Fault detection method and device, electronic equipment and storage medium

Abstract

The application provides a fault detection method and device, electronic equipment and a computer readable storage medium. The method comprises: in the case that a fault point is detected in a power network, determining a fault identifier of a target power terminal corresponding to the fault point, the fault identifier being used to represent whether the target power terminal is prone to failure; in the case that the fault identifier represents that the target power terminal is prone to failure, determining the location of the fault point based on the location of the target power terminal. The embodiment of the application can reduce the time cost of power inspection.

Description

Technical Field

[0001] The present invention relates to the field of power detection technology, and in particular to a fault detection method, device, electronic device, and computer-readable storage medium. Background Technology

[0002] Over long-term operation, power grids inevitably experience a gradual decline in performance, reduced reliability, and increased failure rate, thereby jeopardizing their safe operation. Furthermore, power outages pose significant risks. To ensure the safe and stable operation of power grids, it is often necessary to conduct fault detection on power terminals within the jurisdiction to guarantee their normal operation.

[0003] In traditional power grids, fault detection of power terminals is usually done manually, which is costly. Summary of the Invention

[0004] This invention provides a fault detection method, apparatus, electronic device, and computer-readable storage medium to address the problem that fault detection of power terminals in power networks typically requires manual inspection, resulting in high detection costs.

[0005] In a first aspect, embodiments of the present invention provide a fault detection method, the method comprising:

[0006] When a fault point is detected in the power network, a fault identifier is determined for the target power terminal corresponding to the fault point. The fault identifier is used to characterize whether the target power terminal is prone to failure.

[0007] When the fault identifier indicates that the target power terminal is prone to failure, the location of the fault point is determined based on the location of the target power terminal.

[0008] In the above scheme, the step of determining the fault identifier of the target power terminal corresponding to the fault point includes:

[0009] The fault identifier of the target power terminal corresponding to the fault point is obtained from a pre-created terminal monitoring status database, which stores the fault identifiers of each power terminal in the power network; or,

[0010] The fault status data of the target power terminal is obtained, and the fault status data of the target power terminal is input into the fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault status data of the target power terminal includes at least one fault status information of the target power terminal in the time series.

[0011] In the above scheme, before obtaining the fault identifier of the target power terminal corresponding to the fault point from the pre-created terminal monitoring status database, the method further includes:

[0012] Acquire training sample data, which includes fault status data and fault labels of multiple monitoring points, wherein the fault label of the first monitoring point is a fault identifier marked based on the fault status data of the first monitoring point, and the first monitoring point is any one of the multiple monitoring points;

[0013] The fault prediction model is trained based on the training sample data;

[0014] Once the fault prediction model has been trained, the fault identifier of each power terminal in the power network is determined based on the fault prediction model.

[0015] Based on the fault identifiers of each power terminal in the power network, a terminal monitoring status database is created.

[0016] In the above scheme, the terminal monitoring status database includes a first terminal monitoring status database and a second terminal monitoring status database. The step of creating the terminal monitoring status database based on the fault identifiers of each power terminal in the power network includes:

[0017] The fault identifiers in the power network that represent power terminals prone to failure are stored in the first terminal monitoring status database.

[0018] The fault identifiers in the power network that indicate power terminals that are not prone to failure are stored in the second terminal monitoring status database.

[0019] In the above scheme, obtaining the fault status data of the first monitoring point includes:

[0020] By monitoring the operational data of the first monitoring point in at least one time period in chronological order, an operational data sequence of the first monitoring point is obtained, wherein the operational data includes the maintenance information of the first monitoring point.

[0021] Based on the operational data sequence, the fault status data of the first monitoring point is obtained.

[0022] Secondly, embodiments of the present invention provide a fault detection device, the device comprising:

[0023] The first determining module is used to determine the fault identifier of the target power terminal corresponding to the fault point when a fault point is detected in the power network. The fault identifier is used to characterize whether the target power terminal is prone to failure.

[0024] The second determining module is used to determine the location of the fault point based on the location of the target power terminal when the fault identifier indicates that the target power terminal is prone to failure.

[0025] In the above scheme, the first determining module is specifically used for:

[0026] The fault identifier of the target power terminal corresponding to the fault point is obtained from a pre-created terminal monitoring status database, which stores the fault identifiers of each power terminal in the power network; or,

[0027] The fault status data of the target power terminal is obtained, and the fault status data of the target power terminal is input into the fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault status data of the target power terminal includes at least one fault status information of the target power terminal in the time series.

[0028] In the above scheme, the device further includes:

[0029] The acquisition module is used to acquire training sample data, which includes fault status data and fault labels of multiple monitoring points. The fault label of the first monitoring point is a fault identifier marked based on the fault status data of the first monitoring point, and the first monitoring point is any one of the multiple monitoring points.

[0030] The training module is used to train the fault prediction model based on the training sample data;

[0031] The third determining module is used to determine the fault identifier of each power terminal in the power network based on the fault prediction model after the fault prediction model has been trained.

[0032] A module is created to create a terminal monitoring status database based on the fault identifiers of each power terminal in the power network.

[0033] In the above scheme, the terminal monitoring status library includes a first terminal monitoring status library and a second terminal monitoring status library, and the creation module is specifically used for:

[0034] The fault identifiers in the power network that represent power terminals prone to failure are stored in the first terminal monitoring status database.

[0035] The fault identifiers in the power network that indicate power terminals that are not prone to failure are stored in the second terminal monitoring status database.

[0036] In the above scheme, the acquisition module is specifically used for:

[0037] By monitoring the operational data of the first monitoring point in at least one time period in chronological order, an operational data sequence of the first monitoring point is obtained, wherein the operational data includes the maintenance information of the first monitoring point.

[0038] Based on the operational data sequence, the fault status data of the first monitoring point is obtained.

[0039] Thirdly, embodiments of the present invention provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-described fault detection method.

[0040] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described fault detection method.

[0041] In this embodiment of the invention, when a fault point is detected in the power network, a fault identifier is determined for the target power terminal corresponding to the fault point. This fault identifier indicates whether the target power terminal is prone to failure. If the fault identifier indicates that the target power terminal is prone to failure, the location of the fault point is determined based on the location of the target power terminal. Thus, when a power network fault is detected, if it is determined that the target power terminal corresponding to the fault point is prone to failure, the location of the fault point can be quickly located based on the location of the target power terminal, thereby reducing the time cost of power grid inspection. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating the fault detection method provided in an embodiment of the present invention;

[0044] Figure 2 This is a flowchart of the training process for the fault prediction model;

[0045] Figure 3 This is a schematic diagram of the structure of the fault detection device provided in an embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0047] In the background art, the existing fault detection method for power terminals in power networks is usually manual inspection, which is relatively costly. Based on this, this invention proposes a new fault detection scheme.

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] The fault detection method provided in the embodiments of the present invention will be described below first.

[0050] It should be noted that the fault detection method provided in this embodiment of the invention relates to the field of electronic power technology, specifically to the field of power detection technology. It can be widely applied in many scenarios such as the operation, scheduling, maintenance, fault diagnosis, and prediction of power networks. This method can be executed by the fault detection device of this embodiment. The fault detection device can be configured in any electronic device to execute the fault detection method; this electronic device can be a server or a terminal, and no specific limitation is made here.

[0051] See Figure 1 The figure shows a schematic flowchart of the fault detection method provided in an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0052] Step 101: If a fault point is detected in the power network, determine the fault identifier of the target power terminal corresponding to the fault point. The fault identifier is used to characterize whether the target power terminal is prone to failure.

[0053] Here, the power network can be a network of a power system, which can encompass at least one of the networks of power generation, transmission, distribution, and consumption. The power network can include a number of power terminals, and these power terminals, along with cables and wires, can constitute a power network. Optionally, the power network can be a distribution network, which can include multiple distribution terminals such as transformers and distribution boxes; these distribution terminals are the power terminals.

[0054] To ensure the normal operation of the power grid, multiple monitoring points are typically set up within the power grid to monitor the operation of each power terminal. Specifically, one or more monitoring points can be set up for each power terminal in the power grid to monitor its operation.

[0055] A fault point refers to a monitoring point in a power network where a fault exists. There can be one or more fault points in a power network, and correspondingly, a fault detection device can detect one or more monitoring points in the power network where a fault exists.

[0056] During the operation of power grids, a large amount of data is generated, which becomes power big data. This data includes various information from monitoring points set up in the power grid, and is of great value for the system operation, scheduling, maintenance, fault diagnosis and prediction of the power grid.

[0057] Therefore, based on this, information and communication technologies can be integrated with the operation technologies of physical power systems to form a smart grid. The foundation of the smart grid's intelligence lies in the rapid processing and analysis of real-time data that accurately reflects the operational status of the power network system. This data must be quickly transformed into information, and based on this effective information, monitoring and prediction can be performed, thereby achieving the intelligent operation of the power network.

[0058] Based on the smart grid, the fault detection device can receive power data such as current, voltage, temperature and operating power from various monitoring points sent by other devices, and perform data analysis based on the received power data to determine the operating status information of each monitoring point in the power network.

[0059] If the operational status information of a monitoring point indicates that the monitoring point is in an abnormal operating state, that is, that the monitoring point has a fault, then the fault detection device will detect a fault point in the power network. However, if the operational status information of each monitoring point in the power network indicates that the corresponding monitoring point is in a normal operating state, then the fault detection device can detect that there is no fault point in the power network.

[0060] The fault detection device can also receive fault information detected by other monitoring devices. The fault information indicates whether there is a fault point in the power network, and if there is a fault point in the power network, which monitoring points have failed. Of course, it also indicates other information such as what kind of fault occurred at the monitoring point, i.e., the fault type, which is not specifically limited here.

[0061] The aforementioned "fault at monitoring point" refers to a potential malfunction in the power terminal being monitored by that point; that is, the fault point may be a power terminal within the power network. Other monitoring equipment can also detect the presence of fault points in the power network using the same method, which will not be elaborated upon here.

[0062] The purpose of this invention is to enable targeted fault location analysis after confirming a fault in the power network, thereby reducing the time cost of power inspection. Furthermore, by automating fault location determination while ensuring overall system reliability, the total number of dispatches can be reduced, and dispatch efficiency improved.

[0063] Specifically, when a fault point is detected in the power network, the fault identifier of the target power terminal corresponding to the fault point can be determined. The fault identifier of the target power terminal can be used to characterize whether the target power terminal is prone to failure.

[0064] The fault identifier can have two types: the first type indicates that the target power terminal is prone to failure, meaning the target power terminal is a power terminal prone to failure; the second type indicates that the target power terminal is not prone to failure, meaning the target power terminal is a power terminal not prone to failure.

[0065] In other words, by identifying faults, power terminals in the power network can be divided into two types: the first type is power terminals with a high probability of fault occurrence, and the second type is power terminals with a low probability of fault occurrence.

[0066] In the actual calibration process, the fault identifier can be represented by a first value such as 0 to indicate that the power terminal is a monitoring point that is not prone to failure, i.e., a monitoring point with a low probability of failure, while a second value such as 1 can be represented to indicate that the power terminal is a monitoring point that is prone to failure, i.e., a monitoring point with a high probability of failure.

[0067] There are multiple ways to determine the fault identifier of the target power terminal corresponding to the fault point. For example, the fault identifiers of all power terminals in the power network can be pre-marked. Accordingly, when a fault point is detected in the power network, the fault identifier of the target power terminal corresponding to the fault point can be obtained from the marked fault identifiers of each power terminal.

[0068] For example, fault status data of the target power terminal can be obtained, and this data can be input into a fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault prediction model can be a deep learning model, such as a recurrent neural network model or a Long Short-Term Memory (LSTM) convolutional network model.

[0069] The fault status data of the target power terminal includes at least one fault status information of the target power terminal in a time series. For example, the fault status data of the target power terminal includes 12 fault status information of the target power terminal. Each fault status information represents whether the target power terminal is operating normally or abnormally within a month. For example, the first fault status information represents the fault status of the target power terminal in the 12th month in history. In that month, the fault status information represents that the target power terminal is normal, represented by the value 0. The second fault status information represents the fault status of the target power terminal in the 11th month in history. In that month, the fault status information represents that the target power terminal is abnormal, represented by the value 1. And the 12th fault status information represents the fault status of the target power terminal in the most recent month.

[0070] Step 102: If the fault identifier indicates that the target power terminal is prone to failure, determine the location of the fault point based on the location of the target power terminal.

[0071] In this step, when the fault identifier indicates that the target power terminal is prone to failure, that is, when the fault identifier is a value of 1, the location of the fault point can be determined based on the location of the target power terminal.

[0072] The location of the target power terminal can be directly determined as the location of the fault point, or the location that has a mapping relationship with the location of the target power terminal can be determined as the location of the fault point; no specific limitation is made here.

[0073] In this embodiment, when a fault point is detected in the power network, a fault identifier is determined for the target power terminal corresponding to the fault point. This fault identifier indicates whether the target power terminal is prone to failure. If the fault identifier indicates that the target power terminal is prone to failure, the location of the fault point is determined based on the location of the target power terminal. Thus, when a power network fault is detected, if it is determined that the target power terminal corresponding to the fault point is prone to failure, the location of the fault point can be quickly and accurately located based on the location of the target power terminal, thereby reducing the time cost of power grid inspection.

[0074] Optionally, step 101 specifically includes:

[0075] The fault identifier of the target power terminal corresponding to the fault point is obtained from a pre-created terminal monitoring status database, which stores the fault identifiers of each power terminal in the power network; or,

[0076] The fault status data of the target power terminal is obtained, and the fault status data of the target power terminal is input into the fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault status data of the target power terminal includes at least one fault status information of the target power terminal in the time series.

[0077] In this embodiment, there are two ways to determine the fault identifier of the target power terminal corresponding to the fault point. The first way is to obtain the fault identifier of the target power terminal corresponding to the fault point from a pre-created terminal monitoring status database.

[0078] The terminal monitoring status database stores the fault identifiers of each power terminal in the power network. The storage can be in various ways, such as associating the terminal identifiers of all power terminals with their fault identifiers and storing them in one database to form the terminal monitoring status database.

[0079] Correspondingly, the fault identifier associated with the terminal identifier of the target power terminal can be obtained from the terminal monitoring status database to obtain the fault identifier of the target power terminal.

[0080] For example, the terminal monitoring status database includes a first terminal monitoring status database and a second terminal monitoring status database. The first terminal monitoring status database stores the terminal identifiers of power terminals that are prone to failure, i.e., it stores power terminals with a fault identifier of 1. The second terminal monitoring status database stores the terminal identifiers of power terminals that are not prone to failure, i.e., it stores power terminals with a fault identifier of 0.

[0081] Accordingly, the terminal identifier of the target power terminal can be compared with the terminal identifiers of power terminals in the first terminal monitoring status database to determine whether the terminal identifier of the target power terminal exists in the first terminal monitoring status database. If it exists, the fault identifier of the target power terminal is determined to be 1. If it does not exist, the fault identifier of the target power terminal is determined to be 0.

[0082] The second method involves acquiring the fault status data of the target power terminal, inputting this data into a fault prediction model to predict the fault identifier, and thus obtaining the fault identifier of the target power terminal. The fault prediction model can be a deep learning model, such as a recurrent neural network model or a Long Short-Term Memory (LSTM) convolutional network model.

[0083] The fault status data of the target power terminal includes at least one fault status information of the target power terminal in a time series. For example, the fault status data of the target power terminal includes 12 fault status information of the target power terminal. Each fault status information represents whether the target power terminal is operating normally or abnormally within a month. For example, the first fault status information represents the fault status of the target power terminal in the 12th month in history. In that month, the fault status information represents that the target power terminal is normal, represented by the value 0. The second fault status information represents the fault status of the target power terminal in the 11th month in history. In that month, the fault status information represents that the target power terminal is abnormal, represented by the value 1. And the 12th fault status information represents the fault status of the target power terminal in the most recent month.

[0084] In practical applications, any one of the determination methods can be used to determine the fault identifier of the target power terminal corresponding to the fault point. Alternatively, the first method can be used to query whether the terminal identifier of the target power terminal exists in the terminal monitoring status database. If it exists, the fault identifier of the target power terminal can be directly determined. If it does not exist, such as in an application scenario where a new power terminal has been added to the power network and the pre-created terminal monitoring status database does not store the fault identifier of that power terminal, the second method can be used to determine it. This can improve processing speed.

[0085] Optionally, before obtaining the fault identifier of the target power terminal corresponding to the fault point from the pre-created terminal monitoring status database, the method further includes:

[0086] Acquire training sample data, which includes fault status data and fault labels of multiple monitoring points, wherein the fault label of the first monitoring point is a fault identifier marked based on the fault status data of the first monitoring point, and the first monitoring point is any one of the multiple monitoring points;

[0087] The fault prediction model is trained based on the training sample data;

[0088] Once the fault prediction model has been trained, the fault identifier of each power terminal in the power network is determined based on the fault prediction model.

[0089] Based on the fault identifiers of each power terminal in the power network, a terminal monitoring status database is created.

[0090] In this embodiment, a fault prediction model can be trained, and the fault identifiers of each power terminal in the power network can be obtained based on the trained fault prediction model. Then, a terminal monitoring status database can be created based on the fault identifiers of each power terminal.

[0091] Specifically, training sample data can be obtained, which includes fault status data and fault labels from multiple monitoring points. Here, the monitoring points can refer to the monitoring points set up for training the power terminals. The power terminals used for training the fault prediction model can be power terminals in the power network or power terminals in other smart grids, without specific limitations.

[0092] The operational data of each power terminal in the smart grid can be monitored through the set monitoring points to obtain fault status data of each power terminal. Since the set monitoring points monitor the operational data of the power terminals, the fault status data of the monitoring points represent the fault status data of the power terminals. The operational data of the power terminals can refer to the data on the working status, fault manifestations, maintenance and recovery processes of the power terminals within a certain period of time, such as one year.

[0093] Once the operating data of the power terminal is obtained, fault analysis can be performed on the operating data of the power terminal, and the fault status of the monitoring point can be marked according to the analysis results. During the marking process, the fault status of the monitoring point can be marked separately for the operating data of different time periods.

[0094] For example, for monitoring point n, the fault status of monitoring point n can be labeled based on the monthly operational data, ultimately obtaining multiple fault status information in the time series, thus constituting the fault status data of monitoring point n. This can be represented as Xn = {xn:0; xn:1; xn:0; ...; xn:1}, where Xn represents the fault status data of monitoring point n, with a value of 0 indicating that the fault status of the power terminal is normal within a certain time period, and a value of 1 indicating that the fault status of the power terminal is abnormal within a certain time period.

[0095] After obtaining the fault status data of the monitoring points, fault identifiers can be marked on the monitoring points based on the fault status data, ultimately obtaining the fault labels of the monitoring points. Among them, a value of 0 indicates a monitoring point that is not likely to fail, and a value of 1 indicates a monitoring point that is likely to fail.

[0096] In other words, the process of acquiring the training sample data involves collecting, processing, and labeling the operational data of the power terminals within a certain time period. The fault state data of the monitoring points ultimately input into the fault prediction model has temporal continuity; that is, the fault state data of a power terminal input into the fault prediction model at one time is a matrix composed of a set of continuously collected fault states of that power terminal. The fault state and fault label of monitoring point n can be manually or automatically identified based on the actual monitored operational data. Examples of logical state identification for monitoring points are shown in Table 1.

[0097] Table 1 Logical Status Identifiers of Monitoring Points

[0098] monitoring points Fault status information Fault Label Monitoring point 1 0 0 Monitoring point 2 1 1 Monitoring point 3 0 0 ... ... ... Monitoring point n 1 0

[0099] Subsequently, the fault prediction model can be trained based on the training sample data. Since the fault state data can be regarded as a time series-based data set, the fault prediction model can use an LSTM convolutional network model. Before the LSTM convolutional network model, a structure of convolutional layer + linear rectified function can be used to extract the feature information of the input data. The convolutional layer can use a convolutional kernel of size 3x3. In this way, the established fault prediction model can improve the prediction accuracy of fault identification of power terminals.

[0100] After establishing the fault prediction model, the fault state data in the training sample data can be input into the fault prediction model for training, and the binary classification cross-entropy loss function can be used to complete the binary classification model training task in the model training process.

[0101] See Figure 2 , Figure 2 This is a flowchart of the training process for the fault prediction model, such as... Figure 2 As shown, the process includes the following steps:

[0102] Step 201: Obtain training sample data and initialize the parameters of the fault prediction model;

[0103] Step 202: Take a training sample from the training sample data and input it into the fault prediction model. After the forward propagation stage, obtain the output of the fault prediction model.

[0104] Step 203: Determine the difference between the output of the fault prediction model and the fault labels in the training sample, and adjust the parameters of the fault prediction model through the backpropagation stage;

[0105] Step 204: Determine whether a set of training samples has been trained and whether the fault prediction model meets the accuracy requirements for fault identification prediction. If yes, proceed to step 205; otherwise, return to step 202.

[0106] Step 205: The fault prediction model training is completed, and the fault prediction model is used to predict the fault identification of each power terminal in the power network.

[0107] Furthermore, once the fault prediction model has been trained, the fault status data of each power terminal in the power network can be obtained in the same way as described above. For each power terminal, the fault status data of that power terminal is input into the trained fault prediction model, and the fault identifier of that power terminal can be output, thus obtaining the fault identifier of each power terminal in the power network.

[0108] Based on the fault identifiers of each power terminal in the power network, the terminal monitoring status database can be created. There are several ways to create it; for example, the terminal identifiers of all power terminals can be associated with their fault identifiers and stored in a single database to create the terminal monitoring status database.

[0109] For example, the terminal monitoring status database may include a first terminal monitoring status database and a second terminal monitoring status database. The first terminal monitoring status database stores the terminal identifiers of power terminals prone to failure, i.e., power terminals with a fault identifier of 1. The second terminal monitoring status database stores the terminal identifiers of power terminals less prone to failure, i.e., power terminals with a fault identifier of 0. Accordingly, power terminals with a fault identifier of 1 can be stored in the first terminal monitoring status database, and power terminals with a fault identifier of 0 can be stored in the second terminal monitoring status database.

[0110] In this embodiment, by combining big data on power grids and deep learning models, fault identifiers of various power terminals in the power network are predicted, and a terminal monitoring status database is constructed. Based on this database, fault points in the power network can be quickly analyzed, thus rapidly locating fault points and reducing the time cost of power inspections. Furthermore, while ensuring the overall reliability of the system, a work optimization module is used to reduce the total number of dispatches and improve dispatch efficiency.

[0111] Optionally, the terminal monitoring status database includes a first terminal monitoring status database and a second terminal monitoring status database. The step of creating the terminal monitoring status database based on the fault identifiers of each power terminal in the power network includes:

[0112] The fault identifiers in the power network that represent power terminals prone to failure are stored in the first terminal monitoring status database.

[0113] The fault identifiers in the power network that indicate power terminals that are not prone to failure are stored in the second terminal monitoring status database.

[0114] In this embodiment, when the fault prediction model reaches a certain level of non-probability risk confidence for a power terminal with a low probability of failure, and the non-probability condition is met, the fault prediction model can be used to identify the power terminal with a fault identifier that indicates that it is not likely to fail, based on the fault status data of the power terminal, and the power terminal can be added to the second terminal monitoring status database. This can reduce the monitoring deployment of the power terminal in order to reduce the operating cost of the power network.

[0115] For power terminals judged to have a high probability of failure, a fault identifier indicating a high likelihood of failure can be assigned to the power terminal, and the power terminal can be added to the first terminal monitoring status database. By conducting targeted enhanced monitoring of the power terminals in the first terminal monitoring status database, the deployment of monitoring and prevention of failures can be strengthened, and failures can be responded to in a timely and rapid manner, thereby improving the optimization goal of the overall network reliability and enhancing the intelligent efficiency of the smart grid's big data processing capabilities.

[0116] Furthermore, by storing power terminals that are prone to failure and those that are not, the matching efficiency of fault identifiers for target power terminals corresponding to fault points can be improved in the event of a fault in the power network.

[0117] Optionally, obtaining the fault status data of the first monitoring point includes:

[0118] By monitoring the operational data of the first monitoring point in at least one time period in chronological order, an operational data sequence of the first monitoring point is obtained, wherein the operational data includes the maintenance information of the first monitoring point.

[0119] Based on the operational data sequence, the fault status data of the first monitoring point is obtained.

[0120] In this embodiment, the operational data of the first monitoring point includes the maintenance information of the first monitoring point. The maintenance information may include data such as the repair and restoration process of the power terminal. The maintenance information, combined with the working status and fault performance of the power terminal, can improve the accuracy of the fault status data of the monitoring point.

[0121] For example, if a monitoring point works normally for most of the month but has been repaired multiple times, in this application scenario, the fault status of the monitoring point in that month can be marked as abnormal.

[0122] The fault detection device provided in the embodiments of the present invention will be described below.

[0123] See Figure 3 The figure shows a schematic diagram of the fault detection device provided in an embodiment of the present invention. Figure 3 As shown, the fault detection device 300 includes:

[0124] The first determining module 301 is used to determine the fault identifier of the target power terminal corresponding to the fault point when a fault point is detected in the power network. The fault identifier is used to characterize whether the target power terminal is prone to failure.

[0125] The second determining module 302 is used to determine the location of the fault point based on the location of the target power terminal when the fault identifier indicates that the target power terminal is prone to failure.

[0126] Optionally, the first determining module 301 is specifically used for:

[0127] The fault identifier of the target power terminal corresponding to the fault point is obtained from a pre-created terminal monitoring status database, which stores the fault identifiers of each power terminal in the power network; or,

[0128] The fault status data of the target power terminal is obtained, and the fault status data of the target power terminal is input into the fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault status data of the target power terminal includes at least one fault status information of the target power terminal in the time series.

[0129] Optionally, the device further includes:

[0130] The acquisition module is used to acquire training sample data, which includes fault status data and fault labels of multiple monitoring points. The fault label of the first monitoring point is a fault identifier marked based on the fault status data of the first monitoring point, and the first monitoring point is any one of the multiple monitoring points.

[0131] The training module is used to train the fault prediction model based on the training sample data;

[0132] The third determining module is used to determine the fault identifier of each power terminal in the power network based on the fault prediction model after the fault prediction model has been trained.

[0133] A module is created to create a terminal monitoring status database based on the fault identifiers of each power terminal in the power network.

[0134] Optionally, the terminal monitoring status database includes a first terminal monitoring status database and a second terminal monitoring status database, and the creation module is specifically used for:

[0135] The fault identifiers in the power network that represent power terminals prone to failure are stored in the first terminal monitoring status database.

[0136] The fault identifiers in the power network that indicate power terminals that are not prone to failure are stored in the second terminal monitoring status database.

[0137] Optionally, the acquisition module is specifically used for:

[0138] By monitoring the operational data of the first monitoring point in at least one time period in chronological order, an operational data sequence of the first monitoring point is obtained, wherein the operational data includes the maintenance information of the first monitoring point.

[0139] Based on the operational data sequence, the fault status data of the first monitoring point is obtained.

[0140] The fault detection device 300 can implement the various processes implemented in the above method embodiments, and will not be described again here to avoid repetition.

[0141] In this embodiment of the invention, a first determining module 301 is used to determine a fault identifier of a target power terminal corresponding to a fault point when a fault point is detected in the power network. The fault identifier is used to characterize whether the target power terminal is prone to failure. A second determining module 302 is used to determine the location of the fault point based on the location of the target power terminal when the fault identifier indicates that the target power terminal is prone to failure. Thus, when a power network fault is detected, if it is determined that the target power terminal corresponding to the fault point is prone to failure, the location of the fault point can be quickly located based on the location of the target power terminal, thereby reducing the time cost of power network inspection.

[0142] The electronic device provided in the embodiments of the present invention will be described below.

[0143] See Figure 4 The figure shows a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 4 As shown, the electronic device 400 includes: a processor 401, a memory 402, a user interface 403, and a bus interface 404.

[0144] Processor 401 is used to read the program from memory 402 and execute the following procedures:

[0145] When a fault point is detected in the power network, a fault identifier is determined for the target power terminal corresponding to the fault point. The fault identifier is used to characterize whether the target power terminal is prone to failure.

[0146] When the fault identifier indicates that the target power terminal is prone to failure, the location of the fault point is determined based on the location of the target power terminal.

[0147] exist Figure 4 In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 401 and memory represented by memory 402 together. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 404 provides an interface. For different user devices, user interface 403 can also be an interface capable of connecting external or internal devices, including but not limited to keypads, displays, speakers, microphones, joysticks, etc.

[0148] The processor 401 is responsible for managing the bus architecture and general processing, while the memory 402 can store the data used by the processor 401 when performing operations.

[0149] Optional, processor 401, specifically used for:

[0150] The fault identifier of the target power terminal corresponding to the fault point is obtained from a pre-created terminal monitoring status database, which stores the fault identifiers of each power terminal in the power network; or,

[0151] The fault status data of the target power terminal is obtained, and the fault status data of the target power terminal is input into the fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault status data of the target power terminal includes at least one fault status information of the target power terminal in the time series.

[0152] Optionally, processor 401 is also used for:

[0153] Acquire training sample data, which includes fault status data and fault labels of multiple monitoring points, wherein the fault label of the first monitoring point is a fault identifier marked based on the fault status data of the first monitoring point, and the first monitoring point is any one of the multiple monitoring points;

[0154] The fault prediction model is trained based on the training sample data;

[0155] Once the fault prediction model has been trained, the fault identifier of each power terminal in the power network is determined based on the fault prediction model.

[0156] Based on the fault identifiers of each power terminal in the power network, a terminal monitoring status database is created.

[0157] Optionally, the terminal monitoring status library includes a first terminal monitoring status library and a second terminal monitoring status library, and the processor 401 is specifically used for:

[0158] The fault identifiers in the power network that represent power terminals prone to failure are stored in the first terminal monitoring status database.

[0159] The fault identifiers in the power network that indicate power terminals that are not prone to failure are stored in the second terminal monitoring status database.

[0160] Optional, processor 401, specifically used for:

[0161] By monitoring the operational data of the first monitoring point in at least one time period in chronological order, an operational data sequence of the first monitoring point is obtained, wherein the operational data includes the maintenance information of the first monitoring point.

[0162] Based on the operational data sequence, the fault status data of the first monitoring point is obtained.

[0163] Preferably, the present invention also provides an electronic device, including a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the computer program is executed by the processor 401, it implements the various processes of the above-described fault detection method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0164] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, this computer program implements the various processes of the above-described fault detection method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0165] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0166] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0168] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0169] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0170] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0171] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A fault detection method, characterized in that, The method includes: When a fault point is detected in the power network, a fault identifier is determined for the target power terminal corresponding to the fault point. The fault identifier is used to characterize whether the target power terminal is prone to failure. When the fault identifier indicates that the target power terminal is prone to failure, the location of the fault point is determined based on the location of the target power terminal. The step of determining the fault identifier of the target power terminal corresponding to the fault point includes: The fault status data of the target power terminal is obtained, and the fault status data of the target power terminal is input into the fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault status data of the target power terminal includes at least one fault status information of the target power terminal in the time series. The target fault status information is used to characterize the operating status of the target power terminal within a target time period. The target fault status information is any one of the at least one fault status information. The target time period is the time period corresponding to the target fault status information in the time series. The operating status includes normal status and abnormal status. The fault identifier includes two types: the first type indicates that the target power terminal is prone to failure; the second type indicates that the target power terminal is not prone to failure.

2. The method according to claim 1, characterized in that, The step of determining the fault identifier of the target power terminal corresponding to the fault point includes: The fault identifier of the target power terminal corresponding to the fault point is obtained from a pre-created terminal monitoring status database, which stores the fault identifiers of each power terminal in the power network.

3. The method according to claim 2, characterized in that, Before obtaining the fault identifier of the target power terminal corresponding to the fault point from the pre-created terminal monitoring status database, the method further includes: Acquire training sample data, which includes fault status data and fault labels of multiple monitoring points, wherein the fault label of the first monitoring point is a fault identifier marked based on the fault status data of the first monitoring point, and the first monitoring point is any one of the multiple monitoring points; The fault prediction model is trained based on the training sample data; Once the fault prediction model has been trained, the fault identifier of each power terminal in the power network is determined based on the fault prediction model. Based on the fault identifiers of each power terminal in the power network, a terminal monitoring status database is created.

4. The method according to claim 3, characterized in that, The terminal monitoring status database includes a first terminal monitoring status database and a second terminal monitoring status database. The step of creating the terminal monitoring status database based on the fault identifiers of each power terminal in the power network includes: The fault identifiers in the power network that represent power terminals prone to failure are stored in the first terminal monitoring status database. The fault identifiers in the power network that indicate power terminals that are not prone to failure are stored in the second terminal monitoring status database.

5. The method according to claim 3, characterized in that, Obtaining the fault status data of the first monitoring point includes: By monitoring the operational data of the first monitoring point in at least one time period in chronological order, an operational data sequence of the first monitoring point is obtained, wherein the operational data includes the maintenance information of the first monitoring point. Based on the operational data sequence, the fault status data of the first monitoring point is obtained.

6. A fault detection device, characterized in that, The device includes: The first determining module is used to determine the fault identifier of the target power terminal corresponding to the fault point when a fault point is detected in the power network. The fault identifier is used to characterize whether the target power terminal is prone to failure. The second determining module is used to determine the location of the fault point based on the location of the target power terminal when the fault identifier indicates that the target power terminal is prone to failure. The first determining module is specifically used for: The fault status data of the target power terminal is obtained, and the fault status data of the target power terminal is input into the fault prediction model to predict the fault identifier, thereby obtaining the fault identifier of the target power terminal. The fault status data of the target power terminal includes at least one fault status information of the target power terminal in the time series. The target fault status information is used to characterize the operating status of the target power terminal within a target time period. The target fault status information is any one of the at least one fault status information. The target time period is the time period corresponding to the target fault status information in the time series. The operating status includes normal status and abnormal status. The fault identifier includes two types: the first type indicates that the target power terminal is prone to failure; the second type indicates that the target power terminal is not prone to failure.

7. The apparatus according to claim 6, characterized in that, The first determining module is specifically used for: The fault identifier of the target power terminal corresponding to the fault point is obtained from a pre-created terminal monitoring status database, which stores the fault identifiers of each power terminal in the power network.

8. The apparatus according to claim 7, characterized in that, The device further includes: The acquisition module is used to acquire training sample data, which includes fault status data and fault labels of multiple monitoring points. The fault label of the first monitoring point is a fault identifier marked based on the fault status data of the first monitoring point, and the first monitoring point is any one of the multiple monitoring points. The training module is used to train the fault prediction model based on the training sample data; The third determining module is used to determine the fault identifier of each power terminal in the power network based on the fault prediction model after the fault prediction model has been trained. A module is created to create a terminal monitoring status database based on the fault identifiers of each power terminal in the power network.

9. The apparatus according to claim 8, characterized in that, The terminal monitoring status database includes a first terminal monitoring status database and a second terminal monitoring status database. The creation module is specifically used for: The fault identifiers in the power network that represent power terminals prone to failure are stored in the first terminal monitoring status database. The fault identifiers in the power network that indicate power terminals that are not prone to failure are stored in the second terminal monitoring status database.

10. The apparatus according to claim 8, characterized in that, The acquisition module is specifically used for: By monitoring the operational data of the first monitoring point in at least one time period in chronological order, an operational data sequence of the first monitoring point is obtained, wherein the operational data includes the maintenance information of the first monitoring point. Based on the operational data sequence, the fault status data of the first monitoring point is obtained.

11. An electronic device, characterized in that, The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the fault detection method as described in any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the fault detection method as described in any one of claims 1 to 5.

Images