Photovoltaic power generation facility abnormality detection system

Abstract

To provide a photovoltaic power generation facility abnormality detection system for enabling accurate monitoring while suppressing a data processing amount.SOLUTION: This photovoltaic power generation facility abnormality detection system comprises an imaging apparatus for imaging a photovoltaic power generation facility and a control section for transmitting image data acquired by the imaging apparatus to the outside via a network. The control section comprises: an image storage section for storing the image data; a difference determination section for determining a difference between a feature amount of first image data imaged at first time and a feature amount of second image data imaged at second time after the first time; and a transmission / reception control section for transmitting the second image data to the outside when the difference is equal to or larger than a predetermined threshold.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an abnormality detection system for a photovoltaic power generation facility and an abnormality detection program. [Background technology]

[0002] In recent years, with the increasing demand for the use of renewable energy, solar power generation facilities have been constructed in various locations. Most solar power generation facilities, excluding rooftop solar power generation panels, are often installed in mountainous areas or other areas far from urban areas. For this reason, an anomaly detection system has been proposed that uses surveillance cameras or the like to monitor solar power generation facilities for malfunctions, theft of parts, the occurrence of natural disasters, etc., and detects the occurrence of abnormalities (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6423767 Summary of the Invention [Problem to be solved by the invention]

[0004] However, monitoring using surveillance cameras poses the problem of the enormous amount of image data required for monitoring, which in turn requires a huge amount of data processing on the data collection server, resulting in increased operational costs. Furthermore, small communication devices installed near solar power generation facilities may lack sufficient data processing capabilities, resulting in delays in data transmission and reception and data errors. On the other hand, thinning out the image data from surveillance cameras to reduce the amount of data processing may result in a decrease in monitoring accuracy.

[0005] In view of the above-mentioned problems, an object of the present invention is to provide an anomaly detection system for photovoltaic power generation equipment that enables accurate monitoring while suppressing the amount of data processing. [Means for solving the problem]

[0006] A first aspect of the present invention provides an anomaly detection system for a photovoltaic power generation facility, comprising: an imaging device for capturing images of the photovoltaic power generation facility; and a control unit for transmitting image data captured by the imaging device to an external device via a network. The control unit comprises an image storage unit for storing the image data, a difference determination unit for determining a difference between a feature amount of first image data captured at a first time and a feature amount of second image data captured at a second time later than the first time, and a transmission / reception control unit for transmitting the second image data to an external device when the difference is equal to or greater than a predetermined threshold.

[0007] The anomaly detection system of the first aspect may further include a learning unit that learns feature quantities of the image data to acquire learning data. In this case, the difference determination unit may further determine a difference between the feature quantities of the image data stored in the image storage unit and the corresponding feature quantities of the learning data. Furthermore, the anomaly detection system of the first aspect may further include an image feature quantity adjustment unit that adjusts the feature quantities of the image data, and the difference determination unit may determine a difference between the feature quantities of the first image data after the feature quantities have been adjusted by the image feature quantity adjustment unit and the feature quantities of the second image data.

[0008] A second aspect of the present invention provides an abnormality detection system for solar power generation equipment, comprising: an imaging device for capturing images of the solar power generation equipment; and a control unit for transmitting image data captured by the imaging device to the outside via a network. The control unit comprises an image memory unit for storing the image data; a learning unit for learning features of the image data to acquire learning data; a difference determination unit for determining the difference between the features of the image data stored in the image memory unit and the corresponding features of the learning data; and a transmission / reception control unit for transmitting the image data to the outside if the difference is greater than or equal to a predetermined threshold. [Brief explanation of the drawings]

[0009] [Figure 1]1 is a schematic diagram showing the overall configuration of an abnormality detection system for a photovoltaic power generation facility according to a first embodiment. [Figure 2] 1 is a schematic diagram illustrating the operation of an abnormality detection system for a photovoltaic power generation facility according to a first embodiment. [Figure 3] 4 is a flowchart illustrating the operation of the abnormality detection system for a photovoltaic power generation facility according to the first embodiment. [Figure 4] FIG. 10 is a schematic diagram showing the overall configuration of an abnormality detection system for a photovoltaic power generation facility according to a second embodiment. [Figure 5] FIG. 10 is a schematic diagram illustrating the operation of an abnormality detection system for a photovoltaic power generation facility according to a second embodiment. [Figure 6] FIG. 10 is a schematic diagram showing the overall configuration of an abnormality detection system for a photovoltaic power generation facility according to a third embodiment. [Figure 7] 10 is a graph showing the operation of the abnormality detection system for a photovoltaic power generation facility according to the third embodiment. [Figure 8] 10 is a flowchart illustrating the operation of an abnormality detection system for a photovoltaic power generation facility according to a third embodiment. [Figure 9] FIG. 10 is a schematic diagram showing the overall configuration of an abnormality detection system for a photovoltaic power generation facility according to a fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, the present embodiment will be described with reference to the accompanying drawings. The accompanying drawings illustrate embodiments according to the principles of the present disclosure, but the drawings are for understanding the present disclosure and are not to be used to interpret the present disclosure in a limiting manner. The description in this specification is merely a typical example and does not limit the scope or application of the present disclosure in any way.

[0011] Although the present embodiment has been described in sufficient detail to enable those skilled in the art to implement the present disclosure, it should be understood that other implementations and forms are possible, and that changes in configuration and structure and substitutions of various elements are possible without departing from the scope and spirit of the technical ideas of the present disclosure. Therefore, the following description should not be interpreted as being limited thereto.

[0012] [First embodiment] An anomaly detection system for a photovoltaic power generation facility according to a first embodiment will be described with reference to Fig. 1. This anomaly detection system is a system that detects anomalies related to a solar panel SP as an anomaly detection target (for example, a failure in the electrical system of the solar panel, theft of parts, intrusion by a suspicious person, destruction of the solar panel due to a natural disaster or the like, collapse of the foundation, etc.), and is roughly composed of a surveillance camera 100, a microcomputer 200, a server 300, a management computer 400, and a group of sensors 500.

[0013] The surveillance camera 100 is an imaging device that captures images of the solar panel SP and its surroundings as video or still image data. The surveillance camera 100 may be a visible light camera, or an infrared camera for use at night. The surveillance camera 100 is not limited to a single camera, but may be multiple cameras. The installation location may be on the ground where the solar panel SP is installed, on a pole or building (not shown), or on an aircraft such as a drone. While FIG. 1 illustrates a single solar panel as the solar panel SP, multiple solar panels may be used. The multiple surveillance cameras 100 may include one camera positioned close to the solar panel SP to capture a close-up image, and another camera positioned on the ground away from the solar panel SP to capture a distant image.

[0014] The microcomputer 200 has the function of importing image data acquired by the surveillance camera 100, making various determinations, and then transmitting the image data to an external server 300 via the network NW. Specifically, the microcomputer 200 includes, for example, an image storage unit 201, an image feature amount acquisition unit 202, a difference determination unit 203, an image processing unit 204, and a transmission / reception control unit 205. Note that the microcomputer 200 may also include a mobile router or the like if the solar panel SP to be monitored is placed in an area with a poor communication environment, such as a mountainous region. The image storage unit 201 to the transmission / reception control unit 205 are realized by a computer program stored inside the microcomputer 200.

[0015] The image storage unit 201 is, for example, a hard disk drive (HDD), flash memory, or the like, and is a storage device that stores image data acquired by the surveillance camera 100. The image feature acquisition unit 202 analyzes the image data stored in the image storage unit 201 and acquires its feature amounts (e.g., values ​​related to the brightness and saturation of the image). For example, if the image data is video data, the feature amounts of the image data can be acquired by acquiring the video data at predetermined time intervals (e.g., every five minutes). The same can be done for image data consisting of successive still images. Note that, for example, if the brightness of the image is used as an index, the image data can be divided into multiple regions and the brightness of each of the multiple regions can be acquired. Alternatively, the average value, variance, standard deviation, or a combination thereof of the brightness of the multiple regions can be acquired as the feature amount.

[0016] The difference determination unit 203 calculates the difference between the feature amounts acquired by the image feature amount acquisition unit 202 and determines whether the difference is equal to or greater than a threshold. The image processing unit 204 performs predetermined image processing on the image data acquired by the surveillance camera 100 and the image data to be transmitted to the server 300. The transmission / reception control unit 205 controls the transmission to the server 300 of image data for which a difference equal to or greater than the threshold has been confirmed by the difference determination unit 203, and also controls the transmission and reception of other necessary data.

[0017] The server 300 receives image data from the microcomputer 200 via the network NW, stores the image data in a memory unit (not shown), and analyzes the image data to detect abnormalities in the solar panel SP. The management computer 400 is a computer that allows an operator to perform various operations necessary for analyzing the image data and other operations necessary for abnormality detection. The sensor group 500 is a collection of various sensors that detect the conditions of the solar panel SP and its surroundings. The sensors may include, for example, a human presence sensor, a temperature sensor, a pressure sensor, a vibration sensor, a sound sensor, etc. It is also possible to omit the sensor group 500 itself.

[0018] The operations of the image feature acquisition unit 202 and the difference determination unit 203 will be described with reference to the schematic diagram of FIG. 2 and the flowchart of FIG. 3. The image feature acquisition unit 202 acquires video data captured by the surveillance camera 100 at intervals of a predetermined time Ti (e.g., every 5 minutes) to acquire capture data P1, P2, P3, etc., and acquires feature values ​​for each of the data (steps S11 and S12). The capture data P1 is image data captured at a certain time t1, and the capture data P2 and P3 are image data captured at times t2 and t3, Ti and 2Ti after the time t1, respectively. The difference determination unit 203 compares the feature values ​​of the capture data P1, P2, and P3 to calculate the difference (step S13) and determines whether the difference is equal to or greater than a threshold value (step S14). As shown in FIG. 2, there is little change in the images between the capture data P1 and P2, and if the difference is less than the threshold value (No), the capture data P2 is not transmitted (uploaded) to the server 300.

[0019] On the other hand, in the capture data P3, an image of a suspicious person H appears near the solar panel SP, which causes the feature amount of the capture data P3 to differ significantly from the feature amount of the capture data P2 captured five minutes earlier, and the difference may be greater than or equal to the threshold (Yes). In this case, the difference determination unit 203 determines that the difference is greater than or equal to the threshold, and the transmission / reception control unit 205 transmits (uploads) the capture data P3 to the server 300 (step S15). The above operation continues while the surveillance camera 100 continues capturing images (step S16). Note that if the determination in step S4 is Yes, the process may proceed to step S15 further taking into consideration the detection results of the sensor group 500.

[0020] As described above, in the anomaly detection system of the first embodiment, image data from the surveillance camera 100 is sent to the server 300 and subjected to anomaly detection only when a significant change occurs in the image data. In the example of FIG. 2 , image data (P3) is sent (uploaded) to the server 300 only when a suspicious person H appears near the solar panel SP and a significant change occurs in the feature quantities of the image data. This reduces the data processing load on the microcomputer 200, data communication charges, and the amount of image data stored in the server 300, thereby reducing the cost of anomaly detection. When monitoring the solar panel SP with the surveillance camera 100, there is often little change in the image, making it inefficient to send and store all image data to the server 300. According to the first embodiment, image data is sent only when a significant change occurs in the image. This reduces the data processing load on the microcomputer 200, and also reduces the data volume and processing load on the server 300 and the management computer 400, thereby keeping operational costs low.

[0021] [Second embodiment] Next, an anomaly detection system according to a second embodiment of the present invention will be described with reference to Fig. 4. In Fig. 4, the same components as those in the anomaly detection system according to the first embodiment (Fig. 1) are given the same reference numerals, and therefore redundant description will be omitted. The anomaly detection system according to the second embodiment differs from the first embodiment in that the microcomputer 200 includes an image feature amount adjustment unit 206.

[0022] As shown in FIG. 5, the image feature amount adjustment unit 206 has a function of adjusting the feature amounts of image data obtained by the surveillance camera 100, taking into consideration, for example, time information indicating the local time, weather information indicating the local weather, and information about the local sunshine. Conditions such as time, weather, and sunshine may differ among the captured data P1, P2, P3, etc., resulting in changes in the image feature amounts even though the solar panel SP and its surrounding conditions remain unchanged. The image feature amount adjustment unit 206 adjusts the image feature amounts to suppress such fluctuations. The difference determination unit 203 determines the difference in feature amounts between the captured data P1', P2', P3', etc. after adjustment by the image feature amount adjustment unit 206.

[0023] The anomaly detection system of the second embodiment can achieve the same effects as the anomaly detection system of the first embodiment. Furthermore, by adjusting the feature amounts by the image feature amount adjuster 206, it becomes possible to more efficiently collect image data required for anomaly detection.

[0024] [Third embodiment] Next, an anomaly detection system according to a third embodiment of the present invention will be described with reference to Fig. 6. In Fig. 6, the same components as those in the anomaly detection system according to the first embodiment (Fig. 1) are given the same reference numerals, and therefore redundant description will be omitted. In the anomaly detection system according to the third embodiment, a microcomputer 200 includes a learning unit 207 that learns the feature quantities of image data obtained in the past. A difference determination unit 203A is configured to determine the difference in the feature quantities between the learning data obtained by the learning unit 207 and image data (actual measurement data) obtained thereafter, which is different from the previous embodiments.

[0025] 7, the learning unit 207 sequentially learns the feature amounts of image data obtained by the surveillance camera 100 in chronological order and acquires this as learning data. The difference determination unit 203A compares the feature amounts of this learning data with the feature amounts of image data subsequently obtained by the surveillance camera 100, and determines whether the difference therebetween is equal to or greater than a threshold. If the difference is equal to or greater than the threshold, the transmission / reception control unit 205 transmits (uploads) the image data with the abnormal difference to the server 300.

[0026] The operation of the anomaly detection system according to the third embodiment will be described in detail with reference to the flowchart in Fig. 8. The image feature amount acquisition unit 202 acquires, for example, video data acquired by the surveillance camera 100 at predetermined time intervals and acquires the feature amounts (step S21). The image feature amount acquisition unit 202 also acquires the feature amounts of learning data corresponding to the acquired images (step S22). The difference determination unit 203A compares the feature amounts of the learning data with the feature amounts of the image data to calculate the difference (step S23), and determines whether the difference is equal to or greater than a threshold (step S24). If the difference is less than the threshold (No), the corresponding image data is not transmitted (uploaded) to the server 300.

[0027] On the other hand, if the difference is equal to or greater than the threshold value (Yes), the transmission / reception control unit 205 transmits (uploads) the corresponding image data to the server 300 (step S25). The above operation continues while the surveillance camera 100 continues capturing images (step S26). Note that if the determination in step S24 is Yes, the process may proceed to step S15, further taking into consideration the detection results of the sensor group 500.

[0028] As described above, in this third embodiment, instead of uploading image data when there is a significant change in the feature of the image data within a predetermined time, image data is uploaded when a difference equal to or greater than a threshold occurs between the feature of the training data and the actual measured image data. The feature of the image data, for example, changes daily in a similar manner under normal circumstances, but may change differently when some abnormality occurs. In the third embodiment, such changes can be detected by comparing the feature of the training data with the feature of the actual measured data. In other words, according to this third embodiment, by acquiring the daily change in the feature as training data, it becomes possible to accurately detect abnormalities in the solar panel SP.

[0029] [Fourth embodiment] Next, an anomaly detection system according to a fourth embodiment of the present invention will be described with reference to FIG. 9. In FIG. 9, the same components as those in the anomaly detection system according to the first embodiment (FIG. 1) are designated by the same reference numerals, and therefore, a repeated description will be omitted. In the anomaly detection system according to the fourth embodiment, a microcomputer 200 includes a learning unit 207 that learns the feature quantities of image data obtained in the past. This is the same as in the third embodiment. However, in this embodiment, a difference determination unit 203B determines the difference in the feature quantities between the learning data obtained by the learning unit 207 and image data (actual measurement data) obtained thereafter. Similarly to the first embodiment, the difference determination unit 203B also determines the difference in the feature quantities of capture data obtained at predetermined time intervals. In other words, the fourth embodiment combines the functions of both the first and third embodiments. The operation is substantially the same as in the previous embodiments, and therefore a description thereof will be omitted.

[0030] [others] The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0031] As an example, in addition to monitoring the difference in the feature amount of the image data, the amount of power generated by the solar panel SP may also be monitored, and if an abnormality is found in both the difference and the amount of power generated, the image data may be transmitted to the server 300. This makes it possible to further reduce the amount of image data transmitted to the server 300 and improve efficiency.

[0032] As another example, when the microcomputer 200 detects a difference equal to or greater than the threshold, the threshold can be changed to a smaller value for a predetermined period of time (e.g., several hours) thereafter. This makes it possible to detect various abnormalities related to the solar panel SP without overlooking them. [Explanation of symbols]

[0033] 100...Surveillance cameras 200···Microcomputer 300 Server 400···Administrative computer 500 sensors NW...Network SP...Solar Panel 201 Image storage unit 202...Image feature memory unit 203, 203A, 203B...Difference judgment section 204···Image processing unit 205 Transmission and reception control section 206···Image feature adjustment unit 207···Learning Department P1~P3, P1'~P3'... Capture data

Claims

1. an imaging device that captures an image of the solar power generation facility; a control unit that transmits image data acquired by the imaging device to an external device via a network; Equipped with The control unit includes an image storage unit that stores the image data; a difference determination unit that determines a difference between a feature amount of first image data captured at a first time and a feature amount of second image data captured at a second time later than the first time; a transmission / reception control unit that transmits the second image data to an external device when the difference is equal to or greater than a predetermined threshold value; An abnormality detection system for solar power generation equipment.

2. a learning unit that learns the feature amount of the image data and acquires learning data; The anomaly detection system according to claim 1 , wherein the difference determination unit further determines a difference between a feature amount of the image data stored in the image storage unit and a feature amount of the corresponding learning data.

3. further comprising an image feature amount adjustment unit that adjusts the feature amount of the image data; The anomaly detection system according to claim 1 , wherein the difference determination unit determines a difference between the feature amount of the first image data after the feature amount has been adjusted by the image feature amount adjustment unit and the feature amount of the second image data.

4. an imaging device that captures an image of the solar power generation facility; a control unit that transmits image data acquired by the imaging device to an external device via a network; Equipped with The control unit includes an image storage unit that stores the image data; a learning unit that learns the feature amount of the image data and acquires learning data; a difference determination unit that determines a difference between a feature amount of the image data stored in the image storage unit and a feature amount of the corresponding learning data; a transmission / reception control unit that transmits the image data to an external device when the difference is equal to or greater than a predetermined threshold value; An abnormality detection system for solar power generation equipment.

5. storing image data of the photovoltaic power generation facility acquired by the imaging device; determining a difference between a feature amount of first image data captured by the imaging device at a first time and a feature amount of second image data captured by the imaging device at a second time later than the first time; transmitting the second image data to an external device when the difference is equal to or greater than a predetermined threshold value; A program for detecting abnormalities in a solar power generation facility configured to cause a computer to execute the above.

6. storing image data of the photovoltaic power generation facility acquired by the imaging device; learning the feature amounts of the image data to obtain learning data; determining a difference between a feature amount of the stored image data and a feature amount of the corresponding training data; transmitting the image data to an external device when the difference is equal to or greater than a predetermined threshold value; A program for detecting abnormalities in a solar power generation facility configured to cause a computer to execute the above.

Images