Fault detection method and system for photovoltaic module

Abstract

According to the photovoltaic module fault detection method and system provided by the invention, the target equipment abnormal operation text corresponding to the to-be-processed equipment abnormal operation text is generated by referring to the photovoltaic module operation text and the to-be-processed equipment abnormal operation text; the fault probability of each first fault detection object in the target equipment abnormal operation text represents an evaluation score of whether a second fault detection object corresponding to the equipment operation state in the to-be-processed equipment abnormal operation text has a hidden danger or not; and the fault detection scheme of the to-be-processed equipment abnormal operation text is determined, so that the accuracy and reliability of fault detection can be ensured.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection and processing, and in particular to a fault detection method and system for a photovoltaic module. Background Art

[0002] With the continuous development and progress of science and technology, people's demand for energy is increasing, and it is also necessary to discover and utilize some new energy to ensure people's normal life.

[0003] At present, photovoltaic energy converts solar radiation into electrical energy based on the photovoltaic effect. Photovoltaic energy has the advantages of no pollution, no noise, low maintenance cost and long service life. It has been rapidly developed in recent years. Equipment may fail during high-intensity operation or aging. If the failure cannot be eliminated in time, it may cause huge losses. Therefore, a technical solution is urgently needed to improve the efficiency and accuracy of fault detection. Summary of the invention

[0004] In view of this, the present application provides a photovoltaic module fault detection method and system.

[0005] In a first aspect, an embodiment of the present application provides a photovoltaic component fault detection method, comprising: obtaining a reference photovoltaic component operation text, and a device abnormal operation text to be processed; determining a target device abnormal operation text corresponding to the device abnormal operation text to be processed through the reference photovoltaic component operation text and the device abnormal operation text to be processed; the failure probability of each first fault detection object in the target device abnormal operation text represents an evaluation score of a hidden danger of a second fault detection object; the second fault detection object is a fault detection object in which the device operation status in the device abnormal operation text to be processed corresponds to the first fault detection object; and generating a fault detection scheme for the device abnormal operation text to be processed through the target device abnormal operation text.

[0006] In this way, by referring to the photovoltaic component operation text and the equipment abnormal operation text to be processed, a target equipment abnormal operation text corresponding to the equipment abnormal operation text to be processed is generated. The failure probability of each first fault detection object in the target equipment abnormal operation text represents an evaluation score of whether there is a hidden danger in the second fault detection object corresponding to the equipment operation state in the equipment abnormal operation text to be processed. Then, based on the target equipment abnormal operation text, the fault detection scheme of the equipment abnormal operation text to be processed is determined, which can ensure the accuracy and reliability of fault detection.

[0007] For some independently implementable technical solutions, the determining of the target device abnormal operation text corresponding to the device abnormal operation text to be processed by using the reference photovoltaic component operation text and the device abnormal operation text to be processed includes: determining a first device abnormal operation text based on the device abnormal operation text to be processed, and determining a second device abnormal operation text based on the reference photovoltaic component operation text; for each third fault detection object in the first device abnormal operation text, determining a plurality of target fault detection objects corresponding to the third fault detection object from the second device abnormal operation text; the degree of distinction between the plurality of target fault detection objects and a target fourth fault detection object in the second device abnormal operation text is less than a first distinction threshold, and the target fourth fault detection object is a fourth fault detection object in which the device operation state in the second device abnormal operation text corresponds to the third fault detection object; for each of the third fault detection objects, determining an evaluation score of the third fault detection object by means of the similarity between the plurality of target fault detection objects and the third fault detection object respectively; and determining an evaluation score of a second fault detection object corresponding to the third fault detection object in the device abnormal operation text to be processed based on the evaluation score of the third fault detection object.

[0008] In this way, by determining from the second device abnormal operation text several target fault detection objects corresponding to each third fault detection object in the first device abnormal operation text, the corresponding third fault detection object evaluation score is determined based on the similarity between the several target fault detection objects and the corresponding third fault detection objects, and then the evaluation score of the second fault detection object corresponding to the third fault detection object is obtained, so that the evaluation score of the second fault detection object is interfered by several fault detection objects in the reference photovoltaic component operation text, so as to reduce the interference of various error influences on the fault detection scheme of the second fault detection object in the device abnormal operation text to be processed, and improve the accuracy of hidden danger analysis of the device abnormal operation text to be processed.

[0009] For some independently implementable technical solutions, the determining of the abnormal operation text of the first device based on the abnormal operation text of the device to be processed, and the determining of the abnormal operation text of the second device based on the reference photovoltaic component operation text, include: determining the abnormal operation text of the device to be processed as the first device abnormal operation text, and determining the reference photovoltaic component operation text as the second device abnormal operation text; or, the determining of the abnormal operation text of the first device based on the abnormal operation text of the device to be processed, and the determining of the abnormal operation text of the second device based on the reference photovoltaic component operation text, include: obtaining a first high-failure rate area information description of the abnormal operation text of the device to be processed, and determining the first high-failure rate area information description as the first device abnormal operation text; obtaining a second high-failure rate area information description of the reference photovoltaic component operation text, and determining the second high-failure rate area information description as the second device abnormal operation text.

[0010] In this way, the abnormal operation text of the device to be processed is determined as the first abnormal operation text of the device, and the operation text of the reference photovoltaic component is determined as the second abnormal operation text of the device, that is, the target device abnormal operation text of the device abnormal operation text to be processed is obtained directly based on the abnormal operation text of the device to be processed and the reference photovoltaic component operation text, and the evaluation score of the existence of hidden dangers of each second fault detection object in the abnormal operation text of the device to be processed represented by the target device abnormal operation text is more accurate; the first high fault rate area information description of the abnormal operation text of the device to be processed is determined as the first device abnormal operation text, and the second high fault rate area information description of the reference photovoltaic component operation text is determined as the second device abnormal operation text, that is, the target device abnormal operation text of the device abnormal operation text to be processed is obtained based on the first high fault rate area information description and the second high fault rate area information description, which is conducive to reducing the resource overhead required for generating the target device abnormal operation text, thereby improving the timeliness of generating the fault detection scheme.

[0011] For some technical solutions that can be implemented independently, for each of the third fault detection objects, an evaluation score of the third fault detection object is determined by the similarities between the several target fault detection objects and the third fault detection object, including: determining the maximum similarity among the similarities between the several target fault detection objects and the third fault detection object; and determining the evaluation score of the third fault detection object through the maximum similarity.

[0012] In this way, the evaluation score of the third fault detection object is determined based on the maximum similarity among the similarities between several target fault detection objects and the third fault detection object, which can improve the credibility of whether the second fault detection objects represented by the abnormal operation text of the target device have hidden dangers.

[0013] For some technical solutions that can be implemented independently, for each third fault detection object in the abnormal operation text of the first device, several target fault detection objects corresponding to the third fault detection object are determined from the abnormal operation text of the second device, including: for each third fault detection object in the abnormal operation text of the first device, a target fourth fault detection object that has a corresponding relationship with the device operation status of the third fault detection object is determined from several fourth fault detection objects in the abnormal operation text of the second device; several fourth fault detection objects whose discrimination degree with the target fourth fault detection object is less than a first discrimination threshold are determined from several fourth fault detection objects in the abnormal operation text of the second device, and the determined fourth fault detection object is determined as the target fault detection object.

[0014] In this way, by setting the first discrimination threshold, the target fault detection object is determined, so as to determine the abnormal operation text of the target equipment based on the difference between each target fault detection object and the corresponding third fault detection object, thereby weakening the interference caused by various types of noise to the hidden danger analysis of the abnormal operation text of the equipment to be processed.

[0015] For some technical solutions that can be implemented independently, for each of the third fault detection objects, the following steps are used to determine the similarity between each target fault detection object and the third fault detection object: based on the device operation status of the third fault detection object in the first device abnormal operation text and a second discrimination threshold set in advance, a first part of object features corresponding to the third fault detection object is obtained; and through the device operation status of each target fault detection object in the second device abnormal operation text and the second discrimination threshold, a second part of object features corresponding to each target fault detection object is obtained; through the first part of object features and the second part of object features, the similarity between each target fault detection object and the third fault detection object is determined.

[0016] In this way, by determining the similarity between the third fault detection object and the target fault detection object through the matching object of the third fault detection object and the matching object of the target fault detection object, the interference caused by various types of noise on the hidden danger analysis of the abnormal operation text of the equipment to be processed can be reduced.

[0017] For some independently implementable technical solutions, the obtaining of the first part of object features corresponding to the third fault detection object based on the device operation state of the third fault detection object in the first device abnormal operation text and the second discrimination threshold set in advance includes: in the first device abnormal operation text, determining a first abnormal operation object set centered on the third fault detection object and specified by the second discrimination threshold, and obtaining the first part of object features through the third fault detection object in the first device abnormal operation text that is located in the first abnormal operation object set; the obtaining of the second part of object features corresponding to each target fault detection object through the device operation state of each target fault detection object in the second device abnormal operation text and the second discrimination threshold includes: in the second device abnormal operation text, determining a second abnormal operation object set centered on each target fault detection object and specified by the second discrimination threshold, and obtaining the second part of object features through the fourth fault detection object in the second device abnormal operation text that is located in the second abnormal operation object set.

[0018] For some technical solutions that can be implemented independently, the obtaining of the first part of object features corresponding to the third fault detection object based on the device operation state of the third fault detection object in the first device abnormal operation text and the second discrimination threshold set in advance includes: determining the target abnormal boundary value through the second discrimination threshold; determining a first matching object set in the first device abnormal operation text that uses the third fault detection object as a sample to determine the target abnormal boundary value as the abnormal boundary value, and obtaining the first part of object features through the third fault detection object in the first device abnormal operation text that is located in the first matching object set; obtaining the second part of object features corresponding to each target fault detection object through the device operation state of each target fault detection object in the second device abnormal operation text and the second discrimination threshold includes: determining a second matching object set in the second device abnormal operation text that uses each target fault detection object as a sample to determine the target abnormal boundary value as the abnormal boundary value; and obtaining the second part of object features through the fourth fault detection object in the second device abnormal operation text that is located in the second matching object set.

[0019] For some technical solutions that can be implemented independently, in the case where the first device abnormal operation text is the device abnormal operation text to be processed and the second device abnormal operation text is the reference photovoltaic component operation text, determining the evaluation score of the second fault detection object corresponding to the third fault detection object in the device abnormal operation text to be processed based on the evaluation score of the third fault detection object includes: determining the evaluation score of each third fault detection object in the first device abnormal operation text as the evaluation score of the second fault detection object in the device abnormal operation text to be processed whose device operation status has a corresponding relationship with the third fault detection object.

[0020] For some technical solutions that can be implemented independently, for the case where the first device abnormal operation text is the first area information description with high fault rate and the second device abnormal operation text is the second area information description with high fault rate, the evaluation score of the second fault detection object corresponding to the third fault detection object in the device abnormal operation text to be processed based on the evaluation score of the third fault detection object is determined, including: determining the evaluation score corresponding to each second fault detection object based on the comparison result between each third fault detection object in the first part of the object characteristics and each second fault detection object in the device abnormal operation text to be processed, and the evaluation score of each third fault detection object in the first part of the object characteristics.

[0021] In a second aspect, a photovoltaic module fault detection device is provided, comprising: A text acquisition module, used to acquire reference photovoltaic module operation text and abnormal operation text of the equipment to be processed; A text determination module, used to determine a target device abnormal operation text corresponding to the device abnormal operation text to be processed through the reference photovoltaic component operation text and the device abnormal operation text to be processed; the failure probability of each first fault detection object in the target device abnormal operation text represents an evaluation score of hidden dangers of a second fault detection object; the second fault detection object is a fault detection object in which the device operation status in the device abnormal operation text to be processed corresponds to the first fault detection object; The strategy generation module is used to generate a fault detection scheme for the abnormal operation text of the device to be processed through the abnormal operation text of the target device.

[0022] A photovoltaic component fault detection method and system provided in an embodiment of the present application generates a target device abnormal operation text corresponding to the device abnormal operation text to be processed by referring to the photovoltaic component operation text and the device abnormal operation text to be processed. The failure probability of each first fault detection object in the target device abnormal operation text represents an evaluation score of whether there is a hidden danger in the second fault detection object corresponding to the device operation state in the device abnormal operation text to be processed. Then, based on the target device abnormal operation text, a fault detection scheme for the device abnormal operation text to be processed is determined, which can ensure the accuracy and reliability of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as specifying the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A flowchart of a photovoltaic module fault detection method provided in an embodiment of the present application.

[0025] Figure 2 A block diagram of a photovoltaic module fault detection device provided in an embodiment of the present application.

[0026] Figure 3 An architectural diagram of a photovoltaic module fault detection system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than designations of the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments may be combined with each other.

[0028] See also Figure 1 , shows a photovoltaic component fault detection method, which may include the technical solutions described in the following steps 101-103.

[0029] Step 101: Obtain reference photovoltaic module operation text and abnormal operation text of equipment to be processed.

[0030] Step 102: Determine a target device abnormal operation text corresponding to the device abnormal operation text to be processed through the reference photovoltaic assembly operation text and the device abnormal operation text to be processed.

[0031] In an embodiment of the present application, the failure probability of each first fault detection object in the abnormal operation text of the target device represents an evaluation score of the hidden danger of the second fault detection object; the second fault detection object is a fault detection object whose equipment operation status in the abnormal operation text of the device to be processed corresponds to the first fault detection object.

[0032] Step 103: Generate a fault detection solution for the abnormal operation text of the device to be processed through the abnormal operation text of the target device.

[0033] Furthermore, the above steps 101 to 103 are exemplarily described below.

[0034] In the above step 101, the reference photovoltaic component operation text refers to the abnormal operation text of the equipment captured from the photovoltaic equipment without hidden dangers when performing hidden danger analysis on the photovoltaic equipment. The abnormal operation text of the equipment to be processed refers to the abnormal operation text of the equipment obtained from the photovoltaic equipment to be processed.

[0035] When performing hidden danger analysis on photovoltaic operation equipment to be processed, for example, the type or catalog of photovoltaic operation equipment to be processed can be first obtained; then, based on the type or catalog of photovoltaic operation equipment, the reference photovoltaic component operation text corresponding to the photovoltaic operation equipment to be processed is obtained from a pre-deployed reference photovoltaic component operation text library; for another example, when there is no reference photovoltaic component operation text of the photovoltaic operation equipment to be processed in the reference photovoltaic component operation text library, for example, a reference photovoltaic operation equipment without hidden dangers can be first determined from a number of photovoltaic operation equipment to be processed, and then the abnormal operation text of the reference photovoltaic operation equipment can be obtained to obtain the reference photovoltaic component operation text.

[0036] The device abnormal operation text to be processed may be obtained, for example, through a device abnormal operation text collection thread set on a hidden danger analysis node, or the device abnormal operation text to be processed transmitted from other ports may be received.

[0037] In the above step 102, in order to reduce the interference of various error influences on the hidden danger analysis process, when determining the target device abnormal operation text corresponding to the device abnormal operation text to be processed, the embodiment of the present application makes the failure probability of any first fault detection object in the target device abnormal operation text be affected by the failure probability of several fault detection objects in the reference photovoltaic component operation text, so that each first fault detection object in the target device abnormal operation text can more accurately represent the evaluation score of the hidden danger of the second fault detection object that has a corresponding relationship with the equipment operation status in the device abnormal operation text to be processed, thereby obtaining a better fault detection scheme for the device abnormal operation text to be processed.

[0038] The following is a further implementation method of the present application for providing a reference photovoltaic assembly operation text and a device abnormal operation text to be processed to determine a target device abnormal operation text corresponding to the device abnormal operation text to be processed.

[0039] Step 201: determining a first device abnormal operation text based on the device abnormal operation text to be processed, and determining a second device abnormal operation text based on the reference photovoltaic component operation text.

[0040] In the embodiment of the present application, for some independently implementable technical solutions, the abnormal operation text of the device to be processed can be determined as the first abnormal operation text of the device, and the reference photovoltaic component operation text can be determined as the second abnormal operation text of the device.

[0041] On the basis of the above contents, the process of determining the target device abnormal operation text corresponding to the device abnormal operation text to be processed based on the first device abnormal operation text and the second device abnormal operation text can be understood as the process of directly implementing steps 202-203 based on the device abnormal operation text to be processed and the reference photovoltaic component operation text to obtain the target device abnormal operation text of the device abnormal operation text to be processed.

[0042] For some technical solutions that can be implemented independently, the first high fault rate area information description of the abnormal operation text of the equipment to be processed can be obtained, and the first high fault rate area information description can be determined as the first equipment abnormal operation text; the second high fault rate area information description of the reference photovoltaic component operation text can be obtained, and the second high fault rate area information description can be determined as the second equipment abnormal operation text.

[0043] It should be understood that the process of determining the target device abnormal operation text corresponding to the device abnormal operation text to be processed based on the first device abnormal operation text and the second device abnormal operation text refers to executing the process of steps 202 to 204 as described below based on the first high fault rate area information description of the device abnormal operation text to be processed and the second high fault rate area information description of the reference photovoltaic component operation text to obtain the target device abnormal operation text of the device abnormal operation text to be processed.

[0044] In other examples, in some possible embodiments, for example, an AI intelligent model can be used to perform description mining processing on the abnormal operation text of the device to be processed and the reference photovoltaic component operation text, respectively, to obtain the first high failure rate area information description of the abnormal operation text of the device to be processed, and the second high failure rate area information description of the reference photovoltaic component operation text.

[0045] In some other examples, when performing hidden danger analysis on multiple equipment abnormal operation texts to be processed of several photovoltaic operating equipment of the same type, the reference photovoltaic component operation texts used are all the same, so the second high failure rate area information description can be extracted only once for the reference photovoltaic component operation text, and the second high failure rate area information description can be retained; when performing hidden danger analysis on each group of equipment abnormal operation texts to be processed in the multiple equipment abnormal operation texts to be processed, on the premise that the second high failure rate area information description of the reference photovoltaic component operation text already exists, it is necessary to call the second high failure rate area information description from the database that retains the second high failure rate area information description, and use the description mining network to perform description mining on the equipment abnormal operation texts to be processed to obtain the first high failure rate area information description of each group of equipment abnormal operation texts to be processed.

[0046] Step 202: For each third fault detection object in the first device abnormal operation text, determine a number of target fault detection objects corresponding to the third fault detection object from the second device abnormal operation text; the degree of distinction between the several target fault detection objects and the target fourth fault detection object in the second device abnormal operation text is less than a first distinction threshold, and the target fourth fault detection object is a fourth fault detection object in the second device abnormal operation text whose device operation status corresponds to the third fault detection object.

[0047] In an embodiment of the present application, the first device abnormal operation text is composed of several third fault detection objects; here, if the first device abnormal operation text is the device abnormal operation text to be processed, then each third fault detection object in the first device abnormal operation text has a one-to-one relationship with each second fault detection object in the device abnormal operation text to be processed; if the first device abnormal operation text is the first high fault rate area information description of the device abnormal operation text to be processed, then each third fault detection object in the first device abnormal operation text has a one-to-one relationship with each description content in the first high fault rate area information description.

[0048] Based on a similar idea, the abnormal operation text of the second device is composed of several fourth fault detection objects; if the abnormal operation text of the second device is the reference photovoltaic component operation text, then each fourth fault detection object in the abnormal operation text of the second device has a one-to-one relationship with each fault detection object in the reference photovoltaic component operation text; if the abnormal operation text of the second device is the second high fault rate area information description of the reference photovoltaic component operation text, then each fourth fault detection object in the abnormal operation text of the second device has a one-to-one relationship with each description content in the second high fault rate area information description.

[0049] Furthermore, the embodiment of the present application provides an exemplary implementation method for determining, for each third fault detection object, several target fault detection objects corresponding to the third fault detection object from the abnormal operation text of the second device, including: for each third fault detection object in the abnormal operation text of the first device, determining, from several fourth fault detection objects in the abnormal operation text of the second device, a target fourth fault detection object that has a corresponding relationship with the device operation state of the third fault detection object; from several fourth fault detection objects in the abnormal operation text of the second device, determining several fourth fault detection objects whose discrimination degree with the target fourth fault detection object is less than the first discrimination threshold, and determining the determined fourth fault detection object as the target fault detection object. Exemplarily, the discrimination degree between the fourth fault detection object and the target fourth fault detection object includes, for example, any one of: cosine distance, Euclidean distance, etc.

[0050] When determining a number of target fault detection objects for each third fault detection object, all fourth fault detection objects whose degree of distinction from the target fourth fault detection object is less than the first distinction threshold can be determined as target fault detection objects; or all fourth fault detection objects whose degree of distinction from the target fourth fault detection object is less than the first distinction threshold can be determined as pending fault detection objects, and then a number of target fault detection objects can be determined from the number of pending fault detection objects according to different sampling strategies.

[0051] Step 203: For each of the third fault detection objects, determine an evaluation score of the third fault detection object by means of the similarities between the plurality of target fault detection objects and the third fault detection object.

[0052] In actual implementation, the embodiment of the present application provides an exemplary implementation of determining the similarity between each target fault detection object and the third fault detection object, which may include the following contents.

[0053] Step 301: Based on the equipment operation status of the third fault detection object in the first equipment abnormal operation text and a second discrimination threshold set in advance, obtain the first part of the object features corresponding to the third fault detection object; through the equipment operation status of each target fault detection object in the second equipment abnormal operation text and the second discrimination threshold, obtain the second part of the object features corresponding to each target fault detection object.

[0054] In an embodiment of the present application, for example, the following steps can be used to obtain the first part of object features corresponding to the third fault detection object: in the abnormal operation text of the first device, a first abnormal operation object set centered on the third fault detection object and specified by the second discrimination threshold is determined, and the first part of object features is obtained through the third fault detection object in the abnormal operation text of the first device that is located in the first abnormal operation object set; the following steps are used to obtain the second part of object features corresponding to each target fault detection object: in the abnormal operation text of the second device, a second abnormal operation object set centered on each target fault detection object and specified by the second discrimination threshold is determined, and the second part of object features is obtained through the fourth fault detection object in the abnormal operation text of the second device that is located in the second abnormal operation object set.

[0055] Exemplarily, the first part of the object features and the second part of the object features have the same layer; and the first part of the object features can be composed based on all the third fault detection objects located in the first abnormal operation object set, and the second part of the object features can be composed based on all the fourth fault detection objects located in the second abnormal operation object set.

[0056] Furthermore, the first part of the object features may be composed based on some of the third fault detection objects in the first abnormal operation object set, and the second part of the object features may be composed based on some of the fourth fault detection objects in the second abnormal operation object set. In this case, the device operation status of each third fault detection object in the first part of the object features in the first device abnormal operation text is in a one-to-one pairing relationship with the device operation status of each fourth fault detection object in the second part of the object features in the second device abnormal operation text.

[0057] For some other technical solutions that can be implemented independently, for example, the following steps can also be used to obtain the first part of object features corresponding to the third fault detection object: determine the target abnormal boundary value through the second discrimination threshold; in the first device abnormal operation text, determine a first matching object set with the third fault detection object as a sample to determine the target abnormal boundary value as the abnormal boundary value, and obtain the first part of object features through the third fault detection object in the first device abnormal operation text that is located in the first matching object set; obtain the second part of object features corresponding to each target fault detection object by the following steps: in the second device abnormal operation text, determine a second matching object set with each target fault detection object as a sample to determine the target abnormal boundary value as the abnormal boundary value; obtain the second part of object features through the fourth fault detection object in the second device abnormal operation text that is located in the second matching object set.

[0058] Based on a similar idea, the first part of object features may be composed based on all third fault detection objects in the first matching object set, and the second part of object features may be composed based on all fourth fault detection objects in the second matching object set.

[0059] Furthermore, the first part of the object features may be composed based on some of the third fault detection objects in the first matching object set, and the second part of the object features may be composed based on some of the fourth fault detection objects in the second matching object set. In this case, the device operation status of each third fault detection object in the first part of the object features in the first device abnormal operation text and the device operation status of each fourth fault detection object in the second part of the object features in the second device abnormal operation text have a one-to-one matching relationship.

[0060] Step 302: Determine the similarity between each target fault detection object and the third fault detection object through the first part of object features and the second part of object features.

[0061] After determining the similarities between several target fault detection objects of each third fault detection object and the third fault detection object, for example, the maximum similarity among the similarities between the several target fault detection objects and the third fault detection object can be determined; and the evaluation score of the third fault detection object is determined through the maximum similarity.

[0062] For another example, a mean similarity value may be determined according to the similarities between a plurality of target fault detection objects and the third fault detection object, and the evaluation score of the third fault detection object may be determined based on the mean similarity value.

[0063] On the basis of the above step 203, the method for determining the target device abnormal operation text corresponding to the device abnormal operation text to be processed provided by the embodiment of the present application also includes the following content.

[0064] Step 204: Based on the evaluation score of the third fault detection object, determine the evaluation score of the second fault detection object corresponding to the third fault detection object in the abnormal operation text of the equipment to be processed.

[0065] In actual implementation, for the case where the device abnormal operation text to be processed is determined as the first device abnormal operation text, and the reference photovoltaic component operation text is determined as the second device abnormal operation text, since in this case, the third fault detection object in the first device abnormal operation text and the second fault detection object in the device abnormal operation text to be processed have a one-to-one relationship, the evaluation score of each third fault detection object in the first device abnormal operation text can be determined as the evaluation score of the second fault detection object in the device abnormal operation text to be processed whose device operation status has a corresponding relationship with the third fault detection object.

[0066] In the case where the first high fault rate area information description of the equipment abnormal operation text to be processed is determined as the first equipment abnormal operation text, and the second high fault rate area information description of the reference photovoltaic component operation text is determined as the second equipment abnormal operation text, since in this case, the third fault detection object of the first equipment abnormal operation text and the description content in the first high fault rate area information description have a one-to-one relationship, and the description content in the first high fault rate area information description and the second description content in the equipment abnormal operation text to be processed have a certain comparison result, therefore each third fault detection object in the first part of the object characteristics and each second fault detection object in the equipment abnormal operation text to be processed also have the same comparison result, therefore, the evaluation score corresponding to each second fault detection object can be determined based on the comparison result between each third fault detection object in the first part of the object characteristics and each second fault detection object in the equipment abnormal operation text to be processed, and the evaluation score of each third fault detection object in the first part of the object characteristics.

[0067] In the above step 103, the fault detection scheme of the abnormal operation text of the device to be processed is generated by the abnormal operation text of the target device. For example, the intermediate fault detection scheme of the abnormal operation text of the device to be processed can be determined by using the reference photovoltaic module operation text and the abnormal operation text of the device to be processed; wherein, the intermediate fault detection scheme includes the first probability that each second fault detection object in the abnormal operation text of the device to be processed has a hidden danger. Then, a feature queue is formed by using the intermediate fault detection scheme, and the layer of the feature queue is consistent with the layer of the abnormal operation text of the device to be processed; the quantitative feature value of a random feature in the feature queue is the probability that the second fault detection object corresponding to the feature has a hidden danger, and the larger the quantitative feature value, the greater the probability that the corresponding second fault detection object has a hidden danger; and in the abnormal operation text of the target device, the fault probability of each first fault detection object represents the evaluation score of the hidden danger of the second fault detection object that has a corresponding relationship with the first fault detection object in the abnormal operation text of the device to be processed; the larger the evaluation score, the greater the probability that the second fault detection object has a hidden danger; then the feature queue and the abnormal operation text of the target device are weighted by the feature queue to obtain the fault detection scheme of the abnormal operation text of the device to be processed. In the fault detection scheme, a second probability that each second fault detection object in the abnormal operation text of the device to be processed has a hidden danger is included.

[0068] Under the premise that there is a deviation in the intermediate fault detection scheme, for example, the intermediate fault detection scheme indicates that a certain second fault detection object is likely to have a hidden danger, but the target device abnormal operation text indicates that the second fault detection object is likely to have no hidden danger, then the second probability of the second fault detection object obtained will change by a certain magnitude, and the change in magnitude indicates that the probability of the second fault detection object having a hidden danger is reduced. For another example, the intermediate fault detection scheme indicates that a certain second fault detection object is likely to have no hidden danger, but the target device abnormal operation text indicates that the second fault detection object is likely to have a hidden danger, then the change in magnitude of the second probability of the second fault detection object obtained indicates that the probability of the second fault detection object having a hidden danger is increased. For another example, the intermediate fault detection scheme indicates that a certain second fault detection object is likely to have a hidden danger, and the target device abnormal operation text indicates that the second fault detection object is likely to have a hidden danger, then the change in magnitude of the second probability of the second fault detection object obtained indicates that the probability of the second fault detection object having a hidden danger is further increased. For another example, if the intermediate fault detection scheme indicates that a second fault detection object is more likely to have no hidden dangers, and the target device abnormal operation text indicates that the second fault detection object is more likely to have no hidden dangers, then the magnitude of the change in the second probability of the second fault detection object indicates that the probability that the second fault detection object has no hidden dangers is further increased. Then, through the target device abnormal operation text, the fault detection scheme of the device abnormal operation text to be processed is obtained, which can ensure the accuracy and reliability of fault detection.

[0069] The embodiment of the present application generates a target device abnormal operation text corresponding to the device abnormal operation text to be processed by referring to the photovoltaic component operation text and the device abnormal operation text to be processed. The failure probability of each first fault detection object in the target device abnormal operation text represents an evaluation score of whether there is a hidden danger in the second fault detection object corresponding to the device operation state in the device abnormal operation text to be processed. Then, based on the target device abnormal operation text, the fault detection scheme of the device abnormal operation text to be processed is determined, which can ensure the accuracy and reliability of fault detection.

[0070] Based on the above, please refer to Figure 2 , a photovoltaic module fault detection device 200 is provided, which is applied to a photovoltaic module fault detection system, and the device comprises: The text acquisition module 210 is used to acquire the reference photovoltaic assembly operation text and the abnormal operation text of the device to be processed; The text determination module 220 is used to determine the target device abnormal operation text corresponding to the device abnormal operation text to be processed through the reference photovoltaic component operation text and the device abnormal operation text to be processed; the failure probability of each first fault detection object in the target device abnormal operation text represents the evaluation score of the hidden danger of the second fault detection object; the second fault detection object is the fault detection object whose device operation status in the device abnormal operation text to be processed corresponds to the first fault detection object; The solution generation module 230 is used to generate a fault detection solution for the abnormal operation text of the device to be processed through the abnormal operation text of the target device.

[0071] Based on the above, please refer to Figure 3 , shows a photovoltaic component fault detection system 300, including a processor 310 and a memory 320 that communicate with each other, and the processor 310 is used to read and execute a computer program from the memory 320 to implement the above method.

[0072] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0073] In summary, based on the above scheme, by referring to the photovoltaic component operation text and the equipment abnormal operation text to be processed, a target equipment abnormal operation text corresponding to the equipment abnormal operation text to be processed is generated, and the failure probability of each first fault detection object in the target equipment abnormal operation text represents an evaluation score of whether there is a hidden danger in the second fault detection object corresponding to the equipment operation state in the equipment abnormal operation text to be processed. Then, according to the target equipment abnormal operation text, the fault detection scheme of the equipment abnormal operation text to be processed is determined, which can ensure the accuracy and reliability of fault detection.

[0074] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0075] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or may be any other beneficial effects that may be obtained.

[0076] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only determined as an example and does not constitute a designation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0077] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0078] In addition, it will be appreciated by those skilled in the art that various aspects of the present application may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present application may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0079] A computer storage medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, etc., or a suitable combination. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0080] The computer program codes required for the operation of each part of the present application can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages, etc. The program code can be run entirely on the user's computer, or determined as an independent software package to run on the user's computer, or partially run on the user's computer and partially run on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or determined as a service such as software as a service (SaaS).

[0081] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this application, the use of alphanumeric characters, or the use of other names are not intended to specify the order of the processes and methods of this application. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of the present application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0082] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more embodiments of the invention, in the above description of the embodiments of the application, multiple features are sometimes combined into one embodiment, drawing or description thereof. However, this disclosure method does not mean that the subject matter of the application requires more features than those mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0083] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used for the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers allow adaptive changes. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which can be changed according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0084] Each patent, patent application, patent application disclosure, and other materials, such as articles, books, instructions, publications, documents, etc., cited in this application are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the content of this application, documents that limit the broadest scope of the claims of this application (currently or later attached to this application) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the attached materials of this application are inconsistent or conflicting with the content described in this application, the descriptions, definitions, and / or use of terms in this application shall prevail.

[0085] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of the present application. Other variations may also fall within the scope of the present application. Therefore, the alternative configurations of the embodiments of the present application, which are determined as examples rather than limitations, may be considered consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly introduced and described in the present application.

[0086] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A photovoltaic module fault detection method, characterized in that: include: Obtain reference PV module operation text and abnormal operation text of the equipment to be processed; Determining a target device abnormal operation text corresponding to the device abnormal operation text to be processed by using the reference photovoltaic assembly operation text and the device abnormal operation text to be processed; The failure probability of each first fault detection object in the abnormal operation text of the target device represents the evaluation score of the hidden danger of the second fault detection object; the second fault detection object is the fault detection object whose equipment operation status in the abnormal operation text of the device to be processed corresponds to the first fault detection object; A fault detection scheme for the abnormal operation text of the device to be processed is generated through the abnormal operation text of the target device.

2. The method according to claim 1, characterized in that The step of determining a target device abnormal operation text corresponding to the device abnormal operation text to be processed by using the reference photovoltaic assembly operation text and the device abnormal operation text to be processed includes: Determine a first device abnormal operation text based on the device abnormal operation text to be processed, and determine a second device abnormal operation text based on the reference photovoltaic assembly operation text; For each third fault detection object in the first device abnormal operation text, determine a number of target fault detection objects corresponding to the third fault detection object from the second device abnormal operation text; the degree of distinction between the several target fault detection objects and the target fourth fault detection object in the second device abnormal operation text is less than a first distinction threshold, and the target fourth fault detection object is a fourth fault detection object in the second device abnormal operation text whose device operation state corresponds to the third fault detection object; For each of the third fault detection objects, determining an evaluation score of the third fault detection object by means of the similarities between the plurality of target fault detection objects and the third fault detection object respectively; Based on the evaluation score of the third fault detection object, an evaluation score of a second fault detection object corresponding to the third fault detection object in the abnormal operation text of the equipment to be processed is determined.

3. The method according to claim 2, characterized in that The determining of the first device abnormal operation text based on the device abnormal operation text to be processed, and the determining of the second device abnormal operation text based on the reference photovoltaic component operation text, comprises: determining the device abnormal operation text to be processed as the first device abnormal operation text, and determining the reference photovoltaic component operation text as the second device abnormal operation text; or, The determining of a first device abnormal operation text based on the device abnormal operation text to be processed, and the determining of a second device abnormal operation text based on the reference photovoltaic component operation text, include: obtaining a first high-failure-rate area information description of the device abnormal operation text to be processed, and determining the first high-failure-rate area information description as the first device abnormal operation text; obtaining a second high-failure-rate area information description of the reference photovoltaic component operation text, and determining the second high-failure-rate area information description as the second device abnormal operation text.

4. The method according to claim 3, characterized in that For each of the third fault detection objects, determining an evaluation score of the third fault detection object by means of similarities between the plurality of target fault detection objects and the third fault detection object, comprises: Determine the maximum similarity among the similarities between the plurality of target fault detection objects and the third fault detection object; and determine the evaluation score of the third fault detection object according to the maximum similarity.

5. The method according to claim 4, characterized in that For each third fault detection object in the first device abnormal operation text, determining a plurality of target fault detection objects corresponding to the third fault detection object from the second device abnormal operation text, including: For each third fault detection object in the abnormal operation text of the first device, determine a target fourth fault detection object having a corresponding relationship with the operation state of the third fault detection object device from a plurality of fourth fault detection objects in the abnormal operation text of the second device; From the plurality of fourth fault detection objects in the abnormal operation text of the second device, determine a plurality of fourth fault detection objects whose degree of distinction from the target fourth fault detection object is less than a first distinction threshold, and determine the determined fourth fault detection objects as the target fault detection object.

6. The method according to claim 5, characterized in that For each of the third fault detection objects, the similarity between each target fault detection object and the third fault detection object is determined by the following steps: Based on the device operation state of the third fault detection object in the first device abnormal operation text and the second discrimination threshold configured in advance, a first part of object features corresponding to the third fault detection object is obtained; Obtaining a second part of object features corresponding to each target fault detection object according to the device operation state of each target fault detection object in the second device abnormal operation text and the second discrimination threshold; The similarity between each target fault detection object and the third fault detection object is determined by using the first part of object features and the second part of object features.

7. The method according to claim 6, characterized in that The method of obtaining the first part of object features corresponding to the third fault detection object based on the device operation state of the third fault detection object in the first device abnormal operation text and the second discrimination threshold value set in advance comprises: determining, in the first device abnormal operation text, a first abnormal operation object set centered on the third fault detection object and specified with the second discrimination threshold value as a requirement, and obtaining the first part of object features through the third fault detection object in the first device abnormal operation text that is within the first abnormal operation object set; The second part of object features corresponding to each target fault detection object is obtained through the equipment operation status of each target fault detection object in the second equipment abnormal operation text and the second discrimination threshold, including: in the second equipment abnormal operation text, a second abnormal operation object set centered on each target fault detection object and specified with the second discrimination threshold is determined, and the second part of object features is obtained through a fourth fault detection object in the second equipment abnormal operation text that is located in the second abnormal operation object set.

8. The method according to claim 6, characterized in that The method of obtaining the first part of object features corresponding to the third fault detection object based on the device operation state of the third fault detection object in the first device abnormal operation text and a second discrimination threshold value set in advance includes: determining a target abnormal boundary value through the second discrimination threshold value; determining a first matching object set in the first device abnormal operation text that takes the third fault detection object as a sample and determines the target abnormal boundary value as an abnormal boundary value, and obtaining the first part of object features through the third fault detection object in the first device abnormal operation text that is located in the first matching object set; The second part of object features corresponding to each target fault detection object is obtained by using the device operation status of each target fault detection object in the second device abnormal operation text and the second discrimination threshold, including: in the second device abnormal operation text, determining a second matching object set with each target fault detection object as a sample to determine the target abnormal boundary value as an abnormal boundary value; and obtaining the second part of object features by using a fourth fault detection object in the second device abnormal operation text that is within the second matching object set.

9. The method according to claim 3, characterized in that: In the case where the first device abnormal operation text is the device abnormal operation text to be processed and the second device abnormal operation text is the reference photovoltaic assembly operation text, determining the evaluation score of the second fault detection object corresponding to the third fault detection object in the device abnormal operation text to be processed based on the evaluation score of the third fault detection object includes: Determine the evaluation score of each third fault detection object in the first device abnormal operation text as the evaluation score of the second fault detection object in the device abnormal operation text to be processed, the device operation status of which corresponds to the third fault detection object; Wherein, for a case where the first device abnormal operation text is the first high fault rate area information description and the second device abnormal operation text is the second high fault rate area information description, determining the evaluation score of the second fault detection object corresponding to the third fault detection object in the device abnormal operation text to be processed based on the evaluation score of the third fault detection object includes: Based on the comparison results between each third fault detection object in the first part of the object characteristics and each second fault detection object in the abnormal operation text of the equipment to be processed, and the evaluation score of each third fault detection object in the first part of the object characteristics, determine the evaluation score corresponding to each second fault detection object.

10. A photovoltaic module fault detection system, characterized in that: It comprises a processor and a memory communicating with each other, the processor is used to call a computer program from the memory, and implement the method according to any one of claims 1 to 9 by running the computer program.

Images