A device abnormality detection method and photovoltaic power generation equipment detection system

Abstract

The present invention discloses a device abnormality detection method and a photovoltaic power generation equipment detection system, and relates to the technical field of photovoltaic power generation fault identification. The present invention includes obtaining the cumulative power generation time and cumulative power generation of each photovoltaic device; obtaining the equivalent working time of each photovoltaic device according to the cumulative power generation time and cumulative power generation of each photovoltaic device; obtaining the power generation of each photovoltaic device on the previous day and multiple adjacent days; obtaining the power generation efficiency proportional coefficient of each photovoltaic device in the current state according to the power generation of each photovoltaic device on the previous day and multiple adjacent days; judging whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient; if so, marking the photovoltaic device as an abnormal state; if not, marking the photovoltaic device as a normal state; outputting the identification code of the photovoltaic device marked as an abnormal state. The present invention improves the detection efficiency of photovoltaic devices.

Description

Technical Field

[0001] The present invention belongs to the technical field of photovoltaic power generation fault identification, and in particular relates to an equipment abnormality detection method and a photovoltaic power generation equipment detection system. Background Art

[0002] With the rapid development of renewable energy technology, photovoltaic power generation has become one of the clean energy sources widely used around the world. Photovoltaic power generation systems (PV) convert sunlight directly into electrical energy, which has the advantages of cleanliness, environmental protection, and sustainable utilization. However, with the large-scale application of photovoltaic power generation devices, how to ensure their efficient and stable operation has become an important issue.

[0003] At present, photovoltaic power generation systems may experience a variety of abnormal conditions during operation, such as component aging, hot spot effects, microcracks, PID effects (potential induction decay), shading, pollution, etc. These problems will cause the output power of the photovoltaic system to decrease, affecting power generation efficiency and economic benefits. Therefore, real-time monitoring and abnormality detection of photovoltaic systems are the key to ensuring stable operation of the system.

[0004] Existing equipment anomaly detection methods mainly include regular manual inspections and sensor-based monitoring systems. Manual inspections are labor-intensive, costly, and inefficient; although sensor monitoring systems can achieve real-time monitoring, they are expensive to deploy in large-scale photovoltaic power plants, and sensors may be damaged by environmental factors, affecting the accuracy and reliability of detection. Summary of the invention

[0005] The purpose of the present invention is to provide a device abnormality detection method and a photovoltaic power generation equipment detection system, which analyzes the power generation status of each photovoltaic device, digs out abnormal photovoltaic devices therein, and improves the detection efficiency of photovoltaic devices.

[0006] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0007] The present invention provides a device abnormality detection method, comprising:

[0008] Obtain the cumulative power generation time and cumulative power generation of each photovoltaic device;

[0009] Obtaining the equivalent working time of each photovoltaic device according to the accumulated power generation time and the accumulated power generation of each photovoltaic device;

[0010] Obtaining the power generation of each photovoltaic device on the previous day and a number of adjacent days;

[0011] Obtaining a power generation efficiency proportional coefficient of each photovoltaic device in a current state according to the power generation of each photovoltaic device on the previous day and a plurality of adjacent days;

[0012] Determining whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient;

[0013] If yes, marking the photovoltaic device as being in an abnormal state;

[0014] If not, marking the photovoltaic device as being in a normal state;

[0015] An identification code of the photovoltaic device marked as being in an abnormal state is output.

[0016] The present invention also discloses a device abnormality detection method, comprising:

[0017] Obtain the identification code and corresponding location of each photovoltaic device;

[0018] Acquire an identification code of the photovoltaic device marked as being in an abnormal state;

[0019] Retrieving and comparing to obtain the location of the photovoltaic device marked as being in an abnormal state;

[0020] The location of the photovoltaic device marked as being in an abnormal state is displayed.

[0021] The present invention also discloses a photovoltaic power generation equipment detection system, comprising:

[0022] An abnormal equipment analysis unit is used to obtain the cumulative power generation time and cumulative power generation of each photovoltaic equipment;

[0023] Obtaining the equivalent working time of each photovoltaic device according to the accumulated power generation time and the accumulated power generation of each photovoltaic device;

[0024] Obtaining the power generation of each photovoltaic device on the previous day and a number of adjacent days;

[0025] Obtaining a power generation efficiency proportional coefficient of each photovoltaic device in a current state according to the power generation of each photovoltaic device on the previous day and a plurality of adjacent days;

[0026] Determining whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient;

[0027] If yes, marking the photovoltaic device as being in an abnormal state;

[0028] If not, marking the photovoltaic device as being in a normal state;

[0029] Outputting an identification code of the photovoltaic device marked as being in an abnormal state;

[0030] A maintenance guidance unit, used to obtain the identification code and corresponding location of each photovoltaic device;

[0031] Acquire an identification code of the photovoltaic device marked as being in an abnormal state;

[0032] Retrieving and comparing to obtain the location of the photovoltaic device marked as being in an abnormal state;

[0033] The location of the photovoltaic device marked as being in an abnormal state is displayed.

[0034] The present invention collects and organizes the power generation and use record data of each photovoltaic device through an abnormal device analysis unit, and analyzes the relationship range between the equivalent working time of normal photovoltaic devices and the power generation efficiency ratio coefficient, and then compares and judges whether the power generation behavior of each photovoltaic device in the current state is abnormal. In this process, no dedicated detection sensors are required, nor a large number of manual inspections are required, which improves the efficiency of abnormal detection and subsequent maintenance of photovoltaic equipment.

[0035] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 A schematic diagram of functional units and information flow of a photovoltaic power generation equipment detection system according to an embodiment of the present invention;

[0038] Figure 2 The abnormal device analysis unit of the present invention is a schematic diagram of the steps of an embodiment of the present invention. Figure 1 ;

[0039] Figure 3 A schematic diagram of a step flow chart of a maintenance and guidance unit according to an embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of the step flow of step S2 in one embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of the step flow of step S4 in one embodiment of the present invention;

[0042] Figure 6This is a schematic diagram of the step flow of step S5 in one embodiment of the present invention;

[0043] Figure 7 A schematic diagram of a step flow chart of step S53 in an embodiment of the present invention;

[0044] Figure 8 This is a schematic diagram of a step flow chart of step S531 in an embodiment of the present invention;

[0045] Fig. 9 A schematic diagram of a step flow chart of step S56 in an embodiment of the present invention;

[0046] Fig.10 The abnormal device analysis unit of the present invention is a schematic diagram of the steps of an embodiment of the present invention. Figure 2 ;

[0047] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0048] 1- Abnormal equipment analysis unit, 2- Maintenance guidance unit. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0050] It should be noted that the terms "first", "second", etc. in this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0051] Photovoltaic power generation equipment is a device that uses solar energy to convert light energy into electrical energy. It directly converts sunlight into DC power through photovoltaic panels. In actual use, a large number of photovoltaic power generation equipment of the same specifications are arrayed to form a solar power station. In order to achieve economies of scale, solar power stations are usually huge in scale, including tens of thousands and hundreds of thousands of individual photovoltaic power generation equipment. This makes it difficult for a small number of maintenance personnel to conduct timely abnormal detection of a large number of photovoltaic power generation equipment. Online sensors can also be used to perform unmanned detection of the working status of photovoltaic equipment, but this requires expensive hardware such as visual imaging such as cameras and thermal sensors to achieve this, and the cost of detection is high.

[0052] In order to improve the inspection and maintenance efficiency of a large number of photovoltaic power generation equipment without significantly increasing the inspection cost, the present invention provides the following solution.

[0053] See also Figure 1 , 2 , 3 and 10, the present invention provides a photovoltaic power generation equipment detection system, which can include an abnormal equipment analysis unit 1 and a maintenance guidance unit 2 from the perspective of functional units. The abnormal equipment analysis unit 1 collects the cumulative power generation time, cumulative power generation and recent power generation of the photovoltaic equipment. These data can be collected and recorded without adding additional hardware, and will not increase the hardware cost of detection and analysis. The maintenance guidance unit 2 in this solution can inform maintenance personnel of the location of photovoltaic equipment in abnormal conditions, and can be a specific display hardware or an application installed on a mobile display device such as a mobile phone or tablet.

[0054] During the operation of this scheme, first, the abnormal device analysis unit 1 executes step S1 to obtain the cumulative power generation time and cumulative power generation of each photovoltaic device. These data can be obtained by querying, retrieving and accumulating the work records or work logs of each photovoltaic device. Next, step S2 can be executed to obtain the equivalent working time of each photovoltaic device according to the cumulative power generation time and cumulative power generation of each photovoltaic device. This is because the working loss state of the photovoltaic power station is not only related to the power generation time, but also to the cumulative power generation. Therefore, it is necessary to combine the two to make corrections, so that the loss state of each photovoltaic device can be relatively accurately obtained. Next, steps S3 and S4 can be executed to obtain the power generation of each photovoltaic device on the previous day and the adjacent days, and the power generation efficiency ratio coefficient of each photovoltaic device in the current state is obtained according to the power generation of each photovoltaic device on the previous day and the adjacent days, that is, the relative loss state of each photovoltaic device in the current state is calculated. Next, step S5 can be executed to determine whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency ratio coefficient, that is, the state of each photovoltaic device is determined by comparing the correlation between the two loss states of each photovoltaic device. Then, the result is obtained according to the comparison result, that is, if yes, then step S6 can be executed to mark the photovoltaic device as abnormal, if not, then step S7 can be executed to mark the photovoltaic device as normal. Finally, step S8 can be executed to output the identification code of the photovoltaic device marked as abnormal for subsequent identification and management.

[0055] In order to facilitate the maintenance personnel to manage the photovoltaic equipment in abnormal state, the maintenance guidance unit 2 is required to push the photovoltaic equipment in abnormal state to the maintenance personnel. For the convenience of use, the maintenance guidance unit 2 is usually installed in the mobile phone application. During work, the maintenance guidance unit 2 can execute step S011 to obtain the identification code and corresponding location of each photovoltaic device. This part of the data can be built-in in the maintenance guidance unit 2, or it can be a map resource located on the cloud server read through the network. After that, step S012 can be executed to obtain the identification code of the photovoltaic equipment marked as abnormal state, which can be obtained through network push. Next, step S013 can be executed to retrieve and compare the location of the photovoltaic equipment marked as abnormal state. Finally, step S014 can be executed to display the location of the photovoltaic equipment marked as abnormal state, or it can be a path generated from the current location of the maintenance personnel to the location of the photovoltaic equipment in abnormal state, so as to facilitate the subsequent maintenance operations of the maintenance personnel.

[0056] See also Figure 4 As shown, the degree of loss of photovoltaic equipment can be measured by the cumulative power generation time, but in specific applications, due to differences in power generation, the cumulative power generation time needs to be adjusted in combination with the cumulative power generation. Therefore, in the above process of calculating the equivalent working time of each photovoltaic power station, step S21 can be first executed to numerically arrange the cumulative power generation time and the cumulative power generation of each photovoltaic device to extract the cumulative working characteristic vector composed of the cumulative power generation time and the cumulative power generation of each photovoltaic device. This step is to comprehensively consider the comprehensive factors of the cumulative power generation time and the cumulative power generation.

[0057] During maintenance, step S9 can be executed to perform maintenance and troubleshooting on the photovoltaic equipment marked as abnormal, and then step S10 can be executed to remove the abnormal state of the photovoltaic equipment after the troubleshooting is removed and mark it as normal. The photovoltaic equipment that has returned to normal continues to participate in the next round of abnormality detection.

[0058] Next, step S22 can be executed to calculate the proportional coefficient between the modulus of the cumulative working characteristic vector of each photovoltaic device as the fusion factor adjustment coefficient of each photovoltaic device, aiming to combine the two factors of cumulative power generation time and cumulative power generation into one-dimensional data. In order to facilitate the subsequent proportional calculation, the sum of the fusion factor adjustment coefficients of all photovoltaic devices can be 0.5. Next, step S23 can be executed to calculate the proportional coefficient between the cumulative power generation time of the photovoltaic devices as the basic proportional coefficient of each photovoltaic device, and adjust the sum of the basic proportional coefficients of all photovoltaic devices to 0.5. This step can simplify the calculation by combining the sum of the fusion factor adjustment coefficients of all photovoltaic devices in step S22 to 0.5. Since the value that best reflects the loss state of the photovoltaic device is the cumulative power generation time, step S24 can be executed next to add the corresponding fusion factor adjustment coefficient to the basic proportional coefficient of each photovoltaic device to obtain the corrected proportional coefficient of each photovoltaic device. Next, step S25 and step S26 can be executed to calculate the cumulative sum of the cumulative power generation time of each photovoltaic device as the total power generation time, and the correction proportional coefficient of each photovoltaic device can be multiplied by the total power generation time to obtain the equivalent working time of each photovoltaic device. In this way, the cumulative power generation can be fully and effectively adjusted to the cumulative power generation time, which can better reflect the loss status of the photovoltaic power generation equipment.

[0059] See also Figure 5 As shown, when the solar panel is working, the speed of the electron movement inside the panel increases, which leads to some electron energy loss, thereby reducing the power generation efficiency. Since the specifications of the photovoltaic equipment in the solar power station are usually consistent, the loss degree of the photovoltaic equipment can also be measured by the power generation efficiency. Based on the above principles, in order to obtain the loss state of each photovoltaic device in the current state, firstly, step S41 can be executed to obtain the maximum power generation and the minimum power generation and the number of statistical days according to the power generation of the photovoltaic equipment on the previous day and the adjacent days. Due to environmental changes and various unexpected conditions, the power generation status of the photovoltaic equipment will fluctuate. In order to avoid this affecting the measurement of the loss degree of the photovoltaic power station, step S42 can be executed next to take the difference between the maximum power generation and the minimum power generation and the ratio of the statistical days as the average daily floating power generation, that is, to obtain the specific value of this fluctuation effect.

[0060] Next, step S43 can be executed to sort the power generation of the photovoltaic equipment on the previous day and the adjacent days according to the numerical size to obtain a power generation sequence, that is, to arrange the working days with similar power generation status adjacent to each other. Next, step S44 can be executed to calculate and compare to obtain multiple power generation in the power generation sequence whose difference with the adjacent power generation is less than the daily average floating power generation to form a power generation collection, that is, to select and classify the working days with adjacent power generation status together. Next, step S45 can be executed to obtain the average of all power generation in the power generation collection containing the largest number of power generation as the steady-state average daily power generation of each photovoltaic device. This is because the solar power station is set in an area with stable sunlight all year round, so its working days with stable power generation account for the vast majority, that is, all power generation in the power generation collection containing the largest number of power generation is the power generation on stable power generation working days. In order to measure the difference in power generation of different photovoltaic devices in a solar power station, step S46 can be finally executed to calculate and obtain the proportional coefficient between the steady-state average daily power generation of each photovoltaic device as the power generation efficiency proportional coefficient of each photovoltaic device in the current state. Since different photovoltaic devices have the same specifications and are set in the same solar power station, the difference in power generation of different photovoltaic devices can also measure the loss status of different photovoltaic devices.

[0061] See also Figure 6 As shown, although both the equivalent working time and the power generation efficiency proportional coefficient reflect the loss state of the photovoltaic equipment, the equivalent working time tends to reflect the loss of the photovoltaic equipment during use, and the power generation efficiency proportional coefficient tends to reflect the power generation efficiency of the photovoltaic equipment. Therefore, there is a correlation between the equivalent working time and the power generation efficiency proportional coefficient, and there are also differences. Since most of the photovoltaic equipment in the solar power station is normal, the photovoltaic equipment in an abnormal state can be screened out through correlation analysis. Based on this principle, the above-mentioned step S5 needs to execute step S51 in the specific implementation process to arrange the equivalent working time of each photovoltaic equipment and the corresponding power generation efficiency proportional coefficient in a set order to obtain the power generation state feature array of each photovoltaic equipment, that is, to prepare data to facilitate subsequent correlation analysis.

[0062] In the specific correlation analysis process, firstly, the power generation state characteristic coordinate points of the power generation state characteristic array of each photovoltaic device in the two-dimensional plane are obtained by executing step S52, and the complex data analysis is converted into a two-dimensional plane data point calculation that is more convenient to calculate, thereby reducing the amount of calculation. Next, step S53 can be executed to obtain the conventional distribution range of the power generation state characteristic coordinate points of the photovoltaic device in the two-dimensional plane according to the distribution state of the power generation state characteristic coordinate points of each photovoltaic device in the two-dimensional plane, that is, the distribution range of the power generation state characteristic coordinate points of the photovoltaic device in the normal state. In the process of abnormal judgment, step S54 can be executed to determine whether the power generation state characteristic coordinate points of each photovoltaic device are within the conventional distribution range. If so, it means that the photovoltaic device is normal, and then step S55 can be executed to determine whether the power generation state of the photovoltaic device is normal. Otherwise, it means that the photovoltaic device is abnormal, but not necessarily abnormal. Therefore, step S56 can be executed next to determine whether the power generation state of the photovoltaic device is abnormal according to the relative position relationship of the power generation state characteristic coordinate points of the photovoltaic device with respect to the conventional distribution range, so as to specifically determine whether it is abnormal. This is because although some devices are not in the normal state, their power generation capacity declines below the normal value after long-term use. Although they are abnormal, they are not considered abnormal and do not need maintenance.

[0063] See also Figure 7 As shown, since the various data collected in the solar power station do not cover all conditions, the actual conventional distribution range of the characteristic coordinate points of the power generation state of the photovoltaic equipment obtained by actual collection in the two-dimensional plane cannot completely cover all new situations that may appear in the future. Therefore, it is necessary to expand the range under the ideal state in combination with the actual data, and also filter out some extreme data. Based on this principle, in the specific implementation process of the above-mentioned step S56, step S531 can be first executed to obtain the real conventional distribution range of the characteristic coordinate points of the power generation state of the photovoltaic equipment in the two-dimensional plane according to the distribution state of the characteristic coordinate points of the power generation state of each photovoltaic equipment in the two-dimensional plane, that is, the actual conventional range. Next, step S532 can be executed to perform quadratic function fitting on all the characteristic coordinate points of the power generation state within the real conventional distribution range to obtain the ideal functional relationship of the power generation efficiency ratio coefficient of the photovoltaic equipment with respect to the equivalent working time as the ideal fitting function, that is, to obtain the correlation relationship under the most ideal state, but this will greatly narrow the data caliber, resulting in the inability to operate in the subsequent steps of determining whether the photovoltaic equipment is abnormal.

[0064] In order to expand the data scope in combination with the actual situation, step S533 can be executed next to obtain the shortest distance between each power generation state characteristic coordinate point and the ideal fitting function curve within the real conventional distribution range in the two-dimensional plane as the discrete distance of each power generation state characteristic coordinate point within the real conventional distribution range. Next, step S534 can be executed to calculate and obtain the mean of the discrete distances of all power generation state characteristic coordinate points within the real conventional distribution range as the extended distance, that is, the natural fluctuation amplitude of the actual value. Next, step S535 can be executed to use the function curve of the ideal fitting function within the real conventional distribution range in the two-dimensional plane as a conventional function curve segment, in order to obtain the core value of the conventional range. Next, step S536 can be executed to use each point of the conventional function curve segment as the center of the circle and the extended distance as the radius to draw a circle, and obtain the coverage range of the corresponding circle of all points of the conventional function curve segment as the conventional distribution range of the power generation state characteristic coordinate points of the photovoltaic device in the two-dimensional plane, that is, to reasonably expand the scope of data comparison, and at the same time, to filter out extreme values ​​in some actual data, so as to avoid abnormal photovoltaic devices being judged as normal and causing increased losses.

[0065] In order to supplement the implementation process of the above steps S531 to S536, the source code of some functional modules is provided, and the explanation is compared in the comment section. In order to avoid the leakage of data involving commercial secrets, some data that does not affect the implementation of the solution are desensitized, the same below.

[0066]

[0067]

[0068]

[0069] This code first defines two classes: PhotovoltaicDevice is used to describe photovoltaic devices, including equivalent working time, power generation efficiency ratio coefficient, and whether the power generation status is normal; Point2D is used to represent points in two-dimensional space. In the main function, an array of photovoltaic devices is created, and the characteristics of each device are converted into coordinate points in two-dimensional space. Then the normal distribution range of these points is calculated, and a threshold is used to determine whether each point is within the normal distribution range, thereby determining whether the power generation status of each photovoltaic device is abnormal. Finally, the power generation status of each device is output.

[0070] See also Figure 8As shown, since there is a correlation between the equivalent working time and the power generation efficiency proportional coefficient, and the specifications and models of the photovoltaic equipment in the solar power station are the same, the length of time they are put into use is different. Due to the light decay problem of photovoltaic equipment, the power generation efficiency proportional coefficient of photovoltaic equipment will slowly decrease with the increase of the equivalent working time. If the photovoltaic power station has an abnormal decay, the distribution of its corresponding power generation state characteristic coordinate points in the two-dimensional plane will also be abnormal. Based on this principle, in the implementation process of the above-mentioned step S531, step S5311 can be first executed to select two or more power generation state characteristic coordinate points from the power generation state characteristic coordinate points of all photovoltaic equipment as core power generation state characteristic coordinate points. This is because most of the photovoltaic equipment is normal equipment, and the power generation state characteristic coordinate points of a small number of abnormal photovoltaic equipment will be discrete parts. Next, step S5312 can be executed to calculate the distance between each core power generation state characteristic coordinate point and each other power generation state characteristic coordinate point, that is, to measure the degree of abnormality between each other.

[0071] In the process of trying to distinguish abnormal photovoltaic equipment from normal photovoltaic equipment, step S5313 can be first executed to form a coordinate point collection with each other power generation state characteristic coordinate point and the closest core power generation state characteristic coordinate point, that is, to try to classify abnormal and normal photovoltaics. Next, step S5314 can be executed to calculate and obtain the power generation state characteristic coordinate point in each coordinate point collection that is closest to the geometric center of the envelope of all power generation state characteristic coordinate points as the updated core power generation state characteristic coordinate point, that is, to continuously adjust the classification standard. Next, step S5315 can be executed to determine whether the core power generation state characteristic coordinate point has changed, that is, to determine whether the accurate classification has been completed. If so, it means that the previous classification is inaccurate, then steps S5311 to S5315 can be executed to return to continuously update the coordinate point collection and the core power generation state characteristic coordinate point. If otherwise, it means that the classification is accurate, then step S5316 can be executed to output the envelope frame range of all power generation state characteristic coordinate points in the coordinate point set containing the largest number of power generation state characteristic coordinate points as the true preliminary conventional distribution range in the two-dimensional plane. In the above process, abnormal photovoltaic devices and normal photovoltaic devices are accurately distinguished by continuously trying to classify and judging whether the classification is accurate through cyclic iteration.

[0072] In order to provide additional explanation for the implementation process of the above-mentioned steps S5311 to S5316, the source code of some functional modules is provided, and a comparative explanation is provided in the comment section.

[0073]

[0074]

[0075]

[0076]

[0077]

[0078] This code finds the normal distribution range of the characteristic coordinate points of the power generation status of photovoltaic devices. First, a certain number of core coordinate points are initialized according to the provided device characteristic coordinate points. Then, by calculating the distance from each device coordinate point to each core coordinate point, the devices are divided into sets formed by the nearest core coordinate points. Then the geometric center of each set is calculated and the core coordinate points are updated accordingly. This process is repeated until the core coordinate points no longer change. Finally, the code outputs the geometric center coordinate point of the set containing the largest number of points as the true normal distribution range of the characteristic coordinate points of the power generation status.

[0079] See also Fig. 9 As shown, since the judgment in step S55 can only identify photovoltaic devices in normal state, it is necessary to further judge which are abnormal devices. In the specific operation, step S561 can be first executed to treat the power generation state characteristic coordinate points of photovoltaic devices that are not within the conventional distribution range as unconventional photovoltaic devices, so it cannot be judged whether they are abnormal.

[0080] If its power generation capacity after long-term use does not decline as much as other photovoltaic devices, it is also in a normal state. In order to make a judgment, for each unconventional photovoltaic device, step S562 can be first executed to obtain the power generation efficiency proportional coefficient of several photovoltaic devices in a normal state with the same equivalent working time as the unconventional photovoltaic device. Next, step S563 can be executed to determine whether the power generation efficiency proportional coefficient of the unconventional photovoltaic device is greater than the power generation efficiency proportional coefficient of several photovoltaic devices in a normal state with the same equivalent working time, that is, to compare the power generation capacity with the photovoltaic device in a normal state with the same equivalent working time. If so, it means that the degree of decline is low, then step S564 can be executed to determine that the power generation state of the unconventional photovoltaic device is normal. Otherwise, it means that the degree of decline is high, then step S565 can be executed to determine that the power generation state of the unconventional photovoltaic device is abnormal. Photovoltaic devices with excellent performance are selected by further comparison to avoid misjudgment.

[0081] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, system, method and computer program product according to multiple embodiments of the present application. In this regard, each square frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the square frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square frames can actually be executed substantially in parallel, and they can also be executed in reverse order sometimes, depending on the functions involved.

[0082] It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented by hardware that performs the corresponding function or action, such as a circuit or ASIC (Application Specific Integrated Circuit), or can be implemented by a combination of hardware and software, such as firmware.

[0083] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0084] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those of ordinary skill in the art without departing from the scope of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A device anomaly detection method, characterized in that: include, Obtain the cumulative power generation time and cumulative power generation of each photovoltaic device; Obtaining the equivalent working time of each photovoltaic device according to the accumulated power generation time and the accumulated power generation of each photovoltaic device; Obtaining the power generation of each photovoltaic device on the previous day and a number of adjacent days; Obtaining a power generation efficiency proportional coefficient of each photovoltaic device in a current state according to the power generation of each photovoltaic device on the previous day and a plurality of adjacent days; Determining whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient; If yes, marking the photovoltaic device as being in an abnormal state; If not, marking the photovoltaic device as being in a normal state; Outputting an identification code of the photovoltaic device marked as being in an abnormal state; Wherein, the step of obtaining the equivalent working time of each photovoltaic device according to the accumulated power generation time and the accumulated power generation of each photovoltaic device includes: Numerically arranging and extracting the accumulated power generation time and accumulated power generation of each photovoltaic device to obtain an accumulated working feature vector composed of the accumulated power generation time and accumulated power generation of each photovoltaic device; Calculate and obtain the proportional coefficient between the modulus lengths of the accumulated working characteristic vectors of each photovoltaic device as the fusion factor adjustment coefficient of each photovoltaic device, wherein the sum of the fusion factor adjustment coefficients of all the photovoltaic devices is 0.5; Calculate and obtain the proportionality coefficient between the accumulated power generation durations of the photovoltaic devices as the basic proportionality coefficient of each photovoltaic device, wherein the sum of the basic proportionality coefficients of all the photovoltaic devices is 0.5; Adding the corresponding fusion factor adjustment coefficient to the basic proportional coefficient of each photovoltaic device to obtain a correction proportional coefficient of each photovoltaic device; Calculate and obtain the cumulative sum of the accumulated power generation time of each photovoltaic device as the total power generation time; Multiplying the correction proportional coefficient of each photovoltaic device by the total power generation duration to obtain the equivalent working duration of each photovoltaic device; The step of obtaining the power generation efficiency proportional coefficient of each photovoltaic device in the current state according to the power generation of each photovoltaic device on the previous day and the adjacent days includes: For each of said photovoltaic devices, According to the power generation of the photovoltaic equipment on the previous day and the adjacent days, the highest power generation and the lowest power generation as well as the statistical days are obtained. The ratio of the difference between the highest power generation and the lowest power generation to the number of statistical days is taken as the daily average floating power generation. The power generation of the photovoltaic device on the previous day and the adjacent days is sorted according to the numerical value to obtain a power generation sequence, Calculate and compare to obtain multiple power generation amounts in the power generation amount sequence whose difference with adjacent power generation amounts is less than the daily average floating power generation amount to form a power generation amount collection, Obtaining the average of all power generation in the power generation collection containing the largest number of power generation as the steady-state average daily power generation of each photovoltaic device; Calculate and obtain the proportional coefficient between the steady-state average daily power generation of each photovoltaic device as the power generation efficiency proportional coefficient of each photovoltaic device in the current state; Wherein, the step of judging whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient includes: Arrange the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient in a set order to obtain a power generation state characteristic array of each photovoltaic device; Obtaining power generation state characteristic coordinate points of the power generation state characteristic array of each photovoltaic device in a two-dimensional plane; Obtaining a conventional distribution range of the power generation state characteristic coordinate points of the photovoltaic device in the two-dimensional plane according to the distribution state of the power generation state characteristic coordinate points of each photovoltaic device in the two-dimensional plane; Determining whether the power generation state characteristic coordinate point of each photovoltaic device is within the conventional distribution range; If yes, it is determined that the power generation state of the photovoltaic device is normal; If not, it is determined whether the power generation state of the photovoltaic device is abnormal based on the relative position relationship of the power generation state characteristic coordinate points of the photovoltaic device with respect to the normal distribution range.

2. The method according to claim 1, characterized in that The step of obtaining the conventional distribution range of the power generation state characteristic coordinate points of each photovoltaic device in the two-dimensional plane according to the distribution state of the power generation state characteristic coordinate points of each photovoltaic device in the two-dimensional plane comprises: Obtaining a real conventional distribution range of the power generation state characteristic coordinate points of the photovoltaic device in the two-dimensional plane according to the distribution state of the power generation state characteristic coordinate points of each photovoltaic device in the two-dimensional plane; Performing quadratic function fitting on all power generation state characteristic coordinate points within the real conventional distribution range to obtain an ideal functional relationship between the power generation efficiency proportional coefficient of the photovoltaic device and the equivalent working time as an ideal fitting function; Obtaining the shortest distance between each power generation state characteristic coordinate point within the real conventional distribution range in the two-dimensional plane and the ideal fitting function curve as the discrete distance of each power generation state characteristic coordinate point within the real conventional distribution range; Calculate and obtain the mean of the discrete distances of all the characteristic coordinate points of the power generation state within the real conventional distribution range as the extended distance; Taking the function curve of the ideal fitting function within the real conventional distribution range in the two-dimensional plane as the conventional function curve segment; A circle is drawn with each point of the conventional function curve segment as the center and the extension distance as the radius to obtain the coverage range of the circle corresponding to all points of the conventional function curve segment as the conventional distribution range of the characteristic coordinate points of the power generation state of the photovoltaic device in the two-dimensional plane.

3. The method according to claim 2, characterized in that The step of obtaining the real conventional distribution range of the power generation state characteristic coordinate points of the photovoltaic device in the two-dimensional plane according to the distribution state of the power generation state characteristic coordinate points of each photovoltaic device in the two-dimensional plane, include, Selecting two or more power generation state characteristic coordinate points from among all the power generation state characteristic coordinate points of the photovoltaic device as core power generation state characteristic coordinate points; Calculate and obtain the distance between each core power generation state characteristic coordinate point and each other power generation state characteristic coordinate point; Each other power generation state characteristic coordinate point and the closest core power generation state characteristic coordinate point form a coordinate point collection; Calculate and obtain the power generation state characteristic coordinate point in each of the coordinate point collections that is closest to the geometric center of the envelope of all power generation state characteristic coordinate points as the updated core power generation state characteristic coordinate point; Determine whether the characteristic coordinate points of the core power generation state have changed; If yes, then return to continuously update the coordinate point collection and the core power generation state characteristic coordinate points; If not, the envelope frame range of all power generation state characteristic coordinate points in the coordinate point set containing the largest number of power generation state characteristic coordinate points is output as the real preliminary regular distribution range in the two-dimensional plane.

4. The method according to claim 1, characterized in that: The step of judging whether the power generation state of the photovoltaic device is abnormal according to the relative position relationship of the power generation state characteristic coordinate points of the photovoltaic device with respect to the normal distribution range, include, The power generation state characteristic coordinate points of the photovoltaic device that are not within the conventional distribution range are regarded as unconventional photovoltaic devices; For each non-conventional photovoltaic device, Obtaining the power generation efficiency ratio coefficients of a plurality of photovoltaic devices in normal state having the same equivalent working time as the unconventional photovoltaic device, Determine whether the power generation efficiency ratio coefficient of the unconventional photovoltaic device is greater than the power generation efficiency ratio coefficients of a plurality of photovoltaic devices in a normal state with the same equivalent working time, If so, the power generation state of the unconventional photovoltaic device is judged to be normal; If not, the power generation state of the unconventional photovoltaic equipment is judged to be abnormal.

5. The method according to claim 1, characterized in that: Also includes, Perform maintenance and troubleshooting on the photovoltaic equipment marked as being in an abnormal state; The photovoltaic equipment after the obstacle is removed will be released from abnormal state and marked as normal state.

6. A device anomaly detection method, characterized in that: include, Obtain the identification code and corresponding location of each photovoltaic device; Obtaining an identification code of the photovoltaic device marked as being in an abnormal state in a device abnormality detection method according to any one of claims 1 to 5; Retrieving and comparing to obtain the location of the photovoltaic device marked as being in an abnormal state; The location of the photovoltaic device marked as being in an abnormal state is displayed.

7. A photovoltaic power generation equipment detection system, characterized in that: include, An abnormal equipment analysis unit is used to obtain the cumulative power generation time and cumulative power generation of each photovoltaic equipment; Obtaining the equivalent working time of each photovoltaic device according to the accumulated power generation time and the accumulated power generation of each photovoltaic device; Obtaining the power generation of each photovoltaic device on the previous day and a number of adjacent days; Obtaining a power generation efficiency proportional coefficient of each photovoltaic device in a current state according to the power generation of each photovoltaic device on the previous day and a plurality of adjacent days; Determining whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient; If yes, marking the photovoltaic device as being in an abnormal state; If not, marking the photovoltaic device as being in a normal state; Outputting an identification code of the photovoltaic device marked as being in an abnormal state; A maintenance guidance unit, used to obtain the identification code and corresponding location of each photovoltaic device; Acquire an identification code of the photovoltaic device marked as being in an abnormal state; Retrieving and comparing to obtain the location of the photovoltaic device marked as being in an abnormal state; Displaying the location of the photovoltaic device marked as abnormal state; Wherein, the step of obtaining the equivalent working time of each photovoltaic device according to the accumulated power generation time and the accumulated power generation of each photovoltaic device includes: Numerically arranging and extracting the accumulated power generation time and accumulated power generation of each photovoltaic device to obtain an accumulated working feature vector composed of the accumulated power generation time and accumulated power generation of each photovoltaic device; Calculate and obtain the proportional coefficient between the modulus lengths of the accumulated working characteristic vectors of each photovoltaic device as the fusion factor adjustment coefficient of each photovoltaic device, wherein the sum of the fusion factor adjustment coefficients of all the photovoltaic devices is 0.5; Calculate and obtain the proportionality coefficient between the accumulated power generation durations of the photovoltaic devices as the basic proportionality coefficient of each photovoltaic device, wherein the sum of the basic proportionality coefficients of all the photovoltaic devices is 0.5; Adding the corresponding fusion factor adjustment coefficient to the basic proportional coefficient of each photovoltaic device to obtain a correction proportional coefficient of each photovoltaic device; Calculate and obtain the cumulative sum of the accumulated power generation time of each photovoltaic device as the total power generation time; Multiplying the correction proportional coefficient of each photovoltaic device by the total power generation duration to obtain the equivalent working duration of each photovoltaic device; The step of obtaining the power generation efficiency proportional coefficient of each photovoltaic device in the current state according to the power generation of each photovoltaic device on the previous day and the adjacent days includes: For each of said photovoltaic devices, According to the power generation of the photovoltaic equipment on the previous day and the adjacent days, the highest power generation and the lowest power generation as well as the statistical days are obtained. The ratio of the difference between the highest power generation and the lowest power generation to the number of statistical days is taken as the daily average floating power generation. The power generation of the photovoltaic device on the previous day and the adjacent days is sorted according to the numerical value to obtain a power generation sequence, Calculate and compare to obtain multiple power generation amounts in the power generation amount sequence whose difference with adjacent power generation amounts is less than the daily average floating power generation amount to form a power generation amount collection, Obtaining the average of all power generation in the power generation collection containing the largest number of power generation as the steady-state average daily power generation of each photovoltaic device; Calculate and obtain the proportional coefficient between the steady-state average daily power generation of each photovoltaic device as the power generation efficiency proportional coefficient of each photovoltaic device in the current state; Wherein, the step of judging whether the power generation state of each photovoltaic device is abnormal according to the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient includes: Arrange the equivalent working time of each photovoltaic device and the corresponding power generation efficiency proportional coefficient in a set order to obtain a power generation state characteristic array of each photovoltaic device; Obtaining power generation state characteristic coordinate points of the power generation state characteristic array of each photovoltaic device in a two-dimensional plane; Obtaining a conventional distribution range of the power generation state characteristic coordinate points of the photovoltaic device in the two-dimensional plane according to the distribution state of the power generation state characteristic coordinate points of each photovoltaic device in the two-dimensional plane; Determining whether the power generation state characteristic coordinate point of each photovoltaic device is within the conventional distribution range; If yes, it is determined that the power generation state of the photovoltaic device is normal; If not, it is determined whether the power generation state of the photovoltaic device is abnormal based on the relative position relationship of the power generation state characteristic coordinate points of the photovoltaic device with respect to the normal distribution range.

Images