CN116073761A

CN116073761A - Fault diagnosis method and device for photovoltaic power station and photovoltaic system

Info

Publication number: CN116073761A
Application number: CN202211730452.6A
Authority: CN
Inventors: 周冰钰; 张家前; 王学能; 方振宇; 张锐
Original assignee: Sunshine Zhiwei Technology Co ltd
Current assignee: Sunshine Zhiwei Technology Co ltd
Priority date: 2022-12-30
Filing date: 2022-12-30
Publication date: 2023-05-05

Abstract

The application discloses a fault diagnosis method and device of a photovoltaic power station and a photovoltaic system, and belongs to the technical field of photovoltaic power generation. The life prediction method of the photovoltaic module comprises the following steps: determining a shadow shielding type corresponding to the photovoltaic power station to be detected based on historical current data of the photovoltaic power station to be detected, wherein the shadow shielding type comprises at least one of fixed shielding, vegetation shielding and full-day inefficiency; determining a target label of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested; the target tag is used for describing characteristics of the photovoltaic power station to be tested from a plurality of different dimensions; and determining the target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label. According to the fault diagnosis method for the photovoltaic power station, the coupling scene can be distinguished, the specific fault type corresponding to the photovoltaic power station to be detected can be diagnosed, and meanwhile, the historical diagnosis result can be utilized to form positive feedback, correction or guidance on the fault diagnosis of the photovoltaic power station.

Description

Fault diagnosis method and device for photovoltaic power station and photovoltaic system

Technical Field

The application belongs to the technical field of photovoltaic power generation, and particularly relates to a fault diagnosis method and device of a photovoltaic power station and a photovoltaic system.

Background

The photovoltaic array is one of core components of the photovoltaic power generation system, and is easy to be abnormal and fault when working in a severe outdoor environment for a long time, so that the photovoltaic system cannot normally operate. Therefore, the fault diagnosis of the photovoltaic array is a necessary condition for ensuring the normal operation of the photovoltaic power generation system. The conventional fault diagnosis method for the photovoltaic power station is not high in diagnosis precision, for example, under the condition that a shadow shielding type corresponding to the photovoltaic power station is represented as fixed shielding, the conventional fault diagnosis method for the photovoltaic power station can only identify the fixed shielding, can not identify the fixed shielding, particularly mountain shielding or big tree shielding, and the like, namely, can not diagnose the specific fault type under the coupling scene, and is limited in applicable scene.

Disclosure of Invention

The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the method, the device and the photovoltaic system for diagnosing the faults of the photovoltaic power station can distinguish the coupling scene so as to diagnose the specific fault type corresponding to the photovoltaic power station to be tested, and meanwhile, the historical diagnosis result can be utilized to form forward feedback, correction or guidance on the fault diagnosis of the photovoltaic power station, so that the technical problem that the specific fault type cannot be diagnosed in the coupling scene is solved.

In a first aspect, the present application provides a fault diagnosis method for a photovoltaic power station, the method comprising:

determining a shadow shielding type corresponding to a photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested, wherein the shadow shielding type comprises fixed shielding, vegetation shielding and full-day inefficiency;

determining a target label of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested; the dynamic data are used for representing the working condition of the photovoltaic power station to be tested, the static data are used for representing the static attribute of the photovoltaic power station to be tested, and the target tag is used for describing the characteristics of the photovoltaic power station to be tested from a plurality of different dimensions;

and determining the target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label.

According to the fault diagnosis method for the photovoltaic power station, the shadow shielding type corresponding to the photovoltaic power station to be tested is determined based on the historical current data of the photovoltaic power station to be tested, then the target label of the photovoltaic power station to be tested is determined based on at least one of the dynamic data and the static data of the photovoltaic power station to be tested, and then the target fault information of the photovoltaic power station to be tested is determined based on the shadow shielding type and the target label, so that a coupling scene can be distinguished to further diagnose the specific fault type corresponding to the photovoltaic power station to be tested, meanwhile, the historical diagnosis result can be utilized to form positive feedback, correction or guidance on the fault diagnosis of the photovoltaic power station, a diagnosis closed loop is formed, the fineness and the accuracy of the fault diagnosis of the final photovoltaic power station are improved, and the technical problem that the specific fault type cannot be diagnosed under the coupling scene is solved.

The fault diagnosis method for a photovoltaic power station according to an embodiment of the present application, wherein the determining, based on at least one of dynamic data and static data of the photovoltaic power station to be tested, a target tag of the photovoltaic power station to be tested includes:

describing at least one of dynamic data and static data of the photovoltaic power station to be tested from at least one dimension, and determining the target tag;

the target label comprises at least one of a fact label, a model label and a prediction label; the fact label is used for describing the fact characteristics of the photovoltaic power station to be tested, the model label is determined based on historical diagnosis results, and the prediction label is used for describing the situation that the photovoltaic power station to be tested may happen in the future.

According to the fault diagnosis method for the photovoltaic power station, provided by the embodiment of the application, the at least one of the dynamic data and the static data of the photovoltaic power station to be tested is described from at least one dimension, the target label is determined, after the shadow shielding type corresponding to the photovoltaic power station to be tested is judged, the coupling scene is further distinguished based on the target label corresponding to the photovoltaic power station to be tested, and the application range of the fault diagnosis method for the photovoltaic power station is widened.

The fault diagnosis method of the photovoltaic power station according to one embodiment of the present application describes at least one of dynamic data and static data of the photovoltaic power station to be tested from at least one dimension, and determines the target tag, including:

determining equipment attributes and running states of the photovoltaic power station to be tested based on the dynamic data and the static data;

quantitatively and/or qualitatively describing the device attributes and determining the fact label;

carrying out abstract processing and cluster analysis on the equipment attribute and the running state to determine the model label;

based on the equipment attribute, predicting and obtaining a potential fault corresponding to the photovoltaic power station to be detected;

the predictive tag is determined based on the potential failure.

According to the fault diagnosis method of the photovoltaic power station, provided by the embodiment of the application, the device attribute is quantitatively and/or qualitatively described, the fact label is determined, and the basic attribute or the device data of the device can be quantitatively or qualitatively described; the model label is determined by carrying out abstract processing and cluster analysis on the equipment attribute and the running state, and can be used for representing the running condition or the safety condition of the equipment; through predicting potential faults corresponding to the photovoltaic power station to be detected based on the equipment attributes, and determining the prediction labels based on the potential faults, equipment can be overhauled and eliminated more accurately in the actual application process, and further fault diagnosis accuracy of the photovoltaic power station is improved.

The method for diagnosing faults of the photovoltaic power station according to the embodiment of the present application, wherein the determining the target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target tag includes:

determining at least one piece of candidate fault information corresponding to the shadow shielding type based on the shadow shielding type;

and screening the target fault information from the at least one candidate fault information based on the target label.

According to the fault diagnosis method for the photovoltaic power station, the at least one candidate fault information corresponding to the shadow shielding type is determined based on the shadow shielding type, then the target fault information is obtained through screening from the at least one candidate fault information based on the target label, the specific low-efficiency fault type corresponding to the photovoltaic power station to be tested can be diagnosed, meanwhile, the fact that coupling exists in the decoupling is assisted by using the known actual situation is achieved, the historical diagnosis result can be used for forming positive feedback, correction or guidance on the fault diagnosis of the photovoltaic power station, a diagnosis closed loop is formed, and further the fineness and accuracy of the fault diagnosis of the photovoltaic power station are improved, and therefore the technical problem that the specific fault type cannot be diagnosed in a coupling scene is solved.

According to the fault diagnosis method for the photovoltaic power station, based on historical current data of the photovoltaic power station to be tested, the shadow shielding type corresponding to the photovoltaic power station to be tested is determined, and the fault diagnosis method comprises the following steps:

determining an inefficient string in a photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested;

and determining the shadow shielding type based on the sub-historical current data corresponding to the low-efficiency group string.

According to the fault diagnosis method for the photovoltaic power station, the low-efficiency group strings in the photovoltaic power station to be tested are determined based on the historical current data of the photovoltaic power station to be tested, then the shadow shielding types are determined based on the sub-historical current data corresponding to the low-efficiency group strings, the shadow shielding types corresponding to the low-efficiency group strings in the photovoltaic power station can be effectively diagnosed, and fault information corresponding to the low-efficiency group strings can be conveniently diagnosed in the follow-up execution process.

The fault diagnosis method for the photovoltaic power station according to the embodiment of the present application, wherein the determining the shadow shielding type based on the sub-historical current data corresponding to the low-efficiency group string includes:

acquiring target characteristics corresponding to the sub-historical current data based on the sub-historical current data corresponding to the low-efficiency group string;

And determining the shadow occlusion type based on the target feature.

According to the fault diagnosis method for the photovoltaic power station, provided by the embodiment of the application, the target characteristics corresponding to the sub-historical current data are obtained based on the sub-historical current data corresponding to the low-efficiency group strings, the shadow shielding type is determined based on the target characteristics, the shadow shielding type corresponding to the low-efficiency group strings corresponding to the characteristics can be determined by analyzing different characteristics of the sub-historical current data, the accuracy is high, the obtained result is accurate, the running state of the photovoltaic power station can be better reflected, and therefore the accuracy of the fault diagnosis of the follow-up photovoltaic power station is improved.

inputting the sub-historical current data into a string low-efficiency refined diagnosis model, obtaining a shadow shielding type corresponding to the sub-historical current data output by the string low-efficiency refined diagnosis model, wherein,

the group string low-efficiency refined diagnosis model is obtained by training by taking sample sub-historical current data as a sample and taking a sample shadow shielding type corresponding to the sample sub-historical current data as a sample label.

According to the fault diagnosis method for the photovoltaic power station, provided by the embodiment of the application, the group string is obtained through training by taking the sample sub-historical current data as 5 samples and the sample shadow shielding type corresponding to the sample sub-historical current data as a sample label

The method comprises the steps of effectively and finely diagnosing a model, inputting sub-historical current data into a string low-efficiency and finely diagnosing model, obtaining a shadow shielding type corresponding to the sub-historical current data output by the string low-efficiency and finely diagnosing model, and directly obtaining data after pre-training before use in practical application, wherein the diagnosis efficiency is high and the accuracy is good; and the string is low-efficiency refined

The learning ability of the diagnosis model is strong, the data in each application process can be used as the training 0 data in the next training process, thereby improving the precision and accuracy of the model, facilitating the use of users, widening the diagnosis range, having higher universality,

and meanwhile, the accuracy of final fault diagnosis is improved.

According to the fault diagnosis method for the photovoltaic power station, the static data comprise at least one of equipment information, defect records, state maintenance records, network security check records, inspection records and installation information of the photovoltaic power station to be tested.

5 according to the fault diagnosis method for the photovoltaic power station provided by the embodiment of the application, static data are set to comprise the light to be tested

At least one of equipment information, defect record, state maintenance record, network security check record, inspection record and installation information of the photovoltaic power station can comprehensively reflect static properties of the photovoltaic power station to be tested, so that a target label of the photovoltaic power station to be tested is determined, and faults of the photovoltaic power station to be tested can be detected more accurately.

In a second aspect, the present application provides a fault diagnosis apparatus for a photovoltaic power station, the apparatus comprising: 0 a first processing module for determining a pair of photovoltaic power stations to be tested based on historical current data of the photovoltaic power stations to be tested

The shadow shielding type comprises at least one of fixed shielding, vegetation shielding and full-day inefficiency;

a second processing module for processing the dynamic data and the static data of the photovoltaic power station to be tested,

determining a target label of the photovoltaic power station to be tested; the dynamic data are used for representing the working condition 5 of the photovoltaic power station to be tested, the static data are used for representing the static attribute of the photovoltaic power station to be tested, and the target labels are used for identifying a plurality of non-tested photovoltaic power stations

The characteristics of the photovoltaic power station to be tested are described in the same dimension;

and the third processing module is used for determining the target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label.

According to the fault diagnosis device of the photovoltaic power station, which is provided by the embodiment of the application, the shadow shielding type corresponding to the photovoltaic power station to be tested is determined based on the historical 0 current data of the photovoltaic power station to be tested, and then the dynamic data of the photovoltaic power station to be tested is based on the dynamic data of the photovoltaic power station to be tested

And determining at least one kind of static data, determining a target label of the photovoltaic power station to be tested, and determining target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label, so that a coupling scene can be distinguished, and then a specific fault type corresponding to the photovoltaic power station to be tested can be diagnosed, meanwhile, a forward feedback, correction or guidance can be formed on the fault diagnosis of the photovoltaic power station by utilizing a historical diagnosis result, a diagnosis closed loop is formed, and the fineness and the accuracy of the fault diagnosis of the final photovoltaic power station are improved, thereby solving the technical problem that the specific fault type cannot be diagnosed under the coupling scene.

In a third aspect, the present application provides a photovoltaic system comprising:

At least one string of photovoltaic groups;

the fault diagnosis device of a photovoltaic power station according to the second aspect.

According to the photovoltaic system provided by the embodiment of the application, the target fault information corresponding to the photovoltaic power station to be tested can be effectively diagnosed by arranging at least one photovoltaic group string and the fault diagnosis device of the photovoltaic power station in the photovoltaic system, so that the technical problem that a specific fault type cannot be diagnosed in a coupling scene is solved.

The above technical solutions in the embodiments of the present application have at least one of the following technical effects:

the method comprises the steps of determining the shadow shielding type corresponding to the photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested, determining the target label of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested, determining the target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label, distinguishing a coupling scene, and diagnosing the specific fault type corresponding to the photovoltaic power station to be tested, simultaneously forming positive feedback, correction or guidance on the fault diagnosis of the photovoltaic power station by utilizing a historical diagnosis result, forming a diagnosis closed loop, and improving the fineness and accuracy of the fault diagnosis of the final photovoltaic power station, so that the technical problem that the specific fault type cannot be diagnosed under the coupling scene is solved.

Further, at least one of dynamic data and static data of the photovoltaic power station to be tested is described from at least one dimension, and the target label is determined, so that after the shadow shielding type corresponding to the photovoltaic power station to be tested is judged, the coupling scene is further distinguished based on the target label corresponding to the photovoltaic power station to be tested, and the application range of the fault diagnosis method of the photovoltaic power station is widened.

Further, by quantitatively and/or qualitatively describing the device attribute and determining the fact label, the basic attribute or the device data of the device can be quantitatively or qualitatively described; the model label is determined by carrying out abstract processing and cluster analysis on the equipment attribute and the running state, and can be used for representing the running condition or the safety condition of the equipment; through predicting potential faults corresponding to the photovoltaic power station to be detected based on the equipment attributes, and determining the prediction labels based on the potential faults, equipment can be overhauled and eliminated more accurately in the actual application process, and further fault diagnosis accuracy of the photovoltaic power station is improved.

Still further, through determining at least one candidate fault information corresponding to the shadow shielding type based on the shadow shielding type, and then screening and obtaining target fault information from at least one candidate fault information based on the target label, a specific low-efficiency fault type corresponding to the photovoltaic power station to be detected can be diagnosed, the condition that coupling exists in the decoupling self is assisted by using the known actual condition is realized, the fault diagnosis of the photovoltaic power station can be formed into forward feedback, correction or guidance by using the historical diagnosis result, a diagnosis closed loop is formed, and the fineness and the accuracy of the fault diagnosis of the photovoltaic power station are improved, so that the technical problem that the specific fault type cannot be diagnosed under the coupling scene is solved.

Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, wherein:

fig. 1 is one of flow diagrams of a fault diagnosis method of a photovoltaic power station provided in an embodiment of the present application;

fig. 2 is a schematic diagram of a fault diagnosis method of a photovoltaic power station according to an embodiment of the present application;

fig. 3 is a second flow chart of a fault diagnosis method of a photovoltaic power station according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of a fault diagnosis device of a photovoltaic power station according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a photovoltaic system provided in an embodiment of the present application;

fig. 6 is a schematic diagram of a system architecture of a photovoltaic system according to an embodiment of the present application.

Detailed Description

Technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.

The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.

The fault diagnosis method of the photovoltaic power station of the present application is described below with reference to fig. 1 to 3.

It should be noted that, the main body of the fault diagnosis method of the photovoltaic power station may be a photovoltaic system, or may be a fault diagnosis device of the photovoltaic power station disposed on the photovoltaic system, or may also be a server electrically connected to the photovoltaic system, or may also be a user terminal communicatively connected to the photovoltaic system, including, but not limited to, a mobile terminal and a non-mobile terminal.

For example, mobile terminals include, but are not limited to, cell phones, PDA smart terminals, tablet computers, vehicle-mounted smart terminals, and the like;

non-mobile terminals include, but are not limited to, PC-side and the like.

As shown in fig. 1, the fault diagnosis method of the photovoltaic power station includes: step 110, step 120 and step 130.

Step 110, determining a shadow shielding type 5 corresponding to the photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested, wherein the shadow shielding type comprises fixed shielding, vegetation shielding and full-day inefficiency;

in this step, the photovoltaic power plant to be tested is the power plant for fault diagnosis.

The historical current data may be current data before the current moment of the photovoltaic power plant to be measured, which is acquired based on a time sequence.

The shadow occlusion type may include at least one of fixed occlusion, vegetation occlusion, and full day inefficiency.

Wherein, the fixed shielding can comprise one or more of mountain shielding, telegraph pole shielding, building shielding, front-back row shielding and the like.

The vegetation shade may include one or more of a vine shade, a shrub shade, a small grass shade, a big tree shade, and the like.

The formation factors that are inefficient throughout the day may include one or more of component aging and component chipping, etc., or may include the presence of one or more attachments of dust, bird droppings, vines, etc. on the component.

The historical current data corresponding to different shadow mask types show different characteristics, and in the actual implementation process, the corresponding shadow mask types can be determined based on the differences of the shown characteristics.

In some embodiments, step 110 may include:

determining an inefficient string in the photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested;

In this embodiment, the low-efficiency string is obtained based on historical current data of the photovoltaic power station to be tested, and in an actual execution process, the generated energy or the generated electricity hour number of the inverter corresponding to the low-efficiency string, which is continuous for several days, is always lower than that of the normal string.

The sub-historical current data may be current data before a current time corresponding to the low-efficiency group string acquired based on a time sequence.

In the actual execution process, the low-efficiency group string in the photovoltaic power station to be tested is determined based on the historical current data of the photovoltaic power station to be tested, then the sub-historical current data corresponding to the low-efficiency group string is obtained, and the shadow shielding type corresponding to the low-efficiency group string can be determined through at least one of a model method or a table look-up method and the like based on different characteristics of the sub-historical current data.

In the table look-up method, the corresponding relation between the sub-historical current data and the shadow occlusion type needs to be established in advance, for example, a target table is established based on historical data, multiple test data or manual experience.

In the subsequent application process, the shadow shielding type corresponding to the sub-historical current data can be searched based on the target table.

In some embodiments, determining the shadow occlusion type based on the sub-historical current data corresponding to the inefficiency group string may include:

acquiring target features corresponding to the sub-historical current data based on the sub-historical current data corresponding to the low-efficiency group string;

based on the target features, a shadow occlusion type is determined.

In this embodiment, the target features may be obtained based on the temporal and spatial manifestations of the sub-historical current data.

The target feature may be a seasonal feature, a growth feature, or a shape feature.

In the practical application process, under the condition that the sub-historical current data changes along with the altitude and azimuth of the sun, the target features shown by the sub-historical current data are seasonal features, and the shadow shielding type can be determined to be fixed shielding.

Under the condition that the sub-historical current data can change along with the growth condition of the vegetation, the target features shown by the sub-historical current data are growth features, and the shadow shielding type can be determined to be the vegetation shielding.

Under the condition that the photovoltaic power station to be tested cannot receive the direct radiation emitted by the sun, the sub-historical current data are low-efficiency on the whole day, the shadow shielding type can be determined to be low-efficiency on the whole day based on the shape characteristics of the low-efficiency on the whole day, as shown in fig. 2, the shape characteristics of the sub-historical current data under the condition that the component of the photovoltaic power station to be tested is cracked are similar to the shape characteristics of the sub-historical current data corresponding to the normal group string under the condition that the component of the photovoltaic power station to be tested is cracked, but the sub-historical current data value of the low-efficiency group string is lower than the sub-historical current data value of the normal group string under the whole day range.

In the actual execution process, the shadow shielding type can be determined based on a table lookup method, and the shadow shielding type corresponding to the target characteristic can be searched based on the target characteristic corresponding to the sub-historical current data and the target table, namely the shadow shielding type corresponding to the low-efficiency group string.

In some embodiments, determining the shadow occlusion type based on the sub-historical current data corresponding to the inefficiency group string may further comprise:

and inputting the sub-historical current data into the string low-efficiency refined diagnosis model, and obtaining the shadow shielding type corresponding to the sub-historical current data output by the string low-efficiency refined diagnosis model.

In the embodiment, the group string low-efficiency refined diagnosis model is a pre-trained model, which is obtained by training by taking sample sub-historical current data as a sample and taking a sample shadow shielding type corresponding to the sample sub-historical current data as a sample tag.

In the actual execution process, as shown in fig. 3, the sub-historical current data corresponding to the low-efficiency group string is input to the group string low-efficiency refined diagnosis model, so that the shadow shielding type corresponding to the sub-historical current data output by the group string low-efficiency refined diagnosis model can be obtained, for example, the shadow shielding type can be at least one of fixed shielding, vegetation shielding or whole-day low efficiency.

According to the fault diagnosis method for the photovoltaic power station, provided by the embodiment of the application, the sample sub-historical current data is used as a sample, the sample shadow shielding type corresponding to the sample sub-historical current data is used as a sample label, the group string low-efficiency refined diagnosis model is obtained through training, the sub-historical current data is input into the group string low-efficiency refined diagnosis model, the shadow shielding type corresponding to the sub-historical current data output by the group string low-efficiency refined diagnosis model is obtained, the data can be directly obtained after pre-training is carried out in practical application, and the diagnosis efficiency is high and the accuracy is good; the learning capability of the string low-efficiency refined diagnosis model is strong, and data in each application process can be used as training data in the next training process, so that the precision and accuracy of the model are improved, the use of a user is facilitated, the diagnosis range is widened, the universality is higher, and meanwhile, the precision of final fault diagnosis is improved.

Step 120, determining a target label of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested; the dynamic data are used for representing the working condition of the photovoltaic power station to be tested, the static data are used for representing the static attribute of the photovoltaic power station to be tested, and the target labels are used for describing the characteristics of the photovoltaic power station to be tested from a plurality of different dimensions;

in the step, the target labels are obtained by describing the characteristics of the photovoltaic power station to be tested from different angles and are used for constructing images corresponding to the photovoltaic power station to be tested.

The dynamic data is used for representing the working condition of the photovoltaic power station to be tested, and the dynamic data can comprise at least one of current, voltage, active power, reactive power and signals of the photovoltaic power station to be tested.

The static data are used for representing static properties of the photovoltaic power station to be tested.

In some embodiments, the static data may include at least one of equipment information, defect records, status overhaul records, network security audit records, inspection records, and installation information of the photovoltaic power plant under test.

In some embodiments, the device information of the photovoltaic power plant under test may include at least one of a model specification, a factory number, an asset number, a device number, a factory date, and a commissioning date of the photovoltaic power plant under test.

According to the fault diagnosis method for the photovoltaic power station, provided by the embodiment of the application, the target label of the photovoltaic power station to be tested is determined based on at least one of equipment information, defect record, state maintenance record, network security check record, inspection record and installation information of the photovoltaic power station to be tested, so that the static attribute of the photovoltaic power station to be tested can be comprehensively reflected, and further, the fault of the photovoltaic power station to be tested can be accurately detected.

In some embodiments, step 120 may include: describing at least one of dynamic data and static data of the photovoltaic power station to be tested from at least one dimension, and determining a target label;

the target label comprises at least one of a fact label, a model label and a prediction label; the fact label is used for describing the fact characteristics of the photovoltaic power station to be tested, the model label is determined based on historical diagnosis results, and the prediction label is used for describing the situation which can happen to the photovoltaic power station to be tested in the future.

In this embodiment, the target tag is used to characterize the data characteristics of the photovoltaic power plant to be tested.

The number of target tags for each station may be one or more.

For example, in the case where the photovoltaic power plant to be tested is a commercial rooftop power plant, the target tag corresponding to the photovoltaic power plant to be tested may be one or more of a commercial power plant, dust shielding, mountain shielding, or the like.

In some embodiments, describing at least one of dynamic data and static data of the photovoltaic power plant to be measured from at least one dimension, determining the target tag may include:

quantitatively and/or qualitatively describing the equipment attribute, and determining a fact label;

carrying out abstract processing and cluster analysis on the equipment attribute and the running state to determine a model label;

based on the equipment attribute, predicting and obtaining potential faults corresponding to the photovoltaic power station to be detected;

based on the potential failure, a predictive tag is determined.

In this embodiment, the device attribute of the photovoltaic power plant to be measured may include at least one of a basic attribute of the device and a device profile.

The operating state of the photovoltaic power plant to be tested may comprise at least one of the operating conditions and safety conditions of the apparatus.

The fact label is used for describing the fact characteristics of the photovoltaic power station to be tested, the equipment attribute can be quantitatively described, and the fact label is determined; or the device attribute can be qualitatively described, and the fact label is determined; or the device attributes may also be described quantitatively and qualitatively to determine the fact label. The specific manner of determining the fact label may be user-defined, and is not limited in this application.

The model tag is determined based on historical diagnosis results, abstract processing and cluster analysis can be performed on the equipment attribute and the running state, the model tag is determined, and the model tag can characterize at least one of the running condition and the safety condition of the equipment.

In some embodiments, data mining may be performed to form model tags based on a history of the final diagnostic results, and forward feedback, correction, guidance, etc., of the diagnostic results based on the model tags may be formed during subsequent applications to form a diagnostic closed loop.

The prediction tag is used for describing the future possible occurrence of the photovoltaic power station to be tested, and can predict and obtain the potential fault corresponding to the photovoltaic power station to be tested based on at least one of equipment attribute, behavior, signaling, position and characteristics, and then determine the prediction tag based on the potential fault.

In the actual execution process, after the dynamic data and the static data of the photovoltaic power station to be tested are obtained, the behavior data can be obtained by using a machine learning method or a data analysis method and the like, at least one of the low-efficiency occurrence time, the frequency and the low-efficiency type of the low-efficiency group string in the photovoltaic power station to be tested is counted, then the dynamic data and the static data of the photovoltaic power station to be tested can be analyzed from at least one dimension and by establishing a behavior data model, and each dimension label of the photovoltaic power station to be tested is determined, namely the target label corresponding to the photovoltaic power station to be tested.

The photovoltaic power station to be tested can be correspondingly provided with a plurality of target labels, and the set of all the target labels can be expressed as an image corresponding to the photovoltaic power station to be tested.

In some embodiments, data mining and statistical analysis may be performed based on the history of the final diagnostic results to complete feedback and updating of the results to the representation, thereby constructing a full-featured device representation.

And 130, determining target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label.

In this step, as shown in fig. 3, the target fault information may be mountain occlusion, pole occlusion, vine occlusion, assembly aging or dust occlusion, etc., and may be determined based on the type of shadow occlusion and the target tag.

The method of determining the target failure information is specifically described below.

As shown in fig. 3, in some embodiments, step 130 may include: determining at least one piece of candidate fault information corresponding to the shadow shielding type based on the shadow shielding type;

and screening the target fault information from at least one candidate fault information based on the target label.

In this embodiment, the shadow shielding type may be subdivided into a plurality of sub-shielding types, for example, the sub-shielding types may be mountain shielding, vine shielding, component aging or dust shielding, and in the case that different sub-shielding types exist in the photovoltaic power station to be tested, the performance of sub-historical current data corresponding to the low-efficiency group string in the photovoltaic power station to be tested may be the same, and the candidate fault information is a set of different sub-shielding types corresponding to the same performance result.

In the actual implementation process, after determining at least one piece of candidate fault information corresponding to the shadow mask type, the shadow mask type can be further subdivided based on the target tag so as to determine the sub-mask type, and then the target fault information is obtained by screening from the at least one piece of candidate fault information.

For example, in the case that the shadow shielding type is determined to be low-efficiency on the whole day, dust shielding and the like can exist on a fact label such as a photovoltaic power station to be detected as a commercial roof power station or a photovoltaic power station to be detected, or a historical diagnosis result can be counted as dust through a model label, and forward feedback, correction or guidance can be formed on fault diagnosis of the photovoltaic power station by utilizing the historical diagnosis result, so that the target fault information is determined to be dust shielding.

In this embodiment, at least one candidate fault information corresponding to a shadow shielding type is determined based on the shadow shielding type, and then target fault information is screened from the at least one candidate fault information based on a target label, so that a specific low-efficiency fault type corresponding to a photovoltaic power station to be tested can be diagnosed, meanwhile, the condition that coupling exists in the decoupling is assisted by using a known actual condition is realized, a forward feedback, correction or guidance can be formed on the fault diagnosis of the photovoltaic power station by using a historical diagnosis result, a diagnosis closed loop is formed, and the fineness and the accuracy of the fault diagnosis of the photovoltaic power station are improved, so that the technical problem that the specific fault type cannot be diagnosed under a coupling scene is solved.

In the method, the shadow shielding type corresponding to the photovoltaic power station to be detected is determined based on historical current data of the photovoltaic power station to be detected, and the shielding type corresponding to the photovoltaic power station to be detected can be initially classified.

Based on at least one of dynamic data and static data of the photovoltaic power station to be tested, determining a target label of the photovoltaic power station to be tested, and further subdividing the shadow shielding type based on the target label, so that target fault information of the photovoltaic power station to be tested can be determined.

According to the fault diagnosis method for the photovoltaic power station, which is provided by the embodiment of the application, the shadow shielding type is determined based on the historical current data of the photovoltaic power station to be tested, and then the shielding type is subdivided based on the target label, so that the coupling scene can be distinguished, the specific fault type corresponding to the photovoltaic power station to be tested can be diagnosed, meanwhile, the fault diagnosis of the photovoltaic power station can be formed into forward feedback, correction or guidance by utilizing the historical diagnosis result, a diagnosis closed loop is formed, the fineness and the accuracy of the fault diagnosis of the final photovoltaic power station are improved, and the technical problem that the specific fault type cannot be diagnosed under the coupling scene is solved.

The fault diagnosis device of the photovoltaic power station provided by the application is described below, and the fault diagnosis device of the photovoltaic power station described below and the fault diagnosis method of the photovoltaic power station described above can be correspondingly referred to each other.

According to the fault diagnosis method for the photovoltaic power station, which is provided by the embodiment of the application, the execution main body can be a fault diagnosis device for the photovoltaic power station. In the embodiment of the present application, a method for performing a fault diagnosis of a photovoltaic power station by using a fault diagnosis device of the photovoltaic power station is taken as an example, and the fault diagnosis device of the photovoltaic power station provided in the embodiment of the present application is described.

The embodiment of the application also provides a fault diagnosis device of the photovoltaic power station.

As shown in fig. 4, the fault diagnosis device for a photovoltaic power plant includes: a first processing module 410, a second processing module 420, and a third processing module 430.

The first processing module 410 is configured to determine a shadow shielding type corresponding to the photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested, where the shadow shielding type includes at least one of fixed shielding, vegetation shielding and full-day inefficiency;

the second processing module 420 is configured to determine a target tag of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested; the dynamic data are used for representing the working condition of the photovoltaic power station to be tested, the static data are used for representing the static attribute of the photovoltaic power station to be tested, and the target labels are used for describing the characteristics of the photovoltaic power station to be tested from a plurality of different dimensions;

The third processing module 430 is configured to determine target fault information of the photovoltaic power plant to be tested based on the shadow occlusion type and the target tag.

According to the fault diagnosis device for the photovoltaic power station, the shadow shielding type corresponding to the photovoltaic power station to be tested is determined based on the historical current data of the photovoltaic power station to be tested, then the target label of the photovoltaic power station to be tested is determined based on at least one of the dynamic data and the static data of the photovoltaic power station to be tested, and then the target fault information of the photovoltaic power station to be tested is determined based on the shadow shielding type and the target label, so that a coupling scene can be distinguished to further diagnose the specific fault type corresponding to the photovoltaic power station to be tested, meanwhile, the fault diagnosis of the photovoltaic power station can be formed into a positive feedback, correction or guidance by utilizing the historical diagnosis result, a diagnosis closed loop is formed, the fineness and the accuracy of the fault diagnosis of the final photovoltaic power station are improved, and the technical problem that the specific fault type cannot be diagnosed under the coupling scene is solved.

In some embodiments, the second processing module 420 may be further configured to describe at least one of dynamic data and static data of the photovoltaic power plant to be tested from at least one dimension, and determine a target tag;

According to the fault diagnosis device for the photovoltaic power station, provided by the embodiment of the application, the at least one of the dynamic data and the static data of the photovoltaic power station to be tested is described from at least one dimension, the target label is determined, after the shadow shielding type corresponding to the photovoltaic power station to be tested is judged, the coupling scene is further distinguished based on the target label corresponding to the photovoltaic power station to be tested, and the application range of the fault diagnosis device for the photovoltaic power station is widened.

In some embodiments, the fault diagnosis device of the photovoltaic power station may further include a fourth processing module, configured to determine the device attribute and the operation state of the photovoltaic power station to be tested based on the dynamic data and the static data;

based on the potential failure, a predictive tag is determined.

According to the fault diagnosis device of the photovoltaic power station, provided by the embodiment of the application, the device attribute is quantitatively and/or qualitatively described, the fact label is determined, and the basic attribute or the device data of the device can be quantitatively or qualitatively described; the model label is determined by carrying out abstract processing and cluster analysis on the equipment attribute and the running state, and can be used for representing the running condition or the safety condition of the equipment; through predicting potential faults corresponding to the photovoltaic power station to be detected based on the equipment attributes, and determining the prediction labels based on the potential faults, equipment can be overhauled and eliminated more accurately in the actual application process, and further fault diagnosis accuracy of the photovoltaic power station is improved.

In some embodiments, the third processing module 430 may be further configured to determine, based on the shadow occlusion type, at least one candidate fault information corresponding to the shadow occlusion type;

According to the fault diagnosis device for the photovoltaic power station, provided by the embodiment of the application, the specific low-efficiency fault type corresponding to the photovoltaic power station to be detected can be diagnosed by determining at least one candidate fault information corresponding to the shadow shielding type based on the shadow shielding type and then screening and obtaining the target fault information from the at least one candidate fault information based on the target label, meanwhile, the condition that coupling exists by the aid of decoupling per se is realized by using the known actual condition, a forward feedback, correction or guidance can be formed on the fault diagnosis of the photovoltaic power station by using the historical diagnosis result, a diagnosis closed loop is formed, and the fineness and the accuracy of the fault diagnosis of the photovoltaic power station are improved, so that the technical problem that the specific fault type cannot be diagnosed under the coupling scene is solved.

In some embodiments, the first processing module 410 may also be configured to determine an inefficient string in the photovoltaic power plant under test based on historical current data of the photovoltaic power plant under test;

According to the fault diagnosis device for the photovoltaic power station, provided by the embodiment of the application, the low-efficiency group string in the photovoltaic power station to be tested is determined based on the historical current data of the photovoltaic power station to be tested, then the shadow shielding type is determined based on the sub-historical current data corresponding to the low-efficiency group string, the shadow shielding type corresponding to the low-efficiency group string in the photovoltaic power station can be effectively diagnosed, and fault information corresponding to the low-efficiency group string can be conveniently diagnosed in the follow-up execution process.

In some embodiments, the fault diagnosis device of the photovoltaic power station may further include a fifth processing module, configured to obtain, based on the sub-historical current data corresponding to the low-efficiency group string, a target feature corresponding to the sub-historical current data;

based on the target features, a shadow occlusion type is determined.

According to the fault diagnosis device for the photovoltaic power station, provided by the embodiment of the application, the target characteristics corresponding to the sub-historical current data are obtained based on the sub-historical current data corresponding to the low-efficiency group strings, the shadow shielding type is determined based on the target characteristics, the shadow shielding type corresponding to the low-efficiency group strings corresponding to the characteristics can be determined by analyzing different characteristics of the sub-historical current data, the accuracy is high, the obtained result is accurate, the running state of the photovoltaic power station can be better reflected, and therefore the accuracy of fault diagnosis of the follow-up photovoltaic power station is improved.

In some embodiments, the fault diagnosis device of the photovoltaic power station may further include a sixth processing module, configured to input the sub-historical current data to the group string inefficiency and fine diagnosis model, obtain a shadow occlusion type corresponding to the sub-historical current data output by the group string inefficiency and fine diagnosis model, where,

According to the fault diagnosis device of the photovoltaic power station, the sample sub-historical current data is used as a sample, the sample shadow shielding type corresponding to the sample sub-historical current data is used as a sample label, the group string low-efficiency refined diagnosis model is obtained through training, the sub-historical current data is input into the group string low-efficiency refined diagnosis model, the shadow shielding type corresponding to the sub-historical current data output by the group string low-efficiency refined diagnosis model is obtained, the data can be directly obtained after pre-training is carried out in practical application, and the diagnosis efficiency is high and the accuracy is good; the learning capability of the string low-efficiency refined diagnosis model is strong, and data in each application process can be used as training data in the next training process, so that the precision and accuracy of the model are improved, the use of a user is facilitated, the diagnosis range is widened, the universality is higher, and meanwhile, the precision of final fault diagnosis is improved.

In some embodiments, the fault diagnosis apparatus of a photovoltaic power station may further include a seventh processing module, where the static data includes at least one of equipment information, defect records, status maintenance records, network security check records, inspection records, and installation information of the photovoltaic power station to be tested.

According to the fault diagnosis device for the photovoltaic power station, provided by the embodiment of the application, static data comprise at least one of equipment information, defect records, state maintenance records, network safety investigation records, inspection records and installation information of the photovoltaic power station to be tested, so that the static attribute of the photovoltaic power station to be tested can be comprehensively reflected, the target label of the photovoltaic power station to be tested is determined, and then the fault of the photovoltaic power station to be tested can be accurately detected.

The fault diagnosis device of the photovoltaic power station in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which is not specifically limited in the embodiments of the present application.

The fault diagnosis device for a photovoltaic power station provided in the embodiment of the present application can implement each process implemented by the embodiments of the methods of fig. 1 to 3, and in order to avoid repetition, a description is omitted here.

The embodiment of the application also provides a photovoltaic system.

The photovoltaic system includes: at least one photovoltaic string and a fault diagnosis device for a photovoltaic power plant as described in any of the embodiments above.

In this embodiment, the fault diagnosis apparatus of the photovoltaic power plant is the fault diagnosis apparatus of the photovoltaic power plant described in any of the above embodiments.

The fault diagnosis device of the photovoltaic power station is used for diagnosing faults of the photovoltaic group string.

The fault diagnosis device of the photovoltaic power station is electrically connected with the photovoltaic string to acquire historical current data of the photovoltaic string, and further determine the shadow shielding type corresponding to the photovoltaic power station to be detected so as to acquire target fault information of the photovoltaic power station to be detected.

As shown in fig. 5, the photovoltaic system provided in the embodiments of the present application includes a processor 501, a memory 502, and a computer program stored in the memory 502 and capable of running on the processor 501, where the program when executed by the processor 501 implements the processes of the embodiments of the fault diagnosis method of the photovoltaic power station, and the same technical effects can be achieved, so that repetition is avoided and redundant description is omitted here.

In the practical application process, the system architecture of the photovoltaic system can be designed based on data and the label as the supporting layer, as shown in fig. 6.

It should be noted that the photovoltaic system in the embodiments of the present application includes the mobile photovoltaic system and the non-mobile photovoltaic system described above.

According to the photovoltaic system provided by the embodiment of the application, through setting at least one photovoltaic group string and the fault diagnosis device of the photovoltaic power station in the photovoltaic system, body support can be provided for maintenance operation of the photovoltaic array, emergency defect elimination and reasonable planning, and the condition that decoupling itself is coupled can be assisted based on the fact label, the model label, the prediction label and the known actual condition, so that target fault information corresponding to the photovoltaic power station to be detected can be effectively diagnosed, and the technical problem that a specific fault type cannot be diagnosed in a coupling scene is solved.

The embodiments of the present application also provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform a method for diagnosing faults of a photovoltaic power plant provided by the above methods, the method comprising: determining a shadow shielding type corresponding to the photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested; determining a target label of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested; the dynamic data are used for representing the working condition of the photovoltaic power station to be tested, and the static data are used for representing the static attribute of the photovoltaic power station to be tested; and determining the target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label.

The embodiment of the application also provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the fault diagnosis method embodiment of the photovoltaic power station and achieve the same technical effects, so that repetition is avoided, and the description is omitted here.

It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.

The embodiments of the present application further provide a non-transitory computer readable storage medium having a computer program stored thereon, the computer program being implemented when executed by a processor to perform the method for diagnosing a fault of a photovoltaic power station provided by the above methods, the method comprising: determining a shadow shielding type corresponding to the photovoltaic power station to be tested based on historical current data of the photovoltaic power station to be tested; determining a target label of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested; the dynamic data are used for representing the working condition of the photovoltaic power station to be tested, and the static data are used for representing the static attribute of the photovoltaic power station to be tested; and determining the target fault information of the photovoltaic power station to be tested based on the shadow shielding type and the target label.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. A fault diagnosis method for a photovoltaic power plant, comprising:

2. The method for diagnosing a fault in a photovoltaic power plant according to claim 1, wherein the determining a target tag of the photovoltaic power plant to be tested based on at least one of dynamic data and static data of the photovoltaic power plant to be tested comprises:

3. The method for diagnosing a fault in a photovoltaic power plant according to claim 2, wherein said describing at least one of dynamic data and static data of the photovoltaic power plant to be tested from at least one dimension, determining the target tag, comprises:

the predictive tag is determined based on the potential failure.

4. A method of diagnosing a fault in a photovoltaic power plant according to any one of claims 1-3, wherein said determining target fault information for the photovoltaic power plant under test based on the shadow mask type and the target tag comprises:

5. A method of diagnosing a fault in a photovoltaic power plant according to any one of claims 1-3, wherein determining a shadow mask type corresponding to a photovoltaic power plant to be tested based on historical current data of the photovoltaic power plant to be tested comprises:

6. The method according to claim 5, wherein determining the shadow mask type based on the sub-historic current data corresponding to the inefficiency group string comprises:

and determining the shadow occlusion type based on the target feature.

7. The method according to claim 5, wherein determining the shadow mask type based on the sub-historic current data corresponding to the inefficiency group string comprises:

8. A method of diagnosing a fault in a photovoltaic power plant according to any of claims 1-3, wherein the static data comprises at least one of equipment information, defect records, status overhaul records, network security audit records, inspection records, and installation information of the photovoltaic power plant under test.

9. A fault diagnosis device for a photovoltaic power plant, comprising:

the first processing module is used for determining a shadow shielding type corresponding to the photovoltaic power station to be detected based on historical current data of the photovoltaic power station to be detected, wherein the shadow shielding type comprises at least one of fixed shielding, vegetation shielding and full-day inefficiency;

the second processing module is used for determining a target label of the photovoltaic power station to be tested based on at least one of dynamic data and static data of the photovoltaic power station to be tested; the dynamic data are used for representing the working condition of the photovoltaic power station to be tested, the static data are used for representing the static attribute of the photovoltaic power station to be tested, and the target tag is used for describing the characteristics of the photovoltaic power station to be tested from a plurality of different dimensions;

10. A photovoltaic system, comprising:

at least one string of photovoltaic groups;

the fault diagnosis device of a photovoltaic power station of claim 9.