Cable branch box-based online operation monitoring system and method

Abstract

The application discloses an online operation monitoring system and method based on a cable branch box, and relates to the technical field of power monitoring.The system performs online operation monitoring on multiple parameters of the cable branch box, accurately identifies whether the cable branch box has dominant operation abnormalities, effectively avoids sudden failures, and after eliminating the dominant abnormalities, relies on a digital twin body constructed by a cable branch box simulation monitoring model to perform long-term trend simulation on progressive and implicit defects such as busbar deformation and conductor creep, performs dynamic similarity analysis on historical data and simulation data by tracing the monitoring unified value system, amplifies early weak abnormal signals and quantifies them into identifiable risk indexes, relies on the digital twin model to simulate the long-term trend of the progressive and implicit defects, combines the dynamic similarity analysis to quantify the risk indexes, realizes the leap from "passive maintenance" to "active prevention", and improves the reliability and operation and maintenance efficiency of the distribution network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power monitoring, more particularly, it relates to an online operation monitoring system and method based on a cable branch box. BACKGROUND

[0002] With the expansion of the power distribution network and the upgrading of intelligence, the cable branch box as the core node of power distribution directly affects the safety of the power grid and the quality of power supply. The traditional operation and maintenance mode highly depends on manual inspection and periodic detection, which has the following technical bottlenecks:

[0003] 1. Lack of prediction ability for hidden defects: The gradual defects such as busbar deformation and conductor creep have long-term latency, and the traditional monitoring lacks dynamic tracking ability for the deterioration of material mechanical properties. Such defects only produce weak signals (such as nanoscale deformation and micro-strain changes) in the early stage, and the conventional threshold alarm mechanism is difficult to capture, leading to the gradual accumulation of hidden dangers until a major accident occurs.

[0004] 2. Limitation of passive maintenance mode: The current "fault-repair" mode leads to long time of equipment operation with defects, and the allocation of operation and maintenance resources depends on manual experience. In recent years, digital twin technology has made breakthroughs in the field of industrial equipment health management, but its application in power equipment still faces challenges such as insufficient model accuracy and low data fusion. The existing digital twin of power equipment focuses on static simulation, lacks dynamic simulation ability for gradual deterioration process, and does not establish a quantitative mapping mechanism between monitoring data and simulation results, leading to lag and misjudgment in risk warning.

[0005] In view of the above problems, the present application innovatively provides an online operation monitoring system and method based on a cable branch box. SUMMARY

[0006] In view of the deficiencies in the prior art, the purpose of the present application is to provide an online operation monitoring system and method based on a cable branch box.

[0007] To achieve the above purpose, the present application provides the following technical solutions:

[0008] The online operation monitoring system based on the cable branch box comprises

[0009] The explicit operation anomaly monitoring module periodically updates the online operation monitoring data set for the cable branch box during the operation of the cable branch box, and further determines whether the cable branch box has an explicit operation anomaly problem.

[0010] The possible operation anomaly monitoring module determines whether the cable branch box has a possible operation anomaly problem after determining that the cable branch box does not have an explicit operation anomaly problem.

[0011] Further, the periodic updating step of the online operation monitoring data set of the cable branch box is as follows: periodically collecting each operation monitoring data generated by the cable branch box in a period, and integrating each generated operation monitoring data into the online operation monitoring data set in a set manner.

[0012] Further, the determination step of whether the cable branch box has a dominant operation abnormality problem is as follows: obtaining the online operation monitoring data set of the cable branch box, importing the online operation monitoring data set into the dominant operation analysis model, and exporting a dominant operation abnormality value by the dominant operation analysis model; when the dominant operation abnormality value is higher than a dominant operation abnormality threshold value, it is determined that the cable branch box has a dominant operation abnormality problem.

[0013] Further, the determination of whether the cable branch box has a possible operation abnormality problem is as follows: collecting N online operation monitoring data sets of the cable branch box updated continuously before, sorting the N online operation monitoring data sets in the order of generation, and marking each online operation monitoring data set with a digital serial number; building a cable branch box simulation monitoring model, controlling the cable branch box simulation monitoring model to perform simulation monitoring under various progressive hidden defects, further determining a trace monitoring uniform value of the various progressive hidden defects, and when the trace monitoring uniform value of the progressive hidden defects is higher than a trace monitoring uniform threshold value, it is determined that the cable branch box may have a possible operation abnormality problem for the progressive hidden defects.

[0014] Further, the determination step of a trace monitoring uniform value of a progressive hidden defect is as follows: selecting a progressive hidden defect, determining hidden defect parameters related to the progressive hidden defect, further determining parameter ranges of the hidden defect parameters, further randomly generating a plurality of possible hidden defect parameters, obtaining an update data similarity value of each possible hidden defect parameter, performing sum-of-means calculation on the update data similarity value of each possible hidden defect parameter, and calculating the trace monitoring uniform value of the progressive hidden defect.

[0015] Further, the acquisition step of the update data similarity value of the possible hidden defect parameter is as follows: selecting a possible hidden defect parameter, importing the possible hidden defect parameter into the cable branch box simulation monitoring model, controlling the cable branch box simulation monitoring model to perform operation monitoring simulation for N-1 periods, collecting N online operation monitoring data sets generated by the cable branch box simulation monitoring model in N-1 periods after the operation monitoring simulation ends, sorting the N online operation monitoring data sets in the order of generation, marking each online operation monitoring data set with a digital serial number, further determining a data set similarity of each digital serial number, calculating a set comparison gap degree and an average set comparison gap degree, performing ratio calculation on the average set similarity and the average set comparison gap degree, and calculating the update data similarity value of the possible hidden defect parameter.

[0016] Further, the sum of the data set similarity of all digital serial numbers is calculated, the average set similarity is calculated, the absolute difference value of all data set similarities of digital serial numbers is calculated, the set contrast gap degree is calculated, and the sum of all set contrast gap degrees is calculated, and the average set contrast gap degree is calculated.

[0017] Further, the online operation monitoring method based on the cable branch box is as follows:

[0018] Step one: online monitoring and collection of cable branch box operation data;

[0019] Step two: monitoring of explicit operation abnormal problems;

[0020] Step three: monitoring of possible operation abnormal problems.

[0021] Compared with the prior art, the present application has the following beneficial effects:

[0022] The system of the present application accurately identifies whether there is an explicit operation abnormality in the cable branch box through online operation monitoring of multiple parameters of the cable branch box, effectively avoids sudden failures, and after eliminating the explicit abnormality, the system relies on the digital twin body constructed by the cable branch box simulation monitoring model to simulate the long-term trend of progressive hidden defects such as busbar deformation and conductor creep, and through dynamic similarity analysis of historical data and simulation data by tracing the monitoring unified value system, early weak abnormal signals are amplified and quantified into identifiable risk indicators.

[0023] The method of the present application accurately identifies the explicit abnormality of the cable branch box through multi-parameter online monitoring to avoid sudden failures, relies on the digital twin model to simulate the long-term trend of progressive hidden defects, and combines dynamic similarity analysis to quantify risk indicators, realizing the leap from "passive maintenance" to "active prevention", and improving the reliability and operation efficiency of the distribution network. BRIEF DESCRIPTION OF DRAWINGS

[0024] Fig. 1 The figure is the principle diagram of the system of the present application;

[0025] Fig. 2 The figure is the determination flow chart of the tracing monitoring unified value of the progressive hidden defect. DETAILED DESCRIPTION

[0026] Example 1: as Figs. 1-2 , the online operation monitoring system based on the cable branch box includes an explicit operation abnormality monitoring module and a possible operation abnormality monitoring module.

[0027] The dominant operation abnormality monitoring module periodically updates the online operation monitoring data set of the cable branch box during the operation of the cable branch box (the periodic time period is set according to the actual monitoring standard and the degree of detail of the cable branch box), and further determines whether the cable branch box has a dominant operation abnormality problem.

[0028] The periodic updating step of the online operation monitoring data set of the cable branch box is as follows: periodically collecting various operation monitoring data generated by the cable branch box in a period (the operation monitoring data includes but is not limited to the following: current of each branch circuit, bus voltage, partial discharge parameter, vibration parameter, temperature parameter, and the above operation monitoring data is collected by the corresponding type of sensor arranged in the cable branch box), and integrating the generated various operation monitoring data into an online operation monitoring data set in a set manner.

[0029] The determination step of whether the cable branch box has a dominant operation abnormality problem is as follows: obtaining the online operation monitoring data set of the cable branch box, importing the online operation monitoring data set into the dominant operation analysis model, and the dominant operation analysis model outputs a dominant operation abnormality value. When the dominant operation abnormality value is higher than the dominant operation abnormality threshold value (otherwise, it is determined that the cable branch box does not have a dominant operation abnormality problem, and the dominant operation abnormality threshold value is comprehensively set in combination with the training result of the dominant operation analysis model), it is determined that the cable branch box has a dominant operation abnormality problem.

[0030] The building step of the dominant operation analysis model is as follows: collecting a plurality of online operation monitoring data sets of the cable branch box, building a deep learning model, taking the online operation monitoring data set as the basis data, training the built deep learning model, in this process, each online operation monitoring data set is assigned a dominant operation abnormality value, the value range of the dominant operation abnormality value is set between 0 and 50, and the size of the dominant operation abnormality value has a clear meaning. The larger the value is, the more abnormal the data performance of the corresponding online operation monitoring data set is, that is, the higher the abnormality degree of the cable branch box is, then the plurality of online operation monitoring data sets are divided into a training set, a validation set and a test set according to a certain proportion, and the specific division proportion is determined as 60%:20%:20%. Stratified sampling is used to ensure that the DBV distribution of each subset is consistent: the cumulative distribution function (CDF) of the DBV of the whole sample is calculated, the deep learning model is repeatedly trained using the training set, the performance in the training stage is verified by means of the validation set, the parameters of the model are adjusted in time according to the verification result, hyperparameter tuning, overfitting prevention and training monitoring are adopted, the test set which does not participate in the training is used to evaluate the final model, and the result is ensured not to rely on data peeking in the training process; scene verification is performed, and finally the dominant operation analysis model is built.

[0031] When it is determined that there is no obvious operation abnormality problem in the cable branch box (immediately handle the obvious operation abnormality problem of the cable branch box when it is determined that there is an obvious operation abnormality problem in the cable branch box), it is determined whether the cable branch box has a possible operation abnormality problem.

[0032] The determination of whether the cable branch box has a possible operation abnormality problem is as follows: collecting N sets of online operation monitoring data of the cable branch box that are continuously updated before (the collected online operation monitoring data include the latest updated online operation monitoring data), sorting the N sets of online operation monitoring data according to the order of generation, and labeling each set of online operation monitoring data with a digital serial number (the digital serial number is 1, 2, …, N), building a cable branch box simulation monitoring model, and controlling the cable branch box simulation monitoring model to perform simulation monitoring under various progressive hidden defects (progressive hidden defects include but are not limited to the following: bus deformation, conductor creep, and insulator micro-cracks. Progressive hidden defects are difficult to be monitored for abnormalities during the operation of the cable branch box, have the characteristics of long incubation period and weak early signals, and are usually discovered through long-term monitoring), further determining the trace monitoring unified value of various progressive hidden defects, and when the trace monitoring unified value of the progressive hidden defects is higher than the trace monitoring unified threshold value (the trace monitoring unified threshold value is set based on historical data analysis), it is determined that the cable branch box may have a possible operation abnormality problem (if the trace monitoring unified value of various progressive hidden defects is not higher than the trace monitoring unified threshold value, it is determined that the cable branch box has no possible operation abnormality problem. If there is a possible operation abnormality problem of the cable branch box for the progressive hidden defects, the cable branch box is immediately detected for the progressive hidden defects).

[0033] The determination of the trace monitoring unified value of a progressive hidden defect is as follows: selecting a progressive hidden defect, determining the hidden defect parameters related to the progressive hidden defect, further determining the parameter range of each hidden defect parameter (taking bus deformation as an example, the hidden defect parameters related to bus deformation include bus curvature radius and stress, the parameter range of the bus curvature radius is 5m≥R>2.75m, and the parameter range of the stress is 60MPa≤σ<100MPa), further randomly generating a plurality of possible hidden defect parameters (each possible hidden defect parameter is different, taking bus deformation as an example, a possible hidden defect parameter can be generated by randomly selecting values within the parameter range of the bus curvature radius and the parameter range of the stress), obtaining the update data similarity value of each possible hidden defect parameter, performing sum-mean calculation on the update data similarity value of each possible hidden defect parameter, and calculating the trace monitoring unified value of the progressive hidden defect.

[0034] The acquisition step of the update data similarity value of the possible hidden defect parameter is as follows: a possible hidden defect parameter is selected, the possible hidden defect parameter is introduced into the cable branch box simulation monitoring model, the cable branch box simulation monitoring model is controlled to perform N-1 cycle operation monitoring simulation, after the operation monitoring simulation is completed, N online operation monitoring data sets generated by the cable branch box simulation monitoring model in N-1 cycles are collected, the N online operation monitoring data sets are sorted according to the generation order, and each online operation monitoring data set is marked with a digital serial number (the digital serial number is 1, 2, …, N), the data set similarity of each digital serial number is further determined, the data set similarity of all digital serial numbers is summed and averaged to calculate the average set similarity, the data set similarity of all digital serial numbers is calculated by two-by-two absolute difference value to calculate the set comparison gap degree, the set comparison gap degree of all sets is summed and averaged to calculate the average set comparison gap degree (when the average set comparison gap degree is actually 0, the average set comparison gap degree is adjusted to a positive number close to 0, such as 0.1), the average set similarity and the average set comparison gap degree are calculated by ratio to calculate the update data similarity value of the possible hidden defect parameter.

[0035] The determination step of the data set similarity of one digital serial number is as follows: two online operation monitoring data sets of the same digital serial number are selected (one is an online operation monitoring data set for the cable branch box, and the other is an online operation monitoring data set for the cable branch box simulation monitoring model), one of the online operation monitoring data sets is vectorized and converted into a vector A=(a i ,a i ,...,a I ), I is the total number of operation monitoring data, the other online operation monitoring data set is vectorized and converted into a vector B=(b i ,b i ,...,b I ), The data set similarity of the digital serial number is calculated.

[0036] The building step of the cable branch box simulation monitoring model is as follows: the cable branch box is disassembled into core components such as the box body, cable joint, insulator, bus, and lightning arrester, and the secondary structures such as bolts are ignored to simplify the calculation (such as the cable joint: hierarchical modeling (conductor layer, insulation layer, shielding layer) is adopted, and the actual size is referred to), the assembly relationship is defined (the joint is connected with the bus through bolts, and the contact resistance (initial value 100 μΩ) is set in the contact area), the material properties are defined (such as the component is a bus, the material is copper, the electrical conductivity is set to 5.96×10 7 S / m, the thermal conductivity is set to 401 W / (m·K), and the thermal expansion coefficient is set to 17×10 -6 / ℃), symmetry utilization (symmetry plane setting: 1 / 2 modeling of the branch box, symmetry plane with electrical / thermal / mechanical symmetry boundary conditions, reducing the amount of calculation; contact area simplification: joint and bus connection is simulated by contact pair, with friction coefficient 0.2 and contact stiffness 1x10 9 N / m 3 ), multi-physics field coupling setting (such as electromagnetic-thermal-mechanical coupling process electromagnetic module (AC / DC interface): applying rated current (such as 630A) to the conductor, calculating the joule heat (Q=I 2 R). The surface of the insulator is set to have an electric field strength threshold (such as 20kV / mm) to trigger the partial discharge criterion. The thermal module (solid heat transfer interface): coupling the heat source of the electromagnetic module, calculating the temperature distribution. The surface of the box is set to have a natural convection boundary (convection coefficient 10W / (m 2 ·K)), and the ambient temperature is 25℃. The mechanical module (solid mechanics interface): coupling thermal expansion effect (thermal expansion coefficient of copper 17x10 -6 / ℃), calculating thermal stress. The joint bolt is pre-tightened (such as 500N) to simulate mechanical fastening, meshing is performed (local encryption: tetrahedral mesh is used in key positions such as joint contact area and insulator umbrella skirt edge, size 0.5-2mm; global mesh: swept mesh is used in other areas, size 5-10mm, total number of units controlled within 500,000), solver is set, finally, through model verification and optimization, the cable branch box simulation monitoring model is built.

[0037] The above system performs online operation monitoring on multiple parameters of the cable branch box, accurately identifies whether there is a dominant operation abnormality in the cable branch box, effectively avoids sudden failure, and after eliminating the dominant abnormality, the system relies on the digital twin body built by the cable branch box simulation monitoring model to simulate the long-term trend of gradual and implicit defects such as busbar deformation and conductor creep, and through dynamic similarity analysis of historical data and simulation data by tracing the monitoring unified value system, early weak abnormal signals are amplified and quantified into identifiable risk indicators.

[0038] Embodiment 2: An online operation monitoring method based on a cable branch box, the method being as follows:

[0039] Step one: online monitoring and collection of cable branch box operation data;

[0040] Step two: monitoring of dominant operation abnormality problems;

[0041] Step three: monitoring of possible operation abnormality problems.

[0042] The method accurately identifies the explicit abnormalities of the cable branch box through multi-parameter online monitoring to avoid sudden failures, relies on a digital twin model to simulate the long-term trend of gradual implicit defects, and combines dynamic similarity analysis to quantify risk indicators, realizing the leap from "passive maintenance" to "active prevention", and improving the reliability and operation efficiency of the distribution network.

[0043] The above formulas are dimensionless values calculated, the formulas are obtained by collecting a large amount of data to simulate a formula of the most recent real situation, and the preset parameters in the formulas are set by a person skilled in the art according to actual conditions.

[0044] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0045] It should be understood that the size of the sequence number of each process described above in various embodiments of the present application does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0046] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0047] Those skilled in the art can clearly understand the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments for the convenience and brevity of description, which will not be repeated here.

[0048] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0049] The above describes only the specific embodiments of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An online operation monitoring system based on cable branch boxes, characterized in that, include The explicit operational anomaly monitoring module regularly updates the online operational monitoring dataset for the cable branch box during its operation to further determine whether there are any explicit operational anomalies in the cable branch box. The abnormal operation monitoring module may determine whether there are any potential abnormal operation problems in the cable branch box after determining that there are no obvious abnormal operation problems in the cable branch box. To determine whether a cable branch box may have operational anomalies, the following steps are taken: Collect N consecutively updated online operation monitoring datasets for the cable branch box, sort these datasets according to their generation order, and label each dataset with a numerical sequence number. Build a simulation monitoring model for the cable branch box, and control this model to simulate monitoring under various progressive latent defects. Further determine the unified traceability monitoring values ​​for each progressive latent defect. If the unified traceability monitoring value for a progressive latent defect is higher than the unified traceability monitoring threshold, it is determined that the cable branch box may have operational anomalies related to that progressive latent defect. The steps for determining a unified value for the traceability monitoring of a progressive latent defect are as follows: Select a progressive latent defect, determine the latent defect parameters involved in the progressive latent defect, further determine the parameter range of each latent defect parameter, further randomly generate multiple possible latent defect parameters, obtain the updated data similarity value of each possible latent defect parameter, sum and average the updated data similarity values ​​of each possible latent defect parameter, and calculate the unified value for the traceability monitoring of the progressive latent defect. The steps for obtaining the updated data similarity value of a potential latent defect parameter are as follows: Select a potential latent defect parameter, import the potential latent defect parameter into the cable branch box simulation monitoring model, control the cable branch box simulation monitoring model to perform N-1 cycles of operation monitoring simulation, after the operation monitoring simulation ends, collect N online operation monitoring datasets generated by the cable branch box simulation monitoring model within N-1 cycles, sort the N online operation monitoring datasets according to the order of generation, and label each online operation monitoring dataset with a numerical sequence number, further determine the data set similarity of each numerical sequence number, calculate the set comparison difference degree and the average set comparison difference degree, calculate the ratio of the average set similarity degree and the average set comparison difference degree, and calculate the updated data similarity value of the potential latent defect parameter. The average set similarity is calculated by summing and averaging the similarities of all sets of numerical indices. The set comparison difference is calculated by pairwise absolute differences of the similarities of all sets of numerical indices. The average set comparison difference is calculated by summing and averaging the comparison differences of all sets.

2. The online operation monitoring system based on cable branch boxes according to claim 1, characterized in that, The steps for regularly updating the online operation monitoring dataset of cable branch boxes are as follows: Regularly collect various operation monitoring data generated by the cable branch boxes within a cycle, and integrate the generated operation monitoring data into an online operation monitoring dataset in a set manner.

3. The online operation monitoring system based on cable branch boxes according to claim 1, characterized in that, The steps for determining whether there is a visible operational anomaly in a cable branch box are as follows: obtain the online operation monitoring dataset of the cable branch box, import the online operation monitoring dataset into the visible operation analysis model, the visible operation analysis model derives a visible operational anomaly value, and when the visible operational anomaly value is higher than the visible operational anomaly threshold, it is determined that there is a visible operational anomaly in the cable branch box.

4. An online operation monitoring method based on cable branch boxes, applied to the online operation monitoring system based on cable branch boxes as described in any one of claims 1-3, characterized in that, The method is as follows: Step 1: Online monitoring and collection of cable branch box operation data; Step Two: Monitoring for Obvious Operational Anomalies; Step 3: Monitor for potential operational anomalies.

Images