Intelligent power monitoring methods, devices, equipment, and media based on fault detection
By acquiring the first operating data of power equipment, using fault levels and a preset component knowledge graph to determine reference components, and combining this with a preset fault probability network, the fault type of power equipment can be quickly and accurately determined, thus solving the problem of low fault detection efficiency in existing technologies.
Patent Information
- Application Number
- CN202311661866.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-05
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2043-12-05
AI Technical Summary
Existing technologies for fault detection in power equipment are inefficient, requiring a considerable amount of time to acquire operational data from all components to pinpoint the location of the fault.
By acquiring the first operating data of the power equipment, a reference part is determined based on the fault level and a preset part knowledge graph. The second operating data of the reference part is then acquired, and the fault type of the power equipment is determined using a preset fault probability network.
It improves the efficiency of identifying power equipment fault types, shortens fault detection time, and enhances the accuracy and efficiency of detection.
Smart Images

Figure CN117668692B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power data processing technology, and in particular to an intelligent power monitoring method, device, equipment and medium based on fault detection. Background Technology
[0002] With the advancement and development of science and technology, electrical equipment is not only an important part of people's lives, but also a crucial component of power distribution systems. Within these systems, each piece of electrical equipment is interconnected and mutually influential; a failure in one piece can cause other equipment to malfunction, ultimately leading to the collapse of the entire power distribution system. Therefore, the detection of electrical equipment faults is of paramount importance for the proper functioning of power distribution systems.
[0003] In related technologies, when a fault is detected in power equipment, the operating data of all components in the power equipment is acquired, and the fault is determined by analyzing the operating data of all components. However, power equipment is a complex power system with a large number of components. Whenever a fault occurs in power equipment, it takes a long time to acquire the operating data of all components one by one. It can be seen that the efficiency of related technologies in determining power equipment faults is poor. Summary of the Invention
[0004] To improve the efficiency of identifying faults in power equipment, this application provides an intelligent power monitoring method, device, equipment, and medium based on fault detection.
[0005] Firstly, this application provides an intelligent power monitoring method based on fault detection, employing the following technical solution: An intelligent power monitoring method based on fault detection includes: When a power equipment fault is detected, the first operating data of the power equipment is acquired, and the fault level of the power equipment is determined based on the first operating data; Based on the fault level and the preset component knowledge graph, several reference components are identified. The reference components are the components that are in an abnormal working state when the power equipment fails. Obtain the second operating data corresponding to each of the aforementioned reference parts; Based on the second operating data corresponding to each of the reference parts and the preset fault probability network, the fault type of the power equipment is determined. The preset fault probability network includes several fault types and their corresponding fault probabilities.
[0006] In a preferred embodiment, this application can be further configured such that, based on the fault level and a preset part knowledge graph, a plurality of reference parts are determined, including: Based on multiple initial preset part knowledge graphs and the fault level, a target preset part knowledge graph corresponding to the fault level is determined. The fault duration of the power equipment is obtained, and the number of parts is determined based on the fault duration; Obtain the first position information corresponding to each part in the target preset part knowledge graph; Based on the number of parts, the first position information corresponding to each part, and the preset key positions, several reference parts are determined from all the parts.
[0007] In a preferred embodiment, this application can be further configured such that the process for determining the preset key location includes: Obtain the environmental information and functional attributes of the power equipment; A reference power device is determined based on the environmental information, and a first critical location is determined based on the reference power device, wherein the environmental information of the reference power device is the same as the environmental information. Based on the preset correspondence between functional attributes and key positions, and the functional attributes, the second key position of the functional attributes is determined; The maintenance time of the key location is obtained, and the preset key location range is determined based on the maintenance time, the first key location, and the second key location. The key location includes the first key location and the second key location.
[0008] In a preferred embodiment, this application may be further configured such that, before obtaining the second operating data corresponding to each of the reference parts, it further includes: Acquire the current infrared image and standard infrared image of the power equipment; The current infrared image is matched with the standard infrared image to identify several abnormal image regions in the current infrared image; Obtain the second location information corresponding to all the abnormal image regions; Based on the second position information and the first position information corresponding to each of the parts, target position information is determined, wherein the target position information is the same as the first position information and the second position information. The reference part corresponding to the target location information is determined as the target reference part; Accordingly, obtaining the second operating data corresponding to each of the reference parts includes: Obtain the second operating data corresponding to each of the target reference parts.
[0009] In a preferred embodiment, this application can be further configured such that determining the fault type of the power equipment based on the second operating data corresponding to each of the reference parts and a preset fault probability network includes: The second running data is input into the preset fault probability network to determine the initial fault occurrence probability corresponding to each of the initial fault types; Obtain historical fault information and determine correction coefficients based on the historical fault information; The correction coefficient is used to correct the initial fault occurrence probability corresponding to each of the initial fault types, so as to obtain the target fault occurrence probability corresponding to each of the initial fault types. From all the target fault occurrence probabilities, an initial fault type corresponding to the maximum target fault occurrence probability is selected, and the initial fault type corresponding to the maximum target fault occurrence probability is used to determine the fault type of the power equipment.
[0010] In a preferred embodiment, this application may be further configured such that, after determining the fault type of the power equipment based on the second operating data corresponding to each of the reference parts and a preset fault probability network, it also includes: Determine the target correspondence of the environmental information of the power equipment, and based on the target correspondence and the fault type, determine the fault cause corresponding to the fault type. The target correspondence is the correspondence between the fault type and the fault cause under the environmental information. The equipment identification, third-party location information, and maintenance information of the maintenance personnel of the power equipment are obtained, wherein the maintenance information includes: maintenance plan and maintenance location; Based on the third location information, the maintenance plan, and the maintenance location, a target maintenance personnel is determined, wherein the third location information of the power equipment is within the range of the target maintenance personnel's maintenance location; A maintenance signal is generated based on the device identifier and all the causes of the fault, and the maintenance signal is sent to the device on the target maintenance personnel side for maintenance.
[0011] Secondly, this application provides an intelligent power monitoring device based on fault detection, which adopts the following technical solution: An intelligent power monitoring device based on fault detection includes: The fault level determination module is used to acquire the first operating data of the power equipment when a fault is detected, and to determine the fault level of the power equipment based on the first operating data. The reference part determination module is used to determine a number of reference parts based on the fault level and a preset part knowledge graph. The reference parts are the parts that are in an abnormal working state when the power equipment fails. The acquisition module is used to acquire the second operating data corresponding to each of the reference parts; The fault type determination module is used to determine the fault type of the power equipment based on the second operating data corresponding to each of the reference parts and a preset fault probability network. The preset fault probability network includes several fault types and their corresponding fault probabilities.
[0012] In a preferred embodiment, this application can be further configured such that, when the reference part determination module determines several reference parts based on the fault level and a preset part knowledge graph, it is used to: Based on multiple initial preset part knowledge graphs and the fault level, a target preset part knowledge graph corresponding to the fault level is determined. The fault duration of the power equipment is obtained, and the number of parts is determined based on the fault duration; Obtain the first position information corresponding to each part in the target preset part knowledge graph; Based on the number of parts, the first position information corresponding to each part, and the preset key positions, several reference parts are determined from all the parts.
[0013] Thirdly, this application provides an electronic device that adopts the following technical solution: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: execute the intelligent power monitoring method based on fault detection as described in any of the first aspects.
[0014] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the intelligent power monitoring method based on fault detection as described in any of the first aspects.
[0015] In summary, this application includes the following beneficial technical effects: When a power equipment fault is detected, the first operating data of the power equipment is acquired, and the fault level is determined based on the first operating data to conduct targeted detection from the perspective of fault level. When the fault level of the power equipment is different, the parts that cause the fault are different. Several reference parts are determined based on the fault level and a preset part knowledge graph, effectively narrowing down the range of reference parts. Then, the second operating data corresponding to each reference part is acquired. A preset fault probability network is set with several fault types and fault probabilities as references. Therefore, the fault type of the power equipment is determined based on the fault types and fault probabilities given in the preset fault probability network, combined with the second operating data of the reference parts, thus effectively improving the efficiency of determining the fault type of the power equipment. Compared with related technologies that determine the fault type of power equipment based on all parts, this application achieves the purpose of determining the fault type by referencing the fault level and reference parts in a targeted manner, thereby achieving the technical effect of improving the efficiency of determining the fault type of power equipment and solving the technical problem of poor efficiency in determining the fault type of power equipment in related technologies. Attached Figure Description
[0016] Figure 1 This is a flowchart illustrating an intelligent power monitoring method based on fault detection, provided in an embodiment of this application.
[0017] Figure 2 This is a schematic diagram of a component knowledge graph provided in an embodiment of this application.
[0018] Figure 3 This is a schematic diagram of the structure of an intelligent power monitoring device based on fault detection, provided in an embodiment of this application.
[0019] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0020] The following is in conjunction with the appendix Figure 1 To be continued Figure 4 This application will be described in further detail.
[0021] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of this application.
[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application are described clearly and completely. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0023] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.
[0024] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.
[0025] This application provides an intelligent power monitoring method based on fault detection, executed by an electronic device. This electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method includes steps S101, S102, S103, and S104, wherein: Step S101: When a power equipment fault is detected, the first operating data of the power equipment is acquired, and the fault level of the power equipment is determined based on the first operating data.
[0026] Specifically, the electronic device detects the power equipment based on a preset detection cycle. When the first operating data of the power equipment is not the preset standard operating data, the power equipment is determined to be faulty. The preset standard operating data is pre-entered into the electronic device by relevant technicians. This application embodiment does not limit the preset detection cycle and the preset standard operating data. The power equipment can be any power equipment in the power distribution system. The first operating data can be one or multiple. For example, when the power equipment is a transformer, the corresponding first operating data can be: transformer current, transformer voltage or transformer frequency, etc. The first operating data can be detected in real time by the corresponding sensor and transmitted to the electronic device. In this embodiment, the fault levels include: a first fault level, a second fault level, and a third fault level. The degree of fault increases with the level of fault, indicating a more severe fault in the power equipment. The fault level is determined based on the deviation between the first operating data and the corresponding preset standard operating data. Specifically, this involves calculating the deviation between the first operating data and the corresponding preset standard operating data, and determining the deviation score corresponding to the deviation value based on a preset correspondence between the deviation value and the deviation score. Then, the target fault level corresponding to the deviation score is determined based on the correspondence between the deviation score and the fault level, serving as the fault level of the power equipment. The preset correspondence between the deviation value and the deviation score, and the correspondence between the deviation score and the fault level, are pre-set by technicians. A larger deviation value corresponds to a larger deviation score, indicating a significant change in the operating state of the power equipment, thus resulting in a higher fault level.
[0027] Step S102: Based on the fault level and the preset part knowledge graph, determine a number of reference parts. The reference parts are the parts that are in an abnormal working state when the power equipment fails.
[0028] Specifically, the preset component knowledge graph is set and input into the electronic device by relevant technical personnel based on their work experience. Different preset component knowledge graphs correspond to different fault levels. The preset component knowledge graph includes the electronic device and the components corresponding to the fault level. Reference components can be abnormal components or faulty components; abnormal components are those in a state between abnormal operation and complete failure. The specific implementation method for determining reference components based on the fault level and the preset component knowledge graph can be found in the following embodiments. It is understood that the preset knowledge graph contains multiple components and is more intuitive; therefore, determining reference components based on the preset knowledge graph can effectively improve the efficiency of reference component determination. For example... Figure 2 The diagram shown is a schematic diagram of a component knowledge graph provided in an embodiment of this application, wherein the transformer is a power device, and the core, windings and cooler are all reference components of the transformer.
[0029] Step S103: Obtain the second running data corresponding to each of the reference parts.
[0030] Specifically, the second set of operational data consists of real-time monitoring by the corresponding sensors and uploaded to the electronic device.
[0031] Step S104: Based on the second operating data corresponding to each of all reference parts and the preset fault probability network, determine the fault type of the power equipment. The preset fault probability network includes several fault types and their corresponding fault probabilities.
[0032] Specifically, the fault type of power equipment can be determined based on historical fault information and correction coefficients, or based on the average fault occurrence probability. In one feasible approach, determining the fault type based on the average fault occurrence probability includes: for each fault type, calculating the sum of fault occurrence probabilities, obtaining the frequency of occurrence of each fault type in all reference parts, obtaining the average fault occurrence probability of each fault type based on the frequency of occurrence and the sum of fault occurrence probabilities, and selecting the fault type corresponding to the highest average fault occurrence probability as the fault type of the power equipment. In this embodiment, preferably, the fault type of the power equipment is determined based on historical fault information and correction coefficients; specific implementation methods can be found in the following embodiments.
[0033] In this embodiment, when a power equipment fault is detected, first operating data of the power equipment is acquired, and the fault level is determined based on the first operating data to perform targeted detection from the perspective of fault level. When the fault level of the power equipment is different, the parts causing the fault are different. Several reference parts are determined based on the fault level and a preset part knowledge graph, effectively narrowing down the range of reference parts. Then, second operating data corresponding to each reference part is acquired. A preset fault probability network is set with several fault types and fault probabilities as references. Therefore, the fault type of the power equipment is determined based on the fault types and fault probabilities given in the preset fault probability network, combined with the second operating data of the reference parts, thus effectively improving the efficiency of determining the fault type of the power equipment. Compared with related technologies that determine the fault type of power equipment based on all parts, this application achieves the purpose of determining the fault type by referencing the fault level and reference parts in a targeted manner, thereby achieving the technical effect of improving the efficiency of determining the fault type of power equipment and solving the technical problem of poor efficiency in determining the fault type of power equipment in related technologies.
[0034] In one possible implementation of this application embodiment, step S102 determines several reference parts based on the fault level and a preset part knowledge graph, including: Based on multiple initial preset part knowledge graphs and fault levels, determine the target preset part knowledge graph corresponding to the fault level; Obtain the fault duration of the power equipment and determine the number of parts based on the fault duration; Obtain the first position information of each part in the target preset part knowledge graph; Based on the number of parts, the first position information corresponding to each part, and the preset key positions, several reference parts are determined from all parts.
[0035] Specifically, the fault level can be matched with the fault levels corresponding to multiple preset part knowledge graphs to determine the target preset part knowledge graph corresponding to the fault level. When the power equipment fails, the electronic equipment will automatically retrieve the first operating data of the power equipment. If the first operating data is not data of normal operating status, the corresponding time information and current time information are obtained to determine the fault duration. The number of parts can be determined according to the correspondence between the fault duration and the number of parts. The correspondence between the fault duration and the number of parts is pre-input into the electronic equipment by technicians based on their work experience. It is understood that determining the number of parts can avoid the problem of reduced data calculation efficiency due to too many parts. The determination can be made by obtaining the first position information corresponding to each part from the part position information database. In this embodiment, the first position information of each part is a set of multiple three-dimensional coordinates. Specifically, the preset key position is determined by relevant technicians based on multiple historical data. The specific determination method can refer to the following embodiment. The preset key position is a set of coordinates composed of multiple three-dimensional coordinates. The first position information corresponding to each part is matched one by one with the preset key position to determine the parts located within the preset key position range. Then, the parts with the corresponding value of the part quantity can be determined and used as reference parts. It is understandable that components located in critical positions of electrical equipment are more closely related to the equipment and its fault types. Therefore, identifying electrical equipment faults based on components located in critical positions can effectively improve the accuracy of fault type identification.
[0036] In this embodiment, the reference parts corresponding to the same power equipment are different under different fault levels. Therefore, it is necessary to determine the target preset part knowledge graph based on the fault level and the initial preset part knowledge graph. Then, the fault duration of the power equipment is obtained. When there are more parts in an abnormal working state, that is, the larger the number of parts, the longer the fault duration of the power equipment may be. Therefore, the number of parts can be determined based on the fault duration. The first position information of all parts is obtained. The parts located in key positions are more related to the power equipment. Therefore, based on the number of parts, the first position information of all parts, and the preset key positions, several reference parts are determined to filter out the parts located in key positions, thereby obtaining more accurate reference parts.
[0037] One possible implementation of this application embodiment includes a process for determining a preset key location range, comprising: To obtain environmental information and functional attributes of power equipment; The reference power equipment is determined based on the environmental information, and the first critical location is determined based on the reference power equipment. The environmental information of the reference power equipment is the same as that of the environmental information. Based on the pre-defined correspondence between functional attributes and key positions, and the functional attributes themselves, determine the second key position of the functional attributes; Obtain the maintenance time of key locations, and determine the preset key location range based on the maintenance time, the first key location, and the second key location.
[0038] Specifically, environmental information of power equipment can be obtained from an environmental information database. This database includes multiple power devices and their corresponding environmental information. The environmental information characterizes the environment in which the power equipment is located, such as a basement environment or an outdoor environment. It is understandable that the environment of power equipment affects the operation of components in different locations, potentially leading to different types of failures. Power equipment in the same environment exhibits a higher degree of similarity in the types of failures. For example, the bottom and bottom components of power equipment in a basement environment are more prone to failure, while power equipment in an outdoor environment is more susceptible to sunlight erosion, making its surface and surface components more prone to failure. Functional attributes characterize the function of the power equipment; for example, when the power equipment is a transformer, the corresponding functional attributes could be voltage conversion and power transmission. The environmental information is then matched with the environmental information of other power equipment in the database to identify reference power equipment with the same environmental information. The specific implementation method for determining the first critical position based on reference power equipment includes: acquiring the historical fault positions corresponding to each of the reference power equipment, determining the frequency of each historical fault position (where frequency represents the occurrence frequency of historical fault positions), comparing the frequency of historical fault positions with a preset frequency threshold, and determining the historical fault positions with frequencies greater than the preset frequency threshold as the first critical position. The preset correspondence between functional attributes and critical positions is pre-input into the electronic equipment by technicians and is set based on experience. It is understood that the critical positions differ for power equipment with different functions. For example, when the power equipment is a transformer, the corresponding critical positions could be the location of the core and the windings; when the power equipment is a high-voltage switchgear, the corresponding critical positions could be the location of the circuit breaker and the disconnector, i.e., the second critical position. Specifically, the maintenance time for critical positions can be obtained from the equipment on the maintenance personnel's side, and the maintenance personnel will record the maintenance time for each critical position during maintenance. It is understood that if no maintenance operation has been performed on any critical position, the corresponding maintenance time is 0; otherwise, the corresponding maintenance time is the actual maintenance time. A feasible method for determining the preset critical location range based on maintenance time, the first critical location, and the second critical location includes: determining the weight value of each critical location according to the correspondence between maintenance time and weight values, then determining the target weight value corresponding to each critical location, comparing the target weight value of the critical location with a preset weight value threshold, and determining the critical location corresponding to the target weight value greater than the preset weight value threshold as the preset critical location range. The aforementioned correspondence between maintenance time and weight values is pre-input by relevant technical personnel, and the aforementioned critical locations include the first critical location and the second critical location.
[0039] In this embodiment, the vulnerable parts of power equipment located in different environments are different, and the vulnerable locations of power equipment with different functions are also different. Therefore, the environmental information and functional attributes of the power equipment are obtained, and a reference power equipment is determined based on the environmental information so as to determine the accurate first critical location using the reference power equipment as a reference. Then, the accurate second critical location is obtained based on the correspondence between functional attributes and critical locations. The maintenance time is then obtained, and the longer the maintenance time, the more critical the location is. Therefore, a preset critical location range is determined based on the maintenance time, the accurate first critical location, and the accurate second critical location, so as to effectively improve the accuracy of the preset critical location range.
[0040] One possible implementation of this application embodiment is that step S104 determines the fault type of the power equipment based on the second operating data corresponding to each of all reference parts and a preset fault probability network, including: The second operating data is input into the preset fault probability network to determine the initial fault occurrence probability corresponding to each of the initial fault types. Obtain historical fault information and determine correction coefficients based on the historical fault information; The initial fault occurrence probability corresponding to each of the initial fault types is corrected by the correction coefficient to obtain the target fault occurrence probability corresponding to each of the initial fault types. The initial fault type corresponding to the maximum target fault occurrence probability is selected from all target fault occurrence probabilities, and the fault type of the power equipment is determined by the initial fault type corresponding to the maximum target fault occurrence probability.
[0041] Specifically, the second operating data of each reference part is input into a preset fault probability network to obtain several fault types and corresponding fault occurrence probabilities for that reference part. This allows for the generation of all fault types for all reference parts, i.e., the initial fault types. Then, the fault occurrence probabilities corresponding to each initial fault type are calculated to obtain the sum of fault occurrence probabilities for each initial fault type. This sum of fault occurrence probabilities is then determined as the initial fault occurrence probability for each initial fault type. It is understood that different reference parts correspond to different initial fault types, and therefore, the initial fault probabilities for each initial fault type are also different. Using the sum of fault occurrence probabilities as the initial fault occurrence probability for each initial fault type allows for a comprehensive consideration of fault occurrence probabilities, effectively improving the accuracy of determining the initial fault occurrence probability through more comprehensive data. Historical fault information within a preset time period can be obtained to reduce the amount of data computation. The preset time period is pre-input by technicians into the electronic device; this embodiment does not limit the preset time period. Historical fault information can be obtained from a fault information database, including: historical fault types that occurred within the preset time period and their corresponding historical fault occurrence frequencies. The feasible method for determining the correction coefficient based on historical fault information includes: for each historical fault type, comparing the frequency of historical fault occurrence with the corresponding preset fault occurrence frequency; if the frequency of historical fault occurrence is greater than the preset fault occurrence frequency, then the correction coefficient corresponding to the aforementioned historical fault type is the first correction coefficient; if the frequency of historical fault occurrence is not greater than the preset fault occurrence frequency, then the correction coefficient corresponding to the aforementioned historical fault type is the second correction coefficient; different historical fault types correspond to different preset fault occurrence frequencies, the first correction coefficient is a value greater than 1, and the second correction coefficient is a value less than 1. This application embodiment does not limit the preset fault occurrence frequency, the first correction coefficient, or the second correction coefficient corresponding to the historical fault type. It is understood that when the frequency of occurrence of a certain historical fault type is not greater than the preset fault occurrence frequency, it indicates that the occurrence of the fault corresponding to that historical fault type has a certain degree of randomness. In order to reduce the impact of random fault types, the corresponding correction coefficient is determined to be the second correction coefficient. It can be calculated using the target fault occurrence probability calculation formula: Target fault occurrence probability = Correction coefficient * Initial fault occurrence probability. All initial fault types are sorted in descending order of the probability of the target fault occurring, and the fault type of the power equipment is determined. It can be understood that the initial fault type corresponding to the highest probability of the target fault occurring indicates that, under the current power equipment fault condition, this initial fault type has the highest probability of occurrence compared to other initial fault types. Therefore, this group is used as the fault type of the power equipment, effectively improving the accuracy of power equipment fault type identification.
[0042] In this embodiment, the initial fault occurrence probability is determined based on the second operating data and a preset fault probability network. Then, historical fault information is acquired, and a correction coefficient is determined to correct the initial fault occurrence probability. By correcting the initial fault occurrence probability, a more accurate initial fault occurrence probability can be obtained. Therefore, the correction coefficient is used to correct all initial fault occurrence probabilities to obtain the target fault occurrence probability corresponding to each initial fault type, i.e., a more accurate target fault occurrence probability. The higher the fault occurrence probability of a fault type, the higher the probability that the power equipment will produce a fault of that type. Therefore, based on the accurate target fault occurrence probability, the initial fault type corresponding to the maximum target fault occurrence probability is determined as the fault type of the power equipment, thereby effectively improving the accuracy of fault type determination.
[0043] In one possible implementation of this application embodiment, before step S103 obtains the second operating data corresponding to each of the reference parts, the method further includes: Acquire current and standard infrared images of the power equipment; The current infrared image is matched with a standard infrared image to identify several abnormal image regions in the current infrared image. Obtain the second location information corresponding to all abnormal image regions; Based on the second location information and the first location information, target location information is determined, wherein the target location information is the same as the first location information and the second location information. The reference part corresponding to the target location information is determined as the target reference part; Accordingly, the second operating data corresponding to each of the reference parts is obtained, including: Obtain the second running data corresponding to each of the target reference parts.
[0044] Specifically, the current infrared image of the power equipment can be acquired using an infrared image acquisition device. The standard infrared image is the infrared image of the power equipment when it is in normal operation, and it is a standard infrared image that has been pre-entered into the image database of the electronic device by technicians. Image matching technology can be used for matching. This application embodiment does not limit the specific process of image matching, thereby identifying areas with image differences as abnormal image areas. A three-dimensional coordinate system can be established with any point in the power equipment as the origin to locate the abnormal image area and determine the corresponding second position information. In this application embodiment, when all three-dimensional coordinates in the second position information are the same as all three-dimensional coordinates in the first position information, or when some three-dimensional coordinates in the second position information are the same as some three-dimensional coordinates in the first position information, it is determined as target position information. The aforementioned partial three-dimensional coordinates represent a preset number of identical three-dimensional coordinates. This application embodiment does not limit the preset number; the user can set it themselves. It is understood that the infrared image can be used to verify the reference part in step S102, effectively improving the accuracy of determining the reference part; then, for the verified reference part with higher accuracy, the corresponding second operating data is obtained, thereby improving the accuracy of the second operating data.
[0045] In this embodiment, infrared images and standard images of power equipment are acquired. When a component in the power equipment malfunctions, its temperature rises, and the infrared image changes accordingly. Therefore, the current infrared image and the standard infrared image are matched to determine the abnormal image area, so as to identify the area where the component with the increased temperature is located. Then, the second location information corresponding to the abnormal area is acquired, and the second location information that overlaps with the location information is determined. The reference component corresponding to the target location information is then determined as the target reference component. The infrared image is used to verify the reference component, thereby effectively improving the accuracy of the reference component determination.
[0046] In one possible implementation of this application embodiment, after step S104 determines the fault type of the electronic device based on the second operating data corresponding to each of the target reference parts and the preset fault probability network, it further includes: Determine the target correspondence with environmental information, and based on the target correspondence and fault type, determine the fault cause corresponding to the fault type. The target correspondence is the correspondence between fault type and fault cause under environmental information. Obtain equipment identification, third-party location information, and maintenance information of maintenance personnel for power equipment. The maintenance information includes maintenance plans and maintenance locations. Based on the third location information, maintenance plan, and maintenance location, the target maintenance personnel are identified, and the third location information of the power equipment is within the maintenance location range of the target maintenance personnel; A maintenance signal is generated based on the equipment identifier and the causes of all faults, and then sent to the equipment on the target maintenance personnel side for maintenance.
[0047] Specifically, the equipment identifier of the power equipment can be obtained from the power equipment information database. The equipment identifier can be the equipment number of the power equipment. The target correspondence is the correspondence between fault types and fault causes under the same environmental information, which can be obtained from the environmental information database. It is understood that when the environment in which the power equipment is located is different, the causes of the same fault type may be different, therefore it is necessary to determine the target correspondence corresponding to the environmental information. The cause of the fault is determined based on the target correspondence and the fault type. The personnel identifiers and corresponding maintenance information of all maintenance personnel can be obtained from the maintenance information database. The maintenance information includes: maintenance plan and maintenance location. The feasible way to determine the target maintenance personnel based on the third location information and maintenance plan information includes: matching the third location information with the range of repairable locations of maintenance personnel to determine multiple initial maintenance personnel; then, based on the corresponding power equipment identifier and maintenance time period of each initial maintenance personnel, determining the idle time period of the initial maintenance personnel; sorting them in order of idle time period from front to back; and selecting the maintenance personnel ranked first as the target maintenance personnel. Once the target maintenance personnel are identified, maintenance signals can be sent to their mobile terminals via voice or SMS to remind them to promptly repair the electrical equipment and prevent it from remaining in a state of prolonged damage.
[0048] In this embodiment, the causes of the same fault vary under different environments. Therefore, it is necessary to determine the target correspondence with the environmental information. When different fault types of equipment are the same, the causes of the fault are also different. Therefore, determining the cause of the fault based on the target correspondence and the fault type effectively improves the accuracy of the cause determination. Then, the equipment identifier, third location information and maintenance personnel's maintenance information are obtained to determine the reference equipment. Then, the maintenance personnel's maintenance location and maintenance plan are obtained, and the target maintenance personnel are determined based on the third location information and maintenance plan information so that available and capable maintenance personnel can be arranged to carry out maintenance in a timely manner. Then, a maintenance signal is generated based on the equipment identifier and the cause of the fault and sent to the equipment on the target maintenance personnel's side for timely inspection and maintenance to avoid long-term damage to the power equipment.
[0049] The above embodiments describe an intelligent power monitoring method based on fault detection from the perspective of method flow. The following embodiments describe an intelligent power monitoring device based on fault detection from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.
[0050] This application provides an intelligent power monitoring device based on fault detection, such as... Figure 3 As shown, the intelligent power monitoring device based on fault detection may specifically include: The fault level determination module 201 is used to acquire the first operating data of the power equipment when a fault is detected, and to determine the fault level of the power equipment based on the first operating data. The reference part determination module 202 is used to determine a number of reference parts based on the fault level and a preset part knowledge graph. The reference parts are the parts that are in an abnormal working state when the power equipment fails. The acquisition module 203 is used to acquire the second running data corresponding to each of the reference parts; The fault type determination module 204 is used to determine the fault type of the power equipment based on the second operating data corresponding to each of the reference parts and the preset fault probability network. The preset fault probability network includes several fault types and their corresponding fault probabilities.
[0051] In one possible implementation of this application embodiment, when the reference part determination module 202 determines several reference parts based on fault level and preset part knowledge graph, it is specifically used for: Based on multiple initial preset part knowledge graphs and fault levels, determine the target preset part knowledge graph corresponding to the fault level; Obtain the fault duration of the power equipment and determine the number of parts based on the fault duration; Obtain the first position information of each part in the target preset part knowledge graph; Based on the number of parts, the first position information corresponding to each part, and the preset key positions, several reference parts are determined from all parts.
[0052] One possible implementation of this application's embodiment, an intelligent power monitoring device based on fault detection, further includes: The preset key position determination module is used for: To obtain environmental information and functional attributes of power equipment; The reference power equipment is determined based on the environmental information, and the first critical location is determined based on the reference power equipment. The environmental information of the reference power equipment is the same as that of the environmental information. Based on the pre-defined correspondence between functional attributes and key positions, and the functional attributes themselves, determine the second key position of the functional attributes; Obtain the maintenance time of key locations, and determine the preset range of key locations based on the maintenance time, the first key location, and the second key location. The key locations include the first key location and the second key location.
[0053] One possible implementation of this application's embodiment, an intelligent power monitoring device based on fault detection, further includes: The verification module is used for: Acquire current and standard infrared images of the power equipment; The current infrared image is matched with a standard infrared image to identify several abnormal image regions in the current infrared image. Obtain the second location information corresponding to all abnormal image regions; Based on the second position information and the first position information corresponding to each part, the target position information is determined. The target position information is the second position information that is the same as the first position information and the second position information. The reference part corresponding to the target location information is determined as the target reference part; Accordingly, when acquiring the second running data corresponding to each of the reference parts, the acquisition module 203 is used to: Obtain the second running data corresponding to each of the target reference parts.
[0054] In one possible implementation of this application embodiment, when the fault type determination module 204 determines the fault type of the power equipment based on the second operating data corresponding to each of all reference parts and a preset fault probability network, it is specifically used for: The second operating data is input into the preset fault probability network to determine the initial fault occurrence probability corresponding to each of the initial fault types. Obtain historical fault information and determine correction coefficients based on the historical fault information; The initial fault occurrence probability corresponding to each of the initial fault types is corrected by the correction coefficient to obtain the target fault occurrence probability corresponding to each of the initial fault types. The initial fault type corresponding to the maximum target fault occurrence probability is selected from all target fault occurrence probabilities, and the fault type of the power equipment is determined by the initial fault type corresponding to the maximum target fault occurrence probability.
[0055] One possible implementation of this application's embodiment, an intelligent power monitoring device based on fault detection, further includes: The maintenance module is used for: Determine the target correspondence of environmental information for power equipment, and based on the target correspondence and fault type, determine the fault cause corresponding to the fault type. The target correspondence is the correspondence between fault type and fault cause under environmental information. Obtain equipment identification, third-party location information, and maintenance information of maintenance personnel for power equipment. The maintenance information includes maintenance plans and maintenance locations. Based on the third location information, maintenance plan, and maintenance location, the target maintenance personnel are identified, and the third location information of the power equipment is within the range of the target maintenance personnel's maintenance location; A maintenance signal is generated based on the equipment identifier and the causes of all faults, and then sent to the equipment on the target maintenance personnel side for maintenance.
[0056] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the power equipment fault detection device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0057] This application provides an electronic device, such as... Figure 4 As shown, Figure 4 The illustrated electronic device includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device does not constitute a limitation on the embodiments of this application.
[0058] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0059] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0060] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.
[0061] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.
[0062] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0063] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.
[0064] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.
[0065] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. An intelligent power monitoring method based on fault detection, characterized in that, include: When a power equipment fault is detected, the first operating data of the power equipment is acquired, and the fault level of the power equipment is determined based on the first operating data; Based on the fault level and the preset component knowledge graph, several reference components are identified. The reference components are the components that are in an abnormal working state when the power equipment fails. Obtain the second operating data corresponding to each of the aforementioned reference parts; Based on the second operating data corresponding to each of the reference parts and the preset fault probability network, the fault type of the power equipment is determined. The preset fault probability network includes: several fault types and their corresponding fault probabilities. Based on the fault level and a preset part knowledge graph, several reference parts are identified, including: Based on multiple initial preset part knowledge graphs and the fault level, a target preset part knowledge graph corresponding to the fault level is determined. The fault duration of the power equipment is obtained, and the number of parts is determined based on the fault duration; Obtain the first position information corresponding to each part in the target preset part knowledge graph; Based on the number of parts, the first position information corresponding to each part, and the preset key position, a number of reference parts are determined from all the parts; Before obtaining the second operating data corresponding to each of the reference parts, the method further includes: Acquire the current infrared image and standard infrared image of the power equipment; The current infrared image is matched with the standard infrared image to identify several abnormal image regions in the current infrared image; Obtain the second location information corresponding to all the abnormal image regions; Based on the second position information and the first position information corresponding to each of the parts, target position information is determined, wherein the target position information is the same as the first position information and the second position information. The reference part corresponding to the target location information is determined as the target reference part; Accordingly, obtaining the second operating data corresponding to each of the reference parts includes: Obtain the second operating data corresponding to each of the target reference parts.
2. The intelligent power monitoring method based on fault detection according to claim 1, characterized in that, The determination of the preset key positions includes: Obtain the environmental information and functional attributes of the power equipment; A reference power device is determined based on the environmental information, and a first critical location is determined based on the reference power device, wherein the environmental information of the reference power device is the same as the environmental information. Based on the preset correspondence between functional attributes and key positions, and the functional attributes, the second key position of the functional attributes is determined; The maintenance time of the key location is obtained, and the preset key location range is determined based on the maintenance time, the first key location, and the second key location. The key location includes the first key location and the second key location.
3. The intelligent power monitoring method based on fault detection according to claim 1, characterized in that, The determination of the fault type of the power equipment based on the second operating data corresponding to each of the reference components and a preset fault probability network includes: The second running data is input into the preset fault probability network to determine the initial fault occurrence probability corresponding to each of the initial fault types; Obtain historical fault information and determine correction coefficients based on the historical fault information; The correction coefficient is used to correct the initial fault occurrence probability corresponding to each of the initial fault types, so as to obtain the target fault occurrence probability corresponding to each of the initial fault types. From all the target fault occurrence probabilities, an initial fault type corresponding to the maximum target fault occurrence probability is selected, and the initial fault type corresponding to the maximum target fault occurrence probability is used to determine the fault type of the power equipment.
4. The intelligent power monitoring method based on fault detection according to claim 1, characterized in that, After determining the fault type of the power equipment based on the second operating data corresponding to each of the reference parts and the preset fault probability network, the method further includes: Determine the target correspondence of the environmental information of the power equipment, and based on the target correspondence and the fault type, determine the fault cause corresponding to the fault type. The target correspondence is the correspondence between the fault type and the fault cause under the environmental information. The equipment identification, third-party location information, and maintenance information of the maintenance personnel of the power equipment are obtained, wherein the maintenance information includes: maintenance plan and maintenance location; Based on the third location information, the maintenance plan, and the maintenance location, a target maintenance personnel is determined, wherein the third location information of the power equipment is within the range of the target maintenance personnel's maintenance location; A maintenance signal is generated based on the device identifier and all the causes of the fault, and the maintenance signal is sent to the device on the target maintenance personnel side for maintenance.
5. An intelligent power monitoring device based on fault detection, characterized in that, The method for intelligent power monitoring based on fault detection as described in any one of claims 1-4 includes: The fault level determination module is used to acquire the first operating data of the power equipment when a fault is detected, and to determine the fault level of the power equipment based on the first operating data. The reference part determination module is used to determine a number of reference parts based on the fault level and a preset part knowledge graph. The reference parts are the parts that are in an abnormal working state when the power equipment fails. The acquisition module is used to acquire the second operating data corresponding to each of the reference parts; The fault type determination module is used to determine the fault type of the power equipment based on the second operating data corresponding to each of the reference parts and a preset fault probability network. The preset fault probability network includes several fault types and their corresponding fault probabilities.
6. An electronic device, characterized in that, include: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, said at least one application being configured to: perform the intelligent power monitoring method based on fault detection as described in any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed in a computer, causes the computer to perform the intelligent power monitoring method based on fault detection as described in any one of claims 1 to 4.
Citation Information
Patent Citations
Fault detection method, device and equipment and readable storage medium
CN114721886A
Substation equipment monitoring method and device, electronic equipment and medium
CN115693962A
Power grid fault positioning method and device, medium and equipment
CN116338372A
