Method and system for monitoring insulation components of a primary and secondary fusion ring network box of a multi-parameter joint insurance

Abstract

The application discloses a primary and secondary fusion ring network box insulation component monitoring method and system, relates to the technical field of ring network box insulation monitoring, and comprises the following steps: establishing a monitoring scene parameter mapping list; connecting multiple source monitoring devices to obtain multiple source monitoring data of insulation components, and matching the multiple source monitoring data with the monitoring scene parameter mapping list; coupling and analyzing the multiple source monitoring data to generate an insulation component monitoring state; establishing an insulation monitoring space-time grid; and performing monitoring space-time analysis and control isolation analysis according to the insulation monitoring space-time grid to generate a monitoring feedback result. The application solves the technical problems of single insulation monitoring parameter, inaccurate fault positioning and untimely isolation control of the prior art, achieves the multiple parameter coupling monitoring of the primary and secondary fusion ring network box insulation components, the accurate fault space-time positioning and intelligent isolation control, and improves the insulation fault identification accuracy and the operation and maintenance response speed.

Description

Technical Field

[0001] This invention relates to the field of ring main unit insulation monitoring technology, specifically to a monitoring method and system for primary and secondary integrated ring main unit insulation components with multiple parameters. Background Technology

[0002] With the intelligent upgrading of distribution networks, integrated primary and secondary ring main units have become key node equipment in distribution lines, and the operational reliability of their internal insulation components directly affects the safe power supply of the power grid. Currently, traditional insulation monitoring often uses single electrical quantities or partial discharge signals as criteria, which suffers from insufficient parameter coupling, susceptibility to environmental interference in anomaly detection, and high false alarm and false negative rates. Furthermore, monitoring and analysis are mostly limited to single-point, static judgment modes, lacking comprehensive modeling of the temporal evolution trend of insulation status and spatial topological transmission relationships, making it difficult to achieve accurate fault location and quantitative analysis of the impact range. In addition, existing systems cannot dynamically adjust monitoring accuracy according to the insulation degradation rate, and fault warning and isolation strategies rely on manual experience, resulting in decision-making lag, coarse location, and unreasonable isolation ranges, failing to meet the needs of high-density, high-reliability distribution networks for real-time perception and intelligent control of ring main unit insulation status.

[0003] Existing technologies address the technical problems of single insulation monitoring parameters, inaccurate fault location, and untimely isolation control in integrated primary and secondary ring network boxes. Summary of the Invention

[0004] This application provides a monitoring method and system for insulation components of primary and secondary integrated ring main units with multiple parameters, which is used to address the technical problems of existing technologies such as single monitoring parameters, inaccurate fault location, and untimely isolation control in primary and secondary integrated ring main units.

[0005] In view of the above problems, this application provides a method and system for monitoring the insulation components of a multi-parameter integrated ring main unit.

[0006] The first aspect of this application provides a method for monitoring the insulation components of a multi-parameter integrated primary and secondary ring main unit, the method comprising:

[0007] A multi-parameter joint protection rule mapping list is established, which maps the rules to monitoring scenario parameters of insulating components. Multi-source monitoring data of insulating components is acquired by connecting to multi-source monitoring devices. The acquired multi-source monitoring data is preprocessed and then matched with the monitoring scenario parameter mapping list to locate the joint protection rules for the multi-source monitoring data. Based on the joint protection rules, the multi-source monitoring data is coupled and analyzed to generate the monitoring status of the insulating components, which reflects the current insulation health status level of the insulating components. The monitoring status of the insulating components is used for temporal and spatial segmentation and positioning to establish an insulation monitoring spatiotemporal grid. Based on the insulation monitoring spatiotemporal grid, spatiotemporal analysis and control isolation analysis are performed to generate monitoring feedback results.

[0008] A second aspect of this application provides a monitoring system for the insulation components of a multi-parameter integrated primary and secondary ring main unit, the system comprising: The system includes the following modules: a parameter mapping list establishment module for establishing a multi-parameter joint protection rule mapping list with monitoring scenario parameters of insulating components; a joint protection rule positioning module for connecting to multi-source monitoring equipment to acquire multi-source monitoring data of insulating components, and matching the pre-processed multi-source monitoring data with the monitoring scenario parameter mapping list to locate the joint protection rules of the multi-source monitoring data; an insulating component monitoring status generation module for performing coupled analysis on the multi-source monitoring data based on the joint protection rules to generate the insulating component monitoring status, which reflects the current insulation health status level of the insulating component; an insulation monitoring spatiotemporal grid establishment module for performing temporal and spatial segmentation and positioning based on the insulating component monitoring status to establish an insulation monitoring spatiotemporal grid; and a monitoring feedback result generation module for performing monitoring spatiotemporal analysis and control isolation analysis based on the insulation monitoring spatiotemporal grid to generate monitoring feedback results.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: A multi-parameter joint protection rule mapping list is established between the monitoring scenario parameters of the insulation components and the multi-source monitoring equipment. Multi-source monitoring data of the insulation components is acquired by connecting to multi-source monitoring devices. After preprocessing the acquired multi-source monitoring data, it is matched with the monitoring scenario parameter mapping list to locate the joint protection rule of the multi-source monitoring data. Based on the joint protection rule, the multi-source monitoring data is coupled and analyzed to generate the monitoring status of the insulation components. An insulation monitoring spatiotemporal grid is established. Based on the insulation monitoring spatiotemporal grid, spatiotemporal analysis of the monitoring and control isolation are performed to generate monitoring feedback results. This achieves the technical effect of realizing multi-parameter coupled monitoring, precise spatiotemporal fault location, and intelligent isolation control of the insulation components of the primary and secondary integrated ring network box, improving the accuracy of insulation fault identification and the speed of operation and maintenance response. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic flowchart of the monitoring method for the insulation components of a multi-parameter integrated ring main unit provided in this application embodiment; Figure 2 This is a schematic diagram of the structure of the multi-parameter joint protection primary and secondary integrated ring network box insulation component monitoring system provided in the embodiments of this application.

[0012] Explanation of reference numerals in the attached diagram: Parameter mapping list establishment module 10, joint protection rule positioning module 20, insulation component monitoring status generation module 30, insulation monitoring spatiotemporal grid establishment module 40, monitoring feedback result generation module 50. Detailed Implementation

[0013] This application provides a monitoring method and system for the insulation components of a primary and secondary integrated ring main unit with multiple parameters, which addresses the technical problems of existing technologies such as single monitoring parameters, inaccurate fault location, and untimely isolation control in primary and secondary integrated ring main units.

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0015] Example 1, as Figure 1 As shown, this application provides a method for monitoring the insulation components of a multi-parameter integrated primary and secondary ring main unit, the method comprising: Step S100: Establish a mapping list of multi-parameter protection rules and monitoring scenario parameters for insulating components.

[0016] Specifically, a multi-source database for primary and secondary integrated ring network enclosures is constructed. This database includes standard test data, historical operating data, and fault case data. The database is segmented and classified according to the life cycle parameters of the insulation components (early, mid, and aging stages) and operating scenario parameters (operating environment and operating load parameters), forming multi-scenario data clusters. Using multi-source joint protection parameters as the target, pre-fault time-series data and normal control data are extracted from each data cluster. After discretization, an association rule mining algorithm is used to generate candidate joint protection rules. Confidence, support, and lift are calculated, and effective rules are selected to establish a fault-multi-source joint protection parameter mapping relationship. Using fault type as the target, joint protection rules for the same fault are aggregated, and the contribution support of each joint protection parameter to fault identification is calculated. The contribution support is normalized and sorted, distinguishing between core parameters and auxiliary parameters. Based on the core parameters, the mapping relationship is filtered and classified. Finally, a multi-parameter joint protection rule mapping list with monitoring scenario parameters of insulation components is constructed, including life cycle stage, operating scenario code, insulation component type, fault type, joint protection parameter combination, logical relationship, rule confidence, and parameter contribution support.

[0017] Step S200: Connect to the multi-source monitoring device to obtain multi-source monitoring data of the insulating components, and after preprocessing the collected multi-source monitoring data, match it with the monitoring scenario parameter mapping list to locate the joint protection rules of the multi-source monitoring data.

[0018] Specifically, a connection is established with multi-source monitoring equipment deployed in the primary and secondary integrated ring network box via a communication interface to collect multi-source monitoring data such as partial discharge, dielectric loss, temperature, humidity, load current, and voltage of insulating components in real time. The collected raw data is preprocessed by noise reduction, filtering, normalization, outlier removal, and timestamp alignment to form a standardized time-series monitoring dataset. The preprocessed monitoring data is then matched item by item with the established monitoring scenario parameter mapping list from dimensions such as life cycle stage, operating scenario code, insulating component type, and real-time parameter values. Through consistency comparison of parameter combinations, logical relationships, and threshold ranges, the joint protection rules applicable to the current monitoring data are accurately located. These rules include the corresponding fault type, joint protection parameter combination, rule confidence, and parameter contribution support, providing a basis for subsequent coupling analysis.

[0019] Step S300: Based on the joint protection rules, the multi-source monitoring data is coupled and analyzed to generate the monitoring status of the insulation components. The monitoring status of the insulation components is used to reflect the current insulation health status level of the insulation components.

[0020] Specifically, based on the identified joint guarantee rules, and according to the joint guarantee parameter combinations, logical relationships, parameter threshold ranges, and contribution support levels stipulated in the rules, multi-parameter joint coupling analysis is carried out on the preprocessed multi-source monitoring data. The matching degree between each monitoring parameter and the rule threshold, the correlation constraint relationship between parameters, and the overall confidence level are comprehensively calculated. Through weighted fusion judgment, the monitoring status of insulation components that can comprehensively characterize the degree of insulation performance degradation, abnormal risk level, and potential fault type is obtained. This status is output in the form of health level, which is used to intuitively reflect the current insulation health level and safe operation status of insulation components in the primary and secondary integrated ring network box.

[0021] Step S400: Perform temporal and spatial segmentation and positioning based on the monitoring status of the insulation components, and establish a spatiotemporal grid for insulation monitoring.

[0022] Specifically, based on the generated monitoring status of insulation components, a multi-scale sliding window is used for time-series state analysis in the time dimension to obtain the time-series status of insulation components changing over time. In the spatial dimension, according to the physical topology of the primary and secondary integrated ring network box, it is divided into multi-level spatial grids at the whole box level, functional unit level, compartment level, phase level, and component level. Each spatial grid unit has a unique spatial coordinate identifier and adjacent topological relationship. The time window obtained from the time-series analysis is spatiotemporally fused with the spatial grid units. Combining the influence relationship between the time-series status of insulation components and physical topology, an insulation monitoring spatiotemporal grid is constructed, which includes the start and end times of the time window, spatial coordinates, insulation health index, anomaly confidence level, fault type label, and joint protection rules for participation in the judgment. When the rate of decrease of the insulation health index of a certain spatial grid unit exceeds a preset threshold, the time window length is automatically shortened and the spatial grid level is refined to achieve dynamic adjustment of spatiotemporal resolution.

[0023] Step S500: Perform spatiotemporal analysis of the insulation monitoring grid and control isolation analysis to generate monitoring feedback results.

[0024] Specifically, based on the established spatiotemporal grid for insulation monitoring, spatiotemporal analysis and control isolation analysis are conducted. According to the insulation health index, anomaly confidence level, and monitoring status of insulation components within the grid, abnormal fault grid cells are accurately identified, and insulation degradation trends and propagation risks are judged. Combining the topological correlation of the spatiotemporal grid, the development trend of the fault in the time dimension and the impact range in the spatial dimension are determined. Based on the degree of insulation degradation and potential danger level, proactive isolation treatment with the minimum scope and optimal timing is performed in advance to quickly lock and cut off the fault propagation path to prevent the fault range from expanding. At the same time, monitoring feedback results containing fault location, degradation level, isolation strategy, and early handling suggestions are generated to guide the timely implementation of preventive isolation and maintenance of primary and secondary integrated ring network boxes, ensuring continuous and reliable power supply to the power grid and avoiding the expansion of faults that affect the safe and stable operation of the power grid.

[0025] In one possible implementation, step S100 further includes: Step S110: Construct a multi-source database for the primary and secondary integrated ring network box, wherein the multi-source database includes at least standard test data, historical operation data, and fault case data.

[0026] Step S120: Classify the multi-source database according to the different operating scenarios of each insulating component in different life cycles, and construct a multi-scenario type data cluster.

[0027] Step S130: Using multi-source joint protection parameters as targets, perform parameter correlation analysis based on the multi-scenario type data clusters respectively, identify multi-source joint protection parameters or combinations of multi-source joint protection parameters that have obtained a threshold of correlation with fault cases in different life cycles and different operating scenarios, and establish a fault-multi-source joint protection parameter mapping relationship.

[0028] Step S140: Based on the fault-multi-source joint protection parameter mapping relationship, perform multi-source joint protection parameter aggregation with fault type as the target, and identify the contribution support of multi-source parameters.

[0029] Step S150: Using the contribution support of the multi-source parameters, perform relationship filtering and classification on the fault-multi-source joint protection parameter mapping relationship, and construct the monitoring scenario parameter mapping list.

[0030] Specifically, a multi-source database for monitoring the insulation components of integrated primary and secondary ring main units is constructed. This database provides fundamental data support for the mining of multi-parameter protection rules and includes at least three types of data: standard test data, historical operating data, and fault case data. Standard test data refers to the baseline insulation performance data measured during factory, type, and acceptance tests of the insulation components, including standard thresholds and characteristic curves for partial discharge, dielectric loss, insulation resistance, and withstand voltage. Historical operating data refers to the steady-state monitoring data collected in real time during long-term energized operation of the insulation components, covering operating temperature, ambient humidity, load current, operating voltage, and long-term insulation state changes. Fault case data refers to the on-site records of faults such as flashover, breakdown, and aging failure that occur in the insulation components during actual operation, including the fault occurrence time, fault phenomena, fault location, changes in monitoring parameters before and after the fault, and fault cause analysis results. By integrating the above multi-dimensional data to form a complete and unified data set, a comprehensive and reliable data source is provided for subsequent scenario classification, correlation analysis, and rule establishment.

[0031] Based on the material characteristics and performance degradation patterns of each insulating component, life cycle segmentation parameters are determined, dividing it into three stages: early, middle, and aging. Simultaneously, considering the actual operating conditions of the primary and secondary integrated ring network box, operating scenario parameters, including operating environment parameters and operating load parameters, are determined. Based on the aforementioned life cycle stages and operating scenario parameters, the constructed multi-source database is uniformly segmented by life cycle matching and classified by operating scenario parameter matching. Data belonging to the same life cycle stage and the same operating scenario are grouped together to form a multi-scenario data cluster covering different operating conditions and degradation stages.

[0032] This study focuses on multi-source joint protection parameters used for jointly determining insulation status. Parameter correlation analysis is conducted on various constructed multi-scenario data clusters. First, time-series data of all monitoring parameters within a preset time window before the fault occurs are extracted along with normal state comparison data. Continuous monitoring values ​​are discretized and converted into state labels. Then, an association rule mining algorithm is used to traverse each data cluster to mine frequent itemsets, generating candidate joint protection rules that reflect the correlation between parameter state combinations and fault types. By calculating the confidence, support, and lift of each candidate rule, effective rules that meet the minimum support and minimum confidence thresholds are selected. Subsequently, under different lifecycles and operating scenarios, multi-source joint protection parameters or combinations of multi-source joint protection parameters with a correlation to fault cases reaching a preset threshold are identified, ultimately establishing a clear fault... The multi-source joint protection parameter mapping relationship includes fault type, joint protection parameter combination, parameter threshold range, logical relationship and confidence level for each mapping record.

[0033] Based on the established fault-multi-source joint protection parameter mapping relationship, and taking fault type as the aggregation target, all joint protection rules belonging to the same fault type in each lifecycle and operational scenario data cluster are extracted and classified to form a multi-source joint protection parameter mapping subset for the corresponding fault type. On this basis, the contribution support of each multi-source joint protection parameter in the identification of the corresponding fault type is calculated. This contribution support is used to quantitatively characterize the sensitivity and decision contribution weight of the multi-source monitoring parameters to fault judgment, reflecting the effectiveness and criticality of each parameter in the fault identification process. This clarifies the primary and secondary roles and functions of different joint protection parameters in the same fault judgment, providing a quantitative basis for subsequent rule selection and mapping list construction.

[0034] The obtained multi-source parameter contribution support scores are normalized so that the sum of the contribution support scores of all parameters under the same fault type is 1. Then, the parameters are sorted from high to low to form a parameter contribution support score table. Based on a preset screening threshold, the joint protection parameters are divided into core parameters and auxiliary parameters. Based on the core parameters, the fault-multi-source joint protection parameter mapping relationship is filtered by rules, and only valid rules containing at least one core parameter are retained. Subsequently, the retained rules are classified and organized according to life cycle stage, operation scenario code, insulation component type, fault type, and core parameter combination. Finally, a monitoring scenario parameter mapping list is constructed, which includes life cycle stage, operation scenario code, insulation component type, fault type, joint protection parameter combination, logical relationship, rule confidence, and contribution support score of each parameter. This provides a standardized basis for the joint protection rule matching of multi-source monitoring data.

[0035] In one possible implementation, step S120 further includes: Step S121: Based on the material and properties of the insulating components, determine the life cycle segmentation parameters of the insulating components, including at least the early, middle and aging periods.

[0036] Step S122: Based on the operating parameters and setting environment of the primary and secondary integrated ring network box, and the relationship between these parameters and the performance of the insulation components, determine the operating scenario parameters, including at least the operating environment parameters and the operating load parameters.

[0037] Step S123: Perform lifecycle matching and segmentation and operation scenario parameter matching and classification on the multi-source database according to the lifecycle segmentation parameters and operation scenario parameters to construct the multi-scenario type data cluster.

[0038] Specifically, based on the material characteristics, electrical performance, structural attributes, and aging failure mechanisms of the insulating components in the primary and secondary integrated ring network boxes, life cycle segmentation parameters are determined to divide the entire life cycle stages. According to the change law of insulation performance from commissioning to deterioration and failure, the entire life cycle of the insulating components is clearly divided into three stages: early stage, middle stage, and aging stage. The early stage is the stage where the performance of the insulating components is stable and there is no obvious deterioration in the initial stage of commissioning; the middle stage is the stage where the performance of the insulating components declines steadily and the state is basically normal; and the aging stage is the stage where the performance of the insulating components declines significantly, defects are prone to occur, and failure is imminent. Through this life cycle segmentation parameter, the different deterioration stages of the insulating components can be accurately distinguished, providing a basis for life cycle dimension division for subsequent scenario-based data classification and rule mining.

[0039] Based on the actual operating parameters and on-site environment of the integrated primary and secondary ring main units (RMUs), and considering their influence on the insulation performance of insulating components, operating scenario parameters for scenario classification are determined. These parameters include at least operating environment parameters and operating load parameters. Operating environment parameters characterize the external conditions of the RMU installation site, including parameters that directly affect the surface insulation performance of insulating components, such as temperature, humidity, pollution level, air pressure, and condensation conditions. Operating load parameters characterize the energized operating state of the RMU, including parameters that affect the internal heating and aging rate of insulating components, such as load current, operating voltage, load fluctuation amplitude, and energization duration. These operating scenario parameters accurately depict different operating conditions, providing a basis for subsequent data classification by operating scenario.

[0040] Based on the established life cycle segmentation parameters and operating scenario parameters, standard test data, historical operating data, and fault case data from multiple source databases are matched in two dimensions. First, life cycle matching and segmentation are completed according to the early, middle, and aging stages of the insulation components. Then, operating scenario parameter matching and classification are completed based on operating environment parameters and operating load parameters. All monitoring and operating data belonging to the same life cycle stage and the same operating scenario are aggregated into a data unit, ultimately forming a multi-scenario data cluster covering different degradation stages and different operating conditions.

[0041] In one possible implementation, step S130 further includes: Step S131: Based on the multi-scenario type data cluster, extract all monitoring parameter time-series data within a preset time window before the occurrence of the fault case, as well as the control data under normal conditions.

[0042] Step S132: Discretize each monitoring parameter and convert continuous values ​​into status labels according to a preset threshold range.

[0043] Step S133: Using an association rule mining algorithm, frequent itemsets are mined from data clusters of various multi-scenario types to generate candidate joint guarantee rules. The candidate joint guarantee rules are used to reflect the association relationship between parameter state combinations and fault types.

[0044] Step S134: Calculate the confidence, support, and lift of each candidate rule in the corresponding data cluster, and select the rule that simultaneously meets the minimum support and minimum confidence thresholds as the effective association rule.

[0045] Step S135: Based on the effective association rules, output the fault-multi-source joint protection parameter mapping relationship of the multi-scenario type data cluster, wherein each mapping record includes: fault type, joint protection parameter combination, threshold range of each parameter, logical relationship, and confidence level.

[0046] Specifically, based on the established multi-scenario data cluster, data is filtered and extracted for each lifecycle and operational scenario combination. For each fault case within the cluster, a continuous period of a preset time window is extracted, and time-series data of all monitoring parameters within this window are collected, including monitoring values ​​of partial discharge, dielectric loss, temperature, humidity, load, and voltage as they change over time. Simultaneously, in the same multi-scenario data cluster, a normal state period with the same lifecycle and operational scenario as the fault case and without fault occurrence is selected, and time-series data of the same monitoring parameters are extracted as control data. By pairing pre-fault data with normal control data, a complete and comparable sample is provided for subsequent parameter correlation analysis.

[0047] The extracted time-series data of various monitoring parameters are discretized. The continuously changing simulated values ​​of partial discharge, dielectric loss, temperature, humidity, load current, voltage, etc. are divided into several discrete value intervals according to the insulation monitoring standard and the preset threshold interval. Each interval is then uniformly mapped to a digital status label that can be used for association rule calculation, thus transforming continuous quantities into discrete status quantities and eliminating the calculation interference caused by the differences in dimensions and numerical ranges between different monitoring parameters.

[0048] For the multi-scenario data cluster after discretization, the Apriori algorithm, an association rule mining algorithm, is used for traversal analysis. This algorithm iteratively scans the dataset, counts the frequency of different monitoring parameter state label combinations, and extracts frequent itemsets that exceed the preset minimum support, i.e., high-frequency state combinations where multiple monitoring parameters appear simultaneously. Based on these frequent itemsets, candidate joint protection rules are generated. Each rule is expressed in the form of "parameter state combination - fault type" to intuitively reflect the potential correlation between the state combinations of multi-source joint protection parameters and the corresponding insulation fault types under different life cycles and operating scenarios, providing a candidate set for subsequent effective rule screening.

[0049] For all candidate joint guarantee rules generated in multi-scenario data clusters, the support, confidence, and lift of each rule are statistically calculated within its corresponding cluster. Support is the frequency of the parameter state combination corresponding to the candidate joint guarantee rule appearing in the total sample of the data cluster, representing the rule's general applicability. Confidence is the conditional probability of the corresponding fault type occurring simultaneously under the given parameter state combination, representing the rule's judgment reliability. Lift is the ratio of the actual fault occurrence probability to the confidence level, representing the rule's association effectiveness. The calculated indicators are compared with the system's preset minimum support and minimum confidence thresholds. Candidate rules that simultaneously meet both threshold requirements are selected and identified as effective association rules for insulation fault identification. Redundant rules with low applicability and low reliability are eliminated to ensure the accuracy and practicality of subsequent mapping relationships.

[0050] Based on the selected effective association rules, for each multi-scenario data cluster, the effective association rules are organized and standardized, and the corresponding fault-multi-source joint protection parameter mapping relationship is output. This mapping relationship is a structured data set used to clarify the correspondence between different fault types and multi-source joint protection parameters. Each mapping record fully contains five key pieces of information: first, the fault type, which clarifies the specific fault of the corresponding insulation component, such as flashover, breakdown, aging failure, etc.; second, the joint protection parameter combination, which is the set of multi-source monitoring parameters involved in the fault judgment, such as the combination of partial discharge and dielectric loss, and the combination of temperature and humidity. The system includes five key aspects: 1) the threshold ranges for each parameter, specifying the discrete threshold range for each joint guarantee parameter and the preset range for the corresponding conversion status label; 2) the logical relationships, clarifying the logical connections between parameters in the joint guarantee parameter combination, such as "AND" or "OR" relationships, meaning that each parameter must simultaneously satisfy its corresponding threshold range or satisfy any threshold range to determine the corresponding fault; 3) the confidence level, which is the confidence level of the effective association rule corresponding to the mapping relationship, used to characterize the reliability of the judgment of the mapping relationship. The resulting fault-multi-source joint guarantee parameter mapping relationship provides a standardized rule basis for subsequent multi-source parameter aggregation and the construction of monitoring scenario parameter mapping lists.

[0051] In one possible implementation, step S140 further includes: Step S141: For each lifecycle-running scenario data cluster, the fault-multi-source joint protection parameter mapping relationship is obtained. Using the fault type as the filtering target, all joint protection rules belonging to the same fault type are extracted, and a multi-source joint protection parameter mapping subset corresponding to the fault type is established. Each joint protection rule contains at least one joint protection parameter combination and the corresponding rule confidence.

[0052] Step S142: For each multi-source joint protection parameter mapping subset, calculate the contribution support degree of each joint protection parameter to the fault type. The contribution support degree is used to reflect the contribution of multi-source monitoring data to the identification of fault type and has a sensitive identification coefficient.

[0053] Specifically, for each data cluster corresponding to a combination of lifecycles and operating scenarios, based on the established fault-multi-source joint protection parameter mapping relationship under that cluster, and using fault type as the classification and filtering target, all joint protection rules belonging to the same fault type in the mapping relationship are uniformly extracted and aggregated, thereby constructing a multi-source joint protection parameter mapping subset exclusive to that fault type. Each joint protection rule contains at least one set of joint protection parameter combinations used for joint fault judgment, as well as the rule confidence level corresponding to the combination when judging the corresponding fault type. Through this mapping subset, centralized management of all joint protection rules under the same type of fault is realized, providing a regular data source for subsequent quantitative calculation of the contribution support of each joint protection parameter.

[0054] For each fault type, a subset of multi-source joint protection parameter mappings is used. Taking the fault type as the judgment object, statistical and quantitative calculations are performed on each joint protection parameter involved in all joint protection rules in the subset to obtain the contribution support degree of each joint protection parameter to the fault type. This contribution support degree serves as a sensitive identification coefficient characterizing the diagnostic capability of the parameter. It is used to quantitatively reflect the degree of decision contribution and response sensitivity of the multi-source monitoring data in the process of identifying the corresponding fault type. The higher the value, the stronger the parameter's characterization capability for the fault and the higher the judgment reliability. This provides a quantitative basis for subsequently distinguishing core decision parameters from auxiliary reference parameters and optimizing the joint protection decision logic.

[0055] In one possible implementation, step S150 further includes: Step S151: Normalize the contribution support of each joint guarantee parameter so that the sum of the contribution support of all parameters under the same fault type is 1.

[0056] Step S152: Sort the parameters by contribution support from high to low, and generate a parameter contribution support table for the corresponding fault type in the current life cycle and operating scenario.

[0057] Step S153: Based on the parameter contribution support table, classify the joint guarantee parameters according to the screening threshold, where those exceeding the screening threshold are core parameters and the rest are auxiliary parameters.

[0058] Step S154: Based on the core parameter set, filter each joint protection rule of the fault-multi-source joint protection parameter mapping relationship, and retain at least one rule containing core parameters.

[0059] Step S155: Classify the retained joint protection rules according to life cycle stage, operation scenario code, fault type and core parameter combination, and construct the monitoring scenario parameter mapping list.

[0060] Specifically, the contribution support calculated for each joint support parameter corresponding to the same fault type is normalized. Based on the sum of the contribution support of all joint support parameters under the fault type, the original contribution support of each parameter is standardized and adjusted by proportional conversion. This ensures that the sum of the contribution support values ​​of all joint support parameters under the same fault type is strictly equal to 1, thereby eliminating decision interference caused by differences in the magnitude of contribution support values ​​under different life cycles and operating scenarios, and realizing a unified quantitative comparison of the importance of each joint support parameter in fault identification.

[0061] The normalized support values ​​of each joint protection parameter are sorted in descending order of their values. A dedicated parameter support table is generated based on the sorting results. This table clearly records the joint protection parameters involved in the corresponding fault type and their normalized support values ​​under the current life cycle stage and current operating scenario, intuitively reflecting the sensitivity and decision weight differences of different parameters in identifying the fault type.

[0062] Based on the generated parameter contribution support table, a preset screening threshold is used to classify and distinguish each joint guarantee parameter in the table. Joint guarantee parameters with contribution support values ​​greater than or equal to the screening threshold are identified as core parameters. These parameters have high sensitivity to fault types and strong decision contribution, and serve as the main judgment basis for fault identification. Joint guarantee parameters with contribution support values ​​lower than the screening threshold are classified as auxiliary parameters to supplement and corroborate the fault status. This achieves a clear distinction between core judgment parameters and auxiliary reference parameters, and provides a classification standard for subsequent joint guarantee rule screening.

[0063] Based on the established set of core parameters, each joint protection rule in the established fault-multi-source joint protection parameter mapping relationship is judged and verified one by one. Only valid joint protection rules with at least one core parameter in the combination of joint protection parameters contained in the rule are retained, and redundant rules that do not contain any core parameters, consist only of auxiliary parameters, and have insufficient decision reliability are eliminated, thereby improving the accuracy and stability of fault judgment.

[0064] The valid joint guarantee rules that are retained after screening are classified and organized in a multi-level structure according to the life cycle stage, operation scenario code, fault type and core parameter combination. Rules with the same life cycle, the same scenario, the same fault and similar core parameter combinations are uniformly arranged to form a structured and directly callable monitoring scenario parameter mapping list.

[0065] In one possible implementation, step S155 further includes: Each record in the monitoring scenario parameter mapping list includes the following fields: life cycle stage, operating scenario code, insulation component type, fault type, joint protection parameter combination, logical relationship, rule confidence, and contribution support of each parameter.

[0066] Specifically, the completed monitoring scenario parameter mapping list is a standardized structured data list. Each record in the list contains a complete set of eight core fields, each with a clearly defined and interrelated meaning, as follows: Lifecycle Stage: This specifies the corresponding degradation stage of the insulation component, i.e., early, mid, or aging stage, characterizing the basic state of the insulation component; Operation Scenario Code: This is a unique identifier for the corresponding operation scenario, corresponding one-to-one with the previously determined operating environment parameters and operating load parameters, used for rapid matching of actual operating conditions; Insulation Component Type: This specifies the specific type of insulation component within the primary and secondary integrated ring network box, such as insulators, insulating bushings, and insulating partitions, distinguishing the fault characteristics of different components; Fault Type: This specifies the specific faults that may occur in the insulation component, such as flashover. The system includes eight fields: network failure, breakdown, aging failure, and excessive partial discharge; joint protection parameter combinations (a set of multi-source monitoring parameters used to jointly determine the corresponding fault type, such as partial discharge and dielectric loss, temperature and load current); logical relationships (clarifying the logical connections between parameters in the joint protection parameter combination, such as "AND" and "OR" relationships, meaning that each parameter must simultaneously satisfy its corresponding threshold range or satisfy any threshold range to determine the corresponding fault); rule confidence (characterizing the reliability of the judgment of the joint protection rule corresponding to the record, i.e., the conditional probability of the corresponding fault occurring when the parameter combination appears); and contribution support of each parameter (the normalized contribution support value of each parameter in the joint protection parameter combination, used to reflect the weight difference and sensitivity of each parameter in fault identification). These eight fields comprehensively cover core information such as operating conditions, components, faults, parameters, and rules, ensuring that the monitoring scenario parameter mapping list can be directly used for rule matching and fault decision-making in subsequent online monitoring.

[0067] In one possible implementation, step S400 further includes: Step S410: Based on the monitoring status of the insulation component, perform state analysis using a multi-scale sliding window in the time dimension to obtain the time-series status of the insulation component.

[0068] Step S420: In the spatial dimension, the spatial grid is divided according to the physical topology of the primary and secondary integrated ring network box. The division level includes at least the whole box level, functional unit level, compartment level, phase level, and component level. Each spatial grid unit has a unique spatial coordinate identifier and adjacent topological relationships.

[0069] Step S430: Perform spatiotemporal fusion of the time window and spatial grid cell, and establish a spatiotemporal grid data structure according to the temporal state of the insulation components and the influence relationship of physical topology. Each spatiotemporal grid cell stores the following: start and end time of the time window, spatial coordinates, insulation health index, anomaly confidence, fault type label, and joint protection rules involved in the judgment.

[0070] Specifically, the temporal and spatial range of the impact of insulation faults is determined based on the spatiotemporal grid of insulation monitoring. When the rate of decline of the insulation health index of a spatial grid unit exceeds a preset threshold, the grid resolution of the corresponding grid unit is automatically dynamically adjusted, including shortening the time window length and / or refining the spatial grid level.

[0071] Specifically, based on the real-time acquisition and preprocessing of the monitoring status of insulation components, a multi-scale sliding window is used to segment and analyze the continuous monitoring data in the time dimension. By using sliding windows of different lengths, the characteristic information of insulation performance in short-term fluctuations, medium-term trends and long-term evolution is extracted. Noise interference is eliminated and abnormal change patterns are highlighted. Finally, a time-series status of insulation components that can completely reflect the evolution of the insulation component status over time is formed.

[0072] Based on the actual physical topology and internal layout of the primary and secondary integrated ring main unit, a multi-level spatial grid is divided for the entire unit and its internal insulation area. The division levels, from coarse to fine, include at least: the whole unit level, functional unit level, compartment level, phase level, and component level, to achieve fine spatial positioning from the overall equipment to key insulation components. Each spatial grid unit is assigned a set of independent and unique spatial coordinate identifiers to accurately distinguish and index different spatial locations, while recording the adjacent, contained, and coupled topological relationships between each grid unit.

[0073] The time window obtained by the multi-scale sliding window is fused with the spatial grid cells after multi-level division in a spatiotemporal dimension. Combining the evolution law of the time-series state of insulation components with the influence of the internal physical topology of the ring network box, a unified spatiotemporal grid data structure is constructed to achieve a joint expression of insulation state in time and space. Each spatiotemporal grid cell stores structured state information, specifically including: the start and end times of the time window, used to mark the time range of the current time-series analysis; spatial coordinates, a unique spatial coordinate identifier for the corresponding grid cell, used to locate the fault location; insulation health index, used to quantitatively characterize the overall health level of the current insulation components; anomaly confidence, used to reflect the degree of credibility of the current state deviating from normal operating conditions; fault type label, a specific fault type identifier obtained through joint protection rules; and the joint protection rules involved in the judgment, which are the faults used to trigger anomaly judgment under the current spatiotemporal grid. Multi-source joint protection parameter mapping rules provide a complete data carrier for the spatiotemporal location, trend analysis, and dynamic tracking of insulation faults.

[0074] In the constructed spatiotemporal grid for insulation monitoring, the temporal and spatial ranges of the impact of insulation faults are determined based on the stored data and topological relationships of each spatiotemporal grid unit, enabling a comprehensive assessment of the fault's temporal evolution and spatial spread. During real-time monitoring, the insulation health index of each spatial grid unit is differentially calculated to obtain its rate of decline over time. When this rate of decline exceeds the system's preset rate threshold, it is determined that the insulation performance at the corresponding location is rapidly deteriorating, and the system automatically implements a dynamic grid resolution adjustment strategy for that spatial grid unit. The adjustment methods include shortening the time window length to improve the time sampling density and response accuracy, and / or refining the spatial grid hierarchy to further subdivide it into smaller spatial positioning units, thereby achieving high-density, high-precision tracking and monitoring of rapidly deteriorating areas and improving the accuracy of early fault identification and location.

[0075] In one possible implementation, step S500 further includes: Step S510: Identify abnormal fault grid cells based on the insulation health index in the insulation monitoring spatiotemporal grid.

[0076] Step S520: Based on the abnormal fault grid cells, locate the temporal impact space and spatial impact range, perform minimum isolation spatiotemporal positioning based on the isolation relationship between grids, and determine the intervention isolation strategy.

[0077] Step S530: The intervention isolation strategy is used as the monitoring feedback result to guide the maintenance isolation control of the primary and secondary integrated ring network box.

[0078] Specifically, taking the completed insulation monitoring spatiotemporal grid as the analysis object, based on the insulation health index values ​​and their changing trends stored in the grid, and comparing them with preset health thresholds, spatiotemporal grid units with insulation health indices lower than normal thresholds or whose index decline rate exceeds warning thresholds are identified as abnormal fault grid units, thereby achieving accurate identification of insulation abnormal locations within the primary and secondary integrated ring network box.

[0079] Taking the identified abnormal fault grid cell as the core, the first step is to determine the fault degradation rate and the potential future temporal impact range based on the insulation health index change rate and anomaly confidence time-series curve of the cell in the spatiotemporal grid using a time extrapolation model. Simultaneously, combining the physical topology of the ring main unit, the conduction relationship between adjacent grids, and the electric field and gas chamber diffusion characteristics, the spatial impact range that the fault may affect is calculated. After determining the impact range, using the physical compartments, circuit breakers, disconnect switches, insulating partitions, and gas pressure seals between grid cells as constraints, the minimum grid set that can completely surround the fault area and achieve effective isolation through existing equipment is selected by backtracking from the boundary grid of the spatial impact range, thus obtaining the minimum isolation spatiotemporal location. Then, based on the spatial coordinates, phase, compartment, and component positions corresponding to this minimum isolation area, the operable equipment of the ring main unit is matched, identifying the switches that need to be tripped, the compartments that need to be locked, and the priority timing operation steps, ultimately forming an intervention isolation strategy that includes timing control sequence, spatial isolation points, and linkage interlocking logic.

[0080] The intervention and isolation strategy generated based on spatiotemporal grid and minimum isolation positioning is output as the final monitoring feedback result. This result includes specific isolation points, operation sequence, linkage interlocking requirements and safety precautions. It is directly used to guide operation and maintenance personnel or automated control systems to carry out targeted maintenance, isolation and protection control of primary and secondary integrated ring main units. By executing corresponding switch actions, compartment interlocking and area power outages, the fault transmission path is quickly cut off, the insulation fault is prevented from further expanding, and the safe and stable operation of the ring main unit is ensured.

[0081] Example 2, based on the same inventive concept as the multi-parameter joint protection primary and secondary fusion ring network box insulation component monitoring method in the aforementioned examples, such as... Figure 2 As shown, this application provides a multi-parameter joint protection primary and secondary integrated ring main unit insulation component monitoring system. The system and method embodiments in this application are based on the same inventive concept. The system includes: The parameter mapping list creation module 10 is used to create a parameter mapping list between multi-parameter protection rules and monitoring scenarios of insulating components.

[0082] The joint protection rule positioning module 20 is used to connect to the multi-source monitoring equipment to obtain multi-source monitoring data of the insulation components, and to match the collected multi-source monitoring data with the monitoring scenario parameter mapping list after preprocessing to locate the joint protection rules of the multi-source monitoring data.

[0083] The insulation component monitoring status generation module 30 is used to perform coupled analysis on the multi-source monitoring data based on the joint protection rules to generate the insulation component monitoring status, which reflects the current insulation health status level of the insulation component.

[0084] The insulation monitoring spatiotemporal grid establishment module 40 is used to perform temporal and spatial segmentation and positioning based on the monitoring status of the insulation components, and to establish an insulation monitoring spatiotemporal grid.

[0085] The monitoring feedback result generation module 50 is used to perform monitoring spatiotemporal analysis and control isolation analysis based on the insulation monitoring spatiotemporal grid to generate monitoring feedback results.

[0086] Furthermore, the system is also used to implement the following functions: A multi-source database for the primary and secondary integrated ring network enclosure is constructed, wherein the multi-source database includes at least standard test data, historical operating data, and fault case data. The multi-source database is classified according to different operating scenarios of each insulating component at different lifecycles, constructing a multi-scenario data cluster. Using multi-source joint protection parameters as targets, parameter correlation analysis is performed on the multi-scenario data clusters to identify multi-source joint protection parameters or combinations of multi-source joint protection parameters whose correlation with fault cases reaches a threshold in different lifecycles and operating scenarios, establishing a fault-multi-source joint protection parameter mapping relationship. Based on the fault-multi-source joint protection parameter mapping relationship, multi-source joint protection parameters are aggregated using fault type as the target, identifying the contribution support of multi-source parameters. Using the contribution support of multi-source parameters, the fault-multi-source joint protection parameter mapping relationship is filtered and classified to construct the monitoring scenario parameter mapping list.

[0087] Furthermore, the system is also used to implement the following functions: Based on the material and properties of the insulation components, life cycle segmentation parameters for the insulation components are determined, including at least the early, middle, and aging periods. Based on the operating parameters and setting environment of the primary and secondary integrated ring network box and their impact on the performance of the insulation components, operating scenario parameters are determined, including at least operating environment parameters and operating load parameters. The multi-source database is then segmented based on life cycle segmentation parameters and classified based on operating scenario parameters to construct the multi-scenario type data cluster.

[0088] Furthermore, the system is also used to implement the following functions: Based on the multi-scenario data cluster, extract time-series data of all monitoring parameters within a preset time window before the occurrence of the fault case, as well as control data under normal conditions; discretize each monitoring parameter, converting continuous values ​​into state labels according to preset threshold intervals; use an association rule mining algorithm to mine frequent itemsets in each multi-scenario data cluster, generating candidate joint guarantee rules, which reflect the association between parameter state combinations and fault types; calculate the confidence, support, and lift of each candidate rule in the corresponding data cluster, and select rules that simultaneously meet the minimum support and minimum confidence thresholds as effective association rules; based on the effective association rules, output the fault-multi-source joint guarantee parameter mapping relationship of the multi-scenario data cluster, wherein each mapping record includes: fault type, joint guarantee parameter combination, threshold intervals of each parameter, logical relationship, and confidence.

[0089] Furthermore, the system is also used to implement the following functions: For each lifecycle-operation scenario data cluster, the fault-multi-source joint protection parameter mapping relationship is obtained. Using fault type as the filtering target, all joint protection rules belonging to the same fault type are extracted, and a multi-source joint protection parameter mapping subset corresponding to the fault type is established. Each joint protection rule contains at least one combination of joint protection parameters and the corresponding rule confidence. For each multi-source joint protection parameter mapping subset, the contribution support degree of each joint protection parameter to the fault type is calculated. The contribution support degree is used to reflect the contribution of multi-source monitoring data to the identification of fault type and has a sensitive identification coefficient.

[0090] Furthermore, the system is also used to implement the following functions: The contribution support of each joint protection parameter is normalized so that the sum of the contribution support of all parameters under the same fault type is 1. The parameters are then sorted from highest to lowest value according to their contribution support to generate a parameter contribution support table for the corresponding fault type under the current lifecycle and operating scenario. Based on this parameter contribution support table, the joint protection parameters are classified according to a screening threshold, with those exceeding the threshold being core parameters and the rest being auxiliary parameters. Based on the set of core parameters, each joint protection rule in the fault-multi-source joint protection parameter mapping relationship is screened, retaining at least one rule containing a core parameter. The retained joint protection rules are then classified according to lifecycle stage, operating scenario code, fault type, and core parameter combination to construct the monitoring scenario parameter mapping list.

[0091] Furthermore, the system is also used to implement the following functions: Each record in the monitoring scenario parameter mapping list includes the following fields: life cycle stage, operating scenario code, insulation component type, fault type, joint protection parameter combination, logical relationship, rule confidence, and contribution support of each parameter.

[0092] Furthermore, the system is also used to implement the following functions: Based on the monitoring status of the insulation components, a multi-scale sliding window is used for status analysis in the time dimension to obtain the temporal status of the insulation components. In the spatial dimension, spatial grids are divided according to the physical topology of the primary and secondary integrated ring network box. The division levels include at least the whole box level, functional unit level, compartment level, phase level, and component level. Each spatial grid unit has a unique spatial coordinate identifier and adjacent topological relationships. The time window and spatial grid units are spatiotemporally fused. According to the temporal status of the insulation components and the influence relationship of the physical topology, a spatiotemporal grid data structure is established. Each spatiotemporal grid unit stores the following: the start and end times of the time window, spatial coordinates, insulation health index, anomaly confidence level, fault type label, and joint protection rules involved in the judgment. Among them, the temporal and spatial range of the impact of insulation faults is determined according to the spatiotemporal grid of insulation monitoring. When the rate of decrease of the insulation health index of a spatial grid unit exceeds a preset threshold, the grid resolution of the corresponding grid unit is automatically dynamically adjusted, including shortening the time window length and / or refining the spatial grid level.

[0093] Furthermore, the system is also used to implement the following functions: Based on the insulation health index in the insulation monitoring spatiotemporal grid, abnormal fault grid cells are identified; based on the abnormal fault grid cells, the temporal impact space and spatial impact range are located, and based on the isolation relationship between grids, the minimum isolation spatiotemporal location is determined to establish an intervention isolation strategy; the intervention isolation strategy is used as the monitoring feedback result to guide the maintenance isolation control of the primary and secondary integrated ring network box.

[0094] It should be noted that the order of the embodiments described above is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. Specific embodiments of this specification have been described above. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0095] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0096] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A monitoring method for insulation components of a multi-parameter integrated primary and secondary ring main unit, characterized in that, include: Establish a mapping list between multi-parameter protection rules and monitoring scenario parameters of insulating components; Connect to multi-source monitoring equipment to acquire multi-source monitoring data of insulating components, and after preprocessing the acquired multi-source monitoring data, match it with the monitoring scenario parameter mapping list to locate the joint protection rules of the multi-source monitoring data; Based on the joint protection rules, the multi-source monitoring data is coupled and analyzed to generate the monitoring status of insulation components. The monitoring status of insulation components is used to reflect the current insulation health status level of insulation components. Based on the monitoring status of the insulation components, a temporal and spatial segmentation and positioning are performed to establish a spatiotemporal grid for insulation monitoring. Based on the insulation monitoring spatiotemporal grid, spatiotemporal analysis of monitoring and control isolation analysis are performed to generate monitoring feedback results; Establish a mapping list between multi-parameter protection rules and monitoring scenario parameters of insulating components, including: Construct a multi-source database for the primary and secondary integrated ring network box, wherein the multi-source database includes at least standard test data, historical operation data, and fault case data; The multi-source database is classified according to the different operating scenarios of each insulating component at different life cycles, and a multi-scenario type data cluster is constructed. Using multi-source joint protection parameters as the target, parameter correlation analysis is performed on the multi-scenario type data clusters respectively to identify multi-source joint protection parameters or combinations of multi-source joint protection parameters that have a threshold correlation with fault cases in different life cycles and different operating scenarios, and to establish a fault-multi-source joint protection parameter mapping relationship. Based on the fault-multi-source joint protection parameter mapping relationship, multi-source joint protection parameters are aggregated with fault type as the target, and the contribution support of multi-source parameters is identified. Using the contribution support of the multi-source parameters, the fault-multi-source joint protection parameter mapping relationship is filtered and classified, and a multi-parameter joint protection rule and the monitoring scenario parameter mapping list of the insulation component are constructed, which include life cycle stage, operation scenario code, insulation component type, fault type, joint protection parameter combination, logical relationship, rule confidence and parameter contribution support. Using the contribution support of the multi-source parameters, the fault-multi-source joint protection parameter mapping relationship is filtered and classified to construct the monitoring scenario parameter mapping list, including: The contribution support of each joint guarantee parameter is normalized so that the sum of the contribution support of all parameters under the same fault type is 1. Sort the parameters by contribution support values ​​from highest to lowest, and generate a parameter contribution support table for the corresponding fault type in the current lifecycle and operating scenario. Based on the parameter contribution support table, the joint guarantee parameters are classified according to the screening threshold. Among them, those exceeding the screening threshold are core parameters, and the rest are auxiliary parameters. Based on the core parameter set, each joint protection rule of the fault-multi-source joint protection parameter mapping relationship is filtered, and at least one rule containing core parameters is retained. The retained joint protection rules are classified according to life cycle stage, operation scenario code, fault type and core parameter combination, and the monitoring scenario parameter mapping list is constructed.

2. The monitoring method for insulation components of a multi-parameter integrated primary and secondary ring network box according to claim 1, characterized in that, The multi-source database is categorized according to the different operating scenarios of each insulating component at different life stages, and a multi-scenario type data cluster is constructed, including: Based on the material and properties of the insulating components, determine the life cycle segmentation parameters of the insulating components, including at least the early, middle and aging periods; Based on the operating parameters and setup environment of the primary and secondary integrated ring main unit, and their relationship with the performance of the insulation components, determine the operating scenario parameters, including at least the operating environment parameters and the operating load parameters. The multi-source database is segmented based on the lifecycle segmentation parameters and the running scenario parameters, and classified based on the running scenario parameters to construct the multi-scenario type data cluster.

3. The monitoring method for insulation components of a multi-parameter integrated primary and secondary ring main unit according to claim 1, characterized in that, Using multi-source joint guarantee parameters as the target, parameter correlation analysis is performed on the data clusters of the aforementioned multi-scenario types, including: Based on the multi-scenario type data cluster, extract all monitoring parameter time-series data within a preset time window before the occurrence of the fault case, as well as the control data under normal conditions; Each monitoring parameter is discretized, and continuous values ​​are converted into status labels according to a preset threshold range; An association rule mining algorithm is used to mine frequent itemsets in data clusters of various multi-scenario types and generate candidate joint guarantee rules. The candidate joint guarantee rules are used to reflect the association relationship between parameter state combinations and fault types. Calculate the confidence, support, and lift of each candidate rule in the corresponding data cluster, and select the rule that simultaneously meets the minimum support and minimum confidence thresholds as the effective association rule; Based on the effective association rules, the fault-multi-source joint protection parameter mapping relationship of the multi-scenario type data cluster is output. Each mapping record includes: fault type, joint protection parameter combination, threshold range of each parameter, logical relationship, and confidence level.

4. The monitoring method for insulation components of a multi-parameter integrated ring main unit as described in claim 3, characterized in that, Based on the aforementioned fault-multi-source joint protection parameter mapping relationship, multi-source joint protection parameters are aggregated with fault type as the target, and the contribution support of multi-source parameters is identified, including: For each lifecycle-running scenario data cluster, the fault-multi-source joint protection parameter mapping relationship is obtained. Using the fault type as the filtering target, all joint protection rules belonging to the same fault type are extracted, and a multi-source joint protection parameter mapping subset corresponding to the fault type is established. Each joint protection rule contains at least one joint protection parameter combination and the corresponding rule confidence. For each subset of multi-source joint protection parameters, the contribution support degree of each joint protection parameter to the fault type is calculated. The contribution support degree is used to reflect the contribution of multi-source monitoring data to the identification of fault type and has a sensitive identification coefficient.

5. The monitoring method for insulation components of a multi-parameter integrated ring main unit as described in claim 1, characterized in that, Each record in the monitoring scenario parameter mapping list includes the following fields: life cycle stage, operating scenario code, insulation component type, fault type, joint protection parameter combination, logical relationship, rule confidence, and contribution support of each parameter.

6. The monitoring method for insulation components of a multi-parameter integrated primary and secondary ring main unit according to claim 1, characterized in that, Based on the monitoring status of the insulation components, a temporal and spatial segmentation and positioning are performed to establish a spatiotemporal grid for insulation monitoring, including: Based on the monitoring status of the insulation components, a multi-scale sliding window is used in the time dimension to perform state analysis and obtain the time-series status of the insulation components. In terms of spatial dimension, the spatial grid is divided according to the physical topology of the primary and secondary integrated ring network box. The division level includes at least the whole box level, functional unit level, compartment level, phase level, and component level. Each spatial grid unit has a unique spatial coordinate identifier and adjacent topological relationship. The time window and spatial grid cell are spatiotemporally fused. According to the temporal state of the insulation components and the influence relationship of physical topology, a spatiotemporal grid data structure is established. Each spatiotemporal grid cell stores the following: start and end time of the time window, spatial coordinates, insulation health index, anomaly confidence, fault type label, and joint protection rules involved in the judgment. Specifically, the temporal and spatial range of the impact of insulation faults is determined based on the spatiotemporal grid of insulation monitoring. When the rate of decline of the insulation health index of a spatial grid unit exceeds a preset threshold, the grid resolution of the corresponding grid unit is automatically dynamically adjusted, including shortening the time window length and / or refining the spatial grid level.

7. The monitoring method for insulation components of a multi-parameter integrated primary and secondary ring main unit according to claim 6, characterized in that, Based on the aforementioned insulation monitoring spatiotemporal grid, spatiotemporal analysis and control isolation analysis are performed to generate monitoring feedback results, including: Based on the insulation health index in the spatiotemporal grid of insulation monitoring, identify abnormal fault grid cells; Based on the abnormal fault grid cells, the temporal impact space and spatial impact range are located, and based on the isolation relationship between grids, the minimum isolation spatiotemporal location is performed to determine the intervention isolation strategy. The aforementioned intervention and isolation strategy is used as the monitoring feedback result to guide the maintenance and isolation control of the primary and secondary integrated ring network box.

8. A multi-parameter integrated primary and secondary ring main unit insulation component monitoring system, characterized in that, The system is used to implement the multi-parameter joint protection primary and secondary integrated ring main unit insulation component monitoring method according to any one of claims 1-7, the system comprising: The parameter mapping list creation module is used to create a parameter mapping list between multi-parameter protection rules and monitoring scenarios of insulating components; The joint protection rule positioning module is used to connect to multi-source monitoring equipment to obtain multi-source monitoring data of insulation components, and to match the collected multi-source monitoring data with the monitoring scenario parameter mapping list after preprocessing to locate the joint protection rules of the multi-source monitoring data. An insulation component monitoring status generation module is used to perform coupled analysis on the multi-source monitoring data based on the joint protection rules to generate an insulation component monitoring status, which reflects the current insulation health status level of the insulation component. The insulation monitoring spatiotemporal grid establishment module is used to perform temporal and spatial segmentation and positioning based on the monitoring status of the insulation components, and to establish an insulation monitoring spatiotemporal grid. The monitoring feedback result generation module is used to perform monitoring spatiotemporal analysis and control isolation analysis based on the insulation monitoring spatiotemporal grid, and generate monitoring feedback results.

Images