Substation fault inspection method and system based on data analysis
By building the topology diagram of substation equipment and optimizing the inspection route based on the degree of failure impact, the problem of inefficient inspection in the existing technology is solved, and more efficient fault detection and repair is achieved.
Patent Information
- Application Number
- CN202411648801.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-19
- Publication Date
- 2024-12-17
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing substation inspection methods ignore the correlation between electrical equipment, resulting in inefficient inspections.
Using data analysis methods, we can build a topology chart by calculating the impact of faults between electrical equipment, plan inspection routes, prioritize equipment with high failure rates and high impact, update the initial failure rate of unrepaired equipment, and determine priority. , ensure that inspection is completed with as little electrical equipment as possible.
It improves the efficiency of substation fault inspection, accurately quantifies the impact of faults between equipment, reduces unnecessary inspections, and improves inspection efficiency.
Smart Images
Figure CN119151261A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of substation inspection, and more specifically, to a substation fault inspection method and system based on data analysis. Background Art
[0002] As an important part of the power dispatching system, the substation plays a key role in the conversion and distribution of electric energy. The substation includes a variety of electrical equipment such as transformers, switchgear (such as circuit breakers, disconnectors, etc.), mutual inductors, capacitors, reactors, voltage regulators, and relay protection devices. Through the mutual cooperation of various electrical equipment, the substation is in a normal state; in order to ensure the safe and stable operation of the substation, operation and maintenance personnel are required to inspect the electrical equipment in the substation.
[0003] The existing Chinese patent application document with publication number CN109872010A discloses a task allocation method for a substation inspection robot, the method comprising: constructing a task point set, the task point set comprising task point locations and task point inspection task amounts; setting the number of security points of the inspection robot; constructing a site selection optimization model for the security points according to the task point inspection task amounts; solving the site selection optimization model according to the number of security points in combination with a particle swarm algorithm and a weighted Voronoi diagram algorithm to obtain security point locations and security point task allocation; the substation inspection robot task allocation method combines the site selection optimization model for the security points and the preset number of security points, optimizes the security point locations and the security point task allocation through a particle swarm algorithm and a weighted Voronoi diagram algorithm, and obtains an optimal location and task allocation solution.
[0004] The above method requires inspection of all task points, and the inspection task volume is huge. However, in the actual inspection process, different electrical equipment in the substation are related, and it is not necessary to inspect all electrical equipment. Therefore, ignoring the correlation between different electrical equipment leads to low efficiency of substation fault inspection. Summary of the invention
[0005] In order to solve the problem of low inspection efficiency, the present invention proposes a substation fault inspection method and system based on data analysis, which can consider the correlation between different electrical equipment and improve the inspection efficiency of substation fault inspection.
[0006] In a first aspect, the present invention discloses a substation fault inspection method based on data analysis, the method comprising: calculating the fault influence of the connected equipment of any electrical equipment in the substation on the electrical equipment; using the fault influence as the edge weight to construct a topological graph, the topological graph comprising each electrical equipment, and directed edges pointing from the connected equipment to the corresponding electrical equipment; planning the inspection route in the topological graph according to the inspection failure rate of the repaired equipment during the inspection, comprising: setting the initial failure rate of each electrical equipment in the topological graph to 1; after the equipment is inspected this time, updating the initial failure rate of the unrepaired equipment according to the inspection failure rate of the repaired equipment; in response to the initial failure rate of the unrepaired equipment being less than the fault threshold, or there being no unrepaired equipment, stopping the inspection, otherwise, calculating the priority of each unrepaired equipment, and taking the unrepaired equipment with the highest priority as the next inspection equipment; the unrepaired equipment The priorities are: , For unrepaired equipment Equipment under repair The distance between For unrepaired equipment The initial failure rate, The unmaintained equipment in the topology diagram The number of outgoing edges, For unrepaired equipment No. The edge weight of the outgoing edge, For the The sum of the edge weights of all the incoming edges of the electrical equipment at the end point of the outgoing edge; is a preset function, in response to the The electrical equipment at the end of the strip is unmaintained. ,on the contrary, .
[0007] The topology map is used to accurately quantify the impact of the connected devices of any electrical equipment on the failure of the electrical equipment. Before the inspection process begins, the initial failure rates of all electrical equipment are set to 1. During the inspection process, the equipment that has been repaired for the first time is used as the starting point. Every time an equipment maintenance is completed, the initial failure rate of the unmaintained equipment is updated in the topology map based on the maintenance failure rate of the repaired equipment, and then the priority of the unmaintained equipment is calculated. The unmaintained equipment with the highest priority is used as the next maintenance equipment until the initial failure rate of the unmaintained equipment is less than the failure threshold, or there is no unmaintained equipment, and the inspection is completed. During the inspection process, there is no need to repair all electrical equipment, which improves the inspection efficiency.
[0008] Preferably, the connected equipment includes a primary connected equipment, and calculating the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment includes: constructing an electrical equipment Failure rate prediction model: , For electrical equipment The failure rate, For electrical equipment The number of connected devices, For connected devices The failure rate, For connected devices For electrical equipment The least square method is used to fit the failure rate prediction model in the historical inspection data to determine the impact of each connected device on the electrical equipment. The impact of the failure.
[0009] Preferably, the connected device includes K connected devices, and calculating the influence of the connected device of any electrical device in the substation on the fault of the electrical device includes: setting an initial K value, and constructing an electrical device Failure rate prediction model: , For electrical equipment The failure rate, For electrical equipment The number of connected devices, For connected devices The failure rate, For connected devices For electrical equipment The failure rate prediction model is fitted in the historical inspection data using the least squares method to determine the initial K value of each connected device on the electrical equipment. The fault impact degree and fitting error of each connected device are obtained; the initial K value is updated multiple times to obtain the fitting errors of different initial K values, and the fitting error curve is drawn; the initial K value corresponding to the inflection point of the fitting error curve is used as the target K value, and the influence of each connected device on the electrical equipment is obtained when the target K value is obtained. The impact of the failure.
[0010] The larger the K value is, the more connected devices the electrical equipment corresponds to, which leads to a larger amount of calculation. In order to ensure that the failure rate of the corresponding electrical equipment can be accurately predicted based on the failure rate of the connected equipment, different target K values are selected for different electrical equipment based on the fitting error curve, which balances the contradiction between the fitting error and the amount of calculation.
[0011] Preferably, the constructing of the topological graph includes: taking each electrical device as a node; for any electrical device, drawing a directed edge from each connected device to the electrical device, and taking the fault impact of each connected device on the electrical device as the edge weight of the directed edge.
[0012] The topology map is constructed based on the fault correlation between the electrical equipment in the substation. The topology map can directly reflect the impact of the connected equipment on the fault of the electrical equipment. Under the premise that the failure rate of all connected equipment is known, the failure rate of the electrical equipment corresponding to all connected equipment can be predicted through the topology map.
[0013] Preferably, any electrical equipment is used as the initial maintenance equipment in the inspection process.
[0014] Preferably, the starting degree of each electrical device is calculated, and the electrical device with the maximum starting degree is used as the first maintenance device in the inspection process, and the starting degree is positively correlated with the number of outgoing edges of each electrical device in the topological graph.
[0015] The outgoing edge of an electrical device is a directed edge in the topological graph starting from the electrical device; the more outgoing edges an electrical device has, the more electrical devices the electrical device can affect, and the failure rates of more electrical devices can be predicted based on the maintenance failure rate of the electrical device.
[0016] Preferably, electrical equipment The starting degree is equal to the electrical equipment The number of outgoing edges.
[0017] Preferably, electrical equipment Starting degree for: , For electrical equipment The number of outgoing edges, For electrical equipment No. The edge weight of the outgoing edge, For the The sum of the edge weights of all incoming edges in the electrical equipment to which the outgoing edge points.
[0018] For For electrical equipment pointed to by the strip, if , indicating that the electrical device has only one connected device (electrical device ), that is, only based on electrical equipment The maintenance failure rate can accurately predict the failure rate of the electrical equipment. The larger the value, the better the electrical equipment No. The greater the contribution of the strip edge to predicting the failure rate of other electrical equipment, the greater the contribution of the electrical equipment The larger the starting degree.
[0019] Preferably, unrepaired equipment The updating process of the initial failure rate is as follows: , and Unrepaired equipment The number of repaired and unrepaired connected devices, For repaired equipment To unrepaired equipment The edge weight of the directed edge of For repaired equipment The maintenance failure rate, For unrepaired equipment To unrepaired equipment The edge weight of the directed edge of For unrepaired equipment The initial failure rate, For unrepaired equipment initial failure rate.
[0020] In a second aspect, the present invention discloses a substation fault inspection system based on data analysis, comprising: a processor; and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the system executes the above-mentioned substation fault inspection method based on data analysis.
[0021] Beneficial effects of the present invention: The topology map is used to accurately quantify the impact of the connected devices of any electrical equipment on the failure of the electrical equipment. Before the inspection process begins, the initial failure rates of all electrical equipment are set to 1. During the inspection process, the equipment that has been repaired for the first time is used as the starting point. Every time an equipment maintenance is completed, the initial failure rate of the unmaintained equipment is updated in the topology map based on the maintenance failure rate of the repaired equipment, and then the priority of the unmaintained equipment is calculated. The unmaintained equipment with the highest priority is used as the next maintenance equipment until the initial failure rate of the unmaintained equipment is less than the failure threshold, or there is no unmaintained equipment, and the inspection is completed. During the inspection process, there is no need to repair all electrical equipment, which improves the inspection efficiency.
[0022] Furthermore, in the case of unrepaired equipment When determining the priority, we comprehensively consider the distance, initial failure rate, and the update effect of the initial failure rate of the unrepaired equipment in the topology map. Equipment under repair The distance between The smaller the size, the higher the priority; unrepaired equipment Initial failure rate The larger the value, the higher the priority. After the maintenance, the initial failure rate of other unmaintained equipment can be accurately predicted, and the updating effect of the initial failure rate of unmaintained equipment in the topology map is better, so that the inspection can be completed with as few electrical equipment as possible, thereby improving the inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 The present invention is a flowchart of a method for substation fault inspection based on data analysis according to an embodiment of the present invention.
[0024] Figure 2 Schematic diagram of K-times connected devices according to an embodiment of the present invention.
[0025] Figure 3 It is a schematic diagram of a topological diagram of an embodiment of the present invention.
[0026] Figure 4 It is a flow chart of an embodiment of the present invention for planning an inspection route in a topology map according to the inspection failure rate of electrical equipment during the inspection process. DETAILED DESCRIPTION
[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.
[0028] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.
[0029] The present invention provides a substation fault inspection method based on data analysis, which is used to plan the inspection route during the inspection process. Figure 1 As shown, a substation fault inspection method based on data analysis includes S1-S3, which is described in detail below.
[0030] S1, calculating the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment.
[0031] In one embodiment, the historical inspection data includes the failure rate of each electrical device during the historical inspection. The failure rate ranges from 0 to 1, and the larger the value, the greater the probability of failure of the electrical device.
[0032] For any electrical equipment in the substation, the connected equipment of the electrical equipment is obtained, wherein the connected equipment includes a primary connected equipment, wherein the primary connected equipment is directly connected to the electrical equipment. Since the primary connected equipment is electrically connected to the electrical equipment, the primary connected equipment will affect the failure rate of the electrical equipment.
[0033] Specifically, calculating the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment includes: constructing an electrical equipment Failure rate prediction model: , For electrical equipment The failure rate, For electrical equipment The number of connected devices, For connected devices The failure rate, For connected devices For electrical equipment The least square method is used to fit the failure rate prediction model in the historical inspection data to determine the impact of each connected device on the electrical equipment. The impact of the failure.
[0034] In this way, following the same steps, the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment can be obtained, and the failure rate of the connected equipment can be used to predict the fault of the electrical equipment. failure rate.
[0035] In another embodiment, the connected device includes K times connected devices, for example, see Figure 2 , is a schematic diagram of K-times connected devices in an embodiment of the present invention; if electrical device 1 is connected to electrical device 2, electrical device 2 is connected to electrical device 3, and electrical device 3 is connected to electrical device 4, then electrical device 1 is a secondarily connected device of electrical device 3, electrical device 1 is a tertiary connected device of electrical device 4, and so on.
[0036] Specifically, calculating the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment includes: setting the initial K value, and constructing the electrical equipment Failure rate prediction model: , For electrical equipment The failure rate, For electrical equipment The number of connected devices, For connected devices The failure rate, For connected devices For electrical equipment The failure rate prediction model is fitted in the historical inspection data using the least squares method to determine the initial K value of each connected device on the electrical equipment. The fault impact degree and fitting error of each connected device are obtained; the initial K value is updated multiple times to obtain the fitting errors of different initial K values, and the fitting error curve is drawn; the initial K value corresponding to the inflection point of the fitting error curve is used as the target K value, and the influence of each connected device on the electrical equipment is obtained when the target K value is obtained. The impact of the failure.
[0037] The initial K value is 1, and each time the initial K value is updated, the initial K value is increased by 1. It can be understood that different electrical devices correspond to different target K values.
[0038] In this way, according to the connection relationship between each electrical equipment, the connected equipment of each electrical equipment in the substation is determined, and the influence of each connected equipment on the failure of the electrical equipment is calculated, so that the failure rate of the corresponding electrical equipment can be predicted by the failure rate of each connected equipment.
[0039] S2, using the fault impact as an edge weight to construct a topology graph, wherein the topology graph includes each electrical device and directed edges from the connected devices to the corresponding electrical devices.
[0040] In one embodiment, the topology graph includes nodes and edges, wherein one node corresponds to one electrical device, and there is a directed edge between the electrical device and its connected device, and the directed edge points from the connected device to the corresponding electrical device.
[0041] Specifically, the construction of the topology graph includes: taking each electrical device as a node; for any electrical device, drawing a directed edge from each connected device to the electrical device, and taking the fault impact of each connected device on the electrical device as the edge weight of the directed edge.
[0042] It can be understood that the connected devices may include K-times connected devices. If the value of K in the K-times connected devices is 2, then the electrical devices in the topology diagram Secondary connected devices Will be directly connected to electrical equipment , and from the 2nd connected device Pointing to electrical equipment .
[0043] In this way, the topology map is constructed based on the fault correlation between the electrical equipment in the substation, and the topology map can directly reflect the influence of the connected equipment on the fault of the electrical equipment.
[0044] S3, planning the inspection route in the topology map according to the inspection failure rate of the electrical equipment during the inspection process.
[0045] In one embodiment, see Figure 3 , is a schematic diagram of a topology diagram of an embodiment of the present invention, the target K value of electrical device 2 is 2, and the target K values of electrical devices 1, 3 and 4 are all 1; for electrical device 2 in the topology diagram, its connected devices include electrical device 1, 3 and 4; under the premise of knowing the failure rate of the connected devices, the failure rate of electrical device 2 can be predicted, and the failure rate of electrical device 2 satisfy: , and are the failure rates of electrical equipment 1, electrical equipment 3, and electrical equipment 4, respectively. is the edge weight of directed edge 12 from electrical device 1 to electrical device 2, and They are the edge weights of directed edge 32 and directed edge 42 respectively.
[0046] During the inspection process, after an electrical device is inspected and repaired, the inspection failure rate of the electrical device can be obtained, and then the failure rate of other electrical devices can be predicted based on the topology map, providing data reference for the inspection path during the inspection process.
[0047] See also Figure 4 , is a flow chart of planning an inspection route in a topology map according to the inspection failure rate of electrical equipment during the inspection process according to an embodiment of the present invention. Specifically, planning an inspection route in a topology map according to the inspection failure rate of electrical equipment during the inspection process includes S301 to S303.
[0048] S301, setting the initial failure rate of each electrical device in the topology map to 1.
[0049] Before the inspection begins, the initial failure rate of each electrical device in the topology diagram is set to 1; that is, the initial failure rate of all electrical devices has reached the maximum, and all electrical devices need to be inspected and repaired.
[0050] S302, after the equipment is overhauled, the initial failure rate of the unrepaired equipment is updated according to the repair failure rate of the repaired equipment.
[0051] In the inspection process, multiple inspections are required. When the equipment to be inspected is the first inspection, the inspector can use any electrical equipment as the first inspection equipment in the inspection process, for example, use electrical equipment 1 as the first inspection equipment.
[0052] In another embodiment, in order to determine the equipment to be inspected for the first time during the inspection process, the starting degree of each electrical device is calculated, and the electrical device with the maximum starting degree is used as the equipment to be inspected for the first time during the inspection process. The starting degree is positively correlated with the number of outgoing edges of each electrical device in the topological graph, wherein an outgoing edge of an electrical device is a directed edge in the topological graph with the electrical device as the starting point; the more outgoing edges an electrical device has, the more electrical devices it can affect, and the failure rates of more electrical devices can be predicted based on the maintenance failure rate of the electrical device.
[0053] Specifically, electrical equipment Starting degree for: , For electrical equipment The number of outgoing edges, For electrical equipment No. The edge weight of the outgoing edge, For the The sum of the edge weights of all incoming edges in the electrical equipment to which the outgoing edge points.
[0054] Understandably, for For electrical equipment pointed to by the strip, if , indicating that the electrical device has only one connected device (electrical device ), that is, only based on electrical equipment The maintenance failure rate can accurately predict the failure rate of the electrical equipment. The larger the value, the better the electrical equipment No. The greater the contribution of the strip edge to predicting the failure rate of other electrical equipment, the greater the contribution of the electrical equipment The larger the starting degree.
[0055] It should be noted that in other embodiments, the electrical device The initial degree of is equal to the number of outgoing edges.
[0056] In one embodiment, after the equipment to be overhauled for the first time is determined, the inspection process can be started. After each overhaul of the equipment is completed, the initial failure rate of the un-overhauled equipment is updated according to the overhaul failure rate of the overhauled equipment.
[0057] Specifically, unrepaired equipment The updating process of the initial failure rate is as follows: , and Unrepaired equipment The number of repaired and unrepaired connected devices, For repaired equipment To unrepaired equipment The edge weight of the directed edge of For repaired equipment The maintenance failure rate, For unrepaired equipment To unrepaired equipment The edge weight of the directed edge of For unrepaired equipment The initial failure rate, For unrepaired equipment initial failure rate.
[0058] In this way, each time the maintenance of an electrical device is completed, the initial failure rate of the unmaintained equipment is updated in the topology map according to the maintenance failure rate of the repaired equipment during the inspection process.
[0059] S303, in response to the initial failure rate of the unmaintained equipment being less than the failure threshold, or there being no unmaintained equipment, the inspection is stopped. Otherwise, the priority of each unmaintained equipment is calculated, and the unmaintained equipment with the highest priority is selected as the next maintenance equipment.
[0060] Among them, after the initial failure rate of the unmaintained equipment is updated, the initial failure rate of the unmaintained equipment is compared with the failure threshold, and the failure threshold is 0.5; if the initial failure rate of the unmaintained equipment is less than the failure threshold, it means that the unmaintained equipment is in normal condition. At this time, the inspection can be stopped, and there is no need to repair all electrical equipment, thereby improving the inspection efficiency; if there is no unmaintained equipment, it means that the maintenance work of all electrical equipment in the substation has been completed, and the inspection can also be stopped.
[0061] On the contrary, if there are unmaintained devices and the initial failure rate of the unmaintained devices is greater than or equal to the failure threshold, it is necessary to calculate the priority of each unmaintained device and use the unmaintained device with the highest priority as the next maintenance device until the inspection is stopped.
[0062] Specifically, unrepaired equipment The priorities are: , For unrepaired equipment Equipment under repair The distance between For unrepaired equipment The initial failure rate, The unmaintained equipment in the topology diagram The number of outgoing edges, For unrepaired equipment No. The edge weight of the outgoing edge, For the The sum of the edge weights of all the incoming edges of the electrical equipment at the end point of the outgoing edge; is a preset function, in response to the The electrical equipment at the end of the strip is unmaintained. ,on the contrary, .
[0063] Understandably, the equipment was not repaired Equipment under repair The distance between The smaller the value, the equipment is not repaired. Equipment under repair The closer it is, the higher its priority; unrepaired equipment Initial failure rate The larger the value, the more unrepaired the equipment is. The greater the probability of failure, the higher its priority; Indicates that the equipment is not repaired After the maintenance, the update effect of the initial failure rate of the unmaintained equipment in the topology map is larger, the better the update effect of the initial failure rate of the unmaintained equipment in the topology map is. The higher the priority, the greater the The electrical equipment at the end of the strip is unmaintained. The value of is 1, when When After the inspection, the The initial failure rate of the electrical equipment at the end of the edge, The maximum value is achieved, which ensures the updating effect of the initial failure rate of the unmaintained equipment in the topology diagram, and thus completes the inspection under the premise of repairing as few electrical equipment as possible, thereby improving the inspection efficiency.
[0064] In this way, the topology map is used to accurately quantify the impact of the connected devices of any electrical equipment on the failure of the electrical equipment. During the inspection process, the first maintenance equipment is used as the starting point. Every time an equipment maintenance is completed, the initial failure rate of the unmaintained equipment is updated in the topology map based on the maintenance failure rate of the repaired equipment, and then the priority of the unmaintained equipment is calculated. The unmaintained equipment with the highest priority is used as the next maintenance equipment until the initial failure rate of the unmaintained equipment is less than the failure threshold, or there is no unmaintained equipment, and the inspection is completed. During the inspection process, there is no need to inspect all electrical equipment, which improves the inspection efficiency.
[0065] An embodiment of the present invention further discloses a substation fault inspection system based on data analysis, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a substation fault inspection method based on data analysis according to the present invention is implemented.
[0066] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.
[0067] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.
[0068] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.
[0069] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A substation fault inspection method based on data analysis, characterized in that: The method comprises: Calculate the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment; Using the fault impact as an edge weight to construct a topology graph, the topology graph includes each electrical device and directed edges from the connected devices to the corresponding electrical devices; Planning the inspection route in the topology map according to the repair failure rate of the repaired equipment during the inspection process, including: setting the initial failure rate of each electrical equipment in the topology map to 1; after the equipment is repaired this time, updating the initial failure rate of the unrepaired equipment according to the repair failure rate of the repaired equipment; in response to the initial failure rate of the unrepaired equipment being less than the failure threshold, or there being no unrepaired equipment, stopping the inspection, otherwise, calculating the priority of each unrepaired equipment, and taking the unrepaired equipment with the highest priority as the next repair equipment; Unmaintained equipment The priorities are: , For unrepaired equipment Equipment under repair The distance between For unrepaired equipment The initial failure rate, The unmaintained equipment in the topology diagram The number of outgoing edges, For unrepaired equipment No. The edge weight of the outgoing edge, For the The sum of the edge weights of all the incoming edges of the electrical equipment at the end point of the outgoing edge; is a preset function, in response to the The electrical equipment at the end of the strip is unmaintained. ,on the contrary, .
2. A substation fault inspection method based on data analysis according to claim 1, characterized in that: The connected equipment includes a primary connected equipment, and calculating the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment includes: Building electrical equipment Failure rate prediction model: , For electrical equipment The failure rate, For electrical equipment The number of connected devices, For connected devices The failure rate, For connected devices For electrical equipment The impact of the failure; The least squares method is used to fit the failure rate prediction model in the historical inspection data to determine the impact of each connected device on the electrical equipment. The impact of the failure.
3. A substation fault inspection method based on data analysis according to claim 1, characterized in that: The connected equipment includes K-times connected equipment, and calculating the influence of the connected equipment of any electrical equipment in the substation on the fault of the electrical equipment includes: Set the initial K value and build the electrical device Failure rate prediction model: , For electrical equipment The failure rate, For electrical equipment The number of connected devices, For connected devices The failure rate, For connected devices For electrical equipment The impact of the failure; The least square method is used to fit the failure rate prediction model in the historical inspection data to determine the initial K value of each connected device for electrical equipment. The fault impact and fitting error; Update the initial K value multiple times to obtain the fitting errors of different initial K values and draw the fitting error curve; take the initial K value corresponding to the inflection point of the fitting error curve as the target K value, and obtain the electrical equipment of each connected device at the target K value. The impact of the failure.
4. A substation fault inspection method based on data analysis according to claim 1, characterized in that: The construction of the topology graph includes: taking each electrical device as a node; for any electrical device, drawing a directed edge from each connected device to the electrical device, and taking the fault impact of each connected device on the electrical device as the edge weight of the directed edge.
5. A substation fault inspection method based on data analysis according to claim 1, characterized in that: Use any electrical equipment as the initial inspection equipment in the inspection process.
6. A substation fault inspection method based on data analysis according to claim 1, characterized in that: The starting degree of each electrical device is calculated, and the electrical device with the maximum starting degree is used as the first maintenance device in the inspection process. The starting degree is positively correlated with the number of outgoing edges of each electrical device in the topology graph.
7. A substation fault inspection method based on data analysis according to claim 6, characterized in that: Electrical Equipment The starting degree is equal to the electrical equipment The number of outgoing edges.
8. A substation fault inspection method based on data analysis according to claim 6, characterized in that: Electrical Equipment Starting degree for: , For electrical equipment The number of outgoing edges, For electrical equipment No. The edge weight of the outgoing edge, For the The sum of the edge weights of all incoming edges in the electrical equipment to which the outgoing edge points.
9. A substation fault inspection method based on data analysis according to claim 1, characterized in that: Unmaintained equipment The updating process of the initial failure rate is as follows: , and Unrepaired equipment The number of repaired and unrepaired connected devices, For repaired equipment To unrepaired equipment The edge weight of the directed edge of For repaired equipment The maintenance failure rate, For unrepaired equipment To unrepaired equipment The edge weight of the directed edge of For unrepaired equipment The initial failure rate, For unrepaired equipment initial failure rate.
10. A substation fault inspection system based on data analysis, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the system executes a substation fault inspection method based on data analysis according to any one of claims 1 to 9.