A cloud-edge collaborative substation fault monitoring management system and method
The cloud-edge collaborative substation fault monitoring and management system enables precise location of substation fault areas and accurate location of fault causes, solving the problems of accuracy and efficiency in fault detection in existing technologies and improving the reliability of fault handling and the efficiency of data processing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUIZHOU POWER GRID CO LTD
- Filing Date
- 2024-11-28
- Publication Date
- 2026-07-24
AI Technical Summary
In existing technologies, substation fault detection is mainly based on fault waveform analysis, which can only locate the fault area but cannot effectively determine the cause of the fault. This is especially true in the case of cascading faults, which increases the difficulty of determining the cause of the fault. Furthermore, the unified uploading of data can easily lead to communication congestion, affecting the timely removal of emergency faults.
The cloud-edge collaborative substation fault monitoring and management system is adopted. The substation area acquisition module divides the power blocks and establishes a secondary information block aggregation station to classify and mark data and identify suspected faults. Combined with the fault analysis module, a secondary fault judgment is performed. The logic embedding module is used to establish the judgment logic of the power transmission change direction, so as to accurately locate the fault type and determine the cause.
It improves the accuracy and efficiency of fault detection, reduces the consumption of manual resources, ensures the efficiency and integrity of data processing, provides reliable support for judging fault causes, and facilitates the operation, maintenance and repair of substations.
Smart Images
Figure CN119919109B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power fault detection technology, and in particular to a cloud-edge collaborative substation fault monitoring and management system and method. Background Technology
[0002] Substation fault detection data is characterized by its multi-source heterogeneity. How to efficiently process and analyze this massive amount of data to realize its value and provide data support for the stable operation of the power system is a key research issue. In existing technologies, substation fault detection mainly adopts a method of uniformly uploading data to the cloud for analysis and processing, i.e., using cloud-edge collaboration to improve information processing efficiency. For example, an existing cloud-edge collaborative task management system and method for substation fault detection reduces network transmission latency through cloud-edge collaborative task management, which is beneficial for the smooth completion of urgent and time-sensitive tasks. It uses load forecasting to predict the system load at the next moment, improving resource utilization efficiency. The system is simple in structure, easy to operate, and easy to promote.
[0003] However, existing technologies still have the following technical shortcomings in practical applications: First, different types of fault data require different computing resources, and substations have varying time requirements and urgency levels for clearing different types of faults. Uploading data uniformly to the cloud for analysis and processing can easily lead to communication congestion, causing emergency faults to fail to be cleared in a timely manner, posing safety hazards to substations. Second, existing substation fault detection mainly relies on fault waveform analysis, which can only locate the fault area and cannot effectively determine the cause of the fault. In particular, when a cascading fault occurs in a substation, the expanded fault range further increases the difficulty of determining the cause of the fault, hindering subsequent maintenance work. Therefore, there is an urgent need to propose a substation fault detection scheme that can ensure efficient data processing and accurate determination of fault causes. Summary of the Invention
[0004] In view of the above-mentioned problems, the present invention is proposed.
[0005] Therefore, the problem to be solved by this invention is how to provide a cloud-edge collaborative substation fault monitoring and management system and method, which solves the problem that conventional fault recording analysis can only locate the fault area and lacks the judgment of the fault cause. In particular, when a substation fault occurs, large-area faults are likely to occur, which further increases the difficulty of judging the fault cause.
[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:
[0007] In a first aspect, embodiments of the present invention provide a cloud-edge collaborative substation fault monitoring and management system, comprising a substation area acquisition module, a data preprocessing module, a fault analysis module, and a logic embedding module. The substation area acquisition module is used to divide the substation into power blocks according to the power transmission direction, establish a secondary information block aggregation station for directly managed power blocks, and collect fault waveform data within the power blocks to obtain block data. The data preprocessing module is used to classify and label the block data according to electrical types, obtain information blocks under the secondary information block aggregation station, perform suspected fault judgment based on the information area, and mark the corresponding electrical quantities of the suspected faults. The fault analysis module is used to perform secondary fault judgment based on the electrical quantities of the suspected faults, and compare the secondary fault judgment results with the suspected faults to obtain the final fault type. The logic embedding module is used to establish judgment logic for the power transmission change direction and corresponding electrical quantity change based on the sequentially marked secondary information block aggregation station.
[0008] As a preferred embodiment of the cloud-edge collaborative substation fault monitoring and management system of the present invention, the data preprocessing module includes a data classification unit, a fault marking unit, and a data backup unit. The data classification unit is used to classify and mark block data according to electrical type to obtain information blocks. The data backup unit is used to back up information blocks under the secondary aggregation station of adjacent upper-order information blocks to obtain the management reference data of the current information block secondary aggregation station. The fault marking unit has the following functions: comparing the information block with the electrical quantities under historical fault types to obtain suspected faults and marking the electrical quantities of the corresponding suspected faults; comparing the management reference data and direct management information according to the judgment logic, and marking abnormal logical changes based on the comparison results.
[0009] As a preferred embodiment of the cloud-edge collaborative substation fault monitoring and management system of the present invention, the method of obtaining the final fault type includes the following steps: comparing the secondary fault judgment result with the suspected fault; if the secondary fault judgment result is inconsistent with the suspected fault judged by the secondary information block aggregation station, the data backup unit uses the secondary information block aggregation station storing the backup information of the information blocks under the corresponding secondary information block aggregation station to re-judge the suspected fault; if the re-judgment result is consistent with the secondary fault judgment result, the secondary fault judgment result is taken as the final fault type; if the re-judgment result is consistent with the suspected fault, the suspected fault is taken as the final fault type; if the secondary fault judgment result is consistent with the suspected fault judged by the secondary information block aggregation station, the suspected fault is taken as the final fault type.
[0010] As a preferred embodiment of the cloud-edge collaborative substation fault monitoring and management system of the present invention, the suspected fault judgment includes the following steps: based on historical fault types, electrical quantity change data is collected using a fault recorder and a fault feature database is established; the information area is compared with the fault feature database to obtain suspected faults; the adjacent upper-order information block secondary aggregation station refers to the information block secondary aggregation station that is sequentially marked according to the substation power transmission direction, and after filtering out the first information block secondary aggregation station, the information block secondary aggregation station with the highest adjacent sequential marking is the adjacent upper-order information block secondary aggregation station; the power transmission change direction includes increasing, decreasing, and remaining unchanged.
[0011] As a preferred embodiment of the cloud-edge collaborative substation fault monitoring and management system of the present invention, the fault analysis module includes a logic analysis unit and a fault location unit; the logic analysis unit is used to determine whether the secondary aggregation station of the fault information block is an abnormal station based on the abnormal logic change markers corresponding to the secondary aggregation station of different information blocks; the fault location unit is used to perform secondary fault judgment based on the electrical quantities of the corresponding suspected fault, and compare the secondary fault judgment result with the suspected fault. If the secondary fault judgment result is consistent with the suspected fault, then the corresponding fault is judged to have occurred.
[0012] As a preferred embodiment of the cloud-edge collaborative substation fault monitoring and management system of the present invention, the determination of whether a secondary aggregation station of fault information blocks is an abnormal station includes the following steps: judging the secondary aggregation stations of information blocks with abnormal logic change markers; if the secondary aggregation stations of information blocks with abnormal logic change markers are continuous secondary aggregation stations, then the first secondary aggregation station of information blocks with abnormal logic change markers is judged as an abnormal station; if the secondary aggregation stations of information blocks with abnormal logic change markers are not continuous secondary aggregation stations, then the secondary aggregation stations of information blocks with abnormal logic change markers are divided into multiple abnormal stations to be judged according to continuity, and the first secondary aggregation station of information blocks to be judged among the abnormal stations to be judged is judged as an abnormal station.
[0013] As a preferred embodiment of the cloud-edge collaborative substation fault monitoring and management system of the present invention, the secondary fault judgment includes the following steps: based on historical fault types, using a fault recorder to collect electrical quantity change data and establish a fault feature database; comparing the electrical quantity of the corresponding suspected fault with the fault feature database to obtain the secondary fault judgment result.
[0014] Secondly, to further address the safety issues in power fault detection, this invention provides a cloud-edge collaborative substation fault monitoring and management method, comprising: dividing the substation area using a substation area acquisition module to obtain power blocks and establishing a secondary information block aggregation station; collecting fault waveform data within the power blocks to obtain block data; classifying and labeling the block data using a data classification unit to obtain information blocks; comparing the information blocks with electrical quantities under historical fault types using a fault labeling unit to obtain suspected faults and labeling the corresponding electrical quantities of suspected faults; performing secondary fault judgment using a fault location unit based on the electrical quantities of suspected faults, and comparing the secondary fault judgment result with the suspected fault; if the two match, a corresponding fault is determined to have occurred; otherwise... If the two are inconsistent, proceed to the next step: use the data backup unit to back up the information blocks under the adjacent upper-order information block secondary aggregation station to obtain the management reference data of the information block secondary aggregation station; use the information block secondary aggregation station that stores the backup information of the information blocks under the corresponding information block secondary aggregation station to re-judge the suspected fault and obtain the final fault type; use the logic embedding module to establish the judgment logic of the power transmission change direction and the corresponding electrical quantity change, the fault marking unit compares the management reference data and the direct management information according to the judgment logic, and marks the abnormal logic change according to the comparison result; the logic analysis unit judges whether the fault information block secondary aggregation station is an abnormal station according to the abnormal logic change mark corresponding to different information block secondary aggregation stations.
[0015] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements any step of the cloud-edge collaborative substation fault monitoring and management system as described in the first aspect of the present invention.
[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the cloud-edge collaborative substation fault monitoring and management system as described in the first aspect of the present invention.
[0017] The beneficial effects of this invention are as follows: By setting up several secondary information block aggregation stations and a central information block station, this invention avoids congestion caused by centralized data processing. Simultaneously, it effectively improves data processing efficiency through cloud-edge collaboration. Furthermore, the classification and formulation of several information blocks enable effective organization of multi-source data, facilitating the secondary information block aggregation stations to perform suspected fault judgments based on directly managed information blocks. The marking of abnormal data accelerates the secondary fault judgment at the central information block station. The comparison of the two fault judgment results ensures the effectiveness of fault type identification. In conjunction with the information backup unit, not only can information blocks be managed separately to ensure data integrity, but it also provides reliable support for the final fault type determination. Through the setting of a logic embedding module, after the secondary information block aggregation stations perform logical comparisons based on directly managed information blocks and managed reference data, they achieve effective judgment of abnormal stations, providing effective reference data support for judging the causes of substation faults, thereby facilitating the operation and maintenance of substations. Attached Figure Description
[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:
[0019] Figure 1 This is a schematic diagram of the system architecture of a cloud-edge collaborative substation fault monitoring and management system in Example 1.
[0020] Figure 2 This is a schematic diagram of a cloud-edge collaborative substation fault monitoring and management system in Example 1.
[0021] Figure 3 This is a schematic diagram showing the distribution of the logic embedding module, the information block main station, and the information block secondary aggregation station in Example 1.
[0022] Figure 4 This is a system principle block diagram of the data preprocessing module in Example 1.
[0023] Figure 5 This is a system principle block diagram of the fault analysis module in Example 1.
[0024] Figure 6 This is a schematic diagram of the computer device in Example 3. Detailed Implementation
[0025] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0026] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.
[0027] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.
[0028] Example 1
[0029] Reference Figures 1-5 This is the first embodiment of the present invention, which provides a cloud-edge collaborative substation fault monitoring and management system.
[0030] Existing power fault detection methods have the following main problems: First, different types of fault data require different computing resources, and substations have varying time requirements and urgency levels for clearing different types of faults. Uploading all data to the cloud for analysis and processing can easily lead to communication congestion, causing emergency faults to fail to be cleared in a timely manner, thus posing a safety hazard to the substation. Second, existing substation fault detection methods are mainly based on fault waveform analysis, which can only locate the fault area and cannot effectively determine the cause of the fault. In particular, when a cascading fault occurs in a substation, the expanded fault range further increases the difficulty of determining the cause of the fault, which is not conducive to the subsequent maintenance work.
[0031] This application provides a solution to the problems mentioned above. The following will describe in detail how to implement the cloud-edge collaborative substation fault monitoring and management system using multiple embodiments.
[0032] Figure 1 A schematic diagram of the architecture distribution of a cloud-edge collaborative substation fault monitoring and management system is shown, including:
[0033] Preferred, such as Figure 2 The diagram shown is a schematic diagram of a cloud-edge collaborative substation fault monitoring and management system. The system includes a substation area acquisition module, a data preprocessing module, a fault analysis module, and a logic embedding module.
[0034] Specifically, the substation area acquisition module is used to divide the area according to the power transmission direction of the substation to obtain power blocks, establish a secondary information block aggregation station for the directly managed power blocks, and collect fault waveform data within the power blocks to obtain block data.
[0035] Preferably, by dividing the substation into different power blocks and establishing a secondary aggregation station, the present invention can better collect and manage fault waveform data within the blocks, effectively improving the accuracy and efficiency of data acquisition. Compared with traditional substation fault detection, which often collects data from the entire station and makes it difficult to analyze the cause of the fault in a targeted manner, the substation area acquisition module can more accurately locate the area where the fault occurs, providing more detailed data for subsequent fault analysis.
[0036] Specifically, the data preprocessing module is used to classify and label the block data according to electrical type, obtain the information blocks under the secondary summary station of the information block, judge the suspected faults according to the information area, and mark the electrical quantities of the corresponding suspected faults.
[0037] Specifically, the fault analysis module acts as the central station for information blocks. It is used to perform secondary fault judgment based on the electrical quantities of suspected faults, and compares the results of the secondary fault judgment with the suspected faults to obtain the final fault type.
[0038] Specifically, such as Figure 3 The diagram shows the distribution of the logic embedding module, the information block main station, and the information block secondary aggregation station. The logic embedding module is used to establish the judgment logic of the power transmission change direction and the corresponding electrical quantity change based on the information block secondary aggregation station with the sequence mark. The power transmission change direction includes increase, decrease, and no change.
[0039] Preferably, the logical rules for fault judgment are established based on the direction of power transmission and the trend of changes in electrical quantities. This fully integrates the physical characteristics of the power system and can better assist in fault location and classification. Compared with traditional fault analysis, which often lacks consideration of the power system topology and transmission laws and whose analysis results are difficult to match with the actual power system conditions, this invention can effectively improve the pertinence and reliability of fault analysis.
[0040] Preferred, such as Figure 4 The diagram shown is a system principle block diagram of the data preprocessing module, which includes a data classification unit, a fault marking unit, and a data backup unit.
[0041] Specifically, the data classification unit is used to classify and label block data according to electrical type to obtain information blocks.
[0042] Specifically, the functions of the fault marking unit include: comparing the information block with the electrical quantities under the historical fault types, obtaining suspected faults, and marking the electrical quantities of the corresponding suspected faults.
[0043] The system compares the differences between the reference data for each department and the information for direct management according to the judgment logic, and marks any abnormal logical changes based on the comparison results.
[0044] Furthermore, the suspected fault identification includes the following steps: based on historical fault types, use a fault recorder to collect electrical quantity change data and establish a fault feature database.
[0045] By comparing the information area with the fault feature database, suspected faults are obtained.
[0046] Specifically, the data backup unit is used to back up the information blocks under the secondary aggregation station of the adjacent upper-order information block to obtain the management reference data of the current secondary aggregation station of the information block.
[0047] Furthermore, the adjacent upper-order information block secondary aggregation station refers to the information block secondary aggregation station that is ranked according to the power transmission direction of the substation. After removing the first information block secondary aggregation station, the information block secondary aggregation station with the highest ranking of adjacent ranking marks is the adjacent upper-order information block secondary aggregation station.
[0048] Preferably, by constructing a data preprocessing module to classify and label the collected data, identify suspected faults, and back up information, it is possible to effectively filter out the fault information that needs to be analyzed in detail, thereby improving the pertinence and accuracy of subsequent fault analysis. Compared with the traditional substation fault detection, which relies on manual analysis of a large amount of raw data and is inefficient, this invention can automatically complete data classification and suspected fault identification, reducing the consumption of manual resources and improving the efficiency of fault detection.
[0049] Preferred, such as Figure 5 The diagram shown is a system principle block diagram of the fault analysis module, which includes a logic analysis unit and a fault location unit.
[0050] Specifically, the logic analysis unit is used to determine whether a secondary summary station of a fault information block is an abnormal station based on the abnormal logic change flags corresponding to the secondary summary stations of different information blocks.
[0051] Furthermore, the determination of whether a secondary summary station of a fault information block is an abnormal station includes the following steps: judging the secondary summary stations of information blocks with abnormal logic change markers; if the secondary summary station of information blocks with abnormal logic change markers is a continuous secondary summary station of information blocks, then the first secondary summary station of information blocks with abnormal logic change markers is judged to be an abnormal station.
[0052] If the secondary aggregation station of the information block with the abnormal logical change mark is not a continuous secondary aggregation station of the information block, then the secondary aggregation station of the information block with the abnormal logical change mark is divided into multiple abnormal stations to be judged according to the continuity, and the first secondary aggregation station of the information block to be judged among the abnormal stations is judged as an abnormal station.
[0053] Specifically, the fault location unit is used to perform secondary fault judgment based on the electrical quantities corresponding to the suspected fault, and compare the results of the secondary fault judgment with the suspected fault. If the results of the secondary fault judgment are consistent with the suspected fault, then the corresponding fault is determined to have occurred.
[0054] Furthermore, secondary fault diagnosis includes the following steps: based on historical fault types, use a fault recorder to collect electrical quantity change data and establish a fault feature database.
[0055] The electrical quantities corresponding to suspected faults are compared with the fault feature database to obtain secondary fault judgment results.
[0056] Preferably, comparing the secondary fault judgment result with the suspected fault to obtain the final fault type includes the following steps: comparing the secondary fault judgment result with the suspected fault; if the secondary fault judgment result is inconsistent with the suspected fault judged by the secondary information block aggregation station, the data backup unit uses the secondary information block aggregation station storing the backup information of the information blocks under the corresponding secondary information block aggregation station to make a second judgment on the suspected fault; if the second judgment result is consistent with the secondary fault judgment result, the secondary fault judgment result is taken as the final fault type.
[0057] If the result of the second assessment is consistent with the suspected fault, then the suspected fault will be taken as the final fault type.
[0058] If the result of the secondary fault assessment is consistent with the suspected fault assessment by the secondary aggregation station of the information block, then the suspected fault will be taken as the final fault type.
[0059] Preferably, by utilizing secondary fault judgment and final fault type judgment, the present invention can more accurately determine the fault type. In particular, by using backup data from adjacent information blocks for re-judgment, the preliminary judgment results are further verified, and the reliability of the judgment is improved. The construction of the fault analysis module makes full use of historical fault data, establishes a fault feature library, realizes intelligent judgment of fault type, and effectively improves the accuracy and efficiency of fault analysis.
[0060] In summary, this invention avoids congestion caused by centralized data processing by setting up several secondary information block aggregation stations and a central information block station. It effectively improves data processing efficiency through cloud-edge collaboration, and, in conjunction with the classification of several information blocks, achieves effective organization of multi-source data. This facilitates the secondary information block aggregation stations in judging suspected faults based on directly managed information blocks, and accelerates secondary fault judgment at the central information block station by marking abnormal data. The comparison of the two fault judgment results ensures the effectiveness of fault type identification. Furthermore, the inclusion of an information backup unit not only enables the division of information blocks and ensures data integrity but also provides reliable support for the final fault type determination. Through the setting of a logic embedding module, the secondary information block aggregation stations, after logically comparing directly managed information blocks and assigned reference data, achieve effective judgment of abnormal stations, providing effective reference data support for determining the causes of substation faults, thereby facilitating substation operation, maintenance, and repair.
[0061] Example 2, an embodiment of the present invention, provides a cloud-edge collaborative substation fault monitoring and management method, comprising: dividing the substation area using a substation area acquisition module to obtain power blocks and establishing a secondary information block aggregation station; collecting fault waveform data within the power blocks to obtain block data; classifying and labeling the block data using a data classification unit to obtain information blocks; comparing the information blocks with electrical quantities under historical fault types using a fault labeling unit to obtain suspected faults and labeling the corresponding electrical quantities of suspected faults; performing secondary fault judgment using a fault location unit based on the electrical quantities of suspected faults, and comparing the secondary fault judgment result with the suspected fault; if the two match, a corresponding fault is determined to have occurred; if the two do not match, ... Proceed to the next step; use the data backup unit to back up the information blocks under the adjacent upper-order information block secondary aggregation station to obtain the management reference data of the information block secondary aggregation station; use the information block secondary aggregation station storing the backup information of the information blocks under the corresponding information block secondary aggregation station to re-judge the suspected fault and obtain the final fault type; use the logic embedding module to establish the judgment logic of the power transmission change direction and the corresponding electrical quantity change, the fault marking unit compares the management reference data and the direct management information according to the judgment logic, and marks the abnormal logic change according to the comparison result, and the logic analysis unit judges whether the fault information block secondary aggregation station is an abnormal station according to the abnormal logic change mark corresponding to different information block secondary aggregation stations.
[0062] Example 3 is an embodiment of the present invention, which differs from the previous embodiment in that:
[0063] like Figure 6As shown, if the function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0064] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.
[0065] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.
[0066] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0067] Example 4 is an embodiment of the present invention, which provides a cloud-edge collaborative substation fault monitoring and management system. In order to verify the beneficial effects of the present invention, a simulation experiment is conducted for scientific demonstration.
[0068] In this embodiment, 10 220kV substations under a provincial power grid company were selected as test objects and connected in series via 500kV transmission lines. To verify the effectiveness of the cloud-edge collaborative task management system of the present invention, a fault detection test was conducted on the substations for a period of 6 months. First, these substations were numbered from upstream to downstream according to the power transmission direction as S1 to S10, and a secondary information block aggregation station was set up in each substation. An intelligent fault recorder was installed in each substation with a sampling frequency of 10kHz.
[0069] During implementation, the 10 substations were first divided into regions using the substation area acquisition module. Two adjacent substations were divided into a power block, forming a total of 9 power blocks (D1 to D9). Each power block was equipped with an edge computing server for real-time acquisition and preprocessing of fault waveform data. The data preprocessing module adopted a distributed storage architecture to classify and label the acquired data according to voltage (V-type), current (I-type), and power (P-type). At the same time, the system established a historical fault feature database containing typical fault types such as short-circuit faults, grounding faults, and circuit breaker faults.
[0070] In the fault analysis process, this example adopts a dual judgment mechanism. First, the fault marking unit intelligently matches the real-time collected electrical quantities with the historical fault feature library and uses an improved dynamic time warping algorithm to perform waveform similarity analysis, with the similarity threshold set at 85%. When a suspected fault is detected, the system automatically triggers a secondary fault judgment mechanism, using a deep learning-based fault feature extraction algorithm to extract the time and frequency domain features of the fault waveform and construct a fault discrimination model.
[0071] To improve the accuracy of fault location, a data backup mechanism for the secondary aggregation station of adjacent upper-order information blocks is introduced. When a suspected fault is detected at station S(n), the system automatically calls the historical data of station S(n-1) as a reference. By comparing and analyzing the direction of power transmission change and the amount of electrical quantity change, a logical relationship for fault judgment is established.
[0072] In terms of logic embedding, this example uses an improved decision tree algorithm to quantify the correspondence between the direction of power transmission change and the amount of electrical quantity change into judgment rules. By setting voltage change thresholds of ±5%, current change thresholds of ±10%, and power change thresholds of ±15%, a complete abnormal logic judgment system is established. When an abnormality is detected, the system will automatically mark the abnormal logic change and determine whether it is a secondary aggregation station of fault information block through the logic analysis unit.
[0073] In this example, the traditional single-site detection method, the method of this invention (without backup mechanism), the method of this invention (single backup), and the method of this invention (complete solution) are compared and tested from three aspects: fault detection accuracy, reliability index, and data processing efficiency. Table 1 shows the comparison table of fault detection accuracy.
[0074] Table 1 Comparison of Fault Detection Accuracy
[0075] Traditional single-site detection 85.3 150 The method of this invention (without backup mechanism) 91.2 95 The method of this invention (single backup) 94.5 85 The method of this invention (complete solution) 98.3 65
[0076] As can be seen from Table 1, in terms of fault detection accuracy, based on the dual judgment mechanism and data backup cross-validation mechanism proposed in this invention, compared with the traditional single-site detection method, this invention effectively improves the fault detection accuracy. By introducing power transmission change direction analysis and logic embedding mechanism, this invention achieves higher positioning accuracy. This high-precision fault positioning capability has important practical significance for rapid fault handling and equipment maintenance.
[0077] Table 2 shows a comparison of reliability indicators. Through step-by-step analysis of the data, it can be found that as the backup mechanism is gradually improved, the reliability of the system gradually increases, which verifies the effectiveness of the multi-level backup and cross-validation mechanism proposed in this invention. This indicates that the invention significantly reduces the false alarm rate and false negative rate of the system.
[0078] Table 2 Comparison of Reliability Indicators
[0079] Traditional single-site detection 8.5 6.2 The method of this invention (without backup mechanism) 5.8 4.1 The method of this invention (single backup) 4.2 3.3 The method of this invention (complete solution) 2.3 1.8
[0080] Table 3 shows a comparison of data processing efficiency.
[0081] Table 3 Comparison of Data Processing Efficiency
[0082] Traditional single-site detection 280 45 The method of this invention (without backup mechanism) 180 75 The method of this invention (single backup) 165 72 The method of this invention (complete solution) 145 68
[0083] As can be seen from the table above, this invention effectively shortens the fault detection response time through a distributed edge computing architecture and optimized data processing flow. Even with the full data backup and cross-validation mechanism enabled, the system still maintains a low response time, demonstrating the optimization effectiveness of this invention in terms of algorithm efficiency and system architecture. Through the optimized edge computing architecture and data classification and storage strategy, this invention maintains high data processing efficiency and effectively balances system performance while ensuring detection accuracy.
[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.
Claims
1. A cloud-edge collaborative substation fault monitoring and management system, characterized in that: include: Substation area acquisition module, data preprocessing module, fault analysis module, and logic embedding module; The substation area acquisition module is used to divide the area according to the power transmission direction of the substation to obtain power blocks, establish a secondary information block aggregation station for the directly managed power blocks, and collect fault waveform data within the power blocks to obtain block data. The data preprocessing module is used to classify and label the block data according to electrical type, obtain the information blocks under the secondary aggregation station of the information block, judge the suspected faults according to the information area, and mark the electrical quantities of the corresponding suspected faults. The fault analysis module is used to perform secondary fault judgment based on the electrical quantities of the suspected fault, and compare the results of the secondary fault judgment with the suspected fault to obtain the final fault type. The logic embedding module is used to establish the judgment logic of the power transmission change direction and the corresponding electrical quantity change based on the information block secondary aggregation station of the sequential marker; The data preprocessing module includes a data classification unit, a fault marking unit, and a data backup unit; The data classification unit is used to classify and label the block data according to electrical type to obtain information blocks; The data backup unit is used to back up the information blocks under the secondary aggregation station of the adjacent upper-order information block to obtain the management reference data of the current secondary aggregation station of the information block. The functions of the fault marking unit include: The information block is compared with the electrical quantities under the historical fault types to obtain suspected faults, and the electrical quantities of the corresponding suspected faults are marked. The system compares the differences between the reference data for each department and the information for direct management according to the judgment logic, and marks any abnormal logical changes based on the comparison results. The suspected fault determination includes the following steps: Based on historical fault types, use a fault recorder to collect electrical quantity change data and establish a fault feature database. The information area is compared with the fault feature database to obtain suspected faults; The adjacent upper-order information block secondary aggregation station refers to the information block secondary aggregation station that is sequentially marked according to the power transmission direction of the substation. After removing the first information block secondary aggregation station, the information block secondary aggregation station with the highest adjacent sequential marking is the adjacent upper-order information block secondary aggregation station. The direction of change in power transmission includes increasing, decreasing, and remaining unchanged; The fault analysis module includes a logic analysis unit and a fault location unit; The logic analysis unit is used to determine whether the secondary aggregation station of the fault information block is an abnormal station based on the abnormal logic change flags corresponding to the secondary aggregation stations of different information blocks. The fault location unit is used to perform secondary fault judgment based on the electrical quantities of the corresponding suspected fault, and compare the secondary fault judgment result with the suspected fault. If the secondary fault judgment result is consistent with the suspected fault, then the corresponding fault is judged to have occurred.
2. The cloud-edge collaborative substation fault monitoring and management system as described in claim 1, characterized in that: The process of determining the final fault type includes the following steps: The secondary fault judgment result is compared with the suspected fault. If the secondary fault judgment result is inconsistent with the suspected fault judged by the secondary information block aggregation station, the data backup unit uses the secondary information block aggregation station that stores the backup information of the information blocks under the corresponding secondary information block aggregation station to make a second judgment on the suspected fault. If the second judgment result is consistent with the secondary fault judgment result, the secondary fault judgment result is taken as the final fault type. If the result of the second assessment is consistent with the suspected fault, then the suspected fault will be taken as the final fault type. If the result of the secondary fault assessment is consistent with the suspected fault assessment by the secondary aggregation station of the information block, then the suspected fault will be taken as the final fault type.
3. The cloud-edge collaborative substation fault monitoring and management system as described in claim 2, characterized in that: The determination of whether the secondary aggregation station of the fault information block is an abnormal station includes the following steps: The system judges the secondary aggregation stations of information blocks that have abnormal logical change markers. If the secondary aggregation stations of information blocks that have abnormal logical change markers are secondary aggregation stations of continuous information blocks, then the first secondary aggregation station of information blocks that has abnormal logical change markers is judged as an abnormal station. If the secondary aggregation station of the information block with the abnormal logical change mark is not a continuous secondary aggregation station of the information block, then the secondary aggregation station of the information block with the abnormal logical change mark is divided into multiple abnormal stations to be judged according to the continuity, and the first secondary aggregation station of the information block to be judged among the abnormal stations is judged as an abnormal station.
4. The cloud-edge collaborative substation fault monitoring and management system as described in claim 3, characterized in that: The secondary fault diagnosis includes the following steps: Based on historical fault types, use a fault recorder to collect electrical quantity change data and establish a fault feature database. The electrical quantities corresponding to suspected faults are compared with the fault feature database to obtain secondary fault judgment results.
5. A cloud-edge collaborative substation fault monitoring and management method, based on the cloud-edge collaborative substation fault monitoring and management system according to any one of claims 1 to 4, characterized in that: include, The substation area acquisition module is used to divide the area into power blocks and establish a secondary information block aggregation station to collect fault waveform data within the power blocks and obtain block data. The data classification unit is used to classify and label the block data to obtain information blocks. The fault labeling unit is used to compare the information blocks with the electrical quantities under the historical fault types to obtain suspected faults, and the electrical quantities of the corresponding suspected faults are labeled. The fault location unit performs secondary fault judgment based on the electrical quantities of the suspected fault, and compares the results of the secondary fault judgment with the suspected fault. If they match, the corresponding fault is determined to have occurred; if they do not match, the next step is executed. The data backup unit is used to back up the information blocks under the secondary aggregation station of the adjacent upper-order information block to obtain the management reference data of the secondary aggregation station of the information block. The information block secondary aggregation station, which stores the backup information of the information blocks under the corresponding information block secondary aggregation station, is used to re-judge suspected faults and obtain the final fault type. The logic embedding module is used to establish the judgment logic for the direction of power transmission change and the corresponding change in electrical quantity. The fault marking unit compares the difference between the branch reference data and the direct pipe information according to the judgment logic, and marks the abnormal logic change based on the comparison result. The logic analysis unit judges whether the secondary aggregation station of the fault information block is an abnormal station based on the abnormal logic change mark corresponding to the secondary aggregation station of different information blocks.
6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the cloud-edge collaborative substation fault monitoring and management system according to any one of claims 1 to 4.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the cloud-edge collaborative substation fault monitoring and management system as described in any one of claims 1 to 4.