A path constraint based unmanned aerial vehicle flight control method

Abstract

The application discloses a kind of based on path constraint's unmanned plane flight control method, belong to unmanned plane inspection technical field, comprising: obtaining inspection task and initial flight path;Monitoring flight environment and task state;According to the data of monitoring, dynamically adjust flight path;Generate the emergency flight path that conforms to current flight environment and task state;Control unmanned plane according to emergency flight path flight, and continue monitoring flight environment and task state when flight;Complete inspection task and return;The based on path constraint's unmanned plane flight control method, through real-time monitoring flight environment and task state, and dynamically adjust flight path, unmanned plane can respond rapidly under emergency, ensure the smooth progress of inspection task, improve emergency response capability.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of unmanned aerial vehicle inspection, and particularly relates to an unmanned aerial vehicle flight control method based on path constraints. BACKGROUND

[0002] In recent years, unmanned aerial vehicle inspection line technology has been widely used in the power industry, mainly due to the rapid development of aviation, remote sensing, and information processing technologies. Unmanned aerial vehicle inspection has the advantages of flexible mode and low cost, and can find defects that manual inspection cannot find, becoming one of the key directions of line inspection technology development.

[0003] Existing unmanned aerial vehicle inspection systems often rely on preset flight paths for automatic inspection, but in actual inspection processes, unexpected situations may occur, such as weather changes, equipment failures, emergency task changes, etc., requiring the unmanned aerial vehicle to quickly adjust the flight path to ensure the smooth completion of the inspection task.

[0004] Defects and deficiencies of the prior art:

[0005] 1. Unmanned aerial vehicle response is not timely: traditional unmanned aerial vehicle inspection path planning methods often respond too slowly when facing these unexpected situations, and it is difficult to fully consider various constraints, resulting in decreased inspection efficiency or even task failure;

[0006] 2. Affected by the environment: in the case of sudden severe weather conditions such as strong winds and heavy rain, the flight performance and stability of the unmanned aerial vehicle will be greatly affected, and it may even be unable to fly normally;

[0007] 3. Lack of intelligence: unmanned aerial vehicle autonomous inspection is still in the early stages of development, and the entire product system needs to be continuously improved; therefore, a new unmanned aerial vehicle flight control method based on path constraints is needed to solve existing problems. SUMMARY

[0008] The purpose of the present application is to provide an unmanned aerial vehicle flight control method based on path constraints to solve the problem of being unable to dynamically adjust the flight path during inspection.

[0009] To achieve the above purpose, the present application provides the following technical solution: an unmanned aerial vehicle flight control method based on path constraints, comprising:

[0010] Obtaining an inspection task and an initial flight path;

[0011] Monitoring the flight environment and task status;

[0012] According to the monitored data, dynamically adjusting the flight path;

[0013] Generating an emergency flight path that conforms to the current flight environment and task status;

[0014] controlling the UAV to fly along the emergency flight path and continuously monitoring the flight environment and the task status during the flight;

[0015] completing the inspection task and returning.

[0016] Preferably, the initial flight path is pre-planned according to the terrain of the inspection area and the tower position.

[0017] Preferably, the flight environment includes wind speed, wind direction and visibility.

[0018] The task status includes remaining power and device health.

[0019] Preferably, the dynamic adjustment of the flight path includes dynamic adjustment of the flight path by a path constraint algorithm; the constraint conditions of the path constraint algorithm include:

[0020] environmental constraints: the actual flight speed V of the UAV actual The calculation formula is: wherein V actual represents the actual flight speed of the UAV, V uav represents the windless flight speed of the UAV, V wind represents the wind speed of the UAV, and θ represents the angle between the wind direction and the flight direction of the UAV; the calculation formula of the flight time T is as follows: wherein L represents the path length.

[0021] Wind direction constraint: set the maximum allowed offset angle θ_max, if the angle θ is greater than the maximum allowed offset angle θ_max, the path is not feasible; wherein if the wind direction is opposite to the flight direction, the angle θ is 180°.

[0022] Visibility constraint: set the minimum allowed visibility V min , if the visibility of any point on the flight path is lower than the minimum allowed visibility V min , the path is not feasible.

[0023] Task constraint: including coverage of inspection points and inspection sequence.

[0024] Flight performance constraint: including maximum speed, maximum climb, maximum dive angle and minimum turning radius of the UAV.

[0025] Power constraint: ensuring sufficient power of the UAV during the inspection.

[0026] Preferably, the processing method of the task constraint includes:

[0027] Path encoding: sorting and marking the key points on the inspection path to form an ordered encoding sequence.

[0028] Discretize the inspection area into a grid map, each grid represents a possible inspection point;

[0029] Encode the flight path of the UAV as a sequence of grid points, each grid point corresponds to a position on the path;

[0030] Randomly generate a preset number of path encodings as the initial population, each encoding represents a possible flight path;

[0031] Evaluate the fitness of each path encoding in the population according to the length, safety and inspection efficiency of the flight path;

[0032] Iteratively optimize the population through selection, crossover and mutation operations in genetic algorithms to generate new path encodings;

[0033] When the preset number of iterations is reached or the fitness meets the set conditions, terminate the algorithm and output the optimal or near-optimal flight path encoding;

[0034] Encode the flight path of the UAV into a chromosome in genetic algorithms, a flight path scheme is a chromosome;

[0035] Evaluate the fitness of each flight path in the population to evaluate its pros and cons;

[0036] The selection method of genetic algorithm includes: according to the fitness function of genetic algorithm to evaluate the pros and cons of each path, using roulette selection or tournament selection method, selecting paths with high fitness from the current population as parents to increase the chance of their genetic to the next generation;

[0037] The crossover method of genetic algorithm is: crossover operation on the selected parent path, including single-point crossover or two-point crossover, generating new path scheme by exchanging path segments;

[0038] The mutation method of genetic algorithm includes: randomly changing the set path, including changing one or more node positions on the path;

[0039] The fitness function of the genetic algorithm includes: reward for coverage rate of inspection points or punishment for uncovered inspection points, combine multiple constraint conditions into a single evaluation index by weighted summation to get the total fitness value;

[0040] Fitness = ω1*coverage reward + ω2*uncovered punishment + ω3*other constraint condition 1 +... + ω n *other constraint condition n;

[0041] Where ω1, ω2,..., ω n are the weights of each constraint condition;

[0042] Wherein: coverage reward = actual covered inspection point number / target covered inspection point number;

[0043] Uncovered penalty = uncovered inspection point number * penalty coefficient;

[0044] Fitness = ω1*(actual covered inspection point number / target covered inspection point number) + ω2*(uncovered inspection point number * penalty coefficient) + ω3*other constraint 1 +... + ωn*other constraint n. n

[0045] Preferably, the flight performance constraint includes: the flight performance constraint includes the maximum speed, the maximum climb, the maximum dive angle, the minimum turning radius, etc. of the unmanned aerial vehicle, and in the genetic algorithm, the flight performance constraint can be processed by the following method:

[0046] Path smoothing processing: Clothoid curve is used to smooth the path, and after the path is generated, smoothing processing is performed to make the path meet the minimum turning radius requirement of the unmanned aerial vehicle; the genetic algorithm and the path smoothing processing are complementary to each other, the genetic algorithm searches for the optimal path segment combination, and the Clothoid curve performs path smoothing processing, so that the optimal and smooth path can be found in the complex environment;

[0047] The Clothoid curve is approximated by the following formula:

[0048]

[0049] Wherein: X and Y represent the horizontal coordinate and vertical coordinate of the point on the curve, A is a proportional constant, and t is the arc length from the starting point of the curve to the current point;

[0050] Path smoothing processing fitness function limit:

[0051] The path smoothing processing fitness function gives a penalty when the maximum slope and the maximum speed change exceed the limit;

[0052] The flight state adaptability calculation formula is F(h, v) = αh + βv, wherein F represents the path smoothing processing fitness function, h represents the flight height, v represents the flight speed, and α and β represent the weight coefficients, which are used to adjust the importance of the height and the speed in the path smoothing processing fitness function.

[0053] Preferably, the power constraint includes:

[0054] Power model: a power consumption model of the unmanned aerial vehicle is established, and the influence of flight speed, flight height, and load factor on power is considered;

[0055] ​The power consumption model structure of the UAV is mainly based on the Thevenin model;

[0056] Thevenin model is a model composed of a voltage source (Thevenin voltage, V TH ) and a series resistor (Thevenin resistance, R TH ), which can be equivalent to replace a complex circuit network; Thevenin model formula can be expressed as:

[0057] V TH =V OC ;

[0058] R TH =R int ;

[0059] V out =V TH -I out *R TH ;

[0060] P=V out *I out ;

[0061] Among them:

[0062] V TH is the Thevenin voltage, equal to the open circuit voltage of the circuit network, that is, the voltage when the two ends are open circuit;

[0063] V OC is the open circuit voltage, that is, the voltage of the circuit network without load;

[0064] R TH is the Thevenin resistance, equal to the input resistance of the circuit network, that is, the internal resistance of the circuit network, when all independent power sources are removed or set to zero, the resistance from the port into the circuit network;

[0065] R int is the internal resistance, that is, the internal resistance of the circuit network;

[0066] V out is the output voltage, that is, the voltage on the load R L ;

[0067] I out is the output current, that is, the current flowing through the load R L ;

[0068] P is the power consumed by the UAV in flight;

[0069] Path evaluation: when evaluating the path, the length of the path is calculated, and the amount of electricity required to complete the length of the path is calculated according to the electricity model, and it is judged whether it is within the electricity limit of the unmanned aerial vehicle, and the path exceeding the electricity limit is given a lower fitness value.

[0070] Preferably, the monitored data includes: obtaining real-time inspection scene information: including inspection line information and inspection weather information;

[0071] The inspection line information includes: line grade, tower and conductor type number of branches;

[0072] The inspection weather information includes: coordinate information, altitude, temperature, wind speed, wind direction and atmospheric pressure;

[0073] A weighted multi-objective optimization function is established, and the position, velocity, acceleration and time distribution of the discrete path points are optimized in combination with flight smoothness, dynamic characteristics and flight time performance indicators; wherein the discrete path points are isolated point sets and path discontinuous points;

[0074] Flight smoothness: the curvature of the trajectory and the rate of change of acceleration are used to quantify the flight smoothness; the curvature of the trajectory can reflect the bending degree of the flight trajectory. For a given flight trajectory, the smoothness is measured by calculating the curvature of each point on the trajectory; the calculation of the trajectory curvature uses the derivative of the trajectory coordinates, for a plane curve, the curvature K is defined as the rate of change of the unit tangent vector with respect to the arc length, and its calculation formula is:

[0075] Wherein: K represents the curvature;

[0076] And Respectively represent the velocity of the curve in the X and Y directions, that is, the first derivative;

[0077] And Respectively represent the acceleration of the curve in the X and Y directions, that is, the second derivative;

[0078] Acceleration rate: the rate of change of acceleration, also known as jerk, is a measure of the rate of change of acceleration with respect to time, and the jerk is the time derivative of acceleration, and its calculation formula is:

[0079] Where d represents the differential operator, which means taking the derivative of a certain physical quantity, a represents acceleration, and t represents time;

[0080] For two-dimensional or three-dimensional motion, the jerk is a vector, and each component is the vector sum of the rate of change of acceleration in the corresponding direction: Where is the acceleration vector;

[0081] If the acceleration vector is represented by its components in the x, y, and z directions, then the jerk vector The components of the jerk vector

[0082] Constructing the performance index function: A performance index function J 平滑性 can be constructed as a weighted sum of the curvature K function and the jerk J function, J

[0083] J 平滑性 is the weighted sum of the curvature K function and the jerk J function, J 平滑性 = ω k · K + ω K · J J where J J is the term based on the curvature K, J K is the term based on the jerk J, ω J and ω k are the corresponding weight coefficients to balance the importance of the two indices in the performance index function; J

[0084] Dynamic characteristics: including the flight mechanics behavior of the UAV, lift, drag, stability, and maneuverability;

[0085] Lift: The lift performance index function is represented as:

[0086]

[0087] where Cl represents the lift coefficient, Cl_max represents the maximum lift coefficient, dCl / dα represents the lift curve slope, α0 represents the zero-lift angle of attack, Induced Drag represents the induced drag, ω Cl , ω Cl_max , ω dCl / dα , ω Induced Drag are weight factors;

[0088] The lift coefficient Cl is calculated by the formula where L is the actual lift, ρ is the air density, V is the flight speed, and S is the wing area;

[0089] Drag: The drag performance index function is represented as:

[0090] J D = ω Cd · Cd-ω DragatZero Lift · Drag at Zero Lift+ω Induced ​Drag • Induced Drag + ω Wave Drag • Wave Drag - ω Parasite Drag • Parasite Drag

[0091] wherein: ω Cd , ω Drag at Zero Lift , ω Induced Drag , ω Wave Drag , ω Parasite Drag are weight factors; Cd represents the drag coefficient, Drag at Zero Lift represents the zero-lift drag, Induced Drag represents the induced drag, Wave Drag represents the wave drag, Parasite Drag represents the parasite drag, and Total Drag represents the total drag;

[0092] Stability: the stability performance index function includes two aspects of static stability and dynamic stability; the stability performance index function is represented as:

[0093] J s = ω static • S static + ω dynamic • S dynamic

[0094] wherein:

[0095] ω static , ω dynamic are weight factors;

[0096] S static represents the static stability index, which is evaluated by the position relationship between the center of gravity and the center of lift, and the basic evaluation formula of the static stability is: wherein:

[0097] is the rate of change of the lift coefficient Cl with the angle of attack a;

[0098] is the rate of change of the pitching moment coefficient Cm with the angle of attack a;

[0099] The pitching moment coefficient itself is represented as:

[0100] Cm 0 is the pitching moment coefficient at zero angle of attack;

[0101] Cm α α represents the rate of change of the pitching moment coefficient caused by the change of the angle of attack;

[0102] Cm q α represents the rate of change of the pitching moment coefficient caused by the change of the pitch rate;

[0103] α represents the rate of change of the pitching moment coefficient caused by the change of the elevator deflection angle;

[0104] α represents the angle of attack;

[0105] q represents the pitch rate;

[0106] δ e α represents the elevator deflection angle;

[0107] S dynamic α represents the dynamic stability index, which is determined by analyzing the dynamic characteristics of the aircraft; damping ratio and natural frequency ω n are the key parameters for determining the dynamic stability of the system. According to the characteristic value S, the dynamic stability of the system is determined,

[0108] If represents over-damping, the characteristic values are all negative real numbers, and the system is dynamically stable;

[0109] If represents critical damping, the characteristic values are a pair of negative real numbers, and the system is dynamically stable, but the response speed is slower;

[0110] If represents under-damping, the characteristic values are complex conjugate roots, with negative real parts, and the system is dynamically stable, and there will be oscillation decay response;

[0111] If represents no damping, the characteristic values are a pair of pure imaginary numbers, and the system is not dynamically stable, and there will be sustained oscillation;

[0112] Controllability: the controllability performance index function is as follows:

[0113]

[0114] where: ω controlsurface , ω frequency , ω steady-state , ω controlforce , ω sensitivity , ω delay , ω handlingquality are weight factors, used to balance the importance of different indexes in the performance function;

[0115] Econtrolsurface representing rudder efficiency,

[0116] R frequency representing frequency response,

[0117] S steady-state representing steady state error,

[0118] F controlforce representing control force,

[0119] S sensitivity representing control sensitivity,

[0120] D delay representing control lag,

[0121] Q handlingquality representing handling quality;

[0122] Flight time: the total time required for the UAV to complete the task, including the flight time from the starting point to the ending point and the possible task execution time;

[0123] Combining flight smoothness, dynamic characteristics and flight time, a weight is assigned to each index, and the formula of the optimization objective function is:

[0124] J = W 平滑性 ·J 平滑性 +W 动力学 ·J 动力学 +W 时间 ·J 时间 ;

[0125] Wherein, J represents a weighted multi-objective optimization function, J 平滑性 represents a flight smoothness performance index function, J 动力学 represents a dynamic characteristics performance index function, J 时间 represents a flight time performance index function, W 平滑性 , W 动力学 and W 时间 are the corresponding weight coefficients respectively;

[0126] The selection of the weight coefficient includes: the task demand and the flight environment of the UAV: if the task requires high flight stability, increase the value of W 平滑性 ; if the task requires rapid response, increase the value of W 动力学 ; if the task is time-sensitive, increase the value of W 时间 ;

[0127] By solving the weighted multi-objective optimization function, a set of optimized discrete path points are obtained, which satisfy all performance indexes at the same time, and realize the optimization of overall performance.

[0128] The positions, velocities, accelerations of the discrete path points and the time distribution of the trajectory are adjusted to minimize the optimization objective function J, and a gradient descent convex optimization algorithm is used to optimize the process to generate a time-continuous trajectory represented by piecewise polynomials, i.e. an emergency flight path that meets the current flight environment and task state.

[0129] In the gradient descent convex optimization algorithm, the objective function is a convex function, and J represents a weighted multi-objective optimization function that maps an input variable or a set of variables to an output value; specifically, J: R n → R is a mapping from the n-dimensional real number space R n to the real number space R, i.e. for any two points x and y, i.e. they are vectors in R n , and any real number λ ∈ [0, 1], have J(λx + (1-λ)y) ≤ λJ(x) + (1-λ)J(y); the gradient descent convex optimization algorithm updates the parameters along the negative gradient direction of the objective function iteratively to find the minimum value point of the objective function.

[0130] The main steps of the gradient descent convex optimization algorithm include:

[0131] Initialization: select an initial point X0, set the learning rate α and the threshold η in the stopping criterion;

[0132] Calculate the gradient: at the current point X k , calculate the gradient of the weighted multi-objective optimization function J(x) at the current point; The gradient is the steepest upward direction of the weighted multi-objective optimization function at the current point;

[0133] Update parameters: update parameters according to the gradient direction and learning rate α Update the parameters along the negative direction of the gradient to find the minimum value of the function;

[0134] Check convergence: repeat the steps of calculating the gradient and updating the parameters until the stopping criterion is met, which includes: the gradient norm is less than the threshold, the gradient of the current point changes very little, the function value changes little, close to the local minimum; the change of the function value is less than the threshold: |J(X k+1 )-J(X k )| ≤ ∈, where ∈ is another small positive number representing the tolerance of the change of the function value;

[0135] Termination condition: if any of the conditions in the stopping criterion is met, the algorithm terminates and outputs the current point Xk as an approximation of the optimal solution; if the stopping criterion is not met, continue to execute the gradient calculation step.

[0136] The technical effect and advantage of the present application: the unmanned aerial vehicle flight control method based on path constraint, by monitoring the flight environment and task state in real time, and dynamically adjusting the flight path, the unmanned aerial vehicle can quickly respond in emergency situation, ensure the smooth progress of the inspection task, improve the emergency response capability; through the inspection route path constraint algorithm, considering various constraint conditions, the optimal emergency flight path is generated, the invalid flight time is reduced, and the inspection efficiency is improved; by considering the flight performance constraint and the power constraint, the unmanned aerial vehicle always maintains in the safe flight state during the inspection process, and the flight accident is avoided. BRIEF DESCRIPTION OF DRAWINGS

[0137] Figure 1 The flowchart of the embodiment of the present application. DETAILED DESCRIPTION

[0138] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0139] The present application provides an unmanned aerial vehicle flight control method based on path constraint as shown in Figure 1 The present application provides an unmanned aerial vehicle flight control method based on path constraint as shown in

[0140] S10: obtaining an inspection task and an initial flight path, the unmanned aerial vehicle receives the inspection task, and obtains the initial flight path corresponding to the task; the initial flight path is pre-planned according to the terrain of the inspection area, tower position and other factors;

[0141] S11: real-time monitoring of flight environment and task state, the unmanned aerial vehicle monitors the flight environment and task state in real time through the sensor carried during flight;

[0142] Flight environment, such as wind speed, wind direction, visibility, etc.

[0143] Task state, such as remaining power, equipment health status, etc.

[0144] S12: inspection route path constraint algorithm, according to the real-time monitoring data, the inspection route path constraint algorithm is used to dynamically adjust the flight path;

[0145] S13: generating an emergency flight path, based on the path constraint algorithm of multi-objective optimization function, an emergency flight path conforming to the current flight environment and task state is generated;

[0146] S14: The UAV flies according to the generated emergency flight path and continues to monitor the flight environment and task status during the flight, further adjusting the flight path;

[0147] S15: Complete the inspection task and return to the base, after completing all inspection tasks according to the emergency flight path, the UAV automatically plans a path to return to the base and lands safely.

[0148] In step S10,

[0149] The determination of the initial flight path involves a detailed analysis of the inspection area, including the ups and downs of the terrain, the specific location of the tower, and any obstacles that may affect the flight path. Based on the above information, the UAV management system will plan an optimal flight path to ensure that the UAV can efficiently and safely complete the inspection task. During the flight, the UAV will also adjust the path according to the actual situation to deal with unexpected situations or optimize flight efficiency.

[0150] In step S11,

[0151] During the flight, the UAV monitors the flight environment and task status in real time through the sensors carried. The sensors can sense various parameters of the surrounding environment, such as wind speed, wind direction, visibility, etc., helping the UAV adjust the flight attitude and path to ensure flight safety. At the same time, the UAV will also monitor its own task status, including remaining power, device health status, etc., to discover and solve potential problems in time and prevent accidents.

[0152] In step S12, according to the real-time monitoring data, the path constraint algorithm is used to dynamically adjust the flight path;

[0153] During the flight, the UAV will dynamically adjust the flight path according to the real-time monitoring data using the path constraint algorithm. The UAV carries multiple sensors such as gas detectors, PM2.5 detectors, etc. to monitor environmental factors such as air, water quality, soil, etc. in real time. At the same time, the UAV system detection will also use sensor detection, data analysis and manual detection methods to comprehensively detect and analyze each part of the UAV to ensure that the UAV can operate normally during the flight and avoid accidents. Based on the real-time monitoring and analysis data, the UAV will use the path constraint algorithm to dynamically adjust its flight path to adapt to environmental changes and task requirements.

[0154] The path constraint algorithm includes the following constraints:

[0155] 1. Environmental constraints: including the influence of wind speed, wind direction, visibility, etc. on the UAV flight,

[0156] The wind speed mainly affects the flight speed and energy consumption of the UAV. In path planning, the influence of wind speed on flight time is considered as part of the path constraint. The actual flight speed V actual of the UAV is determined by the windless flight speed V uav of the UAV, the wind speed V wind and the angle θ between the wind direction and the flight direction of the UAV. The actual flight speed V actual of the UAV under the influence of wind speed can be calculated as: The flight time T can be calculated by the path length L and the actual flight speed Vactual:

[0157] The wind direction mainly affects the flight direction and energy consumption of the UAV. In path planning, it is necessary to ensure that the UAV can fly in the predetermined direction while considering the deviation of the flight trajectory caused by the wind direction. The deviation of the flight trajectory caused by the wind direction can be evaluated by calculating the angle (θ) between the wind direction and the flight direction. If the wind direction is opposite to the flight direction, the angle is 180°, and the UAV needs to consume more energy to maintain the flight direction. In the path constraint, a maximum allowed deviation angle θ_max can be set. If the calculated deviation angle is greater than θ_max, the path is considered infeasible.

[0158] Visibility mainly affects the visual navigation and obstacle avoidance ability of the UAV. In path planning, it is necessary to ensure that the UAV can maintain sufficient visibility during flight to ensure safety. The visibility constraint can be realized by setting a minimum allowed visibility V min . If the visibility of any point on the path is lower than V min , the path is considered infeasible.

[0159] 2. Task constraint: The task constraint refers to the specific requirements of the inspection task, such as the coverage of inspection points and the inspection order. The task constraint is processed by the following methods:

[0160] Path encoding: Sort and mark the key points on the inspection path to form an ordered encoding sequence;

[0161] Discretize the inspection area into a grid map, where each grid represents a possible inspection point;

[0162] Encode the flight path of the UAV as a sequence of grid points, each grid point corresponding to a position on the path;

[0163] Randomly generate a preset number of path encodings as the initial population, each encoding representing a possible flight path;

[0164] According to the length, safety and inspection efficiency of the flight path, the fitness of each path code in the population is evaluated;

[0165] Through the selection, crossover and mutation operations in the genetic algorithm, the population is iteratively optimized to generate new path codes;

[0166] When the preset number of iterations is reached or the fitness meets the set condition, the algorithm is terminated, and the optimal or near-optimal flight path code is output;

[0167] The flight path of the UAV is encoded into a chromosome in the genetic algorithm by the genetic algorithm, and a flight path scheme is a chromosome;

[0168] The fitness of each flight path in the population is evaluated to evaluate its advantages and disadvantages;

[0169] The selection method of the genetic algorithm includes: according to the fitness function of the genetic algorithm, the advantages and disadvantages of each path are evaluated, and the roulette selection or tournament selection method is used to select the path with high fitness from the current population as the parent to increase the chance of its inheritance to the next generation;

[0170] The crossover method of the genetic algorithm is: the selected parent path is subjected to crossover operation, including single-point crossover or two-point crossover, and new path schemes are generated by exchanging path segments;

[0171] The mutation method of the genetic algorithm includes: randomly changing the set path, including changing the position of one or more nodes on the path;

[0172] The fitness function of the genetic algorithm includes: rewarding the coverage rate of the inspection points or punishing the uncovered inspection points, and the multiple constraint conditions are combined into a single evaluation index to obtain the total fitness value by weighted summation;

[0173] Fitness = ω1*coverage reward + ω2*uncovered penalty + ω3*other constraint condition 1 +... + ω n *other constraint condition n;

[0174] Wherein, ω1, ω2,..., ω n are the weights of each constraint condition;

[0175] Wherein: coverage reward = actual number of covered inspection points / target number of covered inspection points;

[0176] Uncovered penalty = number of uncovered inspection points * penalty coefficient;

[0177] Fitness = ω1*(actual number of covered inspection points / target number of covered inspection points) + ω2*(number of uncovered inspection points * penalty coefficient) + ω3*other constraint condition 1 +... + ωn Other constraints n.

[0178] 3. Flight performance constraints: considering the maximum flight distance, maximum turning angle, maximum climb / descent rate, etc. of the UAV.

[0179] Flight performance constraints include the maximum speed, maximum climb / dive angle, minimum turning radius, etc. of the UAV. In the genetic algorithm, flight performance constraints can be handled by the following methods:

[0180] Path smoothing processing: Clothoid curve is used to smooth the path. After generating the path, smoothing processing is performed to make the path meet the minimum turning radius requirement of the UAV; genetic algorithm and path smoothing processing are complementary to each other. Genetic algorithm searches for the optimal path segment combination, and Clothoid curve performs path smoothing processing, which can find the optimal and smooth path in complex environment.

[0181] The Clothoid curve is approximated by the following formula:

[0182]

[0183] Where X' and Y' represent the horizontal and vertical coordinates of the point on the curve, A is a proportionality constant, and t is the arc length from the starting point of the curve to the current point.

[0184] Path smoothing processing fitness function limit:

[0185] The path smoothing processing fitness function gives a penalty when the maximum slope and maximum speed change exceed the limit.

[0186] The flight state adaptability calculation formula is F(h, v) = αh + βv, where F represents the path smoothing processing fitness function, h represents the flight height, v represents the flight speed, and α and β represent the weight coefficients, which are used to adjust the importance of height and speed in the path smoothing processing fitness function.

[0187] 4. Power constraint: ensure that the UAV has sufficient power during the inspection process, and automatically plan the return and replace power path if necessary. The power constraint is handled by the following methods:

[0188] Power model: establish a power consumption model of the UAV, considering the influence of flight speed, flight height, load, etc. on power.

[0189] The structure of the UAV power consumption model is mainly based on the Thevenin model;

[0190] The basic Thevenin model is composed of a voltage source Thevenin voltage, V TH and a series resistance Thevenin resistance, RTH Thevenin model, which is equivalent to a complex circuit network; The formula of Thevenin model can be expressed as:

[0191] V TH =V OC ;

[0192] R TH =R int ;

[0193] V out =V TH -I out *R TH ;

[0194] P=V out *I out ;

[0195] Wherein:

[0196] V TH is the Thevenin voltage, which is equal to the open-circuit voltage of the circuit network, i.e. the voltage when the two ends are open-circuited;

[0197] V OC is the open-circuit voltage, i.e. the voltage of the circuit network when there is no load;

[0198] R TH is the Thevenin resistance, which is equal to the input resistance of the circuit network, i.e. the internal resistance of the circuit network, when all independent power sources are removed or set to zero, the resistance from the port;

[0199] R int is the internal resistance, i.e. the internal resistance of the circuit network;

[0200] V out is the output voltage, i.e. the voltage on the load R L ;

[0201] I out is the output current, i.e. the current flowing through the load R L ;

[0202] P is the power consumed by the UAV in flight;

[0203] Path evaluation: when evaluating the path, in addition to considering the path length, the amount of electricity required to complete the path should be calculated according to the electricity model, and it should be judged whether it is within the electricity limit of the UAV. Paths exceeding the electricity limit should be given a lower fitness value.

[0204] In step S13, based on the inspection route path constraint algorithm, an emergency flight path conforming to the current flight environment and task state is generated.

[0205] Obtain real-time inspection scene information: including inspection route information and inspection weather information, which provides basic data for path planning; inspection route information, such as route level, tower, conductor type and number of branches;

[0206] Inspection weather information, such as coordinate information, altitude, temperature, wind speed, wind direction, and atmospheric pressure;

[0207] Coordinate information and altitude help determine the geographical location and height of the path, which helps analyze the geographical environment and terrain of the path.

[0208] Temperature, wind speed, wind direction and other meteorological elements affect the climate conditions on the path. For example, high or low temperature environment, strong wind, etc. may have different effects on the vehicle and personnel, which need to be adjusted accordingly to adjust the path planning.

[0209] Atmospheric pressure and other weather information helps predict weather changes on the path, ensuring the safety of path selection. For example, when planning an aviation or navigation path, the impact of pressure changes on flight or navigation must be considered.

[0210] Establish a safe flight corridor: based on real-time data, establish a safe flight corridor represented by a convex polyhedron set to ensure the safety of the flight path.

[0211] Establish a weighted multi-objective optimization function that combines flight smoothness, dynamic characteristics, and flight time performance indicators to optimize the position, velocity, acceleration, and trajectory time distribution of discrete path points, which are isolated point sets and path discontinuous points.

[0212] It should be noted that the multi-objective optimization function is a method of balancing and optimizing between multiple performance indicators. In the path planning of unmanned aerial vehicles, a weighted multi-objective optimization function can be established by combining flight smoothness, dynamic characteristics, flight time, etc. Performance indicators to optimize the position, velocity, acceleration, and trajectory time distribution of discrete path points.

[0213] First, clarify the specific meaning and calculation method of each performance indicator:

[0214] Flight smoothness: use the curvature of the trajectory and the rate of change of acceleration to quantify flight smoothness;

[0215] Trajectory curvature calculation: the curvature of the trajectory can reflect the bending degree of the flight trajectory. For a given flight trajectory, the smoothness is measured by calculating the curvature of each point on the trajectory. The calculation of curvature usually involves the derivative of the trajectory coordinates. For a plane curve, the curvature K is defined as the rate of change of the unit tangent vector with respect to the arc length, and its calculation formula is:

[0216] where: K represents the curvature;

[0217] and are the first derivatives, i.e. the velocities of the curve in the X and Y directions, respectively;

[0218] and are the second derivatives, i.e. the accelerations of the curve in the X and Y directions, respectively;

[0219] Jerk: Jerk, also known as jolt, is a measure of the rate of change of acceleration over time. It is the time derivative of acceleration, and its formula is:

[0220] where d represents the differential operator, which means taking the derivative of a certain physical quantity, a is the acceleration, and t is the time;

[0221] For two-dimensional or three-dimensional motion, jerk J is a vector, and each component is the vector sum of the rate of change of acceleration in the corresponding direction: where is the acceleration vector;

[0222] If the acceleration vector is represented by its components in the x, y, and z directions, then the components of the jerk vector can be expressed as:

[0223] Performance index function construction: A smoothness performance index function J 平滑性 is constructed as a weighted sum of the curvature K function and the jerk J function, J 平滑性 = ω k .K K + ω J .J J where J K is the term based on curvature K, J J is the term based on jerk J, ω k and ω J are the corresponding weight coefficients to balance the importance of the two indicators in the performance index function;

[0224] Dynamic characteristics: Include the flight dynamics behavior of the UAV, lift, drag, stability, and maneuverability;

[0225] Lift: The lift performance index function is usually used to measure the ability of the aircraft to generate lift under certain conditions. Lift is one of the key forces that enable the aircraft to fly in the air, and it is generated by the relative movement of the wings or rotors in the air. The lift performance index function can include the following key parameters:

[0226] Lift coefficient, Cl: Lift coefficient is a dimensionless parameter that measures the ratio of actual lift to theoretical lift, calculated by where L is actual lift, p is air density, V is flight speed, S is wing area,

[0227] Maximum lift coefficient, Cl_max: The maximum lift coefficient that an aircraft can generate under certain flight conditions, such as a specific angle of attack or flight speed;

[0228] Lift curve slope dCl / dα: Indicates the sensitivity of lift coefficient to changes in angle of attack, the rate of change of lift coefficient when the angle of attack changes;

[0229] Zero-lift angle of attack a0: The angle of attack at which the aircraft does not generate lift, that is, the angle of attack when the lift coefficient is zero;

[0230] Induced drag: Additional drag induced due to the generation of lift, usually proportional to the square of the lift coefficient;

[0231] Lift performance index function is represented as:

[0232]

[0233] where: Cl represents the lift coefficient, Cl_max represents the maximum lift coefficient, dCl / dα represents the lift curve slope, a0 represents the zero-lift angle of attack, Induced Drag represents the induced drag, ω Cl , ω Cl_max , ω dCl / dα , ω Induced Drag is a weight factor;

[0234] Drag: Drag performance index function is used to measure the resistance of the object in the fluid, in the field of aviation, drag performance is particularly important, because it is directly related to the fuel efficiency and range of the aircraft, drag performance index function can contain the following several key parameters:

[0235] Drag coefficient Cd: Drag coefficient is a dimensionless parameter that measures the ratio of the resistance of the object in the fluid to the product of the dynamic pressure and the reference area, the smaller the drag coefficient, the better the aerodynamic design of the object, the smaller the drag;

[0236] Zero-lift drag: The drag under the condition of no lift, usually including shape drag and friction drag;

[0237] Induced Drag: Induced drag is generated by lift. When lift is generated, vortices are formed on the upper and lower surfaces of the wing. The vortices form a vortex at the wingtip, which generates additional drag.

[0238] Wave Drag: When flying at supersonic speed, the front of the aircraft will compress the air and form a shock wave, resulting in wave drag.

[0239] Parasite Drag: Parasite drag includes form drag and friction drag, which is caused by the friction between the aircraft surface and the air and the shape of the aircraft.

[0240] Total Drag: Total drag is the sum of all the drag experienced by the aircraft under certain flight conditions.

[0241] The drag performance index function is represented as:

[0242] J D = ω Cd ·Cd- ω Drag at Zero Lift ·Drag at Zero Lift + ω InducedDrag ·InducedDrag + ω Wave Drag ·Wave Drag - ω Parasite Drag ·Parasite Drag

[0243] Where: ω Cd , ω Drag at Zero Lift , ω Induced Drag , ω Wave Drag , ω Parasite Drag are weight factors.

[0244] Stability: Stability performance index function generally includes static stability and dynamic stability. Static stability mainly considers the return or deviation trend of the aircraft after being disturbed in the equilibrium state, while dynamic stability involves the dynamic response characteristics such as damping characteristics and natural frequency of the aircraft.

[0245] The stability performance index function is represented as:

[0246] J s = ω static ·S static + ω dynamic ·S dynamic

[0247] wherein:

[0248] ω static , ω dynamic is a weight factor used to balance the importance of different indicators in the performance function;

[0249] S static represents the static stability indicator, which is evaluated by the position relationship between the center of gravity and the center of lift; the evaluation formula of static stability is:

[0250] is the rate of change of the lift coefficient (Cl) with the angle of attack (a);

[0251] is the rate of change of the pitching moment coefficient (Cm) with the angle of attack;

[0252] The pitching moment coefficient is expressed as:

[0253] Cm 0 is the pitching moment coefficient at zero angle of attack, which includes the sum of the moments generated by the fuselage, wings, tail and other components at zero angle of attack;

[0254] Cm α · a is the rate of change of the pitching moment coefficient caused by the change of the angle of attack;

[0255] Cm q is the rate of change of the pitching moment coefficient caused by the change of the pitch rate;

[0256] is the rate of change of the pitching moment coefficient caused by the change of the elevator deflection angle;

[0257] a is the angle of attack;

[0258] q is the pitch rate;

[0259] δ e is the elevator deflection angle;

[0260] If the above inequality holds, the aircraft is considered to be statically stable, because the increase in the angle of attack will result in an increase in lift, thereby generating a moment that will cause the angle of attack of the aircraft to decrease, restoring it to its original flight state;

[0261] S dynamic represents the dynamic stability indicator, which is determined by analyzing the dynamic characteristics of the aircraft; the damping ratio and the natural frequency ω n are the key parameters for judging the dynamic stability of the system. According to the characteristic value S, the dynamic stability of the system is judged,

[0262] If represents over-damped), the eigenvalues are all negative real numbers, the system is dynamically stable.

[0263] If represents critically damped), the eigenvalues are a pair of negative real numbers, the system is dynamically stable, but the response is slow.

[0264] If represents under-damped, the eigenvalues are complex conjugate roots with negative real parts, the system is dynamically stable, and there will be a damped response with oscillation.

[0265] If represents undamped, the eigenvalues are a pair of pure imaginary numbers, the system is not dynamically stable, and there will be a sustained oscillation.

[0266] Controllability: The controllability performance index function is a mathematical representation used to quantify the response capability of an aircraft to control inputs, taking into account factors such as control surface efficiency, frequency response, steady-state error, control force, control sensitivity, control lag, and control quality.

[0267] Control surface efficiency E controlsurface : determined through experiments, or predicted through numerical simulation.

[0268] Frequency response R frequency : Frequency response refers to the response of the system to periodic inputs.

[0269] Steady-state error S steady-state : Steady-state error refers to the difference between the expected output and the actual output when the system transitions from one steady state to another.

[0270] Control force F controlforce : The size of the control force directly affects the degree of fatigue of the pilot in the air and the difficulty of the aircraft control.

[0271] Control sensitivity S sensitivity : Control sensitivity refers to the sensitivity of the system to control inputs.

[0272] Control lag D delay : Control lag refers to the time delay between control input and system response.

[0273] Control quality Q handlingquality : Control quality refers to the subjective evaluation of the pilot on the performance of the aircraft control.

[0274] Based on the above factors, a control performance index function is defined as follows:

[0275]

[0276] Where: ωcontrolsurface , ω frequency , ω steady-state , ω controlforce , ω sensitivity , ω delay , ω handlingquality is a weight factor to balance the importance of different indicators in the performance function;

[0277] The dynamic performance indicator function J 动力学 is defined as L . L + ω D . D + ω S . S + ω C . C ,

[0278] where ω L , ω D , ω S , ω C represent the corresponding weight coefficients respectively;

[0279] Flight time: the total time required for the UAV to complete the task, including the flight time from the starting point to the ending point and the possible task execution time.

[0280] Combining flight smoothness, dynamic characteristics and flight time, a weight is assigned to each indicator, and the formula of the optimization objective function is:

[0281] J = W 平滑性 · J 平滑性 + W 动力学 · J 动力学 + W 时间 · J 时间 ;

[0282] where J represents the weighted multi-objective optimization function, J 平滑性 represents the flight smoothness performance indicator function, J 动力学 represents the dynamic characteristics performance indicator function, J 时间 represents the flight time performance indicator function, W 平滑性 , W 动力学 and W 时间 are the corresponding weight coefficients respectively;

[0283] The selection of weight coefficients includes: the task requirements and flight environment of the UAV: if the task requires high flight smoothness, increase the value of W 平滑性 ; if the task requires rapid response, increase the value of W 动力学 ; if the task is time-sensitive, increase the value of W 时间 ;

[0284] By solving the weighted multi-objective optimization function, a set of optimized discrete path points are obtained, which satisfy all performance indicators at the same time, and realize the optimization of overall performance. Such path planning method can make the unmanned aerial vehicle more efficiently and stably complete various tasks in complex environment.

[0285] Generating emergency flight path: using gradient descent based convex optimization algorithm to generate time domain continuous trajectory represented by piecewise polynomial, that is, emergency flight path conforming to current flight environment and task state.

[0286] Adjusting the position, velocity, acceleration of discrete path points and the time allocation of trajectory to minimize the optimization objective function J, using gradient descent based convex optimization algorithm for optimization processing, generating time domain continuous trajectory represented by piecewise polynomial, that is, emergency flight path conforming to current flight environment and task state.

[0287] In convex optimization problem, the objective function is a convex function, J represents the weighted multi-objective optimization function, which maps an input variable or a set of variables to an output value. Specifically, J: R n → R is a mapping from n-dimensional real number space R n to real number space R, that is, for any two points x and y, that is, they are vectors in R n , and any real number λ ∈ [0, 1], have J(λx+(1-λ)y)≤λJ(x)+(1-λ)J(y); Gradient descent based convex optimization algorithm updates parameters along the negative gradient direction of objective function by iteration to find the minimum value point of objective function.

[0288] The main steps of gradient descent based convex optimization algorithm include:

[0289] Initialization: select initial point X0, set learning rate α and threshold η in stopping criterion;

[0290] Calculate gradient: at the current point X k , calculate the gradient of the weighted multi-objective optimization function J(x) at the current point X

[0291] Update parameters: update parameters according to gradient direction and learning rate α Update parameters along the negative direction of gradient to find the minimum value of function;

[0292] Check convergence: repeat the steps of calculating gradient and updating parameters until the stopping criterion is met, which includes: the gradient norm is less than the threshold, The gradient of the current point changes very little, the function value changes little, and it is close to the local minimum; The change of function value is less than the threshold: |J(X k+1) - J(X k ) | < ε, where ε is another preset small positive number, representing the tolerance of function value change;

[0293] Termination condition: if any of the stopping criteria is met, the algorithm terminates and outputs the current point Xk as an approximation of the optimal solution; if none of the stopping criteria is met, continue to perform the gradient calculation step.

[0294] In step S14, the UAV flies according to the generated emergency flight path and continues to monitor the flight environment and task status during the flight to further adjust the flight path if necessary;

[0295] The UAV flies according to the generated emergency flight path, which is calculated by considering the flight environment, task requirements and safety factors, using advanced path generation algorithms, to ensure that the UAV can efficiently and safely complete the task. During the flight, the UAV also continues to monitor the flight environment and task status, as well as the flight status and equipment health of the UAV. Based on these real-time monitoring data, the UAV can further adjust the flight path as necessary to adapt to changes in the environment and task requirements, ensuring the safety of the flight and the smooth execution of the task.

[0296] In step S15, after completing all the inspection tasks according to the emergency flight path, the UAV automatically plans a return path to the base and lands safely;

[0297] After completing all the inspection tasks, the UAV can automatically plan a return path to the base and land safely. During this process, the UAV mainly relies on its advanced automatic return system. This system can build a map of the flight environment in real time during flight and record the flight trajectory. Once the flight control signal is interrupted or a sudden situation occurs, the flight control system will take over the control of the aircraft, refer to the original flight path planning route, and control the aircraft to return. During the return process, the UAV can also intelligently choose to hover or bypass obstacles to ensure safe return. In addition, the UAV also has an intelligent low battery return function, which can automatically plan a return path and land safely when the battery is low.

[0298] Finally, it should be noted that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent replacements to some technical features, as long as they are within the spirit and principles of the present application. Any modification, equivalent replacement, improvement, etc. made within the scope of the present application shall be included in the protection scope of the present application.

Claims

1. A UAV flight control method based on path constraints, characterized by: include: Obtain inspection tasks and initial flight paths; Monitor flight environment and mission status; Dynamically adjust the flight path based on the monitored data; Generate emergency flight paths that are consistent with the current flight environment and mission status; Control the UAV to fly along the emergency flight path and continue to monitor the flight environment and mission status during flight; Complete the inspection task and return; The dynamically adjusting the flight path includes: dynamically adjusting the flight path through a path constraint algorithm; the constraint conditions of the path constraint algorithm include: Environmental constraints: the actual flight speed V of the drone actual The calculation formula is: Among them, V actual Represents the actual flight speed of the drone, V uav Represents the drone's wind-free flight speed, V wind represents the wind speed of the drone, θ represents the angle between the wind direction and the flight direction of the drone; the calculation formula for the flight time T is as follows: Where L represents the path length; Wind direction constraint: Set the maximum allowable deviation angle θ_max. If the angle θ is greater than the maximum allowable deviation angle θ_max, the path is infeasible. If the wind direction is opposite to the flight direction, the angle θ is 180°. Visibility constraint: Set the minimum allowed visibility V min If the visibility at any point on the flight path is lower than the minimum permissible visibility V min , then the path is not feasible; Task constraints: including inspection point coverage and inspection sequence; Flight performance constraints: including the maximum speed, maximum climb, maximum dive angle, and minimum turning radius of the drone; Power constraint: Ensure that the drone has sufficient power during the inspection process; The task constraint method includes: Path coding: sort and mark the key points on the inspection path to form an orderly coding sequence; Discretize the inspection area into a grid map, where each grid represents a possible inspection point; Encode the UAV's flight path as a sequence of grid points, where each grid point corresponds to a position on the path; A preset number of path codes are randomly generated as the initial population, each code representing a possible flight path; The fitness of each path code in the population is evaluated based on the length, safety, and inspection efficiency of the flight path; Through the selection, crossover and mutation operations of the genetic algorithm, the population is continuously optimized iteratively to generate new path codes; When the preset number of iterations is reached or the fitness meets the set conditions, the algorithm is terminated and the optimal or approximately optimal flight path code is output; The flight path of the UAV is encoded into a chromosome in the genetic algorithm through the genetic algorithm. A flight path plan is a chromosome. Conduct fitness assessment on each flight path within the population to evaluate its quality; The selection methods of the genetic algorithm include: evaluating the quality of each path according to the genetic algorithm fitness function, using roulette or tournament selection methods, and selecting paths with high fitness from the current population as parents to increase the chance of their inheritance to the next generation; The crossover method of the genetic algorithm is: perform a crossover operation on the selected parent path, including single-point crossover or two-point crossover, and exchange path segments to generate a new path solution; The mutation methods of genetic algorithms include: making random changes to the set path, including changing the position of one or more nodes on the path; The fitness function of the genetic algorithm includes: rewards for inspection point coverage or penalties for uncovered inspection points, and a total fitness value is obtained by combining multiple constraints into a single evaluation index in the form of weighted summation; Fitness = ω1*coverage reward + ω2*non-coverage penalty + ω3*other constraints 1 + ... + ω n * Other constraints n-2; Among them, ω1, ω2, ..., ω n is the weight of each constraint; Where: Coverage bonus = actual number of inspection points covered / target number of inspection points covered; Non-coverage penalty = number of uncovered inspection points * penalty coefficient; Fitness = ω1*(actual number of inspection points covered / target number of inspection points covered) + ω2*(number of uncovered inspection points*penalty coefficient) + ω3*other constraints 1 + ... + ω n *Other constraints n-2.

2. The method for controlling a UAV flight based on path constraints according to claim 1, characterized in that: The initial flight path is pre-planned based on the terrain and tower locations of the inspection area.

3. The UAV flight control method based on path constraints according to claim 1, characterized in that: The flight environment includes: wind speed, wind direction and visibility; The task status includes: remaining power and device health status.

4. The method for controlling a UAV flight based on path constraints according to claim 1, wherein: The flight performance constraints include: The maximum speed, maximum climb, maximum dive angle, and minimum turning radius of the UAV are handled by the genetic algorithm through the following methods: Path smoothing: Use Clothoid curve to smooth the path. After the path is generated, it is smoothed to ensure that the path meets the minimum turning radius requirement of the drone. The Clothoid curve is approximated by the following formula: Where: X' and Y' represent the horizontal and vertical coordinates of the point on the curve respectively, A is a proportional constant, and t is the arc length from the starting point of the curve to the current point; Path smoothing fitness function limitations: The path smoothing fitness function imposes penalties when the maximum slope and maximum speed change exceed the limit; The flight state adaptability calculation formula is F(h,v)=αh+βv, where F represents the path smoothing fitness function, h represents the flight altitude, v represents the flight speed, and α and β represent weight coefficients used to adjust the importance of altitude and speed in the path smoothing fitness function.

5. The UAV flight control method based on path constraints according to claim 1, characterized in that: The power constraints include: Power consumption model: Establish a power consumption model for the UAV, including the impact of flight speed, flight altitude, and load factors on power consumption; The power consumption model structure is constructed based on the Thevenin model; The formula of the Thevenin model is expressed as: V TH =V OC ; R TH =R int ; V out =V TH -I out *R TH ; P=V out *I out ; Where: V TH It represents the Thevenin voltage, which is equal to the open-circuit voltage of the circuit network; V OC Indicates the voltage when the circuit network is unloaded; R TH represents Thevenin resistance; R int Indicates the internal resistance of the circuit network; V out Indicates the output voltage; I out Indicates output current; P represents the power consumed by the drone during flight; Path evaluation: When evaluating a path, the path length is calculated and the amount of power required to complete the path length is calculated based on the power model to determine whether it is within the drone's power limit. Paths that exceed the power limit are assigned a lower fitness value.

6. The UAV flight control method based on path constraints according to claim 1, characterized in that: The monitored data includes: obtaining real-time inspection scene information: including inspection route information and inspection weather information; Inspection line information includes: line grade, tower and conductor model split number; Inspection meteorological information includes: coordinate information, altitude, temperature, wind speed, wind direction and atmospheric pressure; Generating an emergency flight path that conforms to the current flight environment and mission status includes: establishing a weighted multi-objective optimization function that optimizes the position, velocity, acceleration, and time allocation of discrete path points, combining flight smoothness, dynamic characteristics, and flight time performance indicators; wherein discrete path points are isolated point sets and points where the path is discontinuous; Flight smoothness: flight smoothness is quantified using trajectory curvature and acceleration change rate indicators; Calculation method of trajectory curvature: The formula is: Where: K represents the curvature; and Represents the speed of the curve in the X and Y directions respectively; and Represents the acceleration of the curve in the X and Y directions respectively; The formula for calculating the rate of change of acceleration is: Where d represents the differential operator, which means to take the derivative of a physical quantity, a represents acceleration, and t represents time; For two-dimensional or three-dimensional motion, the jerk J is a vector whose components are the vector sums of the rates of change of acceleration in the corresponding directions: in is the acceleration vector; If the acceleration vector The jerk vector is represented by its components in the x, y, and z directions. The components are expressed as: Constructing the flight smoothness performance index function includes: flight smoothness performance index function J 平滑性 is the weighted sum of the curvature K function and the jerk J function, J 平滑性 =ω k .J K +ω J .J J Among them, J K is a term based on the curvature K, J J is a term based on the jerk J, ω k and ω J is the corresponding weight coefficient; Dynamic characteristics: including the flight mechanical behavior of the UAV, lift, drag, stability and maneuverability; lift: the lift performance index function is expressed as: Where: Cl represents the lift coefficient, Cl max represents the maximum lift coefficient, dCl / dα represents the slope of the lift line, α0 represents the zero lift angle of attack, Induced Drag represents the lift-induced drag, ω Cl 、ω Cl_max 、ω dCl / dα 、 ω Induced Drag is the weight factor; The lift coefficient Cl is calculated as follows: Where L is the actual lift, ρ is the air density, V is the flight speed, and S is the wingspan area; Resistance: The resistance performance index function is expressed as: J D =ω Cd ·Cd-ω DragatZeroLift ·DragatZero Lift+ω InducedDrag · Induced Drag+ω Wave Drag ·Wave Drag-ω Parasite Drag ·Parasite Drag Where: Cd 、ω Drag atZero Lift 、ω Induced Drag 、ω Wave Drag 、ω Parasite Drag is the weighting factor; Cd represents the drag coefficient, DragatZero Lift represents zero lift drag, Induced Drag represents induced drag, Wave Drag represents wave drag, Parasite Drag represents parasitic drag, and Total Drag represents total drag; Stability: The stability performance index function includes two aspects: static stability and dynamic stability. The stability performance index function is expressed as: J s =ω static ·S static +oh dynamic ·S dynamic in: ω static 、ω dynamic is the weight factor; S static It represents the static stability index, which is evaluated by the positional relationship between the center of gravity and the center of lift. The basic evaluation formula for static stability is: in: is the rate of change of the lift coefficient Cl with the angle of attack α; is the rate of change of the pitching moment coefficient Cm with the angle of attack α; The pitching moment coefficient itself is expressed as: Cm 0 is the pitching moment coefficient at zero angle of attack; Cm α α is the rate of change of the pitching moment coefficient caused by the change in angle of attack; Cm q It represents the rate of change of the pitch moment coefficient caused by the change of the pitch angular velocity; It expresses the rate of change of the pitching moment coefficient caused by the change of the elevator deflection angle; α represents the angle of attack; q represents the pitch angular velocity; δ e Indicates the elevator deflection angle; S dynamic Indicates the dynamic stability index, which is determined by analyzing the dynamic characteristics of the aircraft; damping ratio and the natural frequency ω n It is the key parameter for judging the dynamic stability of the system. The dynamic stability of the system is judged according to the characteristic value S. if represents overdamping, the eigenvalues ​​are all negative real numbers, and the system is dynamically stable; if Represents critical damping, the eigenvalue is a pair of negative real numbers, the system is dynamically stable, but the response speed is slow; if It represents underdamping, the eigenvalue is the complex conjugate root, the real part is negative, the system is dynamically stable, and there will be an oscillatory damped response; if It represents no damping, the eigenvalue is a pair of pure imaginary numbers, the system is not dynamically stable and there will be continuous oscillations; Maneuverability: The maneuverability performance index function is as follows: Where: ω controlsurface , ω frequency , ω steady-state , ω controlforce , ω sensitivity , ω delay , ω handlingquality are weighting factors; E controlsurface represents the efficiency of the control surface, R frequency represents the frequency response, S steady-state represents the steady-state error, F controlforce Represents control, S sensitivity Represents control sensitivity, D delay represents the control lag, Q handlingquality Represents the quality of manipulation; Dynamic performance index function J 动力学 =ω L .J L +ω D .J D +ω S .J S +ω C .J C , where ω L 、ω D 、ω S 、ω C Represent the corresponding weight coefficients respectively; Flight time: The total time required for the drone to complete the mission, including the flight time from the starting point to the destination and possible mission execution time; Combining flight smoothness, dynamic characteristics, and flight time, and assigning a weight to each indicator, the formula for optimizing the objective function is: J=W 平滑性 ·J 平滑性 +W 动力学 ·J 动力学 +W 时间 ·J 时间 ; Among them, J represents the weighted multi-objective optimization function, J 平滑性 Represents the flight smoothness performance index function, J 动力学 Represents the dynamic characteristics performance index function, J 时间 Represents the flight time performance indicator function, W 平滑性 、W 动力学 and W 时间 are the corresponding weight coefficients respectively; The selection of weight coefficients includes: the mission requirements of the UAV and the flight environment: if the mission requires high flight stability, increase W 平滑性 If the task requires fast response, increase W 动力学 If the task is time-sensitive, increase W 时间 The value of By solving the weighted multi-objective optimization function, a set of optimized discrete path points is obtained. The discrete path points meet all performance indicators while achieving the optimization of the overall performance.

7. The method for controlling a UAV flight based on path constraints according to claim 6, characterized in that: The method for optimizing the position, velocity, acceleration, and time allocation of the trajectory of discrete path points includes: using a convex optimization algorithm with gradient descent to generate a time-domain continuous trajectory represented by a piecewise polynomial, that is, an emergency flight path that conforms to the current flight environment and mission status; In the convex optimization algorithm of gradient descent, the objective function is a convex function. J represents a weighted multi-objective optimization function that maps an input variable or a set of variables to an output value. J:R n →R is a real number space from n dimensions R n Mapping to the real space R, that is, for any two points x and y, that is, they are R n For any vector in , and any real number λ∈[0,1], J(λx+(1-λ)y)≤λJ(x)+(1-λ)J(y); the gradient descent convex optimization algorithm iteratively updates the parameters along the negative gradient direction of the objective function to find the minimum point of the objective function.

8. The method for controlling a UAV flight based on path constraints according to claim 7, characterized in that: The convex optimization algorithm steps of gradient descent include: Initialization: Select the initial point X0, set the learning rate α and the threshold η in the stopping criterion; Calculate the gradient: At the current point Xk, calculate the gradient of the weighted multi-objective optimization function J(x) The gradient is the steepest rising direction of the weighted multi-objective optimization function at the current point; Update parameters: Update parameters according to the gradient direction and learning rate α Update the parameters along the negative direction of the gradient to find the minimum value of the function; Check convergence: Repeat the steps of calculating gradients and updating parameters until a stopping criterion is met, which includes: the norm of the gradient is less than a threshold, The gradient change of the current point is close to the local minimum; the change of the function value is less than the threshold: |J(Xk+1)-J(Xk)|≤∈, where ∈ is another preset small positive number, indicating the tolerance of the function value change; Termination condition: If any of the stopping criteria is met, the algorithm terminates and outputs the current point Xk as an approximation of the optimal solution; if the stopping criteria is not met, the gradient calculation step continues.

Images