A method, system, device and medium for optimizing extraction of operating parameters of a drone charged spray water column

Abstract

The present application relates to unmanned aerial vehicle live spraying technical field, especially a kind of unmanned aerial vehicle live spraying water column control parameter optimization extraction method, system, equipment and medium, it includes establishing the initial state mathematical model of describing spray gun space position and attitude, and constructs angle matrix for representing water column axis direction;With spray gun position, spray angle and coating thickness as the control parameter to be optimized, construct the objective function for the collaborative optimization of control parameter;According to the change of unmanned aerial vehicle attitude caused by the reduction of coating mass in the spraying process, the spray angle of the spraying water column is dynamically compensated, and the objective function is updated based on the compensated angle;The updated objective function is solved using intelligent optimization algorithm, and the target spraying water column control parameter combination containing spray gun position, spray angle and coating thickness is output.The beneficial effects of the present application are to effectively enhance the efficiency, quality and stability of unmanned aerial vehicle live spraying operation.

Description

Technical Field

[0001] This invention relates to the field of electric spraying technology for unmanned aerial vehicles (UAVs), and in particular to a method, system, equipment, and medium for optimizing and extracting control parameters of water jet spraying for UAVs. Background Technology

[0002] In recent years, the use of drones for live-line spraying of anti-flashover coatings on high-voltage transmission line insulators has become an important technical means in the field of power operation and maintenance. In existing technologies, researchers have explored this technology from multiple perspectives, such as setting the spraying direction based on the pollution accumulation morphology, quantifying the relationship between electric field and atomization parameters, constructing digital twin models for simulation optimization, or fitting empirical models with experimental data to seek better spraying results.

[0003] However, most of these methods remain at the "static" level, assuming that the target and environment are fixed and unchanging. They also handle the optimization of spray water column control parameters in a relatively simple way, mostly only qualitatively analyzing the factors affecting spraying and setting the control parameters of the spray water column based on empirical values. They have not yet been able to finely optimize the control parameters based on the actual engineering aspects of work safety, spraying quality, work efficiency and economy. Overall, they are still in the initial stage of transitioning from experience-driven to model and data-driven approaches, and face many challenges such as limited measurement methods, insufficient dynamic adaptability of models, and unclear multi-physics coupling mechanisms. Summary of the Invention

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for optimizing and extracting control parameters of an UAV for spraying water jets, including establishing an initial state mathematical model describing the spatial position and attitude of the spray gun by defining the attached coordinate system of the spray gun and the homogeneous transformation matrix. Based on the initial state mathematical model and the jet angle, an angle matrix is ​​constructed to characterize the direction of the water column axis. Using the spray gun position, spray angle, and coating thickness as the control parameters to be optimized, an objective function is constructed to collaboratively optimize the control parameters. Based on the change in UAV attitude caused by the reduction in paint quality during the spraying process, the spraying angle of the water jet is dynamically compensated, and the objective function is updated based on the compensated angle. An intelligent optimization algorithm is used to solve the updated objective function, and the output is a combination of control parameters for the target spray water column, including the spray gun position, spray angle and coating thickness.

[0005] As a preferred embodiment of the method for optimizing and extracting control parameters of an UAV-based electrified water jet spraying system according to the present invention, the method includes: establishing an initial state mathematical model describing the spatial position and attitude of the spray gun by defining the attached coordinate system and homogeneous transformation matrix of the spray gun, including: The spray gun attachment coordinate system takes the center of the drone nozzle as the origin, determines the first coordinate axis with the direction of the nozzle axis, and determines the other two coordinate axes according to the right-hand rule; The homogeneous transformation matrix consists of a rotation matrix describing the UAV's attitude and a position vector describing the spray gun's position.

[0006] As a preferred embodiment of the method for optimizing and extracting control parameters of an UAV-based electrically sprayed water column according to the present invention, the method includes: constructing an angle matrix to characterize the axial direction of the water column, including... When constructing the angle matrix, rotation and translation transformations are used in combination to correct the end spraying position error caused by the non-parallelism between the spray axis and the expected direction.

[0007] As a preferred embodiment of the method for optimizing and extracting control parameters of UAV electrified water jet spraying according to the present invention, the objective function is constructed to simultaneously minimize the spray gun position deviation, spray angle deviation, and the deviation between the coating thickness and the target value.

[0008] As a preferred embodiment of the method for optimizing and extracting control parameters of UAV electric spraying water column according to the present invention, the intelligent optimization algorithm is a genetic algorithm.

[0009] As a preferred embodiment of the method for optimizing and extracting control parameters for UAV-based electrified water jet spraying according to the present invention, the updated objective function is solved using an intelligent genetic algorithm, including: Initialize a population containing multiple candidate parameter combinations; The fitness of individuals in the population is calculated based on the updated objective function; The population is iteratively updated through selection, crossover, and mutation operations until the preset termination condition is met. The combination of control parameters corresponding to the individual with the best fitness is then output as the control parameter combination for the target water jet spraying.

[0010] As a preferred embodiment of the method for optimizing and extracting control parameters of live water jet spraying for UAVs according to the present invention, the coating thickness on which the objective function is based is obtained by multi-point measurement of the spraying area on the surface of the insulator.

[0011] Secondly, the present invention provides a method for optimizing and extracting control parameters of an UAV for spraying water jets, comprising: a module for establishing an initial state mathematical model describing the spatial position and attitude of the spray gun by defining the attached coordinate system of the spray gun and the homogeneous transformation matrix. The first construction module is used to construct an angle matrix that characterizes the direction of the water column axis based on the initial state mathematical model and the jet angle. The second construction module is used to construct an objective function for the collaborative optimization of the control parameters, using the spray gun position, spray angle and coating thickness as the control parameters to be optimized. The update module is used to dynamically compensate the spray angle of the water jet based on the change in the attitude of the UAV caused by the reduction of paint quality during the spraying process, and update the objective function based on the compensated angle. The output module is used to solve the updated objective function using an intelligent optimization algorithm, and outputs a combination of target spray water column control parameters including spray gun position, spray angle, and coating thickness.

[0012] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0013] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described above.

[0014] Compared with existing technologies, the beneficial effects of this invention are as follows: By constructing an initial state mathematical model and angle matrix for UAV water jet spraying, and using the spray gun position, spray angle, and coating thickness as the core optimization parameters of the objective function, a theoretical basis is laid for achieving uniform and efficient spraying operations. On this basis, by introducing a dynamic angle compensation mechanism based on paint consumption, and using a genetic algorithm to solve the compensated objective function, the optimal combination of control parameters is obtained, which significantly improves the utilization rate of paint and parameter adaptability during the spraying process. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart for optimizing and extracting control parameters for electrified water jet spraying by unmanned aerial vehicles.

[0017] Figure 2 This is a schematic diagram of the coordinate system attached to the spray gun. Detailed Implementation

[0018] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0019] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrostatic spraying water jets, including: S100: By defining the spray gun attachment coordinate system and homogeneous transformation matrix, an initial state mathematical model describing the spatial position and attitude of the spray gun is established. S200: Based on the initial state mathematical model and the jet angle, construct an angle matrix to characterize the direction of the water column axis; S300: Using the spray gun position, spray angle, and coating thickness as the control parameters to be optimized, construct an objective function for the collaborative optimization of the control parameters. S400: Based on the change in UAV attitude caused by the reduction in paint quality during the spraying process, the spraying angle of the water jet is dynamically compensated, and the objective function is updated based on the compensated angle. S500: It uses an intelligent optimization algorithm to solve the updated objective function and outputs a combination of target spray water column control parameters, including spray gun position, spray angle and coating thickness.

[0020] It should be noted that during the live-line spraying of anti-flashover coatings onto high-voltage transmission line insulators by drones, the coating quality is directly affected by the combined influence of multiple dynamic parameters, such as the spatial position of the spray gun, the spray angle, and the coating thickness. Since the operation takes place in a high-voltage electric field environment, the spraying process must also consider both operational safety and coating uniformity. However, traditional methods often rely on static, empirical parameters, which cannot adapt in real time to changes in the drone's weight due to coating consumption during the spraying process. This can lead to spray axis deviation, affecting spraying accuracy and coating utilization. Furthermore, the coupling between these multiple parameters makes system optimization difficult through manual experience, resulting in uneven coating thickness and low spraying efficiency, severely hindering the large-scale and reliable application of this technology.

[0021] Therefore, this method establishes a precise mathematical model of the spray gun's spatial attitude to provide a descriptive basis for parameter system optimization. It then constructs an angle matrix that can correct the spray direction, reducing end-position errors. Based on this, it integrates multiple parameters to establish an objective function, achieving synergistic optimization of spray position, angle, and thickness. Furthermore, it introduces a dynamic angle compensation mechanism based on paint consumption, enabling the optimization model to adapt to real-time changes during operation. Finally, it automatically solves for the optimal parameter combination through an intelligent optimization algorithm, thereby improving spray uniformity, coating quality, and operational efficiency while ensuring operational safety.

[0022] Example 2, refer to Figures 1-2 As an embodiment of the present invention, based on the above embodiment, a method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) electrostatic spraying water column is provided.

[0023] In this embodiment of the application, step S100 establishes an initial state mathematical model describing the spatial position and attitude of the spray gun by defining the spray gun attachment coordinate system and the homogeneous transformation matrix, including the following steps A1-A2: A1: The spray gun attachment coordinate system takes the center of the drone nozzle as the origin, determines the first coordinate axis with the direction of the nozzle axis, and determines the other two coordinate axes according to the right-hand rule.

[0024] like Figure 2 As shown, the origin of the coordinate system is selected at the center of the drone nozzle, the z-axis is the axis of the drone nozzle and the direction of the water jet is its positive direction, the x-axis is the width direction of the drone nozzle and the y-axis is the thickness direction of the nozzle. The positive direction of the y-axis is selected in accordance with the right-hand coordinate system.

[0025] Preferably, based on the above coordinate system, any spatial movement of the spray gun itself, whether translation or rotation, can be intuitively transformed into a transformation of this coordinate system relative to the global coordinate system.

[0026] A2: The homogeneous transformation matrix consists of a rotation matrix describing the UAV's attitude and a position vector describing the spray gun's position.

[0027] It should be noted that the homogeneous transformation matrix G is specifically represented as follows: In the formula: T is the 3×3 UAV attitude matrix; D is the 3×1 UAV spray gun position matrix, which is related to the surface shape of the insulator being sprayed and the path formed on the surface during spraying.

[0028] Preferably, the complete spatial pose of the spray gun at any given time can be accurately and uniformly digitized through matrix G.

[0029] In an optional implementation, the initial state mathematical model describing the spatial position and attitude of the spray gun in step S100 can also be achieved by defining the spatial pose vector of the spray gun. Specifically, the process is as follows: First, in the global operating coordinate system, the spatial position of the spray gun is defined as a position vector P composed of three-dimensional coordinates (X, Y, Z). Second, Euler angles (e.g., roll angle φ, pitch angle θ, yaw angle ψ) or unit quaternions Q are used to compactly describe the orientation attitude of the spray gun. Finally, this position vector and attitude representation together form the complete spatial pose state S=(P,Q) of the spray gun. This model serves as the basis for subsequent optimization and compensation. By directly performing mathematical operations and iterations on the pose state S, the spatial motion of the spray gun can be described and analyzed, avoiding the construction of a homogeneous transformation matrix and simplifying model expression and calculation while ensuring accuracy.

[0030] In another optional implementation, the initial state mathematical model describing the spatial position and attitude of the spray gun in step S100 can also be achieved by solving the geometric relationship between the UAV flight control commands and the spray gun. The specific process is as follows: First, acquire the real-time state output of the UAV flight control system, including key information such as the three-dimensional coordinates of the UAV's center of mass, the airframe attitude angle, and the rotor speed. Then, based on the rigid connection structure between the UAV and the spray gun (i.e., a fixed installation position and angular relationship), establish a fixed coordinate transformation relationship from the UAV's airframe coordinate system to the center of the spray gun's outlet. Finally, by superimposing this fixed transformation relationship with the UAV's real-time pose state, the precise position of the spray gun's outlet center in the global coordinate system and the spatial orientation of its spray axis are directly derived.

[0031] In this embodiment of the application, step S200 constructs an angle matrix to characterize the direction of the water column axis based on the initial state mathematical model and the jet angle, including the following steps B1-B2: Understandably, the initial mathematical model does not fully characterize the parallelism of the spray axis, only representing the spatial intersection angle of the axes. However, when this angle is incorrect, it will cause a significant error in the end position of the water jet ejected from the nozzle. Therefore, this method describes this situation by constructing an angle matrix. Specifically, when constructing the angle matrix, rotation and translation transformations are used in combination to correct the end spraying position error caused by the non-parallelism between the spray axis and the expected direction.

[0032] B1: Rotation transformation based on injection angle.

[0033] Specifically, using the specified spray angle θ as input, rotation transformations are performed around the X and Y axes of the spray gun's attached coordinate system, respectively. and .

[0034] Preferably, through these two rotational transformations, a mathematical description can be constructed that accurately reflects the spatial direction of the spray axis of the spray gun after it is adjusted by an angle θ.

[0035] B2: Translation transformation based on coating thickness deviation.

[0036] Specifically, a translation transformation is performed along the Z-axis of the spray gun's attached coordinate system (i.e., the direction of the nozzle axis). It is understandable that the translation distance r is not a fixed value, but a variable related to the coating thickness control target.

[0037] Furthermore, the angle matrix is ​​as follows: In the formula: This indicates a counterclockwise rotation of vector ox by θ degrees; This indicates a counterclockwise rotation of the oy vector by θ degrees. This indicates that the vector oz is translated by a distance r.

[0038] In an optional implementation, the angle matrix used to characterize the direction of the water column axis in step S200 can also be constructed by directly building a direction cosine matrix from the spray gun attachment coordinate system to the target spraying reference coordinate system. That is, first, based on the three coordinate axis vectors of the spray gun attachment coordinate system and the desired spraying target reference direction, the direction cosine relationship between the two coordinate systems is calculated. This relationship is then directly represented as a 3x3 orthogonal matrix, where each column of the matrix represents the direction cosine of each coordinate axis of the spray gun coordinate system in the target reference coordinate system.

[0039] In another optional implementation, the angle matrix used to characterize the direction of the water column axis in step S200 can be constructed by first describing the required rotation using a unit quaternion, and then converting it into a rotation matrix. Specifically, the process is as follows: First, based on the spray angle parameters, determine the rotation axis and rotation angle required to rotate the original spray direction of the spray gun (e.g., the Z-axis of the attached coordinate system) to the desired direction. Then, construct a unit quaternion using this rotation axis vector and rotation angle. Finally, calculate the corresponding 3x3 rotation matrix according to the standard conversion formula between the unit quaternion and the rotation matrix.

[0040] In this embodiment of the application, step S300 uses the spray gun position, spray angle, and coating thickness as the control parameters to be optimized, and constructs an objective function for the collaborative optimization of the control parameters, including the following steps C1-C2: C1: The coating thickness on which the objective function is based is obtained by multi-point measurement of the sprayed area on the insulator surface.

[0041] It should be noted that, in order to obtain information on the thickness distribution of the anti-flashover coating, the spray gun axis was perpendicular to the insulator during the spraying process. After spraying, the position of the intersection of the spray gun axis and the tangential plane of the insulator surface was marked. After the coating was completely dry, the geometric dimensions and coating thickness of the sprayed area were measured with the marked point as the origin, the major axis of the elliptical region as the x-axis, and the minor axis as the y-axis. Furthermore, for each measurement point, the measurement was performed three times, and the average value was taken as the measurement result for that point.

[0042] Preferably, the data obtained through the above method can accurately reflect the uniformity, integrity, and average thickness of the coating distribution on the insulator surface.

[0043] C2: The objective function is constructed to simultaneously minimize the spray gun position deviation, spray angle deviation, and the deviation between the coating thickness and the target value.

[0044] Specifically, the expression for the objective function is: In the formula: n is the total number of measurement data; r i r0 is the measured value of the coating thickness; θ is the ideal value of the required coating thickness; D is the spray angle θ; and D is the 3×1 UAV spray gun position matrix.

[0045] Preferably, this step directly addresses the problem that existing technologies cannot precisely optimize control parameters based on practical engineering aspects such as operational safety, coating quality, operational efficiency, and economy. By encoding objectives such as safety (maintaining safe distance through position control), quality (uniform coating thickness), and efficiency (reasonable spray gun movement and angle adjustment) into a computable model, global, system-level automatic parameter optimization becomes possible.

[0046] In an optional implementation, the objective function for collaboratively optimizing the control parameters in step S300 can also be achieved by defining a weighted mean square error function with the uniformity of coating coverage as its core. The specific process is as follows: First, collect coating thickness data from gridded measurement points on the insulator surface and calculate the difference between the thickness at each point and the target thickness; second, divide the spraying area into a core area and an edge area, and set weight coefficients for different areas reflecting their importance to insulation performance; finally, normalize and linearly weight the weighted mean square error of the thickness, the deviation between the actual movement trajectory of the spray gun and the ideal path (measured by path length and deviation), and the overall variation of the spray angle sequence, thereby forming a multi-objective optimization function that comprehensively evaluates coating uniformity, motion stability, and operational economy.

[0047] In another optional implementation, the objective function for co-optimizing the control parameters in step S300 can also be achieved by constructing a multi-objective cost function that integrates direct quality indicators and indirect economic costs. Specifically, the standard deviation of the coating thickness on the insulator surface after spraying (reflecting uniformity) and the percentage of points reaching the target thickness (reflecting coverage) are used as core quality indicators. Simultaneously, energy consumption costs proportional to the total travel distance of the spray gun, operational efficiency costs related to the total spraying time, and material costs based on the estimated paint consumption are introduced as economic indicators. Finally, by assigning different priority weights to each quality and economic indicator, they are combined into a quantifiable total cost function, thereby guiding the optimization algorithm to find the optimal parameter combination that saves as much time, energy, and material as possible while ensuring spraying quality.

[0048] In this embodiment of the application, in step S400, the spray angle of the water jet is dynamically compensated based on the change in the attitude of the UAV caused by the reduction of paint quality during the spraying process, and the objective function is updated based on the compensated angle.

[0049] It should be noted that during live-line spraying operations using drones, the overall weight of the drone decreases as the paint is consumed. This weight reduction causes the drone to shift at a certain angle relative to the spray axis, resulting in a shift in the water jet spraying angle θ. This method compensates for this shift by correcting the spraying angle θ as follows: In the formula: θ0 is the initial injection angle.

[0050] Therefore, the objective function for optimizing the control parameters of the UAV water jet spraying after compensation is: Preferably, the compensation mechanism in this step ensures that the system-recommended or used spray angle parameters will automatically take into account changes in the machine's attitude, whether at the beginning of the operation or when the paint is about to run out, thus guaranteeing the long-term accuracy and stability of the water column spatial orientation throughout the entire spraying cycle from start to finish.

[0051] In this embodiment of the application, step S500 uses an intelligent optimization algorithm to solve the updated objective function and outputs a combination of target spray water column control parameters including spray gun position, spray angle, and coating thickness, including the following steps E1-E3: It should be noted that the intelligent optimization algorithm is a genetic algorithm.

[0052] E1: Initialize a population containing multiple candidate parameter combinations.

[0053] E2: Calculate the fitness of individuals in the population based on the updated objective function.

[0054] E3: The population is iteratively updated through selection, crossover and mutation operations until the preset termination condition is met, and the combination of control parameters corresponding to the individual with the best fitness is output as the control parameter combination for the target spray water column.

[0055] Specifically, the preset termination condition is that the fitness value reaches its minimum value (<180), and the program terminates when n=10.

[0056] In an optional implementation, solving the updated objective function in step S500 can also be achieved using a particle swarm optimization algorithm. The specific process is as follows: First, each candidate combination of control parameters is encoded as a particle in a multi-dimensional space, and a group of random particles is initialized, assigned random positions and velocities. Second, the fitness value of each particle is calculated based on the updated objective function, and the individual's historical best position and the global best position of the entire swarm are recorded. Subsequently, in each iteration, the velocity and position of each particle are dynamically updated based on the individual and swarm optimal information, driving the entire particle swarm to move towards a solution region with better fitness. Finally, the search terminates when the number of iterations reaches a preset upper limit or the optimal solution no longer significantly improves over multiple generations, and the combination of control parameters corresponding to the globally optimal particle is output as the optimal solution.

[0057] In another optional implementation, the updated objective function is solved in step S500 using a simulated annealing algorithm. The specific process is as follows: First, a set of control parameters is randomly generated as the current solution, and a relatively high initial temperature is set. Second, in each iteration, a new solution is generated by randomly perturbing the neighborhood of the current solution, and the fitness difference between the new solution and the current solution is calculated based on the updated objective function. Then, the Metropolis acceptance criterion (accepting inferior solutions with a certain probability) determines whether to update the current solution. This probability decreases as the temperature gradually decreases, allowing for a broad exploration of the solution space in the early stages of the search process, while focusing on local improvement in the later stages. Finally, when the temperature drops to the termination threshold or the maximum number of iterations is reached, the currently found optimal combination of control parameters is output.

[0058] The following is a specific example to further illustrate this point: Step 1: Establish a mathematical model of the initial state of the UAV-electro-converted water jet: The position of the spray gun at a certain moment can be described by the spray gun's attached coordinate system at that moment, that is, expressed by the homogeneous transformation matrix G: Step 2: Construct the angle matrix of the water jet; Given a spray angle of θ = 30°, an ideal coating thickness of r0 = 1 mm, and a UAV spray gun position matrix of D = (x, y, z) = (1, 4, 2), the angle matrix is: Therefore, the homogeneous transformation matrix in step one is: Step 3: Construct the objective function for optimizing the control parameters of the UAV water jet spraying: Measurements were taken during the live-line spraying operation: ① The ten coating thickness data are 1, 2, 1.5, 0.5, 3, 2, 2, 1, 1, 1 mm.

[0059] ②The drone spray gun position matrix D is as follows: (0,10,3)(0,10,5)(0,11,5)(1,12,5)(1,12,8)(1,8,9)(5,8,9)(7,8,9)(6,9,9)(9,8,10).

[0060] ③ The spray angles are θ=0,20,30,50,20,30,35,45,0,60.

[0061] Taking into account the three factors of spray gun position, water jet angle, and coating thickness on the insulator surface after spraying, the objective function (fitness function) for optimizing the control parameters of UAV water jet spraying is as follows: Step 4: Compensate for the water column angle deviation caused by the reduction in paint quality during the spraying process, and form the objective function for optimizing the control parameters of the UAV spraying water column after compensation: To compensate for the slight angular shift of the drone relative to the spray axis caused by the reduced drone weight, the spray angle θ will be corrected. The objective function for optimizing the drone's water jet control parameters after adjustment and compensation is: Step 5: Use a genetic algorithm to solve for the optimal values ​​of the water jet control parameters of the objective function: The optimal control parameters for the sprayed water column, including the spraying position D, coating thickness r, and spraying angle, are obtained using a genetic algorithm. The specific solution process is as follows: a) Initialization: Set the generation counter.

[0062] b) Individual evaluation: Calculate group fitness.

[0063] c) Selection operation: Apply the selection operator to the population. This yields the 3rd, 6th, 7th, 8th, 9th, and 10th data points.

[0064] d) Crossover operation: Apply the crossover operator to the population. This yields the 3rd, 6th, and 7th data points.

[0065] e) Mutation operation: The mutation operator is applied to the population. After selection, crossover, and mutation operations, the next generation of the population is obtained.

[0066] f) Termination condition judgment: The individual with the minimum fitness value (<180) obtained during the evolution process is output as the optimal solution, and the calculation is terminated when it is the 10th iteration.

[0067] The optimal control parameters for the water jet spraying corresponding to the minimum fitness value individual obtained by the solution are the 6th data, that is, the coating thickness r=2mm, the spraying position D=(1,8,9), and the spraying angle=30 degrees are the optimal control parameter combination for the UAV spraying water jets.

[0068] In summary, the beneficial effects of the UAV-based method for optimizing and extracting control parameters for electrified water jet spraying are as follows: by constructing an initial state mathematical model and angle matrix for UAV-based water jet spraying, and using the spray gun position, spray angle, and coating thickness as the core optimization parameters, a theoretical basis is laid for achieving uniform and efficient spraying operations. Based on this, a dynamic angle compensation mechanism based on paint consumption is introduced, and a genetic algorithm is used to solve the compensated objective function, thereby obtaining the optimal combination of control parameters, which significantly improves the utilization rate of paint and the adaptability of parameters during the spraying process.

[0069] Example 3 illustrates a schematic scheme for optimizing and extracting control parameters of a UAV's electrified water jet spraying system. It should be noted that the technical solution of this UAV electrified water jet spraying system is based on the same concept as the aforementioned UAV electrified water jet spraying system optimization method. Details not described in detail in this example can be found in the description of the aforementioned UAV electrified water jet spraying system optimization method.

[0070] This embodiment also provides a system for optimizing and extracting control parameters for live water jet spraying from a UAV, including: A module is established to create an initial state mathematical model describing the spatial position and attitude of the spray gun by defining the spray gun attachment coordinate system and the homogeneous transformation matrix. The first construction module is used to construct an angle matrix that characterizes the direction of the water column axis based on the initial state mathematical model and the jet angle. The second construction module is used to construct an objective function for the collaborative optimization of the control parameters, using the spray gun position, spray angle and coating thickness as the control parameters to be optimized. The update module is used to dynamically compensate the spray angle of the water jet based on the change in the attitude of the UAV caused by the reduction of paint quality during the spraying process, and update the objective function based on the compensated angle. The output module is used to solve the updated objective function using an intelligent optimization algorithm, and outputs a combination of target spray water column control parameters including spray gun position, spray angle, and coating thickness.

[0071] This embodiment also provides an electronic device suitable for optimizing and extracting control parameters for live water jet spraying from a UAV, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the method for optimizing and extracting control parameters for live water jet spraying from a UAV as proposed in the above embodiment.

[0072] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for optimizing and extracting control parameters for live water jet spraying from a UAV as proposed in the above embodiments.

[0073] The storage medium proposed in this embodiment and the method for optimizing and extracting control parameters of UAV electrostatic spraying water column proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0074] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0075] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrified water jet spraying, characterized in that: include, By defining the spray gun attachment coordinate system and homogeneous transformation matrix, an initial state mathematical model describing the spatial position and attitude of the spray gun is established. Based on the initial state mathematical model and the jet angle, an angle matrix is ​​constructed to characterize the direction of the water column axis. Using the spray gun position, spray angle, and coating thickness as the control parameters to be optimized, an objective function is constructed to collaboratively optimize the control parameters. Based on the change in UAV attitude caused by the reduction in paint quality during the spraying process, the spraying angle of the water jet is dynamically compensated, and the objective function is updated based on the compensated angle. An intelligent optimization algorithm is used to solve the updated objective function, and the output is a combination of target spray water column control parameters including the spray gun position, spray angle and coating thickness.

2. The method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrified water jet spraying as described in claim 1, characterized in that: The process involves defining a spray gun attachment coordinate system and a homogeneous transformation matrix to establish an initial state mathematical model describing the spatial position and attitude of the spray gun, including: The spray gun attachment coordinate system takes the center of the UAV nozzle as the origin, determines the first coordinate axis with the direction of the nozzle axis, and determines the other two coordinate axes according to the right-hand rule. The homogeneous transformation matrix consists of a rotation matrix describing the UAV's attitude and a position vector describing the spray gun's position.

3. The method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrified water jet spraying as described in claim 2, characterized in that: The constructed angle matrix used to characterize the axial direction of the water column includes, When constructing the angle matrix, rotation and translation transformations are used in combination to correct the end spraying position error caused by the spray axis not being parallel to the expected direction.

4. The method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrified water jet spraying as described in claim 3, characterized in that: The objective function is constructed to simultaneously minimize the spray gun position deviation, spray angle deviation, and the deviation between the coating thickness and the target value.

5. The method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrified water jet spraying as described in any one of claims 1-4, characterized in that: The intelligent optimization algorithm is a genetic algorithm.

6. The method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrified water jet spraying as described in claim 5, characterized in that: The updated objective function is solved using a smart genetic algorithm, including: Initialize a population containing multiple candidate parameter combinations; The fitness of individuals in the population is calculated based on the updated objective function; The population is iteratively updated through selection, crossover, and mutation operations until a preset termination condition is met. The combination of control parameters corresponding to the individual with the best fitness is then output as the control parameter combination for the target water jet.

7. The method for optimizing and extracting control parameters of an unmanned aerial vehicle (UAV) for electrified water jet spraying as described in claim 6, characterized in that: The coating thickness on which the objective function is based is obtained by multi-point measurement of the sprayed area on the surface of the insulator.

8. A system for optimizing and extracting control parameters for electrostatic spraying water jets from unmanned aerial vehicles (UAVs), employing the method described in any one of claims 1-7, characterized in that... include: A module is established to create an initial state mathematical model describing the spatial position and attitude of the spray gun by defining the spray gun attachment coordinate system and the homogeneous transformation matrix. The first construction module is used to construct an angle matrix representing the direction of the water column axis based on the initial state mathematical model and the jet angle. The second construction module is used to construct an objective function for the coordinated optimization of the control parameters, using the spray gun position, spray angle and coating thickness as the control parameters to be optimized. The update module is used to dynamically compensate the spray angle of the water jet based on the change in the attitude of the UAV caused by the reduction of paint quality during the spraying process, and update the objective function based on the compensated angle. The output module is used to solve the updated objective function using an intelligent optimization algorithm, and outputs a combination of target spray water column control parameters including the spray gun position, spray angle, and coating thickness.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images