Power distribution network fault detection method based on multi-source information fusion and related equipment

Abstract

The invention discloses a power distribution network fault detection method based on multi-source information fusion and related equipment, and the method comprises the steps: extracting transient high-frequency voltage information from original data collected by power distribution automation equipment, and capturing a transient response when a fault occurs; fault detection data which is not influenced by a control strategy and a conversion resistor of the converter are provided for subsequent power distribution network fault detection; according to the method, manufacturer equipment data and equipment operation data are utilized and analyzed, and equipment fault degree information can be obtained through analysis, so that the reason and possibility of fault occurrence can be understood from the equipment level; fault detection can be carried out through analysis of fusion information, fault elements and fault probability in the power distribution network can be accurately positioned, and effective fault positioning can be realized even under the condition that fault features are not obvious.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault detection, and in particular to a distribution network fault detection method based on multi-source information fusion and related equipment. Background Art

[0002] With the large-scale implementation and application of distribution automation, the scale of distribution automation construction will only increase in the current and next few years. As a result, the number of distribution automation terminals will increase significantly. The debugging, on-site maintenance and management application of a large number of terminals will become the focus of the next stage of development.

[0003] Currently, there are many distribution terminal manufacturers operating in power supply companies. The debugging software and debugging methods of each manufacturer are very different. Even different models of equipment from the same manufacturer have great differences.

[0004] At the same time, the workload of commissioning acceptance and on-site operation and maintenance has doubled. Due to the existence of a large amount of repetitive work, the improvement of on-site work efficiency has become a shackle. This has greatly affected the application speed of distribution automation terminals and slowed down the development of distribution automation.

[0005] During the power distribution commissioning process, we often have to deal with the commissioning work of dozens or even hundreds of manufacturers. Each manufacturer provides different commissioning software, which is extremely inflexible for the commissioning personnel to operate. However, due to problems such as protocol implementation degree and point table inconsistency, the compatibility is poor.

[0006] Currently, graph neural networks are commonly used to capture the interdependence of nodes in the graph through the message passing mechanism between nodes in the topological structure, map the electrical nodes and lines of the distribution network into vertices and edges in the graph, and use graph neural networks to learn and identify the behavior and response patterns of different devices, thereby realizing distribution debugging.

[0007] However, under actual distribution network conditions, the electrical data collected by distribution automation equipment at the monitoring point will be distorted to a certain extent. In the process of transmission to the information center, noise interference may be superimposed, which will seriously affect the accuracy of fault location. When the fault characteristics are not obvious, it will become particularly difficult to accurately obtain the fault probability of the actual faulty component. Summary of the invention

[0008] Based on the problems raised by the above background technology, the purpose of the present invention is to provide a distribution network fault detection method and related equipment based on multi-source information fusion, which solves the problem that in actual distribution network conditions, the electrical data collected by distribution automation equipment at the monitoring point will be distorted to a certain extent, and noise interference may be superimposed in the process of transmission to the information center, which will seriously affect the accuracy of fault location. When the fault characteristics are not obvious, it will become particularly difficult to accurately obtain the fault probability of the actual faulty component.

[0009] The present invention is achieved through the following technical solutions:

[0010] A first aspect of the present invention provides a distribution network fault detection method based on multi-source information fusion, comprising the following steps:

[0011] Step S1, acquiring power distribution data of a power distribution terminal, and extracting transient high-frequency voltage information from the power distribution data;

[0012] Step S2, using compressed sensing theory to calculate and analyze the transient high-frequency voltage information to obtain the electrical quantity fault degree;

[0013] Step S3: Obtain manufacturer equipment data and equipment operation data, analyze the manufacturer equipment data and equipment operation data, and obtain equipment failure degree;

[0014] Step S4: establishing a distribution network topology map, and fusing the electrical fault degree and the equipment fault degree based on the distribution network topology map to obtain fusion information;

[0015] Step S5: perform fault detection on the fused information to obtain distribution network fault information.

[0016] In the above technical scheme, in a complex distribution network, due to the lack of measurement points and the fact that the fault characteristics are greatly affected by the control strategy of power electronic equipment, it is proposed to extract transient high-frequency voltage information from the raw data collected by the distribution automation equipment, so as to capture the transient response when the fault occurs, and provide fault detection data that is not affected by the control strategy and conversion resistance of the converter for subsequent distribution network fault detection.

[0017] Compressed sensing theory can recover high-frequency information from sparsely sampled data, which is beneficial for processing electrical data distorted by noise interference. By calculating the fault degree of electrical quantities, faults can be accurately identified even in the case of data distortion and noise interference.

[0018] Since there are many distribution terminal manufacturers currently operating in power supply companies, the debugging software and debugging methods of each manufacturer are very different, and even different models of equipment from the same manufacturer are very different. The compatibility of each device is poor due to problems such as protocol implementation degree and point table inconsistency. Therefore, this method proposes to use the manufacturer's equipment data and equipment operation data and analyze them. Through analysis, the equipment fault degree information can be obtained, which helps to understand the cause and possibility of the fault from the equipment level.

[0019] Finally, fault detection can be performed by analyzing the fused information, accurately locating the faulty components and fault probabilities in the distribution network, and achieving effective fault location even when the fault characteristics are not obvious.

[0020] In an optional embodiment, extracting transient high-frequency voltage information from the power distribution data includes the following steps:

[0021] Step S11, dividing the power distribution data into sections according to the interval time to obtain time series node data;

[0022] Step S12, filtering out the time series nodes whose change rate is greater than the change rate threshold from the time series node data, and calculating the average interval value between the time series nodes;

[0023] Step S13, using the average interval value as the size of the sliding window to extract transient high-frequency voltage from the time series node data, to obtain high-frequency data of the time series nodes and high-frequency data between time series nodes;

[0024] Step S14, equating the high-frequency data between the time series nodes to the adjacent time series nodes to generate equivalent high-frequency data of the time series nodes;

[0025] Step S15, synthesizing the timing node data and the equivalent timing node high-frequency data to obtain transient high-frequency voltage information.

[0026] In an optional embodiment, the high-frequency data between the time series nodes is equivalent to the time series nodes adjacent thereto, including the following steps:

[0027] Step S141, selecting the high-frequency data between the i-th time series nodes, and determining the high-frequency data between the j-th time series nodes and the high-frequency data between the j+1-th time series nodes adjacent to the high-frequency data between the i-th time series nodes;

[0028] Step S142, establishing an equivalent relationship between faults of timing nodes, bringing the high-frequency data of the i-th timing node, the high-frequency data of the j-th timing node, and the high-frequency data of the j+1-th timing node into the equivalent relationship between faults of timing nodes to obtain an equivalent relationship distribution;

[0029] Step S143: distribute the high-frequency data between the i-th timing nodes to the j-th timing node high-frequency data and the j+1-th timing node high-frequency data based on the equivalent relationship distribution, and obtain the j-th equivalent timing node high-frequency data and the j+1-th equivalent timing node high-frequency data.

[0030] In an optional embodiment, the transient high-frequency voltage information is calculated and analyzed using compressed sensing theory, including the following steps:

[0031] Step S21, determining the number of decomposition layers, and decomposing the transient high-frequency voltage information based on the number of decomposition layers to obtain decomposed transient high-frequency voltage information;

[0032] Step S22, based on the compressed sensing theory, the distribution probability of each layer of decomposed transient high-frequency voltage information is calculated in sequence, and the distribution probability of the last layer is used as the fault value of the corresponding sliding window;

[0033] Step S23, assign the fault degree of the first sliding window to the electrical quantity fault degree, move the sliding window, and compare the fault values ​​in two adjacent sliding windows. If the fault value in the adjacent sliding window is greater than the electrical quantity fault degree, assign the fault value in the adjacent sliding window to the electrical quantity fault degree.

[0034] In an optional embodiment, before calculating and analyzing the transient high-frequency voltage information using the compressed sensing theory, the method further includes: performing node reconstruction on the transient high-frequency voltage information, wherein the node reconstruction includes:

[0035]

[0036] In the above formula, is the transient high-frequency voltage information of the jth time node after reconstruction, U j is the transient high-frequency voltage information of the jth timing node, t is the average interval value, and T is the interval time.

[0037] In an optional embodiment, analyzing the manufacturer's equipment data and equipment operation data includes the following steps:

[0038] Step S31, calculating the failure rate of the manufacturer's equipment data;

[0039] Step S32, pre-processing the equipment operation data to obtain analysis data;

[0040] Step S33, extracting fault features from the analysis data, analyzing the fault features, and obtaining fault distribution features and fault variation features;

[0041] Step S34, comprehensively analyzing the failure rate, the failure distribution characteristics and the failure variation characteristics to obtain the equipment failure degree.

[0042] In an optional embodiment, the electrical fault degree and the device fault degree are merged based on the distribution network topology diagram, comprising the following steps:

[0043] Step S41, normalizing the electrical fault degree and the equipment fault degree to obtain a standardized fault characteristic and an equipment fault characteristic;

[0044] Step S42, randomly selecting a topological node from the distribution network topology map, performing fault degree fusion processing on the standardized fault characteristics on the topological node and the equipment fault characteristics to obtain a fused fault degree;

[0045] Step S43: performing fault identification on the fused fault degree, and determining the distribution network fault according to the fault identification result.

[0046] The second aspect of the present invention provides a schematic diagram of the structure of a distribution network fault detection system based on multi-source information fusion, such as Figure 2 As shown, the distribution network fault detection system based on multi-source information fusion includes:

[0047] A transient extraction module, used to obtain power distribution data of a power distribution terminal and extract transient high-frequency voltage information from the power distribution data;

[0048] An electrical fault module, used to calculate and analyze the transient high-frequency voltage information using compressed sensing theory to obtain an electrical quantity fault degree;

[0049] An equipment failure module is used to obtain manufacturer equipment data and equipment operation data, analyze the manufacturer equipment data and equipment operation data, and obtain the equipment failure degree;

[0050] A fusion module, used for establishing a distribution network topology map, and fusing the electrical fault degree and the equipment fault degree based on the distribution network topology map to obtain fusion information;

[0051] The detection module is used to perform fault detection on the fused information to obtain distribution network fault information.

[0052] A third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a distribution network fault detection method based on multi-source information fusion when executing the computer program.

[0053] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a distribution network fault detection method based on multi-source information fusion.

[0054] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0055] Fault detection can be performed by analyzing the fused information, accurately locating the faulty components and fault probabilities in the distribution network, and effectively locating the fault even when the fault characteristics are not obvious. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0057] Figure 1 A schematic diagram of a flow chart of a distribution network fault detection method based on multi-source information fusion provided in Embodiment 1 of the present invention;

[0058] Figure 2 A schematic diagram of the structure of a distribution network fault detection system based on multi-source information fusion provided in Example 2 of the present invention;

[0059] Figure 3 A schematic diagram of the structure of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0060] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0061] Example 1

[0062] Figure 1 A schematic flow chart of a distribution network fault detection method based on multi-source information fusion provided in Embodiment 1 of the present invention, wherein the distribution network fault detection method based on multi-source information fusion comprises the following steps:

[0063] Step S1, acquiring power distribution data of a power distribution terminal, and extracting transient high-frequency voltage information from the power distribution data;

[0064] Step S2, using compressed sensing theory to calculate and analyze the transient high-frequency voltage information to obtain the electrical quantity fault degree;

[0065] Step S3: Obtain manufacturer equipment data and equipment operation data, analyze the manufacturer equipment data and equipment operation data, and obtain equipment failure degree;

[0066] Step S4: establishing a distribution network topology map, and fusing the electrical fault degree and the equipment fault degree based on the distribution network topology map to obtain fusion information;

[0067] Step S5: perform fault detection on the fused information to obtain distribution network fault information.

[0068] It should be noted that in a complex distribution network, due to the lack of measurement points and the fact that fault characteristics are greatly affected by the control strategy of power electronic equipment, it is proposed to extract transient high-frequency voltage information from the raw data collected by distribution automation equipment, so as to capture the transient response when a fault occurs, and provide fault detection data that is not affected by the control strategy and conversion resistance of the converter for subsequent distribution network fault detection.

[0069] Compressed sensing theory can recover high-frequency information from sparsely sampled data, which is beneficial for processing electrical data distorted by noise interference. By calculating the fault degree of electrical quantities, faults can be accurately identified even in the case of data distortion and noise interference.

[0070] Since there are many distribution terminal manufacturers currently operating in power supply companies, the debugging software and debugging methods of each manufacturer are very different, and even different models of equipment from the same manufacturer are very different. The compatibility of each device is poor due to problems such as protocol implementation degree and point table inconsistency. Therefore, this method proposes to use the manufacturer's equipment data and equipment operation data and analyze them. Through analysis, the equipment fault degree information can be obtained, which helps to understand the cause and possibility of the fault from the equipment level.

[0071] Finally, fault detection can be performed by analyzing the fused information, accurately locating the faulty components and fault probabilities in the distribution network, and achieving effective fault location even when the fault characteristics are not obvious.

[0072] In an optional embodiment, extracting transient high-frequency voltage information from the power distribution data includes the following steps:

[0073] Step S11, dividing the power distribution data into sections according to the interval time to obtain time series node data;

[0074] Step S12, filtering out the time series nodes whose change rate is greater than the change rate threshold from the time series node data, and calculating the average interval value between the time series nodes;

[0075] Step S13, using the average interval value as the size of the sliding window to extract transient high-frequency voltage from the time series node data, to obtain high-frequency data of the time series nodes and high-frequency data between time series nodes;

[0076] Step S14, equating the high-frequency data between the time series nodes to the adjacent time series nodes to generate equivalent high-frequency data of the time series nodes;

[0077] Step S15, synthesizing the timing node data and the equivalent timing node high-frequency data to obtain transient high-frequency voltage information.

[0078] It should be noted that the time series nodes with a change rate greater than the change rate threshold are screened out from the divided time series node data. By screening the time series nodes with a change rate greater than the change rate threshold, transient high-frequency voltage events in the distribution system can be more accurately identified. The average interval value as the window size can more accurately capture the local features and patterns in the data. This method helps to identify and extract time series nodes related to the change rate threshold, thereby improving the accuracy of the analysis results; at the same time, using the average interval value as the window size helps to maintain the continuity and integrity of the data, ensuring that the number of data points in the window remains relatively stable during the movement of the sliding window, thereby reducing data jumps caused by changes in the window size.

[0079] In addition to faults occurring at timing nodes, faults between timing nodes are also a source of faults. Unlike faults on timing nodes, faults between timing nodes cannot be reflected on nodes, resulting in the risk of missed detection and misdetection in the subsequent identification of electrical quantity faults. Therefore, it is necessary to make the high-frequency data between timing nodes equivalent to the adjacent timing nodes, while reducing the discontinuity of the data and improving the overall quality of the data, and avoiding missed detection of faults between timing nodes. By combining timing node data and equivalent timing node high-frequency data, more comprehensive transient high-frequency voltage information can be obtained, which helps to deeply analyze and understand high-frequency transient phenomena in the distribution system, and provide support for the stable operation and fault diagnosis of the power system. The problem of effective information loss that may occur during the detection process is solved.

[0080] In an optional embodiment, the high-frequency data between the time series nodes is equivalent to the time series nodes adjacent thereto, including the following steps:

[0081] Step S141, selecting the high-frequency data between the i-th time series nodes, and determining the high-frequency data between the j-th time series nodes and the high-frequency data between the j+1-th time series nodes adjacent to the high-frequency data between the i-th time series nodes;

[0082] Step S142, establishing an equivalent relationship between faults of timing nodes, bringing the high-frequency data of the i-th timing node, the high-frequency data of the j-th timing node, and the high-frequency data of the j+1-th timing node into the equivalent relationship between faults of timing nodes to obtain an equivalent relationship distribution;

[0083] Step S143: distribute the high-frequency data between the i-th timing nodes to the j-th timing node high-frequency data and the j+1-th timing node high-frequency data based on the equivalent relationship distribution, and obtain the j-th equivalent timing node high-frequency data and the j+1-th equivalent timing node high-frequency data.

[0084] It should be noted that in addition to the faults that occur at the timing nodes, the faults between the timing nodes are also the source of faults. Unlike the faults on the timing nodes, they cannot be reflected on the nodes, resulting in the risk of missed detection and false detection in the subsequent identification of electrical quantity faults. Therefore, it is necessary to process the high-frequency data between the timing nodes so that they are equivalent to the adjacent timing nodes, and distribute the high-frequency data between the timing nodes to the adjacent timing nodes according to a certain equivalent relationship. In this way, the high-frequency data on the timing nodes can be analyzed to complete the accurate detection of the entire timing.

[0085] Among them, the i-th timing node is located in the middle position between the j-th timing node and the j+1-th timing node. If a fault occurs at this position, it can be equivalent to the subsequent effect caused by the fault of the j-th timing node and the predecessor of the j+1-th timing node fault.

[0086] In this embodiment, the fault equivalence relationship between sequential nodes can be constructed as follows:

[0087] U j→j+1 =-λU j→i +(1-λ)U i→j+1

[0088]

[0089] In the above formula, U j→j+1 is the voltage difference from the jth timing node to the j+1th timing node, U j→i is the voltage difference between the jth timing node and the ith timing node, U i→j+1 is the voltage difference from the ith timing node to the j+1th timing node, λ is the fault location coefficient, Δt is the fault time, and T is the interval time.

[0090] Among them, the failure time is the process time relative to the jth timing node.

[0091] In an optional embodiment, the transient high-frequency voltage information is calculated and analyzed using compressed sensing theory, including the following steps:

[0092] Step S21, determining the number of decomposition layers, and decomposing the transient high-frequency voltage information based on the number of decomposition layers to obtain decomposed transient high-frequency voltage information;

[0093] Step S22, based on the compressed sensing theory, the distribution probability of each layer of decomposed transient high-frequency voltage information is calculated in sequence, and the distribution probability of the last layer is used as the fault value of the corresponding sliding window;

[0094] Step S23, assign the fault degree of the first sliding window to the electrical quantity fault degree, move the sliding window, and compare the fault values ​​in two adjacent sliding windows. If the fault value in the adjacent sliding window is greater than the electrical quantity fault degree, assign the fault value in the adjacent sliding window to the electrical quantity fault degree.

[0095] It should be noted that the transient high-frequency voltage information generated by faults in distribution networks is often sparse, that is, most signal components do not carry valid information at the moment of the fault. Therefore, based on the compressed sensing theory, these features can be more accurately extracted from complex signals, thereby improving the accuracy of fault location.

[0096] In an optional embodiment, before calculating and analyzing the transient high-frequency voltage information using the compressed sensing theory, the method further includes: performing node reconstruction on the transient high-frequency voltage information, wherein the node reconstruction includes:

[0097]

[0098] In the above formula, is the transient high-frequency voltage information of the jth time node after reconstruction, U j is the transient high-frequency voltage information of the jth timing node, t is the average interval value, and T is the interval time.

[0099] It should be noted that when using compressed sensing theory to calculate and analyze transient high-frequency voltage information, the amplitude data in the transient high-frequency voltage information will change with the fault conditions, resulting in inaccurate data calculation during analysis, resulting in large errors in the fault degree of the electrical quantity obtained. Therefore, it is necessary to reconstruct the nodes of the transient high-frequency voltage information to ensure the correctness of the calculation.

[0100] In an optional embodiment, analyzing the manufacturer's equipment data and equipment operation data includes the following steps:

[0101] Step S31, calculating the failure rate of the manufacturer's equipment data;

[0102] Step S32, pre-processing the equipment operation data to obtain analysis data;

[0103] Step S33, extracting fault features from the analysis data, analyzing the fault features, and obtaining fault distribution features and fault variation features;

[0104] Step S34, comprehensively analyzing the failure rate, the failure distribution characteristics and the failure variation characteristics to obtain the equipment failure degree.

[0105] Furthermore, the failure rate, the failure distribution characteristics and the failure change characteristics are comprehensively considered, including:

[0106]

[0107] In the above formula, D i is the equipment failure degree of the i-th equipment, α i is the failure rate of the ith device, is the mth fault interval of the ith device, M is the number of fault intervals, (TD i ) min is the minimum failure interval of the ith device, R j is the fault value of the jth device.

[0108] The fault distribution feature is represented by a fault value within a certain range. In this embodiment, the 2k devices adjacent to the i-th device are taken as an example to calculate the device fault conditions in the 2k adjacent devices as a representation of the device fault degree. Furthermore, since the closer the device is, the higher the correlation between the fault condition of the i-th device is, the fault value is multiplied by The effect of characterization distance on fault distribution characteristics.

[0109] Furthermore, in order to reflect the fault change characteristics, the fault interval time of the equipment is taken as an example, and the ratio of the minimum fault interval time to the total fault interval time is taken as the fault change characteristic of the equipment to reflect the frequency of faults of the i-th equipment.

[0110] In an optional embodiment, the electrical fault degree and the device fault degree are merged based on the distribution network topology diagram, comprising the following steps:

[0111] Step S41, normalizing the electrical fault degree and the equipment fault degree to obtain a standardized fault characteristic and an equipment fault characteristic;

[0112] Step S42, randomly selecting a topological node from the distribution network topology map, performing fault degree fusion processing on the standardized fault characteristics on the topological node and the equipment fault characteristics to obtain a fused fault degree;

[0113] Step S43: performing fault identification on the fused fault degree, and determining the distribution network fault according to the fault identification result.

[0114] Further, a topological node is randomly selected from the distribution network topological map, and a fault degree fusion process is performed on the standardized fault characteristics on the topological node and the device fault characteristics, including:

[0115]

[0116] α+β=1

[0117] In the above formula, θ n(t) is the fusion fault degree of the nth topological node at time t, is the equipment failure characteristic of the nth topological node at time t, is the standardized fault characteristic of the nth topological node at time t, and α and β are the fault coefficients.

[0118] When the fused fault degree of the nth topological node at time t exceeds the fault threshold, it means that the nth topological node has a fault at time t in the distribution network topology diagram, and it can be found that the device corresponding to the topological node in the distribution network has a fault.

[0119] Example 2

[0120] Figure 2 A schematic diagram of the structure of a distribution network fault detection system based on multi-source information fusion provided in Example 2 of the present invention, such as Figure 2 As shown, the distribution network fault detection system based on multi-source information fusion includes:

[0121] A transient extraction module, used to obtain power distribution data of a power distribution terminal and extract transient high-frequency voltage information from the power distribution data;

[0122] An electrical fault module, used to calculate and analyze the transient high-frequency voltage information using compressed sensing theory to obtain an electrical quantity fault degree;

[0123] An equipment failure module is used to obtain manufacturer equipment data and equipment operation data, analyze the manufacturer equipment data and equipment operation data, and obtain the equipment failure degree;

[0124] A fusion module, used for establishing a distribution network topology map, and fusing the electrical fault degree and the equipment fault degree based on the distribution network topology map to obtain fusion information;

[0125] The detection module is used to perform fault detection on the fused information to obtain distribution network fault information.

[0126] Example 3

[0127] Figure 3 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention is shown in FIG. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the computer device can be one or more. Figure 3 A processor 21 is taken as an example; the processor 21, the memory 22, the input device 23 and the output device 24 in the electronic device can be connected by a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0128] The memory 22 is a computer-readable storage medium that can be used to store software programs, computer executable programs, and modules. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 22, that is, the distribution network fault detection method based on multi-source information fusion of Example 1 is implemented.

[0129] The memory 22 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 22 may further include a memory remotely arranged relative to the processor 21, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0130] The input device 23 can be used to receive the ID and password input by the user, etc. The output device 24 is used to output the network configuration page.

[0131] Example 4

[0132] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-executable instructions, when executed by a computer processor, are used to implement the distribution network fault detection method based on multi-source information fusion as provided in Embodiment 1.

[0133] An embodiment of the present invention provides a storage medium containing computer executable instructions, and its computer executable instructions are not limited to the method operations provided in Example 1, and can also execute related operations in the distribution network fault detection method based on multi-source information fusion provided in any embodiment of the present invention.

[0134] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A distribution network fault detection method based on multi-source information fusion, characterized in that: The steps include: Step S1, acquiring power distribution data of a power distribution terminal, and extracting transient high-frequency voltage information from the power distribution data; Step S2, using compressed sensing theory to calculate and analyze the transient high-frequency voltage information to obtain the electrical quantity fault degree; Step S3: Obtain manufacturer equipment data and equipment operation data, analyze the manufacturer equipment data and equipment operation data, and obtain equipment failure degree; Step S4: establishing a distribution network topology map, and fusing the electrical fault degree and the equipment fault degree based on the distribution network topology map to obtain fusion information; Step S5: perform fault detection on the fused information to obtain distribution network fault information.

2. The distribution network fault detection method based on multi-source information fusion according to claim 1 is characterized in that: Extracting transient high-frequency voltage information from the power distribution data includes the following steps: Step S11, dividing the power distribution data into sections according to the interval time to obtain time series node data; Step S12, filtering out the time series nodes whose change rate is greater than the change rate threshold from the time series node data, and calculating the average interval value between the time series nodes; Step S13, using the average interval value as the size of the sliding window to extract transient high-frequency voltage from the time series node data, to obtain high-frequency data of the time series nodes and high-frequency data between time series nodes; Step S14, equating the high-frequency data between the time series nodes to the adjacent time series nodes to generate equivalent high-frequency data of the time series nodes; Step S15, synthesizing the timing node data and the equivalent timing node high-frequency data to obtain transient high-frequency voltage information.

3. The distribution network fault detection method based on multi-source information fusion according to claim 2 is characterized in that: The high-frequency data between the time series nodes is equivalent to the time series nodes adjacent thereto, including the following steps: Step S141, selecting the high-frequency data between the i-th time series nodes, and determining the high-frequency data between the j-th time series nodes and the high-frequency data between the j+1-th time series nodes adjacent to the high-frequency data between the i-th time series nodes; Step S142, establishing an equivalent relationship between faults of timing nodes, bringing the high-frequency data of the i-th timing node, the high-frequency data of the j-th timing node, and the high-frequency data of the j+1-th timing node into the equivalent relationship between faults of timing nodes to obtain an equivalent relationship distribution; Step S143: distribute the high-frequency data between the i-th timing nodes to the j-th timing node high-frequency data and the j+1-th timing node high-frequency data based on the equivalent relationship distribution, and obtain the j-th equivalent timing node high-frequency data and the j+1-th equivalent timing node high-frequency data.

4. The distribution network fault detection method based on multi-source information fusion according to claim 1 is characterized in that: The transient high-frequency voltage information is calculated and analyzed using compressed sensing theory, including the following steps: Step S21, determining the number of decomposition layers, and decomposing the transient high-frequency voltage information based on the number of decomposition layers to obtain decomposed transient high-frequency voltage information; Step S22, based on the compressed sensing theory, the distribution probability of each layer of decomposed transient high-frequency voltage information is calculated in sequence, and the distribution probability of the last layer is used as the fault value of the corresponding sliding window; Step S23, assign the fault degree of the first sliding window to the electrical quantity fault degree, move the sliding window, and compare the fault values ​​in two adjacent sliding windows. If the fault value in the adjacent sliding window is greater than the electrical quantity fault degree, assign the fault value in the adjacent sliding window to the electrical quantity fault degree.

5. The distribution network fault detection method based on multi-source information fusion according to claim 4 is characterized in that: Before calculating and analyzing the transient high-frequency voltage information using the compressed sensing theory, the method further includes: performing node reconstruction on the transient high-frequency voltage information, wherein the node reconstruction includes: In the above formula, is the transient high-frequency voltage information of the jth time node after reconstruction, U j is the transient high-frequency voltage information of the jth timing node, t is the average interval value, and T is the interval time.

6. The distribution network fault detection method based on multi-source information fusion according to claim 1 is characterized in that: Analyzing the manufacturer's equipment data and equipment operation data includes the following steps: Step S31, calculating the failure rate of the manufacturer's equipment data; Step S32, pre-processing the equipment operation data to obtain analysis data; Step S33, extracting fault features from the analysis data, analyzing the fault features, and obtaining fault distribution features and fault variation features; Step S34, comprehensively analyzing the failure rate, the failure distribution characteristics and the failure variation characteristics to obtain the equipment failure degree.

7. The distribution network fault detection method based on multi-source information fusion according to claim 1 is characterized in that: The electrical fault degree and the equipment fault degree are integrated based on the distribution network topology diagram, comprising the following steps: Step S41, normalizing the electrical fault degree and the equipment fault degree to obtain a standardized fault characteristic and an equipment fault characteristic; Step S42, randomly selecting a topological node from the distribution network topology map, performing fault degree fusion processing on the standardized fault characteristics on the topological node and the equipment fault characteristics to obtain a fused fault degree; Step S43: performing fault identification on the fused fault degree, and determining the distribution network fault according to the fault identification result.

8. The distribution network fault detection system based on multi-source information fusion is characterized by: include: A transient extraction module, used to obtain power distribution data of a power distribution terminal and extract transient high-frequency voltage information from the power distribution data; An electrical fault module, used to calculate and analyze the transient high-frequency voltage information using compressed sensing theory to obtain an electrical quantity fault degree; An equipment failure module is used to obtain manufacturer equipment data and equipment operation data, analyze the manufacturer equipment data and equipment operation data, and obtain the equipment failure degree; A fusion module, used for establishing a distribution network topology map, and fusing the electrical fault degree and the equipment fault degree based on the distribution network topology map to obtain fusion information; The detection module is used to perform fault detection on the fused information to obtain distribution network fault information.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the distribution network fault detection method based on multi-source information fusion as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the distribution network fault detection method based on multi-source information fusion as described in any one of claims 1 to 7 is implemented.

Images