Power distribution network fault detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a three-phase imbalance-based power distribution network fault detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining first sample power grid data of a reference power distribution network during normal operation and second sample power grid data of the reference power distribution network during various faults; respectively identifying parameter features corresponding to the first sample power grid data and the second sample power grid data to obtain a first parameter feature and a second parameter feature; constructing a fault detection model according to the first parameter feature and the second parameter feature; and performing fault detection on a target power distribution network through the fault detection model. According to the scheme, the power distribution network fault detection efficiency based on three-phase imbalance can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of distribution network detection, and in particular to a distribution network fault detection method, device, electronic device and storage medium based on three-phase imbalance. Background Art

[0002] There are a series of problems in the distribution network system, among which the most prominent one is the three-phase imbalance problem. The three-phase imbalance problem is mainly caused by the following reasons: on the one hand, due to the normal operation of the power system, the load of the distribution network gradually increases, but the load is not planned, resulting in uneven distribution of the load in time and space; on the other hand, during the line transformation process, the staff did not distinguish the three-phase lines well, but arbitrarily connected the load to a certain phase, resulting in unbalanced loads in the three-phase lines of the distribution network. Therefore, the analysis of three-phase imbalance is very meaningful. An excellent three-phase imbalance analysis method can quickly and accurately analyze the degree of three-phase imbalance, which is conducive to reducing the power loss of the line, preventing the distribution transformer from generating zero-sequence current, ensuring the safe operation of electrical equipment and improving the efficiency of the motor.

[0003] In the related technology, when performing three-phase balance calculation, it is necessary to collect three-phase electrical quantity data of one cycle, and then use the full-wave Fourier algorithm to perform relatively complex analysis and calculation on the three-phase electrical quantity data of one cycle to obtain the amplitude and phase of each of the three phases, and then obtain the three-phase imbalance of the cycle based on the amplitude and phase of each of the three phases. Finally, based on the three-phase imbalance, it is possible to determine whether the three phases of the cycle are balanced. It can be seen that the current distribution network fault detection scheme based on three-phase imbalance has poor detection efficiency. Summary of the invention

[0004] The embodiments of the present application provide a distribution network fault detection system, method, electronic device and storage medium based on three-phase imbalance, which can improve the detection efficiency of distribution network faults based on three-phase imbalance.

[0005] In a first aspect, an embodiment of the present application provides a distribution network fault detection method based on three-phase imbalance, comprising:

[0006] Acquire first sample grid data of the reference distribution network during normal operation and second sample grid data of the reference distribution network during various types of faults;

[0007] Respectively identifying parameter features corresponding to the first sample power grid data and the second sample power grid data to obtain a first parameter feature and a second parameter feature;

[0008] Constructing a fault detection model according to the first parameter characteristics and the second parameter characteristics;

[0009] Fault detection is performed on the target distribution network using the fault detection model.

[0010] Optionally, in some embodiments of the present application, constructing a fault detection model according to the first parameter feature and the second parameter feature includes:

[0011] Extracting zero-sequence current parameters from the first parameter feature and the second parameter feature respectively to obtain a first zero-sequence current parameter and a second zero-sequence current parameter;

[0012] Get the preset basic detection model;

[0013] The basic detection model is trained according to the first zero-sequence current parameter and the second zero-sequence current parameter to obtain a fault detection model.

[0014] Optionally, in some embodiments of the present application, the training of the basic detection model according to the first zero-sequence current parameter and the second zero-sequence current parameter to obtain a fault detection model includes:

[0015] Determine a distribution network fault corresponding to each second zero-sequence current parameter;

[0016] estimating an estimated distribution network fault corresponding to the second zero-sequence current parameter based on the basic detection model;

[0017] training the basic detection model according to the distribution network fault corresponding to the second zero-sequence current parameter and the estimated distribution network fault corresponding to the second zero-sequence current parameter;

[0018] Verifying the trained detection model using the first zero-sequence current parameter and the distribution network fault corresponding to the first zero-sequence current parameter;

[0019] When the trained detection model passes the verification, the trained detection model is determined as a fault detection model.

[0020] Optionally, in some embodiments of the present application, the performing fault detection on the target distribution network by using the fault detection model includes:

[0021] Obtain zero-sequence current parameters of the target distribution network;

[0022] Based on the fault detection model and the zero-sequence current parameter of the target distribution network, fault detection is performed on the target distribution network.

[0023] Optionally, in some embodiments of the present application, the performing fault detection on the target distribution network based on the fault detection model and the zero-sequence current parameter of the target distribution network includes:

[0024] Based on the fault detection model and the zero-sequence current parameter of the target distribution network, determining whether the target distribution network has a preset type of fault;

[0025] If the target distribution network is not a fault of a preset type, it is detected whether the zero-sequence current parameter of the target distribution network meets a preset condition, so as to perform fault detection on the target distribution network.

[0026] Optionally, in some embodiments of the present application, the method further includes:

[0027] Obtain the basic simulation model and preset distribution network fault parameters;

[0028] The basic simulation model is adjusted according to the distribution network fault parameters to obtain a distribution network fault simulation model;

[0029] The second sample power grid data of the reference distribution network when various types of faults occur is simulated based on the distribution network fault simulation model.

[0030] Optionally, in some embodiments of the present application, after simulating the second sample power grid data of the reference distribution network at various faults based on the distribution network fault simulation model, the method further includes:

[0031] Determining a distribution network fault corresponding to the second sample power grid data;

[0032] deriving a correlation between the zero-sequence current and the three-phase voltage from the second sample power grid data, and constructing a parameter feature library based on the correlation;

[0033] The performing fault detection on the target distribution network by using the fault detection model includes: performing fault detection on the target distribution network according to the fault detection model and a parameter feature library.

[0034] In a second aspect, an embodiment of the present application provides a distribution network fault detection device based on three-phase imbalance, comprising:

[0035] An acquisition module, used to acquire first sample grid data of the reference distribution network when it is in normal operation and second sample grid data of the reference distribution network when it is in various faults;

[0036] An identification module, used to identify parameter features corresponding to the first sample power grid data and the second sample power grid data, respectively, to obtain a first parameter feature and a second parameter feature;

[0037] A construction module, used to construct a fault detection model according to the first parameter characteristics and the second parameter characteristics;

[0038] The detection module is used to perform fault detection on the target distribution network through the fault detection model.

[0039] Correspondingly, the present application also 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 executes the steps of any of the above methods when executing the program.

[0040] The present application also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements any of the above methods when the computer program is executed by a processor.

[0041] The present application provides a method, device, electronic device and storage medium for fault detection of distribution network based on three-phase imbalance. After obtaining the first sample grid data of the reference distribution network in normal operation and the second sample grid data of the reference distribution network in various faults, the parameter features corresponding to the first sample grid data and the second sample grid data are respectively identified to obtain the first parameter feature and the second parameter feature. Then, according to the first parameter feature and the second parameter feature, a fault detection model is constructed. Finally, the target distribution network is detected by the fault detection model. In the scheme of fault detection of distribution network based on three-phase imbalance provided by the present application, the first sample grid data of the reference distribution network in normal operation and the second sample grid data of the reference distribution network in various faults can be obtained. Then, based on the first parameter feature corresponding to the first sample grid data and the second parameter feature corresponding to the second sample grid data, a fault detection model is constructed. In actual detection, the fault detection model can be directly used to detect distribution network faults, without collecting three-phase electrical quantity data of one cycle, and then using the full-wave Fourier algorithm to perform a relatively complex analysis and calculation on the three-phase electrical quantity data of one cycle, thereby simplifying the process of distribution network fault detection, thereby improving the detection efficiency of distribution network faults based on three-phase imbalance. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 It is a flow chart of a distribution network fault detection method based on three-phase imbalance provided in an embodiment of the present application;

[0044] Figure 2 It is a schematic diagram of the cause analysis of three-phase imbalance provided in an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of the three-phase unbalanced parameter characteristic analysis conclusion provided by the embodiment of the present application;

[0046] Figure 4 is a flow chart for constructing a distribution network fault location model provided in an embodiment of the present application;

[0047] Figure 5 It is a schematic diagram of three-phase symmetrical vector decomposition provided in an embodiment of the present application;

[0048] Figure 6 This is the zero-sequence current collection process provided by the embodiment of the present application;

[0049] Figure 7 It is a simplified schematic diagram of a single-phase grounding model of a distribution network provided in an embodiment of the present application;

[0050] Figure 8 It is a waveform diagram before and after a zero-sequence component fault provided in an embodiment of the present application;

[0051] Fig. 9 Schematic diagram of the process of zero-sequence current detection method based on three-phase imbalance provided in the embodiment of the present application

[0052] Fig.10 It is a structural schematic diagram of a zero-sequence current detection device based on three-phase imbalance provided in an embodiment of the present application;

[0053] Fig.11 It is a structural schematic diagram of a distribution network fault detection device based on three-phase imbalance provided in an embodiment of the present application;

[0054] Fig.12 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are merely examples of systems and methods consistent with the examples detailed in the attached claims, or with some aspects of the present application.

[0056] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover descriptions such as non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0057] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0059] Embodiments of the present application provide a distribution network fault detection method, device, electronic device and storage medium based on three-phase imbalance.

[0060] Among them, the distribution network fault detection device based on three-phase imbalance can be deployed in a terminal, and the terminal can be a smart phone, a tablet, an intelligent audio and video interactive device, a smart home appliance, a vehicle-mounted terminal, an aircraft, a wearable intelligent device, a medical device, etc. As mentioned above, the above-mentioned terminal 102 is often configured with a display device, and the display device can also be a display, a display screen, a touch screen, etc. The touch screen can also be a touch screen, a touch panel, etc., but is not limited to this. The terminal can communicate with the server in a wired or wireless manner. The server can include an independently running server or a distributed server, or a server cluster composed of multiple servers. The terminal can include a mobile phone, a tablet computer or a personal computer (PC, Personal Computer).

[0061] It should be noted that the order of description of the following embodiments is not intended to limit the priority order of the embodiments.

[0062] The present application provides a distribution network fault detection method based on three-phase imbalance, including: obtaining first sample grid data of a reference distribution network during normal operation and second sample grid data of the reference distribution network during various types of faults; respectively identifying parameter features corresponding to the first sample grid data and the second sample grid data to obtain first parameter features and second parameter features; constructing a fault detection model based on the first parameter features and the second parameter features; and performing fault detection on a target distribution network through the fault detection model.

[0063] See also Figure 1 , Figure 1 : is a flow chart of a distribution network fault detection method based on three-phase imbalance provided by the present application, and the distribution network fault detection method based on three-phase imbalance specifically includes the following process:

[0064] 101. Obtain first sample grid data of a reference distribution network in normal operation and second sample grid data of the reference distribution network in various types of faults.

[0065] Distribution network refers to the power network in the power system that transmits electric energy from substations or power stations to end users (such as households, commercial and industrial users). The distribution network is an important part of the power system. It is responsible for the final distribution and supply of electric energy. The reference distribution network refers to the distribution network used as a benchmark or reference standard.

[0066] The first sample grid data refers to the data collected under normal operating conditions of the distribution network (i.e., without any faults or abnormalities). This type of data includes electrical parameters such as voltage, current, power, power factor, frequency, and other related parameters that may affect the performance of the grid. These data are usually collected through sensors and measuring devices installed at key nodes of the distribution network.

[0067] The second sample grid data refers to the data samples collected when a fault occurs in the distribution network. The second sample data can cover various types of faults, such as single-phase grounding, two-phase short circuit, three-phase short circuit, etc. The fault data usually exhibits different characteristics from normal operation, such as voltage drop, current surge, frequency change, etc.

[0068] For example, when the distribution network is operating normally, voltage and current data are collected for a week. These data show that the three-phase voltage is balanced and the current waveform is normal, that is, the first sample grid data; one day, a single-phase grounding fault occurred in the distribution network. We immediately collected the voltage, current and zero-sequence current data after the fault occurred. The data showed that the zero-sequence current increased significantly and the voltage dropped, that is, the second sample grid data was obtained.

[0069] 102. Identify parameter features corresponding to the first sample power grid data and the second sample power grid data respectively to obtain a first parameter feature and a second parameter feature.

[0070] Parameter features refer to key data points or attributes extracted from power grid data to describe the operating status of the power grid. In distribution network fault detection, parameter features are the basis for identifying and distinguishing normal operating status from fault status. Parameter features can include voltage, current, power, power factor, frequency, etc. In normal state, voltage is characterized by balanced three-phase voltage and stable amplitude; in fault state, voltage is characterized by unbalanced voltage, and there may be voltage sag or surge. In normal state, current is characterized by symmetrical three-phase current and no zero-sequence current; in fault state, current is characterized by asymmetric current and zero-sequence current may appear. In normal state, power is characterized by stable power and no abnormal fluctuation; in fault state, power is characterized by sudden increase or decrease. In normal state, power factor is characterized by close to ideal value, indicating high power grid efficiency; in fault state, power factor decreases, which may indicate load change or fault. In normal state, frequency is characterized by stable power grid frequency, usually 50Hz or 60Hz; in fault state, frequency fluctuates or deviates from normal value.

[0071] 103. Construct a fault detection model based on the first parameter feature and the second parameter feature.

[0072] For example, specifically, key parameter features are identified from the first sample grid data and the second sample grid data. The parameter features may be the most distinguishing features for fault detection, such as zero-sequence current, voltage imbalance, etc. Signal processing techniques are used to extract features, such as Fourier transform, wavelet transform, etc., to obtain frequency domain features. Then, a suitable algorithm is selected to construct a fault detection model, such as a support vector machine (SVM), a neural network, a decision tree, etc.

[0073] Optionally, in some embodiments of the present application, the step of “building a fault detection model according to the first parameter feature and the second parameter feature” may specifically include:

[0074] Extracting zero-sequence current parameters from the first parameter characteristic and the second parameter characteristic respectively to obtain a first zero-sequence current parameter and a second zero-sequence current parameter;

[0075] Get the preset basic detection model;

[0076] The basic detection model is trained according to the first zero-sequence current parameter and the second zero-sequence current parameter to obtain a fault detection model.

[0077] For example, specifically, the zero-sequence current parameter is extracted from the first sample grid data during normal operation. Ideally, a three-phase balanced grid in normal operation should have no or very small zero-sequence current. The zero-sequence current parameter is extracted from the second sample grid data during a fault. In the event of a fault, the zero-sequence current parameter will change significantly, such as an increase in current. Then, a preset basic detection model is selected, such as a support vector machine (SVM), a decision tree, a random forest, or a neural network. When training the model, the zero-sequence current parameter is extracted from the first sample and the second sample data. The training data is labeled to clarify which data represents a normal state and which represents a fault state. The second zero-sequence current parameter (fault data) and the corresponding annotation are used to train the basic detection model. The performance of the model is optimized by adjusting model parameters, such as a learning rate, a regularization coefficient, etc. The first zero-sequence current parameter (normal data) is used to verify the accuracy of the model to ensure that the model can distinguish between normal and fault states. Finally, the model is adjusted according to the verification results, including reselecting features, adjusting the model structure or parameters, etc.

[0078] Optionally, in some embodiments of the present application, the step of “training the basic detection model according to the first zero-sequence current parameter and the second zero-sequence current parameter to obtain a fault detection model” may specifically include:

[0079] Determine a distribution network fault corresponding to each second zero-sequence current parameter;

[0080] An estimated distribution network fault corresponding to a second zero-sequence current parameter is estimated based on a basic detection model;

[0081] Training a basic detection model according to a distribution network fault corresponding to the second zero-sequence current parameter and an estimated distribution network fault corresponding to the second zero-sequence current parameter;

[0082] Verifying the trained detection model using the first zero-sequence current parameter and the distribution network fault corresponding to the first zero-sequence current parameter;

[0083] When the trained detection model passes the verification, the trained detection model is determined as a fault detection model.

[0084] For example, the second zero-sequence current parameter is analyzed to determine the correspondence between each parameter change and a specific distribution network fault. For example, a significant increase in zero-sequence current corresponds to a single-phase ground fault. The second zero-sequence current parameter is analyzed using the basic detection model to predict possible distribution network faults. The basic detection model is trained based on actual faults (known faults) and faults predicted by the model. This step involves adjusting the model parameters to minimize the difference between actual faults and predicted faults. The accuracy of the model is verified using the first zero-sequence current parameter (normal operating data) and the corresponding distribution network state (no fault). This step is to ensure that the model can not only identify faults but also correctly identify the fault-free state. When the model shows satisfactory accuracy and reliability during the verification process, the model is confirmed as the final fault detection model. This means that the model is ready to be deployed in the actual distribution network monitoring system.

[0085] 104. Perform fault detection on the target distribution network through the fault detection model.

[0086] For example, the grid operation data, including three-phase voltage, current, power, frequency, etc., are collected from the target distribution network in real time. Key parameter features, such as zero-sequence current and voltage imbalance, are extracted from the collected data. These features are the basis for model analysis. The extracted features are preprocessed as necessary, such as normalization and denoising, to improve the analysis efficiency and accuracy of the model. The trained fault detection model is loaded to prepare for the analysis of real-time data. The real-time data is analyzed using the fault detection model. The model will process the input features and output the analysis results. The model will identify abnormal patterns in the data and determine whether there is a fault and the type of fault based on the learned knowledge, thereby realizing fault detection for the target distribution network.

[0087] Optionally, in some embodiments of the present application, the step of “performing fault detection on the target distribution network by using a fault detection model” may specifically include:

[0088] Obtain zero-sequence current parameters of the target distribution network;

[0089] Based on the fault detection model and the zero-sequence current parameters of the target distribution network, fault detection is performed on the target distribution network.

[0090] Optionally, in some embodiments of the present application, the step of “performing fault detection on the target distribution network based on the fault detection model and the zero-sequence current parameter of the target distribution network” may specifically include:

[0091] Based on the fault detection model and the zero-sequence current parameter of the target distribution network, determining whether the target distribution network has a preset type of fault;

[0092] If the target distribution network is not a preset type of fault, it is detected whether the zero-sequence current parameter of the target distribution network meets the preset conditions to perform fault detection on the target distribution network.

[0093] For example, specifically, the zero-sequence current parameters of the target distribution network, including amplitude, phase, frequency, etc., are obtained in real time. Then, the zero-sequence current parameters are converted into numerical vectors for processing by the fault detection model, and then the zero-sequence current parameter vector is input into the fault detection model for fault identification. The model analyzes the input parameters to determine whether they meet the preset fault type characteristics. If the model determines that the current fault does not meet any preset fault type, it further checks whether the zero-sequence current parameters meet other preset conditions, which may include specific thresholds or change patterns. Based on the judgment of the model and the inspection results of the preset conditions, a comprehensive decision is made as to whether there is a fault in the target distribution network and the type of fault. Finally, the final result of the fault detection is output, including information such as the existence, type, and location of the fault.

[0094] It should be noted that some faults occurring in the distribution network may be difficult to obtain in the actual power grid, especially some rare or extreme fault conditions. Therefore, in some embodiments of the present application, a simulation model may be used to simulate the fault of the reference distribution network, thereby obtaining the second sample power grid data of the reference distribution network when various faults occur. That is, the distribution network fault detection method may further include:

[0095] Obtain the basic simulation model and preset distribution network fault parameters;

[0096] The basic simulation model is adjusted according to the distribution network fault parameters to obtain the distribution network fault simulation model;

[0097] The second sample grid data of the reference distribution network under various fault conditions is simulated based on the distribution network fault simulation model.

[0098] Determine the possible fault types of the distribution network and define parameters for each fault, such as ground resistance, fault location, fault time, etc. Adjust the basic simulation model according to the preset fault parameters to reflect different types of fault conditions. The adjusted basic simulation model becomes a distribution network fault simulation model that can simulate specific fault conditions. Use the distribution network fault simulation model to simulate the operating status of the distribution network under various faults and generate simulation data. Collect the grid data under simulated fault conditions from the simulation model, which will be used as the second sample grid data for training and verification of the fault detection model.

[0099] After obtaining the second sample power grid data, a parameter feature library may be constructed according to the correlation between the zero-sequence current and the three-phase voltage in the second sample power grid data, so as to perform fault detection later. That is, optionally, in some embodiments of the present application, after the step of "simulating the second sample power grid data of the reference distribution network at various faults based on the distribution network fault simulation model", the following may be specifically included:

[0100] Determine a distribution network fault corresponding to the second sample power grid data;

[0101] The correlation between the zero-sequence current and the three-phase voltage is obtained from the second sample power grid data, and a parameter feature library is constructed based on the correlation.

[0102] The step of "performing fault detection on the target distribution network through the fault detection model" may specifically include: performing fault detection on the target distribution network according to the fault detection model and the parameter feature library.

[0103] Specifically, data is collected from the target distribution network and features are extracted. The features are matched with the data in the parameter feature library to identify possible fault modes. If the parameter feature library matching fails to give a clear result or further verification is required, the fault detection model is used for analysis.

[0104] In practical applications, parameter feature library matching and fault detection models can complement each other: the parameter feature library provides a fast pattern recognition method suitable for identifying known types of faults.

[0105] Fault detection models can provide deeper analysis, especially for new types of faults or patterns not included in the signature library.

[0106] The above is the distribution network fault detection process based on three-phase imbalance provided in the embodiment of the present application.

[0107] In summary, the embodiment of the present application, after obtaining the first sample grid data of the reference distribution network in normal operation and the second sample grid data of the reference distribution network in various faults, respectively identifies the parameter features corresponding to the first sample grid data and the second sample grid data, obtains the first parameter feature and the second parameter feature, then, according to the first parameter feature and the second parameter feature, constructs a fault detection model, and finally, performs fault detection on the target distribution network through the fault detection model. In the scheme of distribution network fault detection based on three-phase imbalance provided in the present application, the first sample grid data of the reference distribution network in normal operation and the second sample grid data of the reference distribution network in various faults can be obtained, then, based on the first parameter feature corresponding to the first sample grid data and the second parameter feature corresponding to the second sample grid data, constructs a fault detection model, in actual detection, the fault detection model can be directly used to perform distribution network fault detection, without collecting three-phase electrical quantity data of one cycle, and then using the full-wave Fourier algorithm to perform a relatively complex analysis and calculation on the three-phase electrical quantity data of one cycle, thereby simplifying the process of distribution network fault detection, thereby improving the detection efficiency of distribution network faults based on three-phase imbalance.

[0108] In order to facilitate the understanding of the zero-sequence current detection scheme based on three-phase imbalance of the present application, the method uses electromagnetic compatibility technology to effectively shield the interference of external electromagnetic fields on zero-sequence current detection, thereby ensuring the accuracy of the detection results. At the same time, it can synchronously detect the three-phase circuit and quickly determine the phase line where the fault occurs. By establishing an accurate distribution network fault location model, the method forms a set of self-diagnosis mechanisms that can adapt to the complex and changeable power grid environment and significantly improve the detection capabilities of traditional detection methods in the face of complex power grid conditions. In addition, the method also includes an early warning system that compares the real-time detected data with the data in the model library to determine whether there is a potential fault in the distribution network line. If a fault is detected, the system will automatically trigger an alarm and notify the operation and maintenance personnel in a timely manner.

[0109] In summary, this zero-sequence current detection method based on three-phase unbalance brings high real-time performance and stronger adaptability to distribution network fault troubleshooting, as follows:

[0110] 1. Analysis of the correlation between three-phase imbalance and zero-sequence current: In-depth exploration of the causes of three-phase imbalance and the corresponding parameter characteristics to provide theoretical support for the detection method.

[0111] 2. High-precision fault location model: This model can accurately detect faults such as short circuit and grounding, improving the efficiency and accuracy of fault detection.

[0112] 3. Comprehensive zero-sequence current analysis: Comprehensive analysis of the relationship between zero-sequence current and voltage under different grid conditions (sound and faulty).

[0113] The process of the zero-sequence current detection method based on three-phase unbalance is as follows:

[0114] Step S1: Analysis of the causes of three-phase imbalance and corresponding parameter characteristics. The causes of three-phase imbalance are analyzed as follows: Figure 2 As shown, the corresponding parameter characteristic analysis conclusions are as follows Figure 3 As shown, by accurately identifying and evaluating three-phase imbalance, the fault point can be quickly located, equipment damage can be prevented, and the grid operation efficiency can be optimized, thereby improving the speed and accuracy of fault detection and ensuring the safe and stable operation of the grid.

[0115] Step S2: Distribution network fault location model: The distribution network fault location model based on zero-sequence current detection can monitor line operation parameters and detect various short circuit and grounding faults.

[0116] Under the condition of three-phase load imbalance, zero-sequence current will be generated, and its magnitude varies with the degree of imbalance, causing the distribution transformer to generate zero-sequence flux and zero-sequence current, increasing the loss of the distribution transformer and reducing the insulation life. Taking zero-sequence current as the data basis for model establishment, after data collection and preprocessing, feature extraction, model design, model verification and testing, a distribution network fault location model is formed to achieve the following process: Figure 4 shown.

[0117] Step S3: Analyze the relationship between the sound circuit and the zero-sequence current and voltage during the fault; Analyze the detection principle and the fault qualitative judgment method based on zero-sequence current detection.

[0118] In a healthy distribution network circuit, since the three-phase load is balanced and there is no ground fault, the zero-sequence current is theoretically zero. However, once an asymmetric load or ground fault occurs, zero-sequence current will be generated. At this time, by monitoring the change of zero-sequence current, the abnormal state of the system can be identified.

[0119] In a three-phase power distribution network, Figure 5 As shown, the asymmetric three-phase phasor can be decomposed into positive sequence component, negative sequence component and zero sequence component. Assume that the three-phase phasor components are Fa, Fb and Fc respectively, and the subscripts 2, 1 and 0 represent the positive sequence component, negative sequence component and zero sequence component respectively:

[0120] Fa=Fa1+Fa2+Fa0

[0121] Fb=Fb1+Fb2+Fb0

[0122] Fc=Fc1+Fc2+Fc0

[0123] Under normal circumstances, there is only positive sequence component in the system. Once a single-phase ground fault occurs in the distribution network, there will be positive sequence component, negative sequence component and zero sequence component in the system at the same time. The core of the detection principle is to capture and analyze the zero sequence current signal. Therefore, it is very important to collect zero sequence current data and ensure that the data is not distorted. The collection logic of zero sequence current is as follows: Figure 6 shown.

[0124] Step S4: Establishing a parameter feature library / establishing a fault characteristic simulation library, taking a single-phase grounding fault as an example for simulation.

[0125] After obtaining the zero-sequence current parameters, the simulation model is established using Matlab simulation software, and then the relationship between the zero-sequence current and voltage is obtained through the simulated zero-sequence current waveform. Figure 7 shown.

[0126] Specifically, the following set of data is taken as an example for simulation. The three-phase voltage source is 10kV, the grounding method is a neutral point ungrounded system, the current and voltage frequency are uniformly 50Hz, the distribution line is a distributed transmission circuit, the lengths of each line are 50km, 70km, and 80km respectively, and the line parameters are positive sequence resistance = 0.01389Ω / km, positive sequence inductance = 0.8997mH / km, positive sequence capacitive reactance = 13.01pF / km, zero sequence resistance = 0.3964Ω / km, zero sequence inductance = 4.3313mH / km, zero sequence capacitive reactance = 7.571pF / km; the capacitance of the line to the ground is set to 1uF, and the grounding resistance when a ground fault occurs is set to 300Ω.

[0127] The simulated zero-sequence current and voltage waveforms are as follows: Figure 8 Based on the above simulation model, the system parameters are modified, including the grounding resistance and line length. In this process, it is found that the longer the line, the greater the zero-sequence current to the ground, the more accurate the detection, and the grounding resistance has almost no effect on the fault judgment.

[0128] The zero-sequence current and voltage waveforms obtained through simulation reveal the waveform changes under different system parameter settings. It is found that as the line length increases, the zero-sequence current to ground also increases, which makes fault detection more accurate.

[0129] Step S5: Establishment of early warning method and early warning mechanism: By comparing with the data in the model library, it is determined whether there is a fault in the distribution network line. When the parameters detected during the inspection of the distribution network line deviate from the normal range, that is, when there is a significant difference with the data in the model library, the early warning mechanism is automatically triggered. This mechanism can issue an alarm in time, and at the same time, the early warning information display and the human-computer interaction interface notify the operation and maintenance personnel to take measures, which can not only prevent the further development of the fault, but also significantly reduce the power outage time and impact range caused by the fault. The early warning mechanism workflow is as follows: Fig. 9 shown.

[0130] Also, see Fig.10 The zero-sequence current detection device based on three-phase imbalance provided by the present application includes a zero-sequence current phase acquisition module, a power supply module, an amplifier circuit, a filter circuit, a digital-to-analog conversion module, and a human-computer interaction module. The zero-sequence current phase acquisition module first obtains the current signal, and then the signal passes through the power supply module to ensure the stable power supply of the entire system. Next, the amplifier circuit enhances the signal strength, and the filter circuit removes unnecessary noise. The digital-to-analog conversion module digitizes the processed signal, and finally the human-computer interaction module converts the digital signal into visual information for operation and maintenance personnel to monitor and operate.

[0131] In order to facilitate better implementation of the distribution network fault detection method based on three-phase imbalance in the embodiment of the present application, the embodiment of the present application also provides a distribution network fault detection device based on three-phase imbalance. The meanings of the terms are the same as those in the above-mentioned distribution network fault detection system based on three-phase imbalance, and the specific implementation details can refer to the description in the system embodiment.

[0132] See also Fig.11 , Fig.11 A schematic diagram of the structure of a distribution network fault detection device based on three-phase imbalance provided in an embodiment of the present application, wherein the distribution network fault detection device based on three-phase imbalance may specifically include an acquisition module 201, an identification module 202, a construction module 203 and a detection module 204, which may be specifically as follows:

[0133] The acquisition module 201 is used to acquire first sample power grid data of the reference distribution network when it is in normal operation and second sample power grid data of the reference distribution network when it is in various types of faults.

[0134] The identification module 202 is used to identify parameter features corresponding to the first sample power grid data and the second sample power grid data respectively, and obtain the first parameter feature and the second parameter feature.

[0135] The construction module 203 is used to construct a fault detection model according to the first parameter feature and the second parameter feature.

[0136] The detection module 204 is used to perform fault detection on the target distribution network through a fault detection model.

[0137] The embodiment of the present application provides a distribution network fault detection device based on three-phase imbalance. After the acquisition module 201 acquires the first sample grid data of the reference distribution network in normal operation and the second sample grid data of the reference distribution network in various types of faults, the identification module 202 respectively identifies the parameter characteristics corresponding to the first sample grid data and the second sample grid data to obtain the first parameter characteristics and the second parameter characteristics. Then, the construction module 203 constructs a fault detection model according to the first parameter characteristics and the second parameter characteristics. Finally, the detection module 204 performs fault detection on the target distribution network through the fault detection model. In the scheme for distribution network fault detection based on three-phase imbalance provided in the present application, first sample grid data of the reference distribution network during normal operation and second sample grid data of the reference distribution network during various types of faults can be obtained. Then, a fault detection model is constructed based on the first parameter characteristics corresponding to the first sample grid data and the second parameter characteristics corresponding to the second sample grid data. During actual detection, the fault detection model can be directly used to perform distribution network fault detection without collecting three-phase electrical quantity data of one cycle and then using the full-wave Fourier algorithm to perform relatively complex analysis and calculation on the three-phase electrical quantity data of one cycle, thereby simplifying the distribution network fault detection process and thereby improving the detection efficiency of distribution network faults based on three-phase imbalance.

[0138] In addition, the present application also provides an electronic device, such as Fig.12 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0139] The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will appreciate that Fig.12 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0140] The processor 301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0141] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and a method for detecting a fault in a power distribution network based on three-phase imbalance by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 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 volatile solid-state storage devices. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0142] The electronic device also includes a power supply 303 for supplying power to each component. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions. The power supply 303 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0143] The electronic device may further include an input unit 304, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0144] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302, thereby realizing various functions, as follows:

[0145] Acquire first sample grid data of a reference distribution network in normal operation and second sample grid data of the reference distribution network in various types of faults; identify parameter features corresponding to the first sample grid data and the second sample grid data respectively to obtain first parameter features and second parameter features; construct a fault detection model based on the first parameter features and the second parameter features; and perform fault detection on the target distribution network through the fault detection model.

[0146] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0147] After obtaining the first sample grid data of the reference distribution network in normal operation and the second sample grid data of the reference distribution network in various types of faults, the embodiment of the present application respectively identifies the parameter features corresponding to the first sample grid data and the second sample grid data, obtains the first parameter feature and the second parameter feature, then, according to the first parameter feature and the second parameter feature, constructs a fault detection model, and finally, performs fault detection on the target distribution network through the fault detection model. In the scheme of distribution network fault detection based on three-phase imbalance provided in the present application, the first sample grid data of the reference distribution network in normal operation and the second sample grid data of the reference distribution network in various types of faults can be obtained, then, based on the first parameter feature corresponding to the first sample grid data and the second parameter feature corresponding to the second sample grid data, a fault detection model is constructed, and in actual detection, the fault detection model can be directly used to perform distribution network fault detection, without collecting three-phase electrical quantity data of one cycle, and then using the full-wave Fourier algorithm to perform a relatively complex analysis and calculation on the three-phase electrical quantity data of one cycle, thereby simplifying the process of distribution network fault detection, thereby improving the detection efficiency of distribution network faults based on three-phase imbalance.

[0148] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0149] To this end, an embodiment of the present application provides a storage medium in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the distribution network fault detection methods based on three-phase imbalance provided in the embodiment of the present application. For example, the instructions can execute the following steps:

[0150] Acquire first sample grid data of a reference distribution network in normal operation and second sample grid data of the reference distribution network in various types of faults; identify parameter features corresponding to the first sample grid data and the second sample grid data respectively to obtain first parameter features and second parameter features; construct a fault detection model based on the first parameter features and the second parameter features; and perform fault detection on the target distribution network through the fault detection model.

[0151] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0152] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0153] Since the instructions stored in the storage medium can execute the steps in any one of the distribution network fault detection methods based on three-phase imbalance provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the distribution network fault detection methods based on three-phase imbalance provided in the embodiments of the present application can be achieved. For details, please see the previous embodiments and will not be repeated here.

[0154] The above is a detailed introduction to a distribution network fault detection method, device, electronic device and storage medium based on three-phase imbalance provided in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A distribution network fault detection method based on three-phase imbalance, characterized in that: include: Acquire first sample grid data of the reference distribution network during normal operation and second sample grid data of the reference distribution network during various types of faults; Respectively identifying parameter features corresponding to the first sample power grid data and the second sample power grid data to obtain a first parameter feature and a second parameter feature; Constructing a fault detection model according to the first parameter characteristics and the second parameter characteristics; Fault detection is performed on the target distribution network using the fault detection model.

2. The method for detecting distribution network faults according to claim 1, characterized in that: The constructing of a fault detection model according to the first parameter feature and the second parameter feature comprises: Extracting zero-sequence current parameters from the first parameter feature and the second parameter feature respectively to obtain a first zero-sequence current parameter and a second zero-sequence current parameter; Get the preset basic detection model; The basic detection model is trained according to the first zero-sequence current parameter and the second zero-sequence current parameter to obtain a fault detection model.

3. The method for detecting distribution network faults according to claim 2, characterized in that: The step of training the basic detection model according to the first zero-sequence current parameter and the second zero-sequence current parameter to obtain a fault detection model includes: Determine a distribution network fault corresponding to each second zero-sequence current parameter; estimating an estimated distribution network fault corresponding to the second zero-sequence current parameter based on the basic detection model; training the basic detection model according to the distribution network fault corresponding to the second zero-sequence current parameter and the estimated distribution network fault corresponding to the second zero-sequence current parameter; Verifying the trained detection model using the first zero-sequence current parameter and the distribution network fault corresponding to the first zero-sequence current parameter; When the trained detection model passes the verification, the trained detection model is determined as a fault detection model.

4. The method for detecting a distribution network fault according to claim 1, characterized in that: The performing fault detection on the target distribution network by using the fault detection model includes: Obtain zero-sequence current parameters of the target distribution network; Based on the fault detection model and the zero-sequence current parameter of the target distribution network, fault detection is performed on the target distribution network.

5. The method for detecting distribution network faults according to claim 4, characterized in that: The performing fault detection on the target distribution network based on the fault detection model and the zero-sequence current parameter of the target distribution network includes: Based on the fault detection model and the zero-sequence current parameter of the target distribution network, determining whether the target distribution network has a preset type of fault; If the target distribution network is not a fault of a preset type, it is detected whether the zero-sequence current parameter of the target distribution network meets a preset condition, so as to perform fault detection on the target distribution network.

6. The distribution network fault detection method according to any one of claims 1 to 5, characterized in that: Also includes: Obtain the basic simulation model and preset distribution network fault parameters; The basic simulation model is adjusted according to the distribution network fault parameters to obtain a distribution network fault simulation model; The second sample power grid data of the reference distribution network when various types of faults occur is simulated based on the distribution network fault simulation model.

7. The method for detecting distribution network faults according to claim 6, characterized in that: After simulating the second sample power grid data of the reference distribution network when various types of faults are detected based on the distribution network fault simulation model, the method further includes: Determining a distribution network fault corresponding to the second sample power grid data; deriving a correlation between the zero-sequence current and the three-phase voltage from the second sample power grid data, and constructing a parameter feature library based on the correlation; The performing fault detection on the target distribution network by using the fault detection model includes: performing fault detection on the target distribution network according to the fault detection model and a parameter feature library.

8. A distribution network fault detection device based on three-phase imbalance, characterized in that: include: An acquisition module, used to acquire first sample grid data of the reference distribution network when it is in normal operation and second sample grid data of the reference distribution network when it is in various faults; An identification module, used to identify parameter features corresponding to the first sample power grid data and the second sample power grid data, respectively, to obtain a first parameter feature and a second parameter feature; A construction module, used to construct a fault detection model according to the first parameter characteristics and the second parameter characteristics; The detection module is used to perform fault detection on the target distribution network through the fault detection model.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the distribution network fault detection method based on three-phase imbalance as described in any one of claims 1 to 7 are performed.

10. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method for detecting a fault in a power distribution network based on three-phase imbalance as claimed in any one of claims 1 to 7.

Images