A photovoltaic module intelligent monitoring method and system

By analyzing the horizontal and vertical difference coefficients of photovoltaic modules and combining them with meteorological data, the ABOD anomaly detection algorithm was adopted to solve the problem of untimely handling of minor anomalies in photovoltaic module monitoring, thereby improving the sensitivity and accuracy of monitoring.

CN119010787BActive Publication Date: 2025-11-28BAODING YUNYING ENERGY TECH CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411042541.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2025-11-28
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

Existing photovoltaic module monitoring methods are not timely in handling minor anomalies, which leads to a cumulative impact on module lifespan, and it is difficult to distinguish between environmental factors and module anomalies.

Method used

By analyzing the horizontal and vertical difference coefficients between photovoltaic modules and combining meteorological environmental data, anomaly weights are determined, and the ABOD anomaly detection algorithm is used to monitor module anomalies.

Benefits of technology

It improves the sensitivity and accuracy of detecting anomalies in photovoltaic modules, enabling timely detection of minor differences and reducing the impact on module lifespan.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119010787B_ABST
    Figure CN119010787B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of photovoltaic module monitoring, in particular to a photovoltaic module intelligent monitoring method and system, which comprises the following steps: acquiring the current, output power of each photovoltaic module at each time, and meteorological environment data at each time, including light intensity, ambient temperature, wind speed and humidity; determining the transverse difference coefficient of each photovoltaic module at each time; determining the longitudinal difference coefficient of each photovoltaic module at each time; determining the abnormal weight of each photovoltaic module at each time; determining the angle-based abnormal factor of each photovoltaic module at each time, and performing abnormal monitoring on the photovoltaic module. The application can improve the capturing ability of various small differences in photovoltaic module monitoring and improve the accuracy of photovoltaic module abnormal monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic module monitoring, in particular to a photovoltaic module intelligent monitoring method and system. BACKGROUND

[0002] With the transformation of global energy structure, photovoltaic power generation as a clean and renewable energy source is increasingly applied. Photovoltaic modules as the core components of photovoltaic power generation systems, their performance directly affects the power generation efficiency of the entire photovoltaic system. Therefore, the monitoring of photovoltaic modules has become the focus of research in the field of photovoltaic power generation.

[0003] In the existing photovoltaic module intelligent monitoring, the commonly used methods are divided into two kinds, one is to build a simulation model of the photovoltaic system, and to determine whether there is an abnormal photovoltaic module according to the difference between the simulation value and the actual value; the other is to determine whether there is an abnormal photovoltaic module by monitoring the difference between the data and the historical data of the photovoltaic module; the dependence of these two methods on the historical data of the photovoltaic module is strong. There is always a difference between the monitoring data and the historical data, and the reason for this difference may be due to environmental factors or abnormalities of the photovoltaic module itself, but it is difficult to distinguish. In the prior art, for such a difference, if the difference is small, it is determined that there is no abnormal photovoltaic module, but if the small difference is caused by the abnormality of the photovoltaic module itself, if it is not paid attention to in time, but is processed when a significant difference appears, the accumulation of the small abnormality will have an irreversible impact on the service life of the photovoltaic module itself. SUMMARY

[0004] In order to solve the above technical problems, a photovoltaic module intelligent monitoring method and system are provided to solve the existing problems.

[0005] The technical problem solved by the present application is to provide a photovoltaic module intelligent monitoring method and system, comprising the following steps:

[0006] In the first aspect, the present application provides a photovoltaic module intelligent monitoring method, which comprises the following steps:

[0007] Obtaining the current, output power of each photovoltaic module at each time, and the meteorological environmental data at each time, including light intensity, environmental temperature, wind speed and humidity;

[0008] According to the differences in current, output power and seasonal periodic characteristics of output power between different photovoltaic modules at each time, determining the lateral difference coefficient of each photovoltaic module at each time;

[0009] determine a longitudinal difference coefficient of each photovoltaic module at each time according to a difference of current and output power of each photovoltaic module between each time and the same time of its historical day, and an influence of meteorological environment data on the output power;

[0010] determine an abnormal weight of each photovoltaic module at each time based on the transverse difference coefficient and the longitudinal difference coefficient;

[0011] determine an angle-based abnormal factor of each photovoltaic module at each time based on the abnormal weight, and perform abnormal monitoring on the photovoltaic module.

[0012] Preferably, the determination of the transverse difference coefficient of each photovoltaic module at each time comprises:

[0013] determine a first difference between each photovoltaic module and the rest of the photovoltaic modules according to a difference of seasonal periodic characteristics and a correlation degree of current and output power;

[0014] determine a first similarity between each photovoltaic module at each time and the rest of the photovoltaic modules at the same time according to a correlation degree of current and output power;

[0015] record a first ratio of the first difference and the first similarity between each photovoltaic module and the rest of the photovoltaic modules as a first ratio;

[0016] fuse the first ratio of each photovoltaic module and the rest of the photovoltaic modules at each time to determine the transverse difference coefficient of each photovoltaic module at each time.

[0017] Preferably, the determination of the first difference between each photovoltaic module and the rest of the photovoltaic modules comprises:

[0018] calculate a seasonal intensity of each photovoltaic module by using a sequence decomposition algorithm on the output power of each photovoltaic module at all times;

[0019] determine a difference of seasonal intensity between each photovoltaic module and the rest of the photovoltaic modules as the first difference between each photovoltaic module and the rest of the photovoltaic modules.

[0020] Preferably, the determination of the first similarity between each photovoltaic module at each time and the rest of the photovoltaic modules comprises:

[0021] compose a photovoltaic output vector of each photovoltaic module at each time by using current and output power of each photovoltaic module at each time;

[0022] The similarity degree of the photovoltaic output vector between each photovoltaic module at each time and the rest of the photovoltaic modules at the same time is calculated, and the calculation result of an exponential function with a natural constant as a base number and the similarity degree as an index is taken as the first similarity degree of each photovoltaic module at each time and the rest of the photovoltaic modules.

[0023] Preferably, the determination of the longitudinal difference coefficient of each photovoltaic module at each time comprises:

[0024] The ratio between the sum of the light intensity and the wind speed at each time and the sum of the ambient temperature and the humidity is taken as the environmental influence coefficient at each time.

[0025] The correlation degree between the output power of each photovoltaic module at all times before each time and the environmental influence coefficient is analyzed to determine the second similarity degree of each photovoltaic module at each time.

[0026] All times are divided into each time of each day according to the date to which the time belongs, and the average of the similarity degrees of the photovoltaic output vector of each photovoltaic module between each time and the same time of all historical days of each day is calculated.

[0027] The product of the average and the second similarity degree is recorded as a first product, and the reciprocal of the result of an exponential function with a natural constant as a base number and the first product as an index is taken as the longitudinal difference coefficient of each photovoltaic module at each time.

[0028] Preferably, the determination of the second similarity degree of each photovoltaic module at each time comprises:

[0029] The output power of each photovoltaic module at all times before each time and the environmental influence coefficient are respectively taken as an output power sequence and an environmental influence sequence at each time.

[0030] The second similarity degree of each photovoltaic module at each time is determined according to the correlation degree between the output power sequence and the environmental influence sequence.

[0031] Preferably, the determination of the abnormal weight of each photovoltaic module at each time is expressed as: wherein, W i,t is the abnormal weight of the ith photovoltaic module at the tth time, A i,t is the horizontal difference coefficient of the ith photovoltaic module at the tth time, C i,t is the longitudinal difference coefficient of the ith photovoltaic module at the tth time, and w0 is a preset initial weight; and a is a preset control coefficient.

[0032] Preferably, the determination of the angle-based abnormal factor of each photovoltaic module at each time comprises:

[0033] The current, output power, light intensity, ambient temperature, wind speed and humidity of each photovoltaic module at each time are combined to form an abnormality monitoring vector of each photovoltaic module at each time;

[0034] The abnormality weights of each photovoltaic module at all times are normalized, and the abnormality monitoring vectors of each photovoltaic module at each time and all times before the time and the normalized abnormality weights are input into an ABOD abnormality detection algorithm to obtain an angle-based abnormality factor of each photovoltaic module at each time.

[0035] Preferably, the abnormality monitoring of the photovoltaic module comprises:

[0036] The angle-based abnormality factor of each photovoltaic module at all times is segmented by a threshold value to obtain an optimal threshold value.

[0037] If the angle-based abnormality factor is less than or equal to the optimal threshold value, the photovoltaic module has an abnormality, otherwise, the photovoltaic module has no abnormality.

[0038] In a second aspect, the embodiments of the present application further provide a photovoltaic module intelligent monitoring system, comprising a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of the photovoltaic module intelligent monitoring method of any one of the above.

[0039] The present application has at least the following beneficial effects:

[0040] The present application determines a horizontal difference coefficient of each photovoltaic module at each time by analyzing the differences in current, output power and seasonal periodic characteristics of output power between different photovoltaic modules at each time, which has the beneficial effect of considering the differences between different photovoltaic modules in the same external environment at the same time, thereby eliminating errors caused by environmental factors; determines a vertical difference coefficient of each photovoltaic module at each time according to the differences in current and output power of each photovoltaic module between each time and the same time of each day in history, and the influence of meteorological environment on output power, which has the beneficial effect of considering the change differences in current and output power of the same photovoltaic module at different times, which helps to improve the judgment of abnormal conditions of photovoltaic modules; determines an abnormality weight of each photovoltaic module at each time based on the horizontal difference coefficient and the vertical difference coefficient; determines an angle-based abnormality factor of each photovoltaic module at each time based on the abnormality weight, and performs abnormality monitoring of the photovoltaic module, which has the beneficial effect of measuring the degree of abnormality of the photovoltaic module, and simultaneously considering the horizontal difference and vertical difference of the photovoltaic module, enhancing the capture ability of various difference changes in photovoltaic module monitoring, being able to find small difference changes in monitoring data, and improving the sensitivity and accuracy of abnormality troubleshooting of photovoltaic modules. BRIEF DESCRIPTION OF DRAWINGS

[0041] The application provides a photovoltaic module intelligent monitoring method.

[0042] Figure 1 A step flow chart of the photovoltaic module intelligent monitoring method provided by the application is shown in FIG. 1.

[0043] Figure 2 A step flow chart of the method for obtaining the transverse difference coefficient of each photovoltaic module at each time point provided by the application is shown in FIG. 2.

[0044] Figure 3 A step flow chart of the method for obtaining the longitudinal difference coefficient of each photovoltaic module at each time point provided by the application is shown in FIG. 3. DETAILED DESCRIPTION

[0045] In order to make the objects, technical solutions and advantages of the application clearer, the application provides a photovoltaic module intelligent monitoring method and system, which are further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the application belongs.

[0047] Referring to FIG. 1, Figure 1 A step flow chart of the photovoltaic module intelligent monitoring method provided by the application is shown in FIG. 1, which comprises the following steps.

[0048] Step 1: obtaining the current and output power of each photovoltaic module at each time point, and the meteorological environmental data at each time point, including the light intensity, ambient temperature, wind speed and humidity.

[0049] The direct current and output power of each photovoltaic module are collected in real time through the current transformer installed on the output line of each photovoltaic module and the power meter installed on the output end of each photovoltaic module, and then the environmental data during photovoltaic operation, including the light intensity, ambient temperature, wind speed and humidity, are collected in real time through the radiation meter, temperature sensor, anemometer and humidity sensor, and the collection time interval is t. All the collected data are uploaded to the photovoltaic module intelligent monitoring system for storage. The current and output power of each photovoltaic module at each time point and the light intensity, ambient temperature, wind speed and humidity at each time point are obtained from the photovoltaic module intelligent monitoring system.

[0050] Preferably, in the embodiment, the collection time interval is 10 min, and as other embodiments, the implementer can set it according to the actual situation.

[0051] At this point, the current, output power of each photovoltaic module at each time, and the light intensity, ambient temperature, wind speed and humidity at each time are obtained.

[0052] Step 2, according to the differences in current, output power between different photovoltaic modules at each time and the seasonal periodic characteristics of output power, determine the lateral difference coefficient of each photovoltaic module at each time.

[0053] In the intelligent monitoring of photovoltaic modules, the error caused by the slight abnormality of the photovoltaic module itself can be determined by the difference between different photovoltaic modules at the same time. However, due to the state of different photovoltaic modules themselves, such as shading and dirt, the current and output power of different photovoltaic modules are affected. There are many reasons affecting the change of the current and output power of photovoltaic modules, and it is impossible to completely determine the abnormality of photovoltaic modules only by the difference between the current and output power of different photovoltaic modules. It needs to be analyzed from multiple dimensions. Therefore, it is necessary to compare the differences between different photovoltaic modules horizontally; and combine the vertical differences between each photovoltaic module and its historical time for comprehensive analysis, so as to determine whether the photovoltaic module is abnormal.

[0054] Under normal circumstances, the running state of all photovoltaic modules in the photovoltaic system and the change of the environment have a certain relationship, so that the change of the current and output power of each photovoltaic module should be relatively consistent. And because the power generation of photovoltaic modules is affected by light intensity, the light intensity has certain seasonal periodic characteristics, so that the output power of photovoltaic modules has periodic change. However, when the running state of photovoltaic modules is not completely the same, photovoltaic modules may be affected by variable shading (such as tree shadow, building shadow), unchanging shading (such as leaves, bird droppings) or global abnormality (such as dust), so that there is a certain difference between different photovoltaic modules. Secondly, variable shading is mostly caused by shadow, so it has periodic change, while the occurrence of unchanging shading has accidental nature, so it will destroy the periodicity to some extent.

[0055] Based on the above analysis, the difference between the current and output power of different photovoltaic modules is analyzed, and the lateral difference coefficient is constructed, which is:

[0056] The output power of each photovoltaic module at all times is decomposed by sequence decomposition algorithm, and the seasonal intensity of each photovoltaic module is calculated.

[0057] Preferably, in the embodiment, the STL time series decomposition algorithm is adopted, wherein the seasonal cycle length parameter is 144, and the STL time series decomposition algorithm and the calculation of the seasonal intensity are known technologies, which will not be described here. As other embodiments, the implementer can adopt other methods in the prior art, such as the X-11 sequence decomposition algorithm, and the embodiment does not specially limit this.

[0058] It should be noted that the output power of the photovoltaic module is related to the light intensity, and the light intensity has a daily periodicity, that is, the light intensity and the change of the light intensity at each time of the day are similar or the same in most cases. Therefore, 144 time points of data can be collected each day, so that the seasonal cycle length parameter in the STL time series decomposition algorithm is 144. Secondly, the seasonal intensity of each photovoltaic module is calculated, including: the output power of each photovoltaic module at all time points is decomposed by using the sequence decomposition algorithm to obtain a seasonal sequence and a residual sequence, and the calculation formula of the seasonal intensity is: Wherein, F T is the trend intensity, Var(R t ) is the variance of the residual sequence, Var(R S +T t ) is the variance of the seasonal sequence and the residual sequence, and max() is the maximum value.

[0059] The difference between each photovoltaic module and the seasonal intensity of the remaining photovoltaic modules is taken as the first difference between each photovoltaic module and the remaining photovoltaic modules;

[0060] The current and the output power of each photovoltaic module at each time point are combined to form a photovoltaic output vector of each photovoltaic module at each time point;

[0061] The similarity between each photovoltaic module and the remaining photovoltaic modules at the same time is calculated, and the calculation result of the exponential function with the natural constant as the base and the similarity as the index is taken as the first similarity between each photovoltaic module and the remaining photovoltaic modules;

[0062] The ratio of the first difference and the first similarity between each photovoltaic module and the remaining photovoltaic modules is recorded as the first ratio;

[0063] The first ratio between each photovoltaic module and the remaining photovoltaic modules at each time point is fused to determine the horizontal difference coefficient of each photovoltaic module at each time point;

[0064] It can be understood that the fusion specific relationship can be an addition relationship, a multiplication relationship, etc., and the specific relationship is determined according to the actual scene, and the embodiment does not specially limit this.

[0065] Preferably, in the embodiment, the cosine similarity of the photovoltaic output vector between each photovoltaic module and the rest of the photovoltaic modules at the same time is obtained, thereby obtaining a first similarity, wherein the calculation method of the cosine similarity is a known technology, which will not be described here.

[0066] In the embodiment, the calculation method of the transverse difference coefficient of each photovoltaic module at each time is as follows: Wherein, A i,t is the transverse difference coefficient of the ith photovoltaic module at the tth time, S i,t is the seasonal intensity of the ith photovoltaic module at the tth time, S j,t is the seasonal intensity of the jth photovoltaic module at the tth time, E i,t is the photovoltaic output vector of the ith photovoltaic module at the tth time, E j,t is the photovoltaic output vector of the jth photovoltaic module at the tth time, N is the number of all photovoltaic modules, R() is the calculation of similarity, and exp() is the exponential function with the natural constant as the base.

[0067] It can be understood that the embodiment measures the similarity between two vectors by cosine similarity. As an alternative, the implementer can use other methods in the prior art, such as Pearson correlation coefficient, DTW distance, etc. The embodiment does not make special limitations on this.

[0068] It should be noted that when the photovoltaic module is in a normal operating state, the operating state of each photovoltaic module and the rest of the photovoltaic modules is basically consistent, and the first similarity is larger. The output power of the normal photovoltaic module is consistent with the light intensity, and the light intensity has periodicity, so that the output power of the photovoltaic module at different times also has periodicity, and the periodic difference of the output power between different photovoltaic modules is small, that is, the first difference is small, and the transverse difference coefficient of the photovoltaic module is small, which indicates that the operating state of the photovoltaic module and the rest of the photovoltaic modules is consistent, and the possibility of abnormality of the photovoltaic module is smaller.

[0069] Further, the step flow chart of the method for obtaining the transverse difference coefficient of each photovoltaic module at each time provided by the embodiment is as shown in Figure 2 .

[0070] Thus, the transverse difference coefficient of each photovoltaic module at each time is obtained.

[0071] Step 3, according to the difference of the current and output power of each photovoltaic module between each time and the same time of each day in history, and the influence of meteorological environmental data on the output power, the longitudinal difference coefficient of each photovoltaic module at each time is determined.

[0072] Based on the above analysis, the transverse difference coefficient can only compare the differences between different photovoltaic modules at the same time. However, if there is an abnormality in the entire photovoltaic system, for example, the surface of the photovoltaic module is covered with dust, thereby affecting the power generation, such global abnormality cannot be found through the transverse difference, so it is necessary to compare and analyze all the historical data of the photovoltaic module to further determine whether the photovoltaic module is abnormal.

[0073] For a photovoltaic module in a normal operating state, the power generation is related to the light intensity, and the light intensity has a daily periodicity, so that the daily power generation of the photovoltaic module should be basically consistent. However, due to different environmental conditions, there may be certain volatility in power generation, but such volatility is related to environmental data.

[0074] By calculating the correlation coefficients of the light intensity, wind speed, environmental temperature and humidity and the output power at all times respectively, it is found that the light intensity and wind speed have a positive correlation with the output power of the photovoltaic module, while the environmental temperature and humidity have a negative correlation with the output power of the photovoltaic module. However, theoretically, when the environmental temperature is high, the light intensity is also strong, and the output power of the photovoltaic module is often high. However, in practice, the higher the environmental temperature, the lower the output power, and the power generation will also decrease accordingly. Therefore, the correlation coefficient only represents the correlation between the single factor of environmental temperature and the photovoltaic power generation, and cannot reflect the influence of multiple coupling between other meteorological factors on the correlation. Therefore, based on the correlation coefficient, the influence of the meteorological environment on the output power of the photovoltaic module is analyzed, which is specifically:

[0075] The sum of the light intensity and the wind speed at each time is denoted as a first sum value; the sum of the environmental temperature and humidity at each time is denoted as a second sum value;

[0076] The ratio of the first sum value to the second sum value is taken as the environmental influence coefficient at each time;

[0077] Further, since the output power is related to the light intensity, the light intensity has a daily periodicity, that is, the light intensity increases first and then decreases every day, therefore, by comparing and analyzing the difference between the output power of the photovoltaic module at each time and the historical time, a longitudinal difference coefficient of each photovoltaic module at each time is constructed, which is specifically:

[0078] The output power of each photovoltaic module at all times before each time and the environmental influence coefficient are respectively combined to form an output power sequence and an environmental influence sequence at each time;

[0079] According to the correlation degree between the output power sequence and the environmental influence sequence, a second similarity of each photovoltaic module at each time is determined;

[0080] dividing all time points into each time point of each day according to the date to which the time point belongs, calculating the average of the similarity degree of the photovoltaic output vector of each photovoltaic module between each time point and the same time point of each day in all historical data;

[0081] taking the product of the average and the second similarity degree as a first product, and taking the reciprocal of the result of the exponential function with the first product as the index and the natural constant as the base as the longitudinal difference coefficient of each photovoltaic module at each time point;

[0082] Preferably, in the embodiment, the Pearson correlation coefficient between the output power sequence and the environmental influence sequence is calculated as the second similarity degree of each photovoltaic module at each time point; and the average of the cosine similarity of the photovoltaic output vector of each photovoltaic module between each time point and the same time point of each day in all historical data.

[0083] In the embodiment, the longitudinal difference coefficient of each photovoltaic module at each time point is calculated by the following method: wherein, C i,t is the longitudinal difference coefficient of the ith photovoltaic module at the tth time point, R i ′ ,t is the second similarity degree of the ith photovoltaic module at the tth time point, is the average of the similarity degree of the photovoltaic output vector of the ith photovoltaic module between the tth time point and the same time point of each day in all historical data.

[0084] It can be understood that the Pearson correlation coefficient and the cosine similarity are used to measure the similarity degree in the embodiment, and other methods can be used to measure the similarity degree in other embodiments, for example, the DTW distance, the Euclidean distance, etc., and the embodiment does not specially limit this.

[0085] It should be noted that when the operating state of the photovoltaic module is normal, the output power of the photovoltaic module at the corresponding time point and the output power at the same time point of each day in all historical data basically remain consistent, that is, larger; and the output power of the photovoltaic module and the environmental influence coefficient have a positive correlation, that is, the second similarity degree is larger, so the longitudinal difference coefficient C is smaller. Conversely, when the photovoltaic module is abnormal, the output power of the photovoltaic module will be affected, and the difference between the photovoltaic module and the historical data is larger; and because of the existence of such abnormality, the photovoltaic module will be affected, and the output power and the environmental influence coefficient will be affected, so the positive correlation between the output power and the environmental influence coefficient is weakened, and the longitudinal difference coefficient is larger.

[0086] Further, the step flow chart of the method for obtaining the longitudinal difference coefficient of each photovoltaic module at each time point provided in the embodiment is shown in Figure 3 .

[0087] At this point, the longitudinal difference coefficient of each photovoltaic module at each time is obtained.

[0088] Step 4, based on the transverse difference coefficient and the longitudinal difference coefficient, determining the abnormal weight of each photovoltaic module at each time.

[0089] Based on the above analysis, through the transverse difference coefficient and the longitudinal difference coefficient, four difference cases may occur, specifically: first, if the transverse difference coefficient is large and the longitudinal difference coefficient is also large, then the difference between the photovoltaic module and the remaining photovoltaic modules is large, and the difference with the historical data is also large, indicating that the abnormality of the photovoltaic module at this time may be sudden, such as bird droppings, leaves and other unchangeable obstructions, which need to be handled in time, otherwise it will affect the service life of the photovoltaic module; second, if the longitudinal difference coefficient is large, but the transverse difference coefficient is small, then the difference between the photovoltaic module and the remaining photovoltaic modules is small, and the difference with the historical data is large, indicating that the photovoltaic module or the entire photovoltaic system has a global abnormality at this time, such as dust, which needs to be cleaned in time, otherwise it will affect the power generation efficiency of the photovoltaic module even the safety of the photovoltaic module; third, if the longitudinal difference coefficient is small, but the transverse difference coefficient is large, then the difference between the photovoltaic module and the remaining photovoltaic modules is large, and the difference with the historical data is small, indicating that the photovoltaic module has a long-term and continuous abnormality at this time, which leads to the difference with other photovoltaic modules, for example, variable shading abnormality, which is caused by shadow and other factors, but this kind of shading only affects the light intensity of the photovoltaic module, and it is determined by the geographical location of the photovoltaic module installation, and there is no damage to the photovoltaic module itself, and no treatment is needed; fourth, if the longitudinal difference coefficient is small, and the transverse difference coefficient is small, then the difference between the photovoltaic module and the remaining photovoltaic modules is small, and the difference with the historical data is also small, indicating that the photovoltaic module is in a normal operating state at this time.

[0090] Based on the above analysis, the abnormal weight is constructed to reflect the abnormality of each photovoltaic module, specifically:

[0091] The abnormal weight of each photovoltaic module at each time is: Wherein, W i,t is the abnormal weight of the i-th photovoltaic module at the t-th time, A i,t is the transverse difference coefficient of the i-th photovoltaic module at the t-th time, C i,t is the longitudinal difference coefficient of the i-th photovoltaic module at the t-th time, w0 is a preset initial weight, which is taken as 1 in this embodiment; a is a preset control coefficient, which is taken as 2 in this embodiment.

[0092] It should be noted that the preset control coefficient is set to a value greater than 1, and the specific value can be determined according to the range of the longitudinal difference coefficient. The value range of the longitudinal difference coefficient of the photovoltaic module in the normal operating state is Therefore Because the value of C is at most 1, C i,t is at least That is, when C i,t is at most 2, the value range of the longitudinal difference coefficient of the photovoltaic module is at this time, the corresponding photovoltaic module is in a normal operating state. Therefore, when the preset control coefficient a is 2, the value range of the longitudinal difference coefficient of the photovoltaic module is at this time, the corresponding photovoltaic module is in a normal operating state. When the preset control coefficient a is 3, the value range of the longitudinal difference coefficient of the photovoltaic module is at this time, the corresponding photovoltaic module is in a normal operating state. The limitation of the abnormal situation of the photovoltaic module is more stringent. Therefore, as other embodiments, the implementer can set it according to the actual situation.

[0093] It should be noted that when the photovoltaic module has a constant shading, the transverse difference coefficient and the longitudinal difference coefficient are both large, and greater than 0, so that the abnormal weight is large, and the more serious the abnormal situation of the corresponding photovoltaic module, the larger the abnormal weight. When the photovoltaic module has a global abnormality, the longitudinal difference coefficient is large, and the transverse difference coefficient is small, that is, A is large and C is small, and greater than 0, so that the abnormal weight is also greater than w0, and the abnormal weight of the photovoltaic module in the normal state is large. When the photovoltaic module has a variable shading, the longitudinal difference is small, and the transverse difference is large, that is, A is large and C is small, and less than 0, so that the abnormal weight is 1, which is relatively small. When the photovoltaic module is normal, A and C are both small, and less than 0, so that the abnormal weight is small, and the value is 1 at this time.

[0094] At this point, the abnormal weight of each photovoltaic module at each time is obtained.

[0095] Step 5, based on the abnormal weight, determining the angle-based abnormal factor of each photovoltaic module at each time, and monitoring the abnormality of the photovoltaic module.

[0096] Further, based on the abnormal weight, the abnormal situation of each photovoltaic module is monitored, specifically:

[0097] The current, output power, light intensity, environmental temperature, wind speed and humidity of each photovoltaic module at each time are combined to form an abnormal monitoring vector of each photovoltaic module at each time;

[0098] normalizing the abnormal weight of each photovoltaic module at all time points, inputting the abnormal monitoring vector of each photovoltaic module at each time point and all time points before the time point and the normalized abnormal weight into an ABOD abnormality detection algorithm to obtain an angle-based abnormality factor of each photovoltaic module at each time point;

[0099] Preferably, in the embodiment, the abnormal weight of each photovoltaic module at all time points is normalized by using a maximum-minimum value normalization method, wherein the maximum-minimum value normalization method is a known technology and will not be described here again. As other implementation manners, the implementer can use other methods in the prior art, for example, mean normalization method, and the embodiment does not specially limit this.

[0100] It should be noted that the ABOD abnormality detection algorithm is a known technology and the specific process will not be described here again. The angle-based abnormality factor of each photovoltaic module at each time point is calculated by using the ABOD abnormality detection algorithm, which needs to be adjusted. When the angle of each photovoltaic module at each time point is calculated, the abnormal weight of the corresponding time point needs to be considered. By assigning different abnormal weights to different time points, the horizontal and vertical differences of different time points in the scene are considered, and a greater weight is assigned to the corresponding time point of the photovoltaic module with a more serious abnormality, which helps to improve the accuracy of abnormality detection. The following angle calculation formula is used: i,t i,t i,t i,t is the angle of the ith photovoltaic module at the tth time point, W i,t is the abnormal weight of the ith photovoltaic module at the tth time point, ω i,t is the original angle of the ith photovoltaic module at the tth time point obtained by using the angle calculation method in the ABOD abnormality detection algorithm.

[0101] The angle-based abnormality factor of each photovoltaic module at all time points is segmented by using a threshold segmentation algorithm to obtain an optimal threshold.

[0102] If the angle-based abnormality factor of each photovoltaic module at each time point is less than or equal to the optimal threshold, the corresponding photovoltaic module has an abnormality at this time and needs to be repaired. If the angle-based abnormality factor of each photovoltaic module at each time point is greater than the optimal threshold, the corresponding photovoltaic module has no abnormality at this time, and the photovoltaic module is monitored.

[0103] Preferably, in the embodiment, the optimal threshold is obtained by using the Otsu threshold segmentation algorithm. As other implementation manners, the implementer can use other methods in the prior art, for example, histogram construction method, and the embodiment does not specially limit this.

[0104] ​​​It should be noted that the greater the angle-based abnormal factor, the smaller the abnormality degree of the corresponding photovoltaic module, and the greater the possibility of being in a normal operating state. The smaller the angle-based abnormal factor, the greater the possibility of the corresponding photovoltaic module being abnormal.

[0105] Based on the same inventive concept as the above method, the embodiments of the present application also provide a photovoltaic module intelligent monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above photovoltaic module intelligent monitoring methods when executing the computer program.

[0106] It should be understood that, although Figure 1 The steps in the flowchart of the above embodiment are displayed in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps in the above embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with other steps or sub-steps or stages of other steps.

[0107] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0108] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation of the present application. It should be noted that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application, without departing from the technical solution of the present application, all belong to the protection scope of the present application.

Claims

1. A method for intelligent monitoring of a photovoltaic assembly, characterized in that, The method comprises the following steps: Obtaining the current, output power of each photovoltaic module at each time, and meteorological environmental data at each time, including light intensity, ambient temperature, wind speed and humidity; Determine the lateral difference coefficient of each photovoltaic module at each time according to the difference of current, output power between different photovoltaic modules at each time and the seasonal periodic characteristics of output power, which is used to represent the difference between different photovoltaic modules at the same time under the same external environment; Determine the longitudinal difference coefficient of each photovoltaic module at each time according to the difference of current and output power of each photovoltaic module between each time and the same time of each day in history, and the influence of meteorological environmental data on output power, which is used to represent the change difference of current and output power of the same photovoltaic module at different times; The determination of the longitudinal difference coefficient of each photovoltaic module at each time comprises: taking the ratio of the sum of light intensity and wind speed to the sum of ambient temperature and humidity at each time as the environmental influence coefficient at each time; Analyze the correlation between the output power of each photovoltaic module at all times before each time and the environmental influence coefficient to determine the second similarity of each photovoltaic module at each time; Calculate the average of the similarity of photovoltaic output vector between each photovoltaic module at each time and the same time of all historical days; Take the product of the average and the second similarity as the first product; Take the reciprocal of the result of the exponential function with the natural constant as the base and the first product as the exponent as the longitudinal difference coefficient of each photovoltaic module at each time; The determination of the second similarity of each photovoltaic module at each time comprises: respectively forming the output power sequence and the environmental influence sequence of each photovoltaic module at each time according to the output power and the environmental influence coefficient of each photovoltaic module at all times before each time; Determine the second similarity of each photovoltaic module at each time according to the correlation between the output power sequence and the environmental influence sequence. Based on the horizontal and vertical difference coefficients, the anomaly weight of each photovoltaic module at each time point is determined; the expression for determining the anomaly weight of each photovoltaic module at each time point is: ,in, For the first At the [time]th moment Abnormal weights of individual photovoltaic modules For the first At the [time]th moment The horizontal difference coefficient of each photovoltaic module For the first At the [time]th moment The longitudinal variation coefficient of each photovoltaic module Preset initial weights; These are preset control coefficients; Determine the angle-based abnormal factor of each photovoltaic module at each time based on the abnormal weight to monitor the abnormality of the photovoltaic module.

2. A method of intelligent monitoring of a photovoltaic assembly according to claim 1, characterized in that, The determination of the lateral difference coefficient of each photovoltaic module at each time comprises: Analyze the difference of seasonal periodic characteristics between each photovoltaic module and the remaining photovoltaic modules, and the correlation of current and output power to determine the first difference between each photovoltaic module and the remaining photovoltaic modules; Analyze the correlation of current and output power between each photovoltaic module at each time and the remaining photovoltaic modules at the same time to determine the first similarity between each photovoltaic module at each time and the remaining photovoltaic modules; Take the ratio of the first difference and the first similarity between each photovoltaic module and the remaining photovoltaic modules as the first ratio; Fuse the first ratio of each photovoltaic module at each time and all the remaining photovoltaic modules to determine the lateral difference coefficient of each photovoltaic module at each time.

3. A method of intelligent monitoring of a photovoltaic assembly according to claim 2, wherein, The determination of the first difference between each photovoltaic module and the remaining photovoltaic modules comprises: Using sequence decomposition algorithm to calculate the seasonal intensity of each photovoltaic module for the output power of each photovoltaic module at all times; Differences in seasonal intensity between each photovoltaic module and the rest of the photovoltaic modules are taken as the first differences between each photovoltaic module and the rest of the photovoltaic modules.

4. A method of intelligent monitoring of a photovoltaic assembly according to claim 2, wherein, The determination of the first similarity between each photovoltaic module and the rest of the photovoltaic modules at each time comprises: The current and output power of each photovoltaic module at each time are combined to form a photovoltaic output vector of each photovoltaic module at each time. The similarity of the photovoltaic output vector between each photovoltaic module and the rest of the photovoltaic modules at the same time is calculated, and the calculation result of an exponential function with a natural constant as the base number and the similarity as the index is taken as the first similarity between each photovoltaic module and the rest of the photovoltaic modules at each time.

5. The method of claim 1, wherein the method further comprises: The determination of the angle-based abnormality factor of each photovoltaic module at each time comprises: The current, output power, light intensity, ambient temperature, wind speed and humidity of each photovoltaic module at each time are combined to form an abnormality monitoring vector of each photovoltaic module at each time. The abnormality weights of each photovoltaic module at all times are normalized, and the abnormality monitoring vector of each photovoltaic module at each time and all times before it and the normalized abnormality weight are input into an ABOD abnormality detection algorithm to obtain the angle-based abnormality factor of each photovoltaic module at each time.

6. A method for intelligent monitoring of a photovoltaic module as recited in claim 1, wherein, The abnormality monitoring of the photovoltaic module comprises: The angle-based abnormality factor of each photovoltaic module at all times is subjected to a threshold segmentation algorithm to obtain an optimal threshold value. If the angle-based abnormality factor is less than or equal to the optimal threshold value, the photovoltaic module has an abnormality, otherwise, the photovoltaic module has no abnormality.

7. An intelligent monitoring system for photovoltaic modules, comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that, The processor executes the computer program to realize the steps of the photovoltaic module intelligent monitoring method according to any one of claims 1-6.

Citation Information

Patent Citations

  • Method and device for judging fault type of photovoltaic module

    CN109271736A

  • Method and device for determining running state of photovoltaic power station

    CN115833746A