Transformer intelligent monitoring analysis method, system, equipment and medium

Abstract

The invention relates to a transformer intelligent monitoring analysis method, system and device and a medium, and is applied to the technical field of transformer monitoring, and the method comprises the steps: obtaining historical fault information, monitoring data of a to-be-monitored transformer, and an operation state of the to-be-monitored transformer, the historical fault information comprises a historical fault transformer, historical abnormal data, a historical abnormal type, a historical operation state and a historical fault type; determining a threshold range based on the historical fault information and a threshold optimization model; determining abnormal information based on the monitoring data and the threshold range, wherein the abnormal information comprises abnormal monitoring data, an abnormal type and a predicted abnormal type; searching a fault type from a preset fault database according to the exception type and the predicted exception type to obtain fault information; and determining a fault processing strategy based on the fault information. The method and the device have the effect of improving the accuracy of transformer monitoring.

Description

Technical Field

[0001] The present application relates to the technical field of transformer monitoring, and in particular to a transformer intelligent monitoring and analysis method, system, equipment and medium. Background Art

[0002] With the rapid development of the power industry, the safety and reliability of transformers, as core equipment supporting the stable operation of the power grid, have received widespread attention. By real-time monitoring of the transformer's operating data, it is possible to determine whether the transformer has failed, thereby improving the transformer's safety and reliability.

[0003] Currently, a variety of transformer monitoring systems have been put into use. These systems can collect transformer operating data in real time. However, these transformer monitoring systems mainly judge whether the transformer is faulty based on fixed thresholds, resulting in low accuracy of fault judgment, that is, low accuracy of transformer monitoring. Summary of the invention

[0004] In order to improve the accuracy of transformer monitoring, the present application provides a transformer intelligent monitoring and analysis method, system, equipment and medium.

[0005] In a first aspect, the present application provides a transformer intelligent monitoring and analysis method, which adopts the following technical solution: A transformer intelligent monitoring and analysis method, comprising: Acquire historical fault information, monitoring data of the transformer to be monitored, and operating status of the transformer to be monitored, wherein the historical fault information includes historical faulty transformers, historical abnormal data, historical abnormal types, historical operating status, and historical fault types; Determine a threshold range based on the historical fault information and a threshold optimization model; Determine abnormal information based on the monitoring data and the threshold range, wherein the abnormal information includes abnormal monitoring data, abnormal type, and predicted abnormal type; According to the abnormality type and the predicted abnormality type, the fault type is searched from a preset fault database to obtain fault information; A fault handling strategy is determined based on the fault information.

[0006] By adopting the above technical solution, when monitoring the transformer, a dynamic threshold range is determined based on historical fault information and a threshold optimization model instead of a fixed threshold, thereby improving the accuracy of the threshold range, and comparing the monitoring data with the dynamic threshold range to obtain abnormal information, thereby improving the accuracy of the abnormal information, and searching for the corresponding fault type based on the abnormal type in the abnormal information and the predicted abnormal type to obtain the fault information, thereby improving the accuracy of fault judgment, that is, improving the accuracy of transformer monitoring.

[0007] Optionally, before determining the threshold range based on the historical fault information and the threshold optimization model, the method further includes: Dividing the historical fault information according to the historical fault transformer and the historical operating state to obtain a plurality of first fault combinations, wherein the historical fault information in each of the first fault combinations corresponds to the same historical fault transformer and the historical operating state; Dividing the first fault combination according to the historical fault type to obtain a plurality of second fault combinations, wherein the historical fault information in each of the second fault combinations corresponds to the same historical fault type; The threshold optimization model is trained based on a plurality of the second fault combinations to obtain the threshold range.

[0008] By adopting the above technical scheme, the historical fault information is divided twice according to the historical fault transformer, the historical operating status and the historical fault type, and multiple second fault combinations are obtained. The threshold optimization model is trained according to the multiple second fault combinations, which improves the accuracy of model training. The threshold range is obtained according to the threshold optimization model, which improves the accuracy of the threshold range.

[0009] Optionally, the determining the abnormal information based on the monitoring data and the threshold range includes: Determine the threshold range corresponding to the operating state of the transformer to be monitored as a target threshold range, wherein the target threshold range includes a plurality of target sub-threshold ranges, each of which corresponds to an abnormal type or a normal type; Comparing the monitoring data with the target threshold range to obtain abnormal monitoring data and abnormal type; Analyze the historical fault information to obtain abnormal type association; Determining a predicted abnormality type based on the abnormality type and the abnormality type association; Abnormality information is determined based on the abnormality monitoring data, the abnormality type, and the predicted abnormality type.

[0010] By adopting the above technical solution, when determining abnormal information, not only is the current abnormal type obtained by comparing the monitoring data with the target threshold range, but the predicted abnormal type is also determined based on the abnormal type association, and the abnormal monitoring data, abnormal type and predicted abnormal type are jointly determined as abnormal information, thereby improving the accuracy of the abnormal information and thus improving the accuracy of transformer monitoring.

[0011] Optionally, the analyzing the historical fault information to obtain an abnormality type association includes: Determine the abnormality types corresponding to every two of the historical abnormality data in each of the historical fault information as an abnormality type combination; Counting a first quantity of each combination of the abnormal types; Counting a second amount of the historical fault information; determining a correlation ratio based on the first number and the second number; The abnormal type association is determined based on the association ratio and a preset ratio.

[0012] By adopting the above technical solution, it is determined whether there is a correlation between two abnormal types according to the proportion of the abnormal type combination composed of each two abnormal types in the historical fault information, thereby obtaining the abnormal type association, making the abnormal type association more reliable.

[0013] Optionally, after searching the fault type from a preset fault database according to the abnormality type and the predicted abnormality type to obtain fault information, the method further includes: Obtaining the operating time and historical maintenance cycle of the transformer to be monitored; Determine the first life stage of the transformer to be monitored according to the corresponding relationship between the operation time and the operation life stage; Obtaining a second life stage corresponding to the historical maintenance cycle; determining a first weight based on the first life stage and the second life stage; Counting a third amount of fault information that occurs when the transformer to be monitored is maintained according to the historical maintenance cycle; determining a second weight based on the third quantity; A new maintenance period is determined based on the first weight, the second weight, and the historical maintenance period.

[0014] By adopting the above technical scheme, the first weight is determined by the first life stage of the monitored transformer and the second life stage corresponding to the historical maintenance cycle, the second weight is determined by the third number of fault information that occurs when the monitored transformer is maintained according to the historical maintenance cycle, and the historical maintenance cycle is modified according to the first weight and the second weight to obtain a new maintenance cycle, thereby improving the reliability of the maintenance cycle.

[0015] Optionally, determining a fault handling strategy based on the fault information includes: Determine whether circuit breaking is required based on the fault type and preset rules; If a short circuit is required, a circuit breaking instruction is generated; Acquire maintenance personnel information based on the fault type; determining a fault level based on the fault information; Determine an early warning strategy based on the fault information, the fault level and the maintenance personnel information; The fault handling strategy is determined based on the circuit breaking instruction and the early warning strategy.

[0016] Optionally, determining the fault level based on the fault information includes: Counting the number of electrical appliances connected to the transformer to be monitored; Obtaining an estimated maintenance duration based on the fault type; Determine an associated fault type based on the fault type and a preset fault association; A fault level is determined based on the number of electrical appliances, the estimated maintenance duration, and the associated fault type.

[0017] By adopting the above technical solution, when determining the fault level, the number of electrical appliances connected to the transformer to be monitored, the expected maintenance time and the associated fault type are fully considered, thereby improving the reliability of the fault level.

[0018] In a second aspect, the present application provides a transformer intelligent monitoring and analysis system, which adopts the following technical solution: A transformer intelligent monitoring and analysis system, comprising: A data acquisition module, used to acquire historical fault information, monitoring data of the transformer to be monitored, and operating status of the transformer to be monitored, wherein the historical fault information includes historical fault transformers, historical abnormal data, historical abnormal types, historical operating status, and historical fault types; A threshold determination module, used to determine a threshold range based on the historical fault information and a threshold optimization model; an abnormality determination module, configured to determine abnormality information based on the monitoring data and the threshold range, wherein the abnormality information includes abnormal monitoring data, abnormality type, and predicted abnormality type; A fault determination module, used to search for the fault type from a preset fault database according to the abnormality type and the predicted abnormality type, and obtain fault information; A strategy determination module is used to determine a fault handling strategy based on the fault information.

[0019] By adopting the above technical solution, when monitoring the transformer, a dynamic threshold range is determined based on historical fault information and a threshold optimization model instead of a fixed threshold, thereby improving the accuracy of the threshold range, and comparing the monitoring data with the dynamic threshold range to obtain abnormal information, thereby improving the accuracy of the abnormal information, and searching for the corresponding fault type based on the abnormal type in the abnormal information and the predicted abnormal type to obtain the fault information, thereby improving the accuracy of fault judgment, that is, improving the accuracy of transformer monitoring.

[0020] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device comprises a processor, wherein the processor is coupled to a memory; The memory stores a computer program that can be loaded by a processor and execute the transformer intelligent monitoring and analysis method described in any one of the first aspects.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the transformer intelligent monitoring and analysis method described in any one of the first aspects.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. When monitoring the transformer, a dynamic threshold range is determined based on historical fault information and a threshold optimization model instead of a fixed threshold, thereby improving the accuracy of the threshold range. The monitoring data is compared with the dynamic threshold range to obtain abnormal information, thereby improving the accuracy of the abnormal information. The corresponding fault type is found based on the abnormal type in the abnormal information and the predicted abnormal type to obtain the fault information, thereby improving the accuracy of fault judgment, that is, improving the accuracy of transformer monitoring; 2. When determining abnormal information, not only is the current abnormal type obtained by comparing the monitoring data with the target threshold range, but the predicted abnormal type is also determined based on the abnormal type association, and the abnormal monitoring data, abnormal type and predicted abnormal type are jointly determined as abnormal information, which improves the accuracy of the abnormal information and thus improves the accuracy of transformer monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a transformer intelligent monitoring and analysis method provided in an embodiment of the present application.

[0024] Figure 2 It is a structural block diagram of a transformer intelligent monitoring and analysis system provided in an embodiment of the present application.

[0025] Figure 3 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application is further described in detail below in conjunction with the accompanying drawings.

[0027] The embodiment of the present application provides a transformer intelligent monitoring and analysis method, which can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0030] like Figure 1 As shown, a transformer intelligent monitoring and analysis method, the main process of the method is described as follows (steps S101 to S105): Step S101, acquiring historical fault information, monitoring data of the transformer to be monitored, and operating status of the transformer to be monitored.

[0031] Among them, historical fault information includes historical faulty transformers, historical abnormal data, historical abnormal types, historical operating status and historical fault types. Historical abnormal data is historical monitoring data with abnormalities. Historical abnormal types are abnormality types corresponding to historical abnormal data, such as: slight current abnormality, moderate current abnormality, etc. Historical fault types are fault types existing in transformers, such as: winding fault, circuit fault, etc. Monitoring data include voltage, waveform, frequency, active power, reactive power, power factor, temperature and current, etc. The operating status is the working status of the transformer, and the operating status varies according to parameters such as input voltage and output voltage.

[0032] Historical fault information is obtained from the database. A small high-voltage current transformer with a voltage level of 10KV is installed on the high-voltage insulator of the transformer, and various sensors are installed on the transformer, such as temperature sensors, vibration sensors, etc. The current is obtained from the small high-voltage current transformer with a voltage level of 10KV, the voltage on the low-voltage side is obtained through the copper busbar, and other monitoring data are obtained from the sensor.

[0033] Step S102: determining a threshold range based on historical fault information and a threshold optimization model.

[0034] The historical fault information is input into the threshold optimization model to train the threshold optimization model, so that the threshold range of each transformer under different operating conditions can be obtained according to the threshold optimization model. The threshold optimization model can be constructed by an adaptive learning algorithm in machine learning, such as reinforcement learning or online learning. There is no specific limitation here. The threshold range is the data range for judging whether there is an anomaly in the monitoring data and determining the type of anomaly.

[0035] Specifically, before determining the threshold range based on historical fault information and the threshold optimization model, the method also includes: dividing the historical fault information according to historical fault transformers and historical operating conditions to obtain multiple first fault combinations, and the historical fault information in each first fault combination corresponds to the same historical fault transformer and historical operating condition; dividing the first fault combination according to historical fault types to obtain multiple second fault combinations, and the historical fault information in each second fault combination corresponds to the same historical fault type; training the threshold optimization model based on the multiple second fault combinations to obtain the threshold range.

[0036] In this embodiment, the historical fault information is divided once according to the historical fault transformers and the historical operating status to obtain multiple first fault combinations, and then each first fault combination is divided once according to the historical fault type to obtain multiple second fault combinations, that is, each first fault combination corresponds to multiple second fault combinations, and the historical fault information in each second fault combination corresponds to the same historical fault transformer, the same historical operating status and the same historical fault type. The threshold optimization model is trained multiple times according to the multiple second fault combinations, so that the threshold range of each transformer under different operating conditions can be obtained according to the threshold optimization model.

[0037] Step S103: determine abnormal information based on the monitoring data and the threshold range.

[0038] Among them, the abnormal information includes abnormal monitoring data, abnormal type and predicted abnormal type.

[0039] Specifically, abnormal information is determined based on monitoring data and a threshold range, including: determining a threshold range corresponding to the operating state of the transformer to be monitored as a target threshold range, the target threshold range including a plurality of target sub-threshold ranges, each target sub-threshold range corresponding to an abnormal type or a normal type; comparing the monitoring data with the target threshold range to obtain abnormal monitoring data and abnormal types; analyzing historical fault information to obtain abnormal type associations; determining predicted abnormal types based on abnormal types and abnormal type associations; and determining abnormal information based on abnormal monitoring data, abnormal types and predicted abnormal types.

[0040] In this embodiment, the threshold range corresponding to the transformer to be monitored in the current (i.e., acquired) operating state is searched from the threshold range, and the found threshold range is determined as the target threshold range. The target threshold range of each monitoring data includes multiple target sub-threshold ranges, and each target sub-threshold range corresponds to an abnormal type or a normal type. For example, for temperature, the target threshold range includes three target sub-threshold ranges AB, BC, and CD. When the temperature is within the AB range, the temperature is a normal type, when the temperature is within the BC range, the temperature is a slightly abnormal type, and when the temperature is within the CD range, the temperature is a serious abnormal type; the monitoring data is compared with the target threshold range, and the monitoring data that is not within the target sub-threshold range corresponding to the normal type is determined as abnormal monitoring data, and the abnormal type of the target sub-threshold range where the abnormal monitoring data is located is determined as the abnormal type of the abnormal monitoring data. It is worth noting that, for ease of comparison, the high voltage current is converted into the low voltage current (400V or other voltage level current), and the specific conversion formula is (U1*I1) / U2=I2, wherein U1 is the high voltage, I1 is the high voltage current, U2 is the low voltage, and I2 is the low voltage current.

[0041] The acquired historical fault information is analyzed to obtain the abnormal type association, that is, whether there is a correlation between every two abnormal types, and the abnormal type that has a correlation with the current abnormal type in the abnormal type association is determined as the predicted abnormal type, and the abnormal monitoring data, abnormal type and predicted abnormal type are jointly determined as the determined abnormal information, and the abnormal information also includes the transformer to be monitored.

[0042] Furthermore, the historical fault information is analyzed to obtain abnormal type associations, including: determining the abnormal types corresponding to every two historical abnormal data in each historical fault information as an abnormal type combination; counting a first number of each abnormal type combination; counting a second number of historical fault information; determining an association ratio based on the first number and the second number; and determining the abnormal type association based on the association ratio and a preset ratio.

[0043] In this embodiment, each historical fault information often includes multiple abnormal types, and the abnormal types corresponding to every two historical abnormal data in each historical fault information are determined as an abnormal type combination. For example, if the historical fault information includes three historical abnormal data a, b, and c, then three abnormal type combinations correspond, including an abnormal type combination consisting of abnormal types corresponding to a and b, an abnormal type combination consisting of abnormal types corresponding to b and c, and an abnormal type combination consisting of abnormal types corresponding to a and c. The first number of each abnormal type combination in all historical fault information is counted, and the second number of historical fault information is counted. The association ratio=first number / second number. Each abnormal type combination corresponds to an association ratio. If the association ratio corresponding to the abnormal type combination is greater than the preset ratio, the two abnormal types in the abnormal type combination have an association relationship. All abnormal types with an associated relationship are stored together in a database corresponding to the abnormal type association. The abnormal type association includes all abnormal types with an associated relationship. The preset ratio is a preset value and is not specifically limited here.

[0044] When determining abnormal information, not only can the real-time monitoring data be compared with the threshold range to obtain abnormal information, but the abnormal information can also be determined by analyzing the changes in data over a period of time.

[0045] Specifically, the abnormal information is determined by analyzing the changes in data over a period of time, including: obtaining the conversion rules between current and load from the database, calculating the load of the transformer by obtaining the current from a small high-voltage current transformer with a voltage level of 10KV and the conversion rules, and analyzing the load changes of the transformer once every preset period. When the load change exceeds the preset change range, abnormal information is generated, and the abnormal type is load abnormality. The method of determining the predicted abnormal type based on the abnormal type is the same as above, which will not be repeated here.

[0046] Step S104: search the fault type from a preset fault database according to the abnormality type and the predicted abnormality type to obtain fault information.

[0047] The preset fault database is a pre-built database, which stores the correspondence between abnormal types and fault types. When all abnormal types corresponding to a fault type appear, a fault type will appear. The abnormal type and the fault type corresponding to the predicted abnormal type will be found in the preset fault database. If a corresponding fault type exists, the fault information includes the fault type and the abnormal information. If no corresponding fault type exists, the fault information includes the abnormal information.

[0048] Specifically, after searching the fault type from the preset fault database according to the abnormal type and the predicted abnormal type to obtain the fault information, the method also includes: obtaining the operating time and historical maintenance cycle of the transformer to be monitored; determining the first life stage in which the transformer to be monitored is currently located according to the correspondence between the operating time and the operating life stage; obtaining the second life stage corresponding to the historical maintenance cycle; determining a first weight based on the first life stage and the second life stage; counting the third number of fault information that occurs when the transformer to be monitored is maintained according to the historical maintenance cycle; determining a second weight based on the third number; and determining a new maintenance cycle based on the first weight, the second weight, and the historical maintenance cycle.

[0049] In this embodiment, in order to improve the safety and reliability of the transformer, the transformer needs to be maintained regularly. The operating time (i.e., the operating time of the transformer to be monitored) and the historical maintenance cycle (i.e., the cycle in which the transformer is currently maintained) are obtained from the staff. The database stores the corresponding relationship between the operating time and the operating life stage. The first life stage of the transformer to be monitored is searched from the database according to the operating time. The second life stage corresponding to the historical maintenance cycle is obtained from the database. The second life stage is the life stage of the transformer when the historical maintenance cycle is determined. The database stores the corresponding relationship between the first life stage, the second life stage and the first weight. For example, if the first life stage is the same as the second life stage, the first weight is 1. If the first life stage is different from the second life stage, the first weight is less than 1 and greater than 0. The first weight is searched from the database according to the first life stage and the second life stage. The third number of fault information that occurs when the transformer to be monitored is maintained according to the historical maintenance cycle is counted. The database stores the corresponding relationship between the third number and the second weight. The second weight is searched from the database according to the third number. The new maintenance cycle = the first weight × the second weight × the historical maintenance cycle, and the transformer is maintained according to the new maintenance cycle.

[0050] Step S105: determine a fault handling strategy based on the fault information.

[0051] Specifically, a fault handling strategy is determined based on the fault information, including: judging whether a circuit break is required based on the fault type and preset rules; generating a circuit breaking instruction if a short circuit is required; obtaining maintenance personnel information based on the fault type; determining the fault level based on the fault information; determining an early warning strategy based on the fault information, the fault level and the maintenance personnel information; and determining a fault handling strategy based on the circuit breaking instruction and the early warning strategy.

[0052] In this embodiment, a preset rule is obtained from a database, and the preset rule is a rule for determining whether the upper and / or lower devices of the transformer to be monitored need to be disconnected by a circuit breaker according to the fault type and the fault type. If the fault type exists in the fault information of the transformer to be monitored, whether the upper and / or lower devices of the transformer to be monitored need to be disconnected by a circuit breaker is found from the preset rule according to the fault type. If disconnection is required, a disconnection instruction is generated and sent to the upper and / or lower devices of the transformer to be monitored, so that after the upper and / or lower devices of the transformer to be monitored receive the disconnection instruction, they will disconnect the circuit through the circuit breaker. Different fault types correspond to different maintenance personnel, and maintenance personnel are selected from the database according to the fault type. The maintenance personnel information is obtained from the database, the fault information is analyzed, and the fault level of the transformer to be monitored is obtained. Different fault levels correspond to different early warning methods. The early warning methods include the alarm corresponding to the transformer to be monitored sending an alarm signal (different fault levels correspond to different alarm signals) and sending fault information to the maintenance personnel. The early warning method corresponding to the current fault level is obtained from the database. The early warning strategy is to send an alarm signal according to the early warning method and send fault information to the maintenance personnel. The fault handling strategy includes: if there is a circuit breaker instruction, the upper and / or lower level equipment of the transformer to be monitored will open the circuit through the circuit breaker and complete the early warning strategy after receiving the circuit breaker instruction.

[0053] Furthermore, the fault level is determined based on the fault information, including: counting the number of electrical appliances connected to the transformer to be monitored; obtaining an estimated maintenance time based on the fault type; determining an associated fault type based on the fault type and preset fault associations; determining the fault level based on the number of electrical appliances, the estimated maintenance time and the associated fault type.

[0054] In this embodiment, information on electrical appliances connected to the transformer to be monitored is obtained from the staff, the number of electrical appliances connected to the transformer to be monitored is counted, and the estimated maintenance time corresponding to the fault type is obtained from the maintenance personnel. Preset fault associations are stored in the database, and the preset fault associations are associations between all fault types. For example, when fault type 1 occurs, fault type 2 will often continue to occur, then fault type 1 has an association with fault type 2, and fault type 2 is an associated fault type of fault type 1. The associated fault type corresponding to the fault type is searched from the preset fault associations. The database stores the correspondence between the number of electrical appliances, the estimated maintenance time, and the associated fault type and the fault level. The fault level of the transformer to be monitored is searched from the database according to the number of electrical appliances, the estimated maintenance time, and the associated fault type.

[0055] If there is no fault type in the transformer to be monitored, the fault information is abnormal information. The fault handling strategy includes sending the abnormal information to the management personnel and storing the abnormal information in the database.

[0056] Figure 2 A structural block diagram of a transformer intelligent monitoring and analysis system 200 provided in an embodiment of the present application.

[0057] like Figure 2 As shown, the transformer intelligent monitoring and analysis system 200 mainly includes: The data acquisition module 201 is used to acquire historical fault information, monitoring data of the transformer to be monitored, and the operating status of the transformer to be monitored, wherein the historical fault information includes historical fault transformers, historical abnormal data, historical abnormal types, historical operating status, and historical fault types; A threshold determination module 202, used to determine a threshold range based on historical fault information and a threshold optimization model; An abnormality determination module 203, used to determine abnormal information based on monitoring data and a threshold range, the abnormal information including abnormal monitoring data, abnormal type and predicted abnormal type; A fault determination module 204 is used to search for the fault type from a preset fault database according to the abnormality type and the predicted abnormality type to obtain fault information; The strategy determination module 205 is used to determine a fault handling strategy based on the fault information.

[0058] As an optional implementation of this embodiment, the threshold determination module 202 is also specifically used to, before determining the threshold range based on historical fault information and the threshold optimization model, also include: dividing the historical fault information according to historical fault transformers and historical operating conditions to obtain multiple first fault combinations, the historical fault information in each first fault combination corresponds to the same historical fault transformer and historical operating condition; dividing the first fault combination according to historical fault types to obtain multiple second fault combinations, the historical fault information in each second fault combination corresponds to the same historical fault type; training the threshold optimization model based on multiple second fault combinations to obtain a threshold range.

[0059] As an optional implementation of this embodiment, the abnormality determination module 203 is also specifically used to determine abnormal information based on monitoring data and a threshold range, including: determining the threshold range corresponding to the operating state of the transformer to be monitored as a target threshold range, the target threshold range includes multiple target sub-threshold ranges, each target sub-threshold range corresponds to an abnormal type or a normal type; comparing the monitoring data with the target threshold range to obtain abnormal monitoring data and abnormal types; analyzing historical fault information to obtain abnormal type associations; determining predicted abnormal types based on abnormal types and abnormal type associations; determining abnormal information based on abnormal monitoring data, abnormal types and predicted abnormal types.

[0060] As an optional implementation of this embodiment, the abnormality determination module 203 is also specifically used to analyze historical fault information to obtain abnormality type associations, including: determining the abnormality types corresponding to every two historical abnormal data in each historical fault information as an abnormality type combination; counting the first number of each abnormality type combination; counting the second number of historical fault information; determining the association ratio based on the first number and the second number; determining the abnormality type association based on the association ratio and the preset ratio.

[0061] As an optional implementation manner of this embodiment, the fault determination module 204 is also specifically used to search for the fault type from a preset fault database according to the abnormality type and the predicted abnormality type, and after obtaining the fault information, it also includes: obtaining the operating time and historical maintenance cycle of the transformer to be monitored; determining the first life stage in which the transformer to be monitored is currently located according to the correspondence between the operating time and the operating life stage; obtaining the second life stage corresponding to the historical maintenance cycle; determining a first weight based on the first life stage and the second life stage; counting the third number of fault information that occurs when the transformer to be monitored is maintained according to the historical maintenance cycle; determining a second weight based on the third number; and determining a new maintenance cycle based on the first weight, the second weight, and the historical maintenance cycle.

[0062] As an optional implementation mode of this embodiment, the strategy determination module 205 is also specifically used to determine the fault handling strategy based on the fault information, including: judging whether it is necessary to open the circuit based on the fault type and preset rules; if a short circuit is required, generating a circuit breaking instruction; obtaining maintenance personnel information based on the fault type; determining the fault level based on the fault information; determining the early warning strategy based on the fault information, the fault level and the maintenance personnel information; determining the fault handling strategy based on the circuit breaking instruction and the early warning strategy.

[0063] As an optional implementation of this embodiment, the strategy determination module 205 is also specifically used to determine the fault level based on fault information, including: counting the number of electrical appliances connected to the transformer to be monitored; obtaining the expected maintenance time based on the fault type; determining the associated fault type based on the fault type and preset fault associations; determining the fault level based on the number of electrical appliances, the expected maintenance time and the associated fault type.

[0064] In one example, the module in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0065] For another example, when the modules in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0066] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0067] Figure 3 A structural block diagram of an electronic device 300 provided in an embodiment of the present application.

[0068] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302 , and may further include an information input / information output (I / O) interface 303 , one or more of a communication component 304 , and a communication bus 305 .

[0069] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps of the above-mentioned transformer intelligent monitoring and analysis method; the memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and data related to the application. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), programmable read-only memory (Programmable Read-Only Memory, PROM), read-only memory (Read-Only Memory, ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0070] The I / O interface 303 provides an interface between the processor 301 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include: Wi-Fi components, Bluetooth components, NFC components.

[0071] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the transformer intelligent monitoring and analysis method given in the above embodiment.

[0072] The communication bus 305 may include a path to transmit information between the above components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0073] The electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and may also be servers, etc.

[0074] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned transformer intelligent monitoring and analysis method are implemented.

[0075] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0076] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0077] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A transformer intelligent monitoring and analysis method, characterized in that: include: Acquire historical fault information, monitoring data of the transformer to be monitored, and operating status of the transformer to be monitored, wherein the historical fault information includes historical faulty transformers, historical abnormal data, historical abnormal types, historical operating status, and historical fault types; Determine a threshold range based on the historical fault information and a threshold optimization model; Determine abnormal information based on the monitoring data and the threshold range, wherein the abnormal information includes abnormal monitoring data, abnormal type, and predicted abnormal type; According to the abnormality type and the predicted abnormality type, the fault type is searched from a preset fault database to obtain fault information; A fault handling strategy is determined based on the fault information.

2. The method according to claim 1, characterized in that: Before determining the threshold range based on the historical fault information and the threshold optimization model, the method further includes: Dividing the historical fault information according to the historical fault transformer and the historical operating state to obtain a plurality of first fault combinations, wherein the historical fault information in each of the first fault combinations corresponds to the same historical fault transformer and the historical operating state; Dividing the first fault combination according to the historical fault type to obtain a plurality of second fault combinations, wherein the historical fault information in each of the second fault combinations corresponds to the same historical fault type; The threshold optimization model is trained based on a plurality of the second fault combinations to obtain the threshold range.

3. The method according to claim 1, characterized in that The determining of abnormal information based on the monitoring data and the threshold range includes: Determine the threshold range corresponding to the operating state of the transformer to be monitored as a target threshold range, wherein the target threshold range includes a plurality of target sub-threshold ranges, each of which corresponds to an abnormal type or a normal type; Comparing the monitoring data with the target threshold range to obtain abnormal monitoring data and abnormal type; Analyze the historical fault information to obtain abnormal type association; Determining a predicted abnormality type based on the abnormality type and the abnormality type association; Abnormality information is determined based on the abnormality monitoring data, the abnormality type, and the predicted abnormality type.

4. The method according to claim 3, characterized in that The analyzing the historical fault information to obtain abnormal type association includes: Determine the abnormality types corresponding to every two of the historical abnormality data in each of the historical fault information as an abnormality type combination; Counting a first quantity of each combination of the abnormal types; Counting a second amount of the historical fault information; determining a correlation ratio based on the first number and the second number; The abnormal type association is determined based on the association ratio and a preset ratio.

5. The method according to claim 1, characterized in that After searching the fault type from the preset fault database according to the abnormality type and the predicted abnormality type to obtain fault information, the method further includes: Obtaining the operating time and historical maintenance cycle of the transformer to be monitored; Determine the first life stage of the transformer to be monitored according to the corresponding relationship between the operation time and the operation life stage; Obtaining a second life stage corresponding to the historical maintenance cycle; determining a first weight based on the first life stage and the second life stage; Counting a third amount of fault information that occurs when the transformer to be monitored is maintained according to the historical maintenance cycle; determining a second weight based on the third quantity; A new maintenance period is determined based on the first weight, the second weight, and the historical maintenance period.

6. The method according to claim 1, characterized in that The determining of a fault handling strategy based on the fault information includes: Determine whether circuit breaking is required based on the fault type and preset rules; If a short circuit is required, a circuit breaking instruction is generated; Acquiring maintenance personnel information based on the fault type; determining a fault level based on the fault information; Determine an early warning strategy based on the fault information, the fault level and the maintenance personnel information; The fault handling strategy is determined based on the circuit breaking instruction and the early warning strategy.

7. The method according to claim 6, characterized in that The determining the fault level based on the fault information includes: Counting the number of electrical appliances connected to the transformer to be monitored; Obtaining an estimated maintenance duration based on the fault type; Determine an associated fault type based on the fault type and a preset fault association; A fault level is determined based on the number of electrical appliances, the estimated maintenance duration, and the associated fault type.

8. A transformer intelligent monitoring and analysis system, characterized in that: include: A data acquisition module, used to acquire historical fault information, monitoring data of the transformer to be monitored, and operating status of the transformer to be monitored, wherein the historical fault information includes historical fault transformers, historical abnormal data, historical abnormal types, historical operating status, and historical fault types; A threshold determination module, used to determine a threshold range based on the historical fault information and a threshold optimization model; an abnormality determination module, configured to determine abnormality information based on the monitoring data and the threshold range, wherein the abnormality information includes abnormal monitoring data, abnormality type, and predicted abnormality type; A fault determination module, used to search for the fault type from a preset fault database according to the abnormality type and the predicted abnormality type, and obtain fault information; A strategy determination module is used to determine a fault handling strategy based on the fault information.

9. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 7.

Images