JP2017215239A - Solar cell inspection system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a solar cell inspection system with which it is possible to automatize the inspection of a solar cell module installed outdoors.SOLUTION: A solar cell inspection system 1 comprises: a flight vehicle 10 flying in the air; a position detection unit 16 for detecting the flying position of the flight vehicle 10 on the basis of a radio wave signal received from a GPS satellite; an imaging device 17 for imaging a solar cell module; a photographing control unit 22 for controlling photographing by the imaging device 17; and an image processing unit 35 for comparing a reference image obtained by photographing the solar cell module with the imaging device 17 when the flying position of the flight vehicle 10 is located at a preset prescribed position and an inspection image obtained by photographing the solar cell module, a prescribed period after the reference image is photographed, with the imaging device 17 when the flying position of the flight vehicle 10 is located at the preset prescribed position and inspecting the solar cell module.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a solar cell inspection system that detects an abnormality occurring in a solar cell module.

  In recent years, with increasing interest in global environmental problems and energy saving, solar power generation using natural energy has attracted attention, and the spread of solar cell modules is rapidly progressing. A solar cell module is generally also referred to as a solar cell panel, and is configured by connecting a plurality of solar cells that convert light energy of sunlight into electric energy by a photovoltaic effect (for example, see Patent Document 1). reference).

JP 2012-253081 A

  By the way, in order to secure a predetermined power generation amount, the solar cell module is mainly installed and used outdoors such as a roof of a building or a rooftop. Therefore, on the surface (glass) of the solar cell module, foreign matter such as dust, bird droppings and dirt adheres due to long-term use outdoors, and the adhering part becomes a shadow on the solar cell, There is a problem that the power generation efficiency decreases. Therefore, normally, it is necessary to periodically inspect the solar cell module for any abnormality. However, in the past, a specialized worker climbed the roof or the roof of the building where the solar cell module was installed, and visually inspected the solar cell module. There was a problem of requiring labor and cost.

  This invention is made | formed in view of such a subject, and it aims at providing the solar cell test | inspection system which can automate the test | inspection of the solar cell module installed outdoors.

In order to achieve the above object, a solar cell inspection system according to the present invention is a solar cell inspection system for detecting an abnormality occurring in a solar cell module that receives sunlight and generates power, and flies in the air. A flying object, flight control means for controlling the flight of the flying object (for example, the flight control unit 21 in the embodiment), and position detection means for detecting the flight position of the flying object based on a radio wave signal received from a GPS satellite ( For example, the position detection unit 16) in the embodiment, the photographing unit (for example, the imaging device 17 in the embodiment) provided on the flying object and photographing the solar cell module, and the photographing of the solar cell module by the photographing unit are controlled. And a flight position of the flying object detected by the position detection unit is predicted. A reference image obtained by photographing the solar cell module with the photographing means when the predetermined position is set, and a predetermined period after the reference image is photographed and detected by the position detecting means. An abnormality that detects an abnormality occurring in the solar cell module by comparing with an inspection image obtained by imaging the solar cell module by the imaging means when the flying position of the flying object is at the predetermined position Detecting means (for example, the image processing unit 35 in the embodiment), wherein the abnormality detecting means detects an outline of the solar cell module included in the reference image and the inspection image, and the reference image and the inspection image. The abnormality is detected by comparing image regions inside the contour in the above.

  According to the solar cell inspection system according to the present invention, the solar cell module installed outdoors can be automatically inspected by aerial photography with a flying object, thus eliminating the labor of visual inspection by humans and requiring inspection. It is possible to reduce the cost by reducing the time, and it is possible to inspect safely and easily even at a high place or a large-scale power generation facility that is difficult for an operator to enter. In the solar cell inspection system according to the present invention, the shooting position (flight position) is shifted due to a GPS error, and the reflected position of the solar cell module differs between the two images (reference image and inspection image). However, it is possible to perform alignment between the two images by extracting the contour of the solar cell module from each image and comparing the image areas inside the contour. The solar cell module can be accurately inspected without being affected by the environment.

It is a block diagram which shows the solar cell test | inspection system which concerns on this embodiment. It is a schematic diagram which shows the outline | summary of the aerial photography by a flying body. It is a schematic diagram which shows a solar cell module. It is a flowchart of an aerial imaging process. It is a flowchart of an abnormality detection process. It is a figure which shows the content of the edge detection process (contour extraction process), (A) shows a reference | standard image, (B) shows a test | inspection image. It is a figure which shows the content of the shading process with respect to a reference | standard image. It is a figure which shows the content of the shading process with respect to a test | inspection image. It is a figure which shows the content of the brightness correction process. It is a figure which shows the content of the abnormality determination process. It is a figure which shows the modification of an outline extraction process, (A) shows a reference | standard image and (B) inspection image.

  Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. 1 and 2 show a solar cell inspection system 1 according to this embodiment, and FIG. 3 shows a solar cell module M to be inspected. First, referring to these drawings, the solar cell inspection system 1 is shown. An overview of the overall configuration will be described.

  As shown in FIGS. 1 and 2, the solar cell inspection system 1 is mainly configured by a flying object 10 that flies in the air and a control device 30 that comprehensively controls the entire system. As shown in FIG. 3, the solar cell module M connects a plurality of solar cells (hereinafter simply referred to as “cells”) C, and a transparent substrate such as tempered glass is disposed on the light receiving surface side, and a transparent resin or protection After sealing with a film or the like, a metal frame F such as aluminum is mounted around the periphery of the film to form a panel type. The cell C is composed of a semiconductor element (photoelectric conversion element) in which a PN junction is formed on a silicon wafer, and converts the light energy of sunlight into electric power using the photovoltaic effect. An assembly (solar cell array A) in which as many solar cell modules M as necessary to obtain a predetermined voltage and current are arranged in a matrix is installed in various places such as a roof or an outer wall of a building. It is used as a photovoltaic power generation device. In the present embodiment, each solar cell module M is given a unique ID number as identification information. Based on this ID number, the arrangement position of the solar cell module M (for example, latitude, longitude, and altitude) is provided. Position information) is specified.

<Aircraft>
The air vehicle 10 is a multi-rotor helicopter as a small unmanned air vehicle, and is configured to be able to fly autonomously by a flight command by remote control or by automatic control according to a preset flight plan. The flying body 10 is configured by four rotors (rotary blades) 12 arranged around the airframe 11 at intervals of 90 degrees in the circumferential direction, and a driving mechanism 13 that rotates each rotor 12 and a component. The position of the flying object 10 by receiving radio signals from a battery 14 that stores power to be supplied, a wireless communication unit 15 that transmits and receives various types of information through wireless communication with the control device 30, and a GPS satellite (Global Positioning System). A position detection unit 16 that detects the image, an imaging device 17 that captures an image of the solar cell module M, a control unit 20 that controls each component of the flying object 10, and a control program and various information related to aerial imaging. And a storage unit 23.

  The rotor 12 is rotatably arranged on the airframe 11 of the flying object 10, and causes the flying object 10 to generate lift and thrust by the rotation. The drive mechanism 13 includes an electric motor (for example, a servomotor) that is driven to rotate by receiving power supplied from the battery 14. The battery 14 supplies the stored electric power to each component of the flying object 10 to operate each component. The battery 14 can be charged by being connected to an external power source or the like during non-flight. The remaining power information of the battery 14 is periodically transmitted to the control device 30 via the wireless communication unit 15. Note that the airframe 11 may be provided with a monitor or the like that displays the remaining power of the battery 14.

  The wireless communication unit 15 includes a transmission circuit and a reception circuit, and can communicate with the control device 30 wirelessly.

  The position detection unit 16 includes a GPS receiver, receives radio waves from GPS satellites, and detects current position information (spatial coordinates including latitude, longitude, and altitude) of the flying object 10. The position information (also referred to as “GPS information”) is output to the control unit 20. Further, the position information detected by the position detection unit 16 is periodically transmitted to the control device 30 via the wireless communication unit 15.

  The imaging device 17 includes a visible light camera 17a that captures a visible light image of the solar cell module M, and an infrared camera 17b that captures an infrared image (thermal image) of the solar cell module M. The visible light camera 17a images the solar cell module M to be inspected in the visible light wavelength band (400 to 700 nm), and generates a visible light image. The visible light camera 17a may be a color camera or a monochrome camera as long as the luminance information of the subject can be obtained. On the other hand, the infrared camera 17b detects the energy of the infrared band emitted from the solar cell module M to be inspected, converts this into temperature, and generates a thermal image indicating temperature distribution information. The visible light image and the thermal image may be a still image or a moving image. Each camera 17a, 17b is provided with an optical lens (not shown) for adjusting the photographing range. The imaging device 17 is equipped with a tilt mechanism 18 for adjusting the optical axis direction of each camera 17a, 17b. The tilt mechanism 18 can individually adjust the optical axis directions of the two cameras 17a and 17b.

  The control unit 20 is mainly configured by a CPU as a central processing unit, and includes a flight control unit 21 that controls the operation of the flying object 10 and a shooting control unit 22 that controls the operation of the imaging device 17, and a ROM. On the basis of a control program stored in a storage unit 23 composed of, a RAM, etc., the flight path, flight conditions, imaging conditions, etc. are calculated, and the operations of the flying object 10 and the imaging device 17 are controlled synchronously.

The flight control unit 21 controls the rotation of the four rotors 12 and performs control for causing the flying object 10 to fly with a flight path and a flight speed according to the flight plan generated by the control device 30.
In this example, the flying object 10 can hover in a stationary state in the air by independently controlling the four rotors 12 and can also fly linearly in the horizontal direction or the vertical direction. Note that the flying object 10 can be operated not only automatically but also semi-automatically and manually by switching the operation mode. Based on the current flight position (GPS information) detected by the position detection unit 16, the flight control unit 21 determines whether or not the flying object 10 is flying on the planned flight route, and the flying object 10 is in the shooting position. It is determined whether or not the (shootable area) has been reached. When the flight control unit 21 determines that the flying object 10 deviates from the scheduled flight path, the flight control unit 21 corrects the flight conditions such as the flight direction and the flight speed so that the flying object 10 returns to the flight path. Control. In addition, when the flying object 10 reaches the shooting position (shootable area), the flight control unit 21 has a predetermined flying posture (hovering) for a certain time (time required for shooting) at the shooting position. Control). The photographing position of the solar cell module M is set in advance for each solar cell module M (ID number).

  The imaging control unit 22 controls the operation of the imaging device 17 and controls the imaging of the solar cell module M by the cameras 17a and 17b. The shooting control unit 22 transmits a shooting command signal to the imaging device 17 when the flying object 10 reaches the shooting position (shootable area) and assumes a predetermined flying posture (hovering state) at the shooting position. Then, the solar cell module M is photographed. In the photographing control unit 22, photographing conditions such as a photographing position (including direction), photographing magnification, and exposure time are set for each ID number of the solar cell module M to be photographed. The image data (visible light image, thermal image) photographed by the imaging device 17 includes position information (latitude, latitude, etc.) at the time of photographing in addition to photographing conditions such as the ID number of the solar cell module M, photographing magnification and exposure time. (Spatial coordinates consisting of longitude and altitude), time information, weather information, outside air temperature information, etc., stored in the storage unit 23 and transmitted to the external control device 30 via the wireless communication unit 15 Is done. Thus, since image data and various types of shooting information are stored in a state of being associated with each other, it is only necessary to specify one of the image data and shooting information (for example, shooting information), and the other information (image Data) is also accessible (readable).

<Control device>
The control device 30 includes a CPU for executing processing, a ROM in which a control program, control data, and the like are set and stored, a RAM that temporarily stores flight / photographing conditions, image data, map information, and the like. The overall operation of the inspection system 1 is controlled. The control device 30 is composed of, for example, a personal computer.

  The control device 30 includes an operation unit 31 used for various input settings and the like, a wireless communication unit 32 that is a communication interface for performing wireless communication with the flying object 10, a control program related to aerial shooting and image processing, A storage unit 33 for storing various information, a control unit 34 for monitoring the flight status of the flying object 10 and generating and managing a flight plan, and analyzing image data sent from the flying object 10 An image processing unit 35 that detects an abnormality of the battery module M and an output unit 36 that outputs an analysis result by the image processing unit 35 and the like are provided.

  The operation unit 31 is provided with input / output devices such as a keyboard, a mouse, and a switch, and a display panel (display) for displaying an operation screen, image data, and the like. On the display panel, program settings and condition selection are performed. An operation command or the like is input.

  The wireless communication unit 32 includes a transmission circuit and a reception circuit, and mainly transmits command information for automatically operating or remotely operating the flying object 10 to the flying object 10. Position information, remaining power information of the battery 14, image data captured by the imaging device 17, and the like are received.

The control unit 34 generates command information such as a flight plan of the flying object 10 and a shooting schedule of the imaging device 17 by sequentially executing processes based on the control program based on the setting information input from the operation unit 31. . The command information generated by the control unit 34 is transmitted from the wireless communication unit 32 toward the flying object 10. In addition, the control unit 34 acquires position information of the flying object 10 and monitors whether the flying object 10 is flying as planned according to the flight plan. Further, the control unit 34 generates a flight history of the flying object 10 based on position information and time information of the flying object 10, weather conditions on the day, map information on the site, and the like.

  The image processing unit 35 uses an image obtained by photographing the solar cell module M (referred to as “inspection image”) as an image obtained by photographing the solar cell module M in advance (referred to as “reference image”). In comparison, it is determined whether or not an abnormality has occurred in the solar cell module M. As the reference image, an image taken when the solar cell module M is in a new state (normal state) such as when the solar cell module M is installed is preferably used. As the inspection image, an image photographed when a predetermined period has elapsed since the installation of the solar cell module M (when the inspection time has come) is preferably used. Here, the inspection image and the reference image are taken from the same position based on the GPS information. However, the position where the solar cell module M is reflected in the image may be different from each other due to an error in the GPS information. is there. Therefore, in this embodiment, as will be described in detail later, instead of comparing the entire inspection image and the reference image, a predetermined image process (such as an edge detection process) is performed on each image data, so that the solar cell The contours of the modules M are extracted, and image regions inside the contours are compared with each other. Each image data is subjected to pre-processing or post-processing such as smoothing, luminance correction, binarization, and light / dark processing as necessary. Then, as a result of comparing the inspection image with the reference image, it is determined that an abnormality has occurred when there is a difference in the tendency of the image feature amount (image luminance distribution, density distribution, temperature distribution, color distribution, etc.) To do. Each image data (reference image and inspection image) may be either still image data or moving image data. The moving image data is composed of a plurality of frame data (a sequence of still image data) continuous at time intervals based on a predetermined frame rate. When the reference image and the inspection image are acquired as moving image data, the moving image data may be cut out as frame data (still image data), and the frame data may be compared and determined. In addition, when acquiring a visible light image and a thermal image as moving image data with the imaging device 17, ID number of the solar cell module M, position information at the time of shooting, shooting time, Shooting conditions (shooting magnification, exposure time, etc.), frame numbers (numbers when the frame data are arranged in order), etc. are recorded in association with each other.

  Here, the types of abnormalities occurring in the solar cell module M include (1) foreign matter adhesion, (2) microcracks, (3) solder failure, and (4) diode failure. The foreign matter adhesion means that foreign matters such as deposits such as dust, bird droppings, and dirt adhere to the surface (tempered glass) of the solar cell module M due to, for example, long-term outdoor use. When foreign matter adheres to the surface of the solar cell module M, the difference in reflectance from the surface (light receiving portion) (for example, the surface has a relatively low reflectance, and the foreign matter has a relatively high reflectance. ), The foreign object can be detected using a visible light image from the visible light camera 17a. In the solar cell module M, electrodes (high reflectivity) are arranged at regular intervals in the vertical direction or the horizontal direction in the surface direction, and a metal frame F (high reflectivity) is provided on the surface contour. Although they are arranged, they appear periodically or regularly on the image, so even if the image features (luminance, density, temperature, color, etc.) show the same level value, It is possible to discriminate foreign substances appearing irregularly (see FIG. 10 for details). On the other hand, when an abnormality such as a microcrack, a solder failure, or a diode failure occurs, the abnormal portion becomes an abnormal heat generation portion called a hot spot, and becomes a portion that is significantly hotter than the ambient temperature of the solar cell module M. The hot spot can be detected using a thermal image (temperature distribution information) from the infrared camera 17b. In the case of the above foreign matter adhesion, the foreign matter becomes a shadow on the cell C, so that the amount of heat generated in the cell C becomes a low-temperature portion as compared with the surrounding cell C, so that the heat generated by the infrared camera 17b. The foreign matter can also be detected using an image (temperature distribution information).

  From the output unit 36, the analysis result (detection result of abnormality occurring in the solar cell module M) by the image processing unit 35, the flight history of the flying object 10, and the like are output and displayed on the display panel or recorded on the recording medium. Data transmission to an external device is performed.

  Next, the procedure of the aerial imaging process executed by the solar cell inspection system 1 will be described. FIG. 4 is a flowchart showing the procedure of the aerial shooting process. In this example, when the solar cell module M to be inspected this time is installed in a building or the like, it is assumed that a reference image obtained by photographing the solar cell module M in advance is acquired. In the following, a case will be described in which a test image is acquired by newly taking a picture of the solar cell module M when a predetermined year has passed since the installation of the solar cell module M.

  First, the control unit 34 of the control device 30 transmits a flight command to the flying object 10 (S101). Upon receiving the flight command from the control device 30, the flight control unit 21 of the flying object 10 controls the rotation of the rotor 12 in accordance with a preset flight plan, and directs the flying object 10 from the base to the first imaging position. (S102).

  Subsequently, the flight control unit 21 determines whether or not the flying object 10 has reached the prescribed shooting position based on the position information (GPS information) from the position detection unit 16 (S103). Specifically, the flight control unit 21 matches the position (latitude, longitude, altitude) of the flying object 10 detected by the position detection unit 16 with the prescribed shooting position (shootable area) defined in the flight plan. It is determined whether or not to do. Each photographing position is set for each solar cell module M (ID number) to be photographed. If the solar cell modules M to be photographed are the same, the same photographing position is always set.

  Next, when the flying object 10 has reached the prescribed shooting position (S103: YES), the flight control unit 21 controls the rotation of the rotor 12 to place the flying object 10 in the hovering state at the shooting position (S104). ). This is because the temperature distribution of the solar cell module M cannot be accurately detected unless the separation distance from the flying vehicle 10 (infrared camera 17b) to the solar cell module M is maintained constant for a predetermined time. When only the visible light camera 17a is used, the flying object 10 does not necessarily have to be in the hovering state. Subsequently, the photographing control unit 22 photographs the solar cell module M by controlling the operation of the imaging device 17 (each camera 17a, 17b) in the hovering state (specified photographing position) (S105). In this example, the imaging range of the imaging device 17 (each camera 17a, 17b) is set to a visual field range in which two solar cell modules M are included.

  The shooting control unit 22 adds various types of shooting information (shooting date and time, shooting conditions, ID number, etc.) to the image data (inspection image) shot by the imaging device 17 (S106). Next, the imaging control unit 22 stores the image data (inspection image) of the solar cell module M imaged by the imaging device 17 in the storage unit 24 in a form associated with the imaging information (S107). The wireless communication unit 15 transmits the image data of the solar cell module M captured this time (image data stored in the storage unit 24) to the control device 30 together with the imaging information (S108).

  Subsequently, the shooting control unit 22 determines whether shooting by the imaging device 17 (shooting of all the solar cell modules M to be shot) is completed at all shooting positions (S109). The flight control unit 21 moves the flying object 10 to the next shooting position when all shooting is not completed (S109: NO) (S110). On the other hand, the flight control unit 21 returns the flying object 10 to the base (S111) when all the photographing has been completed (S109: YES).

Next, the procedure of the abnormality detection process performed by the solar cell inspection system 1 will be described. FIG.
These are the flowcharts which show the procedure of an abnormality detection process. In this example, a case will be described in which an abnormality (mainly foreign matter adhesion) of the solar cell module M is detected based on a visible light image obtained by photographing with the visible light camera 17a out of the two cameras 17a and 17b.

  First, the image processing unit 35 determines whether image data (inspection image) of the solar cell module M has been received from the flying object 10 (S201). When receiving image data (inspection image) (S201: YES), the image processing unit 35 acquires the image data and stores it in the storage unit 33 (S202). Subsequently, the image processing unit 35 reads a reference image to be compared with the inspection image acquired this time from the storage unit 33 based on the ID number of the solar cell module M (S203).

  Next, the image processing unit 35 performs known differential filter processing such as a Laplacian filter or a Sobel filter on the reference image and the inspection image, and detects an edge (the contour of the solar cell module M) in each image ( S204).

  Here, FIG. 6 is a schematic diagram showing the contents of the edge detection process, where (A) shows a reference image and (B) shows an inspection image. In each image, two solar cell modules M in the center among 12 (4 rows × 3 columns) solar cell modules M are imprinted as the solar cell array A. That is, in the present embodiment, the shooting range of each camera is set to a shooting field of view including two solar cell modules M, and image inspection is performed using the two solar cell modules M as a comparison target. However, when the reference image and the inspection image are compared, the shooting position of each image shifts due to a GPS error or the like, so that the reflection position of the solar cell module M does not correspond to each other. For this reason, each image (reference image, inspection image) is subjected to known image processing to detect an edge (contour), and a region surrounded by the edge (contour) should be compared with each other (solar cell module) By extracting as a region corresponding to M), corresponding portions of the reference image and the inspection image are specified. Note that the cause of the GPS error mainly includes the radio wave delay when passing through the ionosphere and the atmospheric layer, the presence of radio wave shields, receiver noise, and multipath effects.

  Subsequently, density processing is performed on the reference image and the inspection image (S205). In the shading process, a color image, which is an original image of each image, is converted into a black and white shading image (grayscale image), and a value indicating the shading of, for example, 256 tones in a luminance range from white to black (gradation information). Is assigned in units of pixels. For example, the density value (256 tone) is set to “0” for black and “255” for white. By performing such density processing, an image in which the defect is emphasized (an image in which the difference between both images is enhanced) is generated. Here, FIG. 7 is a schematic diagram showing the contents of the shading process for the target area of the reference image, and FIG. 8 is a schematic diagram showing the contents of the shading process for the target area of the inspection image. Each image region (target region) shown in FIGS. 7 to 8 is inverted by 90 degrees (vertical and horizontal are opposite) with respect to the image region (target region) in FIG.

  Subsequently, brightness correction is performed on the reference image (S206). The brightness correction is a process for correcting the brightness when the brightness of the reference image and the inspection image are different. This is because when shooting outdoors with the flying object 10, the brightness of the image varies depending on the difference in season, time of day, weather, etc. (regarding light) even if the shooting location is the same. is there. In this brightness correction, a correction value is calculated so that the average value of the brightness of the entire image (the entire target area) matches for the reference image and the inspection image, and the brightness of the inspection image is corrected. Here, FIG. 9 is a schematic diagram showing the content of the brightness correction for the reference image, where (A) shows the target area of the reference image before the brightness correction, and (B) shows the target area of the reference image after the brightness correction. . In this example, only the brightness of the reference image is corrected, but only the brightness of the inspection image or the brightness of both images may be corrected.

Next, the reference image and the inspection image are compared to determine whether there is an abnormality in the solar cell module M (S207). Here, FIG. 10 is a schematic diagram showing the contents of the abnormality determination process, where (A) shows the target area of the reference image and (B) shows the target area of the inspection image. Each image (FIGS. 6 to 10) is accompanied by a density distribution (luminance distribution) within a small area (details will be described later) set in each image. The horizontal axis represents the position between A and B, and the vertical axis represents the average density value at each position. In this abnormality determination processing, the target area of each image (reference image, inspection image) is divided into a plurality of small areas of arbitrary size (rectangular area of N pixels × M pixels), and both of these small areas are taken as a unit. The image regions are compared for each small region at a corresponding position in the image (comparison is performed for the number of divided small regions). As a result of the comparison, if the tendency of the density distribution is different, or if the density value has a difference greater than or equal to the threshold value, it is determined that there is an abnormality in the location. At this time, for example, when small regions at corresponding positions are compared at the same position, the density difference between each other tends to be small when there is no defect, and the density difference between each other tends to be large when there is a defect. . Here, the size of the small area in this example substantially corresponds to the size of 12 cells C (6 cells of each module M). Therefore, comparison of 12 cells C is sequentially performed between both images. Each time one comparison is completed, the small area is shifted in the vertical direction by one cell C. Therefore, the abnormality determination of the two solar cell modules M is completed by comparing the small area 10 times. The abnormality determination method is not limited to the above-described determination method, and a known technique can be applied. For example, a difference image between the reference image and the inspection image may be generated and it may be determined that there is an abnormality at a location where the difference information is greater than a predetermined threshold.

  Then, the output unit 36 outputs the result of abnormality determination (analysis result) by the image processing unit 35 (S208).

  As mentioned above, according to the solar cell inspection system 1 which concerns on this embodiment, since the solar cell module M installed outdoors can be automatically inspected by aerial photography by the flying object 10, the labor of visual inspection by humans is reduced. It is possible to reduce costs by reducing the time required for inspection, and to perform inspection safely and easily even at high locations and large-scale power generation facilities that are difficult for workers to enter. Is possible.

  Further, in the solar cell inspection system 1 according to the present embodiment, the shooting position (flight position) is shifted due to GPS error, and the reflection position of the solar cell module M is different between both images (reference image and inspection image). Even if it is a case, since the outline of the solar cell module M is extracted from each image and the image regions inside the outline are compared with each other, alignment between both images can be performed. The solar cell module M can be accurately inspected without being affected by the reception environment of the radio wave.

  In addition, this invention is not limited to the said embodiment, If it is a range which does not deviate from the summary of this invention, it can improve suitably.

In the above-described embodiment, the contour of the solar cell module M is extracted by performing known image processing to detect an edge included in the image. However, the present invention is not limited to this configuration. By attaching a mark (alignment mark) AM on the metal frame F of the module M, and detecting the mark AM from an image (reference image, inspection image) obtained by photographing the solar cell module M, You may comprise so that the outline of this solar cell module M may be detected. Specifically, as shown in FIG. 11, circular marks AM are attached to the corners (positions on one diagonal line) of the two solar cell modules M. For example, the mark AM may be affixed to the surface like a seal or may be affixed to the surface like an ink. The mark AM has durability, heat resistance, Those excellent in environmental resistance are preferably used. Then, in the comparison between the reference image and the inspection image, based on the feature amount of the mark image (feature amount that can be distinguished from the solar cell module M in the image: luminance, shape, hue, saturation, etc.) The mark AM is detected. Based on the relative positional relationship between the two marks AM, the outline of the two solar cell modules M included in the image (rectangular image corresponding to the outer shape of the two solar cell modules M) is detected. . According to such a configuration, since the outline of the solar cell module M can be extracted more accurately from the reference image and the inspection image, it is possible to improve the accuracy and reliability of the inspection. The number of marks AM may be singular or may be three or more. Further, the shape of the mark AM may be a shape other than a circle, such as a cross shape, a square shape, or a star shape. Further, the attachment position of the mark AM is preferably on the contour line (particularly the corner) of the solar cell module M, but the area inside the solar cell module M such as the center of gravity of the solar cell module M and the center position of each cell. It may be. For example, if the position information of these marks AM (the relative position of the marks AM with respect to the entire solar cell module M) is set in the control unit 20 or the control device 30 in advance, the marks AM can be detected more correctly. .

  Moreover, although the above-mentioned embodiment illustrated and demonstrated the case where abnormality of the solar cell module M was detected based on the visible light image acquired by image | photographing with the visible light camera 17a, it is limited to this structure. The abnormality of the solar cell module M may be detected based on a thermal image obtained by photographing with the infrared camera 17b. Here, when the ambient temperature reaches around 30 ° C. in the hot summer season, the surface temperature of the solar cell module M may rise to 50 to 60 degrees. At that time, if the temperature of the cell C and the temperature of the metal frame F are the same, the outline of the solar cell module M may not be accurately detected only from the thermal image (temperature distribution image). Therefore, in such a case, the visible light image and the thermal image are used in combination, and after first detecting the contour (edge) of the solar cell module M based on the visible light image, the local high temperature is detected from the thermal image. You may comprise so that a site | part (hot spot) or a low-temperature site | part may be detected. Furthermore, when detecting an abnormality based on the thermal image, after considering not only the absolute temperature of the solar cell module M but also a relative temperature difference from the ambient temperature of the solar cell module M (ambient air temperature). The presence or absence of abnormality may be determined. According to such a configuration, it is possible to improve the accuracy and reliability of the inspection without being affected by the environmental conditions (season, time zone, solar radiation intensity, temperature, etc.) at the time of measurement.

  Further, in the above-described embodiment, the case where foreign matter adhesion such as dust is detected as the detection of the abnormality by the visible light image is not limited to this. For example, other abnormality such as glass breakage is detected. It can also be detected. Glass cracking means that the transparent substrate (tempered glass) of the solar cell module M is broken by collision with a flying object (for example, falling rocks by crows, etc.).

  In the above-described embodiment, the case where two solar cell modules M are photographed has been described as an example. However, even if one solar cell module M is photographed depending on the setting of the photographing field of view (imaging range) or the like. Three or more solar cell modules M may be photographed.

  Moreover, although the multirotor helicopter which has the four rotors 12 was illustrated and demonstrated in the above-mentioned embodiment as the flying body 10, it is not limited to this structure, Other small unmanned flying bodies (radio control helicopters) It may be adopted.

  In the above-described embodiment, the flying object 10 is maintained in a hovering state at a predetermined shooting position based on position information (latitude, longitude, altitude) specified by a signal from a GPS satellite. In order to more correctly detect the separation distance between the solar cell module M and the solar cell module M, for example, a distance measuring sensor such as an ultrasonic sensor that detects the separation distance from the solar cell module M by reflected waves of the emitted ultrasonic waves May be installed.

Moreover, in the above-described embodiment, the solar cell inspection system 1 is configured by dividing the function into the flying object 10 and the control device 30, but is not limited to this structure. The functions of the apparatus 30 may be integrated (at least the image processing unit 35 of the control apparatus 30 is mounted on the flying object 10), and the solar cell inspection system 1 may be configured only from the flying object 10.

DESCRIPTION OF SYMBOLS 1 Solar cell inspection system 10 Flying body 11 Airframe 12 Rotor 13 Drive mechanism 14 Battery 15 Wireless communication part 16 Position detection part (position detection means)
17 Imaging device (photographing means)
18 Tilt mechanism 20 Control unit 21 Flight control unit 22 Imaging control unit (imaging control means)
23 storage unit 30 control unit 31 operation unit 32 wireless communication unit 33 storage unit 34 control unit 35 image processing unit (abnormality detection means)
36 Output part A Solar cell array C Solar cell F Metal frame M Solar cell module

Claims (1)

A solar cell inspection system for detecting an abnormality occurring in a solar cell module that receives sunlight and generates power,
An aircraft flying in the air,
Flight control means for controlling the flight of the flying object;
Position detecting means for detecting a flight position of the flying object based on a radio wave signal received from a GPS satellite;
Imaging means provided on the flying body for imaging a solar cell module;
Photographing control means for controlling photographing of the solar cell module by the photographing means;
When a reference image obtained by photographing the solar cell module by the photographing means when the flight position of the flying object detected by the position detecting means is at a predetermined position set in advance, and the reference image are photographed An inspection image obtained by photographing the solar cell module by the photographing means when the flying position of the flying object detected by the position detecting means is at the predetermined position In comparison, with an abnormality detection means for detecting an abnormality occurring in the solar cell module,
The abnormality detection unit detects an outline of the solar cell module included in the reference image and the inspection image, and compares the image areas inside the outline in the reference image and the inspection image to detect the abnormality. A solar cell inspection system.