Zone area line loss anomaly analysis method based on segmented metering mode and related device

Abstract

The invention belongs to the technical field of low-voltage power distribution networks, and discloses a transformer area line loss anomaly analysis method based on a segmented metering mode and a related device.A transformer area anomaly reason is preliminarily diagnosed through a pre-trained line loss anomaly analysis model: after a power grid structure and meteorological parameters of a transformer area to be analyzed are input, the model outputs a line loss preliminary conclusion; if the result is fuzzy judgment, starting a step-by-step sectional metering method, in the first level, comparing the power supply quantity and the power sale quantity of each branch under the transformer outlet bus by group, and if the difference value exceeds a preset first threshold value, marking an abnormal branch group, terminating the detection of the level, and turning to a second level; and the second level repeatedly compares the sub-branch groups of the abnormal branch group, accurately locates the fault point, and finally locks the minimum abnormal unit. According to the method, through dynamic threshold management and grouping progressive detection, closed-loop analysis from model inference to physical troubleshooting is realized, and efficiency and precision of transformer area line loss anomaly analysis are both considered.

Description

Technical Field

[0001] The present invention belongs to the technical field of low-voltage distribution networks, and specifically relates to the field of line loss anomaly analysis, and in particular to a substation line loss anomaly analysis method based on a segmented metering mode and related devices. Background Art

[0002] In modern power systems, low-voltage distribution networks, as a critical link directly serving a vast number of users, exhibit significant structural complexity, encompassing numerous branches. Low-voltage distribution networks play a crucial role in the overall power supply system, responsible for efficiently and stably distributing electricity to various users. However, line loss has long been a key challenge plaguing the efficient operation of low-voltage distribution networks. Abnormal line loss not only triggers a series of safety hazards and threatens the stable operation of the power system, but also severely impacts the economic benefits of power companies, leading to unnecessary waste of power resources and increased operating costs. At the same time, with the rapid development of society and the economy, various industries are placing increasingly high demands on the stability and reliability of power supply, making the effective reduction of line loss a critical issue that urgently needs to be addressed in the power sector.

[0003] Currently, abnormal line losses in low-voltage distribution networks are caused by a variety of factors, with power theft, leakage, and inaccurate metering being particularly prominent. Traditional methods for detecting and analyzing these line losses have exposed numerous drawbacks. For example, leakage detection primarily relies on manual line inspections, a highly inefficient approach that is susceptible to subjective factors and various limitations, such as geographical conditions, making it difficult to comprehensively and promptly identify potential leakage hazards. Furthermore, traditional line loss analysis methods are relatively simplistic, often considering only a limited number of dimensions and failing to comprehensively and systematically analyze complex line loss scenarios. Furthermore, regional differences in power grid structure, meteorological conditions, and electricity usage habits make traditional technologies difficult to fully account for these regional characteristics. Consequently, in practical applications, the accuracy and effectiveness of line loss analysis are significantly compromised, making it unable to meet the growing demand for refined management.

[0004] It can be seen that the traditional method of analyzing abnormal line loss in substations has the problems of poor analysis accuracy and low analysis efficiency. Summary of the Invention

[0005] The present invention provides a method and related device for analyzing line loss anomalies in a substation based on a segmented metering mode. The method can comprehensively consider the regional characteristics, grid structure and meteorological parameters of the substation, and combine with large model reasoning technology to accurately and efficiently analyze the abnormal line loss situation in the substation.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A method for analyzing abnormal line loss in a transformer area based on a segmented metering mode includes: Input the grid structure and meteorological parameters of the substation to be analyzed into a pre-trained line loss anomaly analysis model to output preliminary line loss causes; the line loss anomaly analysis model is trained based on historical actual line loss causes, historical grid structure, and historical meteorological parameters; If the initial cause of line loss is ambiguous, use the step-by-step section measurement method to locate the abnormal line and fault point, including: In the first-level circuit, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process is cyclically executed for the next group of branches until the comparison result exceeds the first threshold range; if the comparison result exceeds the first threshold range, the current group of branches is regarded as an abnormal group of branches and the second-level circuit measurement is completed, and the first-level circuit measurement is terminated; In the second-level circuit, the actual power supply corresponding to each group of sub-branches is compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches is cyclically executed until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches is regarded as an abnormal group of sub-branches and abnormal line inspection is carried out to locate the abnormal line and fault point in the substation to be analyzed; Among them, the substation lines are pre-divided into two levels. The first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

[0007] Furthermore, the basic model of the line loss anomaly analysis model adopts a deep neural network model; the historical actual line loss causes, historical power grid structure and historical meteorological parameters are all stored in a pre-built model knowledge base; After taking the current group sub-branch as an abnormal group sub-branch to conduct abnormal line investigation to locate the abnormal line and fault point in the substation to be analyzed, the following steps are also included: The actual line loss causes, grid structure and meteorological parameters corresponding to abnormal lines and fault points are collected during this measurement; The actual line loss causes, grid structure and meteorological parameters corresponding to abnormal lines and fault points obtained from this measurement are used to update the model knowledge base.

[0008] Furthermore, if the initial cause of abnormal line loss is a clear result, the multi-level positioning method of substation-line-fault point is used to locate the abnormal line and fault point in the substation to be analyzed.

[0009] Furthermore, the definite result includes leakage, and the multi-level location method of the substation-line-fault point is used to locate the abnormal line and fault point in the substation to be analyzed, including: Substation inspection process: Inject a characteristic signal into the ground wire on the secondary side of the distribution transformer. Based on whether the characteristic signal is coupled into the secondary side line, determine whether a leakage fault occurs in the secondary side three-phase four-wire line; Line inspection process: Inspect different branch lines at the substation to identify leakage branch lines and faulty phases; Fault point troubleshooting process: gradually detect the leakage signal strength along the leakage branch line, and determine whether the current point is a leakage point based on the degree of change in the leakage signal strength at the current point.

[0010] Further, During the substation inspection process, if the injected characteristic signal can be coupled into the secondary side line, it is determined that there is a leakage fault in the secondary side three-phase four-wire line; otherwise, it is determined that there is no leakage fault in the secondary side three-phase four-wire line; During the fault point troubleshooting process, if the difference between the leakage signal strength before and after the current point exceeds the preset signal strength threshold, the current point is judged to be a leakage point; otherwise, the current point is judged to be in a normal state.

[0011] Furthermore, the magnetic needle identification method is used to re-test the leakage point.

[0012] Further, In the first-level circuit, before comparing the actual power supply and power sales corresponding to each group of branches, the following steps are included: In the first-level circuit, the separate-phase and combined-phase electricity of all branches in the same group are measured simultaneously, and the actual power supply corresponding to the branch is obtained based on the separate-phase and combined-phase electricity of all branches; In the second-level circuit, before comparing the actual power supply and power sales corresponding to each group of sub-branches, the following steps are included: In the second-level line, the individual-phase and combined-phase power of all sub-branches in the same group of sub-branches are measured simultaneously, and the actual power supply corresponding to the sub-branch is obtained based on the individual-phase and combined-phase power of all sub-branches.

[0013] A substation line loss anomaly analysis system based on a segmented metering mode includes: A preliminary line loss cause analysis module is used to input the grid structure and meteorological parameters of the substation to be analyzed into a pre-trained line loss anomaly analysis model and output preliminary line loss causes; the line loss anomaly analysis model is trained based on historical actual line loss causes, historical grid structure, and historical meteorological parameters; The abnormal line location module is used to locate the abnormal line and fault point using a step-by-step section measurement method if the preliminary line loss cause is ambiguous. It includes: In the first-level circuit, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process is cyclically executed for the next group of branches until the comparison result exceeds the first threshold range; if the comparison result exceeds the first threshold range, the current group of branches is regarded as an abnormal group of branches and the second-level circuit measurement is completed, and the first-level circuit measurement is terminated; In the second-level circuit, the actual power supply corresponding to each group of sub-branches is compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches is cyclically executed until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches is regarded as an abnormal group of sub-branches and abnormal line inspection is carried out to locate the abnormal line and fault point in the substation to be analyzed; Among them, the substation lines are pre-divided into two levels. The first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

[0014] An electronic device, comprising: memory for storing computer programs; A processor is used to implement the steps of the above-mentioned method for analyzing line loss anomalies in a substation based on a segmented metering mode when executing the computer program.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, is used to implement the steps of the above-mentioned method for analyzing line loss anomalies in a substation based on a segmented metering mode.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method for analyzing line loss anomalies in a substation area based on a segmented metering model. By inputting the grid topology and meteorological parameters of the substation to be analyzed into a pre-trained deep learning model, the model leverages historical data correlation to quickly generate preliminary line loss causes. When the preliminary line loss cause is ambiguous, a two-tiered segmented metering strategy is used to gradually narrow the fault scope. The first tier compares the difference in power supply and sales by branch group, using threshold screening to identify the abnormal branch group. The second tier further performs refined power comparisons on the sub-branch groups of the abnormal branch group, ultimately accurately locating the faulty line and node. This method achieves preliminary screening by integrating multi-dimensional influencing factors through a machine learning model, avoiding blind, full-scale investigations. The segmented metering strategy utilizes the hierarchical conduction characteristics of power differences to deconstruct complex power grids into progressively removable detection units. Combined with a dynamic threshold mechanism, it effectively filters out environmental interference and significantly improves anomaly location efficiency. This significantly reduces the workload of manual inspections and improves fault location accuracy to the branch level. Furthermore, a regionalized model training mechanism adapts to the differences in power grid characteristics across different regions, significantly improving the accuracy of line loss analysis and meeting the refined management needs of differentiated power grid scenarios.

[0017] The present invention preferably employs a deep neural network model to construct the basic framework for line loss analysis. This model's knowledge base continuously stores historical data and dynamically updates it, enabling the model to self-learn and evolve. A feedback-based update mechanism for newly added abnormal cases corrects model deviations in real time, addressing the reduced analysis accuracy associated with data lag in traditional methods and improving the accuracy of line loss diagnosis.

[0018] The multi-level fault location method of the present invention utilizes a three-level progressive screening process: substation, line, and fault point. For specific line loss causes (such as leakage), this method bypasses the fuzzy diagnosis process, shortening the fault location process. This strategy avoids redundant detection steps, effectively shortening the troubleshooting time for typical faults like leakage, and improving emergency response efficiency.

[0019] Preferably, in the present invention, characteristic signal injection and signal strength gradient detection technology realize accurate spatial positioning of leakage faults: substation-level signal coupling judgment quickly locks the fault phase, line-level branch screening narrows the fault range, and fault point-level signal strength mutation detection realizes centimeter-level positioning accuracy.

[0020] Preferably, the present invention uses a magnetic needle method as a physical verification method, verifying the electrical detection results of the leakage point through magnetic field distortion characteristics, forming an "electromagnetic-magnetic" dual-modal verification mechanism. This redundant design greatly increases the confidence level of the leakage diagnosis conclusion and eliminates the false alarm problem that may occur with a single detection method.

[0021] Preferably, in the present invention, the split-phase-combined-phase synchronous electricity metering technology eliminates the electricity statistical deviation caused by traditional single-phase metering, and improves the calculation accuracy of the power supply electricity through real-time correction of three-phase imbalance. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a method for analyzing abnormal line loss in a transformer area based on a segmented metering mode according to an embodiment of the present invention; Figure 2 A schematic diagram of the training of the line loss anomaly analysis model provided by an embodiment of the present invention; Figure 3 A schematic diagram of the leakage locating process in a transformer area provided by an embodiment of the present invention; Figure 4 A schematic diagram of the step-by-step metering method provided in an embodiment of the present invention; Figure 5 A flow chart of the method for analyzing abnormal line loss in a transformer area based on the segmented metering mode provided by the present invention; Figure 6 This is a structural schematic diagram of a substation line loss anomaly analysis system based on a segmented metering mode provided by the present invention. DETAILED DESCRIPTION

[0023] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0024] like Figure 1 As shown, this embodiment provides a method for analyzing abnormal line loss in a substation based on a segmented metering mode. This method relies on advanced equipment systems such as segmented metering devices and leakage detection modules, combined with a large model knowledge base, to analyze and determine the cause of abnormal line loss, such as power theft and leakage, including: S1. Model training: Artificial intelligence model training is carried out by combining historically known causes of line loss anomalies with historical correlations such as power grid structure and meteorology in different regions. A line loss anomaly analysis model for line loss anomaly analysis is constructed, which only has preliminary analysis functions.

[0025] S2. Model analysis: Based on the line loss situation of the substation to be analyzed, factors such as the region (grid structure) and meteorological parameters are input into the line loss anomaly analysis model to provide a preliminary guiding reference cause, i.e., the preliminary line loss cause. For example, if the actual output data shows that meteorological factors are closely related to fault factors, it can be determined that the probability of line loss in the substation to be analyzed being caused by leakage is greater.

[0026] S3. Leakage Troubleshooting: If the model analysis indicates a clear cause, such as leakage, the leakage detection module can be used for screening. This uses a multi-level location method (station-line-fault point) and a magnetic needle method to detect leakage. This method uses electromagnetic induction to test for leakage. A magnetic needle is placed at the location to be tested. If the needle deviates, leakage is detected at that location.

[0027] S4. Segmented Metering: If the model analysis is unclear, i.e., if the output is fuzzy, the cause of the abnormal line loss is investigated using a step-by-step segmented metering method. In this embodiment, a multi-channel segmented metering module can be used for actual measurement. The segmented metering module can collect and analyze whether the meter is experiencing electricity theft or operation.

[0028] The analysis method provided in this embodiment is described in more detail below: This embodiment provides a method for analyzing line loss anomalies in a substation based on a segmented metering mode. This method combines an artificial intelligence model, a leakage detection and analysis module, a segmented metering module, and other means. First, the artificial intelligence model is used to roughly check possible fault problems in the substation. Then, based on the rough inspection results, the leakage test module or the segmented metering module is used to perform a specific analysis of the substation branch lines, fault points, etc. involved. In the leakage inspection process, the magnetic needle identification method is used to assist in confirming the leakage situation. This can effectively improve the efficiency and accuracy of line loss anomaly analysis. The specific steps are as follows: S1. Training of line loss anomaly analysis model: like Figure 2 As shown, in this step, the main purpose is to train a model based on an artificial intelligence algorithm. The training data includes: actual line loss causes, substation grid structure (new or old), and meteorological factors. The above factors may have a strong correlation with potential leakage phenomena. Therefore, we can rely on existing historical data such as regional grid structure, meteorological factors, and actual line loss abnormal causes (such as leakage, electricity theft, metering, etc.) to build a line loss anomaly analysis model. The more accurate the model, the more it can support the preliminary analysis of the problem in the next step; among them, the historical actual line loss causes, historical grid structure, and historical meteorological parameters are all stored in a pre-built model knowledge base.

[0029] The line loss anomaly analysis model can be constructed using a neural network-based reasoning method. This method processes input data through a multi-layer neural network to generate predictions. Deep learning reasoning is primarily based on input data, a neural network model, and the model's training algorithm. Input data describes the input, the neural network model serves as the basis for the relevant functions that process the input data, and the trained algorithm serves as a method for continuous model optimization.

[0030] Deep learning inference can be implemented using the following steps: (1) Provide training data; (2) Selecting a suitable neural network model. In this embodiment, a deep neural network model can be used as the basic model; (3) Continuously optimize model-related parameters; (4) Output the trained line loss anomaly analysis model.

[0031] The basic mathematical formula of this reasoning method is:

[0032] In the formula, y represents the prediction result of the model, f represents the constructed neural network model, x represents the input, and Ø represents the parameters involved in the model.

[0033] S2. Analyze the preliminary causes of line loss based on the line loss abnormality analysis model: For the substation to be checked, this embodiment uses a line loss anomaly analysis model to conduct a preliminary analysis of the causes of its line loss. The grid information, meteorological information and other factors corresponding to the substation are input, and the line loss anomaly analysis model outputs potential problems in a targeted manner. The preliminary causes of line loss are analyzed and used as a reference for further line loss analysis.

[0034] It should be noted that the preliminary line loss causes output by this embodiment are divided into two types. The first type is a clear result, which can be accurately judged through the results output by the line loss anomaly analysis model. For example, if the output result can clearly determine that the current fault is a leakage fault, the fault cause will be directly output; the second type is a fuzzy result. That is to say, after analysis, the results output by the line loss anomaly analysis model are associated with multiple fault factors, so further judgment is needed.

[0035] S3. Leakage inspection: like Figure 3 As shown, in this embodiment, the clarity result is based on leakage as an example; if the preliminary cause of line loss is leakage, the leakage detection module is used for analysis. The specific execution steps are based on the multi-level location method of station area-line-fault point, including: 1) Substation inspection: Use a leakage tester to detect the characteristic signal. Specifically, the characteristic signal can be injected into the ground wire on the secondary side of the distribution transformer through a coupling clamp. If the characteristic signal cannot be coupled into the secondary side line, it indicates that there is no leakage fault in the secondary side three-phase four-wire line; if the characteristic signal can be coupled into the line, it indicates that there is a leakage fault in the secondary side three-phase four-wire line.

[0036] 2) Line inspection: Use a leakage tester to inspect different line branches on the substation side to screen out leakage branch lines and faulty phases.

[0037] 3) Leakage locating: The slave module of the leakage locating system is used to gradually detect the leakage signal strength along the fault line. The leakage is determined based on the degree of change in the leakage signal strength at a certain point. If there is a significant difference in the leakage signal strength before and after measurement at a certain point, it can be determined that the point is a leakage point.

[0038] 4) Leakage retest: Place a magnetic pointer at the potential leakage location (the leakage point preliminarily determined in step 3). Use the magnetic needle identification method to perform a re-measurement with the help of electromagnetic induction. If the pointer direction deviates, it indicates that leakage exists at that location.

[0039] If the initial cause of line loss is ambiguous, use the step-by-step section measurement method to locate the abnormal line and fault point, such as Figure 4 As shown, the specific steps include: In the positioning step of the step-by-step segmented metering method, a segmented and layered metering mode is adopted for analysis. The first level is the branches of the transformer outlet busbar; the second level is the sub-branches under a branch; the set of measurement modules used has a multi-channel measurement configuration, which can realize functions such as electricity metering, communication meter reading, and topology signal sending and identification. Its working principle is: by measuring the difference between the power supply and power consumption (power sales) of the substation, the abnormal lines and fault points in the substation are gradually checked, and whether there is an abnormality caused by line loss, as well as the location of the specific line fault.

[0040] like Figure 4 As shown, if the segmented metering module has three-way measurement capability, the analysis steps are as follows: In the first step, at the first level, branches 1, 2, and 3 are grouped together, and their currents and common-point voltages are measured simultaneously. This allows for simultaneous measurement of both phase-by-phase and combined power, as well as forward and reverse power. This is also applicable to photovoltaic substations. Based on this, the relevant substation topology is generated.

[0041] The segmented metering module includes a master submodule and a slave submodule, both of which have the functions of sending, receiving and identifying characteristic signals on the power line. The master and slave cooperate with each other to effectively support the realization of substation topology identification and segmented metering.

[0042] The second step is to obtain the actual power supply (kw·h) in the group through measurement and compare it with the power sales (kw·h) provided by the power supply company. If the difference is within the first threshold range, it is determined that there is no power theft, leakage, or metering abnormality in the group, and the next group is measured in a loop; otherwise, it is determined that there is an abnormal group branch in the current group, and power theft, leakage, or metering abnormality exists, then the first-level measurement is terminated and the second-level measurement is executed.

[0043] In the third step, at the second level, the power situation of the sub-branches corresponding to the abnormal group branches is measured and compared. The measurement and comparison methods are similar to those in the first step. By analogy, the number of users is gradually reduced until the abnormal lines and fault points in the substation are found.

[0044] Step 4: If the cause of the line loss is determined to be electricity theft or meter abnormality, contact the power supply company for on-site inspection and arrange further rectification.

[0045] Step 5: Feedback the associated factors and abnormal causes to the training model to update and improve the model knowledge base.

[0046] Thus, this embodiment provides a method for analyzing line loss anomalies in a substation area based on a segmented metering mode, which has the following advantages over traditional analysis methods: This method uses the model analysis-leakage investigation-segmented metering model to effectively combine the relationship between regional characteristics of the power grid, meteorological and other environmental factors and abnormal line losses. It can accurately and efficiently analyze the abnormal causes of line losses, effectively support power supply companies in daily line loss management, and improve economic benefits.

[0047] For example, Figure 5 As shown, this embodiment also provides a method for analyzing abnormal line loss in a substation based on a segmented metering mode, including: Input the grid structure and meteorological parameters of the substation to be analyzed into a pre-trained line loss anomaly analysis model to output preliminary line loss causes; the line loss anomaly analysis model is trained based on historical actual line loss causes, historical grid structure, and historical meteorological parameters; If the initial cause of line loss is ambiguous, use the step-by-step section measurement method to locate the abnormal line and fault point, including: In the first-level circuit, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process is cyclically executed for the next group of branches until the comparison result exceeds the first threshold range; if the comparison result exceeds the first threshold range, the current group of branches is regarded as an abnormal group of branches and the second-level circuit measurement is completed, and the first-level circuit measurement is terminated; In the second-level circuit, the actual power supply corresponding to each group of sub-branches is compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches is cyclically executed until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches is regarded as an abnormal group of sub-branches and abnormal line inspection is carried out to locate the abnormal line and fault point in the substation to be analyzed; Among them, the substation lines are pre-divided into two levels. The first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

[0048] In this embodiment, the basic model of the line loss anomaly analysis model adopts a deep neural network model; the historical actual line loss causes, historical power grid structure and historical meteorological parameters are all stored in a pre-built model knowledge base; After taking the current group sub-branch as an abnormal group sub-branch to conduct abnormal line investigation to locate the abnormal line and fault point in the substation to be analyzed, the following steps are also included: The actual line loss causes, grid structure and meteorological parameters corresponding to abnormal lines and fault points are collected during this measurement; The actual line loss causes, grid structure and meteorological parameters corresponding to abnormal lines and fault points obtained from this measurement are used to update the model knowledge base.

[0049] In this embodiment, if the cause of the preliminary abnormal line loss is a clear result, a multi-level positioning method of substation-line-fault point is used to locate the abnormal line and fault point in the substation to be analyzed.

[0050] In this embodiment, the definite result includes leakage, and the multi-level location method of substation-line-fault point is used to locate the abnormal line and fault point in the substation to be analyzed, including: Substation inspection process: Inject a characteristic signal into the ground wire on the secondary side of the distribution transformer. Based on whether the characteristic signal is coupled into the secondary side line, determine whether a leakage fault occurs in the secondary side three-phase four-wire line; Line inspection process: Inspect different branch lines at the substation to identify leakage branch lines and faulty phases; Fault point troubleshooting process: gradually detect the leakage signal strength along the leakage branch line, and determine whether the current point is a leakage point based on the degree of change in the leakage signal strength at the current point.

[0051] In this embodiment, During the substation inspection process, if the injected characteristic signal can be coupled into the secondary side line, it is determined that there is a leakage fault in the secondary side three-phase four-wire line; otherwise, it is determined that there is no leakage fault in the secondary side three-phase four-wire line; During the fault point troubleshooting process, if the difference between the leakage signal strength before and after the current point exceeds the preset signal strength threshold, the current point is judged to be a leakage point; otherwise, the current point is judged to be in a normal state.

[0052] In this embodiment, a magnetic needle identification method is used to perform leakage retest on the leakage point.

[0053] In this embodiment, In the first-level circuit, before comparing the actual power supply and power sales corresponding to each group of branches, the following steps are included: In the first-level circuit, the separate-phase and combined-phase electricity of all branches in the same group are measured simultaneously, and the actual power supply corresponding to the branch is obtained based on the separate-phase and combined-phase electricity of all branches; In the second-level circuit, before comparing the actual power supply and power sales corresponding to each group of sub-branches, the following steps are included: In the second-level line, the individual-phase and combined-phase power of all sub-branches in the same group of sub-branches are measured simultaneously, and the actual power supply corresponding to the sub-branch is obtained based on the individual-phase and combined-phase power of all sub-branches.

[0054] like Figure 6 As shown, this embodiment also provides a substation line loss anomaly analysis system based on the segmented metering mode, including: a preliminary line loss cause analysis module, which is used to input the power grid structure and meteorological parameters of the substation to be analyzed into a pre-trained line loss anomaly analysis model, and output a preliminary line loss cause; the line loss anomaly analysis model is trained based on historical actual line loss causes, historical power grid structure and historical meteorological parameters; an abnormal line locating module is used to locate abnormal lines and fault points using a step-by-step segmented metering method if the preliminary line loss cause is a fuzzy result, including: in the first-level line, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process of the next group of branches is cyclically executed until the comparison result exceeds the first threshold range; if the comparison result is fuzzy, the abnormal line locating module is used to locate the abnormal line and the fault point using a step-by-step segmented metering method. If the result exceeds the first threshold range, the current group of branches will be taken as an abnormal group of branches for second-level line measurement, and the first-level line measurement will be ended; in the second-level line, the actual power supply corresponding to each group of sub-branches will be compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches will be executed cyclically until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches will be taken as an abnormal group of sub-branches for abnormal line investigation to locate the abnormal lines and fault points in the substation to be analyzed; wherein, the substation lines are pre-divided into two levels, the first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

[0055] The present invention also provides an electronic device, comprising: a memory for storing a computer program; and a processor for implementing the steps of the method for analyzing abnormal line loss in an area based on a segmented metering mode when executing the computer program.

[0056] When the processor executes the computer program, the steps of the above-mentioned substation line loss anomaly analysis based on the segmented metering mode are implemented, for example: the grid structure and meteorological parameters of the substation to be analyzed are input into the pre-trained line loss anomaly analysis model, and the preliminary line loss cause is output; the line loss anomaly analysis model is trained based on the historical actual line loss cause, the historical grid structure and the historical meteorological parameters; if the preliminary line loss cause is a fuzzy result, the abnormal line and the fault point are located by using the step-by-step segmented metering method, including: in the first-level line, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process of the next group of branches is cyclically executed until the comparison result exceeds the first threshold range; if the comparison result exceeds the first threshold range The current group of branches is taken as the abnormal group of branches for the second-level line measurement, and the first-level line measurement is ended; in the second-level line, the actual power supply corresponding to each group of sub-branches is compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches is executed cyclically until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches is taken as the abnormal group of sub-branches for abnormal line investigation to locate the abnormal lines and fault points in the substation to be analyzed; wherein, the substation lines are pre-divided into two levels, the first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

[0057] Exemplarily, the computer program can be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete preset functions, and the instruction segments are used to describe the execution process of the computer program in the substation line loss anomaly analysis device based on the segmented metering mode. For example, the computer program can be divided into a preliminary line loss cause analysis module and an abnormal line location module; the specific functions of each module are as follows: a preliminary line loss cause analysis module, which is used to input the power grid structure and meteorological parameters of the substation to be analyzed into a pre-trained line loss anomaly analysis model, and output a preliminary line loss cause; the line loss anomaly analysis model is trained based on historical actual line loss causes, historical power grid structure and historical meteorological parameters; an abnormal line location module, which is used to locate abnormal lines and fault points using a step-by-step segmented metering method if the preliminary line loss cause is a fuzzy result, including: in the first-level line, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process of the next group of branches is cyclically executed until the comparison result exceeds the first threshold range ; If the comparison result exceeds the first threshold range, the current group of branches will be taken as an abnormal group of branches for second-level line measurement, and the first-level line measurement will be ended; in the second-level line, the actual power supply corresponding to each group of sub-branches will be compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches will be executed cyclically until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches will be taken as an abnormal group of sub-branches for abnormal line investigation to locate the abnormal lines and fault points in the substation to be analyzed; wherein, the substation lines are pre-divided into two levels, the first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

[0058] The substation line loss anomaly analysis device based on the segmented metering mode can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The substation line loss anomaly analysis device based on the segmented metering mode may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the above is an example of a substation line loss anomaly analysis device based on the segmented metering mode, and does not constitute a limitation on the substation line loss anomaly analysis device based on the segmented metering mode. It may include more components than the above, or a combination of certain components, or different components. For example, the substation line loss anomaly analysis device based on the segmented metering mode may also include input and output devices, network access devices, buses, etc.

[0059] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc. The processor serves as the control center of the substation line loss anomaly analysis based on the segmented metering mode, and utilizes various interfaces and lines to connect various parts of the substation line loss anomaly analysis device based on the segmented metering mode.

[0060] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the substation line loss anomaly analysis device based on the segmented metering mode by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory.

[0061] The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on the use of the mobile phone (such as audio data and a phone book). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0062] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the method for analyzing line loss anomalies in a substation based on a segmented metering mode.

[0063] If the module / unit integrated in the substation line loss anomaly analysis system based on the segmented metering mode is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0064] Based on this understanding, the present invention implements all or part of the processes in the above-mentioned method for analyzing line loss anomalies in a substation area based on a segmented metering mode, and can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned method for analyzing line loss anomalies in a substation area based on a segmented metering mode. The computer program includes computer program code, which can be in source code form, object code form, executable file, or preset intermediate form.

[0065] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0066] It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable storage media do not include electrical carrier signals and telecommunication signals.

[0067] The above embodiment is only one of the implementation methods that can realize the technical solution of the present invention. The scope of protection claimed by the present invention is not limited only to this embodiment, but also includes changes, replacements and other implementation methods that can be easily thought of by any technician familiar with this technical field within the technical scope disclosed by the present invention.

[0068] 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, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for analyzing abnormal line loss in a substation based on a segmented metering mode, characterized in that: include: Input the grid structure and meteorological parameters of the substation to be analyzed into the pre-trained line loss anomaly analysis model, and output the preliminary cause of line loss; The line loss anomaly analysis model is trained based on historical actual line loss causes, historical power grid structure and historical meteorological parameters; If the initial cause of line loss is ambiguous, use the step-by-step section measurement method to locate the abnormal line and fault point, including: In the first-level circuit, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process is cyclically executed for the next group of branches until the comparison result exceeds the first threshold range; if the comparison result exceeds the first threshold range, the current group of branches is regarded as an abnormal group of branches and the second-level circuit measurement is completed, and the first-level circuit measurement is terminated; In the second-level circuit, the actual power supply corresponding to each group of sub-branches is compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches is cyclically executed until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches is regarded as an abnormal group of sub-branches and abnormal line inspection is carried out to locate the abnormal line and fault point in the substation to be analyzed; Among them, the substation lines are pre-divided into two levels. The first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

2. The method for analyzing abnormal line loss in a substation area based on a segmented metering mode according to claim 1 is characterized in that: The basic model of the line loss anomaly analysis model adopts a deep neural network model; the historical actual line loss causes, historical power grid structure and historical meteorological parameters are all stored in a pre-built model knowledge base; After taking the current group sub-branch as an abnormal group sub-branch to conduct abnormal line investigation to locate the abnormal line and fault point in the substation to be analyzed, the following steps are also included: The actual line loss causes, grid structure and meteorological parameters corresponding to abnormal lines and fault points are collected during this measurement; The actual line loss causes, grid structure and meteorological parameters corresponding to abnormal lines and fault points obtained from this measurement are used to update the model knowledge base.

3. The method for analyzing abnormal line loss in a substation area based on a segmented metering mode according to claim 1, characterized in that: If the initial cause of abnormal line loss is clear, the multi-level location method of substation-line-fault point is used to locate the abnormal line and fault point in the substation to be analyzed.

4. The method for analyzing abnormal line loss in a transformer area based on a segmented metering mode according to claim 3 is characterized in that: The clear result includes leakage, and the multi-level location method of using the substation-line-fault point to locate the abnormal line and fault point in the substation to be analyzed includes: Substation inspection process: Inject a characteristic signal into the ground wire on the secondary side of the distribution transformer. Based on whether the characteristic signal is coupled into the secondary side line, determine whether a leakage fault occurs in the secondary side three-phase four-wire line; Line inspection process: Inspect different branch lines at the substation to identify leakage branch lines and faulty phases; Fault point troubleshooting process: gradually detect the leakage signal strength along the leakage branch line, and determine whether the current point is a leakage point based on the degree of change in the leakage signal strength at the current point.

5. The method for analyzing abnormal line loss in a substation area based on a segmented metering mode according to claim 4 is characterized in that: During the substation inspection process, if the injected characteristic signal can be coupled into the secondary side line, it is determined that there is a leakage fault in the secondary side three-phase four-wire line; otherwise, it is determined that there is no leakage fault in the secondary side three-phase four-wire line; During the fault point troubleshooting process, if the difference between the leakage signal strength before and after the current point exceeds the preset signal strength threshold, the current point is judged to be a leakage point; otherwise, the current point is judged to be in a normal state.

6. The method for analyzing abnormal line loss in a transformer area based on a segmented metering mode according to claim 5, characterized in that: The magnetic needle identification method is used to re-test the leakage point.

7. The method for analyzing abnormal line loss in a transformer area based on a segmented metering mode according to claim 1, characterized in that: In the first-level circuit, before comparing the actual power supply and power sales corresponding to each group of branches, the following steps are included: In the first-level circuit, the separate-phase and combined-phase electricity of all branches in the same group are measured simultaneously, and the actual power supply corresponding to the branch is obtained based on the separate-phase and combined-phase electricity of all branches; In the second-level circuit, before comparing the actual power supply and power sales corresponding to each group of sub-branches, the following steps are included: In the second-level line, the individual-phase and combined-phase power of all sub-branches in the same group of sub-branches are measured simultaneously, and the actual power supply corresponding to the sub-branch is obtained based on the individual-phase and combined-phase power of all sub-branches.

8. A substation line loss anomaly analysis system based on segmented metering mode, characterized in that: include: The preliminary line loss cause analysis module is used to input the grid structure and meteorological parameters of the substation to be analyzed into the pre-trained line loss anomaly analysis model and output the preliminary line loss cause; The line loss anomaly analysis model is trained based on historical actual line loss causes, historical power grid structure and historical meteorological parameters; The abnormal line location module is used to locate the abnormal line and fault point using a step-by-step section measurement method if the preliminary line loss cause is ambiguous. It includes: In the first-level circuit, the actual power supply corresponding to each group of branches is compared with the power sales; if the comparison result is within the first threshold range, the comparison process is cyclically executed for the next group of branches until the comparison result exceeds the first threshold range; if the comparison result exceeds the first threshold range, the current group of branches is regarded as an abnormal group of branches and the second-level circuit measurement is completed, and the first-level circuit measurement is terminated; In the second-level circuit, the actual power supply corresponding to each group of sub-branches is compared with the power sales; if the comparison result is within the second threshold range, the comparison process of the next group of sub-branches is cyclically executed until the comparison result exceeds the second threshold range; if the comparison result exceeds the second threshold range, the current group of sub-branches is regarded as an abnormal group of sub-branches and abnormal line inspection is carried out to locate the abnormal line and fault point in the substation to be analyzed; Among them, the substation lines are pre-divided into two levels. The first-level lines include the branches of the transformer outlet busbar, and the second-level lines include the sub-branches corresponding to each branch; each branch and each sub-branch are divided into groups.

9. An electronic device, characterized in that: include: memory for storing computer programs; A processor is configured to implement the steps of the method for analyzing line loss anomaly in a substation based on a segmented metering mode as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it is used to implement the steps of the substation line loss anomaly analysis method based on the segmented metering mode as described in any one of claims 1 to 7.

Images