ICD model defect detection and repair method and system based on SCD file
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID ANHUI ELECTRIC POWER CO LTD
- Filing Date
- 2026-05-07
- Publication Date
- 2026-06-02
Smart Images
Figure CN122132569A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of SCD file defect detection technology, and specifically to a method and system for detecting and repairing defects in ICD models based on SCD files. Background Technology
[0002] During the power system infrastructure construction phase, the SCD file (Substation Configuration Description) is the core configuration file for information interaction and functional implementation of the secondary system in intelligent substations. It contains the instance configurations, data objects, communication parameters, and logical connection relationships of all IEDs (Intelligent Electronic Devices) in the entire substation. The manufacturer's ICD model (IED Capability Description), as the basic building block of the SCD file, can directly lead to problems such as incorrect virtual terminal connections and version inconsistencies in the SCD file, affecting the efficiency of substation infrastructure commissioning and the operational reliability of secondary equipment.
[0003] The manufacturer's ICD model is provided by the equipment manufacturer. Due to differences in the technical standards and secondary circuit design specifications of the equipment manufacturers, defects such as missing or incorrectly connected virtual terminals may appear in the manufacturer's ICD model. These defects are highly concealed and difficult to accurately identify using conventional manual inspection methods. They are often only discovered during the commissioning phase of the secondary equipment, when the primary equipment is switched on and tested. This leads to delays in problem investigation, restricts the overall efficiency of secondary circuit acceptance, and may even affect the overall commissioning progress of the power project due to the extended acceptance cycle, posing a significant challenge to the quality and efficiency of power system infrastructure construction.
[0004] In the process of realizing this invention, the inventors of this application discovered that the above-mentioned solutions in the prior art have the defects of lagging ICD model defect identification and low identification accuracy. Summary of the Invention
[0005] The purpose of this invention is to provide a method and system for detecting and repairing defects in ICD models based on SCD files. This method and system for detecting and repairing defects in ICD models based on SCD files has the function of improving the efficiency and accuracy of model defect identification.
[0006] To achieve the above objectives, embodiments of the present invention provide a method for defect detection and repair of ICD models based on SCD files, including: Import the SCD file and parse multiple elements and their attributes in the SCD file, wherein the element attributes include the device name; Construct a pre-trained model for each device type, and obtain the corresponding device type based on the device name and the pre-trained model. Obtaining the corresponding device type based on the device name and the pre-trained model includes: obtaining the device type corresponding to each device name according to formula (1). (1) in, For the first The device type of the device name. For preprocessing functions, This is a word segmentation function. For filtering functions, For mapping functions, The parameter value at which the conditional probability reaches its maximum. For the first The device name mentioned above. For the first Class of equipment types, For device name Corresponding device type The conditional probability, Numbered by integer; Based on the element attributes and the device type, obtain the manufacturer's ICD model and the set of virtual terminals of the manufacturer's ICD model; Obtain the set of secondary loops from the manufacturer's ICD model; Model defects are obtained based on the set of virtual terminals in the manufacturer's ICD model and the sets of virtual terminals on both sides of the secondary circuit set. The model defects are classified and archived to obtain a list of model defects; Obtain a list of causes for model defects based on the aforementioned list of model defects; Obtain a model defect repair plan based on the list of model defect causes, and execute the model defect repair plan.
[0007] Optionally, the element attributes may also include manufacturer, model, version, virtual terminal set, and secondary circuit set.
[0008] Optionally, building a pre-trained model for the device type includes: Define a rule base for device type identification; A pre-trained model for device types is constructed based on the device type identification rule base.
[0009] Optionally, obtaining the corresponding device type based on the device name and the pre-trained model further includes: The likelihood probability of the device name is obtained according to formula (2). (2) in, For a given number Class of equipment types When entering the device name The matching probability, The samples that contain keywords in the historical input of the pre-trained model. To and The corresponding confirmed standard equipment types, The historical set in the pre-trained model. For text similarity functions, For smoothing coefficients, For each type of device during the traversal, For circular subscripts, and Numbered by integer; The conditional probability of the device name is obtained according to formula (3). (3) in, The prior probability of the device type; The corresponding device type is obtained based on the conditional probability of the device name.
[0010] Optionally, the virtual terminal attributes in the virtual terminal set of the manufacturer's ICD model include virtual terminal type, virtual terminal description, and virtual terminal internal short address.
[0011] Optionally, obtaining the manufacturer's ICD model and the set of virtual terminals of the manufacturer's ICD model based on the element attributes and the device type includes: Preset the priority of virtual terminal type values; Obtain the internal short address of the same virtual terminal of the ICD model from the same manufacturer; Determine whether there are cases where the internal short address of the same virtual terminal in the same ICD model from the same manufacturer belongs to different virtual terminal types; If it is determined that the internal short address of the same virtual terminal in the same ICD model of the same manufacturer belongs to different virtual terminal types, multiple virtual terminal types corresponding to the internal short address of the virtual terminal are obtained. The virtual terminal type with the highest priority is obtained based on the multiple virtual terminal types and the value priority. The virtual terminal type with the highest priority is used as the unique virtual terminal type for the internal short address of the virtual terminal.
[0012] Optionally, model defects are obtained based on the set of virtual terminals in the manufacturer's ICD model and the sets of virtual terminals on both sides of the secondary circuit set, including: The first model defect set is obtained according to formula (4). (4) in, For the first model's defect set, This refers to the set of virtual terminals on both sides of the secondary circuit set. This is the set of virtual terminals for the manufacturer's ICD model; The second model defect set is obtained according to formula (5). (5) in, For the second model defect set, This refers to the set of input virtual terminals in the virtual terminal set of the manufacturer's ICD model. This refers to the set of output virtual terminals in the virtual terminal set of the manufacturer's ICD model.
[0013] Optionally, obtaining model defects based on the set of virtual terminals in the manufacturer's ICD model and the set of virtual terminals on both sides of the secondary circuit set further includes: Obtain the virtual terminals whose short internal addresses end with data attributes from the virtual terminal sets on both sides of the secondary circuit set; Determine whether there is a value loop in the virtual terminals whose short addresses end with data attributes in the virtual terminal sets on both sides of the secondary loop set; If it is determined that there is no value loop in the virtual terminal whose internal short address ends with the data attribute in the virtual terminal set on both sides of the secondary loop set, the corresponding manufacturer's ICD model is obtained, and a third model defect set is constructed.
[0014] Optionally, obtaining the list of causes of model defects based on the list of model defects includes: Determine whether the defect set of the first model is empty; If the first model defect set is not empty, it is determined that the virtual terminal definition is missing, the virtual terminal definition is incorrect, or the virtual terminal reference is incorrect. Determine whether the defect set of the second model is empty; If the second model defect set is not empty, it is determined that the manufacturer's ICD model has a virtual terminal reference error or a secondary circuit redundancy. Determine whether the defect set of the third model is empty; If the defect set of the third model is not empty, it is determined that the secondary loop of the manufacturer's ICD model is missing.
[0015] On the other hand, the present invention also provides an ICD model defect detection and repair system based on SCD files, comprising: The file parsing module is used to import and parse SCD files; The control module, connected to the file parsing module, is used to execute any of the ICD model defect detection and repair methods described above.
[0016] Through the above technical solution, the ICD model defect detection and repair method and system based on SCD files provided by this invention parses the imported SCD file into multiple elements and corresponding attributes, then constructs a pre-trained model. Based on the equipment name attribute of each element, the corresponding equipment type is obtained. Based on the element attributes and equipment type, the manufacturer's ICD model and the corresponding virtual terminal set and secondary circuit set can be obtained. Model defects are detected based on the virtual terminal set and the two-sided virtual terminal set in the secondary circuit set, thereby obtaining a list of model defect causes and corresponding model defect repair solutions. The manufacturer's ICD model can then be repaired based on these solutions. By parsing the attributes of elements in the SCD file to obtain the virtual terminal set of the manufacturer's ICD model and the two-sided virtual terminal set in the secondary circuit set, and then detecting model defects based on these virtual terminal sets and the two-sided virtual terminal set in the secondary circuit set, early detection of model defects can be achieved. This effectively improves the detection efficiency of ICD model defects and has high detection accuracy, thus shortening the on-site debugging time of secondary equipment in the SCD file and improving the efficiency and reliability of substation infrastructure debugging and operation.
[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0018] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the construction of a pre-trained model for a device type in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention. Figure 3 This is a flowchart illustrating the process of obtaining the device type in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 4 This is a flowchart of obtaining the virtual terminal type in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 5This is a flowchart of obtaining model defects in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 6 This is a flowchart of obtaining the cause of model defects in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention. Figure 7 This is a flowchart of virtual terminal matching in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the virtual terminal set of the manufacturer's ICD model in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention. Figure 9 This is a schematic diagram of the secondary loop of the manufacturer's ICD model in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention. Figure 10 This is a schematic diagram of a first model defect in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 11 This is a schematic diagram of a first model defect in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 12 This is a schematic diagram of a second model defect in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention; Figure 13 This is a schematic diagram of a third model defect in an ICD model defect detection and repair method based on SCD files according to an embodiment of the present invention. Detailed Implementation
[0019] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.
[0020] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0021] Figure 1This is a flowchart of a real-time ICD model defect detection and repair method based on SCD files according to the present invention. Figure 1 In this context, the ICD model defect detection and repair method may include: In step S1, the SCD file is imported and its multiple elements and attributes are parsed. Attributes include the device name. Specifically, element attributes may include device name, manufacturer, type, version, virtual terminal set, and secondary loop set. Specifically, the virtual terminal set may include an output virtual terminal set and an input virtual terminal set. The output virtual terminal set is obtained by parsing the FCDA element of the logical device node LD, and the input virtual terminal set is obtained by parsing elements under the logical node LN whose prefixes begin with GOIN or SVIN. Furthermore, the secondary loop set is obtained by parsing the Inputs element of the logical device node LD. This element is also... <ied>Elements, the SCD file includes multiple <ied>Element, each <ied>An element includes multiple attributes.
[0022] In step S2, a pre-trained model for device types is constructed, and the corresponding device type is obtained based on the device name and the pre-trained model. The device type can be extracted from the device name, and this may include defining a device type recognition rule base and establishing a pre-trained model for extracting device types based on the device name. Specifically, obtaining the corresponding device type based on the device name and the pre-trained model may include: According to formula (1), obtain the device type corresponding to each device name. (1) in, For the first Device Name / <ied>The device type of the element, For preprocessing functions, This is a word segmentation function. For filtering functions, For mapping functions, The parameter value at which the conditional probability is maximized, i.e. The device type corresponding to the maximum value , For the first Device name / keyword text, For the first Class of equipment types, For device name Corresponding device type The conditional probability, The number is an integer.
[0023] Furthermore, assuming For SCD files <ied>The collection of name attributes of an element Indicates the first indivual <ied>The name value of the element, which is the device name. This is a collection of equipment types, including protection devices, integrated protection and testing devices, measurement and control devices, merging units, intelligent terminals, and integrated intelligent systems. For the first Each device type. Furthermore, the preprocessing function... This may include the first indivual <ied>The `name` value of the element is preprocessed to filter out invalid characters unrelated to the device type, such as voltage level codes, interval numbers, and set numbers. This word segmentation function... After filtration Perform character segmentation, where the number of segments is less than or equal to 1. That is, less than the total number of characters after preprocessing, resulting in A set of characters. This filtering function... According to the naming rules for protection-related logical devices in the IEC 61850 engineering relay protection application model, for example, PROT represents protection device, MU represents merging unit, ST represents intelligent terminal, MST represents integrated intelligent device, MEAS represents measurement and control device, etc., the segmented character set is weighted and sorted, redundant and low-relevance characters are removed, and a set of keywords that can match the device type is selected. This mapping function... Mapping a set of keywords to a set of device types, for example. , , . Indicates the first indivual <ied>The name value of the element Mapped to the Device types The conditional probability, and .
[0024] In step S3, the manufacturer's ICD model and its virtual terminal set are obtained based on element attributes and device type. Specifically, this is based on the SCD file... <ied>The manufacturer, model, version, and equipment type of an element can be used to extract the manufacturer's ICD model. The unique identifier of the manufacturer's ICD model is: manufacturer, model, version, and equipment type. IEDs with the same manufacturer, model, version, and equipment type... <ied>The elements were extracted to be of the same manufacturer type. Furthermore, these IEDs / <ied>The union of the virtual terminal sets of the elements is taken as the virtual terminal set of the manufacturer's ICD model. Specifically, the virtual terminal attributes of the manufacturer's ICD model include: virtual terminal type (SV output / SV input / GOOSE output / GOOSE input), virtual terminal description, and internal short address of the virtual terminal, which can be further specified as follows: Figure 8 As shown.
[0025] In step S4, the set of secondary loops of the manufacturer's ICD model is obtained. Specifically, based on the IED element list of the manufacturer's ICD model obtained in step S3, the union of the secondary loop sets in this IED element list is extracted as the set of secondary loops for the manufacturer's ICD model. This set of secondary loops includes sets of virtual terminals on both sides, which can be specifically as follows: Figure 9 As shown.
[0026] In step S5, model defects are obtained based on the set of virtual terminals in the manufacturer's ICD model and the sets of virtual terminals on both sides of the secondary circuit. Specifically, after obtaining the set of virtual terminals and the secondary circuit in the manufacturer's ICD model, the set of virtual terminals can be compared with the sets of virtual terminals on both sides of the secondary circuit to determine the model defects in the manufacturer's ICD model.
[0027] In step S6, model defects are categorized and archived to obtain a list of model defects. Specifically, after identifying and obtaining different model defects, these defects can be summarized to obtain a list of model defects.
[0028] In step S7, a list of model defect causes is obtained based on the list of model defects. Each model defect is analyzed to identify its corresponding cause, and these causes are then summarized to obtain the list of model defect causes.
[0029] In step S8, a model defect repair plan is obtained based on the list of model defect causes, and then executed. Specifically, for each model defect cause in the list, a corresponding model defect repair plan is obtained, and the model defect is repaired by executing the plan accordingly. Furthermore, this repair plan supports manual review and confirmation, providing a self-checking basis for the manufacturer's subsequent ICD model creation. Specifically, the repair plan can be as follows: Figure 10-13 As shown.
[0030] In steps S1 to S8, the imported SCD file is first parsed to obtain multiple elements and their corresponding attributes. Then, a pre-trained model for the device type is constructed; the device type is obtained based on the device name in the element attributes. Multiple manufacturer ICD models are determined based on the consistency of the device type and other element attributes. The virtual terminals and secondary / both-side virtual terminals of each manufacturer's ICD model are summarized to obtain the virtual terminal set and secondary / both-side virtual terminal set for each manufacturer's ICD model. Diagnostic detection is performed on the virtual terminal set and the two-side virtual terminal set in the secondary circuit set of each manufacturer's ICD model to obtain the corresponding model defects. The model defects of each manufacturer's ICD model are classified to obtain a model defect list. Further analysis is performed on the model defect list to obtain the corresponding model defect causes and their corresponding lists. Finally, a model defect repair plan is obtained based on the model defect cause list and executed.
[0031] Traditional manufacturer ICD models often suffer from well-hidden defects such as missing or incorrect virtual terminals, making them difficult to identify accurately using conventional manual inspection methods. These defects are often only discovered during the secondary equipment commissioning phase, specifically during primary equipment switch-on testing. This delays in problem identification hinders the overall efficiency of secondary circuit acceptance and can even impact the overall commissioning schedule of power projects, posing a significant challenge to the quality and efficiency of power system infrastructure. In this embodiment of the invention, the attributes of elements in the SCD file are parsed to obtain the virtual terminal set of the manufacturer's ICD model and the sets of virtual terminals on both sides of the secondary circuit. Based on these virtual terminal sets and the sets of virtual terminals on both sides of the secondary circuit, model defect detection is achieved. This method enables early detection of model defects, effectively improving the detection efficiency of ICD model defects with high accuracy. It also shortens the on-site commissioning time for secondary equipment using the SCD file, improving the commissioning efficiency and operational reliability of substation infrastructure.
[0032] In this embodiment of the invention, when it is necessary to obtain the corresponding device type based on the device name, a pre-trained model of the device type can be constructed first. Specifically, the steps for constructing the pre-trained model of the device type can be as follows: Figure 2 As shown. Specifically, in Figure 2 The ICD model defect detection and repair scheme may also include: In step S20, a device type identification rule base is defined. This rule base can be obtained based on existing device type classifications.
[0033] In step S21, a pre-trained model for device types is constructed based on the device type identification rule base. This pre-trained model may include a preprocessing function. Word segmentation function Filtering functions and mapping functions The model can be trained based on a rule base for device type recognition, so that the device name can be directly input into the pre-trained model and the corresponding device type can be output.
[0034] In this embodiment of the invention, after the device name is input into the pre-trained model, the device name can be processed multiple times to obtain the corresponding device type. Specific steps can be as follows: Figure 3 As shown. Specifically, in Figure 3 Furthermore, the ICD model defect detection and repair method may also include: In step S22, the likelihood probability of the device name is obtained according to formula (2). (2) in, For a given number Class of equipment types When entering device name / keyword text The matching probability, For samples that contain keywords in the historical input of the pre-trained model, To and The corresponding confirmed standard device / equipment type, For the historical set in the pre-trained model, For text similarity functions, such as the cosine similarity function, etc. For smoothing coefficients, For each type of device during the traversal, For circular subscripts, and The identifier is an integer. Furthermore, For fixed terms, it represents the type of equipment being calculated, such as "protective device". For protection, molecules only accumulate similarity of this type; It iterates through all three categories, such as... To protect, For measurement and control, To ensure consistency between the test and the calculation, the denominator is the sum of the similarities of all three classes; that is, one for the current class and one for all classes. Specifically, assume the historical set in the pre-trained model is... ,and ,in, For set The total number of samples in the sample, Keywords for historical input The sample, To and The corresponding confirmed standard device type. Text similarity function. Used to measure the currently input keyword text Compared with historical samples The correlation, The value range of is [0, 1]. Let be... For set The middle belongs to the first Sample count of device type, i.e. .set up For smoothing coefficients, The value is 1. The value is set to 0.01 to avoid an abnormal value of 0 in probability calculations. Keywords The possible standard device types for mapping are: ,but When set When empty, .
[0035] In step S23, the conditional probability of the device name is obtained according to formula (3). (3) in, Enter keyword text Corresponding to the Conditional probability of device type. This represents the prior probability of the current device type. To iterate through the prior probabilities of each device type, specifically, based on the derivation of Bayes' theorem, the input keyword text is calculated. Corresponding to the The conditional probability of a device type can be calculated as shown in formula (3). When they are respectively protection devices, measurement and control devices, and integrated protection and measurement devices, the conditional probability is... The value is taken as follows. When the value is at its maximum The device type used for output.
[0036] In step S24, the corresponding device type is obtained based on the conditional probability of the device name. Specifically, the device type is obtained based on the maximum conditional probability of the device name. The output device type can be manually modified and confirmed. After confirmation, the keyword and the confirmed device type form a new sample and are added to the set. In this process, the set is automatically updated, and the updated set is used for probability calculation of subsequent device type extraction, thereby enabling the pre-trained model to continuously self-optimize based on actual application data.
[0037] In this embodiment of the invention, after obtaining the manufacturer's ICD model, the virtual terminals of the manufacturer's ICD model can be summarized to obtain the corresponding virtual terminal set. Specific steps can be as follows: Figure 4 As shown. Specifically, in Figure 4 In this context, the ICD model defect detection and repair method may include: In step S30, the value priority of the virtual terminal type is preset. This priority can be set according to the label position to which the virtual terminal is defined, such as LN > Inputs > FCDA.
[0038] In step S31, the internal short address of the same virtual terminal of the same ICD model from the same manufacturer is obtained. Specifically, if the internal short address of the same virtual terminal of the same ICD model from the same manufacturer belongs to different virtual terminal types in different IEDs, the internal short address of the same virtual terminal of the same ICD model from the same manufacturer can be determined first.
[0039] In step S32, it is determined whether there are cases where the internal short address of the same virtual terminal in the same ICD model from the same manufacturer belongs to different virtual terminal types. Specifically, for the same internal short address of the same virtual terminal in the same ICD model from the same manufacturer, its virtual terminal type can be determined first, and then it can be determined whether the virtual terminal types of the same internal short address are different. That is, different virtual terminals in the virtual terminal set of the manufacturer's ICD model may have the same internal short address, but different virtual terminal types.
[0040] In step S33, if it is determined that the internal short address of the same virtual terminal in the same ICD model from the same manufacturer belongs to different virtual terminal types, multiple virtual terminal types corresponding to the internal short address of the virtual terminal are obtained. For example, if the internal short address of the virtual terminal MUSV / LLNO.DelayTRtg is defined as an output virtual terminal in the FCDA of IL1101, and is used as an input virtual terminal in the Inputs loop of IL1102, then the virtual terminal types of the same internal short address of the virtual terminal are inconsistent, namely an output virtual terminal and an input virtual terminal.
[0041] In step S34, the virtual terminal type with the highest priority is obtained based on multiple virtual terminal types and value priority. Among them, for the two virtual terminal types with the same internal short address as the above virtual terminal, MUSV / LLNO.DelayTRtg can be added to the input virtual terminal set according to the value priority Inputs>FCDA.
[0042] In step S35, the virtual terminal type with the highest priority is selected as the only virtual terminal type for the short address inside the virtual terminal. Only virtual terminals of this type are retained in the virtual terminal set; other virtual terminal types are ignored.
[0043] In steps S30 to S35, the priority of virtual terminal type is first preset. Then, the internal short address of the same virtual terminal in the same ICD model from the same manufacturer is obtained, and the virtual terminal type of the internal short address is collected to determine whether the virtual terminal types of the same internal short address are the same. If the virtual terminal types of the same internal short address are different, the virtual terminal type with the highest priority can be obtained based on the priority of value acquisition, and the virtual terminal type with the highest priority is used as the unique virtual terminal type of the internal short address / virtual terminal.
[0044] In this embodiment of the invention, after obtaining the set of virtual terminals and the set of secondary circuits and the sets of virtual terminals on both sides of the manufacturer's ICD model, virtual terminal matching can be performed to determine model defects. The specific steps are as follows: Figure 5 As shown. In Figure 5 Furthermore, the ICD model defect detection and repair method may also include: In step S50, the first model defect set is obtained according to formula (4). (4) in, For the first model's defect set, This refers to the set of virtual terminals on both sides of the secondary circuit set. This refers to the set of virtual terminals in the manufacturer's ICD model. Specifically, based on the virtual terminal type and the internal short address of the virtual terminal, it verifies whether the virtual terminals on both sides of the secondary circuit exist in the virtual terminal set. This can be done as follows: Figure 10 , Figure 11 As shown. Furthermore, the verification logic for checking the virtual terminal type and internal short address of the virtual terminals in the virtual terminal sets on both sides of the virtual terminal set in the ICD model and the secondary loop set can be based on, as follows: Figure 7 To achieve this, follow the steps shown: In step S501, the virtual terminal types of the virtual terminal sets on both sides of the virtual terminal sets in the virtual terminal set and the secondary circuit set are encoded to obtain the corresponding type vectors. The corresponding text and character encodings may include, but are not limited to, ASCII encoding known to those skilled in the art.
[0045] In step S502, the similarity of virtual terminal types between the virtual terminal sets and the two virtual terminal sets in the secondary circuit set is obtained according to formula (7). (7) in, This refers to the similarity of virtual terminal types between the virtual terminal sets of the virtual terminal combination and the two virtual terminal sets in the secondary circuit set. This refers to the virtual terminal type of the set of virtual terminals on both sides of the secondary circuit set. For the virtual terminal type of the virtual terminal set in the manufacturer's ICD model, Let be the vector of virtual terminal types for the sets of virtual terminals on both sides of the set of quadratic loops. Let be the vector of virtual terminal types for the sets of virtual terminals on both sides of the set of quadratic loops. To predefine the hierarchical weights, if the input type and output type are at the same level (input types can include SV input, GOOSE input, etc.), they do not belong to the same level. Specifically, the hierarchical weights for the same level can be set higher, such as 0.9-1, while the hierarchical weights for different levels can be set lower, such as 0.6-0.7, to amplify the differences between different levels and improve the matching accuracy of type similarity.
[0046] In step S503, the internal short addresses of the virtual terminals in the virtual terminal sets and the two virtual terminal sets in the secondary loop set are hierarchically divided and encoded respectively. This hierarchical division can be determined based on the general classification logic of virtual terminal types, such as device, node, data object, data attribute, etc.
[0047] In step S504, the similarity of the internal short addresses of the virtual terminals in the virtual terminal sets and the two virtual terminal sets in the secondary loop set is obtained according to formula (8). (8) in, This refers to the similarity of the internal short addresses of the virtual terminals in the virtual terminal set and the two virtual terminal sets in the secondary loop set. The first of the internal short addresses of the virtual terminal The layer structure weights, specifically, can be determined based on the importance of each layer. For the matching function, when and The value is 1 if they are exactly the same, otherwise it is 0. The first short address inside the virtual terminal in the virtual terminal set Layer structure, The first short address inside the virtual terminal of the virtual terminal set on both sides of the secondary circuit set. Layer structure, This represents the number of levels in the internal short address space of the virtual terminal. The number is an integer.
[0048] In step S505, the virtual terminal similarity between the virtual terminal sets and the two virtual terminal sets in the secondary loop set is obtained according to formula (9). (9) in, This represents the virtual terminal similarity between the virtual terminal sets and the virtual terminal sets on both sides of the virtual terminal set and the secondary loop set. , , These are the type weight for virtual terminal matching, the internal short address weight, and the coordination weight, which can be set according to the actual situation. . For the collaborative constraint terms, specifically, the collaborative constraint terms can be obtained according to formula (10). (10) in, , These are the short internal addresses of the virtual terminals in the virtual terminal set and the two virtual terminal sets in the secondary circuit set, respectively. For joint encoding functions, The similarity function includes, but is not limited to, cosine similarity and dot product. Specifically, the mapping relationship between the type of the virtual terminal and the internal short address also reflects whether the virtual terminal conforms to engineering conventions. For example, if the type of the virtual terminal and the internal short address are similar, but the mapping relationship is very different, this situation can be adjusted by reducing the overall similarity through collaborative constraint terms, thereby improving the accuracy and effect of virtual terminal matching.
[0049] In step S51, the second model defect set is obtained according to formula (5). (5) in, For the second model defect set, This refers to the set of input virtual terminals in the virtual terminal set of the manufacturer's ICD model. This refers to the set of output virtual terminals within the virtual terminal set of the manufacturer's ICD model. Specifically, it verifies whether there is an intersection between the set of input virtual terminals and the set of output virtual terminals for the secondary circuit, i.e., whether the same virtual terminal serves as both an input and an output terminal for the secondary circuit. Specifically, this can be done as follows: Figure 12 As shown.
[0050] In step S52, virtual terminals whose internal short addresses end with data attributes are obtained from the virtual terminal sets on both sides of the secondary loop set. Here, a secondary loop refers to a loop between secondary devices, with a transmitting side and a receiving side; the virtual terminals on both sides refer to the transmitting virtual terminal and the receiving virtual terminal. Further, the virtual terminal whose internal short address ends with a data attribute may include the internal short address of the virtual terminals on both sides of the secondary loop ending with the data attribute .q (quality) or .t (time stamp).
[0051] In step S53, it is determined whether a value loop exists in the virtual terminals whose internal short addresses in the virtual terminal sets on both sides of the secondary loop set end with a data attribute. Specifically, it can be checked whether a value loop exists in the corresponding virtual terminal's internal short address ending with .f or .stVal, that is, whether the virtual terminals on both sides of the secondary loop have internal short addresses ending with .f or .stVal. Specifically, this can be done as follows: Figure 13 As shown.
[0052] In step S54, if it is determined that there is no value loop in the virtual terminal whose short address ends with a data attribute in the virtual terminal sets on both sides of the secondary loop set, the corresponding manufacturer's ICD model is obtained, and a third model defect set is constructed. If a value loop does not exist, it indicates a missing loop, and the missing loop is added to the set. The quality (or time-scaled) loop can be converted into the corresponding value loop according to formula (6). RPIT / GGIO1.Ind1.t PIGO / GOINGGIO15.Ind21.t
[0053] (6) Formula (6) can indicate to the user which circuit is missing, making it easier for the user to repair the defect based on the prompt information.
[0054] Based on the above verification results, defects in the manufacturer's ICD model can be detected, and these defects can be classified and archived.
[0055] In this embodiment of the invention, after detecting model defects, each model defect can be analyzed to determine the cause of the defect. Specifically, this can be done as follows: Figure 6 As shown. Specifically, in Figure 6 Furthermore, the ICD model defect detection and repair method may also include: In step S70, it is determined whether the first model defect set is empty.
[0056] In step S71, if the first model defect set is not empty, it is determined that the virtual terminal definition is missing, the virtual terminal definition is incorrect, or the virtual terminal reference is incorrect. The first model defect set... If the value is not empty, it means that the input virtual terminal of the secondary circuit does not exist in the input virtual terminal set, or the output virtual terminal does not exist in the output virtual terminal set. The manufacturer's ICD model may have issues such as missing virtual terminal definitions, incorrect virtual terminal definitions, or incorrect virtual terminal references. Further, it can be checked whether the virtual terminal definition exists in the virtual terminal set. If it does not exist, the problem is a missing virtual terminal definition; if it exists, the problem may be an incorrect virtual terminal reference or an incorrect virtual terminal definition.
[0057] In step S72, it is determined whether the second model defect set is empty.
[0058] In step S73, if the second model defect set is not empty, it is determined that the manufacturer's ICD model has a virtual terminal reference error or secondary circuit redundancy. The second model defect set... If it is not empty, it means that the same virtual terminal is used as both the input terminal and the output terminal of the secondary circuit. The manufacturer's ICD model may have virtual terminal reference errors and secondary circuit redundancy issues.
[0059] In step S74, it is determined whether the defect set of the third model is empty.
[0060] In step S75, if the third model defect set is not empty, it is determined that the manufacturer's ICD model has a missing secondary loop. The third model defect set... If the value is not empty, it means that when the short address inside the virtual terminals on both sides of the secondary loop ends with the data attribute .q (quality) or .t (time stamp), the value loop of the corresponding virtual terminal ending with .f or .stVal does not exist. The manufacturer's ICD model may have a problem with missing secondary loops.
[0061] On the other hand, the present invention also provides an ICD model defect detection and repair system based on SCD files. This ICD model defect detection and repair system may include a file parsing module and a control module. Specifically, the file parsing module is used to import and parse SCD files, and the control module is connected to the file parsing module to execute any of the above-mentioned ICD model defect detection and repair methods.
[0062] Through the above technical solution, the ICD model defect detection and repair method and system based on SCD files provided by this invention parses the imported SCD file into multiple elements and corresponding attributes, then constructs a pre-trained model. Based on the equipment name attribute of each element, the corresponding equipment type is obtained. Based on the element attributes and equipment type, the manufacturer's ICD model and the corresponding virtual terminal set and secondary circuit set can be obtained. Model defects are detected based on the virtual terminal set and the two-sided virtual terminal set in the secondary circuit set, thereby obtaining a list of model defect causes and corresponding model defect repair solutions. The manufacturer's ICD model can then be repaired based on these solutions. By parsing the attributes of elements in the SCD file to obtain the virtual terminal set of the manufacturer's ICD model and the two-sided virtual terminal set in the secondary circuit set, and then detecting model defects based on these virtual terminal sets and the two-sided virtual terminal set in the secondary circuit set, early detection of model defects can be achieved. This effectively improves the detection efficiency of ICD model defects and has high detection accuracy, thus shortening the on-site debugging time of secondary equipment in the SCD file and improving the efficiency and reliability of substation infrastructure debugging and operation.
[0063] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0064] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0065] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0066] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0067] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0068] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0069] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0070] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0071] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.< / ied> < / ied> < / ied> < / ied> < / ied> < / ied> < / ied> < / ied> < / ied> < / ied> < / ied>
Claims
1. A method for defect detection and repair of ICD models based on SCD files, characterized in that, include: Import the SCD file and parse multiple elements and their attributes in the SCD file, wherein the element attributes include the device name; Construct a pre-trained model for each device type, and obtain the corresponding device type based on the device name and the pre-trained model. Obtaining the corresponding device type based on the device name and the pre-trained model includes: obtaining the device type corresponding to each device name according to formula (1). ，（1） in, For the first The device type of the device name. For preprocessing functions, This is a word segmentation function. For filtering functions, For mapping functions, The parameter value at which the conditional probability reaches its maximum. For the first The device name mentioned above. For the first Class of equipment types, For device name Corresponding device type The conditional probability, Numbered by integer; Based on the element attributes and the device type, obtain the manufacturer's ICD model and the set of virtual terminals of the manufacturer's ICD model; Obtain the set of secondary loops from the manufacturer's ICD model; Model defects are obtained based on the set of virtual terminals in the manufacturer's ICD model and the sets of virtual terminals on both sides of the secondary circuit set. The model defects are classified and archived to obtain a list of model defects; Obtain a list of causes for model defects based on the aforementioned list of model defects; Obtain a model defect repair plan based on the list of model defect causes, and execute the model defect repair plan.
2. The ICD model defect detection and repair method according to claim 1, characterized in that, The element attributes also include manufacturer, model, version, virtual terminal set, and secondary circuit set.
3. The ICD model defect detection and repair method according to claim 1, characterized in that, Building pre-trained models for device types includes: Define a rule base for device type identification; A pre-trained model for device types is constructed based on the device type identification rule base.
4. The ICD model defect detection and repair method according to claim 1, characterized in that, Obtaining the corresponding device type based on the device name and the pre-trained model also includes: The likelihood probability of the device name is obtained according to formula (2). ，（2） in, For a given number Class of equipment types When entering the device name The matching probability, The samples that contain keywords in the historical input of the pre-trained model. To and The corresponding confirmed standard equipment types, The historical set in the pre-trained model. For text similarity functions, For smoothing coefficients, For each type of device during the traversal, For circular subscripts, and Numbered by integer; The conditional probability of the device name is obtained according to formula (3). ，（3） in, The prior probability of the device type; The corresponding device type is obtained based on the conditional probability of the device name.
5. The ICD model defect detection and repair method according to claim 2, characterized in that, The virtual terminal attributes in the virtual terminal set of the manufacturer's ICD model include virtual terminal type, virtual terminal description, and virtual terminal internal short address.
6. The ICD model defect detection and repair method according to claim 2, characterized in that, The manufacturer's ICD model and the set of virtual terminals of the manufacturer's ICD model are obtained based on the element attributes and the device type, including: Preset the value priority of virtual terminal type; Obtain the internal short address of the same virtual terminal of the ICD model from the same manufacturer; Determine whether there are cases where the internal short address of the same virtual terminal in the same ICD model from the same manufacturer belongs to different virtual terminal types; If it is determined that the internal short address of the same virtual terminal in the same ICD model of the same manufacturer belongs to different virtual terminal types, multiple virtual terminal types corresponding to the internal short address of the virtual terminal are obtained. The virtual terminal type with the highest priority is obtained based on the multiple virtual terminal types and the value priority. The virtual terminal type with the highest priority is used as the unique virtual terminal type for the internal short address of the virtual terminal.
7. The ICD model defect detection and repair method according to claim 2, characterized in that, Based on the set of virtual terminals in the manufacturer's ICD model and the sets of virtual terminals on both sides of the secondary circuit set, the model defects are obtained, including: The first model defect set is obtained according to formula (4). ，（4） in, For the first model's defect set, This refers to the set of virtual terminals on both sides of the secondary circuit set. This is the set of virtual terminals for the manufacturer's ICD model; The second model defect set is obtained according to formula (5). ，（5） in, For the second model defect set, This refers to the set of input virtual terminals in the virtual terminal set of the manufacturer's ICD model. This refers to the set of output virtual terminals in the virtual terminal set of the manufacturer's ICD model.
8. The ICD model defect detection and repair method according to claim 7, characterized in that, The model defects obtained based on the set of virtual terminals in the manufacturer's ICD model and the set of virtual terminals on both sides of the secondary circuit set also include: Obtain the virtual terminals whose short internal addresses end with data attributes from the virtual terminal sets on both sides of the secondary circuit set; Determine whether there is a value loop in the virtual terminals whose short addresses end with data attributes in the virtual terminal sets on both sides of the secondary loop set; If it is determined that there is no value loop in the virtual terminal whose internal short address ends with the data attribute in the virtual terminal set on both sides of the secondary loop set, the corresponding manufacturer's ICD model is obtained, and a third model defect set is constructed.
9. The ICD model defect detection and repair method according to claim 8, characterized in that, The list of causes of model defects obtained from the aforementioned list of model defects includes: Determine whether the defect set of the first model is empty; If the first model defect set is not empty, it is determined that the virtual terminal definition is missing, the virtual terminal definition is incorrect, or the virtual terminal reference is incorrect. Determine whether the defect set of the second model is empty; If the second model defect set is not empty, it is determined that the manufacturer's ICD model has a virtual terminal reference error or a secondary circuit redundancy. Determine whether the defect set of the third model is empty; If the defect set of the third model is not empty, it is determined that the secondary loop of the manufacturer's ICD model is missing.
10. A defect detection and repair system for ICD models based on SCD files, characterized in that, include: The file parsing module is used to import and parse SCD files; The control module, connected to the file parsing module, is used to execute the ICD model defect detection and repair method as described in any one of claims 1-9.