Power system fault positioning method and device, processor and storage medium

Abstract

The invention discloses a power system fault positioning method and device, a processor and a storage medium. The method comprises the following steps: acquiring basic data of the power system, the basic data being used for indicating electrical parameters of a plurality of monitoring points in the power system; on the basis of the basic data, graph structure information of the power system is determined, and the graph structure information is used for representing the positions of multiple monitoring points in the power system and the connection relation between the multiple monitoring points; the graph structure information is input into a target detection model to be analyzed, the fault position of the power system is obtained, the target detection model is obtained by training historical basic data of the power system, and the historical basic data are used for indicating historical electrical parameters of multiple monitoring points in the power system. According to the invention, the technical problem of low power system fault positioning efficiency is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system fault detection, and in particular to a method, device, processor and storage medium for locating a power system fault. Background Art

[0002] At present, as one of the infrastructures of modern society, the power system undertakes the important task of providing stable and reliable power supply to various users. However, the power system is highly complex, including multiple links such as power generation, transmission, and distribution, involving a large number of equipment and lines. This complexity makes the power system prone to various faults during operation, such as line short circuits and equipment damage. The stability of the power system is the basis for its efficient operation. When a system fails, if it cannot be located and repaired in time, it may cause the fault to expand and even cause the system to collapse. Therefore, in the power system, accurately and quickly locating the fault point is crucial to ensure the stable operation of the power system.

[0003] In the related art, the fault diagnosis methods based on manual experience, such as fault tree analysis, fault mode and effect analysis, event tree analysis, etc., rely on the experience and knowledge level of the operator, so their accuracy may be limited. Therefore, there is a technical problem of low efficiency in locating power system faults.

[0004] With respect to the above-mentioned technical problem of low efficiency in locating power system faults, no effective solution has been proposed so far. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, processor and storage medium for locating a power system fault, so as to at least solve the technical problem of low efficiency in locating a power system fault.

[0006] According to one aspect of an embodiment of the present invention, a method for locating a power system fault is provided. The method may include: obtaining basic data of the power system, wherein the basic data is used to indicate electrical parameters of multiple monitoring points in the power system; determining graph structure information of the power system based on the basic data, wherein the graph structure information is used to indicate the locations of multiple monitoring points in the power system and the connection relationship between the multiple monitoring points; inputting the graph structure information into a target detection model for analysis to obtain the fault location of the power system, wherein the target detection model is trained using historical basic data of the power system, and the historical basic data is used to indicate historical electrical parameters of multiple monitoring points in the power system.

[0007] Optionally, based on basic data, graph structure information of the power system is determined, including: based on the basic data, determining each monitoring point of the power system, wherein the monitoring point is used to indicate a location for monitoring the operating status of the power system; based on the monitoring point, determining the graph structure information of the power system.

[0008] Optionally, based on the monitoring points, graph structure information of the power system is determined, including: based on the monitoring points, determining monitoring point connection data, wherein the monitoring point connection data is used to indicate connection information between monitoring points; and constructing the monitoring points and monitoring point data into graph structure information of the power system.

[0009] Optionally, the method for locating a power system fault further includes: acquiring historical basic data of the power system; and training an initial detection model using the historical basic data to obtain a target detection model.

[0010] Optionally, the historical basic data is input into the initial detection model for training to obtain a target detection model, including: determining the historical fault types of power system faults corresponding to the historical basic data; determining adjustment parameters of the initial detection model based on the historical fault types and the historical basic data; and training the initial detection model based on the adjustment parameters and the historical basic data to obtain a target detection model.

[0011] Optionally, the method for locating a power system fault further includes: evaluating an initial detection model to determine an evaluation result of the initial detection model, wherein the evaluation result is used to indicate the accuracy of the initial detection model in locating the power system fault; in response to the evaluation result being greater than an evaluation result threshold, determining the initial detection model as a target detection model.

[0012] According to another aspect of an embodiment of the present invention, a device for locating a fault in a power system is also provided. The device may include: an acquisition unit, used to acquire basic data of the power system, wherein the basic data is used to indicate electrical parameters of multiple monitoring points in the power system; a determination unit, used to determine graph structure information of the power system based on the basic data, wherein the graph structure information is used to indicate the locations of multiple monitoring points in the power system and the connection relationship between the multiple monitoring points; an analysis unit, used to input the graph structure information into a target detection model for analysis to obtain the fault location of the power system, wherein the target detection model is trained using historical basic data of the power system, and the historical basic data is used to indicate historical electrical parameters of multiple monitoring points in the power system.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method for locating a power system fault in an embodiment of the present invention.

[0014] According to another aspect of an embodiment of the present invention, a processor is further provided. The processor is used to run a program, wherein when the program is run, the method for locating a power system fault in an embodiment of the present invention is executed.

[0015] According to another aspect of the embodiment of the present invention, a computer program product is also provided, which includes computer instructions, and when the computer instructions are executed by a processor, the method for locating a power system fault in the embodiment of the present invention is implemented.

[0016] In an embodiment of the present invention, basic data of an electric power system is obtained, wherein the basic data is used to indicate electrical parameters of multiple monitoring points in the electric power system; based on the basic data, graph structure information of the electric power system is determined, wherein the graph structure information is used to indicate the locations of multiple monitoring points in the electric power system and the connection relationship between the multiple monitoring points; the graph structure information is input into a target detection model for analysis to obtain the fault location of the electric power system, wherein the target detection model is trained using historical basic data of the electric power system, and the historical basic data is used to indicate historical electrical parameters of multiple monitoring points in the electric power system. In other words, the present invention establishes graph structure information of the electric power system through the basic data of the electric power system, and inputs the graph structure information into the target detection model for analysis, thereby determining the fault location of the electric power system, thereby solving the technical problem of low efficiency in locating electric power system faults, and achieving the technical effect of improving the efficiency of locating electric power system faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 is a flow chart of a method for locating a power system fault according to an embodiment of the present invention;

[0019] Figure 2 is a flow chart of a novel power system method according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of a device for locating a power system fault according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, functional component or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, functional components or devices.

[0023] According to an embodiment of the present invention, an embodiment of a method for locating a power system fault is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] Figure 1 FIG. 1 is a flow chart of a method for locating a power system fault according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0025] Step S101, obtaining basic data of the power system.

[0026] In the technical solution provided in the above step S101 of the present invention, the basic data is used to indicate the electrical parameters of multiple monitoring points in the power system.

[0027] In this embodiment, basic data of the power system is obtained, where the basic data may be electrical parameters such as current, voltage, power, etc. of the power system.

[0028] Optionally, by installing sensors at key nodes of the power system, basic data of the power system is obtained through the sensors. This is only an illustrative example and does not limit the specific method of obtaining the basic data of the power system.

[0029] Step S102: determining graph structure information of the power system based on basic data.

[0030] In the technical solution provided in the above step S102 of the present invention, the graph structure information is used to represent the locations of multiple monitoring points in the power system and the connection relationship between the multiple monitoring points.

[0031] In this embodiment, after the basic data of the power system is acquired in step S101, the graph structure information of the power system is determined according to the basic data, wherein the graph structure information may also be referred to as graph structure.

[0032] Optionally, each monitoring point of the power system is determined from the basic data, the monitoring points are used as nodes in the graph structure, and the connection information between the nodes is used as edges in the graph structure, so as to establish a graph structure model and further determine the graph structure information.

[0033] For example, the power system is abstracted into a graph structure G = (V, E), where V can be used to represent a set of nodes, representing monitoring points in the power system; E is an edge set, representing the connections between monitoring points.

[0034] Optionally, by analyzing and calculating the properties of the nodes and edges of the power system, more accurate heuristic information can be provided for fault location, thereby improving the efficiency and accuracy of fault location, wherein the heuristic information may be the distance between nodes, etc.

[0035] Step S103: input the graph structure information into the target detection model for analysis to obtain the fault location of the power system.

[0036] In the technical solution provided in the above step S103 of the present invention, the target detection model is trained using historical basic data of the power system, and the historical basic data is used to indicate historical electrical parameters of multiple monitoring points in the power system.

[0037] In this embodiment, after the graph structure information of the power system is determined in step S102, the graph structure information is input into the target detection model for analysis to obtain the fault location of the power system.

[0038] Optionally, historical basic data of the power system is input into an initial detection model for training, thereby determining a target detection model. The initial detection model may include a fault location algorithm.

[0039] For example, for each node v in the graph structure information i ∈V, giving the following properties: the electrical parameter vector P i =(I i ,V i ,W i ...), where I iCan be used to represent node v i Current value, V i is the voltage value, W i It is the power value and other related electrical parameters. Position coordinates (x i ,y i ,z i )(If it is a three-dimensional space, or on a two-dimensional plane (x i ,y i )) is used to calculate the distance between nodes and other heuristic information. For each edge e ij =(v i ,v j )∈E, determine the following attributes: weight w ij , calculated as follows: Considering the electrical characteristics, the initial detection model can be expressed using the following formula (1):

[0040] E ij =k1×|I i -I j |+k2×|V i -V j |+k3×|W i -W J |+… (1)

[0041] Among them, K1, K2, K3, ... can be used to represent adjustment coefficients. The adjustment coefficients can be adjusted according to actual conditions. The adjustment coefficients are continuously determined by inputting historical basic data into the above initial detection model for training, thereby obtaining a target detection model.

[0042] It should be noted that the above embodiments can be implemented by a power system fault locating device.

[0043] In the above steps S101 to S103 of the present invention, basic data of the power system is obtained, wherein the basic data is used to indicate the electrical parameters of multiple monitoring points in the power system; based on the basic data, the graph structure information of the power system is determined, wherein the graph structure information is used to indicate the locations of multiple monitoring points in the power system and the connection relationship between the multiple monitoring points; the graph structure information is input into the target detection model for analysis to obtain the fault location of the power system, wherein the target detection model is trained using the historical basic data of the power system, and the historical basic data is used to indicate the historical electrical parameters of multiple monitoring points in the power system. In other words, the embodiment of the present invention establishes the graph structure information of the power system through the basic data of the power system, and inputs the graph structure information into the target detection model for analysis, thereby determining the fault location of the power system, thereby solving the technical problem of low efficiency in locating power system faults, and achieving the technical effect of improving the efficiency of locating power system faults.

[0044] The above method of this embodiment is further introduced below.

[0045] As an optional implementation method, step S102, based on basic data, determines the graph structure information of the power system, including: based on the basic data, determines each monitoring point of the power system, wherein the monitoring point is used to indicate the location for monitoring the operating status of the power system; based on the monitoring point, determines the graph structure information of the power system.

[0046] In this embodiment, each monitoring point of the power system is determined from the basic data. For example, the location information of the monitoring points of the power system is extracted from the basic data. This is only an example and does not limit the specific method of determining the monitoring points of the power system.

[0047] Optionally, the graph structure information of the power system is determined according to each monitoring point. For example, each monitoring point is abstracted into a node set, that is, the node set V represents the monitoring points in the power system, so as to construct a graph structure model of the power system according to the node set, and then determine the graph structure information of the power system according to the graph structure model.

[0048] As an optional implementation method, the graph structure information of the power system is determined based on the monitoring points, including: determining the monitoring point connection data based on the monitoring points, wherein the monitoring point connection data is used to indicate the connection information between the monitoring points; and constructing the monitoring points and the monitoring point data into the graph structure information of the power system.

[0049] In this embodiment, the monitoring point connection data is determined according to each monitoring point, for example, by determining the connection information between each monitoring point, thereby determining the monitoring point connection data.

[0050] Optionally, the monitoring points and monitoring point data are constructed as graph structure information of the power system, that is, the power system is abstracted into a graph structure G = (V, E), where V is a node set representing the monitoring points in the power system; E is an edge set representing the connection information between the monitoring points.

[0051] As an optional implementation method, historical basic data is input into an initial detection model for training to obtain a target detection model, including: determining the historical fault types of power system faults corresponding to the historical basic data; determining adjustment parameters of the initial detection model based on the historical fault types and the historical basic data; and training the initial detection model based on the adjustment parameters and the historical basic data to obtain a target detection model.

[0052] In this embodiment, the historical fault type of the power system fault corresponding to the historical basic data is determined, wherein the fault type may be a short circuit fault, a ground fault, and the like.

[0053] Optionally, the adjustment parameters of the initial detection model are determined according to the historical fault types and historical basic data. The adjustment parameters may also be referred to as adjustment coefficients, which are used to adjust the weights of different electrical parameters in the calculation of electrical characteristic factors. For example, in the aforementioned formula (1), K1, K2, K3, etc. represent adjustment coefficients, which may be determined according to the specific characteristics of the power system, the fault type, and the analysis results of the actual data.

[0054] Optionally, the initial detection model is trained according to the adjustment parameters and historical basic data to obtain the target detection model. For example, the initial detection model is trained according to the adjustment parameters and historical basic data. If it is determined that the difference in current parameters is very important for judging the electrical connection status between two monitoring points, the current parameter value can be increased so that the current difference occupies a larger proportion in the electrical characteristic factors.

[0055] Optionally, the adjustment coefficient can also be used to adjust the weight of voltage parameter differences. The value can be adjusted according to the importance of voltage parameters to fault judgment in the actual power system. If the voltage change has a significant indicative effect on the fault, the weight of the voltage change can be appropriately increased. It is mainly used to adjust the weight of power parameter differences. When the change of power parameters has a greater impact on determining the fault location, the weight of the power parameters can be increased.

[0056] Optionally, by determining different adjustment parameters, the adjustment coefficient can be determined according to the specific power system characteristics, fault type and analysis results of actual data. By adjusting these coefficients, the target detection model can be better adapted to different power system scenarios and the accuracy of fault location can be improved.

[0057] As an optional implementation mode, the method for locating power system faults also includes: evaluating the initial detection model to determine an evaluation result of the initial detection model, wherein the evaluation result is used to indicate the accuracy of the initial detection model in locating power system faults; in response to the evaluation result being greater than an evaluation result threshold, determining the initial detection model as a target detection model.

[0058] In this embodiment, the initial detection model is evaluated to determine the evaluation result of the initial detection model. For example, the initial detection model is evaluated using different evaluation indicators, which is only an example and does not limit the specific method of evaluating the initial detection model.

[0059] Optionally, when the evaluation result is greater than the evaluation result threshold, it indicates that the accuracy of the initial detection model meets the detection requirement at this time. Based on this, the initial detection model can be determined as the target detection model.

[0060] Optionally, the fault location results are verified and evaluated, and the models and algorithms are continuously improved to improve the accuracy and reliability of fault location.

[0061] It should be noted that the above embodiments can be implemented by a power system fault locating device.

[0062] In this embodiment, basic data of the power system is obtained, wherein the basic data is used to indicate the electrical parameters of multiple monitoring points in the power system; based on the basic data, graph structure information of the power system is determined, wherein the graph structure information is used to indicate the locations of multiple monitoring points in the power system and the connection relationship between the multiple monitoring points; the graph structure information is input into a target detection model for analysis to obtain the fault location of the power system, wherein the target detection model is trained using historical basic data of the power system, and the historical basic data is used to indicate the historical electrical parameters of multiple monitoring points in the power system. In other words, the embodiment of the present invention establishes graph structure information of the power system through the basic data of the power system, and inputs the graph structure information into the target detection model for analysis, thereby determining the fault location of the power system, thereby solving the technical problem of low efficiency in locating power system faults, and achieving the technical effect of improving the efficiency of locating power system faults.

[0063] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0064] At present, as one of the infrastructures of modern society, the power system undertakes the important task of providing stable and reliable power supply to various users. However, the power system is highly complex, including multiple links such as power generation, transmission, and distribution, involving a large number of equipment and lines. This complexity makes the power system prone to various faults during operation, such as line short circuits and equipment damage. The stability of the power system is the basis for its efficient operation. When a system fails, if it cannot be located and repaired in time, it may cause the fault to expand and even cause the system to collapse. Therefore, in the power system, accurately and quickly locating the fault point is crucial to ensure the stable operation of the power system.

[0065] In the related art, the fault diagnosis methods based on manual experience, such as fault tree analysis, fault mode and effect analysis, event tree analysis, etc., rely on the experience and knowledge level of the operator, so their accuracy may be limited. Therefore, there is a technical problem of low efficiency in locating power system faults. With respect to the above-mentioned technical problem of low efficiency in locating power system faults, no effective solution has been proposed so far.

[0066] However, an embodiment of the present invention proposes a new power system model and method for locating power system faults. By collecting electrical parameters such as current, voltage, and power, and determining the location coordinates of nodes, the power system is abstracted into a graph structure, and the fault location of the power system is determined using the constructed model. By adjusting the algorithm parameters and the adjustment coefficients in the model, the performance of fault location is optimized, thereby solving the technical problem of low efficiency in locating power system faults and achieving the technical effect of improving the efficiency of locating power system faults.

[0067] The embodiments of the present invention are further described below.

[0068] Figure 2 is a flow chart of a novel power system method according to an embodiment of the present invention, the analysis method comprising the following steps:

[0069] Step S201 , collecting electrical parameters such as current, voltage, power, etc. of the power system, and determining the location coordinates of the nodes.

[0070] In this embodiment, sensors are installed at key nodes of the power system to collect electrical parameters such as current, voltage, power, etc., and determine the location coordinates of the nodes.

[0071] Step S202: construct a power system model based on the collected data and determine the attributes of nodes and edges.

[0072] In this embodiment, the power system is abstracted into a graph structure G=(V, E), where V is a node set representing monitoring points in the power system; and E is an edge set representing connections between monitoring points.

[0073] Optionally, for each node v i ∈V, giving the following properties: the electrical parameter vector P i =(I i ,V i ,W i …), where I i is node v i Current value, V i is the voltage value, W i It is the power value and other related electrical parameters.

[0074] Optionally, the position coordinates (x i ,y i ,z i )(If it is a three-dimensional space, or on a two-dimensional plane (x i ,y i )) is used to calculate the distance between nodes and other heuristic information. For each edge e ij =(v i ,v j)∈E, determine the following attributes: weight w ij , calculated by the above formula (1).

[0075] Optionally, in the aforementioned power system model, K1, K2, K3, etc. are adjustment coefficients used to adjust the weights of different electrical parameters in the calculation of electrical characteristic factors.

[0076] Optionally, the adjustment coefficient is used to adjust the weight of the current parameter difference in the electrical characteristic factor. For example, if the difference in the current parameter is considered to be very important for determining the electrical connection state between two monitoring points, the value can be increased so that the current difference occupies a larger proportion in the electrical characteristic factor.

[0077] Optionally, the adjustment coefficient can also be used to adjust the weight of voltage parameter differences. The value can be adjusted according to the importance of voltage parameters to fault judgment in the actual power system. If the voltage change has a significant effect on the indication of the fault, it can be appropriately increased. It is mainly used to adjust the weight of power parameter differences. When the change of power parameters has a greater impact on determining the fault location, it can be increased.

[0078] Optionally, these adjustment coefficients can be determined according to the specific characteristics of the power system, the fault type and the analysis results of the actual data. By adjusting these coefficients, the model can be better adapted to different power system scenarios and the accuracy of fault location can be improved.

[0079] Optionally, considering the physical distance, if the location coordinates of the node are (X, Y, Z), the physical distance can be expressed using the following formula (2):

[0080]

[0081] Optionally, further set the distance factor The matrix is ​​introduced to comprehensively consider the electrical characteristics and distance, then the electrical characteristics M E , element M E (i,j) represents node v i and v j The electrical characteristic relationship between them can be based on the electrical characteristic factor E ij To set up, let the distance matrix M D , where M D (i,j) represents node v i and v j The distance relationship between them can be calculated based on the distance factor D ij Make settings.

[0082] Alternatively, the electrical characteristics and distance relationships between nodes in the power system are complex and diverse. By introducing a matrix, these relationships can be represented in a structured way. The electrical characteristic matrix can integrate the difference information of multiple electrical parameters such as current, voltage, and power, and fully reflect the electrical connection between nodes. The distance matrix can accurately reflect the spatial position relationship between nodes, providing important clues about distance for fault location.

[0083] Optionally, the matrix format makes it easier to store and process various relationships. Matrix operations can be used to quickly calculate edge weights between nodes, improving the efficiency of the algorithm. At the same time, the matrix also facilitates data analysis and pattern recognition, helping to discover potential fault characteristics and patterns.

[0084] Optionally, the weight function can be expressed using the following formula (3):

[0085] w ij =f(M E (i,j),M D (i,j)) (3)

[0086] Optionally, a linear function is used to further adjust the model, wherein the linear function can be expressed using the following formula (4):

[0087] f(M E (i,j),M D (i,j))=(M E (i,j) γ +1)×(M D (i,j) δ +1) (4)

[0088] Among them, γ and δ are adjustment parameters used to balance the contribution of electrical characteristics and distance in edge weight.

[0089] Step S203: Apply the constructed model to the fault location algorithm to determine the target detection model.

[0090] In this embodiment, the constructed model can be combined with various fault location algorithms, and is particularly suitable for fault location based on ant colony algorithm. In the ant colony algorithm, ants will select paths based on the edge weights and electrical parameter differences between nodes, thereby gradually approaching the fault point.

[0091] Optionally, by analyzing and calculating the attributes of nodes and edges in the model, more accurate heuristic information can be provided for fault location, thereby improving the efficiency and accuracy of fault location.

[0092] Optionally, the introduction of matrices provides a basis for combining with more complex algorithms. For example, advanced algorithms such as matrix decomposition technology and graph neural networks can be used to analyze and process the electrical characteristic matrix and distance matrix to further improve the accuracy and efficiency of fault location.

[0093] Optionally, during the optimization of the model, the matrix can be adjusted as an important parameter. By adjusting the element values, structure, and parameters of the matrix, different weight distribution schemes can be explored to find the optimal fault location strategy. At the same time, the matrix is ​​also convenient for parallel computing and distributed processing, providing an effective solution for fault location in large-scale power systems.

[0094] Step S204: perform fault detection on the power system using the target detection model.

[0095] In this embodiment, the currently acquired data of the power system is input into the target detection model to perform fault detection on the power system.

[0096] Alternatively, in actual power systems, the relationships between nodes are often not simple linear relationships. Introducing matrices can better capture these complex nonlinear relationships, thereby improving the accuracy of the model's description of the power system. For example, by adjusting the element values ​​of the electrical characteristic matrix and the distance matrix, flexible modeling can be performed according to different power system scenarios and fault types, making the model more adaptable.

[0097] Optionally, adapt to systems of different sizes: The matrix can be easily expanded and adjusted for power systems of different sizes and structures. Whether it is a small local power network or a large complex power system, the relationship between nodes can be accurately described by constructing a suitable matrix to ensure that the model can effectively locate faults in various situations.

[0098] Optionally, power system fault location is a key link to ensure stable operation of the power system, and existing methods thereof mainly include the following: offline fault location method, online fault location method and other methods.

[0099] Optionally, the offline fault location method includes: pulse signal injection method and fault indicator method. Among them, the pulse signal injection method injects a high-voltage pulse signal into the disconnected fault line and then detects the fault point along the line. The specific method is to use the DC method to locate the section and the AC method to locate the point.

[0100] Alternatively, the pulse signal injection method requires power outage and disconnection of the faulty line, and also requires the provision of on-board power, which may cause certain inconveniences in actual operation.

[0101] Optionally, the fault indicator method installs a ground short circuit fault indicator on the line to detect the line current in real time. When a fault is detected, the fault indicator flips, emits light or sends an alarm signal.

[0102] Alternatively, although the fault indicator method can be monitored online, the installation and maintenance costs are high, and the fault indicator needs to be checked and replaced regularly.

[0103] Optionally, the online fault location method includes: S signal injection method and partial discharge method. Among them, the S signal injection method injects a 220H signal on the low voltage side of the PT. Z signals and detect fault points along the way.

[0104] Alternatively, the capital cost of the s signal injection method is relatively large, and it may increase the workload of line maintenance, and there are certain safety hazards.

[0105] Alternatively, the partial discharge method locates the fault by monitoring the partial discharge signal of the cable. Partial discharge is generated when the cable insulation material is aged, damaged or defective. Specific sensors and measuring equipment are used to monitor in real time, detect the strength and location of the discharge signal, and thus determine the fault area.

[0106] Alternatively, the partial discharge method has high requirements on the accuracy of the monitoring equipment and may be interfered by environmental factors.

[0107] Optionally, the cable reflection method locates the fault based on the reflection characteristics of the signal in the cable. A voltage or current signal is applied at one end, and the reflected signal is received at the other end. The transmission time and intensity change are measured, and the approximate distance of the fault is calculated based on the signal transmission speed and reflection time.

[0108] Alternatively, the cable reflection method measurement accuracy may be affected by factors such as cable length, load resistance and fault type.

[0109] Alternatively, time domain reflectometry analyzes the transmission line characteristics and reflected signals in the cable. A pulse signal is sent at one end, and the time and amplitude of the reflected signal are measured to calculate the fault distance and type.

[0110] Alternatively, for signals propagating over long distances, the time domain reflectometry method has more factors affecting the wave velocity, which makes it difficult to accurately estimate, resulting in increased positioning errors.

[0111] Alternatively, infrared thermography uses an infrared thermal imager to scan the cable and detect heat changes at the fault point. Cable faults are often accompanied by local temperature rise, and the thermal imager can visualize the heat distribution and determine the fault location.

[0112] Alternatively, infrared thermal imaging is affected by ambient temperature and cable heat dissipation conditions and may not accurately reflect the actual temperature of the fault point.

[0113] Optionally, other methods include fault ranging and traveling wave ranging.

[0114] Optionally, the fault distance measurement calculates the fault distance by measuring electrical quantities (such as voltage and current) between the fault point and the measuring end.

[0115] Optionally, the fault distance measurement may result in inaccurate distance measurement results due to the influence of different circuit lengths and waveform distortion factors.

[0116] Optionally, traveling wave ranging uses the propagation characteristics of traveling waves generated by faults in transmission lines to perform ranging.

[0117] Optionally, the installation and maintenance of traveling wave ranging requires power outage, and the power supply method is difficult; the accuracy is affected by external factors such as terrain, meteorological conditions, and line parameter changes.

[0118] In summary, the existing methods have certain shortcomings in terms of cost and positioning effect. Based on this, the present invention provides a new power system model that can more effectively support power fault location, improve the accuracy and speed of fault location, and enhance adaptability to power systems of different sizes and types.

[0119] In this embodiment, by collecting electrical parameters such as current, voltage, and power, and determining the location coordinates of the nodes, the power system is abstracted into a graph structure, and the fault location of the power system is determined using the constructed model. By adjusting the algorithm parameters and the adjustment coefficients in the model, the performance of fault location is optimized, thereby solving the technical problem of low efficiency in locating power system faults and achieving the technical effect of improving the efficiency of locating power system faults.

[0120] According to an embodiment of the present invention, a power system fault location device is also provided. It should be noted that the power system fault location device can be used to execute the power system fault location method in the method embodiment.

[0121] Figure 3 FIG. 1 is a schematic diagram of a device for locating a power system fault according to an embodiment of the present invention. Figure 3 As shown, the power system fault positioning device 300 may include: an acquisition unit 301 , a determination unit 302 and an analysis unit 303 .

[0122] The acquisition unit 301 is used to acquire basic data of the power system, wherein the basic data is used to indicate electrical parameters of multiple monitoring points in the power system.

[0123] The determination unit 302 is used to determine graph structure information of the power system based on basic data, wherein the graph structure information is used to represent the locations of multiple monitoring points in the power system and the connection relationship between the multiple monitoring points.

[0124] The analysis unit 303 is used to input the graph structure information into the target detection model for analysis to obtain the fault location of the power system, wherein the target detection model is trained using the historical basic data of the power system, and the historical basic data is used to indicate the historical electrical parameters of multiple monitoring points in the power system.

[0125] Optionally, the determination unit 302 may include: a first determination module, used to determine each monitoring point of the power system based on basic data, wherein the monitoring point is used to indicate the location for monitoring the operating status of the power system; and a second determination module, used to determine the graph structure information of the power system based on the monitoring point.

[0126] Optionally, the second determination module may include: a determination submodule, used to determine monitoring point connection data based on the monitoring points, wherein the monitoring point connection data is used to indicate connection information between the monitoring points; and a construction submodule, used to construct the monitoring points and monitoring point data into graph structure information of the power system.

[0127] Optionally, the power system fault positioning device 300 may further include: a first acquisition unit, used to acquire historical basic data of the power system; and a training unit, used to train an initial detection model using the historical basic data to obtain a target detection model.

[0128] Optionally, the training unit may include: a third determination module, used to determine the historical fault type of the power system fault corresponding to the historical basic data; a fourth determination module, used to determine the adjustment parameters of the initial detection model based on the historical fault type and the historical basic data; a training module, used to train the initial detection model based on the adjustment parameters and the historical basic data to obtain a target detection model.

[0129] Optionally, the power system fault locating device 300 may further include: an evaluation unit, used to evaluate the initial detection model and determine the evaluation result of the initial detection model, wherein the evaluation result is used to indicate the accuracy of the initial detection model in locating the power system fault; and a second determination unit, used to determine the initial detection model as a target detection model in response to the evaluation result being greater than an evaluation result threshold.

[0130] In this embodiment, basic data of the power system is obtained, wherein the basic data is used to indicate the electrical parameters of multiple monitoring points in the power system; based on the basic data, graph structure information of the power system is determined, wherein the graph structure information is used to indicate the locations of multiple monitoring points in the power system and the connection relationship between the multiple monitoring points; the graph structure information is input into a target detection model for analysis to obtain the fault location of the power system, wherein the target detection model is trained using historical basic data of the power system, and the historical basic data is used to indicate the historical electrical parameters of multiple monitoring points in the power system. In other words, the embodiment of the present invention establishes graph structure information of the power system through the basic data of the power system, and inputs the graph structure information into the target detection model for analysis, thereby determining the fault location of the power system, thereby solving the technical problem of low efficiency in locating power system faults, and achieving the technical effect of improving the efficiency of locating power system faults.

[0131] According to an embodiment of the present invention, a computer-readable storage medium is further provided. The storage medium includes a stored program, wherein the program executes the method for locating a power system fault in the method embodiment.

[0132] According to an embodiment of the present invention, a processor is further provided. The processor is used to run a program, wherein the method for locating a power system fault in the method embodiment is executed when the program is run.

[0133] According to an embodiment of the present invention, a computer program product is further provided. The computer program product includes computer instructions. When the computer instructions are executed by a processor, the method for locating a power system fault in the method embodiment is implemented.

[0134] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0135] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent functional component, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software functional component, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program codes.

[0140] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for locating a power system fault, characterized in that: include: Acquiring basic data of the power system, wherein the basic data is used to indicate electrical parameters of a plurality of monitoring points in the power system; Based on the basic data, determining graph structure information of the power system, wherein the graph structure information is used to represent the positions of the plurality of monitoring points in the power system and the connection relationship between the plurality of monitoring points; The graph structure information is input into a target detection model for analysis to obtain the fault location of the power system, wherein the target detection model is trained using historical basic data of the power system, and the historical basic data is used to indicate historical electrical parameters of multiple monitoring points in the power system.

2. The method according to claim 1, characterized in that Determining graph structure information of the power system based on the basic data includes: Based on the basic data, determining each of the monitoring points of the power system, wherein the monitoring point is used to indicate a location for monitoring an operating state of the power system; Based on the monitoring points, the graph structure information of the power system is determined.

3. The method according to claim 2, characterized in that Determining the graph structure information of the power system based on the monitoring point includes: Based on the monitoring points, determining the monitoring point connection data, wherein the monitoring point connection data is used to indicate connection information between the monitoring points; The monitoring points and the monitoring point data are constructed into the graph structure information of the power system.

4. The method according to claim 1, characterized in that The method further comprises: Acquiring the historical basic data of the power system; The initial detection model is trained using the historical basic data to obtain the target detection model.

5. The method according to claim 4, characterized in that Inputting the historical basic data into the initial detection model for training to obtain the target detection model includes: Determine the historical fault type of the power system fault corresponding to the historical basic data; Determining adjustment parameters of the initial detection model based on the historical fault types and the historical basic data; Based on the adjustment parameters and the historical basic data, the initial detection model is trained to obtain the target detection model.

6. The method according to claim 5, characterized in that The method further comprises: Evaluating the initial detection model to determine an evaluation result of the initial detection model, wherein the evaluation result is used to indicate the accuracy of the initial detection model in locating the power system fault; In response to the evaluation result being greater than an evaluation result threshold, the initial detection model is determined as the target detection model.

7. A device for locating a power system fault, characterized in that: include: An acquisition unit, configured to acquire basic data of a power system, wherein the basic data is used to indicate electrical parameters of a plurality of monitoring points in the power system; A determining unit, configured to determine graph structure information of the power system based on the basic data, wherein the graph structure information is used to represent the locations of a plurality of monitoring points in the power system and the connection relationship between the plurality of monitoring points; An analysis unit is used to input the graph structure information into a target detection model for analysis to obtain a fault location of the power system, wherein the target detection model is trained using historical basic data of the power system, and the historical basic data is used to indicate historical electrical parameters of multiple monitoring points in the power system.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 6.

9. A processor, characterized in that: The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 6 when running.

10. A computer program product, characterized in that The computer program product comprises computer instructions, which implement the method according to any one of claims 1 to 6 when executed by a processor.

Images