Medium-voltage special power distribution station constant value intelligent management method and related device

Abstract

The invention provides a medium-voltage special power distribution station constant value intelligent management method and a related device, and belongs to the technical field of distribution network automation equipment constant value management. Whether a fixed value needs to be set or not is determined according to a preset condition, namely, a power distribution station switch is a circuit breaker switch and assets belong to customer assets. The method comprises the following steps: for a power distribution station needing setting a fixed value, acquiring data information and a work order uploaded by online application fixed value auditing of a power user, automatically and primarily auditing application fixed value data according to a preset algorithm, rechecking a primary auditing result in combination with the information, and inputting the fixed value data by the user after the auditing is passed. And then obtaining execution confirmation data, and completing user data archiving. Whether a set value is set or not is judged according to a circuit breaker switch and customer asset attributes, and whole-process management from application to archiving is achieved; the intelligent level and the process level of constant value management are improved, the auditing efficiency and accuracy are improved, safe and stable operation of a power grid is guaranteed, and the problems existing in a traditional management mode are effectively solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of fixed value management of distribution network automation equipment, and in particular relates to a fixed value intelligent management method for a medium-voltage dedicated distribution station and a related device. Background Art

[0002] With the advancement of distribution network automation construction, the management of automatic equipment setting values ​​is becoming increasingly critical to the stable operation of the power grid. Medium-voltage distribution stations are divided into medium-voltage dedicated and public distribution stations according to asset ownership and operation and maintenance entities. Public distribution stations are uniformly planned, constructed, operated and maintained by power grid companies, and the switch relay setting values ​​are also uniformly managed. Medium-voltage dedicated distribution stations are invested, constructed, operated and maintained by electricity users, and the switch relay setting values ​​are calculated and set by themselves. Because they are located at the end of the power grid line, the rationality of construction, operation and setting values ​​will affect the stability of the power grid, so the power grid company needs to conduct pre-power delivery acceptance and daily inspections, and the setting values ​​must be reviewed and approved. When the equipment changes, the setting values ​​also need to be adjusted. However, there is currently a lack of effective full life cycle management solutions for the setting values ​​of medium-voltage dedicated distribution stations.

[0003] At present, there are still some problems in the fixed value management of medium-voltage special distribution stations. The application review adopts traditional paper filling and manual review, which is inefficient and prone to errors. Paper materials are also easy to lose, and it is inconvenient to save and query. In terms of equipment change management, user change business and fixed value application review belong to different business lines and systems. After the equipment is changed, there are often omissions in application or late application for fixed value review, resulting in a mismatch between the fixed value and the equipment change. In daily inspections, there is a lack of real-time linkage between electricity inspection personnel and power grid company fixed value management personnel, making it difficult to discover and deal with problems in a timely manner. At the same time, the matching degree between the fixed value and the equipment lacks intuitive and visual presentation, which brings difficulties to analysis and statistics, affecting the security of the power grid. Summary of the invention

[0004] In view of this, the present invention aims to provide a method and related devices for intelligent management of set values ​​of medium-voltage dedicated distribution stations, which systematically manage the set values ​​of switches and relays in medium-voltage dedicated distribution stations from application review, equipment changes, daily inspections, and matching between set values ​​and current equipment throughout the entire life cycle, thereby improving work efficiency and ensuring safe and reliable operation of the power grid.

[0005] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0006] In a first aspect, the present invention provides a method for intelligent management of medium voltage dedicated distribution station settings, comprising the following steps:

[0007] Confirm whether the medium voltage dedicated distribution station needs to set a fixed value according to the preset confirmation conditions; the confirmation conditions are that the medium voltage dedicated distribution station switch is a circuit breaker switch and the asset attribute is a customer asset;

[0008] For medium-voltage special distribution stations that need to set fixed values, obtain the data uploaded by power users who apply for fixed value review online;

[0009] Obtain the work order submitted by the power user for online application for fixed value review, and automatically conduct preliminary review of the fixed value data applied for review according to the preset algorithm;

[0010] Combine data and materials to review the automatic preliminary review results so that power users can input fixed value data based on the reviewed results;

[0011] Obtain execution confirmation information for fixed value data input and archive all information of power users.

[0012] Furthermore, it also includes fixed value change and account cancellation management, which includes:

[0013] According to the relevant power business changes initiated by the power users, the relevant original data are modified using the fixed value change process and the fixed value is changed based on the modified data, and all changes are recorded in the change log;

[0014] The account cancellation business process is used to complete the account cancellation business for electricity users and terminate the user files.

[0015] Furthermore, the data and information uploaded by the power user for online application for fixed value review include:

[0016] Basic information of the user, transformer capacity, three-phase and zero-sequence current transformer ratios of each switch, various fixed value data that need to be reviewed, and materials for manual review and archiving records;

[0017] The materials used for manual review and archiving include 10kV primary wiring diagram, protection equipment principle and manual, switch cabinet relay protection test report, design manual, power approval document and motor parameters.

[0018] Furthermore, the various fixed value data applied for review are automatically reviewed according to the preset algorithm, including:

[0019] Calculate the primary side rated current based on the transformer capacity reported by the user , the calculation formula is ,in is the transformer capacity, is the high voltage side line voltage;

[0020] Determine the value or value range of each primary current setting as follows:

[0021] Instantaneous quick-break current, the value range is determined by 8 times the rated current of the primary side, and the delay is 0s;

[0022] Time-limited quick-break current: when the user's transformer capacity is less than 4000KVA, it is set at twice the rated current of the primary side, with a delay of 0.3s; when the user's transformer capacity exceeds 4000KVA, the time-limited quick-break current limit is 720A, with a delay of 0.15s;

[0023] The value range of inverse time overcurrent protection is 1.2-1.3 times the rated current, the limit is 480A, and the relationship coefficient between the action time and current of inverse time overcurrent protection is K=0.1;

[0024] Zero sequence overcurrent is 20A, delay is 0.1s;

[0025] According to the transformation ratio of the three-phase and zero-sequence current transformers of each switch reported by the user, divide the primary current setting value by the transformation ratio value to obtain the secondary current setting value;

[0026] Determine whether the various fixed value data filled in by the user are within the corresponding value range. If all meet the requirements, the initial review will be passed and an electronic fixed value sheet will be generated. If there are any non-compliance, the non-compliant items and their basis will be output.

[0027] Furthermore, after the automatic preliminary review is passed, it also includes automatic verification. The automatic verification process includes:

[0028] Use OCR optical character recognition technology to extract text information from the data that has passed the automatic preliminary review and perform post-processing to obtain the OCR original text;

[0029] Clean the acquired OCR original text;

[0030] Determine the document type of the processed OCR original text;

[0031] If it is a structured document, a rule / template matching method is used to process it, and first text information arranged according to a preset structure is obtained;

[0032] If it is an unstructured document, it is processed by NLP semantic analysis to obtain the second text information arranged according to the preset causal relationship;

[0033] Performing logic verification and error correction on the first text information and / or the second text information to obtain text information arranged according to a logical structure;

[0034] The data to be verified is extracted from the text information arranged in a logical structure and automatically verified to check the consistency between the information filled in by the user when submitting the work order and the data uploaded by the user.

[0035] Furthermore, it also includes a fixed value abnormal condition mark, specifically:

[0036] When the electricity inspector finds that the power user's relay protection device is abnormal and the set value cannot play a normal protective role, he / she can upload photos of the on-site situation through the mobile terminal and mark the user's abnormal setting condition.

[0037] Furthermore, it also includes visual monitoring, alarming and statistical analysis, specifically:

[0038] On the GIS map, according to the status of the fixed value review and the business change work order, red / yellow / green warning lights are used to mark the medium-voltage dedicated distribution station, representing the alarm of the fixed value not set / the alarm of the fixed value mismatch / the fixed value match respectively; according to the daily inspection results, the abnormal / normal status is marked with red / green warning lights;

[0039] On the 10kV single-line diagram, the status of the medium-voltage dedicated substation is marked with the same red / yellow / green warning lights as on the GIS map, which intuitively displays the substation setting status;

[0040] Perform classified statistical analysis on medium-voltage dedicated distribution stations in different states and generate an exportable list; send the alarm information corresponding to the red and yellow warning lights to the corresponding regional account managers in the form of text messages every day until the alarm is lifted; the list can export all medium-voltage dedicated distribution station information and show whether setting values ​​are required and the corresponding warning light status.

[0041] In a second aspect, the present invention provides a medium voltage dedicated distribution station setting intelligent management device, comprising:

[0042] The initial judgment module is used to confirm whether the medium-voltage dedicated distribution station needs to set a fixed value according to a preset confirmation condition; the confirmation condition is that the medium-voltage dedicated distribution station switch is a circuit breaker switch and the asset attribute is a customer asset;

[0043] The data acquisition module is used to obtain the data uploaded by the power user who applies for the fixed value review online for the medium voltage special distribution station that needs to set the fixed value;

[0044] The automatic preliminary review module is used to obtain the work orders submitted by power users for online application for fixed value review, and automatically conduct preliminary review of various fixed value data applied for review according to the preset algorithm;

[0045] The manual review module is used to review the automatic preliminary review results in combination with data materials, so that power users can input fixed value data based on the reviewed results;

[0046] The execution archiving module is used to obtain the execution confirmation information of the fixed value data input and archive the relevant information of the power users.

[0047] In a third aspect, the present invention provides a computer device, the device comprising a processor and a memory:

[0048] The memory is used to store the computer program and send the instructions of the computer program to the processor;

[0049] The processor executes a method for intelligent management of medium-voltage dedicated distribution station settings according to the instructions of the computer program as described in the first aspect.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for intelligent management of medium-voltage dedicated distribution station settings as in the first aspect.

[0051] In summary, the present invention provides a method and related device for intelligent management of fixed values ​​of medium-voltage special distribution stations, which confirms whether the medium-voltage special distribution station needs to set a fixed value according to a preset confirmation condition; the confirmation condition is that the switch of the medium-voltage special distribution station is a circuit breaker switch and the asset attribute is a customer asset; for the medium-voltage special distribution station that needs to set a fixed value, obtain the data uploaded by the power user for online application for fixed value review; obtain the work order submitted by the power user for online application for fixed value review, and automatically conduct a preliminary review of the various fixed value data applied for review according to the preset algorithm; review the automatic preliminary review results in combination with the data, so that the power user can input the fixed value data according to the result of the review; obtain the execution confirmation information of the fixed value data input, and archive the relevant information of the power user. The present invention determines whether to set a value based on the circuit breaker switch and the customer asset attribute, and realizes the whole process management from application to archiving; it not only improves the intelligence and process level of fixed value management, improves the review efficiency and accuracy, but also ensures the safe and stable operation of the power grid, and effectively solves the problems existing in the traditional management method. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A flow chart of a method for intelligent management of medium voltage dedicated distribution station settings provided by an embodiment of the present invention;

[0054] Figure 2 A block diagram of a medium voltage dedicated distribution station setting intelligent management device provided by an embodiment of the present invention;

[0055] Figure 3 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] See also Figure 1 The embodiment of the present invention provides a method for intelligent management of medium voltage dedicated distribution station settings, comprising the following steps:

[0058] S1: Confirm whether the medium voltage dedicated distribution station needs to set a fixed value according to the preset confirmation conditions; the confirmation conditions are that the medium voltage dedicated distribution station switch is a circuit breaker switch and the asset attribute is a customer asset.

[0059] It should be noted that medium-voltage dedicated substations are substations funded, constructed, and operated by electricity users, and are the assets of electricity users. They need to be constructed and operated in accordance with relevant national and industry standards for electricity, and the power grid company needs to regularly check their electricity usage. In contrast, medium-voltage public substations are substations funded, constructed, and operated by power grid companies, and are the assets of the power grid. The power grid company will carry out unified planning, construction, and operation and maintenance.

[0060] This step determines the switch type and asset attribute of the medium-voltage dedicated distribution station. Only when the switch is a circuit breaker switch and the asset attribute is a customer asset, it is determined that the distribution station needs to set a fixed value. This can screen out the medium-voltage dedicated distribution stations that really need to set fixed values, avoid subsequent operations on unnecessary distribution stations, and improve the pertinence and efficiency of management.

[0061] S2: For medium-voltage dedicated distribution substations that need to set fixed values, obtain the data uploaded by power users who apply online for fixed value review.

[0062] It should be noted that data and information refer to the information related to the fixed value review uploaded by the electricity user during the application process, which may include the electrical drawings of the distribution station, equipment parameters, power load information, etc. These materials are important bases for subsequent reviews.

[0063] This step obtains the data and information uploaded by the electricity users from the online application platform to provide basic data support for subsequent fixed value audits.

[0064] S3: Obtain the work order submitted by the power user for online application for fixed value review, and automatically conduct a preliminary review of the fixed value data applied for review according to the preset algorithm.

[0065] It should be noted that this step calculates and judges the set value data in the work order according to the preset algorithm. The algorithm will analyze each set value data based on the professional knowledge and operation requirements of the power system, such as checking whether the set value is within the range allowed by the equipment and whether it matches the upper and lower level protection set values.

[0066] Through automated preliminary review, we can quickly screen out value applications that obviously do not meet the requirements, improve review efficiency, reduce the workload of manual review, and at the same time ensure the objectivity and accuracy of the preliminary review.

[0067] S4: Review the automatic preliminary review results in combination with data information so that power users can input fixed value data based on the reviewed results.

[0068] It should be noted that this step will conduct a detailed comparison and analysis of the automatic preliminary review results with the data uploaded by the power users, taking into account various factors, such as the actual operating environment of the equipment, the user's special electricity needs, etc., to determine whether the preliminary review results are correct.

[0069] S5: Obtain the execution confirmation information of the fixed value data input and archive all the information of the power users.

[0070] It should be noted that execution confirmation information refers to the relevant information submitted by the power user to confirm the execution after entering the fixed value data, such as operation records, confirmation signatures, etc., which are used to prove that the fixed value data has been correctly entered according to the audit results. Archiving processing is to organize and store the relevant information of the power user (including data uploaded at the time of application, work orders, audit results, execution confirmation information, etc.) for subsequent query and management.

[0071] This step obtains execution confirmation information to confirm that the fixed value data has been correctly entered, and then stores the relevant information in the entire fixed value management process electronically according to certain archive management rules. This ensures that the fixed value setting operation is effectively confirmed on the one hand, and archives the information of the entire process on the other hand, which is convenient for future query, statistics and analysis, and provides data support for the operation, maintenance and management of the power system.

[0072] The management method provided in this embodiment determines the objects that need to set fixed values ​​based on the judgment of the characteristics of medium-voltage dedicated distribution stations. Relevant information and work orders are obtained through online applications from power users, and the fixed value data is automatically preliminarily reviewed using a preset algorithm. The data is then reviewed in combination to ensure the accuracy of the audit results, and finally the data is archived after the fixed value data input is confirmed. This method automatically screens the distribution stations that need to set fixed values ​​by judging the attributes of circuit breaker switches and customer assets, which greatly improves the accuracy and efficiency of management compared to the traditional comprehensive review method. The preset algorithm is used to automatically preliminarily review the fixed value data, reducing the workload and subjectivity of manual review, improving the efficiency and accuracy of the review, and at the same time using professional algorithms to ensure that the audit results meet the operating requirements of the power system.

[0073] In one embodiment, it also includes fixed value change and account cancellation management, and the fixed value change and account cancellation management include:

[0074] According to the relevant power business changes initiated by the power users, the relevant original data are modified using the fixed value change process and the fixed value is changed based on the modified data, and all changes are recorded in the change log;

[0075] The account cancellation business process is used to complete the account cancellation business for electricity users and terminate the user files.

[0076] It should be noted that in the actual operation of medium-voltage dedicated distribution stations, business changes of power users, such as changes in transformer capacity, replacement of switchgear, and replacement of relay protection devices, are common, and these changes will inevitably lead to the need to update the fixed value data. The fixed value change process is to use the fixed value change function of the system to accurately modify the fixed value in the power control system when the power user proposes a business change requirement. In addition, all changes will be recorded in detail to form a change log for subsequent review and audit at any time.

[0077] The account cancellation business process is that after the user submits an account cancellation application and the system receives the application, it will conduct a comprehensive termination process on the user's file, officially update the user status to "account cancelled", and mark the cancellation date in detail. In addition, the user's past file information is properly sealed for possible subsequent inquiries and statistical analysis. The account cancellation business process enables the entire management process to fully cover the entire process of the distribution station from activation, operation to deactivation, ensuring the standardization and integrity of power management work.

[0078] In one embodiment, the data and information uploaded by the power user for online application for fixed value review include:

[0079] Basic information of the user, transformer capacity, transformation ratio of three-phase and zero-sequence current transformers (CT) of each switch, various fixed value data that need to be reviewed, and materials for manual review and archiving records;

[0080] The materials used for manual review and archiving include 10kV primary wiring diagram, protection equipment principle and manual, switch cabinet relay protection test report, design manual, power approval document and motor parameters.

[0081] It should be noted that this embodiment describes in detail the data that users need to upload when applying. These data are the basis for subsequent fixed value review. The basic information of users helps to accurately identify and manage users; equipment parameters such as transformer capacity and CT ratio are the key basis for calculating and judging the rationality of fixed values; 10kV primary wiring diagram, protection equipment principle and instructions and other materials provide comprehensive technical information for manual review, ensuring that auditors can have an in-depth understanding of the actual situation of the distribution station and make accurate audit judgments, making the entire application review process more rigorous and scientific. The uploaded materials are as follows:

[0082] (1) 10kV primary wiring diagram;

[0083] (2) Principles and instructions of protection equipment;

[0084] (3) Switchgear relay protection test report;

[0085] (4) Design specifications;

[0086] (5) Electricity use approval documents;

[0087] (6) If a medium voltage dedicated distribution station is equipped with a large motor, the motor rated current, starting current multiple, and maximum starting time must be submitted.

[0088] In one embodiment, each set value data for application review is automatically reviewed according to a preset algorithm, specifically including:

[0089] (1) Calculate the primary side rated current based on the transformer capacity reported by the user , the calculation formula is ,in is the transformer capacity, is the high voltage side line voltage;

[0090] (2) Instantaneous quick-break current, the value range is determined according to 8 times the rated current, and the delay is 0s;

[0091] (3) Time-limited quick-break current: when the user's transformer capacity is less than 4000KVA, the overcurrent protection stage II (i.e. time-limited quick-break current) is set at 2 times the rated current, with a delay of 0.3s; when the user's transformer capacity exceeds 4000KVA, the time-limited quick-break limit is 720A, with a delay of 0.15s;

[0092] (4) The value range of inverse time overcurrent protection is 1.2-1.3 times the rated current, the limit is 480A, and the relationship coefficient between the action time of inverse time overcurrent protection and the current is K=0.1;

[0093] (5) Zero-sequence overcurrent is 20A, delay is 0.1s;

[0094] (6) Based on the transformation ratio values ​​of the three-phase and zero-sequence current transformers of each switch reported by the user, divide the primary current constants, i.e., instantaneous quick-break current, time-limited quick-break current, inverse time overcurrent and zero-sequence overcurrent, by the transformation ratio value to obtain the secondary side value;

[0095] (7) Determine whether the various fixed value data filled in by the user are within the above range. If all meet the requirements, the initial review will be passed and an electronic fixed value sheet will be generated. If there are any non-compliance, the non-compliant items and their basis will be output.

[0096] It should be noted that automatic preliminary review is a key link in the entire review process. This link uses a preset algorithm to quickly screen and judge the fixed value data reported by the user. By calculating the rated current according to the transformer capacity and setting the value range and calculation method of various current fixed values ​​based on this, it is possible to efficiently judge whether the data reported by the user is reasonable. This automated preliminary review method not only improves the review efficiency, but also reduces the subjective errors that may occur in manual review, providing a standardized basis for subsequent manual review, making the entire review process more efficient and accurate.

[0097] In one embodiment, after the automatic preliminary review is passed, automatic verification is also included. The process of automatic verification includes:

[0098] (1) Use OCR optical character recognition technology to extract text information from the data that has passed the automatic preliminary review and perform post-processing to obtain the OCR original text.

[0099] It should be noted that this step uses the drawings, test reports and other technical materials uploaded by users, as well as process materials such as power approval (pdf format or doc format) as data sources. Using OCR (Optical Character Recognition) technology, through a series of image preprocessing technologies (denoising and enhancement, such as using Gaussian filtering and histogram equalization to eliminate image blur, shadows, and folds; binarization, using Otsu (Otsu's method) algorithm to convert color / grayscale images into black and white images to highlight the text area;Geometric correction, adjusting tilted and distorted text through affine transformation and perspective transformation), text detection technology (traditional methods are based on edge detection such as Canny (Canny Edge Detector) operator or connected region analysis such as MSER (Maximally Stable Extremal Regions), deep learning methods use target detection models such as Faster R-CNN (Faster Region-based Convolutional Neural Network), YOLO to locate text areas, or dedicated text detectors such as EAST (Efficient and Accurate Scene Text, efficient and accurate scene text detection algorithm), CRAFT (Character Region Awareness For Text Detection, character region perception algorithm for text detection)), character recognition technology (traditional OCR through feature extraction such as HOG (Histogram of Oriented Gradients, directional gradient histogram), SIFT (Scale-Invariant Feature Transform) combined with classifiers such as SVM (Support Vector Machine, support vector machine), random forest, deep learning models use CNN (Convolutional Neural CRNN (Convolutional Recurrent Neural Network) or Transformer architecture (such as TrOCR) of Convolutional Neural Network + RNN (Recurrent Neural Network) + CTC (Connectionist Temporal Classification) and post-processing optimization (using N-gram (N-gram) or BERT (Bidirectional Encoder Representations from Transformers) to correct recognition errors in language models, such as "1" is mistakenly recognized as "l", and format restoration retains the original text layout and table structure), extract information from electronic materials and form OCR original text. ;

[0100] (2) Clean the acquired OCR original text.

[0101] It should be noted that the acquired OCR original text is cleaned. On the one hand, noise filtering is performed, using regular expressions (such as [^a-zA-Z0 - 9\u4e00 - \u9fa5]) to match all characters except English letters, numbers and Chinese characters, which may usually be garbled or unnecessary special characters, and statistical outlier detection (such as deleting abnormal strings with length > 50); on the other hand, text reorganization is performed, using paragraph merging algorithms (judging paragraph boundaries through line spacing and indentation) and table restoration technology (combining OpenCV to detect table lines + Pandas DataFrame reconstruction) to improve the quality and standardization of the text and prepare for subsequent processing.

[0102] (3) Determine the document type of the processed OCR original text.

[0103] It should be noted that the original OCR text after cleaning enters the document type determination stage. This step determines whether the text belongs to a structured document or an unstructured document so that different processing methods can be used later. Structured documents have certain formats and rules, while unstructured documents are relatively free and disordered.

[0104] (4) If it is a structured document, it is processed using a rule / template matching method to obtain the first text information arranged according to a preset structure.

[0105] It should be noted that if it is judged to be a structured document, it is processed by rule / template matching. Taking transformer capacity extraction as an example, a specific template such as patterns = {"total_amount": r"(capacity| total)[:\s]*(\d+.\d {2})", "date": r"\d {4} transformer1\d {4} transformer2\d {4} transformer3"} is used for matching, where patterns is a template in the form of a Python dictionary, which is used to match specific key information in a structured document. In this scenario, the keys of the dictionary ("total_amount" and "date") represent the categories of information to be extracted, and the corresponding values ​​are regular expression patterns used to match the specific content of the corresponding categories in the document. In total_amount, r indicates that this is a raw string to prevent the backslash in the string from being escaped; (capacity| total) means matching any one of the two words "capacity" or "total", and | is the or operator in the regular expression. [:\s]* means matching zero or more colons or blank characters (\s means blank characters, including spaces, tabs, etc.). (\d+.\d{2}) means this is a capture group, \d+ means matching one or more numbers, \. means matching a decimal point, and \d {2} means matching two numbers. In date, it means matching four numbers, corresponding to transformers 1-4. The LayoutLM model is then used to simultaneously analyze the text content and layout position, and the logical structure of the document is reconstructed through OCR coordinate information, thereby obtaining the first text information arranged according to the preset structure, accurately extracting the key information in the structured document and arranging it according to the logical structure.

[0106] (5) If it is an unstructured document, it is processed using NLP (Natural Language Processing) semantic analysis to obtain second text information arranged according to a preset causal relationship.

[0107] It should be noted that if it is judged to be an unstructured document, it will be processed using NLP semantic analysis. Through entity recognition technology (such as Spacy (open source software library for natural language processing) / BERT-NER (Bidirectional Encoder Representations from Transformers-Named Entity Recognition) to extract the name of the distribution station, power supply line, capacity, etc.), relationship extraction technology (such as OpenIE (Open Information Extraction) algorithm to build "subject-verb-object" triples), topic modeling technology (such as LDA (Latent Dirichlet Allocation) algorithm to identify the distribution of core topics in documents), and based on dependency syntax analysis (such as using stanza library (Python library for natural language processing) to reconstruct the logical chain, for example, analyzing the causal relationship of "the capacity of the user's transformer is less than 4000KVA, and the overcurrent protection stage II (i.e., time-limited quick-break protection) is set to twice the rated current"), the second text information arranged according to the preset causal relationship is obtained, and the information in the unstructured document is converted into a text expression with a logical relationship.

[0108] (6) Performing logic verification and error correction on the first text information and / or the second text information to obtain text information arranged according to a logical structure.

[0109] It should be noted that the first text information (from the structured document processing result) and / or the second text information (from the unstructured document processing result) is logically verified and corrected. A verification and error correction mechanism is established, including rule verification (such as power parameter field verification value range, unit symbol consistency, test report logic check test date < submission date) and AI verification (such as using GPT-4 to generate candidate texts and comparing the credibility of OCR results), so as to obtain text information arranged according to the logical structure and ensure the accuracy and logic of the text information.

[0110] Error correction for rule verification includes:

[0111] Numerical range correction: When the value of the power parameter field exceeds the preset range, the system can automatically mark the abnormal data point. For some data with clear standard values ​​or derivable standard values, such as the standard rated capacity range of a certain type of power equipment, if the input value exceeds the range, a standard value suggestion pop-up window can be provided to prompt the user to make corrections; or based on other known data related to the data, a reasonable value can be estimated through a specific algorithm (such as linear regression, assuming that the value has a linear relationship with other data), and automatically replaced in the system, while recording the modification log for subsequent review.

[0112] Unit symbol consistency correction: If the unit symbol is found to be inconsistent, the system can identify the correct unit symbol specification (for example, the electric power unit should be unified as "kW" instead of "kw" or other incorrect variants), automatically replace the incorrect unit symbol with the correct form, and mark it in the text to inform the user that the unit symbol has been corrected here for user confirmation.

[0113] Logical error correction of test report date: If the test date is greater than the submission date, the system can prompt the user to check the accuracy of the date entry and provide a date selector for the user to reselect the correct test date; or record the abnormal situation in the system, and at the same time, infer a reasonable test date based on other relevant information (such as report number sequence, equipment usage records, etc.), and suggest the user to confirm the modification.

[0114] The error correction for the AI ​​verification part includes:

[0115] Use GPT-4 to generate candidate texts for error correction: When there are differences between the candidate texts generated by GPT-4 and the OCR results, the system can highlight the differences. For parts where the differences are small and clearly OCR recognition errors (such as obvious typos), the correct text generated by GPT-4 is directly used to replace them; for cases where the differences are large and difficult to judge directly, the OCR results and the candidate texts generated by GPT-4 are displayed to the user at the same time, with a credibility score (derived by the comparison algorithm), and the user manually selects the correct text content based on the actual situation, or provides a text editing box in the system for the user to modify it to the correct content. At the same time, the system can feed back these error correction processes and results to the AI ​​model to further optimize the subsequent verification and error correction effects.

[0116] (7) Extract the data to be verified from the text information arranged in a logical structure and perform automatic verification to verify the consistency between the information filled in by the user when submitting the work order and the data uploaded by the user.

[0117] It should be noted that the data to be verified are extracted from the text information arranged in a logical structure, such as the CT ratio, transformer capacity and other data extracted from the technical data. Then, automatic verification is performed to compare these data with the corresponding data in the user-filled information, and the consistency of the user-filled information and the user-uploaded information is verified, including whether the project name, substation, line, and medium-voltage distribution station on the power approval and other materials are consistent with those reported by the customer, whether they are stamped with the corresponding official seal and the audit official seal, and whether the data extracted from the technical data is consistent with the user's report, whether the test is qualified, etc. If not consistent, the preliminary review opinion is output and linked to the corresponding electronic data and the corresponding filled information.

[0118] This embodiment uses OCR technology to perform a series of automated processing from original text acquisition to logical verification and error correction on various formats of data uploaded by users, which can effectively remove data noise, correct errors, and ensure data accuracy. The automated process greatly improves audit efficiency and reduces manpower and time costs. The extracted data is compared with the information filled in by the user to ensure that the information is consistent between the data and avoid management problems. Combined with the preliminary review process, we can jointly ensure the accuracy, standardization and reliability of fixed value management and support the safe and stable operation of the distribution station.

[0119] In one embodiment, the execution confirmation information of the fixed value data input is obtained, specifically:

[0120] Electricity users take the approved fixed value sheet to the site to input the fixed value data, and are required to take on-site photos of the data entry execution as required and upload them to the backend via a mobile terminal to complete the execution confirmation.

[0121] It should be noted that this embodiment further clarifies the specific method of obtaining execution confirmation information. Users are required to take photos of the scene of execution data entry and upload them to the background. This measure ensures that the fixed value data is accurately executed on site and avoids the situation where the audit is passed but the fixed value is not set as required on site. At the same time, the on-site photos serve as the basis for execution confirmation, which facilitates subsequent management and traceability, so that the entire fixed value management process forms a complete closed loop from review to execution.

[0122] In one embodiment, it also includes a fixed value abnormal condition mark, specifically:

[0123] When the electricity inspector finds that the power user's relay protection device is abnormal and the set value cannot play a normal protective role, he / she can upload photos of the on-site situation through the mobile terminal and mark the user's abnormal setting condition.

[0124] It should be noted that the fixed value abnormal condition marking in this embodiment can timely discover problems such as abnormalities in the power user's relay protection device, and upload on-site photos through the mobile phone terminal for marking, which is convenient for management personnel to quickly understand abnormal situations.

[0125] Furthermore, it also includes visual monitoring, alarming and statistical analysis, specifically:

[0126] Based on GIS maps, red / yellow / green warning lights are marked on the map for medium-voltage dedicated distribution stations. According to the current approved fixed values, unapproved fixed values, and unapproved fixed value review situations, the business change work order extracted by the user in the business processing system is compared to mark the current medium-voltage dedicated distribution station fixed value status as [fixed value not set alarm] / [fixed value mismatch alarm] / [fixed value match], set red / yellow / green warning lights respectively, and indicate the status; according to the daily inspection results of the power inspection personnel, mark the current medium-voltage dedicated distribution station fixed value as [abnormal] / [normal], and set red / green warning lights respectively. Various situations are visually presented to the staff.

[0127] Based on the 10kV single-line diagram, red / yellow / green warning lights are marked on the drawing for the medium-voltage dedicated distribution station and the corresponding status is annotated. The classification marking and content are consistent with the GIS map-based classification method and content.

[0128] Perform classified statistical analysis on medium-voltage dedicated distribution stations in different states and generate an exportable list; send the alarm information corresponding to the red and yellow warning lights to the corresponding regional account managers in the form of text messages every day until the alarm is lifted; the list can export all medium-voltage dedicated distribution station information and show whether setting values ​​are required and the corresponding warning light status.

[0129] It should be noted that the visual monitoring alarm and statistical analysis of this embodiment uses GIS maps and 10kV single-line diagrams to identify different set value states with intuitive warning lights, so that managers can understand the operation of the distribution station at a glance. At the same time, the classification statistical analysis and alarm information sending functions help to discover potential problems in a timely manner, take corresponding measures, and ensure the safe and stable operation of the power grid.

[0130] Based on the same inventive concept, the embodiment of the present application also provides a medium-voltage dedicated distribution station fixed value intelligent management device for implementing the above-mentioned medium-voltage dedicated distribution station fixed value intelligent management method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiment of the medium-voltage dedicated distribution station fixed value intelligent management device provided below can refer to the above-mentioned limitations on the medium-voltage dedicated distribution station fixed value intelligent management method, and will not be repeated here.

[0131] See also Figure 2 The embodiment of the present invention further provides a medium voltage dedicated distribution station setting intelligent management device, comprising:

[0132] The initial judgment module is used to confirm whether the medium-voltage dedicated distribution station needs to set a fixed value according to a preset confirmation condition; the confirmation condition is that the medium-voltage dedicated distribution station switch is a circuit breaker switch and the asset attribute is a customer asset;

[0133] The data acquisition module is used to obtain the data uploaded by the power user who applies for the fixed value review online for the medium voltage special distribution station that needs to set the fixed value;

[0134] The automatic preliminary review module is used to obtain the work orders submitted by power users for online application for fixed value review, and automatically conduct preliminary review of various fixed value data applied for review according to the preset algorithm;

[0135] The manual review module is used to review the automatic preliminary review results in combination with data materials, so that power users can input fixed value data based on the reviewed results;

[0136] The execution archiving module is used to obtain the execution confirmation information of the fixed value data input and archive all the information of the power users.

[0137] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0138] Reference Figure 3 An embodiment of the present invention further provides a computer device, comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, a method for intelligent management of medium-voltage dedicated distribution station settings as described in any one of the above methods is implemented.

[0139] The computer device may be a desktop computer, a notebook, a PDA, a cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 3It is only an example of a computer device and does not constitute a limitation of the computer device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0140] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0141] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may include both an internal storage unit and an external storage device of the computer device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is to be output.

[0142] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a method for intelligent management of medium-voltage dedicated distribution station settings as described in any one of the above methods is implemented.

[0143] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0144] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0145] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0146] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0147] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent management of medium voltage dedicated distribution station settings, characterized in that: The steps include: Confirm whether the medium voltage dedicated distribution station needs to set a fixed value according to a preset confirmation condition; the confirmation condition is that the medium voltage dedicated distribution station switch is a circuit breaker switch and the asset attribute is a customer asset; For the medium voltage dedicated distribution station that needs to set a fixed value, obtain the data uploaded by the power user who applies for the fixed value review online; Obtain the work order submitted by the power user for online application for fixed value review, and automatically conduct preliminary review of the fixed value data applied for review according to the preset algorithm; Review the automatic preliminary review results in combination with the data and information so that the power user can input the fixed value data according to the reviewed results; Obtain execution confirmation information for fixed value data input and archive all information of power users.

2. The method for intelligent management of medium voltage dedicated distribution station settings according to claim 1 is characterized in that: It also includes fixed value change and account cancellation management, which includes: According to the relevant power business changes initiated by the power users, the relevant original data are modified using the fixed value change process and the fixed value is changed based on the modified data, and all changes are recorded in the change log; The account cancellation business process is used to complete the account cancellation business for electricity users and terminate the user files.

3. The method for intelligent management of medium voltage dedicated distribution station settings according to claim 1 is characterized in that: The data and information uploaded by power users for online application for fixed value review include: Basic information of the user, transformer capacity, three-phase and zero-sequence current transformer ratios of each switch, various fixed value data that need to be reviewed, and materials for manual review and archiving records; The materials used for manual review and archiving include 10kV primary wiring diagram, protection equipment principle and instructions, switch cabinet relay protection test report, design instructions, power approval documents and motor parameters.

4. The method for intelligent management of medium voltage dedicated distribution station settings according to claim 1 is characterized in that: The various fixed value data applied for review are automatically reviewed according to the preset algorithm, including: Calculate the primary side rated current based on the transformer capacity reported by the user , the calculation formula is ,in is the transformer capacity, is the high voltage side line voltage; Determine the value or value range of each primary current setting as follows: Instantaneous quick-break current, the value range is determined according to 8 times the rated current of the primary side, and the delay is 0s; Time-limited quick-break current: when the user's transformer capacity is less than 4000KVA, it is set at twice the rated current of the primary side, with a delay of 0.3s; when the user's transformer capacity exceeds 4000KVA, the time-limited quick-break current limit is 720A, with a delay of 0.15s; The value range of inverse time overcurrent protection is 1.2-1.3 times the rated current, the limit is 480A, and the relationship coefficient between the action time and current of inverse time overcurrent protection is K=0.1; Zero sequence overcurrent is 20A, delay is 0.1s; According to the transformation ratio of the three-phase and zero-sequence current transformers of each switch reported by the user, divide the primary current setting value by the transformation ratio value to obtain the secondary current setting value; Determine whether the various fixed value data filled in by the user are within the corresponding value range. If all meet the requirements, the initial review will be passed and an electronic fixed value sheet will be generated. If there are any non-compliance, the non-compliant items and their basis will be output.

5. The method for intelligent management of medium voltage dedicated distribution station settings according to claim 1 is characterized in that: After the automatic preliminary review is passed, the automatic verification is also included. The process of the automatic verification includes: Using OCR optical character recognition technology, extracting text information from the data after automatic preliminary review and performing post-processing to obtain OCR original text; Cleaning the acquired OCR original text; Determine the document type of the processed OCR original text; If it is a structured document, a rule / template matching method is used to process it, and first text information arranged according to a preset structure is obtained; If it is an unstructured document, it is processed by NLP semantic analysis to obtain the second text information arranged according to the preset causal relationship; Performing logic verification and error correction on the first text information and / or the second text information to obtain text information arranged according to a logical structure; The data to be verified is extracted from the text information arranged in a logical structure and automatically verified to check the consistency between the information filled in by the user when submitting the work order and the data uploaded by the user.

6. The method for intelligent management of medium voltage dedicated distribution station settings according to claim 1 is characterized in that: It also includes abnormal status flags, specifically: When the electricity inspector finds that the power user's relay protection device is abnormal and the set value cannot play a normal protective role, he / she can upload photos of the on-site situation through the mobile terminal and mark the user's abnormal setting condition.

7. The method for intelligent management of medium voltage dedicated distribution station settings according to claim 1 is characterized in that: It also includes visual monitoring, alarming and statistical analysis, specifically: On the GIS map, according to the status of the fixed value review and the business change work order, red / yellow / green warning lights are used to mark the medium-voltage dedicated distribution station, representing the alarm of the fixed value not set / the alarm of the fixed value mismatch / the fixed value match respectively; according to the daily inspection results, the abnormal / normal status is marked with red / green warning lights; On the 10kV single-line diagram, the status of the medium-voltage dedicated substation is marked with the same red / yellow / green warning lights as on the GIS map, which intuitively displays the substation setting status; Performing classified statistical analysis on the medium voltage dedicated distribution stations in different states and generating an exportable list; The alarm information corresponding to the red and yellow warning lights will be sent to the corresponding regional account manager in the form of text messages every day until the alarm is lifted; the list can export all medium-voltage dedicated distribution station information and display whether setting values ​​are required and the corresponding warning light status.

8. A medium voltage dedicated distribution station fixed value intelligent management device, characterized in that: include: An initial judgment module is used to confirm whether a fixed value needs to be set for a medium voltage dedicated distribution station according to a preset confirmation condition; The confirmation condition is that the medium voltage dedicated distribution station switch is a circuit breaker switch and the asset attribute is a customer asset; A data acquisition module is used to obtain data uploaded by power users who apply for fixed value review online for the medium voltage dedicated distribution station that needs to set fixed value; The automatic preliminary review module is used to obtain the work orders submitted by power users for online application for fixed value review, and automatically conduct preliminary review of various fixed value data applied for review according to the preset algorithm; A manual review module is used to review the automatic preliminary review results in combination with the data, so that the power user can input the fixed value data according to the reviewed results; The execution archiving module is used to obtain the execution confirmation information of the fixed value data input and archive all the information of the power users.

9. A computer device, characterized in that: The device comprises a processor and a memory: The memory is used to store a computer program and send instructions of the computer program to the processor; The processor executes a method for intelligent management of medium-voltage dedicated distribution station settings according to instructions of the computer program as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for intelligent management of medium-voltage dedicated distribution station settings is implemented as described in any one of claims 1-7.

Images