Power distribution network fault early warning method based on multi-source data fusion

Abstract

The invention relates to a power distribution network fault early warning method based on multi-source data fusion. The specific process comprises the steps of S1, differentially configuring fault sensing conditions of a power distribution master station and equipment inside and outside the station; s2, monitoring a line signal in real time; s3, fault early warning: the main station calls and measures recording files of all feeder line complete switches under the bus, abnormal waveform files are screened out and then sent to an algorithm research and judgment module, system disturbance or instantaneous fault research and judgment and positioning are carried out, and a fault early warning result is displayed; and S4, checking and eliminating the suspected fault points, displaying a fault early warning result in combination with a network topological graph, and notifying operation and maintenance personnel to go to check and eliminate the suspected fault points through short messages. The system has a prospective fault sensing capability, can capture tiny disturbance or transient faults of the system in advance, and efficiently and accurately completes defect elimination before potential faults are evolved into permanent faults, so that stable operation of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution automation, and in particular to a power distribution network fault early warning method based on multi-source data fusion. Background Art

[0002] In the complex operating environment of the distribution network, many permanent faults often originate from initial transient faults or system minor disturbances. These potential threats pose a severe challenge to power supply reliability. Although a variety of advanced fault analysis and judgment technologies and methods have been widely used in the current distribution network, most of them focus on the rapid identification and accurate positioning of faults that have occurred, but it is difficult to capture and warn those initial transient faults or system disturbance signals that may evolve into permanent faults. These are the "reefs" hidden behind the stability of power supply. In addition, with the rapid improvement of the degree of distribution automation, the convenience of obtaining abnormal waveform data has also increased. The amount of abnormal information is large and complex, and the traditional fault intelligent identification algorithm cannot fully adapt to the current data stream. Therefore, in order to eliminate the possibility of potential faults turning into permanent faults from the root and improve the accuracy of fault identification by using multi-source data, it is necessary to introduce a distribution network fault warning system and method based on multi-source data fusion, so as to achieve accurate warning and complete the fault elimination work efficiently and accurately before the potential faults evolve into permanent faults, and improve the reliability of power supply. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a distribution network fault warning method based on multi-source data fusion, which can collect and comprehensively analyze multi-source data from different distribution terminals, so that the fault warning signal can be keenly captured when the fault is still in its infancy, that is, in the stage of instantaneous fault or system disturbance. This can not only greatly improve the efficiency of fault handling, but also achieve accurate fault elimination before the fault has a substantial impact, thereby significantly enhancing the reliability of the power supply system and bringing users a more stable and uninterrupted power supply.

[0004] To achieve the above object, the present invention adopts the following technical solution: a distribution network fault early warning method based on multi-source data fusion, comprising the following steps: Step S1, differentially configure the fault perception conditions of the power distribution master station and the equipment inside and outside the station, that is, differentially configure the electrical quantity alarm / early warning trigger thresholds of the power distribution master station, the equipment inside the station and the equipment outside the station. The early warning threshold of the equipment inside and outside the station should be lower than the early warning threshold of the power distribution master station, so that the fault early warning sensitivity of the equipment inside and outside the station is higher than that of the power distribution master station; Step S2: The power distribution master station monitors the line signal in real time. If the equipment inside and outside the station sends a fault alarm signal and no fault pop-up window appears at the power distribution master station, the fault warning process is started; Step S3, fault warning: the master station calls for the recording files of all feeder switch sets under the bus, filters out abnormal waveform files and sends them to the algorithm analysis module to analyze and locate system disturbances or transient faults, and display fault warning results; Step S4: Check and eliminate suspected fault points, display the fault warning results in combination with the network topology diagram, and notify the operation and maintenance personnel to check and eliminate the suspected fault points via SMS.

[0005] In a preferred embodiment, the warning threshold of the equipment inside and outside the station in step 1 should be lower than the warning threshold of the distribution master station, which means setting the fault analysis start threshold and fault confirmation delay threshold parameters through the equipment panels inside and outside the station to ensure that the threshold parameters are lower than the threshold parameters of the distribution master station.

[0006] In a preferred embodiment, in step 2, the equipment inside and outside the station sends a fault alarm signal but no fault pop-up window appears at the distribution master station, which means that the characteristics or duration of the fault may not have reached the threshold that the distribution master station can detect, so the distribution master station will ignore the fault; since the sensitivity of the equipment inside and outside the station is higher than that of the distribution master station, they can perceive this abnormal phenomenon earlier and send out an alarm signal in advance.

[0007] In a preferred embodiment, the step 3 specifically includes the following steps: Step S31: The master station calls for recording waveform files of all feeder switches under the bus, and sends the abnormal waveform files to the algorithm analysis module after filtering them out; Step S32: analyzing and locating system disturbances or transient faults; Step S33: Display the fault warning result, and display the fault warning result in combination with the network topology diagram.

[0008] In a preferred embodiment, in step 31, the filtering out of abnormal waveform files refers to filtering and removing waveforms with abnormal signal acquisition, missing part of information, and distorted acquisition signals; Signal acquisition anomaly means that during the signal acquisition process, due to sensor failure, acquisition equipment damage or improper acquisition parameter settings, the collected signal deviates significantly from the actual signal. Partial information missing means that during the recording process, due to data loss, storage device failure or transmission error, some information in the waveform file is missing, which cannot fully reflect the true situation of the signal; Acquisition signal distortion refers to the distortion of the collected signal compared to the actual signal due to reasons such as accuracy limitations of the acquisition equipment, attenuation or interference during signal transmission, such as deviation in frequency, amplitude or phase parameters.

[0009] In a preferred embodiment, step 4 specifically includes: displaying the fault warning results in combination with the network topology diagram, which is an effective method to help operation and maintenance personnel quickly locate and handle potential faults in an intuitive manner by marking abnormal or potentially faulty devices and sections in the network device connection diagram.

[0010] Compared with the prior art, the present invention has the following beneficial effects: 1) Efficient application of multi-source data: The system can efficiently process waveform files from different terminals and use them for centralized analysis. The multi-source waveform data helps to more comprehensively reflect the operating status of the distribution network and improve the accuracy of fault warning.

[0011] 2) Foresight of fault perception: The system has forward-looking fault perception capabilities, which can capture small disturbances or instantaneous faults in the system in advance, and complete the fault elimination work efficiently and accurately before the potential faults evolve into permanent faults, ensuring the stable operation of the system.

[0012] 3) Visualization of warning information: The system can provide an intuitive visualization interface to display warning information to operation and maintenance personnel in the form of charts, images or text messages, making it easy for operation and maintenance personnel to query warning information and go to the location of potential faults in time for verification and elimination. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a flow chart of a fault warning system and method according to an embodiment of the present invention.

[0014] Figure 2 It is a flow chart of the fault warning link in one embodiment of the present invention.

[0015] Figure 3 It is the content of the fault warning information SMS notification in one embodiment of the present invention. DETAILED DESCRIPTION

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0017] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0018] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application; as used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations.

[0019] like Figure 1-3 As shown, the present invention provides a distribution network fault early warning system and method based on multi-source data fusion, comprising the following steps: Step S1, differentially configure the fault perception conditions of the distribution master station and the equipment inside and outside the station, that is, differentially configure the electrical quantity alarm / prewarning trigger thresholds (such as zero-sequence voltage and zero-sequence current) of the distribution master station, the equipment inside the station and the equipment outside the station. Under normal circumstances, the warning threshold of the equipment inside and outside the station should be lower than the warning threshold of the distribution master station, so that the fault warning sensitivity of the equipment inside and outside the station is higher than that of the distribution master station.

[0020] Specifically, the warning threshold of equipment inside and outside the station should be lower than the warning threshold of the distribution master station. The threshold parameters such as the fault analysis start threshold and fault confirmation delay are set through the equipment panels inside and outside the station to ensure that their threshold parameters are lower than the threshold parameters of the distribution master station.

[0021] Step S2: The power distribution master station monitors the line signal in real time. If the equipment inside and outside the station sends a fault alarm signal and no fault pop-up window appears at the power distribution master station, the fault warning process is started.

[0022] Specifically, the fact that the equipment inside and outside the station sends fault alarm signals but the distribution master station does not display a fault pop-up window indicates that the characteristics or duration of the fault may not have reached the threshold that the distribution master station can detect, so the distribution master station will ignore the fault. However, since the equipment inside and outside the station is more sensitive than the distribution master station, they can perceive this abnormal phenomenon earlier and send out alarm signals in advance.

[0023] Step S3, fault warning, the master station calls for the recording files of all feeder switch sets under the bus, and sends them to the algorithm analysis module after filtering out abnormal waveform files, and then analyzes and locates system disturbances or transient faults, and displays the fault warning results. The fault warning step flow chart is as follows Figure 2 shown.

[0024] Specifically, the algorithm analysis module refers to a module that efficiently collects, stores and analyzes the recorded waveforms collected by all distribution terminals under the same bus, and uses advanced technical algorithms such as artificial intelligence to determine whether system disturbances or faults have occurred. This module can achieve real-time monitoring and early warning of the operating status of the power grid, and promptly discover and deal with potential safety hazards.

[0025] Step S3-1, the master station calls for the waveform recording files of all feeder switch sets under the bus, and sends the abnormal waveform files to the algorithm analysis module after filtering them out.

[0026] The filtering out of abnormal waveform files refers to filtering and removing waveforms with abnormal signal acquisition, partial information missing, and distorted acquisition signals.

[0027] Signal acquisition anomaly refers to the situation in which, during the signal acquisition process, due to sensor failure, damage to the acquisition equipment, or improper setting of acquisition parameters, the collected signal deviates significantly from the actual signal.

[0028] Partial information missing means that during the recording process, due to data loss, storage device failure or transmission error, some information in the waveform file is missing, which cannot fully reflect the true situation of the signal.

[0029] Acquisition signal distortion refers to the distortion of the collected signal compared to the actual signal due to reasons such as accuracy limitations of the acquisition equipment, attenuation or interference during signal transmission, such as deviations in parameters such as frequency, amplitude or phase.

[0030] Step S3-2: System disturbance or transient fault analysis and location.

[0031] Step S3-3: Display the fault warning result, and display the fault warning result in combination with the network topology diagram.

[0032] Step S4: Check and eliminate suspected fault points, display the fault warning results in combination with the network topology diagram, and notify the operation and maintenance personnel to check and eliminate the suspected fault points via SMS.

[0033] Specifically, displaying fault warning results in combination with a network topology diagram refers to an effective method that helps operation and maintenance personnel quickly locate and handle potential faults in an intuitive manner by marking abnormal or potentially faulty devices and sections in a network device connection diagram.

[0034] Specifically, the SMS notification means that when a potential fault risk point is found, the operation and maintenance personnel can be notified via SMS to go for inspection. The SMS content is as follows: Figure 3 shown.

Claims

1. A distribution network fault early warning method based on multi-source data fusion, characterized in that: The following steps are involved: Step S1, differentially configure the fault perception conditions of the power distribution master station and the equipment inside and outside the station, that is, differentially configure the electrical quantity alarm / early warning trigger thresholds of the power distribution master station, the equipment inside the station and the equipment outside the station. The early warning threshold of the equipment inside and outside the station should be lower than the early warning threshold of the power distribution master station, so that the fault early warning sensitivity of the equipment inside and outside the station is higher than that of the power distribution master station; Step S2: The power distribution master station monitors the line signal in real time. If the equipment inside and outside the station sends a fault alarm signal and no fault pop-up window appears at the power distribution master station, the fault warning process is started; Step S3, fault warning: the master station calls for the recording files of all feeder switch sets under the bus, filters out abnormal waveform files and sends them to the algorithm analysis module to analyze and locate system disturbances or transient faults, and display fault warning results; Step S4: Check and eliminate suspected fault points, display the fault warning results in combination with the network topology diagram, and notify the operation and maintenance personnel to check and eliminate the suspected fault points via SMS.

2. A distribution network fault early warning method based on multi-source data fusion according to claim 1, characterized in that: In step 1, the warning threshold of the equipment inside and outside the station should be lower than the warning threshold of the distribution master station, which means setting the fault analysis start threshold and fault confirmation delay threshold parameters through the equipment panels inside and outside the station to ensure that their threshold parameters are lower than the threshold parameters of the distribution master station.

3. A distribution network fault early warning method based on multi-source data fusion according to claim 1, characterized in that: In step 2, the equipment inside and outside the station sends a fault alarm signal but no fault pop-up window appears at the distribution master station, which means that the characteristics or duration of the fault may not have reached the threshold that the distribution master station can detect, so the distribution master station will ignore the fault; since the sensitivity of the equipment inside and outside the station is higher than that of the distribution master station, they can perceive this abnormal phenomenon earlier and send out an alarm signal in advance.

4. A distribution network fault early warning method based on multi-source data fusion according to claim 1, characterized in that: The step 3 specifically comprises the following steps: Step S31: The master station calls for recording waveform files of all feeder switches under the bus, and sends the abnormal waveform files to the algorithm analysis module after filtering them out; Step S32: analyzing and locating system disturbances or transient faults; Step S33: Display the fault warning result, and display the fault warning result in combination with the network topology diagram.

5. A distribution network fault early warning method based on multi-source data fusion according to claim 4, characterized in that: In the step 31, the abnormal waveform files are screened out, which refers to screening and removing the waveforms with abnormal signal acquisition, missing part of the information, and distorted acquisition signals; Signal acquisition anomaly means that during the signal acquisition process, due to sensor failure, acquisition equipment damage or improper acquisition parameter settings, the collected signal deviates significantly from the actual signal. Partial information missing means that during the recording process, due to data loss, storage device failure or transmission error, some information in the waveform file is missing, which cannot fully reflect the true situation of the signal; Acquisition signal distortion refers to the distortion of the collected signal compared to the actual signal due to reasons such as accuracy limitations of the acquisition equipment, attenuation or interference during signal transmission, such as deviation in frequency, amplitude or phase parameters.

6. A distribution network fault early warning method based on multi-source data fusion according to claim 1, characterized in that: The step 4 is specifically as follows: displaying the fault warning results in combination with the network topology diagram refers to an effective method of helping operation and maintenance personnel to quickly locate and handle potential faults in an intuitive manner by marking abnormal or potentially faulty devices and sections in the network device connection diagram.

Images