Unmanned aerial vehicle intelligent inspection multi-objective optimization method for photovoltaic system

Abstract

The invention discloses an unmanned aerial vehicle intelligent inspection multi-objective optimization method for a photovoltaic system, and the method comprises the steps: giving out the constraint conditions that an unmanned aerial vehicle inspection path should meet the obstacle avoidance and image collection according to the three-dimensional point cloud of the photovoltaic system; according to the endurance condition of the unmanned aerial vehicle, giving a constraint condition which should be met by the inspection duration; analyzing the influence mechanism of the environmental factors on the temperature characteristics of the photovoltaic module, and setting an environmental factor optimization target; setting an image definition optimization target by combining the flight parameters and the wind speed of the unmanned aerial vehicle; setting an inspection efficiency optimization target in combination with the inspection area and the inspection duration; and on the premise of meeting constraint conditions, comprehensively considering environmental factors, image definition and inspection efficiency, and solving a photovoltaic system-oriented unmanned aerial vehicle intelligent inspection multi-objective optimization problem. According to the method, the image analysis technology and the panoramic splicing technology are combined, fault diagnosis and positioning of the photovoltaic array, the combiner box, the inverter and the power transmission and transformation equipment are achieved, and an important basis is provided for intelligent operation and maintenance of a photovoltaic system.

Description

Technical Field

[0001] The present invention relates to a multi-objective optimization technology for intelligent inspection of unmanned aerial vehicles (UAVs) for photovoltaic systems, and belongs to the technical field of inspection and operation and maintenance of photovoltaic power generation systems. Background Art

[0002] Solar energy is an important new energy source with the advantages of being widely distributed, renewable, clean, low-carbon, safe and efficient. Photovoltaic power generation is the main form of utilizing solar energy. In recent years, the installed capacity of photovoltaic power generation has continued to grow at home and abroad. Photovoltaic systems usually include photovoltaic arrays, combiner boxes, inverters, power transmission and transformation equipment, etc. Photovoltaic arrays are composed of several photovoltaic modules, and internal defects, abnormal shading, wiring faults, etc. may occur during operation. Combiner boxes, inverters, and power transmission and transformation equipment may experience abnormal temperatures, power losses, and communication failures. Timely diagnosis of various faults and taking effective operation and maintenance measures will help improve the power generation and stability of photovoltaic systems.

[0003] The fault diagnosis methods of photovoltaic systems mainly include condition monitoring methods based on electrical data and alarm information, and visual analysis methods based on image data. Compared with 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. At present, drone inspection is an effective way to acquire images of large-scale photovoltaic systems. Therefore, drone inspection strategies for photovoltaic systems are crucial.

[0004] The existing technology has studied the generation method of drone inspection paths and analyzed the correlation between image clarity and drone flight altitude and camera field of view. However, the existing technology has not fully considered the impact of flight speed and wind speed on image jitter. In addition, environmental factors also have a significant impact on the temperature characteristics of photovoltaic modules. The multi-objective optimization problem that comprehensively considers environmental factors, image clarity, and inspection efficiency has not yet been solved. How to set reasonable optimization goals and achieve multi-objective optimization while satisfying constraints is an important issue that needs to be considered for drone inspections of photovoltaic systems. Summary of the invention

[0005] Technical problem: The present invention aims to solve the deficiencies in the prior art, comprehensively consider the constraints of the UAV inspection path and inspection duration, as well as the optimization goals of environmental factors, image clarity, and inspection efficiency, and provide a multi-objective optimization method for UAV intelligent inspection of photovoltaic systems.

[0006] Technical solution: A multi-objective optimization method for intelligent inspection of photovoltaic systems by drones of the present invention comprises the following steps in sequence:

[0007] S1: Based on the 3D point cloud of the photovoltaic system, the constraint conditions of obstacle avoidance and image acquisition that the inspection path of the UAV should meet are given respectively;

[0008] S2: According to the drone's endurance, give the constraints that the inspection duration should meet;

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

[0010] S4: Combine the UAV flight parameters and wind speed to set the image clarity optimization target;

[0011] S5: Set inspection efficiency optimization goals based on inspection areas and inspection duration;

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

[0013] Furthermore, in step S1, based on the three-dimensional 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 inspection path of the drone, and f i represents the i-th waypoint; m represents the number of obstacle feature points, b j The jth feature point represents the obstacle. The obstacle avoidance constraints that the drone 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 of ​​the photovoltaic array, combiner box, inverter, and power transmission and transformation equipment is U, and the east-west span is The north-south span is The inspection height of the drone relative to the photovoltaic system is h, the total length of the route is l, the diagonal field of view of the camera is DFOV, and the inspection path of the drone should meet the following image acquisition constraints:

[0017]

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

[0019]

[0020] Furthermore, in step S3, the irradiance affects the heat generated by the photovoltaic module per unit time, the ambient temperature affects the electric power of the silicon wafer, the wind speed affects the heat convection between the photovoltaic module and the surrounding environment, and the reflection and projection will 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 target is O A (G,T a ,W,R,S) are as follows:

[0021]

[0022] Where η represents the temperature coefficient of the maximum power of the photovoltaic module; T a,0 Indicates the ambient temperature under standard conditions; k0, k1, μ1, μ2 are constants; R indicates a reflective mark, and S indicates a projected mark:

[0023]

[0024] Furthermore, in step S4, the flying height of the drone affects the size of the area involved by the unit pixel in the image, and the flying speed of the drone and the wind speed affect the degree of image jitter; the image clarity 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, and the inspection time depends on the waypoint, route, and flight speed of the drone; the inspection efficiency optimization target O E (l,v,n) is as follows:

[0028]

[0029] Among them, σ1 and σ2 are constants.

[0030] Furthermore, in step S6, the optimization goal taking into account environmental factors, image clarity, and inspection efficiency is as follows: 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] Among them, λ1, λ2, λ3 are constants.

[0032] Furthermore, in step S6, the comprehensive optimization target O M (G,T a ,W,R,S,h,v,l,n) is decomposed into independent sub-goals 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 paths, O2(G,T a ,W,R,S) are related to environmental factors:

[0035]

[0036]

[0037] Furthermore, in step S6, the maximum value of the optimization target O1(h, v, l, n) is solved when the inspection path meets the constraint conditions of obstacle avoidance and image acquisition, and the inspection duration meets the constraint conditions of endurance; within a given time range, the optimization target O2(G, T a ,W,R,S); the maximum value of sub-goals O1(h,v,l,n) and O2(G,T a , W, R, S) respectively achieve the maximum value, the comprehensive optimization goal O M (G,T a ,W,R,S,h,v,l,n) also achieves the maximum value, which can be used as the optimal solution to the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

[0038] Beneficial effects: The present invention provides a multi-objective optimization method for intelligent inspection of unmanned aerial vehicles for photovoltaic systems, which comprehensively considers the constraints of the inspection path and inspection duration of unmanned aerial vehicles, as well as the optimization goals of environmental factors, image clarity, and inspection efficiency, and generates an intelligent inspection strategy for unmanned aerial vehicles for photovoltaic systems to achieve high-quality image acquisition. This method can combine image analysis technology with panoramic stitching technology to achieve fault diagnosis and positioning of photovoltaic arrays, junction boxes, inverters, and power transmission and transformation equipment, providing an important basis for the intelligent operation and maintenance of photovoltaic systems. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0040] Figure 2 Schematic diagram of irradiance variation over time;

[0041] Figure 3It is a schematic diagram of the change of ambient temperature over time;

[0042] Figure 4 Schematic diagram of wind speed changing with time;

[0043] Figure 5 Schematic diagram of the impact of environmental factors on the temperature characteristics of photovoltaic modules, where (a) is the irradiance of 800W / m 2 , the temperature characteristics of the photovoltaic module under the condition of ambient temperature of 20℃ and wind speed of 1m / s; (b) is the irradiance of 100W / m 2 , temperature characteristics of photovoltaic modules under ambient temperature of 10℃ and wind speed of 5m / s. DETAILED DESCRIPTION

[0044] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the embodiments. Figure 1 As shown, a multi-objective optimization method for intelligent inspection of a photovoltaic system by a drone in this embodiment includes the following steps in sequence:

[0045] S1: Based on the 3D point cloud of the photovoltaic system, the constraint conditions of obstacle avoidance and image acquisition that the UAV inspection path should meet are given respectively.

[0046] In this embodiment, based on the three-dimensional 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 inspection path of the drone, and f i represents the i-th waypoint; m represents the number of obstacle feature points, b j The jth feature point represents the obstacle. The obstacle avoidance constraints that the drone 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 of ​​the photovoltaic array, combiner box, inverter, and power transmission and transformation equipment is U, with a span of The north-south span is The inspection height of the drone relative to the photovoltaic system is h, the total length of the route is l, the diagonal field of view of the camera is DFOV, and the inspection path of the drone should meet the following image acquisition constraints:

[0049]

[0050] S2: According to the UAV's endurance, give the constraints that the inspection duration should meet.

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

[0052]

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

[0054] In this embodiment, the irradiance affects the heat generated by the photovoltaic module per unit time, the ambient temperature affects the electric power of the silicon wafer, the wind speed affects the heat convection between the photovoltaic module and the surrounding environment, and the reflection and projection will 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 target is O A (G,T a ,W,R,S) are as follows:

[0055]

[0056] Where η represents the temperature coefficient of the maximum power of the photovoltaic module; T a,0 Indicates the ambient temperature under standard conditions; k0, k1, μ1, μ2 are constants; R indicates a reflective mark, and S indicates a projected mark:

[0057]

[0058] S4: Combine the UAV flight parameters and wind speed to set the image clarity optimization target.

[0059] In this embodiment, the flying height of the drone affects the size of the area involved by the unit pixel in the image, and the flying speed of the drone and the wind speed affect the degree of image jitter; the image clarity optimization target is D (h,v,W) are as follows:

[0060]

[0061] Where c is a constant.

[0062] S5: Set inspection efficiency optimization goals based on the inspection area and inspection duration.

[0063] In this embodiment, the photovoltaic installed capacity of the inspection area is P, and the inspection time depends on the waypoint, route, and flight speed of the drone; the inspection efficiency optimization target is O. E (l,v,n) is as follows:

[0064]

[0065] Among them, σ1 and σ2 are constants.

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

[0067] In this embodiment, the optimization goals taking into account environmental factors, image clarity, and inspection efficiency are as follows: 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] Among them, λ1, λ2, λ3 are constants.

[0069] The comprehensive optimization goal O M (G,T a ,W,R,S,h,v,l,n) is decomposed into independent sub-goals as follows: 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 paths, O2(G,T a ,W,R,S) are related to environmental factors:

[0071]

[0072] Under the constraints that the inspection path meets the obstacle avoidance and image acquisition constraints, and the inspection duration meets the endurance constraints, solve the maximum value of the optimization target O1(h,v,l,n); within a given time range, solve the optimization target O2(G,T a ,W,R,S). In this embodiment, Figure 2 Schematic diagram of irradiance variation over time; Figure 3 It is a schematic diagram of the change of ambient temperature over time;

[0073] Figure 4 The wind speed changes over time. a , W, R, S) respectively achieve the maximum value, the comprehensive optimization goal O M (G,T a,W,R,S,h,v,l,n) also achieves the maximum value, which can be used as the optimal solution to the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

[0074] Figure 5 A schematic diagram of the effect of environmental factors on the temperature characteristics of photovoltaic modules provided by an embodiment of the present invention. In this embodiment, the temperature characteristics of a defective photovoltaic module are extracted through infrared images. Figure 5 (a) Irradiance 800W / m 2 , the temperature characteristics of photovoltaic modules under the condition of ambient temperature of 20℃ and wind speed of 1m / s; Figure 5 (b) Irradiance is 100W / 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 rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements 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 by unmanned aerial vehicles, characterized by: The following steps are included in sequence: S1: Based on the 3D point cloud of the photovoltaic system, the constraint conditions of obstacle avoidance and image acquisition that the inspection path of the UAV should meet are given respectively; S2: According to the drone's endurance, give the constraints that the inspection duration should meet; S3: Analyze the impact mechanism of environmental factors on the temperature characteristics of photovoltaic modules and set the optimization goals of environmental factors; S4: Combine the UAV flight parameters and wind speed to set the image clarity optimization target; S5: Set inspection efficiency optimization goals based on inspection areas and inspection duration; S6: Under the premise of satisfying the constraints, environmental factors, image clarity, and inspection efficiency are comprehensively considered to solve the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

2. The multi-objective optimization method for intelligent inspection of photovoltaic systems by unmanned aerial vehicles according to claim 1 is characterized in that: In step S1, based on the three-dimensional 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 inspection path of the drone, and f i represents the i-th waypoint; m represents the number of obstacle feature points, b j The jth feature point represents the obstacle. The obstacle avoidance constraints that the drone inspection path should satisfy are as follows: Where i = 1, 2, ..., n-1; j = 1, 2, ..., m; δ represents the distance threshold for obstacle avoidance.

3. The multi-objective optimization method for intelligent inspection of photovoltaic systems by unmanned aerial vehicles according to claim 2 is characterized in that: In step S1, the inspection area of ​​the photovoltaic array, combiner box, inverter, and power transmission and transformation equipment is U, and the east-west span is The north-south span is The inspection height of the drone relative to the photovoltaic system is h, the total length of the route is l, the diagonal field of view of the camera is DFOV, and the inspection path of the drone should meet the following image acquisition constraints:

4. The multi-objective optimization method for intelligent inspection of photovoltaic systems by unmanned aerial vehicles according to claim 3 is characterized by: In step S2, the drone's flight time is τ, the flight speed is v, the drone's adjustment time at each waypoint is t0, the return reserved time is τ0, and the inspection duration should meet the following constraints:

5. The multi-objective optimization method for intelligent inspection of photovoltaic systems by unmanned aerial vehicles according to claim 4 is characterized in that: In step S3, the irradiance affects the heat generated by the photovoltaic module per unit time, the ambient temperature affects the electric power of the silicon wafer, the wind speed affects the heat convection between the photovoltaic module and the surrounding environment, and the reflection and projection will 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 target is O A (G,T a ,W,R,S) are as follows: Where η represents the temperature coefficient of the maximum power of the photovoltaic module; T a,0 Indicates the ambient temperature under standard conditions; k0, k1, μ1, μ2 are constants; R indicates a reflective mark, and S indicates a projected mark:

6. The multi-objective optimization method for intelligent inspection of photovoltaic systems by unmanned aerial vehicles according to claim 5 is characterized by: In step S4, the flying height of the drone affects the size of the area involved by the unit pixel in the image, and the flying speed of the drone and the wind speed affect the degree of image jitter; the image clarity optimization target is D (h,v,W) are as follows: Where c is a constant.

7. The multi-objective optimization method for unmanned aerial vehicle intelligent inspection of photovoltaic systems according to claim 6 is characterized by: In step S5, the photovoltaic installed capacity of the inspection area is P, and the inspection time depends on the waypoint, route, and flight speed of the drone; the inspection efficiency optimization target is O E (l,v,n) is as follows: Among them, σ1 and σ2 are constants.

8. The multi-objective optimization method for intelligent inspection of photovoltaic systems by unmanned aerial vehicles according to claim 7 is characterized in that: In step S6, the optimization goals 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) Among them, λ1, λ2, λ3 are constants.

9. The multi-objective optimization method for unmanned aerial vehicle intelligent inspection of photovoltaic systems according to claim 8 is characterized by: In step S6, the comprehensive optimization target O M (G,T a ,W,R,S,h,v,l,n) is decomposed into independent sub-goals 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) Among them, O1(h,v,l,n) is related to flight parameters and inspection paths, O2(G,T a ,W,R,S) are related to environmental factors:

10. The multi-objective optimization method for unmanned aerial vehicle intelligent inspection of photovoltaic systems according to claim 9, characterized in that: In step S6, the maximum value of the optimization target O1(h,v,l,n) is solved when the inspection path meets the constraint conditions of obstacle avoidance and image acquisition, and the inspection duration meets the constraint conditions of endurance; the optimization target O2(G,T a ,W,R,S); the maximum value of sub-goals O1(h,v,l,n) and O2(G,T a , W, R, S) respectively achieve the maximum value, the comprehensive optimization goal O M (G,T a ,W,R,S,h,v,l,n) also achieves the maximum value, which can be used as the optimal solution to the multi-objective optimization problem of UAV intelligent inspection for photovoltaic systems.

Images