A multi-objective optimization method for unmanned aerial vehicle intelligent inspection of photovoltaic systems

Abstract

This invention discloses a multi-objective optimization method for intelligent drone inspection of photovoltaic systems, comprising: based on the 3D point cloud of the photovoltaic system, defining the constraints that the drone inspection path should meet for obstacle avoidance and image acquisition; based on the drone's endurance, defining the constraints that the inspection duration should meet; analyzing the influence mechanism of environmental factors on the temperature characteristics of photovoltaic modules and setting environmental factor optimization objectives; combining drone flight parameters and wind speed to set image clarity optimization objectives; combining inspection area and inspection duration to set inspection efficiency optimization objectives; and, under the premise of meeting the constraints, comprehensively considering environmental factors, image clarity, and inspection efficiency, solving the multi-objective optimization problem of intelligent drone inspection for photovoltaic systems. This invention combines image analysis technology and panoramic stitching technology to realize fault diagnosis and location of photovoltaic arrays, combiner boxes, inverters, and power transmission and transformation equipment, providing important basis for intelligent operation and maintenance of photovoltaic systems.

Description

Technical Field

[0001] This invention relates to a multi-objective optimization technology for intelligent inspection of photovoltaic systems using unmanned aerial vehicles (UAVs), belonging to the field of inspection and maintenance technology for photovoltaic power generation systems. Background Technology

[0002] Solar energy is an important new energy source with advantages such as wide distribution, renewability, cleanliness, low carbon emissions, safety, and high efficiency. Photovoltaic power generation is the main form of utilizing solar energy, and in recent years, the installed capacity of photovoltaic systems both domestically and internationally has continued to grow. A photovoltaic system typically includes photovoltaic arrays, combiner boxes, inverters, and transmission and distribution equipment. Photovoltaic arrays consist of several photovoltaic modules, and during operation, they may experience internal defects, abnormal shading, wiring faults, etc. Combiner boxes, inverters, and transmission and distribution equipment may experience abnormal temperatures, power losses, communication failures, etc. Timely diagnosis of various faults and the implementation of effective operation and maintenance measures help improve the power generation and stability of photovoltaic systems.

[0003] Fault diagnosis methods for photovoltaic (PV) systems mainly include condition monitoring methods based on electrical data and alarm information, and visual analysis methods based on image data. Compared to condition monitoring methods, visual analysis methods can obtain more intuitive diagnostic results and achieve more accurate fault classification and location. It is worth noting that visual analysis methods rely on high-quality image acquisition. Currently, drone inspection is an effective way to acquire images for large-scale PV systems. Therefore, a drone inspection strategy for PV systems is crucial.

[0004] Existing technologies have studied methods for generating inspection paths using unmanned aerial vehicles (UAVs) and analyzed the correlation between image sharpness and UAV flight altitude and camera field of view. However, these technologies have not fully considered the impact of flight speed and wind speed on image jitter. Furthermore, environmental factors significantly affect the temperature characteristics of photovoltaic modules, and the multi-objective optimization problem that comprehensively considers environmental factors, image sharpness, and inspection efficiency remains unsolved. How to set reasonable optimization objectives and achieve multi-objective optimization while satisfying constraints is an important issue that needs to be considered for UAV inspection of photovoltaic systems. Summary of the Invention

[0005] Technical Problem: This invention aims to address the shortcomings of existing technologies by comprehensively considering the constraints of UAV inspection paths and inspection durations, as well as optimization objectives such as environmental factors, image clarity, and inspection efficiency, to provide a multi-objective optimization method for intelligent UAV inspection of photovoltaic systems.

[0006] Technical solution: The present invention provides a multi-objective optimization method for intelligent inspection of photovoltaic systems using unmanned aerial vehicles (UAVs), comprising the following steps:

[0007] S1: Based on the 3D point cloud of the photovoltaic system, give the constraints that the UAV inspection path should meet for obstacle avoidance and image acquisition.

[0008] S2: Based on the drone's battery life, provide the constraints that the inspection duration should meet;

[0009] S3: Analyze the influence mechanism of environmental factors on the temperature characteristics of photovoltaic modules and set optimization objectives for environmental factors;

[0010] S4: Combine drone flight parameters and wind speed to set image clarity optimization targets;

[0011] S5: Set inspection efficiency optimization targets by combining inspection area and inspection duration;

[0012] S6: Under the premise of satisfying the constraints, comprehensively consider environmental factors, image clarity, and inspection efficiency to solve the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

[0013] Furthermore, in step S1, based on the 3D point cloud of the photovoltaic system, the photovoltaic array, combiner box, inverter, power transmission and transformation equipment, and obstacles are identified; n represents the number of ordered waypoints on the UAV inspection path, f i Let m represent the i-th waypoint; m represents the number of obstacle feature points; b j Let j represent the j-th feature point of an obstacle. The obstacle avoidance constraints that the UAV inspection path should satisfy are as follows:

[0014]

[0015] Where i = 1, 2, ..., n-1; j = 1, 2, ..., m; δ represents the distance threshold for obstacle avoidance.

[0016] Furthermore, in step S1, the inspection area involving the photovoltaic array, combiner box, inverter, and power transmission and transformation equipment is U, with an east-west span of [missing information]. The north-south span is The drone's inspection altitude relative to the photovoltaic system is h, the total flight path length is l, and the camera's diagonal field of view is DFOV. The drone's inspection path should meet the following constraints for image acquisition:

[0017]

[0018] Furthermore, in step S2, the UAV's endurance is τ, its flight speed is v, the adjustment time at each waypoint is t0, the return-to-home time is τ0, and the inspection duration should meet the following constraints:

[0019]

[0020] Furthermore, in step S3, irradiance affects the heat generated by the photovoltaic module per unit time, ambient temperature affects the electrical power of the silicon wafer, wind speed affects the heat convection between the photovoltaic module and the surrounding environment, and reflection and projection interfere with the temperature characteristics of the photovoltaic module; irradiance is G, and ambient temperature is T. a Wind speed is W, environmental factor optimization objective is O A (G,T a The following (W,R,S) are as follows:

[0021]

[0022] Where η represents the temperature coefficient of the photovoltaic module's maximum power; T a,0 Indicates the ambient temperature under standard conditions; k0, k1, μ1, μ2 are constants; R represents reflective markings, S represents projected markings:

[0023]

[0024] Furthermore, in step S4, the drone's flight altitude affects the size of the area involved by a unit pixel in the image, and the drone's flight speed and wind speed affect the degree of image jitter; the image sharpness optimization target O D (h,v,W) are as follows:

[0025]

[0026] Where c is a constant.

[0027] Furthermore, in step S5, the photovoltaic installed capacity of the inspection area is P, the inspection time depends on the waypoint, route, and flight speed of the UAV; the inspection efficiency optimization objective is O. E (l,v,n) are as follows:

[0028]

[0029] Where σ1 and σ2 are constants.

[0030] Furthermore, in step S6, the optimization objectives, taking into account environmental factors, image clarity, and inspection efficiency, are as follows: O M (G,T a ,W,R,S,h,v,l,n)=λ1·O A (G,T a ,W,R,S)+λ2·O D (h,v,W)+λ3·O E (l,v,n)

[0031] Where λ1, λ2, and λ3 are constants.

[0032] Furthermore, in step S6, the comprehensive optimization target O will be... M (G,T a The decomposition of W, R, S, h, v, l, n into mutually independent sub-objectives is as follows:

[0033] O M (G,T a ,W,R,S,h,v,l,n)=O1(h,v,l,n)+O2(G,T a ,W,R,S)

[0034] Among them, O1(h,v,l,n) is related to flight parameters and inspection path, and O2(G,T) is related to inspection path. a W, R, S) are related to environmental factors:

[0035]

[0036]

[0037] Furthermore, in step S6, under the constraints of obstacle avoidance and image acquisition on the inspection path, and the constraint of endurance on the inspection duration, the maximum value of the optimization objective O1(h,v,l,n) is solved; within a given time range, the maximum value of the optimization objective O2(G,T) is solved. a The maximum value of (,W,R,S); sub-objectives O1(h,v,l,n) and O2(G,T) a When W, R, and S respectively reach their maximum values, the comprehensive optimization objective O is... M (G,T a The maximum value of ,W,R,S,h,v,l,n is obtained, which can be used as the optimal solution to the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

[0038] Beneficial Effects: This invention provides a multi-objective optimization method for intelligent drone inspection of photovoltaic systems. It comprehensively considers constraints on drone inspection paths and durations, as well as optimization objectives such as environmental factors, image clarity, and inspection efficiency, to generate an intelligent drone inspection strategy for photovoltaic systems, achieving high-quality image acquisition. This method can combine image analysis and panoramic stitching technologies to achieve fault diagnosis and location of photovoltaic arrays, combiner boxes, inverters, and power transmission and transformation equipment, providing important data for the intelligent operation and maintenance of photovoltaic systems. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the overall process of an embodiment;

[0040] Figure 2 This is a schematic diagram illustrating the change in irradiance over time.

[0041] Figure 3This is a schematic diagram illustrating the change of ambient temperature over time.

[0042] Figure 4 This is a schematic diagram illustrating the change in wind speed over time.

[0043] Figure 5 This diagram illustrates the influence of environmental factors on the temperature characteristics of photovoltaic modules, where (a) represents an irradiance of 800 W / m². 2 (a) Temperature characteristics of photovoltaic modules under ambient temperature of 20℃ and wind speed of 1m / s; (b) Temperature characteristics of photovoltaic modules under irradiance of 100W / m 2 Temperature characteristics of photovoltaic modules under ambient temperature of 10℃ and wind speed of 5m / s. Detailed Implementation

[0044] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings; however, the scope of protection of the present invention is not limited to the described embodiments. Figure 1 As shown in the figure, a multi-objective optimization method for intelligent inspection of photovoltaic systems using unmanned aerial vehicles (UAVs) in this embodiment includes the following steps:

[0045] S1: Based on the 3D point cloud of the photovoltaic system, give the constraints that the UAV inspection path should meet for obstacle avoidance and image acquisition.

[0046] In this embodiment, based on the 3D point cloud of the photovoltaic system, photovoltaic arrays, combiner boxes, inverters, power transmission and transformation equipment, and obstacles are identified; n represents the number of ordered waypoints on the UAV inspection path, and f i Let m represent the i-th waypoint; m represents the number of obstacle feature points; b j Let j represent the j-th feature point of an obstacle. The obstacle avoidance constraints that the UAV inspection path should satisfy are as follows:

[0047] Where i = 1, 2, ..., n-1; j = 1, 2, ..., m; δ represents the distance threshold for obstacle avoidance.

[0048] The inspection area involving photovoltaic arrays, combiner boxes, inverters, and power transmission and transformation equipment is U, with an east-west span of [missing information]. The north-south span is The drone's inspection altitude relative to the photovoltaic system is h, the total flight path length is l, and the camera's diagonal field of view is DFOV. The drone's inspection path should meet the following constraints for image acquisition:

[0049]

[0050] S2: Based on the drone's battery life, provide the constraints that the inspection duration should meet.

[0051] In this embodiment, the drone's endurance is τ, its flight speed is v, the adjustment time at each waypoint is t0, the return-home allowance is τ0, and the inspection duration should meet the following constraints:

[0052]

[0053] S3: Analyze the influence mechanism of environmental factors on the temperature characteristics of photovoltaic modules and set optimization objectives for environmental factors.

[0054] In this embodiment, irradiance affects the heat generated by the photovoltaic module per unit time, ambient temperature affects the electrical power of the silicon wafer, wind speed affects the heat convection between the photovoltaic module and the surrounding environment, and reflection and projection interfere with the temperature characteristics of the photovoltaic module; the irradiance is G, and the ambient temperature is T. a Wind speed is W, environmental factor optimization objective is O A (G,T a The following (W,R,S) are as follows:

[0055]

[0056] Where η represents the temperature coefficient of the photovoltaic module's maximum power; T a,0 Indicates the ambient temperature under standard conditions; k0, k1, μ1, μ2 are constants; R represents reflective markings, S represents projected markings:

[0057]

[0058] S4: Combine drone flight parameters and wind speed to set image clarity optimization targets.

[0059] In this embodiment, the drone's flight altitude affects the size of the area represented by a single pixel in the image, while the drone's flight speed and wind speed affect the degree of image jitter; the image sharpness optimization target O D (h,v,W) are as follows:

[0060]

[0061] Where c is a constant.

[0062] S5: Set inspection efficiency optimization targets by combining inspection area and inspection duration.

[0063] In this embodiment, the photovoltaic installed capacity of the inspection area is P, the inspection time depends on the UAV's waypoints, flight paths, and flight speed; the inspection efficiency optimization objective is O. E (l,v,n) are as follows:

[0064]

[0065] Where σ1 and σ2 are constants.

[0066] S6: Under the premise of satisfying the constraints, comprehensively consider environmental factors, image clarity, and inspection efficiency to solve the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

[0067] In this embodiment, the optimization objectives, taking into account environmental factors, image clarity, and inspection efficiency, are as follows: O M (G,T a ,W,R,S,h,v,l,n)=λ1·O A (G,T a ,W,R,S)+λ2·O D (h,v,W)+λ3·O E (l,v,n)

[0068] Where λ1, λ2, and λ3 are constants.

[0069] The comprehensive optimization objective O M (G,T a The decomposition of W, R, S, h, v, l, n) into mutually independent sub-objectives is as follows: O M (G,T a ,W,R,S,h,v,l,n)=O1(h,v,l,n)+O2(G,T a ,W,R,S)

[0070] Among them, O1(h,v,l,n) is related to flight parameters and inspection path, and O2(G,T) is related to inspection path. a W, R, S) are related to environmental factors:

[0071]

[0072] Given that the inspection path satisfies the constraints of obstacle avoidance and image acquisition, and the inspection duration satisfies the constraint of endurance, solve for the maximum value of the optimization objective O1(h,v,l,n); within a given time range, solve for the maximum value of the optimization objective O2(G,T). a The maximum value of (W, R, S). In this embodiment, Figure 2 This is a schematic diagram illustrating the change in irradiance over time. Figure 3 This is a schematic diagram illustrating the change of ambient temperature over time.

[0073] Figure 4 This is a schematic diagram illustrating wind speed changes over time. Sub-targets O1(h,v,l,n) and O2(G,T) a When W, R, and S respectively reach their maximum values, the comprehensive optimization objective O is... M (G,T aThe maximum value of ,W,R,S,h,v,l,n is obtained, which can be used as the optimal solution to the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

[0074] Figure 5 This is a schematic diagram illustrating the influence of environmental factors on the temperature characteristics of a photovoltaic module according to an embodiment of the present invention. In this embodiment, the temperature characteristics of a defective photovoltaic module are extracted using infrared images. Figure 5 (a) Irradiance of 800 W / m 2 Temperature characteristics of photovoltaic modules under ambient temperature of 20℃ and wind speed of 1m / s; Figure 5 (b) Irradiance of 100 W / m 2 Temperature characteristics of photovoltaic modules under ambient temperature of 10℃ and wind speed of 5m / s.

[0075] Finally, 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 the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-objective optimization method for intelligent inspection of photovoltaic systems using unmanned aerial vehicles (UAVs), characterized in that: The steps are as follows: S1: Based on the 3D point cloud of the photovoltaic system, give the constraints that the UAV inspection path should meet for obstacle avoidance and image acquisition. S2: Based on the drone's battery life, provide the constraints that the inspection duration should meet; S3: Analyze the influence mechanism of environmental factors on the temperature characteristics of photovoltaic modules and set environmental factor optimization targets; S4: Combine UAV flight parameters and wind speed to set image clarity optimization targets; S5: Set inspection efficiency optimization targets by combining inspection area and inspection duration; S6: Under the premise of satisfying the constraints, and taking into account environmental factors, image clarity, and inspection efficiency, solve the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems. In step S3, irradiance affects the heat generated by the photovoltaic module per unit time, ambient temperature affects the electrical power of the silicon wafer, wind speed affects the heat convection between the photovoltaic module and the surrounding environment, and reflection and projection interfere with the temperature characteristics of the photovoltaic module; irradiance is The ambient temperature is Wind speed is Environmental factors optimization objectives as follows: in, The temperature coefficient representing the maximum power of a photovoltaic module; Indicates the ambient temperature under standard conditions; , , , It is a constant; Indicates reflective markings, Indicates projection markers: In the step S4, the flight height of the unmanned aerial vehicle affects the size of the area involved by a unit pixel in the image, and the flight speed of the unmanned aerial vehicle and the wind speed affect the shaking degree of the image; and the image definition optimization target As follows: wherein, is a constant, is the inspection height of the UAV relative to the photovoltaic system, DFOV is the diagonal field of view angle of the camera, is the flight speed of the UAV.

2. The multi-objective optimization method for intelligent inspection of photovoltaic systems using unmanned aerial vehicles (UAVs) according to claim 1, characterized in that: In step S1, the photovoltaic array, combiner box, inverter, power transmission and transformation equipment, and obstacles are identified based on the three-dimensional point cloud of the photovoltaic system. This indicates the number of ordered waypoints along the drone's inspection path. Indicates the first One waypoint; Indicates the number of feature points of the obstacle. The first obstacle represents the first obstacle. For each feature point, the drone inspection path should meet the following obstacle avoidance constraints: wherein ; ; represents a distance threshold for obstacle avoidance.

3. The multi-objective optimization method for intelligent inspection of photovoltaic systems using unmanned aerial vehicles (UAVs) according to claim 2, characterized in that: In step S1, the inspection area involving the photovoltaic array, combiner box, inverter, and power transmission and transformation equipment is [area missing]. The east-west span is The north-south span is The inspection altitude of the drone relative to the photovoltaic system is The total length of the route is The camera's diagonal field of view is DFOV, and the UAV inspection path should meet the following constraints for image acquisition: 。 4.The method of claim 3, wherein: In step S2, the drone's flight time is Flight speed is The adjustment time for the drone at each waypoint is The return flight time is The following constraints must be met for the inspection duration: 。 5. The multi-objective optimization method for intelligent inspection of unmanned aerial vehicles oriented to photovoltaic systems according to claim 4, characterized in that: In step S5, the photovoltaic installed capacity of the inspection area is: The inspection time depends on the drone's waypoints, routes, and flight speed; Patrol efficiency optimization objective As follows: wherein with is constant. 6.The method of claim 5, wherein: In step S6, the optimization objectives, taking into account environmental factors, image clarity, and inspection efficiency, are as follows: wherein , , is a constant.

7. The method of claim 6, wherein: In the step S6, the comprehensive optimization objective is decomposed into the following mutually independent sub-objectives: wherein, related to flight parameters, inspection routes, related to environmental factors: 。 8.The method of claim 7, wherein: In step S6, under the conditions that the inspection path satisfies the constraints of obstacle avoidance and image acquisition, and the inspection time satisfies the constraints of endurance, the optimization objective is solved. Find the maximum value; within a given time frame, solve the optimization objective. The maximum value; sub-target and When each value is obtained, the overall optimization objective is... The maximum value is obtained, which can be used as the optimal solution to the multi-objective optimization problem of UAV intelligent inspection of photovoltaic systems.

Images