A low-voltage variable station distribution box state monitoring method based on big data analysis

Abstract

The present application belongs to the technical field of intelligent power distribution monitoring, and particularly relates to a low-voltage transformer substation power distribution box state monitoring method based on big data analysis. The present application comprises: collecting the operation state measurement data of the low-voltage transformer substation power distribution box, establishing the association between the sampling time index and the equipment identification, and forming a state measurement data set; discriminating the trend of the change direction and the change amplitude of the measurement deviation index in the time dimension, and forming measurement evolution information; performing cross-constraint judgment on the current operation state of the low-voltage transformer substation power distribution box, and generating a power distribution box state monitoring report. The present application introduces the cooperative mechanism of the trusted state measurement data set and the digital twin measurement model in the power distribution box state monitoring process, so that the operation state evaluation is established on the basis of high-trust data input based on the continuity and stability constraints of the measurement behavior, effectively supports the stable identification and long-term tracking of the operation state of the low-voltage transformer substation power distribution box, and realizes the continuous and stable and constraintable evaluation of the operation state.

Description

Technical Field

[0001] This invention belongs to the field of intelligent power distribution monitoring technology, and in particular relates to a method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis. Background Technology

[0002] As power distribution networks evolve towards more refined operation and intelligent maintenance, low-voltage transformer substations and distribution boxes, as crucial equipment connecting transformers and users, are increasingly shifting their operational status monitoring from traditional periodic manual inspections to a technology based on online data acquisition and status analysis. Current technologies widely utilize online acquisition of voltage, current, power, and some environmental parameters to achieve basic monitoring of the distribution box's operational status. Furthermore, data mining and statistical analysis methods are being gradually introduced to perform trend analysis and anomaly identification on the operational data, thereby improving maintenance efficiency and reducing labor costs.

[0003] In the course of technological evolution, some studies have attempted to introduce model-driven and simulation analysis methods to combine equipment structural characteristics with operational data in order to achieve a comprehensive assessment of the operating status of distribution boxes. However, existing solutions mostly focus on data judgment within a single point in time and a short time window, lacking characterization of the reliability of the collected data itself. Furthermore, the relationship between the actual operating status and the model simulation response often fails to form a unified and sustainable evolutionary judgment mechanism, resulting in insufficient stability of the status assessment results under complex operating conditions. Summary of the Invention

[0004] To address the shortcomings of the existing technologies, this invention provides a method for monitoring the status of low-voltage transformer substations and distribution boxes based on big data analysis. Its purpose is to solve the problem of the lack of a unified judgment mechanism that simultaneously considers the reliability of measurement data and the consistency of simulation response during the monitoring of the operating status of low-voltage transformer substations and distribution boxes, making it difficult to achieve continuous, stable, and constrained evaluation of the operating status.

[0005] The technical solution adopted by the present invention to achieve the above objectives is as follows:

[0006] A method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis includes:

[0007] Collect operational status measurement data of low-voltage transformer distribution boxes, and establish a sampling time index associated with equipment identification to form a status measurement data set;

[0008] The continuity and stability of the measurement behavior are judged on the state measurement data set, measurement confidence labeling information is generated, and the measurement confidence labeling information is associated with the state measurement data set one by one to obtain a reliable state measurement dataset;

[0009] A digital twin measurement model of the distribution box is constructed, and a reliable state measurement dataset is mapped to the digital twin measurement model of the distribution box. Continuous change relationship matching and response generation are performed to obtain the simulation state feature sequence.

[0010] The trusted state measurement dataset is compared with the simulation state feature sequence over time to determine the degree of continuous deviation of the trusted state measurement data from the simulation state features over time, and a measurement deviation index is generated.

[0011] The direction and magnitude of the measurement deviation index over time are analyzed to determine the trend and form measurement evolution information.

[0012] Based on the changes in measurement evolution information and measurement reliability labeling information during operation, cross-constraint judgments are performed on the current operating status of the low-voltage transformer distribution box, and a distribution box status monitoring report is generated.

[0013] Furthermore, the step of collecting operational status measurement data from low-voltage transformer distribution boxes and establishing a sampling time index associated with equipment identifiers to form a status measurement data set includes:

[0014] Collect operational status measurement data of low-voltage transformer distribution boxes, including electrical operation status measurement data, thermal status measurement data, and structural response status measurement data;

[0015] A unified measurement time reference is established and a continuous sampling time index is generated. The operation process of the distribution box is divided into continuous sampling periods to obtain a sampling time index sequence.

[0016] Based on the sampling time index sequence, the operating status measurement data of the distribution box at the corresponding time in each sampling period is collected synchronously, and the operating status measurement data is time-aligned and associated with the corresponding sampling time index to form time-series status measurement data;

[0017] The time-series status measurement data are associated one by one with the predetermined distribution box equipment identifiers, and continuously packaged according to the sampling time index order to generate a status measurement data set.

[0018] Furthermore, the step of determining the continuity and stability of measurement behavior in the state measurement data set, generating measurement confidence labeling information, and associating the measurement confidence labeling information with each item in the state measurement data set to obtain a reliable state measurement dataset includes:

[0019] Based on the time-series state measurement data in the state measurement dataset, the continuity of the change relationship of the running state measurement data corresponding to adjacent sampling time indices in the time dimension is determined to obtain continuity determination information;

[0020] Based on the continuity discrimination information, the stability of the change amplitude of the operation status measurement data within the continuous sampling period is judged to obtain the stability discrimination information;

[0021] Based on the continuity discrimination information and stability discrimination information, the running status measurement data under the corresponding sampling time index are labeled to generate measurement confidence label information;

[0022] Based on the state measurement data set, the consistency of the measurement confidence label information under the corresponding sampling time index and the execution time index of the running state measurement data is verified to obtain the associated candidate data;

[0023] Based on the associated candidate data, the measurement confidence labeling information and the operational status measurement data are bound one by one to form associated data records;

[0024] The associated data records are continuously organized and packaged according to the sampling time index order to generate a reliable state measurement dataset.

[0025] Furthermore, the construction of a digital twin measurement model of the distribution box, mapping the reliable state measurement dataset to the digital twin measurement model of the distribution box, and performing continuous change relationship matching and response generation to obtain a simulation state feature sequence includes:

[0026] Based on the trusted state measurement dataset, the measurement channel information and its correspondence with the sampling time index of the operation state measurement data during the acquisition process are analyzed to form measurement mapping information;

[0027] Based on the measurement mapping information, the measurement channels corresponding to the operation status measurement data and their correspondence with the sampling time index are instantiated and configured, and time constraints consistent with the sampling time index are established to form a twin operation structure.

[0028] Based on the trusted state measurement dataset, historical operating state samples within the stable operating range are extracted under the condition that the sampling time index is consistent.

[0029] Based on historical operational status samples, the correspondence between operational status measurement data and operational result records is determined, forming a mapping relationship between status input and status response;

[0030] The mapping relationship between state input and state response is embedded in the twin operation structure to generate a digital twin measurement model of the distribution box;

[0031] Based on the trusted state measurement dataset, the operating state measurement data is written into the digital twin measurement model of the distribution box according to the sampling time index order to generate the corresponding simulation response data;

[0032] The simulation response data under each sampling time index are processed by time sequence and feature extraction to form a simulation state feature sequence.

[0033] Furthermore, the step of comparing the credible state measurement dataset with the simulation state feature sequence over time to determine the degree of continuous deviation of the credible state measurement data from the simulation state features over time, and generating a measurement deviation index, includes:

[0034] Based on the sampling time index, the running state measurement data in the trusted state measurement dataset and the simulation state features in the simulation state feature sequence are time-aligned and organized to form comparison data pairs.

[0035] Based on the comparison data pairs, the time change relationship between the reliable state measurement data within the continuous sampling time index interval and the corresponding simulation state characteristics is compared to obtain the deviation measurement information.

[0036] Based on deviation metric information, the degree of continuous deviation of the reliable state measurement data from the simulated state characteristics is calculated, generating a measurement deviation index; including:

[0037] The electrical deviation between the electrical operating condition measurement data and the electrical condition response data is calculated using the following formula:

[0038] ;

[0039] in, Indicates the first Electrical deviation value at each sampling time index position; , and Indicates the first Voltage measurement data, current measurement data, and power status measurement data at each sampling time index position; , and This represents the voltage response data, current response data, and power response data in the electrical state response data at the same sampling time index position. , and This indicates the rated voltage, rated current, and rated power specified by the manufacturer when the distribution box was manufactured. Indicates the sampling time index;

[0040] The thermal deviation between the thermal state measurement data and the thermal state response data is calculated using the following formula:

[0041] ;

[0042] in, Indicates the first Thermal deviation value at each sampling time index position; This indicates the total number of key heat source locations; Indicates the location number of key heat-generating points, including circuit breaker contact connection points, busbar connection joints, cable inlet and outlet crimping points, and power device mounting bases; Indicates the first The first sampling time index Temperature measurement data at key heating points; Indicates the first The first sampling time index Thermal status response data of key heating points; Indicates the first Reference values ​​for allowable temperature rise corresponding to the locations of key heating points;

[0043] The structural deviation between the measured structural response state data and the actual structural response state data is calculated using the following formula: ;

[0044] in, Indicates the first Structural deviation values ​​at each sampling time index position; Indicates the first Displacement state measurement data under each sampling time index; Indicates the first Displacement response data under each sampling time index; Indicates the first Vibration amplitude state measurement data under each sampling time index; Indicates the first Vibration amplitude response data under each sampling time index; Indicates the allowable displacement reference value; This indicates the reference value for the permissible vibration amplitude.

[0045] Furthermore, the step of determining the trend of the change direction and magnitude of the measurement deviation index over time to form measurement evolution information includes:

[0046] The measurement deviation indexes are continuously organized according to the sampling time index order to form a time-series deviation index sequence;

[0047] Based on the time-series deviation index sequence, the direction and magnitude of the change in the measurement deviation index within the continuous sampling time index interval are jointly judged to obtain trend discrimination information;

[0048] Based on trend discrimination information, the evolution of the measurement deviation index over time is summarized and identified to form measurement evolution information;

[0049] The process involves performing cross-constraint judgments on the current operating status of the low-voltage transformer distribution box based on changes in measurement evolution information and measurement reliability labeling information during operation, and generating a distribution box status monitoring report; including:

[0050] Based on the sampling time index, the measurement evolution information and measurement confidence labeling information are correlated with the same index to form state evidence information;

[0051] Based on the state evidence information, cross-constraint judgment is performed on the consistency and constraint compliance of the changes in measurement evolution information and measurement confidence labeling information under the same sampling time index to obtain the operation state determination information;

[0052] The operating status information of the low-voltage transformer distribution boxes is summarized and organized according to the sampling time index order, and a distribution box status monitoring report is generated.

[0053] A low-voltage transformer substation distribution box status monitoring device based on big data analysis, used to implement the steps of any one of the low-voltage transformer substation distribution box status monitoring methods based on big data analysis, including:

[0054] The data acquisition module is used to collect the operating status measurement data of the low-voltage transformer distribution box, and establish a sampling time index associated with the equipment identifier to form a status measurement data set;

[0055] The measurement behavior continuity and stability discrimination module is used to discriminate the measurement behavior continuity and stability of the state measurement data set, generate measurement confidence label information, and associate the measurement confidence label information with the state measurement data set one by one to obtain a reliable state measurement dataset.

[0056] The module is used to build a digital twin measurement model of the distribution box, map the reliable state measurement dataset to the digital twin measurement model of the distribution box, perform continuous change relationship matching and response generation, and obtain the simulation state feature sequence.

[0057] The comparison module is used to compare the trusted state measurement dataset with the simulation state feature sequence in time correspondence, determine the degree of continuous deviation of the trusted state measurement data from the simulation state features over time, and generate a measurement deviation index.

[0058] The execution trend discrimination module is used to discriminate the direction and magnitude of change of the measurement deviation index over time, thereby generating measurement evolution information.

[0059] The report generation module is used to perform cross-constraint judgments on the current operating status of the low-voltage transformer distribution box based on the changes in measurement evolution information and measurement confidence labeling information during operation, and generate a distribution box status monitoring report.

[0060] Furthermore, the measurement behavior continuity and stability discrimination module is used to perform measurement behavior continuity and stability discrimination on the state measurement data set, generate measurement confidence labeling information, and associate the measurement confidence labeling information with each item in the state measurement data set to obtain a reliable state measurement dataset; including:

[0061] Based on the time-series state measurement data in the state measurement dataset, the continuity of the change relationship of the running state measurement data corresponding to adjacent sampling time indices in the time dimension is determined to obtain continuity determination information;

[0062] Based on the continuity discrimination information, the stability of the change amplitude of the operation status measurement data within the continuous sampling period is judged to obtain the stability discrimination information;

[0063] Based on the continuity discrimination information and stability discrimination information, the running status measurement data under the corresponding sampling time index are labeled to generate measurement confidence label information;

[0064] Based on the state measurement data set, the consistency of the measurement confidence label information under the corresponding sampling time index and the execution time index of the running state measurement data is verified to obtain the associated candidate data;

[0065] Based on the associated candidate data, the measurement confidence labeling information and the operational status measurement data are bound one by one to form associated data records;

[0066] The associated data records are continuously organized and packaged according to the sampling time index order to generate a reliable state measurement dataset.

[0067] A computer device includes a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods for monitoring the status of a low-voltage transformer distribution box based on big data analysis.

[0068] A computer storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of any one of the methods for monitoring the status of a low-voltage transformer distribution box based on big data analysis.

[0069] The present invention has the following beneficial effects and advantages:

[0070] This invention first associates measurement confidence labeling information with each piece of state measurement data, ensuring that each operational state measurement data under a sampling time index carries a corresponding confidence label. This forms a trusted state measurement dataset where operational state measurement data, sampling time indices, and measurement confidence labeling information are mutually bound. Instead of assuming all collected data is reliable, it identifies data corresponding to sampling interruptions, time misalignments, instantaneous jumps, or measurement link fluctuations as low-confidence data, retaining this confidence information for subsequent judgment. Subsequently, the trusted state measurement dataset is mapped to the digital twin measurement model of the distribution box, generating a simulated state feature sequence corresponding to the sampling time index. A measurement deviation index is generated by comparing the time correspondence between the trusted state measurement dataset and the simulated state feature sequence. This allows distribution box state monitoring to no longer rely solely on measured data thresholds or short-term statistical trends, but to comprehensively compare the relative electrical operating state, thermal state, and structural response state under the same sampling time index. The measurement deviation index is used to determine the degree of deviation from the simulation reference state. By analyzing the trend of the change direction and magnitude of the measurement deviation index over time, measurement evolution information is formed. This information is then linked with the measurement confidence label information using the same index, and cross-constraint judgment is performed. When the measurement confidence label information is high confidence and the measurement evolution information is in a transitional evolution stage, it is determined to be an abnormal operating state. When the measurement confidence label information is low confidence, it is determined to be an operating state pending confirmation. This allows for the differentiation between stable operating states, abnormal operating states, and operating states pending confirmation, thus forming a continuous state determination chain of "confidential state measurement dataset - digital twin simulation reference - measurement deviation index - measurement evolution information - same index cross-constraint judgment". This enables the distribution box status monitoring to simultaneously utilize the reliability of measurement data and the trend of simulation deviation evolution, avoiding the direct equation of measurement anomalies with equipment anomalies, and improving the accuracy, stability, and traceability of low-voltage transformer distribution box operating status determination.

[0071] This invention introduces a collaborative mechanism between a reliable state measurement dataset and a digital twin measurement model during the condition monitoring of distribution boxes. This allows the operational status assessment to no longer rely solely on the original measurement data itself, but rather to be based on highly reliable data input constrained by the continuity and stability of measurement behavior. By mapping the reliable state measurement dataset to the digital twin measurement model to perform continuous change relationship matching and response generation, and quantifying the continuous deviation relationship between the actual measured state and the simulated state characteristics, the determination of the operational status can simultaneously reflect the theoretical evolution law under the constraints of the physical structure and the real change characteristics in the actual operation process. This results in a state monitoring result with temporal continuity, evolutionary interpretability, and judgment consistency, effectively supporting the stable identification and long-term tracking of the operational status of low-voltage transformer distribution boxes. Attached Figure Description

[0072] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0073] Figure 1 This is a flowchart of the low-voltage transformer distribution box status monitoring method based on big data analysis according to the present invention.

[0074] Figure 2 This is a flowchart illustrating the generation of the state measurement data set in this invention.

[0075] Figure 3 This is a flowchart of the process for generating a trusted state measurement dataset according to the present invention.

[0076] Figure 4 This is a flowchart of the process for generating a digital twin measurement model of a distribution box according to the present invention. Detailed Implementation

[0077] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0078] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0079] The following reference Figures 1-4 The technical solutions of some embodiments of the present invention are described below.

[0080] Example 1

[0081] This invention provides an embodiment of a method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis, specifically including the following steps:

[0082] S1. Collect the operating status measurement data of the low-voltage transformer distribution box, and establish a sampling time index associated with the equipment identifier to form a status measurement data set.

[0083] S1.1: Collect operational status measurement data of low-voltage transformer distribution boxes, including electrical operational status measurement data, thermal status measurement data, and structural response status measurement data.

[0084] It should be noted that electrical operating status measurement data refers to measurement data used to reflect the power transmission and load response characteristics of low-voltage transformer distribution boxes during operation, including voltage measurement data, current measurement data, and power status measurement data.

[0085] Thermal state measurement data refers to measurement data used to reflect the thermal response characteristics of low-voltage transformer distribution boxes during operation due to the effects of electrical load and environment. This includes internal temperature data of the box and temperature state measurement data of key conductive parts. The key conductive parts include: circuit breaker contact connection parts, busbar connection joints, cable inlet and outlet crimping parts, and power device mounting base parts, which are prone to contact resistance and local heating.

[0086] Structural response state measurement data refers to the measurement data used to characterize the structural mechanical response characteristics of low-voltage transformer distribution boxes caused by electromagnetic force, thermal stress and external disturbances during operation, including vibration amplitude state measurement data and displacement state measurement data.

[0087] S1.2: Establish a unified measurement time benchmark and generate a continuous sampling time index. Divide the operation process of the distribution box into continuous sampling cycles to obtain the sampling time index sequence.

[0088] Specifically, a unified measurement time benchmark is selected as the time reference for the measurement data of the operating status of the low-voltage transformer distribution box. All time markers involved in the acquisition process are aligned and organized, and the time markers are divided sequentially according to fixed time intervals. This makes the operating process of the low-voltage transformer distribution box divided into a set of sampling cycles with consecutive beginnings and end and consistent time spans in the time dimension. The position of each sampling cycle in the time sequence is numbered one by one to form a sampling time index sequence.

[0089] It should be noted that the fixed time interval is a time division length that is predetermined before the collection of low-voltage transformer distribution box operation status measurement data begins and remains unchanged throughout the monitoring process, used as the basis for time division between adjacent sampling periods.

[0090] S1.3: Based on the sampling time index sequence, the operating status measurement data of the distribution box at the corresponding time in each sampling period is collected synchronously, and the operating status measurement data is time-aligned and associated with the corresponding sampling time index to form time-series status measurement data.

[0091] Specifically, based on the sampling time index sequence, within the sampling period corresponding to each sampling time index, electrical operation status measurement data, thermal status measurement data, and structural response status measurement data of the low-voltage transformer distribution box are synchronously collected at the time position pointed to by the sampling time index identifier to form operation status measurement data. The operation status measurement data is directly appended with the corresponding sampling time index identifier for recording, so that each set of operation status measurement data corresponds one-to-one with a unique sampling time index, forming time-series status measurement data with a clear time correspondence.

[0092] S1.4: Associate the time-series status measurement data with the predetermined distribution box equipment identifiers one by one, and encapsulate them continuously according to the sampling time index order to generate a status measurement data set.

[0093] Specifically, each time-series state measurement data is labeled with a predetermined distribution box equipment identifier, so that the time-series state measurement data clearly belongs to the corresponding low-voltage transformer distribution box. The time-series state measurement data with distribution box equipment identifiers are arranged and packaged according to the sampling time index, forming a state measurement data set that is organized in an orderly manner according to the sampling time index and contains distribution box equipment identifier information.

[0094] It should be noted that the equipment identification of the distribution box is a unique identifier that is pre-determined in the operation and maintenance management ledger before the low-voltage transformer distribution box is put into operation. It is used to distinguish different low-voltage transformer distribution boxes and remains fixed throughout the entire operation status monitoring process.

[0095] S2. Perform measurement behavior continuity and stability discrimination on the state measurement data set, generate measurement confidence label information, and associate the measurement confidence label information with the state measurement data set one by one to obtain a reliable state measurement dataset.

[0096] S2.1: Based on the time-series state measurement data in the state measurement dataset, the continuity of the change relationship of the running state measurement data corresponding to adjacent sampling time indices in the time dimension is determined to obtain continuity determination information.

[0097] Specifically, based on the time-series status measurement data with the power distribution box equipment identifier in the status measurement data set, the operation status measurement data corresponding to adjacent sampling time indices are selected in chronological order according to the sampling time index. The operation status measurement data corresponding to adjacent sampling time indices are compared item by item to check whether there are complete records of operation status measurement data between adjacent sampling time indices and whether the time sequence is not broken. This is to confirm whether the operation status measurement data maintains consistency and continuity without interruption or jump during the time process, thus forming continuity discrimination information.

[0098] S2.2: Based on the continuity discrimination information, the stability of the change amplitude of the operation status measurement data within the continuous sampling period is judged to obtain the stability discrimination information.

[0099] Specifically, based on continuity discrimination information, on the premise that the operation status measurement data is completely recorded in adjacent sampling periods, the operation status measurement data corresponding to adjacent sampling periods are compared period by period according to the sampling time index order to determine whether the recorded changes of the operation status measurement data between adjacent sampling periods are in a relatively consistent state and whether there is a situation where the stable change state changes into a sudden change state, thus forming stability discrimination information.

[0100] It should be noted that the transition from a stable state to a sudden state refers to the situation where, in the operational state measurement data corresponding to adjacent sampling periods, the original relationship of continuous and gradual changes in the same direction between adjacent state measurement data is broken, and instead, a change in direction and a sudden change in amplitude occurs within one sampling period.

[0101] S2.3: Based on the continuity discrimination information and stability discrimination information, the running status measurement data under the corresponding sampling time index is labeled to generate measurement confidence label information.

[0102] Specifically, based on continuity and stability discrimination information, the operational status measurement data under the corresponding sampling time index are mapped one-to-one with the continuity and stability discrimination information. When the continuity discrimination information indicates that the operational status measurement data record is complete and the stability discrimination information indicates that the changes in the operational status measurement data record are consistent, the operational status measurement data is assigned a high confidence label. When the continuity and stability discrimination information indicate that the operational status measurement data record has interruptions, abrupt changes in direction, or abrupt changes in amplitude, the operational status measurement data is assigned a low confidence label. The high confidence labels and low confidence labels are then uniformly organized according to the sampling time index order to form measurement confidence label information.

[0103] S2.4: Based on the state measurement data set, verify the consistency between the measurement confidence label information under the corresponding sampling time index and the execution time index of the running state measurement data to obtain associated candidate data.

[0104] Specifically, the running status measurement data in the status measurement data set is read one by one according to the sampling time index. The sampling time index carried by the running status measurement data is checked item by item with the sampling time index corresponding to the measurement confidence label information. If the sampling time index of the measurement confidence label information and the running status measurement data are completely consistent, the running status measurement data and the measurement confidence label information are paired and recorded to form associated candidate data.

[0105] S2.5: Based on the associated candidate data, the measurement confidence labeling information and the operation status measurement data are bound one by one to form associated data records.

[0106] Specifically, each piece of operational status measurement data in the associated candidate data is fixedly bound to the measurement confidence label information under the same sampling time index and recorded as the same data entry, so that the operational status measurement data and the measurement confidence label information maintain a one-to-one correspondence in the same record structure, forming an associated data record.

[0107] S2.6: Organize and encapsulate the associated data records sequentially according to the sampling time index to generate a reliable state measurement dataset.

[0108] Specifically, the associated data records are arranged one by one according to the order of the sampling time index. The associated data records with adjacent sampling time indices are integrated into a unified data sequence. All associated data records are then encapsulated as a whole while keeping the sampling time index order unchanged to form a reliable state measurement dataset.

[0109] S3. Construct a digital twin measurement model of the distribution box, and map the reliable state measurement dataset to the digital twin measurement model of the distribution box to perform continuous change relationship matching and response generation to obtain the simulation state feature sequence.

[0110] S3.1: Based on the trusted state measurement dataset, analyze the measurement channel information and its correspondence with the sampling time index of the running state measurement data during the acquisition process to form measurement mapping information.

[0111] Specifically, the corresponding measurement channel information is extracted from the operational status measurement data contained in the trusted state measurement dataset (the measurement channel information is recorded together with the operational status measurement data and stored in the state measurement data set when the operational status measurement data is collected). The measurement channel information is then matched with the sampling time index corresponding to the operational status measurement data, so that the operational status measurement data can clearly indicate the source position and sampling time index position in the same record structure, forming measurement mapping information that records the correspondence between measurement channel information and sampling time index.

[0112] S3.2: Based on the measurement mapping information, the measurement channels corresponding to the running status measurement data and their correspondence with the sampling time index are instantiated and configured, and time constraints consistent with the sampling time index are established to form a twin running structure.

[0113] Specifically, the measurement channel information recorded in the measurement mapping information is registered one by one with the corresponding sampling time index. The corresponding measurement channel position and sampling time index position are specified for each piece of operational status measurement data. The operational status measurement data are written into the same operational structure record according to the correspondence between the measurement channel position and the sampling time index position. The operational structure record is arranged according to the time order of the sampling time index so that the operational structure record is consistent with the sampling time index in the time dimension, forming a twin operational structure.

[0114] S3.3: Based on the trusted state measurement dataset, extract historical operating state samples within the stable operating range under the condition of consistent sampling time index.

[0115] Specifically, based on the reliable state measurement dataset, the operational state measurement data is continuously organized in the order of sampling time index. Within the sampling time index interval where the continuity discrimination information and stability discrimination information of the operational state measurement data are consistent, the operational state measurement data and corresponding sampling time index records of the corresponding sampling time index interval are selected as historical operational state samples. (For example, when the operational state measurement data maintains a consistent direction of change within consecutive sampling time index intervals, the corresponding interval record is the historical operational state sample.)

[0116] S3.4: Based on historical operating status samples, determine the correspondence between operating status measurement data and operating result records, and form a mapping relationship between status input and status response.

[0117] Specifically, based on historical operating status samples, the operating status measurement data corresponding to adjacent sampling time index positions in the historical operating status samples are organized accordingly, so that the operating status measurement data form a continuous change relationship record under the sampling time index order, and the continuous change relationship record is used as the correspondence between the operating status measurement data at different sampling time index positions, forming a mapping relationship between state input and state response.

[0118] S3.5: Embed the mapping relationship between state input and state response into the twin operation structure to generate a digital twin measurement model of the distribution box.

[0119] Specifically, in the twin operation structure, a one-to-one correspondence between the operation status measurement data and the measurement channel information is established according to the sampling time index sequence. The operation status measurement data under the corresponding sampling time index is written at each sampling time index position in the twin operation structure, so that the twin operation structure has both sampling time index constraints and measurement channel constraints. Based on the record of continuous change relationship between historical operation status samples and adjacent sampling time indices, a reusable time evolution correspondence rule is established for the operation status measurement data at adjacent sampling time index positions in the twin operation structure. The time evolution correspondence rule is bound to the corresponding position of the measurement channel information, so that the twin operation structure can generate corresponding response status data according to the record of continuous change relationship between adjacent sampling time indices during the sampling time index advancement process, forming a digital twin measurement model of the distribution box.

[0120] It should be noted that the training data for the digital twin measurement model of the distribution box comes from historical operating state samples obtained by organizing the trusted state measurement dataset in the order of sampling time index. The historical operating state samples are composed of operating state measurement data corresponding to adjacent sampling time index positions within a continuous sampling time index interval, and the correspondence between measurement channel information and sampling time index is retained. The loss function uses the difference between the response state data and the operating state measurement data of the historical operating state samples at the next sampling time index position as the objective. The differences of electrical operating state measurement data, thermal state measurement data and structural response state measurement data at their respective measurement channel information positions are normalized and then merged to ensure that the differences of different categories converge under a unified scale. The historical operating state samples are updated in segments according to the sampling time index order, and the time evolution correspondence rules are repeatedly corrected in multiple rounds within each segment. When the decrease of the loss function corresponding to multiple consecutive sampling time index intervals tends to stabilize, the update stops and the time evolution correspondence rules are solidified into the twin operating structure, thus completing the training of the digital twin measurement model of the distribution box.

[0121] S3.6: Based on the trusted state measurement dataset, write the operating state measurement data into the digital twin measurement model of the distribution box according to the sampling time index order to generate the corresponding simulation response data.

[0122] Specifically, according to the sampling time index order, the operating status measurement data at the corresponding sampling time index position in the trusted state measurement dataset is written into the digital twin measurement model of the distribution box at the position consistent with the measurement channel information to perform continuous change relationship matching. Based on the mapping relationship between state input and state response, response state data is generated at the corresponding sampling time index position to obtain simulation response data.

[0123] It should be noted that the simulation response data includes electrical state response data, thermal state response data, and structural response state data corresponding to the operating state measurement data. The electrical state response data consists of voltage response data, current response data, and power response data generated by the digital twin measurement model of the distribution box at the corresponding sampling time index position. The thermal state response data consists of temperature state response data at key heat-generating points (including circuit breaker contact connection points, busbar connection joints, cable inlet and outlet crimping points, and power device mounting bases that are prone to contact resistance and local heating). The structural response state data consists of displacement response data and vibration amplitude response data of the shell and internal support structure at the corresponding sampling time index position.

[0124] S3.7: Perform time-series processing and feature extraction on the simulation response data under each sampling time index to form a simulation state feature sequence.

[0125] Specifically, the simulation response data generated at each sampling time index position are arranged sequentially according to the order of the sampling time index. During the arrangement process, the electrical state response data, thermal state response data, and structural response state data corresponding to the electrical operation state measurement data, thermal state measurement data, and structural response state measurement data under each sampling time index are determined as simulation state features. The simulation state features corresponding to each sampling time index are written into the same sequence in the order of the sampling time index, so that the simulation state features form a continuous record in the time dimension, forming a simulation state feature sequence.

[0126] S4. Compare the trusted state measurement dataset with the simulation state feature sequence over time to determine the degree of continuous deviation of the trusted state measurement data from the simulation state features over time, and generate a measurement deviation index.

[0127] S4.1: According to the sampling time index, the running state measurement data in the credible state measurement dataset and the simulation state features in the simulation state feature sequence are time-aligned and organized to form a comparison data pair.

[0128] Specifically, according to the order of the sampling time index, the running state measurement data corresponding to each sampling time index in the trusted state measurement dataset is paired one by one with the simulation state features corresponding to the same sampling time index in the simulation state feature sequence. The corresponding running state measurement data and simulation state features are then combined and registered according to the sampling time index position, so that each sampling time index position forms a corresponding record containing running state measurement data and simulation state features. The corresponding records of each sampling time index position are arranged in the order of the sampling time index to form a comparison data pair.

[0129] S4.2: Based on the comparison data pairs, the time change relationship between the reliable state measurement data within the continuous sampling time index interval and the corresponding simulation state characteristics is compared to obtain the deviation measurement information.

[0130] Specifically, based on the comparison data pairs arranged in the order of sampling time index, two adjacent sampling time indices are selected to form a continuous sampling time index interval. Within the continuous sampling time index interval, the reliable state measurement data corresponding to each sampling time index position is compared with the simulation state features one by one according to the order of the sampling time index, and the differences between the reliable state measurement data and the simulation state features are recorded at the same sampling time index position. The differences of each sampling time index position within the continuous sampling time index interval are collected and organized according to the sampling time index order to form deviation measurement information.

[0131] S4.3: Based on deviation measurement information, calculate the degree of continuous deviation of the credible state measurement data from the simulation state characteristics, and generate the measurement deviation index.

[0132] Specifically, within the continuous sampling time index interval, the differences in the sampling time index positions in the deviation measurement information are uniformly arranged according to the sampling time index order. The operating state measurement data and simulation response data in the credible state measurement dataset are compared in terms of sampling time index and measurement channel dimension. The electrical deviation value between electrical operating state measurement data and electrical state response data, the thermal deviation value between thermal state measurement data and thermal state response data, and the structural deviation value between structural response state measurement data and structural response state data are calculated respectively. The deviation values ​​of each category are normalized and fused to generate a measurement deviation index.

[0133] The electrical deviation between the electrical operating condition measurement data and the electrical condition response data is calculated using the following expression:

[0134] ;

[0135] in, Indicates the first Electrical deviation value at each sampling time index position; , and Indicates the first Voltage measurement data, current measurement data, and power status measurement data at each sampling time index position; , and This represents the voltage response data, current response data, and power response data in the electrical state response data at the same sampling time index position. , and This indicates the rated voltage, rated current, and rated power specified by the manufacturer when the distribution box was manufactured. The variable with the subscript 'a' represents the sampling time index. In the formula, the variable with the subscript 'a' represents the data corresponding to the a-th sampling time index position.

[0136] The thermal deviation between the thermal state measurement data and the thermal state response data is calculated using the following expression:

[0137] ;

[0138] in, Indicates the first Thermal deviation value at each sampling time index position; This indicates the total number of key heat source locations; Indicates the location number of key heat-generating points, including circuit breaker contact connection points, busbar connection joints, cable inlet and outlet crimping points, and power device mounting bases; Indicates the first The first sampling time index Temperature measurement data at key heating points; Indicates the first The first sampling time index Thermal status response data of key heating points; For the first Reference values ​​for allowable temperature rise corresponding to key heating points.

[0139] The structural deviation between the measured structural response state data and the actual structural response state data is calculated using the following expression:

[0140] ;

[0141] in, Indicates the first Structural deviation values ​​at each sampling time index position; Indicates the first Displacement state measurement data under each sampling time index; Indicates the first Displacement response data under each sampling time index; Indicates the first Vibration amplitude state measurement data under each sampling time index; Indicates the first Vibration amplitude response data under each sampling time index; Indicates the allowable displacement reference value; This indicates the reference value for the permissible vibration amplitude.

[0142] It should be noted that the allowable temperature rise reference value is derived from the maximum allowable temperature rise limit specified for each key heat-generating point in the product technical manual and factory type test report of key components, which has been clearly defined and recorded during the equipment selection and factory inspection stages; the allowable displacement reference value is derived from the maximum allowable deformation limit specified in the structural design drawings and strength verification documents of the shell and internal support structure, and is confirmed in conjunction with the structural factory vibration test records; the allowable vibration amplitude reference value is derived from the maximum allowable vibration amplitude specified in the vibration resistance design index and vibration tolerance test results of the distribution box structure.

[0143] S5. Perform trend discrimination on the direction and magnitude of change of the measurement deviation index in the time dimension to form measurement evolution information.

[0144] S5.1: The measurement deviation index is continuously sorted according to the sampling time index order to form a time-series deviation index sequence.

[0145] Specifically, according to the order of the sampling time index in the sampling time index sequence, the measurement deviation index corresponding to each sampling time index position is sorted sequentially. Each sampling time index and its corresponding measurement deviation index are written into the same arrangement structure while maintaining the original correspondence. This makes the measurement deviation indexes arranged sequentially from small to large according to the sampling time index, forming a time-series deviation index sequence consistent with the sampling time index order.

[0146] S5.2: Based on the time-series deviation index sequence, the direction and magnitude of the change in the measurement deviation index within the continuous sampling time index interval are jointly judged to obtain trend discrimination information.

[0147] Specifically, the measurement deviation index corresponding to adjacent sampling time index positions in the time deviation index sequence is selected for segment-by-segment comparison. According to the advancing order of the sampling time index, the increase or decrease of the measurement deviation index relative to the previous sampling time index position in each adjacent sampling time index interval is recorded to determine the direction of change. At the same time, the difference of the measurement deviation index between the two sampling time index positions in the same adjacent sampling time index interval is recorded. By judging whether the difference in two or more consecutive adjacent sampling time index intervals increases or decreases, the change state of the change amplitude is determined. Intervals in two or more consecutive adjacent sampling time index intervals with the same change direction and no increase or decrease in change amplitude are uniformly summarized and identified to form trend discrimination information.

[0148] S5.3: Based on the trend discrimination information, summarize and label the evolution of the measurement deviation index over time to form measurement evolution information.

[0149] Specifically, based on the change direction and change magnitude indicators corresponding to each sampling time index interval in the trend discrimination information, the trend discrimination information of adjacent sampling time index intervals is continuously connected according to the sampling time index order. Sampling time index intervals where the change direction and change magnitude remain consistent are divided and marked as stable evolution stages, while sampling time index intervals where the change direction and change magnitude change are divided and marked as turning point evolution stages, thus forming measurement evolution information that reflects the change process of the measurement deviation index over time.

[0150] S6. Based on the changes in measurement evolution information and measurement reliability labeling information during operation, perform cross-constraint judgment on the current operating status of the low-voltage transformer distribution box and generate a distribution box status monitoring report.

[0151] S6.1: Based on the sampling time index, the measurement evolution information and measurement confidence labeling information are associated with the same index to form state evidence information.

[0152] Specifically, according to the sampling time index order, the evolution stage corresponding to each sampling time index position in the measurement evolution information is aligned and registered one by one with the confidence label corresponding to the same sampling time index position in the measurement confidence label information. Under the same sampling time index position, the evolution stage identifier and confidence label are combined and recorded, so that each sampling time index position forms a corresponding entry containing measurement evolution information and measurement confidence label information. All corresponding entries are arranged in order according to the sampling time index to form state evidence information.

[0153] S6.2: Based on the state evidence information, perform cross-constraint judgment on the consistency and constraint compliance of the changes in measurement evolution information and measurement confidence labeling information under the same sampling time index to obtain the operation state judgment information.

[0154] Specifically, based on the evolution stage identifier and confidence level label corresponding to each sampling time index position in the state evidence information, the evolution stage identifier and confidence level label under the same sampling time index position are compared and verified. When the evolution stage identifier is in a stable evolution stage and the confidence level label is a high confidence level label, the corresponding sampling time index position is marked as a stable operating state. When the evolution stage identifier is in a transitional evolution stage and the measurement confidence level label is a high confidence level label, the corresponding sampling time index position is marked as an abnormal operating state. When the measurement confidence level label is a low confidence level label, the corresponding sampling time index position is marked as an operating state to be confirmed. All the labeling results are arranged in the order of sampling time index to form the operating state determination information.

[0155] S6.3: Summarize and organize the operating status judgment information of the low-voltage transformer distribution box according to the sampling time index order, and generate a distribution box status monitoring report.

[0156] Specifically, according to the sampling time index order, the stable operating status, abnormal operating status, and pending confirmation operating status corresponding to each sampling time index position in the operating status determination information are arranged one by one. While keeping the sampling time index order unchanged, the operating status determination information corresponding to each sampling time index position is centrally collected with the measurement evolution information and measurement reliability labeling information corresponding to the same sampling time index position, so that each sampling time index position forms a complete record containing operating status determination information, measurement evolution information, and measurement reliability labeling information. All records are organized and presented in a unified manner according to the sampling time index order to generate a distribution box status monitoring report.

[0157] In summary, this invention introduces a collaborative mechanism between a reliable state measurement dataset and a digital twin measurement model during the distribution box status monitoring process. This allows the operational status assessment to no longer rely solely on the original measurement data but to be based on highly reliable data input constrained by the continuity and stability of measurement behavior. By mapping the reliable state measurement dataset to the digital twin measurement model to perform continuous change relationship matching and response generation, and quantifying the continuous deviation relationship between the actual measured state and the simulated state characteristics, the determination of the operational status can simultaneously reflect the theoretical evolution law under physical structure constraints and the real change characteristics in the actual operation process. This results in a status monitoring result with temporal continuity, evolutionary interpretability, and judgment consistency, effectively supporting the stable identification and long-term tracking of the operational status of low-voltage transformer distribution boxes.

[0158] Example 2

[0159] This invention provides another embodiment, which is a low-voltage transformer substation distribution box status monitoring device based on big data analysis, used to implement the steps of the low-voltage transformer substation distribution box status monitoring method based on big data analysis described in Embodiment 1, specifically including:

[0160] The data acquisition module is used to collect the operating status measurement data of the low-voltage transformer distribution box, and establish a sampling time index associated with the equipment identifier to form a status measurement data set;

[0161] The measurement behavior continuity and stability discrimination module is used to discriminate the measurement behavior continuity and stability of the state measurement data set, generate measurement confidence label information, and associate the measurement confidence label information with the state measurement data set one by one to obtain a reliable state measurement dataset.

[0162] The module is used to build a digital twin measurement model of the distribution box, map the reliable state measurement dataset to the digital twin measurement model of the distribution box, perform continuous change relationship matching and response generation, and obtain the simulation state feature sequence.

[0163] The comparison module is used to compare the trusted state measurement dataset with the simulation state feature sequence in time correspondence, determine the degree of continuous deviation of the trusted state measurement data from the simulation state features over time, and generate a measurement deviation index.

[0164] The execution trend discrimination module is used to discriminate the direction and magnitude of change of the measurement deviation index over time, thereby generating measurement evolution information.

[0165] The report generation module is used to perform cross-constraint judgments on the current operating status of the low-voltage transformer distribution box based on the changes in measurement evolution information and measurement confidence labeling information during operation, and generate a distribution box status monitoring report.

[0166] Example 3

[0167] The present invention provides another embodiment, which is a low-voltage transformer distribution box status monitoring device based on big data analysis, used to implement the steps of the low-voltage transformer distribution box status monitoring method based on big data analysis described in Embodiment 1.

[0168] The measurement behavior continuity and stability discrimination module is used to perform measurement behavior continuity and stability discrimination on the state measurement data set, generate measurement confidence labeling information, and associate the measurement confidence labeling information with each item in the state measurement data set to obtain a reliable state measurement dataset; specifically including:

[0169] S2.1: Based on the time-series state measurement data in the state measurement dataset, the continuity of the change relationship of the running state measurement data corresponding to adjacent sampling time indices in the time dimension is determined to obtain continuity determination information;

[0170] S2.2: Based on the continuity discrimination information, the stability of the change amplitude of the operation status measurement data within the continuous sampling period is judged to obtain the stability discrimination information;

[0171] S2.3: Based on the continuity discrimination information and stability discrimination information, the running status measurement data under the corresponding sampling time index is labeled to generate measurement confidence label information.

[0172] S2.4: Based on the state measurement data set, verify the consistency between the measurement confidence label information under the corresponding sampling time index and the execution time index of the running state measurement data to obtain associated candidate data;

[0173] S2.5: Based on the associated candidate data, the measurement confidence labeling information and the operation status measurement data are bound one by one to form associated data records;

[0174] S2.6: Organize and encapsulate the associated data records sequentially according to the sampling time index to generate a reliable state measurement dataset.

[0175] Example 4

[0176] Based on the same inventive concept, embodiments of the present invention also provide a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, it implements the steps of any one of the methods for monitoring the status of a low-voltage transformer substation based on big data analysis described in Embodiment 1 or 2.

[0177] Example 5

[0178] Based on the same inventive concept, this embodiment of the invention also provides a computer storage medium storing a computer program, which, when executed by a processor, implements the steps of any one of the methods for monitoring the status of a low-voltage transformer distribution box based on big data analysis as described in Embodiment 1 or 2.

[0179] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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.

[0180] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0181] 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 1The function specified in one or more boxes.

[0182] 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.

[0183] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis, characterized by: include: Collect operational status measurement data of low-voltage transformer distribution boxes, and establish a sampling time index associated with equipment identification to form a status measurement data set; The continuity and stability of the measurement behavior are judged on the state measurement data set, measurement confidence labeling information is generated, and the measurement confidence labeling information is associated with the state measurement data set one by one to obtain a reliable state measurement dataset; A digital twin measurement model of the distribution box is constructed, and a reliable state measurement dataset is mapped to the digital twin measurement model of the distribution box. Continuous change relationship matching and response generation are performed to obtain the simulation state feature sequence. The trusted state measurement dataset is compared with the simulation state feature sequence over time to determine the degree of continuous deviation of the trusted state measurement data from the simulation state features over time, and a measurement deviation index is generated. The direction and magnitude of the measurement deviation index over time are analyzed to determine the trend and form measurement evolution information. Based on the changes in measurement evolution information and measurement reliability labeling information during operation, cross-constraint judgments are performed on the current operating status of the low-voltage transformer distribution box, and a distribution box status monitoring report is generated.

2. The method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis according to claim 1, characterized in that: The process involves collecting operational status measurement data from low-voltage transformer distribution boxes and establishing a sampling time index associated with equipment identifiers to form a status measurement data set; including: Collect operational status measurement data of low-voltage transformer distribution boxes, including electrical operation status measurement data, thermal status measurement data, and structural response status measurement data; A unified measurement time reference is established and a continuous sampling time index is generated. The operation process of the distribution box is divided into continuous sampling periods to obtain a sampling time index sequence. Based on the sampling time index sequence, the operating status measurement data of the distribution box at the corresponding time in each sampling period is collected synchronously, and the operating status measurement data is time-aligned and associated with the corresponding sampling time index to form time-series status measurement data; The time-series status measurement data are associated one by one with the predetermined distribution box equipment identifiers, and continuously packaged according to the sampling time index order to generate a status measurement data set.

3. The method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis according to claim 1, characterized in that: The process involves determining the continuity and stability of measurement behavior in the state measurement data set, generating measurement confidence labeling information, and then associating the measurement confidence labeling information with each item in the state measurement data set to obtain a reliable state measurement dataset. include: Based on the time-series state measurement data in the state measurement dataset, the continuity of the change relationship of the running state measurement data corresponding to adjacent sampling time indices in the time dimension is determined to obtain continuity determination information; Based on the continuity discrimination information, the stability of the change amplitude of the operation status measurement data within the continuous sampling period is judged to obtain the stability discrimination information; Based on the continuity discrimination information and stability discrimination information, the running status measurement data under the corresponding sampling time index are labeled to generate measurement confidence label information; Based on the state measurement data set, the consistency of the measurement confidence label information under the corresponding sampling time index and the execution time index of the running state measurement data is verified to obtain the associated candidate data; Based on the associated candidate data, the measurement confidence labeling information and the operational status measurement data are bound one by one to form associated data records; The associated data records are continuously organized and packaged according to the sampling time index order to generate a reliable state measurement dataset.

4. The method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis according to claim 1, characterized in that: The process involves constructing a digital twin measurement model of the distribution box, mapping a reliable state measurement dataset to the digital twin measurement model of the distribution box, performing continuous change relationship matching and response generation, and obtaining a simulation state feature sequence. include: Based on the trusted state measurement dataset, the measurement channel information and its correspondence with the sampling time index of the operation state measurement data during the acquisition process are analyzed to form measurement mapping information; Based on the measurement mapping information, the measurement channels corresponding to the operation status measurement data and their correspondence with the sampling time index are instantiated and configured, and time constraints consistent with the sampling time index are established to form a twin operation structure. Based on the trusted state measurement dataset, historical operating state samples within the stable operating range are extracted under the condition that the sampling time index is consistent. Based on historical operational status samples, the correspondence between operational status measurement data and operational result records is determined, forming a mapping relationship between status input and status response; The mapping relationship between state input and state response is embedded in the twin operation structure to generate a digital twin measurement model of the distribution box; Based on the trusted state measurement dataset, the operating state measurement data is written into the digital twin measurement model of the distribution box according to the sampling time index order to generate the corresponding simulation response data; The simulation response data under each sampling time index are processed by time sequence and feature extraction to form a simulation state feature sequence.

5. The method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis according to claim 1, characterized in that: The step of comparing the reliable state measurement dataset with the simulation state feature sequence over time to determine the degree of continuous deviation of the reliable state measurement data from the simulation state features over time and generating a measurement deviation index includes: Based on the sampling time index, the running state measurement data in the trusted state measurement dataset and the simulation state features in the simulation state feature sequence are time-aligned and organized to form comparison data pairs. Based on the comparison data pairs, the time change relationship between the reliable state measurement data within the continuous sampling time index interval and the corresponding simulation state characteristics is compared to obtain the deviation measurement information. Based on deviation metric information, the degree of continuous deviation of the reliable state measurement data from the simulated state characteristics is calculated, generating a measurement deviation index; including: The electrical deviation between the electrical operating condition measurement data and the electrical condition response data is calculated using the following formula: ； in, Indicates the first Electrical deviation value at each sampling time index position; , and Indicates the first Voltage measurement data, current measurement data, and power status measurement data at each sampling time index position; , and This represents the voltage response data, current response data, and power response data in the electrical state response data at the same sampling time index position. , and This indicates the rated voltage, rated current, and rated power specified by the manufacturer when the distribution box was manufactured. Indicates the sampling time index; The thermal deviation between the thermal state measurement data and the thermal state response data is calculated using the following formula: ； in, Indicates the first Thermal deviation value at each sampling time index position; This indicates the total number of key heat source locations; Indicates the location number of key heat-generating points, including circuit breaker contact connection points, busbar connection joints, cable inlet and outlet crimping points, and power device mounting bases; Indicates the first The first sampling time index Temperature measurement data at key heating points; Indicates the first The first sampling time index Thermal status response data of key heating points; Indicates the first Reference values ​​for allowable temperature rise corresponding to the locations of key heating points; The structural deviation between the measured structural response state data and the actual structural response state data is calculated using the following formula: ; in, Indicates the first Structural deviation values ​​at each sampling time index position; Indicates the first Displacement state measurement data under each sampling time index; Indicates the first Displacement response data under each sampling time index; Indicates the first Vibration amplitude state measurement data under each sampling time index; Indicates the first Vibration amplitude response data under each sampling time index; Indicates the allowable displacement reference value; This indicates the reference value for the permissible vibration amplitude.

6. The method for monitoring the status of low-voltage transformer distribution boxes based on big data analysis according to claim 1, characterized in that: The process of determining the trend of the change direction and magnitude of the measurement deviation index over time is used to form measurement evolution information; including: The measurement deviation indexes are continuously organized according to the sampling time index order to form a time-series deviation index sequence; Based on the time-series deviation index sequence, the direction and magnitude of the change in the measurement deviation index within the continuous sampling time index interval are jointly judged to obtain trend discrimination information; Based on trend discrimination information, the evolution of the measurement deviation index over time is summarized and identified to form measurement evolution information; The process involves performing cross-constraint judgments on the current operating status of the low-voltage transformer distribution box based on changes in measurement evolution information and measurement reliability labeling information during operation, and generating a distribution box status monitoring report; including: Based on the sampling time index, the measurement evolution information and measurement confidence labeling information are correlated with the same index to form state evidence information; Based on the state evidence information, cross-constraint judgment is performed on the consistency and constraint compliance of the changes in measurement evolution information and measurement confidence labeling information under the same sampling time index to obtain the operation state determination information; The operating status information of the low-voltage transformer distribution boxes is summarized and organized according to the sampling time index order, and a distribution box status monitoring report is generated.

7. A low-voltage transformer substation distribution box status monitoring device based on big data analysis, used to implement the steps of the low-voltage transformer substation distribution box status monitoring method based on big data analysis as described in any one of claims 1-6, characterized in that: include: The data acquisition module is used to collect the operating status measurement data of the low-voltage transformer distribution box, and establish a sampling time index associated with the equipment identifier to form a status measurement data set; The measurement behavior continuity and stability discrimination module is used to discriminate the measurement behavior continuity and stability of the state measurement data set, generate measurement confidence label information, and associate the measurement confidence label information with the state measurement data set one by one to obtain a reliable state measurement dataset. The module is used to build a digital twin measurement model of the distribution box, map the reliable state measurement dataset to the digital twin measurement model of the distribution box, perform continuous change relationship matching and response generation, and obtain the simulation state feature sequence. The comparison module is used to compare the trusted state measurement dataset with the simulation state feature sequence in time correspondence, determine the degree of continuous deviation of the trusted state measurement data from the simulation state features over time, and generate a measurement deviation index. The execution trend discrimination module is used to discriminate the direction and magnitude of change of the measurement deviation index over time, thereby generating measurement evolution information. The report generation module is used to perform cross-constraint judgments on the current operating status of the low-voltage transformer distribution box based on the changes in measurement evolution information and measurement confidence labeling information during operation, and generate a distribution box status monitoring report.

8. The low-voltage transformer distribution box status monitoring device based on big data analysis according to claim 7, characterized in that: The measurement behavior continuity and stability discrimination module is used to perform measurement behavior continuity and stability discrimination on the state measurement data set, generate measurement confidence label information, and associate the measurement confidence label information with the state measurement data set one by one to obtain a reliable state measurement dataset. include: Based on the time-series state measurement data in the state measurement dataset, the continuity of the change relationship of the running state measurement data corresponding to adjacent sampling time indices in the time dimension is determined to obtain continuity determination information; Based on the continuity discrimination information, the stability of the change amplitude of the operation status measurement data within the continuous sampling period is judged to obtain the stability discrimination information; Based on the continuity discrimination information and stability discrimination information, the running status measurement data under the corresponding sampling time index are labeled to generate measurement confidence label information; Based on the state measurement data set, the consistency of the measurement confidence label information under the corresponding sampling time index and the execution time index of the running state measurement data is verified to obtain the associated candidate data; Based on the associated candidate data, the measurement confidence labeling information and the operational status measurement data are bound one by one to form associated data records; The associated data records are continuously organized and packaged according to the sampling time index order to generate a reliable state measurement dataset.

9. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the low-voltage transformer distribution box status monitoring method based on big data analysis as described in any one of claims 1-6.

10. A computer storage medium, characterized in that: The computer storage medium contains a computer program, which, when executed by a processor, implements the steps of the low-voltage transformer distribution box status monitoring method based on big data analysis as described in any one of claims 1-6.

Images