Diagnosis method and system suitable for intelligent fault detection of power distribution network

Abstract

The invention relates to the technical field of power distribution networks, in particular to a diagnosis method and system suitable for intelligent fault detection of a power distribution network, and the method comprises the steps: collecting the visual data of power distribution nodes which N using main bodies belong to, and constructing a dynamic grid visual frame of the power distribution network; calculating a real-time fault state value of the power distribution network, importing the fault state value of the power distribution network into a fault state comparison strategy, and judging whether the current power distribution network reaches a fault state or not; constructing a fault prediction model to predict visual data after the n time nodes, obtaining a power distribution network fault state value after the n time nodes, performing structure adjustment on the fault prediction model, and outputting a fault adjustment model; and adjusting the equipment state of the power distribution node according to the equipment operation state adjustment value output by the fault adjustment model.

Description

Background Art

[0002] As an important part of the power system, the accuracy and real-time performance of fault diagnosis of the distribution network directly affects the operational safety and stability of the power system. With the development of intelligent technology, traditional fault diagnosis methods are gradually replaced by more intelligent and automated solutions. In the existing technology, fault detection mainly relies on data from equipment such as protection devices and relays, but due to the complexity and diversity of the distribution network, traditional methods have certain limitations.

[0003] Problems existing in the existing technology: Traditional fault detection methods are mainly based on the physical data of the equipment, such as operating status, action of protection devices and relays, etc., which are difficult to fully reflect the complex situation of the distribution network, resulting in low accuracy of fault judgment; existing fault diagnosis methods are generally based on the analysis of historical data and static status, which cannot effectively predict possible future fault risks and lack forward-looking adjustment of the equipment operating status. Summary of the invention

[0004] The main purpose of the present invention is to provide a diagnostic method suitable for intelligent fault detection in distribution networks, and further to provide a diagnostic system suitable for intelligent fault detection in distribution networks that can run and implement the above method, so as to effectively solve the above problems mentioned in the background technology.

[0005] The technical solution of the present invention is as follows:

[0006] In a first aspect, a diagnostic method suitable for intelligent fault detection in a distribution network is proposed, the method comprising the following steps:

[0007] S1. Collect visualization data of distribution nodes belonging to N users and build a dynamic grid visualization framework of the distribution network;

[0008] S2. Calculate the real-time fault state value of the distribution network, import the fault state value of the distribution network into the fault state comparison strategy, and determine whether the current distribution network has reached a fault state;

[0009] S3, construct a fault prediction model to predict the visualized data after n time nodes, obtain the distribution network fault state value after n time nodes, and adjust the structure of the fault prediction model to output the fault adjustment model;

[0010] S4. According to the equipment operation status adjustment value output by the fault adjustment model under the safe state of the distribution network, the equipment status of the distribution node is adjusted.

[0011] A further improvement of the present invention is that the dynamic grid visualization framework in S1 includes: N distribution nodes belonging to the user entity, wherein the visualization data of the distribution nodes includes real-time equipment operation status data, real-time equipment operation environment data, real-time protection device and relay data, real-time fault status value data, and real-time fault adjustment data.

[0012] A further improvement of the present invention is that S2 comprises the following specific steps:

[0013] S21, extracting real-time equipment operation status data sb(i), real-time equipment operation environment data hj(i), real-time protection device and relay data bh(i), and calculating the real-time fault status value D(i) of the distribution network. The specific formula is:

[0014]

[0015] Among them, SB is the comparison value of equipment operation status fault, HJ is the comparison value of equipment operation environment fault, BH is the comparison value of protection device and relay fault, a 1 、a 2 is a constant;

[0016] S22, preset a fault state threshold δ, when D(i)<δ, determine that the distribution network has not reached a fault state, when D(i)≥δ, determine that the distribution network has reached a fault state, and proceed to step S3.

[0017] A further improvement of the present invention is that S3 comprises the following specific steps:

[0018] S31, the real-time equipment operation status data sb(i), the real-time equipment operation environment data hj(i), the real-time protection device and relay data bh(i), the real-time fault state value D(i) of the distribution network are respectively formed into sample pairs with the time node i and a fault prediction model is constructed, and the equipment operation status data sb(i+n), the equipment operation environment data hj(i+n), the protection device and relay data bh(i+n), and the fault state value D(i+n) after n time nodes are output, and the value of n is the mean value of the historical fault adjustment time of the distribution network;

[0019] S32, calculate the distribution network fault state value after n time nodes, the calculation formula is:

[0020]

[0021] S33. Compare D(i+n) with the preset fault state comparison threshold δ. When D(i+n)<δ, it is determined that the distribution network will not reach a fault state after n time nodes; when D(n+1)≥δ, the distribution network will reach a fault state after n time nodes.

[0022] A further improvement of the present invention is that the fault prediction model in S3 is a deep neural network model, which includes an input layer, a hidden layer, and an output layer, wherein the number of nodes in the input layer, the hidden layer, and the output layer are 3, 9, and 1, respectively.

[0023] A further improvement of the present invention is that S3 further includes:

[0024] S34, respectively obtain the safety range of the equipment operation status data sb(i), the equipment operation environment data hj(i), the protection device and the relay data bh(i) and import them into the fault state value calculation formula to obtain the safety range of the distribution network fault state value D(i), and extract the distribution network fault state value with the largest difference from the fault state threshold within the safety range;

[0025] S35, adjusting the structure of the fault prediction model, adjusting the number of nodes of the input layer, hidden layer and output layer of the fault prediction model to 2, 9 and 2 respectively, obtaining a fault adjustment model, inputting the distribution network fault state value with the largest difference from the fault state threshold within the safety range and the real-time equipment operation environment data into the fault adjustment model, outputting the optimal equipment operation state data under the safe state of the distribution network, and outputting the protection device and relay data adjustment value at the same time;

[0026] S36. Adjust the protection devices and relays of the distribution network according to the optimal equipment operation status data under the safe state of the distribution network.

[0027] In the second aspect, a diagnostic system suitable for intelligent fault detection in distribution networks is proposed, the system comprising: an acquisition construction module, a fault calculation module, a fault prediction module, and a fault adjustment module;

[0028] The acquisition and construction module is used to collect visualization data of the distribution nodes to which N users belong, and to construct a dynamic grid visualization framework of the distribution network;

[0029] The fault calculation module is used to calculate the real-time fault state value of the distribution network, import the fault state value of the distribution network into the fault state comparison strategy, and determine whether the current distribution network has reached a fault state;

[0030] The fault prediction module is used to construct a fault prediction model to predict the visualized data after n time nodes, obtain the distribution network fault state value after n time nodes, and perform structural adjustment on the fault prediction model to output a fault adjustment model;

[0031] The fault adjustment module is used to adjust the device state of the power distribution node according to the device operation state adjustment value output by the fault adjustment model.

[0032] The technical effects of the present invention are as follows:

[0033] A diagnostic method suitable for intelligent fault detection in distribution networks is constructed. By collecting visualization data of distribution nodes belonging to N users, a dynamic grid visualization framework of the distribution network is constructed. The real-time fault state value of the distribution network is calculated, and the fault state value of the distribution network is imported into the fault state comparison strategy to determine whether the current distribution network has reached a fault state. A fault prediction model is constructed to predict the visualization data after n time nodes, and the fault state value of the distribution network after n time nodes is obtained. The fault prediction model is structurally adjusted to output a fault adjustment model. According to the equipment operation state adjustment value output by the fault adjustment model, the equipment state of the distribution node is adjusted. The comprehensiveness of data and the precision of monitoring are improved. The monitoring data covers hardware, system status and objective environment, and the overall fault condition of the distribution network is comprehensively evaluated. The fault detection process of the distribution network is quantitatively evaluated, making the detection results more intuitive, improving the work efficiency of managers, and contributing to the further resolution of system faults. The solution can not only predict future fault states, but also output the optimal operation state of the equipment in real time through the fault adjustment model, help adjust the equipment state of the distribution node, and ensure that the entire system operates within a safe range. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0035] Figure 1 A schematic flow chart of a diagnostic method for intelligent fault detection in a distribution network according to Embodiment 1 of the present invention;

[0036] Figure 2 This is a structural diagram of a diagnostic system suitable for intelligent fault detection in a distribution network according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0037] Embodiment 1:

[0038] This embodiment constructs a diagnostic method suitable for intelligent fault detection of distribution network, by collecting visualization data of distribution nodes belonging to N users, constructing a dynamic grid visualization framework of distribution network; calculating the real-time fault state value of distribution network, importing the fault state value of distribution network into fault state comparison strategy, judging whether the current distribution network reaches fault state; constructing fault prediction model to predict visualization data after n time nodes, obtaining fault state value of distribution network after n time nodes, and adjusting the structure of fault prediction model, outputting fault adjustment model; adjusting the equipment state of distribution node according to the equipment operation state adjustment value output by fault adjustment model. It improves the comprehensiveness of data and the precision of monitoring, the monitoring data covers hardware, system state and objective environment, comprehensively evaluates the overall fault condition of distribution network, quantifies and evaluates the fault detection process of distribution network, makes the detection result more intuitive, improves the work efficiency of management personnel, and helps to further solve system faults; this scheme can not only predict future fault state, but also output the optimal operation state of equipment in real time through fault adjustment model, helps to adjust the equipment state of distribution node, and ensures that the whole system operates within a safe range.

[0039] A diagnostic method suitable for intelligent fault detection in distribution networks, such as Figure 1 As shown, the following specific steps are included:

[0040] S1. Collect visualization data of distribution nodes belonging to N users and build a dynamic grid visualization framework of the distribution network;

[0041] S2. Calculate the real-time fault state value of the distribution network, import the fault state value of the distribution network into the fault state comparison strategy, and determine whether the current distribution network has reached a fault state;

[0042] S3, construct a fault prediction model to predict the visualized data after n time nodes, obtain the distribution network fault state value after n time nodes, and adjust the structure of the fault prediction model to output the fault adjustment model;

[0043] S4. According to the equipment operation status adjustment value output by the fault adjustment model under the safe state of the distribution network, the equipment status of the distribution node is adjusted.

[0044] In this embodiment, the dynamic grid visualization framework in S1 includes: N distribution nodes belonging to the user entity, wherein the visualization data of the distribution nodes includes real-time equipment operation status data, real-time equipment operation environment data, real-time protection device and relay data, real-time fault status value data, and real-time fault adjustment data.

[0045] In this embodiment, S2 includes the following specific steps:

[0046] S21, extracting real-time equipment operation status data sb(i), real-time equipment operation environment data hj(i), real-time protection device and relay data bh(i), and calculating the real-time fault status value D(i) of the distribution network. The specific formula is:

[0047]

[0048] Among them, SB is the comparison value of equipment operation status fault, HJ is the comparison value of equipment operation environment fault, BH is the comparison value of protection device and relay fault, a 1 、a 2 is a constant;

[0049] S22, preset a fault state threshold δ, when D(i)<δ, determine that the distribution network has not reached a fault state, when D(i)≥δ, determine that the distribution network has reached a fault state, and proceed to step S3.

[0050] In this embodiment, S3 includes the following specific steps:

[0051] S31, the real-time equipment operation status data sb(i), the real-time equipment operation environment data hj(i), the real-time protection device and relay data bh(i), the real-time fault state value D(i) of the distribution network are respectively formed into sample pairs with the time node i and a fault prediction model is constructed, and the equipment operation status data sb(i+n), the equipment operation environment data hj(i+n), the protection device and relay data bh(i+n), and the fault state value D(i+n) after n time nodes are output, and the value of n is the mean value of the historical fault adjustment time of the distribution network;

[0052] S32, calculate the distribution network fault state value after n time nodes, the calculation formula is:

[0053]

[0054] S33. Compare D(i+n) with the preset fault state comparison threshold δ. When D(i+n)<δ, it is determined that the distribution network will not reach a fault state after n time nodes; when D(n+1)≥δ, the distribution network will reach a fault state after n time nodes.

[0055] In this embodiment, the fault prediction model in S3 is a deep neural network model, which includes an input layer, a hidden layer, and an output layer, wherein the number of nodes in the input layer, the hidden layer, and the output layer are 3, 9, and 1, respectively.

[0056] In this embodiment, S3 further includes:

[0057] S34, respectively obtain the safety range of the equipment operation status data sb(i), the equipment operation environment data hj(i), the protection device and the relay data bh(i) and import them into the fault state value calculation formula to obtain the safety range of the distribution network fault state value D(i), and extract the distribution network fault state value with the largest difference from the fault state threshold within the safety range;

[0058] S35, adjusting the structure of the fault prediction model, adjusting the number of nodes of the input layer, hidden layer and output layer of the fault prediction model to 2, 9 and 2 respectively, obtaining a fault adjustment model, inputting the distribution network fault state value with the largest difference from the fault state threshold within the safety range and the real-time equipment operation environment data into the fault adjustment model, outputting the optimal equipment operation state data under the safe state of the distribution network, and outputting the protection device and relay data adjustment value at the same time;

[0059] S36. Adjust the protection devices and relays of the distribution network according to the optimal equipment operation status data under the safe state of the distribution network.

[0060] Embodiment 2:

[0061] This embodiment proposes a diagnostic system suitable for intelligent fault detection in distribution networks, such as Figure 2 As shown, it includes: an acquisition construction module, a fault calculation module, a fault prediction module, and a fault adjustment module;

[0062] The acquisition and construction module is used to collect visualization data of the distribution nodes to which N users belong, and to construct a dynamic grid visualization framework of the distribution network;

[0063] The fault calculation module is used to calculate the real-time fault state value of the distribution network, import the fault state value of the distribution network into the fault state comparison strategy, and determine whether the current distribution network has reached a fault state;

[0064] The fault prediction module is used to construct a fault prediction model to predict the visualized data after n time nodes, obtain the distribution network fault state value after n time nodes, and perform structural adjustment on the fault prediction model to output a fault adjustment model;

[0065] The fault adjustment module is used to adjust the device state of the power distribution node according to the device operation state adjustment value output by the fault adjustment model.

[0066] Embodiment 3:

[0067] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned diagnostic method suitable for intelligent fault detection in a distribution network by calling the computer program stored in the memory.

[0068] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement a diagnostic method suitable for intelligent fault detection of distribution networks provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0069] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), and it can also be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0070] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0071] The present invention is described with reference to flowcharts and block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process or block in the flowchart and block diagram, as well as the combination of processes and blocks in the flowchart or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 Process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 Process or multiple processes and boxes Figure 1 A step that specifies a function in one or more boxes.

[0073] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A diagnostic method suitable for intelligent fault detection in a distribution network, characterized in that: The specific steps include: S1. Collect visualization data of distribution nodes belonging to N users and build a dynamic grid visualization framework of the distribution network; S2. Calculate the real-time fault state value of the distribution network, import the fault state value of the distribution network into the fault state comparison strategy, and determine whether the current distribution network has reached a fault state; S3, construct a fault prediction model to predict the visualized data after n time nodes, obtain the distribution network fault state value after n time nodes, and adjust the structure of the fault prediction model to output the fault adjustment model; S4. Adjust the equipment status of the distribution node according to the equipment operation status adjustment value output by the fault adjustment model under the safe state of the distribution network.

2. A diagnostic method suitable for intelligent fault detection in a distribution network according to claim 1, characterized in that: The dynamic grid visualization framework in S1 includes: N distribution nodes belonging to the user entities, wherein the visualization data of the distribution nodes includes real-time equipment operation status data, real-time equipment operation environment data, real-time protection device and relay data, real-time fault status value data, and real-time fault adjustment data.

3. A diagnostic method suitable for intelligent fault detection in a distribution network according to claim 2, characterized in that: The S2 comprises the following specific steps: S21, extracting real-time equipment operation status data sb(i), real-time equipment operation environment data hj(i), real-time protection device and relay data bh(i), and calculating the real-time fault status value D(i) of the distribution network. The specific formula is: Among them, SB is the equipment operation status fault comparison value, HJ is the equipment operation environment fault comparison value, BH is the protection device and relay fault comparison value, a1 and a2 are constants; S22, preset a fault state threshold δ, when D(i)<δ, determine that the distribution network has not reached a fault state, when D(i)≥δ, determine that the distribution network has reached a fault state, and proceed to step S3.

4. A diagnostic method suitable for intelligent fault detection in a distribution network according to claim 3, characterized in that: The S3 includes the following specific steps: S31, the real-time equipment operation status data sb(i), the real-time equipment operation environment data hj(i), the real-time protection device and relay data bh(i), the real-time fault state value D(i) of the distribution network are respectively formed into sample pairs with the time node i and a fault prediction model is constructed, and the equipment operation status data sb(i+n), the equipment operation environment data hj(i+n), the protection device and relay data bh(i+n), and the fault state value D(i+n) after n time nodes are output, and the value of n is the mean value of the historical fault adjustment time of the distribution network; S32, calculate the distribution network fault state value after n time nodes, the calculation formula is: S33. Compare D(i+n) with the preset fault state comparison threshold δ. When D(i+n)<δ, it is determined that the distribution network will not reach a fault state after n time nodes; when D(n+1)≥δ, the distribution network will reach a fault state after n time nodes.

5. A diagnostic method suitable for intelligent fault detection in a distribution network according to claim 4, characterized in that: The fault prediction model in S3 is a deep neural network model, which includes an input layer, a hidden layer, and an output layer, wherein the number of nodes in the input layer, the hidden layer, and the output layer are 3, 9, and 1, respectively.

6. A diagnostic method suitable for intelligent fault detection in a distribution network according to claim 5, characterized in that: The S3 further includes: S34, respectively obtain the safety range of the equipment operation status data sb(i), the equipment operation environment data hj(i), the protection device and the relay data bh(i) and import them into the fault state value calculation formula to obtain the safety range of the distribution network fault state value D(i), and extract the distribution network fault state value with the largest difference from the fault state threshold within the safety range; S35, adjusting the structure of the fault prediction model, adjusting the number of nodes of the input layer, hidden layer and output layer of the fault prediction model to 2, 9 and 2 respectively, obtaining a fault adjustment model, inputting the distribution network fault state value with the largest difference from the fault state threshold within the safety range and the real-time equipment operation environment data into the fault adjustment model, outputting the optimal equipment operation state data under the safe state of the distribution network, and outputting the protection device and relay data adjustment value at the same time; S36. Adjust the protection devices and relays of the distribution network according to the optimal equipment operation status data under the safe state of the distribution network.

7. A diagnostic system for intelligent fault detection in a distribution network, which is implemented based on a diagnostic method for intelligent fault detection in a distribution network as claimed in any one of claims 1 to 6, characterized in that: The system includes: an acquisition and construction module, a fault calculation module, a fault prediction module, and a fault adjustment module; The acquisition and construction module is used to collect visualization data of the distribution nodes to which N users belong, and to construct a dynamic grid visualization framework of the distribution network; The fault calculation module is used to calculate the real-time fault state value of the distribution network, import the fault state value of the distribution network into the fault state comparison strategy, and determine whether the current distribution network has reached a fault state; The fault prediction module is used to construct a fault prediction model to predict the visualized data after n time nodes, obtain the distribution network fault state value after n time nodes, and perform structural adjustment on the fault prediction model to output a fault adjustment model; The fault adjustment module is used to adjust the device state of the power distribution node according to the device operation state adjustment value output by the fault adjustment model.

Images