the quaternion is used to describe the attitude:

[0152] q=a+bi+cj+dk

[0153] Among them, a, b, c, d are real numbers, i, j, k are mutually orthogonal unit vectors. The initialization quaternion is:

[0154] q0=1,q1=0,q2=0,q3=0

[0155] Normalize the acceleration data to obtain the angular velocity ω of the three axes of the sensor x ,ω y ,ω z Acceleration x ,a y ,a z , normalize the acceleration:

[0156]

[0157] Perform error vector calculation based on accelerometer and gyroscope data and calculate the error through vector product:

[0158] e=a norm ×g

[0159] Where g is the geographic gravity vector converted to the body coordinate system.

[0160] Update the quaternion using the processed gyroscope data:

[0161]

[0162] Among them, h T=0.001 is the time step, Ω is the angular velocity matrix.

[0163] Specifically, the attitude control of the UAV adopts a nested PI-PID controller to control the pitch angle, yaw angle and roll angle by adjusting the angular velocity of the propeller. The state equation of the UAV can be expressed as:

[0164]

[0165]

[0166] Among them, θ is the pitch angle, ψ is the yaw angle, φ is the roll angle, τ θ ,τ ψ ,τ φ is the corresponding moment, and u is the thrust.

[0167] The PID controller is responsible for the smooth control of the drone's attitude. It is used to adjust the speed of attitude angle change and adjust the system gain by comparing the filtered attitude angle with the expected angle.

[0168] Furthermore, the drone is running in a simulated training environment. Without real sensors, it is impossible to obtain the drone's flight status data. Therefore, the sensor must be modeled in the simulated environment to obtain the flight status and data in the simulated training environment.

[0169] The sensor module mainly includes five parts: GPS, barometer, magnetometer, accelerometer and gyroscope. Since there are certain errors in the sensor data collected in actual training, in order to make the sensor data closer to the actual situation, in addition to modeling the sensor data collected, the sensor error was simulated during the modeling process.

[0170] GPS: Provides location data and adds horizontal and vertical errors to the simulation.

[0171] Barometer: measures atmospheric pressure based on the Torricelli principle and converts it into altitude.

[0172] Magnetometer: measures magnetic field components for attitude calculation.

[0173] Accelerometer and gyroscope: IMU core components, responsible for calculating the linear acceleration and angular velocity of the drone, and the output is used for attitude estimation.

[0174] GPS error simulation is mainly used in horizontal error and vertical error, and the error gradually decreases over time.

[0175] The barometer simulates the relationship between air pressure and altitude. The air pressure value changes with altitude. The calculation formula is:

[0176]

[0177] Among them, p0, L, h, T0, g, and R are the standard air pressure at sea level, temperature gradient, altitude, reference temperature, gravitational acceleration, and gas constant, respectively.

[0178] Furthermore, the system supports multiple deployment methods and can be run on Windows systems:

[0179] Support video streaming deployment: Use UE pixel streaming technology to deploy on the teacher's computer (high-performance computer), execute system logic and render each frame of the picture, support the teaching method of teacher computer operation and student computer observation and learning.

[0180] Support independent deployment: Support independent deployment of teacher machines and students through independent deployment, and can run without third-party support.

[0181] It should be noted that the above step S200 can not only predict and avoid potential flight risks in advance, but also optimize the flight path and operation strategy of the UAV, ensure the flight safety and operation efficiency of the UAV in complex environments, and through precise physical simulation analysis, it can effectively reduce the number of field tests, save costs and speed up the development and deployment of the UAV patrol system.

[0182] In the embodiment of the present application, the above step S300 performs drone patrol track planning based on physical motion simulation analysis, generates drone flight routes and performs simulated flight, and realizes the simulation of substation drone flight, including:

[0183] Due to the high voltage level and many live equipment in substations, the live working electric field environment is more complex than that of conventional transmission lines. Therefore, the substation drone simulation inspection module is developed according to the real substation drone simulation inspection standard. The autonomous inspection of drones needs to set the flight area of ​​the substation according to the voltage level first, and then conduct flight inspections of the substation structure, lightning rods, HGIS equipment, etc. in sequence. Each area is set with safe take-off and landing positions to clarify the flight route. During the flight of the UAV, it should avoid flying beyond its performance indicators. The flight speed during inspection should not be greater than 10m / s. It should avoid flying over densely populated areas such as the low-voltage side of the main transformer. When it is really necessary to cross the lead, the upper crossing method should be adopted. The clearance distance from the topmost lead should be not less than 10m, and it should not hover directly above the electrical equipment for a long time. The main purpose is to combine the UAV flight parameters, camera parameters, three-dimensional terrain data, and tower coordinate data to calculate the track point coordinates, aircraft attitude and gimbal angle, etc., provide single-point, single-device, and global track point corrections at all levels, have spatial collision detection and automatic avoidance capabilities, provide standard, open format route file output, and provide strategic guidance for real flight.

[0184] Specifically, Figure 5As shown in the figure, the population individuals are transformed into track points in the inspection area, and each track point is represented by its distance and direction angle:

[0185] Chromosome={(r1,θ1),(r2,θ2),...,(r n ,θ n )}

[0186] Among them, r i is the distance of the current track point relative to the reference point, θ i It is the polar angle relative to the reference point. Polar coordinate system encoding has unique advantages in dealing with angle changes and rotation problems in trajectory planning. When a drone is flying around an obstacle, the trajectory direction can be easily changed by adjusting the angle θ to avoid the obstacle.

[0187] The design of the fitness function should comprehensively consider various factors in the UAV trajectory planning to ensure that the path meets the mission requirements while optimizing the goal as much as possible. Combined with the planning mission requirements, the fitness function is designed by comprehensively considering the path length, obstacle avoidance performance and smoothness. Describes the path length of the track, where P i Indicates the track point, D(P i ,P i+1 ) represents the distance between two consecutive track points. Penalty design is performed by determining the safe distance from obstacles, and the smoothness of flight is measured by calculating the change in heading angle between consecutive track points.

[0188] It should be noted that the penalty design formula is expressed as:

[0189]

[0190] It should be noted that when the track changes frequently, the fitness value is low. Among them, θ i Represents the direction angle of the i-th track point.

[0191] The fitness function F is designed based on the comprehensive track path length, obstacle avoidance performance and smoothness, which is expressed as:

[0192]

[0193] Among them, w i is the weight value of each reference, s represents the smoothness of flight, and p represents the obstacle avoidance of flight;

[0194] Furthermore, suppose that the point set that the drone needs to inspect is X = {X1,X2,…,X n}, where X n Represents the inspection point. The inspection process plans the path to visit all inspection points in turn and return to the starting point. Calculate the X of the two inspection pointsi ,X j The Euclidean distance between them is:

[0195]

[0196] where x i ,y i Indicates inspection point X i coordinate.

[0197] All inspection points are fully arranged (n-1)! , all inspection paths are listed by exhaustive method, and the inspection process of each path and the total distance D back to the origin are calculated. Xi =d 12 +d 23 ,...,d n1 , select the path with the shortest distance as the optimal inspection path.

[0198] After generating the route, you can set the flight altitude, flight speed, flight distance, gimbal angle and other parameters of the drone route in the simulation scene, and perform simulated flight in the scene according to the planned route to ensure the accuracy of the planned route.

[0199] It should be noted that the above step S300 can not only ensure the safety and rationality of the flight route, discover and resolve potential flight obstacles and risks in advance, but also optimize the flight path and improve patrol efficiency and quality. At the same time, the operation process of the UAV can be rehearsed through simulated flight, which helps operators become familiar with flight missions, reduces errors and uncertainties in actual operations, and comprehensively improves the safety and reliability of UAV patrol operations.

[0200] In addition, this embodiment also includes basic UAV flight skills training, which must cover the basic knowledge of UAV control, flight skills, laws and regulations, safe operation and application practice. Design AOPA flight skills such as UAV takeoff, landing, hovering, figure 8 flight, and four-sided route. Meet the training needs of students from basic flight skills training, advanced flight skills training and AOPA test training. Students can complete learning and training on the job, improve training efficiency and greatly reduce the loss of bombing caused by training errors.

[0201] like Figure 6 Figure 8 flight is a complex maneuver that requires precise control of the drone's speed, direction, and turning angle. This flight mode requires the drone to turn continuously, forming two intersecting arcs, and the overall path looks like the number "8".

[0202] like Figure 7The display shows single-channel hovering: GPS flight mode / attitude stabilization mode, with switchable pitch, aileron, and single-channel four-sided hovering (supports one-key switching of tail-to-tail flight training, head-to-head flight training, left-side flight training, and right-side flight training).

[0203] like Figure 8 The display shows dual-channel hovering: GPS flight mode / attitude stabilization mode, with switchable pitch, aileron, and dual-channel four-sided hovering (supports one-key switching of tail-to-tail flight training, head-to-head flight training, left-side flight training, and right-side flight training).

[0204] like Fig. 9 The display shows AOPA: it has AOPA flight skills such as drone take-off, landing, hovering, figure-8 flight, and four-side route. It supports the display and hiding of flight training tracks and can be cleared with one click. It has and supports the display of training results such as flight training time and number of successes.

[0205] This embodiment also includes the function of realizing the intelligent inspection and defect identification of substation equipment by drones, such as Fig.10 The operator controls the simulated drone to identify various equipment defects in the substation through cameras and sensors, and completes the substation drone inspection equipment defect training. At the same time, the drone is equipped with infrared, visible light and other detection equipment to shoot equipment inspection images, and the defects of the equipment are identified using the defect image recognition model. The detected defects are classified using the deep learning algorithm. The system automatically generates an inspection report based on the inspection results, and generates a new training model and plan, which supports the operator to manually select the defect mode for training. The built-in dynamic defect library already contains common defects in power line inspection, including bird nests, insulator self-explosion, foreign objects in pole towers, rust on pole towers, phase sequence plate tilt, phase sequence plate fall-off, serious contamination of insulators, hanging floating objects, pin fall-off, voltage equalizing ring tilt, shockproof hammer displacement, shockproof hammer fall-off, shockproof hammer deformation, bolt loosening and other common defects in transmission lines, as well as substation structure, lightning rod, busbar, lead wire and other high-altitude equipment fixing bolt connection loosening, fall-off and breakage. Common defects in substations can appear randomly during inspections, giving operators a real power line inspection scene.

[0206] From the above, it can be seen that the present invention provides a substation drone flight simulation method and system, which realistically restores the substation environment through high-precision three-dimensional modeling technology. The simulation system can realize real-time data feedback and display, providing operators with a highly realistic training platform; patrol reports can be automatically generated in the simulation environment, significantly improving patrol efficiency; at the same time, the built-in dynamic defect library supports flexible setting of common equipment defects and allows batch import / export, ensuring the diversity and pertinence of training content, and the full-scene simulation assessment helps operators to comprehensively improve the drone inspection capabilities and ensure that they can complete tasks efficiently and accurately in actual work.

[0207] Example 2

[0208] This embodiment provides a substation drone flight simulation system, including:

[0209] A terrain model generation module is used to digitally reconstruct the collected substation geographic data and equipment data to generate a three-dimensional terrain model;

[0210] The simulation analysis module is used to simulate the flight characteristics of substation UAVs using a three-dimensional terrain model, and to perform physical motion simulation analysis of UAV motion from the perspectives of UAV motion analysis, collision detection, and UAV attitude calculation;

[0211] The simulation flight module is used to plan the UAV patrol trajectory based on physical motion simulation analysis, generate the UAV flight route and perform simulated flight, so as to realize the simulation of substation UAV flight.

[0212] It should be noted that the technical solution of the substation drone flight simulation system and the technical solution of the above-mentioned substation drone flight simulation method belong to the same concept. For the details not described in detail in the technical solution of the substation drone flight simulation system in this embodiment, please refer to the description of the technical solution of the above-mentioned substation drone flight simulation method.

[0213] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0214] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a substation drone flight simulation method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0215] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0216] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0217] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention 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 a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0218] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0219] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0220] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0221] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0222] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0223] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0224] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A substation drone flight simulation method, characterized in that: include: Digitally reconstruct the collected substation geographic data and equipment data to generate a three-dimensional terrain model; The three-dimensional terrain model is used to simulate the flight characteristics of the substation UAV, and the physical motion simulation analysis of the UAV motion is performed from the perspective of UAV motion analysis, collision detection and UAV attitude calculation; Based on the physical motion simulation analysis, the UAV patrol track planning is carried out, the UAV flight route is generated and the simulated flight is carried out to realize the simulation of the substation UAV flight.

2. The substation UAV flight simulation method according to claim 1, characterized in that: The digital reconstruction of the collected substation geographic data and equipment data to generate a three-dimensional terrain model includes: The UAV laser radar is used to collect the original point cloud data of the precise geography and equipment of the substation, and the point cloud candidate points of different categories are marked by clustering method to separate the ground object point cloud from the non-ground object point cloud, and the original point cloud data is noise filtered and enhanced; By analyzing the three-dimensional coordinates and morphological features of point cloud data, the direction of the terrain and the distribution of objects can be determined; The selected point cloud data is used in combination with its spatial position to perform three-dimensional modeling of the power lines and the entire surface; In three-dimensional terrain modeling, a three-dimensional terrain model is generated based on triangulation and Poisson reconstruction algorithm, and the three-dimensional terrain model is smoothed.

3. The substation UAV flight simulation method according to claim 2, characterized in that: The substation UAV flight characteristics simulation includes: Based on the three-dimensional terrain model, the Airsim+Pixhawk flight control semi-physical platform is used to simulate the flight characteristics, simulate the real physical state of the UAV flight, and use a real UAV remote control for control.

4. The substation UAV flight simulation method according to claim 3 is characterized in that: The UAV motion analysis is to conduct physical motion simulation analysis of the UAV motion from the perspective of UAV force analysis, UAV acceleration, and UAV speed, position, angular velocity and direction; The UAV force analysis includes: During the motion of the drone, the linear drag and angular velocity drag are important factors in changing its motion state. The direction of the linear drag is opposite to the velocity vector v. Assuming that the partial angular velocity of the rigid surface ds is ω, ds is subject to two kinds of resistance torques, namely the friction torque, i.e. the torque generated by the tangential component of the velocity, and the torque generated by the shear stress. The linear resistance of ds is obtained according to the linear resistance equation, and the resistance torque of the drone surface is calculated by integration; Then obtain the total force and torque F acting on the drone net for: F net =∑ i F i +F d Among them, F i is the thrust of the four vertices relative to the center of gravity of the drone, F d is the linear resistance; The UAV acceleration includes: calculating the total linear acceleration and angular acceleration of the UAV according to the total force and torque acting on the UAV, synthesizing the calculated linear acceleration and angular acceleration and the gravity acceleration g, and obtaining the actual acceleration a of the UAV as: Among them, m represents the mass of the UAV; The drone speed, position, angular velocity and direction include: At time t+1, the speed V is updated by time integrating the speed at the previous time t. t+1 and position p t+1 At time t+1, the angular velocity ω is updated by time-integrating the angular velocity at the previous time t t+1 ; Calculate the angle axis pair (a dt ,u), where a dt is the angular velocity of rotation around the unit vector u, with the change in quaternion at time dt representing the change in direction.

5. The substation UAV flight simulation method according to claim 4, characterized in that: Physical motion simulation analysis of drone motion from the perspective of collision detection includes: In the collision detection system, each entity has a collision attribute, which determines whether the entity collides with other entities. If a collision or overlap event occurs during the rendering interval, the collision detection system calls the collision response, returns the collision position, collision type and input depth, calculates the returned data, and modifies the motion state of the drone according to the calculation results.

6. The substation UAV flight simulation method according to claim 5, characterized in that: Physical motion simulation analysis of UAV motion from two aspects: UAV attitude estimation and attitude control. Quaternions are used to save the attitude of the drone in the geographic coordinate system. When input into the drone control algorithm, they are converted into Euler angles. Pitch angle (θ), yaw angle (ψ), and roll angle (φ) are used to represent the attitude of the drone relative to the ground. The pitch angle represents the rotation of the drone around the x-axis, and the drone nose is facing up, which is positive; the yaw angle represents the rotation of the drone around the y-axis, and the drone nose is yawed to the right, which is positive; the roll angle represents the rotation of the drone around the z-axis, and the nose rolls to the right, which is positive; The drone attitude estimation uses IMU sensor data and adopts Mahony complementary filter algorithm combined with PID feedback controller to compensate and correct gyroscope errors; The attitude control of the UAV adopts a nested PI-PID controller to control the pitch angle, yaw angle and roll angle by adjusting the angular velocity of the propeller.

7. The substation UAV flight simulation method according to claim 6, characterized in that: The UAV patrol track planning includes: In the inspection area, the population individuals are transformed into track points, each track point is represented by its distance and direction angle; pass Describes the path length of the track, where P i Indicates the track point, D(P i ,P i+1 ) represents the distance between two consecutive track points. Penalty design is performed by determining the safe distance from obstacles, and the smoothness of flight is measured by calculating the change in heading angle between consecutive track points. The fitness function F is designed based on the track path length, obstacle avoidance performance and smoothness, which is expressed as: Among them, w i is the weight value of each reference, s represents the smoothness of flight, and p represents the obstacle avoidance of flight; Assume that the point set that the drone needs to inspect is X = {X1, X2, ..., X n }, where X n Indicates inspection points. During the inspection process, the planning path visits all inspection points in sequence and returns to the starting point. All inspection points are fully arranged (n-1)! , all inspection paths are listed by exhaustive method, the inspection process of each path and the total distance back to the origin are calculated, and the path with the shortest distance is selected as the optimal inspection path.

8. A system using the substation UAV flight simulation method according to any one of claims 1 to 7, characterized in that: include: A terrain model generation module is used to digitally reconstruct the collected substation geographic data and equipment data to generate a three-dimensional terrain model; A simulation analysis module, used to simulate the flight characteristics of the substation UAV using the three-dimensional terrain model, and to perform physical motion simulation analysis on the UAV motion from the perspectives of UAV motion analysis, collision detection, and UAV attitude calculation; The simulation flight module is used to plan the UAV patrol trajectory based on physical motion simulation analysis, generate the UAV flight route and perform simulated flight, so as to realize the simulation of substation UAV flight.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the substation drone flight simulation method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the substation UAV flight simulation method according to any one of claims 1 to 7.

Images