Power distribution line equipment fault monitoring method and system based on photovoltaic new energy

Abstract

The invention relates to the technical field of data fault monitoring, and provides a distribution line equipment fault monitoring method and system based on photovoltaic new energy, and the method comprises the steps: selecting distribution line monitoring data characters from distribution line monitoring data after classification processing, and transmitting a distribution line equipment fault monitoring model; according to the method, the situation that all selected distribution line monitoring data characters are transmitted to the distribution line equipment fault monitoring model after each time of classification processing is avoided as much as possible, so that the problem that the work task load of the distribution line equipment fault monitoring model is too large can be solved, and thus the production equipment monitoring efficiency can be effectively improved. Therefore, the accuracy and efficiency of fault monitoring can be improved.

Description

Technical Field

[0001] This application relates to the technical field of data fault monitoring. Specifically, it relates to a method and system for monitoring faults of distribution line equipment based on photovoltaic new energy. Background Art

[0002] ‌Faults of distribution line equipment‌ mainly include types such as single-phase grounding faults, interphase short-circuit faults, and line faults. The causes of these faults are diverse, including equipment aging, damage to insulating materials, weather effects, human factors, etc.

[0003] Currently, with the continuous development and progress of artificial intelligence, mechanical fault monitoring has gradually been replaced by artificial intelligence. In this way, the monitoring efficiency of faults can be effectively improved. However, in the actual operation process, it is difficult to accurately determine the location and type of the fault point. Therefore, a technical solution is needed to improve the accuracy and efficiency of fault monitoring. Summary of the Invention

[0004] In view of this, this application provides a method and system for monitoring faults of distribution line equipment based on photovoltaic new energy.

[0005] In a first aspect, a method for monitoring faults of distribution line equipment based on photovoltaic new energy is provided. The method at least includes: Classify the distribution line monitoring data that needs to be analyzed to obtain the classified distribution line monitoring data; Select at least one distribution line monitoring data character from the classified distribution line monitoring data; determine the distribution line monitoring data character that needs to be classified from the at least one distribution line monitoring data character. Among them, the quantity and analysis accuracy of the distribution line monitoring data characters that need to be classified determined successively on the premise of the first and non-first execution of classification processing are different; On the premise of non-first execution of classification processing, determine the distribution line monitoring data character that needs to be classified from the at least one distribution line monitoring data character according to the current description content of the core description of the distribution line monitoring data that needs to be analyzed; obtain the evaluation result of the core description in the distribution line monitoring data character that needs to be classified through the distribution line equipment fault monitoring model; Determine the distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed according to the evaluation result of the core description in the distribution line monitoring data character that needs to be classified.

[0006] In this application, the classification processing of the distribution line monitoring data that needs to be analyzed includes: Classify the power distribution line monitoring data to be analyzed according to the unparsed decoding specified values in the decoding percentage set.

[0007] In this application, the power distribution line equipment fault monitoring result of the power distribution line monitoring data to be analyzed determined according to the evaluation result of the core description in the power distribution line monitoring data characters to be classified includes: If there is no unparsed decoding specified value in the decoding percentage set or it is determined that there is no power distribution line monitoring data character to be classified in the at least one power distribution line monitoring data character, determine the power distribution line equipment fault monitoring result of the power distribution line monitoring data to be analyzed according to the evaluation result of the core description in the power distribution line monitoring data characters to be classified.

[0008] In this application, the decoding percentage set includes: at least two different decoding specified values, and the smaller decoding specified value is parsed before the larger decoding specified value.

[0009] In this application, determining the power distribution line monitoring data characters to be classified from the at least one power distribution line monitoring data character includes: on the premise of first performing the classification process, determining all power distribution line monitoring data characters as the power distribution line monitoring data characters to be classified.

[0010] In this application, determining the power distribution line monitoring data characters to be classified from the at least one power distribution line monitoring data character includes: on the premise of non-first performing the classification process, the number of power distribution line monitoring data characters to be classified is less than or equal to the number of currently selected power distribution line monitoring data characters, and / or, the data analysis accuracy of the power distribution line monitoring data to be analyzed after the current classification process is greater than the data analysis accuracy after the previous classification process.

[0011] In this application, determining the power distribution line monitoring data characters to be classified from the at least one power distribution line monitoring data character according to the current description content of the core description of the power distribution line monitoring data to be analyzed includes: Determine the current description content of each core description according to the current evaluation results of the core descriptions in the multiple core descriptions included in the power distribution line monitoring data to be analyzed; Count the number of core descriptions that achieve the preset description content in the current description content of the core descriptions in the power distribution line monitoring data set bound by the power distribution line monitoring data characters; Determine the power distribution line monitoring data characters that do not meet the preset requirements in terms of the core description quantity for implementing the preset description content as the power distribution line monitoring data characters that need to be classified.

[0012] In this application, the determination of the power distribution line monitoring data characters that do not meet the preset requirements in terms of the core description quantity for implementing the preset description content as the power distribution line monitoring data characters that need to be classified includes: On the premise of the power distribution line monitoring data characters, on the premise that the percentage result of the core description quantity for implementing the preset description content and the total core descriptions of the power distribution line monitoring data set to be analyzed bound to this power distribution line monitoring data character is less than the preset percentage result, determine this power distribution line monitoring data character as the power distribution line monitoring data character that needs to be classified.

[0013] In this application, the steps for obtaining the current evaluation results of each core description of the power distribution line monitoring data to be analyzed include: On the premise of the first execution of the classification process, associate the evaluation results of each core description in all the power distribution line monitoring data characters that need to be classified output by the power distribution line equipment fault monitoring model to the power distribution line monitoring data to be analyzed, and obtain the evaluation results of each core description of the power distribution line monitoring data to be analyzed; wherein, the evaluation results of each core description of the power distribution line monitoring data to be analyzed are determined as the current evaluation results of each core description of the power distribution line monitoring data to be analyzed.

[0014] In this application, the steps for obtaining the current evaluation results of each core description of the power distribution line monitoring data to be analyzed include: On the premise of non-first execution of the classification process, associate the evaluation results of each core description in all the power distribution line monitoring data characters that need to be classified output by the power distribution line equipment fault monitoring model to the power distribution line monitoring data to be analyzed, and obtain the evaluation results of multiple core descriptions of the power distribution line monitoring data to be analyzed; update the current evaluation results of the corresponding core descriptions of the power distribution line monitoring data to be analyzed according to the evaluation results of multiple core descriptions of the power distribution line monitoring data to be analyzed obtained this time.

[0015] In this application, the update of the current evaluation results of the corresponding core descriptions of the power distribution line monitoring data to be analyzed according to the evaluation results of multiple core descriptions of the power distribution line monitoring data to be analyzed obtained this time includes: Statistically determine the values of the evaluation results of multiple core descriptions of the power distribution line monitoring data to be analyzed obtained this time and the current evaluation results of the corresponding core descriptions in the power distribution line monitoring data to be analyzed; Update the current evaluation result of the corresponding core description in the distribution line monitoring data to be analyzed by using the determined value obtained through statistics.

[0016] In this application, determining the distribution line equipment fault monitoring result of the distribution line monitoring data to be analyzed based on the evaluation result of the core description in the distribution line monitoring data characters to be classified includes: On the premise of one of the core descriptions in the distribution line monitoring data to be analyzed, determine the best percentage result among the percentage results belonging to each type in the current evaluation result of this core description, and determine the best percentage result and the type bound to the best percentage result as the distribution line equipment fault monitoring result of this core description.

[0017] In this application, the analysis accuracy of the distribution line monitoring data example for training the distribution line equipment fault monitoring model includes: successively classifying the distribution line monitoring data according to each decoding specified value in the decoding percentage set, and the analysis accuracy of each obtained distribution line monitoring data.

[0018] In a second aspect, a distribution line equipment fault monitoring system based on photovoltaic new energy is provided, including a processor and a memory that communicate with each other. The processor is used to retrieve a computer program from the memory and implement the above method by running the computer program.

[0019] A distribution line equipment fault monitoring method and system based on photovoltaic new energy provided by an embodiment of this application. The present disclosure selects distribution line monitoring data characters from the classified distribution line monitoring data and transmits the distribution line equipment fault monitoring model, and as much as possible avoids transmitting all the selected distribution line monitoring data characters to the distribution line equipment fault monitoring model after each classification process, so as to be able to improve the problem that the workload of the distribution line equipment fault monitoring model is too large. In this way, the efficiency of production equipment monitoring can be effectively improved. Therefore, the accuracy and efficiency of fault monitoring can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of this application, the drawings to be analyzed in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application, and therefore should not be regarded as a limitation of the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a flowchart of a distribution line equipment fault monitoring method provided by an embodiment of this application.

[0022] Figure 2 It is a block diagram of a fault monitoring device for distribution line equipment based on photovoltaic new energy provided by an embodiment of the present application.

[0023] Figure 3 It is an architecture diagram of a fault monitoring system for distribution line equipment based on photovoltaic new energy provided by an embodiment of the present application. Specific implementation manners

[0024] In order to better understand the above technical solution, the technical solution of the present application will be 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 solution of the present application, rather than limitations on the technical solution of the present application. Without conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0025] Please refer to Figure 1 , which shows a method for monitoring faults in distribution line equipment based on photovoltaic new energy. The method may include the technical solutions described in the following steps 100-step 140.

[0026] Step 100: Classify the distribution line monitoring data to be analyzed to obtain the classified distribution line monitoring data.

[0027] In a possible embodiment, the present disclosure can classify the distribution line monitoring data to be analyzed in multiple ways. For example, the present disclosure has a pre-trained set of decoding percentages, which includes at least two different decoding specified values. The present disclosure can select an unparsed decoding specified value from the set of decoding percentages and classify the distribution line monitoring data to be analyzed according to the selected decoding specified value. In addition, when the present disclosure selects an unparsed decoding specified value, it generally first selects the smallest unparsed decoding specified value. Furthermore, the present disclosure can also classify the distribution line monitoring data to be analyzed by means of convolutional processing or decoding processing.

[0028] Step 110: Select at least one distribution line monitoring data character from the classified distribution line monitoring data.

[0029] In a possible embodiment, the present disclosure generally divides the distribution line monitoring data obtained after classification processing into multiple distribution line monitoring data characters according to the preset requirements of the distribution line equipment fault monitoring model for the transmitted data. The presets of all the selected distribution line monitoring data characters are generally exactly the same. Each selected distribution line monitoring data character corresponds in sequence to a set in the distribution line monitoring data to be analyzed, and different distribution line monitoring data characters correspond to different sets. The preset of the set bound to the distribution line monitoring data character is generally related to the decoding specified value and the preset requirements of the distribution line equipment fault monitoring model for the transmitted data.

[0030] Step 120: Determine the distribution line monitoring data characters to be classified from at least one distribution line monitoring data character.

[0031] In a possible embodiment, on the premise of first performing the classification processing, the present disclosure may determine all the distribution line monitoring data characters as the distribution line monitoring data characters to be classified. On the premise of non-first performing the classification processing, the number of the determined distribution line monitoring data characters to be classified is generally less than the number of all the currently selected distribution line monitoring data characters.

[0032] In a possible embodiment, on the premise of not performing the classification process for the first time, the present disclosure can select each selected power distribution line monitoring data character according to the current description content of the core description of the power distribution line monitoring data that needs to be analyzed. The selected power distribution line monitoring data characters are the power distribution line monitoring data characters that need to be classified. For example, the present disclosure first determines the current description content of each core description according to the current evaluation results of each core description in the power distribution line monitoring data that needs to be analyzed. For example, for a core description in the power distribution line monitoring data that needs to be analyzed, the percentage result of the first percentage result (the best percentage result) and the second percentage result (the second largest percentage result) of the core description is statistically calculated, and the statistically calculated percentage result is determined as the current description content of the core description. According to this process, the current description content of all core descriptions in the power distribution line monitoring data that needs to be analyzed can be obtained. Then, the number of core descriptions that realize the preset description content in the core descriptions of the power distribution line monitoring data set that needs to be analyzed and to which the power distribution line monitoring data characters are bound is statistically calculated, and the power distribution line monitoring data characters whose number of core descriptions that realize the preset description content does not meet the preset requirements are determined as the power distribution line monitoring data characters that need to be classified. For example, on the premise that the percentage result of the number of core descriptions that realize the preset description content and the number of all core descriptions in the power distribution line monitoring data set that needs to be analyzed and to which the power distribution line monitoring data character is bound is less than the preset percentage result, the power distribution line monitoring data character can be determined as the power distribution line monitoring data character that needs to be classified.

[0033] In a possible embodiment, the present disclosure can obtain the current evaluation results of each core description of the power distribution line monitoring data that needs to be analyzed in the following two ways: (1) On the premise of performing the classification process for the first time, the evaluation results of each core description in all the power distribution line monitoring data characters that need to be classified output by the power distribution line equipment fault monitoring model are associated with the power distribution line monitoring data that needs to be analyzed, and the evaluation results of each core description of the power distribution line monitoring data that needs to be analyzed are obtained. The present disclosure can determine the currently obtained evaluation results of each core description of the power distribution line monitoring data that needs to be analyzed as the current evaluation results of each core description of the power distribution line monitoring data that needs to be analyzed.

[0034] (2) On the premise of not performing classification processing for the first time, associate the evaluation results of each core description in all the power distribution line monitoring data characters that need to be classified and output by the power distribution line equipment fault monitoring model to the power distribution line monitoring data that needs to be analyzed, obtain the evaluation results of multiple core descriptions of the power distribution line monitoring data that needs to be analyzed, and update the current evaluation results of the corresponding core descriptions of the power distribution line monitoring data that needs to be analyzed according to the evaluation results of multiple core descriptions of the power distribution line monitoring data obtained this time. For example, count the determination values of the evaluation results of multiple core descriptions of the power distribution line monitoring data obtained this time and the current evaluation results of the corresponding core descriptions in the power distribution line monitoring data that needs to be analyzed, and use the counted determination values to update the current evaluation results of the corresponding core descriptions in the power distribution line monitoring data that needs to be analyzed. After the update process, the present disclosure obtains the current evaluation results of each core description of the power distribution line monitoring data that needs to be analyzed.

[0035] Step 130: Obtain the evaluation results of the core descriptions in the power distribution line monitoring data characters that need to be classified through the power distribution line equipment fault monitoring model.

[0036] In a possible embodiment, the power distribution line equipment fault monitoring model in the present disclosure can be a power distribution line equipment fault monitoring model. By classifying the power distribution line monitoring data that needs to be analyzed and transmitting the data set that needs to be classified in the classified power distribution line monitoring data to the power distribution line equipment fault monitoring model, it is beneficial to improve the computing power of the power distribution line equipment fault monitoring model, thereby helping to improve the problem that the core description of the power distribution line monitoring data by the power distribution line equipment fault monitoring model is incorrect.

[0037] In a possible embodiment, the power distribution line equipment fault monitoring model in the present disclosure is trained by using power distribution line monitoring data examples with multiple different analysis precisions. For example, the analysis precision of each power distribution line monitoring data example belongs to the analysis precisions sequentially bound to the respective decoding specified values in the decoding percentage set. For example, the reduction percentage set includes: the first decoding specified value, the second decoding specified value, and the third decoding specified value. The first decoding specified value corresponds to the first analysis precision, the second decoding specified value corresponds to the second analysis precision, and the third decoding specified value corresponds to the third analysis precision. Then, the present disclosure can use the power distribution line monitoring data examples with the first analysis precision, the power distribution line monitoring data examples with the second analysis precision, and the power distribution line monitoring data examples with the third analysis precision to train the power distribution line equipment fault monitoring model to be trained. The successfully trained power distribution line equipment fault monitoring model can be used for the power distribution line monitoring data matching in the present disclosure.

[0038] Step 140: Determine the power distribution line equipment fault monitoring result of the power distribution line monitoring data to be analyzed based on the evaluation result of the core description in the power distribution line monitoring data characters to be classified as needed.

[0039] In a possible embodiment, the present disclosure will execute the step of determining the power distribution line equipment fault monitoring result of the power distribution line monitoring data to be analyzed based on the evaluation result of the core description in the power distribution line monitoring data characters to be classified as needed when there is no unparsed decoding specified value in the decoding percentage set or when it is impossible to determine the power distribution line monitoring data characters to be classified from at least one power distribution line monitoring data character. For example, under the premise of one of the core descriptions in the power distribution line monitoring data to be analyzed, determine the best percentage result among the percentage results of each type in the current evaluation result of this core description, and determine the best percentage result and the type bound to the best percentage result as the power distribution line equipment fault monitoring result of this core description.

[0040] The power distribution line equipment fault monitoring method based on photovoltaic new energy of the present disclosure may specifically include the following steps: Step 200, Step 210, Step 220, and Step 230.

[0041] Step 200: Classify the power distribution line monitoring data to be analyzed according to the smallest unparsed decoding specified value in the decoding percentage set.

[0042] In a possible embodiment, the decoding percentage set is composed of multiple decoding specified values, and the value of each decoding specified value is greater than 1 and not greater than 2.

[0043] In a possible embodiment, the present disclosure should sort according to the decoding specified value, select a decoding specified value from the decoding percentage set each time, and classify the power distribution line monitoring data to be analyzed according to the selected decoding specified value. The selected decoding specified value becomes the parsed decoding specified value.

[0044] Step 210: Divide the classified power distribution line monitoring data into at least one power distribution line monitoring data character.

[0045] In a possible embodiment, the present disclosure generally divides the distribution line monitoring data obtained after classification processing into multiple distribution line monitoring data characters according to the preset requirements of the transmission data for the distribution line equipment fault monitoring model. The presets of all the selected distribution line monitoring data characters are generally exactly the same. Each selected distribution line monitoring data character corresponds in sequence to a set in the distribution line monitoring data to be analyzed, and different distribution line monitoring data characters correspond to different sets. The preset of the set bound to the distribution line monitoring data character is generally related to the decoding specified value and the preset requirements of the distribution line equipment fault monitoring model for the transmission data.

[0046] Step 220: Select distribution line monitoring data characters from each distribution line monitoring data character according to the current description content of the core description of the distribution line monitoring data to be analyzed, and obtain the evaluation results of each core description in each selected distribution line monitoring data character through the distribution line equipment fault monitoring model. Among them, the selected distribution line monitoring data characters are the distribution line monitoring data characters to be classified as described above.

[0047] In a possible embodiment, on the premise of first performing classification processing, the present disclosure generally determines all the selected distribution line monitoring data characters as the selected distribution line monitoring data characters. The present disclosure can consider that on the premise of first performing classification processing, the current description content of the core description of the distribution line monitoring data to be analyzed is updated. Therefore, all the selected distribution line monitoring data characters are selected and transmitted in sequence to the distribution line equipment fault monitoring model, so that the evaluation results of all the core descriptions of all the currently selected distribution line monitoring data characters can be obtained through the distribution line equipment fault monitoring model. The evaluation results of all the core descriptions of all the currently obtained distribution line monitoring data characters can be used to update the current description content of the core description of the distribution line monitoring data to be analyzed. For example, it is set that the distribution line equipment fault monitoring model of the present disclosure can perform division processing for X types. After each distribution line monitoring data character passes through the distribution line equipment fault monitoring model in sequence, the present disclosure can obtain the evaluation results of all the core descriptions in all the distribution line monitoring data characters for X types in sequence.

[0048] In a possible embodiment, on the premise of non-first execution of classification processing, the present disclosure generally selects power distribution line monitoring data characters from all the power distribution line monitoring data characters selected this time according to the current description content of the core description of the power distribution line monitoring data to be analyzed. It can be understood that the power distribution line monitoring data characters selected this time may be all the power distribution line monitoring data characters selected this time, or may be some of the power distribution line monitoring data characters among all the power distribution line monitoring data characters selected this time; of course, it is also possible that no power distribution line monitoring data character can be selected from all the power distribution line monitoring data characters selected this time.

[0049] The present disclosure classifies the power distribution line monitoring data to be analyzed and transmits the data set in the classified power distribution line monitoring data to a power distribution line equipment fault monitoring model (such as the power distribution line equipment fault monitoring model), which is beneficial to improving the computing power of the power distribution line equipment fault monitoring model (such as the power distribution line equipment fault monitoring model), and thus is beneficial to improving the problem that the core description of the power distribution line equipment fault monitoring model for the power distribution line monitoring data is incorrect.

[0050] The method for the present disclosure to select power distribution line monitoring data characters (i.e., the power distribution line monitoring data characters to be classified) according to the current description content of the core description of the power distribution line monitoring data to be analyzed may specifically include the following steps.

[0051] Step 300: Determine the current description content of each core description according to the current evaluation result of each core description of the power distribution line monitoring data to be analyzed.

[0052] In a possible embodiment, the current evaluation results of each core description of the power distribution line monitoring data to be analyzed in the present disclosure are composed based on the evaluation results of each core description in the power distribution line monitoring data characters output by the power distribution line equipment fault monitoring model for each of the multiple transmitted power distribution line monitoring data characters. In the process of each execution of classification processing by the present disclosure, it is necessary to update the current evaluation results of each core description of the power distribution line monitoring data to be analyzed (such as updating the current evaluation results of each core description of the power distribution line monitoring data to be analyzed).

[0053] In a possible embodiment, for any core description (X, Y) in the distribution line monitoring data to be analyzed, the manner in which the present disclosure determines the current description content of the core description (X, Y) based on the current evaluation result of the core description (X, Y) of the distribution line monitoring data to be analyzed may be as follows: It is set that the distribution line equipment fault monitoring model can select X types from the distribution line monitoring data. The current evaluation result of the core description (X, Y) will include X percentage results. The present disclosure can identify the best percentage result and the second-largest percentage result (i.e., the fourth-largest percentage result) from these X percentage results, and count the percentage result of the identified first percentage result and the second percentage result. The present disclosure can determine this percentage result as the current description content of the core description (X, Y). The present disclosure can also determine the current description content of each core description of the distribution line monitoring data to be analyzed by parsing other methods based on the current evaluation results of each core description of the distribution line monitoring data to be analyzed. The present disclosure does not limit the specific manner of determining the current description content of each core description of the distribution line monitoring data to be analyzed.

[0054] Step 310: Count the number of core descriptions whose current description content in the initial distribution line monitoring data set bound by the distribution line monitoring data characters achieves the preset description content.

[0055] In a possible embodiment, the preset of the preset description content in the present disclosure can be based on current training. For example, the preset description content can be trained to be 16.

[0056] Step 320: Determine the distribution line monitoring data characters whose number of core descriptions achieving the preset description content does not meet the preset requirements as the selected distribution line monitoring data characters.

[0057] In a possible embodiment, for any distribution line monitoring data character, if the percentage result of the number of core descriptions in the initial distribution line monitoring data set bound by the distribution line monitoring data character that achieves the preset description content to the total number of all core descriptions in the set does not achieve the preset percentage result, then the distribution line monitoring data character can be determined as the selected distribution line monitoring data character and transmitted to the distribution line equipment fault monitoring model, so as to obtain the evaluation results of each core description in the distribution line monitoring data character through the distribution line equipment fault monitoring model; if the above percentage result achieves the preset percentage result, then it is not necessary to transmit the distribution line monitoring data character to the distribution line equipment fault monitoring model. The preset percentage result in the present disclosure can be based on current training.

[0058] In addition, the present disclosure can also analyze other methods to determine the distribution line monitoring data characters that do not meet the preset requirements. For example, on the premise that the result of the difference between the number of core descriptions that implement the preset description content and the number of core descriptions that do not implement the preset description content in the initial distribution line monitoring data set bound to the distribution line monitoring data character realizes the preset difference result, the distribution line monitoring data character can be determined as the selected distribution line monitoring data character and transmitted to the distribution line equipment fault monitoring model. Otherwise, it is not necessary to transmit the distribution line monitoring data character to the distribution line equipment fault monitoring model. For another example, on the premise that the percentage result of the number of core descriptions that implement the preset description content and the number of core descriptions that do not implement the preset description content in the initial distribution line monitoring data set bound to the distribution line monitoring data character does not realize the preset percentage result, the distribution line monitoring data character can be determined as the selected distribution line monitoring data character and transmitted to the distribution line equipment fault monitoring model. Otherwise, it is not necessary to transmit the distribution line monitoring data character to the distribution line equipment fault monitoring model.

[0059] The steps for the present disclosure to update the current evaluation results of each core description of the distribution line monitoring data that needs to be analyzed specifically may include the following content. Step 400: The distribution line equipment fault monitoring method based on photovoltaic new energy of the present disclosure starts. Optionally, the present disclosure can update the current evaluation results of each core description of the distribution line monitoring data that needs to be analyzed when the distribution line equipment fault monitoring method based on photovoltaic new energy starts, such as training the current evaluation results of each core description of the distribution line monitoring data that needs to be analyzed to 0. Of course, it is also completely feasible not to perform the update step on the current evaluation results of each core description of the distribution line monitoring data that needs to be analyzed.

[0060] On the premise that the present disclosure performs classification processing for the first time, the execution of step 410 is triggered.

[0061] On the premise that the present disclosure performs classification processing for the second time or the third time, etc., which is not the first time, the execution of step 440 is triggered.

[0062] Step 410: All the distribution line monitoring data characters selected from the distribution line monitoring data after the current classification processing are transmitted to the distribution line equipment fault monitoring model. As a result, the distribution line equipment fault monitoring model will sequentially output the evaluation results of each core description in each distribution line monitoring data character for the selected all distribution line monitoring data. Proceed to step 420.

[0063] Step 420: Sequentially associate the evaluation results of each core description in each distribution line monitoring data character output by the distribution line equipment fault monitoring model to the distribution line monitoring data to be analyzed, so as to obtain the evaluation results of each core description of the distribution line monitoring data to be analyzed. Proceed to step 430.

[0064] In a possible embodiment, on the premise of the first execution of classification processing in the present disclosure, based on the evaluation results of each core description in each distribution line monitoring data character output by the distribution line equipment fault monitoring model, obtain the evaluation result of any core description (X, Y) in the distribution line monitoring data to be analyzed. Among them, for the first execution of classification processing, G represents the number of types divided by the distribution line equipment fault monitoring model. represents the evaluation result that any core description (X, Y) in the distribution line monitoring data to be analyzed belongs to the first type on the premise of the first execution of analysis accuracy processing. represents the evaluation result that any core description (X, Y) in the distribution line monitoring data to be analyzed belongs to the second type on the premise of the first execution of analysis accuracy processing. represents the evaluation result that any core description (X, Y) in the distribution line monitoring data to be analyzed belongs to the Gth type on the premise of the first execution of analysis accuracy processing.

[0065] Step 430: Determine the evaluation results of each core description of the distribution line monitoring data to be analyzed obtained this time as the current evaluation results of each core description of the distribution line monitoring data to be analyzed. For example, the current evaluation result of any core description (X, Y) of the distribution line monitoring data to be analyzed.

[0066] Step 440: Select distribution line monitoring data characters from all the distribution line monitoring data characters selected after this classification processing, and transmit the selected distribution line monitoring data characters to the distribution line equipment fault monitoring model. Proceed to step 450.

[0067] Step 450: Sequentially associate the evaluation results of each core description in each distribution line monitoring data character output by the distribution line equipment fault monitoring model to the distribution line monitoring data to be analyzed, so as to obtain the evaluation results of at least some core descriptions of the distribution line monitoring data to be analyzed. Proceed to step 460.

[0068] In a possible embodiment, on the premise of performing classification processing for the i-th time (i > 2) in the present disclosure, based on the evaluation results of each core description in each distribution line monitoring data character output by the distribution line equipment fault monitoring model, the evaluation result of any core description (X, Y) in the distribution line monitoring data that needs to be analyzed is obtained. Here, i represents the i-th execution of classification processing, G represents the number of types divided by the distribution line equipment fault monitoring model, represents the evaluation result that any core description (X, Y) in the distribution line monitoring data that needs to be analyzed belongs to the first type on the premise of performing analysis accuracy processing for the i-th time, represents the evaluation result that any core description (X, Y) in the distribution line monitoring data that needs to be analyzed belongs to the second type on the premise of performing analysis accuracy processing for the i-th time, and represents the evaluation result that any core description (X, Y) in the distribution line monitoring data that needs to be analyzed belongs to the G-th type on the premise of performing analysis accuracy processing for the i-th time. It can be understood that if the core description (X, Y) in the distribution line monitoring data that needs to be analyzed belongs to the core description of the set in the distribution line monitoring data characters selected in the current classification processing process and is associated with the distribution line monitoring data that needs to be analyzed, it is the evaluation result of the corresponding core description output by the distribution line equipment fault monitoring model. If the core description (X, Y) does not belong to the core description of the set in the distribution line monitoring data characters selected in the current classification processing process and is associated with the distribution line monitoring data that needs to be analyzed, the present disclosure can set it to 0 for training.

[0069] Step 460: Update the current evaluation results of each core description of the distribution line monitoring data that needs to be analyzed by using the evaluation results of at least some core descriptions of the distribution line monitoring data that needs to be analyzed obtained this time.

[0070] In a possible embodiment, on the premise of performing classification processing for the second time, the third time, or other non-first times, the present disclosure obtains the current evaluation results of each core description of the distribution line monitoring data that needs to be analyzed by iteratively evaluating the results of each core description in each distribution line monitoring data character obtained successively each time.

[0071] Set that on the premise of performing classification processing for the first time, the evaluation result of any core description (X, Y) in the distribution line monitoring data obtained by the present disclosure is, so the present disclosure will record it as the current evaluation result of any core description (X, Y) in the distribution line monitoring data that needs to be analyzed.

[0072] On the premise of the second execution of the classification process, the evaluation result of any core description (X, Y) in the distribution line monitoring data to be analyzed obtained by the present disclosure based on the distribution line equipment fault monitoring model can be expressed as follows. Among them, if the core description (X, Y) in the distribution line monitoring data to be analyzed belongs to the core description of the set associated with the distribution line monitoring data characters selected in the second classification process and is associated with the distribution line monitoring data to be analyzed, it is the evaluation result of the corresponding core description output by the distribution line equipment fault monitoring model. If the core description (X, Y) in the distribution line monitoring data to be analyzed does not belong to the core description of the set associated with the distribution line monitoring data characters selected in the second classification process and is associated with the distribution line monitoring data to be analyzed, it is 0. The present disclosure can target the determination value of the non-zero statistical sum and use the statistically determined value to update the current evaluation result of the corresponding core description (X, Y) in the distribution line monitoring data to be analyzed.

[0073] On the premise of the third execution of the classification process, the evaluation result of any core description (X, Y) in the distribution line monitoring data to be analyzed obtained by the present disclosure based on the distribution line equipment fault monitoring model can be expressed as follows. Among them, if the core description (X, Y) in the distribution line monitoring data to be analyzed belongs to the core description of the set associated with the distribution line monitoring data characters selected in the third classification process and is associated with the distribution line monitoring data to be analyzed, it is the evaluation result of the corresponding core description output by the distribution line equipment fault monitoring model. If the core description (X, Y) in the distribution line monitoring data to be analyzed does not belong to the core description of the set associated with the distribution line monitoring data characters selected in the third classification process and is associated with the distribution line monitoring data to be analyzed, it is 0. The present disclosure can target the determination value of the non-zero statistical sum and use the statistically determined value to update the current evaluation result of the corresponding core description (X, Y) in the distribution line monitoring data to be analyzed.

[0074] Furthermore, based on the process of the current evaluation results of the core descriptions of the distribution line monitoring data that need to be analyzed for the updates performed on the premise of the above-mentioned classification processing in the second and third executions, it can be known that on the premise of the non-first (the i-th time) execution of the classification processing such as the fourth or fifth time, the process of the current evaluation results of the core descriptions of the distribution line monitoring data that need to be analyzed for the updates performed is actually to integrate the evaluation results of each time. For example, for integration, the current evaluation results of the core descriptions of the distribution line monitoring data that need to be analyzed after the update are constituted. However, when the present disclosure selects the distribution line monitoring data characters for which the distribution line equipment fault monitoring model needs to be transmitted, the current evaluation results of the core descriptions of the distribution line monitoring data that need to be analyzed are the results of integrating the evaluation results of each previous time. For example, the results of integration for.

[0075] Step 230: On the premise that there is no unparsed minimum decoding specified value in the decoding percentage set or no distribution line monitoring data character can be selected from each distribution line monitoring data character, determine the distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed according to the evaluation results of the core descriptions in the distribution line monitoring data that needs to be analyzed based on the evaluation results of each core description in each distribution line monitoring data character; otherwise, return to the above step 200.

[0076] In a possible embodiment, on the premise that there is no unparsed minimum decoding specified value in the decoding percentage set, the present disclosure can determine the distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed according to the current evaluation results of all the core descriptions in the distribution line monitoring data that needs to be analyzed, that is, after the present disclosure integrates the distribution line equipment fault monitoring result and, the best percentage result is determined as the distribution line equipment fault monitoring result of the core description (X, Y) in the distribution line monitoring data that needs to be analyzed.

[0077] In a possible embodiment, on the premise that no distribution line monitoring data character can be selected from each distribution line monitoring data character, the present disclosure can determine the distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed according to the current evaluation results of all the core descriptions in the distribution line monitoring data that needs to be analyzed, that is, after the present disclosure integrates the distribution line equipment fault monitoring result and, the best percentage result is determined as the distribution line equipment fault monitoring result of the core description (X, Y) in the distribution line monitoring data that needs to be analyzed.

[0078] In a possible embodiment, when the present disclosure trains a distribution line equipment fault monitoring model, the parsed distribution line monitoring data examples generally include distribution line monitoring data examples with multiple analysis precisions, and the number of different analysis precisions is generally related to the number of decoding specified values in the decoding percentage set. For example, on the premise that the decoding percentage set includes three decoding specified values, the example dataset should at least include distribution line monitoring data examples with the analysis precisions bound by these three decoding specified values, and each distribution line monitoring data example has significant information. Generally, in the example dataset, the number of distribution line monitoring data examples with different analysis precisions is basically the same. By using the distribution line monitoring data examples with different analysis precisions in the example dataset to train the distribution line equipment fault monitoring model, it is beneficial to improve the accuracy and reliability of the evaluation results output by the distribution line equipment fault monitoring model for each transmitted distribution line monitoring data character, thereby facilitating the improvement of the confidence level of the distribution line equipment fault monitoring model in matching the distribution line monitoring data.

[0079] Based on the above premise, please refer to Figure 2 and a distribution line equipment fault monitoring device 200 based on photovoltaic new energy is provided, which is applied to a distribution line equipment fault monitoring system based on photovoltaic new energy. The device includes: A data classification module 210, configured to classify the distribution line monitoring data to be analyzed to obtain the classified distribution line monitoring data; A character monitoring module 220, configured to select at least one distribution line monitoring data character from the classified distribution line monitoring data; determine the distribution line monitoring data character to be classified from the at least one distribution line monitoring data character, wherein, on the premise of the first and non-first execution of the classification process, the number and analysis precision of the distribution line monitoring data characters to be classified determined successively are different; A result evaluation module 230, configured to, on the premise of the non-first execution of the classification process, determine the distribution line monitoring data character to be classified from the at least one distribution line monitoring data character according to the current description content of the core description of the distribution line monitoring data to be analyzed; obtain the evaluation result of the core description in the distribution line monitoring data character to be classified through the distribution line equipment fault monitoring model; A fault monitoring module 240, configured to determine the distribution line equipment fault monitoring result of the distribution line monitoring data to be analyzed according to the evaluation result of the core description in the distribution line monitoring data character to be classified.

[0080] Based on the above premise, please refer to Figure 3, which shows a fault monitoring system 100 for distribution line equipment based on photovoltaic new energy, including a processor 200 and a memory 300 that communicate with each other. The processor 200 is configured to read and execute a computer program from the memory 300 to implement the above method.

[0081] On the above premise, a computer-readable storage medium is also provided, on which the computer program stored realizes the above method when running.

[0082] In summary, based on the above solutions, the present disclosure selects distribution line monitoring data characters from the classified distribution line monitoring data, and transmits the distribution line equipment fault monitoring model, as much as possible avoiding transmitting all the selected distribution line monitoring data characters to the distribution line equipment fault monitoring model after each classification process, thereby being able to improve the problem of excessive workload of the distribution line equipment fault monitoring model. In this way, the efficiency of production equipment monitoring can be effectively improved. Therefore, the accuracy and efficiency of fault monitoring can be improved.

[0083] It should be understood that the above-described systems and their modules can be implemented in various ways. For example, in some embodiments, the systems and their modules can be implemented through 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 the memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above methods and systems can be implemented using computer-executable instructions and / or included in the processor control code. For example, such code is provided on 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. The systems and their modules of the present application can be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips and transistors, or programmable hardware devices such as field programmable gate arrays and programmable logic devices, but also by software implemented by various types of processors, or by a combination of the above hardware circuits and software (for example, firmware).

[0084] It should be noted that the beneficial effects that may be produced by different embodiments are different. In different embodiments, the beneficial effects that may be produced can be a combination of any one or several of the above, or any other beneficial effects that may be obtained.

[0085] 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 limitation to this application. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are proposed in this application, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this application.

[0086] Meanwhile, this application analyzes specific terms to describe the embodiments of this application. For example, "an embodiment", "one embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be appropriately combined.

[0087] In addition, those skilled in the art can understand that various aspects of this application can be illustrated and described by several patentable types or situations, including any new and useful processes, machines, products, or combinations of substances, or any new and useful improvements to them. Accordingly, various aspects of this application can be executed entirely by hardware, can be executed entirely by software (including firmware, resident software, microcode, etc.), or can be executed by a combination of hardware and software. The above hardware or software can all be referred to as "data blocks", "modules", "engines", "units", "components", or "systems". In addition, various aspects of this application may be embodied as a computer product located in one or more computer-readable media, and this product includes computer-readable program code.

[0088] A computer storage medium may contain a propagated data signal containing computer program code, such as on a baseband or determined as part of a carrier wave. This propagated signal may have various forms of manifestation, including electromagnetic form, optical form, etc., or a suitable combination of forms. A computer storage medium can be any computer-readable medium other than a computer-readable storage medium, and this medium can be connected to an instruction execution system, device, or equipment to realize communication, propagation, or transmission of a program for analysis. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0089] The computer program code required for the operations of each part of this 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. This program code can run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially 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., through the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0090] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers and letters, or the use of other names in this application are not used to limit the order of the processes and methods of this application. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on an existing server or mobile device.

[0091] Similarly, it should be noted that, in order to simplify the presentation of the disclosure of this application and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this application, sometimes multiple features are merged into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this application are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0092] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used in the description of embodiments are modified by the modifiers "about", "approximately", or "substantially" in some examples. Unless otherwise specified, "about", "approximately", or "substantially" indicate that the said numbers allow for adaptive variations. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may vary according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of the present application to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0093] For each patent, patent application, patent application publication, and other materials cited in the present application, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into the present application by reference. Except for the application history documents that are inconsistent with or conflict with the content of the present application, and except for the documents that limit the broadest scope of the claims of the present application (currently or subsequently appended to the present application). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the attached materials of the present application and the content described in the present application, the descriptions, definitions, and / or uses of terms in the present application shall prevail.

[0094] Finally, it should be understood that the embodiments described in the present 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, by way of example and not limitation, alternative configurations of the embodiments of the present application 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.

[0095] The above are only the 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 modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for monitoring faults in distribution line equipment based on photovoltaic new energy, characterized in that: The method at least comprises: Classify and process the distribution line monitoring data that needs to be analyzed to obtain the classified distribution line monitoring data; Selecting at least one distribution line monitoring data character from the distribution line monitoring data after the classification process; determining the distribution line monitoring data character to be classified from the at least one distribution line monitoring data character, wherein the number and analysis accuracy of the distribution line monitoring data characters to be classified determined sequentially on the premise of performing the classification process for the first time and the non-first time are different; On the premise that the classification process is not performed for the first time, the distribution line monitoring data characters that need to be classified are determined from the at least one distribution line monitoring data character according to the current description content of the core description of the distribution line monitoring data that needs to be analyzed; the evaluation result of the core description in the distribution line monitoring data characters that need to be classified is obtained through the distribution line equipment fault monitoring model; The distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed is determined according to the evaluation result of the core description in the character of the distribution line monitoring data that needs to be classified.

2. The method according to claim 1, characterized in that: The classification processing of the distribution line monitoring data to be analyzed includes: The distribution line monitoring data to be analyzed is classified and processed according to the decoding specified values ​​that have not been parsed in the decoding percentage set.

3. The method according to claim 2, characterized in that The step of determining the distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed based on the evaluation result of the core description in the distribution line monitoring data characters that need to be classified includes: Based on the fact that there is no unparsed decoding specified value in the decoding percentage set or it is determined that there is no distribution line monitoring data character that needs to be classified in at least one distribution line monitoring data character, the distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed is determined based on the evaluation result of the core description in the distribution line monitoring data character that needs to be classified.

4. The method according to claim 2, characterized in that: The decoding percentage set includes: at least two different decoding specified values, and the smaller decoding specified value is parsed first relative to the larger decoding specified value.

5. The method according to any one of claims 1 to 4, characterized in that The determining of the distribution line monitoring data characters that need to be classified from the at least one distribution line monitoring data character comprises: determining all the distribution line monitoring data characters as the distribution line monitoring data characters that need to be classified on the premise of performing the classification process for the first time; Wherein, the determination of the distribution line monitoring data characters that need to be classified from the at least one distribution line monitoring data character includes: on the premise that the classification processing is not performed for the first time, the number of distribution line monitoring data characters that need to be classified is less than or equal to the number of currently selected distribution line monitoring data characters, and / or, the data analysis accuracy of the distribution line monitoring data that needs to be analyzed after the current classification processing is greater than the data analysis accuracy after the last classification processing.

6. The method according to claim 1, characterized in that The step of determining the power distribution line monitoring data character that needs to be classified from the at least one power distribution line monitoring data character according to the current description content of the core description of the power distribution line monitoring data that needs to be analyzed comprises: Determining the current description content of each core description according to the current evaluation result of each core description in the multiple core descriptions included in the distribution line monitoring data to be analyzed; Counting the current description content of the core description in the distribution line monitoring data set that needs to be analyzed and bound to the distribution line monitoring data character to achieve the number of core descriptions of the preset description content; Determining the power distribution line monitoring data characters whose number of core descriptions realizing the preset description content does not meet the preset requirements as power distribution line monitoring data characters that need to be classified; The step of determining the distribution line monitoring data characters whose number of core descriptions realizing the preset description content does not meet the preset requirements as the distribution line monitoring data characters that need to be classified includes: For the distribution line monitoring data character, on the premise that the percentage result of the number of core descriptions of the preset description content and the number of all core descriptions in the distribution line monitoring data set that needs to be analyzed and is bound to the distribution line monitoring data character is less than the preset percentage result, the distribution line monitoring data character is determined as the distribution line monitoring data character that needs to be classified; The step of obtaining the current evaluation results of each core description of the distribution line monitoring data to be analyzed includes: On the premise of executing the classification processing for the first time, the evaluation results of each core description in all the distribution line monitoring data characters that need to be classified output by the distribution line equipment fault monitoring model are associated with the distribution line monitoring data that need to be analyzed, and the evaluation results of each core description of the distribution line monitoring data that need to be analyzed are obtained; wherein, the evaluation results of each core description of the distribution line monitoring data that need to be analyzed are determined as the current evaluation results of each core description of the distribution line monitoring data that need to be analyzed.

7. The method according to claim 6, characterized in that The step of obtaining the current evaluation results of each core description of the distribution line monitoring data that needs to be analyzed includes: on the premise that the classification processing is not performed for the first time, associating the evaluation results of each core description in all the distribution line monitoring data characters that need to be classified output by the distribution line equipment fault monitoring model to the distribution line monitoring data that needs to be analyzed, and obtaining the evaluation results of multiple core descriptions of the distribution line monitoring data that needs to be analyzed; updating the current evaluation results of the corresponding core descriptions of the distribution line monitoring data that needs to be analyzed based on the evaluation results of the multiple core descriptions of the distribution line monitoring data that needs to be analyzed obtained this time.

8. The method according to claim 7, characterized in that The updating of the current evaluation results of the corresponding core descriptions of the distribution line monitoring data to be analyzed according to the evaluation results of the multiple core descriptions of the distribution line monitoring data to be analyzed acquired this time includes: Counting the evaluation results of multiple core descriptions of the distribution line monitoring data that need to be analyzed and the determination values ​​of the current evaluation results of the corresponding core descriptions in the distribution line monitoring data that need to be analyzed; Using the statistically determined values, the current evaluation results of the corresponding core descriptions in the distribution line monitoring data to be analyzed are updated; Wherein, determining the distribution line equipment fault monitoring result of the distribution line monitoring data that needs to be analyzed according to the evaluation result of the core description in the distribution line monitoring data characters that need to be classified includes: On the premise of one of the core descriptions in the distribution line monitoring data that needs to be analyzed, determine the best percentage result among the percentage results of each type in the current evaluation result of the core description, and determine the best percentage result and the type bound to the best percentage result as the distribution line equipment fault monitoring result of the core description.

9. The method according to any one of claims 2 to 4, characterized in that The analysis accuracy of the distribution line monitoring data examples used to train the distribution line equipment fault monitoring model includes: classifying the distribution line monitoring data in turn according to each decoding specified value in the decoding percentage set, and obtaining the analysis accuracy of each distribution line monitoring data.

10. A distribution line equipment fault monitoring system based on photovoltaic new energy, 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