Transformer anomaly early warning methods, devices, equipment and storage media

Abstract

This application discloses a method, apparatus, device, and storage medium for transformer anomaly early warning. The method includes: acquiring m temperature datasets at m locations within the transformer within a preset time period, and an electrical dataset within the preset time period; identifying temperature mutation datasets from the m temperature datasets to obtain n temperature mutation datasets; identifying temperature mutation datasets from the n temperature mutation datasets that satisfy a first preset condition as abnormal temperature datasets to obtain i abnormal temperature datasets; sending a first early warning message for the i abnormal temperature datasets to a monitoring device; identifying k segments of electrical mutation data from the electrical dataset; identifying electrical mutation data from the k segments of electrical mutation data that satisfy a second preset condition as abnormal electrical data to obtain p segments of abnormal electrical data; and sending a second early warning message for the p segments of abnormal electrical data to the monitoring device. This application is beneficial for improving the accuracy of transformer anomaly early warning.

Description

Technical Field

[0001] This application relates to the field of transformer monitoring technology, and in particular to a method, device, equipment and storage medium for early warning of transformer anomalies. Background Technology

[0002] Transformers are a critical component of power systems. With the rapid development of modern power systems, the safe operation of transformers has received greater attention, making timely diagnosis of transformer faults particularly important. Modern intelligent transformers are equipped with intelligent diagnostic systems that can analyze monitoring data and operating status to achieve early warning and rapid diagnosis of transformer faults, thereby improving the reliability and security of the power grid.

[0003] Existing fault diagnosis technologies typically monitor transformer electrical data to determine if the data falls within a reference range, thereby identifying whether a fault has occurred or if an abnormal trend is present. However, abnormal changes in transformer electrical data are only one factor contributing to transformer failure. Therefore, relying solely on electrical data for early warning of transformer anomalies results in poor accuracy. Summary of the Invention

[0004] To address the aforementioned problems in the prior art, this application provides a method, apparatus, device, and storage medium for abnormal early warning of transformers. By analyzing m temperature datasets at m locations within a preset time period within the transformer, n temperature abrupt change datasets are identified. When a temperature abrupt change dataset meets a first preset condition, it is designated as an abnormal temperature dataset, and a first early warning message for the abnormal temperature dataset is sent to the monitoring device. Furthermore, based on the electrical dataset of the transformer within the preset time period, k segments of electrical abrupt change data are identified. Electrical abrupt change data that meets a second preset condition is designated as abnormal electrical data, and a second early warning message for the abnormal electrical data is sent to the monitoring device. This improves the accuracy of abnormal early warning for transformers.

[0005] In a first aspect, embodiments of this application provide a method for early warning of transformer anomalies, comprising:

[0006] Obtain m temperature datasets at m locations within a preset time period, as well as the electrical dataset of the transformer within the preset time period; each location corresponds to one temperature dataset; m is an integer greater than 1;

[0007] The temperature dataset containing temperature abrupt changes among the m temperature datasets is identified as the temperature abrupt change dataset, resulting in n temperature abrupt change datasets; the temperature abrupt change data is temperature data whose temperature change value for a first preset time period is greater than or equal to a first threshold; n is a positive integer less than or equal to m;

[0008] Among the n temperature mutation datasets, the temperature mutation dataset that meets the first preset condition is identified as an abnormal temperature dataset, resulting in i abnormal temperature datasets; i is a positive integer less than or equal to n.

[0009] Send a first warning message to the monitoring device for the i abnormal temperature datasets; the first warning message includes the i locations corresponding to the i abnormal temperature datasets among the m locations; each abnormal temperature dataset corresponds to one location;

[0010] Determine k segments of electrical abrupt change data for the transformer from the electrical dataset;

[0011] The electrical mutation data that meets the second preset condition among the k segments of electrical mutation data is identified as abnormal electrical data, and p segments of abnormal electrical data are obtained;

[0012] Send a second early warning message to the monitoring device regarding the abnormal electrical data in segment p.

[0013] Secondly, embodiments of this application provide an abnormality early warning device for a transformer, the device comprising a data acquisition module, a data processing module, and an early warning module;

[0014] The data acquisition module is used to acquire m temperature datasets at m locations within the transformer within a preset time period, as well as electrical datasets of the transformer within the preset time period; each location corresponds to one temperature dataset; m is an integer greater than 1;

[0015] The data processing module is used to determine the temperature dataset containing temperature abrupt changes among the m temperature datasets as temperature abrupt change datasets, and to obtain n temperature abrupt change datasets; the temperature abrupt change data is temperature data whose temperature change value for a first preset time period is greater than or equal to a first threshold; n is a positive integer less than or equal to m;

[0016] Among the n temperature mutation datasets, the temperature mutation dataset that meets the first preset condition is identified as an abnormal temperature dataset, resulting in i abnormal temperature datasets; i is a positive integer less than or equal to n.

[0017] The early warning module is used to send a first early warning message to the monitoring device for the i abnormal temperature datasets; the first early warning message includes i locations corresponding to the i abnormal temperature datasets among the m locations; each abnormal temperature dataset corresponds to one location;

[0018] The data processing module is used to determine k segments of electrical mutation data of the transformer in the electrical dataset;

[0019] The electrical mutation data that meets the second preset condition among the k segments of electrical mutation data is identified as abnormal electrical data, and p segments of abnormal electrical data are obtained;

[0020] The early warning module is used to send a second early warning message to the monitoring device regarding the abnormal electrical data of segment p.

[0021] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory, so that the electronic device performs the method as described in the first aspect.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that is executed by a processor to implement the method described in the first aspect.

[0023] Fifthly, embodiments of this application provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program, the computer program product being operable to cause a computer to perform the method as described in the first aspect.

[0024] Implementing the embodiments of this application has the following beneficial effects:

[0025] In this embodiment, firstly, m temperature datasets at m locations within the transformer within a preset time period, and an electrical dataset of the transformer within the preset time period are obtained, where each location corresponds to one temperature dataset. Then, the temperature datasets containing temperature abrupt changes are identified as temperature abrupt change datasets, resulting in n temperature abrupt change datasets. Temperature abrupt change data refers to temperature data where the temperature change over a first preset time period is greater than or equal to a first threshold. Next, the temperature abrupt change datasets satisfying a first preset condition are identified as abnormal temperature datasets, resulting in i abnormal temperature datasets. Further, a first warning message for the i abnormal temperature datasets is sent to the monitoring device. The first warning message includes the i locations corresponding to the i abnormal temperature datasets among the m locations, with each abnormal temperature dataset corresponding to one location. Therefore, based on the m temperature datasets at m locations within the preset time period, abnormal temperature datasets can be determined, and a first warning message can be sent to the monitoring device to improve the safety and stability of the transformer operation. The first warning message also includes the location corresponding to each abnormal temperature dataset, which can improve the accuracy of transformer anomaly warnings. Furthermore, this application can identify k segments of electrical mutation data of the transformer from the electrical dataset, and then determine the electrical mutation data that meets the second preset condition among the k segments of electrical mutation data as abnormal electrical data, thus obtaining p segments of abnormal electrical data. Finally, a second early warning message for the p segments of abnormal electrical data is sent to the monitoring equipment. Therefore, based on the electrical dataset of the transformer within a preset time period, abnormal electrical data of the transformer can be determined, and a second early warning message can be sent to the monitoring equipment, thereby improving the safety and stability of the transformer during operation. Compared to determining whether an anomaly has occurred during transformer operation solely through electrical data, this application can combine temperature data and electrical data to more accurately determine whether the transformer is abnormal, improving the accuracy of transformer anomaly early warning. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A schematic diagram of an abnormality early warning system for a transformer provided in an embodiment of this application;

[0028] Figure 2 A flowchart illustrating an abnormality early warning method for a transformer provided in an embodiment of this application;

[0029] Figure 3A schematic diagram of an abnormality early warning device for a transformer provided in an embodiment of this application;

[0030] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0033] In this document, the term "embodiment" means that a particular feature, result, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0034] First, refer to Figure 1 , Figure 1 This is a schematic diagram of an abnormality early warning system for a transformer provided in an embodiment of this application. Figure 1 As shown, the transformer anomaly early warning system includes: transformer, database, processing equipment, and monitoring equipment.

[0035] A transformer is an electrical device that uses the principle of electromagnetic induction to change alternating current (AC) voltage. It mainly consists of an iron core and windings. The iron core provides the magnetic circuit for the transformer, concentrating and guiding magnetic lines of force. There can be two or more windings, including a primary winding and a secondary winding. The primary winding receives the input voltage, and the secondary winding outputs the transformed voltage. Setting up a transformer in a circuit can serve functions such as changing AC voltage, circuit isolation, and impedance matching. It should be noted that the transformer in this embodiment can be a digital intelligent transformer. A digital intelligent transformer is a new type of transformer that integrates digital and intelligent technologies on the basis of a traditional transformer, possessing characteristics such as high intelligence, digital control, and high energy efficiency. In power systems, digital intelligent transformers, as one of the key pieces of equipment, can realize intelligent monitoring, control, and management of the power system, improving the reliability and stability of the power grid. The transformer is equipped with various sensors that can monitor electrical data, temperature data, and other data during transformer operation.

[0036] The database is used to store and manage data, including electrical data, temperature data, and so on, during transformer operation. The database can be a server with data storage capabilities, including: a cloud server (Elastic Compute Service, ECS), an embedded server (Embedded Service Processor, ESP), a database server, etc. The database can also be a storage device with data storage capabilities, including: Random Access Memory (RAM), Read-Only Memory (ROM), Non-volatile Flash Memory, hard disk, optical disk, etc. This application embodiment does not limit this. The database can acquire the transformer's electrical data, temperature data, etc., at the current moment from the transformer's sensors, and correlate the collected electrical and temperature data with the acquisition time. Therefore, the database stores the transformer's electrical and temperature data at every moment.

[0037] The processing device can be, for example, a server for data processing and communication functions, including rack servers, application servers, cloud servers, virtual private servers (VPS), etc. The processing device can also be a processor chip for data processing and communication functions, including a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), etc. This application embodiment does not limit this. In this application embodiment, the processing device can communicate with a database to obtain electrical and temperature data during transformer operation, and determine whether the transformer has malfunctioned based on the electrical and temperature data.

[0038] The monitoring equipment can be electronic devices with data display capabilities, including mobile phones, computers, etc. The monitoring equipment can communicate with the processing equipment. When the processing equipment determines that the transformer is malfunctioning, it sends an early warning message to the monitoring equipment, which then displays the message. Users can use the early warning message displayed on the monitoring equipment to identify the transformer malfunction and perform maintenance, thereby improving the safety and stability of transformer operation.

[0039] It should be noted that in traditional transformer anomaly early warning methods, the transformer's electrical data is monitored to determine whether an abnormal state has occurred. However, anomalies that occur during transformer operation are determined by a variety of factors. Therefore, relying solely on monitoring the transformer's electrical data will result in poor accuracy in transformer anomaly early warning.

[0040] Therefore, in the transformer anomaly early warning method of this application, the processing device acquires m temperature datasets at m locations within the transformer within a preset time period, and an electrical dataset of the transformer within the preset time period; the processing device determines the temperature dataset containing temperature abrupt changes among the m temperature datasets as temperature abrupt change datasets, obtaining n temperature abrupt change datasets; the processing device determines the temperature abrupt change dataset satisfying a first preset condition among the n temperature abrupt change datasets as abnormal temperature datasets, obtaining i abnormal temperature datasets; the processing device sends a first early warning message for the i abnormal temperature datasets to the monitoring device; the processing device identifies k segments of electrical abrupt change data of the transformer in the electrical dataset; the processing device determines the electrical abrupt change data satisfying a second preset condition among the k segments of electrical abrupt change data as abnormal electrical data, obtaining p segments of abnormal electrical data; the processing device sends a second early warning message for the p segments of abnormal electrical data to the monitoring device.

[0041] As can be seen, the anomaly early warning system applied to the aforementioned transformer allows the processing equipment to determine abnormal temperature datasets based on m temperature datasets from m locations within the transformer over a preset time period. This allows the system to send a first early warning message for the abnormal temperature dataset to the monitoring equipment, improving the safety and stability of the transformer during operation. The first early warning message also includes the location corresponding to the abnormal temperature dataset, enhancing the accuracy of transformer anomaly early warnings. Furthermore, the processing equipment can determine abnormal electrical data based on the transformer's electrical dataset over a preset time period, sending a second early warning message for the abnormal electrical data to the monitoring equipment, further improving the safety and stability of the transformer during operation. By monitoring both the transformer's temperature and electrical data, the accuracy of transformer anomaly early warnings can be improved.

[0042] See Figure 2 , Figure 2 This is a flowchart illustrating a transformer anomaly early warning method provided in an embodiment of this application. The method is applied to the processing equipment in the aforementioned transformer anomaly early warning system. The method includes, but is not limited to, the following steps:

[0043] 201: Obtain m temperature datasets at m locations within a preset time period, and electrical datasets of the transformer within the preset time period.

[0044] In this embodiment, each location corresponds to a temperature dataset, where m is an integer greater than 1. The electrical dataset includes a current dataset and a voltage dataset. The preset time period includes the current moment. The processing device can obtain m temperature datasets for m locations within the transformer within the preset time period, as well as the electrical dataset of the transformer within the preset time period, from the database. Optionally, the database can be divided into a temperature database and an electrical database, or it can include a total database of the transformer's temperature data and electrical data.

[0045] It should be noted that the temperature sensors inside the transformer can collect temperature data at m locations within the transformer. Within a preset time period, the temperature sensors can collect multiple temperature data points according to the temperature acquisition cycle, thus forming m temperature datasets for the m locations within the transformer during the preset time period. Similarly, the current sensors inside the transformer can collect multiple current data points within a preset time period according to the current acquisition cycle, forming a current dataset. The voltage sensors can collect multiple voltage data points within a preset time period according to the voltage acquisition cycle, forming a voltage dataset. This results in an electrical dataset.

[0046] 202: Determine the temperature dataset containing temperature abrupt changes among the m temperature datasets as the temperature abrupt change dataset, and obtain n temperature abrupt change datasets.

[0047] In this embodiment, temperature mutation data refers to temperature data where the temperature change value over a first preset time period is greater than or equal to a first threshold, and n is a positive integer less than or equal to m. The processing device can analyze m temperature datasets separately to determine the temperature datasets containing temperature mutation data, thus obtaining n temperature mutation datasets.

[0048] It should be noted that when temperature abrupt changes are present in the temperature dataset, it indicates that the temperature changes in that dataset may be abnormal. Therefore, it is necessary to extract this temperature dataset to obtain a temperature abrupt change dataset. This dataset will then be analyzed to determine whether the transformer's temperature is abnormal during operation.

[0049] For example, identifying a temperature dataset containing temperature abrupt changes among m temperature datasets as a temperature abrupt change dataset, and thus obtaining n temperature abrupt change datasets, may include the following steps:

[0050] Obtain the target temperature dataset;

[0051] The preset time period is divided into multiple segments based on the first preset duration, resulting in multiple first time periods;

[0052] Determine the temperature data corresponding to multiple first time periods in the target temperature dataset to obtain multiple temperature data segments;

[0053] Determine the temperature change value corresponding to each segment of temperature data in multiple temperature data points to obtain multiple temperature change values;

[0054] If at least one of the multiple temperature change values ​​is greater than or equal to the first threshold, then the target temperature dataset is determined to be one of the n temperature mutation datasets.

[0055] In this embodiment, the target temperature dataset includes multiple temperature data points, each corresponding to a collection time. The target temperature dataset is any one of the m temperature datasets. The temperature change value is the difference between the temperature data corresponding to the start time and the temperature data corresponding to the end time of the first time period.

[0056] Specifically, the processing device acquires the target temperature dataset from m temperature datasets. It then divides a preset time period into multiple segments based on a first preset duration, resulting in multiple first time periods. The first preset duration can be pre-set based on the acquisition time corresponding to each temperature data point and the accuracy of determining the temperature change dataset; a shorter first preset duration results in a more accurate determination of the temperature change dataset.

[0057] Then, the processing device determines the temperature data corresponding to multiple first time periods in the target temperature dataset, obtaining multiple temperature data segments. By analyzing each temperature data segment, it can determine whether there are any temperature abrupt changes in the target temperature dataset. Specifically, the processing device can determine the difference between the temperature data at the start and end of the first time period for each temperature data segment, obtaining the temperature change value corresponding to each temperature data segment, thus obtaining multiple temperature change values ​​corresponding to multiple temperature data segments. It should be noted that the temperature change value is the difference between the temperature data at the start and end of the first time period, and only reflects the overall temperature change of each temperature data segment within the first time period. The processing first determines whether the overall temperature change of each temperature data segment within the first time period is within the normal range to determine whether the target temperature dataset is a temperature abrupt change dataset.

[0058] If at least one of the multiple temperature change values ​​is greater than or equal to a first threshold, it indicates that there is a temperature abrupt change in the target temperature dataset, and the target temperature dataset is determined to be one of n temperature abrupt change datasets. The first threshold can be preset according to the accuracy of the determination of the temperature abrupt change dataset.

[0059] If multiple temperature change values ​​are all less than the first threshold, it means that there is no temperature mutation data in the target temperature dataset, and the target temperature dataset is determined not to be a temperature mutation dataset.

[0060] In this way, the processing equipment can process m temperature datasets according to the processing method of the target temperature dataset, identify the temperature datasets containing temperature abrupt changes as temperature abrupt change datasets, and obtain n temperature abrupt change datasets. Therefore, the temperature abrupt change datasets can be extracted from the m temperature datasets, analyzed, and used to determine whether temperature data anomalies have occurred, thereby improving the accuracy of transformer anomaly early warning.

[0061] 203: Determine the temperature mutation dataset that meets the first preset condition among the n temperature mutation datasets as the abnormal temperature dataset, and obtain i abnormal temperature datasets.

[0062] In this embodiment, i is a positive integer less than or equal to n. The processing device can analyze each of the n temperature mutation datasets to determine whether each temperature mutation dataset meets a first preset condition, thereby identifying i abnormal temperature datasets from the n temperature mutation datasets.

[0063] For example, among n temperature mutation datasets, the temperature mutation dataset that meets a first preset condition is identified as an abnormal temperature dataset, resulting in i abnormal temperature datasets, which may include, for example:

[0064] Obtain multiple temperature data points from the target temperature mutation dataset to obtain multiple target temperature data points;

[0065] By fitting multiple target temperature data, temperature curves corresponding to the target temperature abrupt change dataset are obtained;

[0066] Determine the slope of the temperature curve corresponding to multiple target temperature data to obtain multiple slopes;

[0067] Multiple slopes are used as multiple temperature change rates corresponding to multiple target temperature data.

[0068] If there are temperature abrupt changes that do not fall within the temperature change reference rate range among multiple temperature change rates, then the target temperature abrupt change dataset is determined to be one of the i abnormal temperature datasets.

[0069] In this embodiment, the target temperature mutation dataset is any one of n temperature mutation datasets. Each target temperature data point corresponds to a slope. Each target temperature data point corresponds to a temperature change rate.

[0070] Specifically, the processing device acquires the target temperature mutation dataset from n temperature mutation datasets, and obtains multiple temperature data points corresponding to the target temperature mutation dataset, resulting in multiple target temperature data points. Then, curve fitting is performed on these multiple target temperature data points to obtain a temperature curve corresponding to the target temperature mutation dataset. The horizontal axis of the temperature curve represents the acquisition time corresponding to each target temperature data point, and the vertical axis represents the target temperature data. The temperature curve reflects the change in temperature data within each temperature mutation dataset over time.

[0071] The processing device then determines the slope at the tangent point of each target temperature data point in the temperature curve to obtain the slope corresponding to each target temperature data point, thus yielding multiple slopes. The slope corresponding to each target temperature data point represents the rate of temperature change at that target temperature data point. The processing device uses these multiple slopes as multiple rates of temperature change corresponding to multiple target temperature data points.

[0072] It should be noted that in this embodiment of the application, the target temperature data is determined to be abnormal temperature data by determining whether the rate of temperature change corresponding to the target temperature data is within the range of the temperature change reference rate.

[0073] If any temperature abrupt change data exists among multiple temperature change rates that does not fall within the temperature change reference rate range, then the target temperature abrupt change dataset is determined as one of the i abnormal temperature datasets. The temperature change reference rate range is determined based on the transformer's preset temperature rise formula.

[0074] If multiple temperature change rates fall within the temperature change reference rate range, the target temperature mutation dataset is determined to be a normal temperature dataset. At this time, the processing device can mark the location corresponding to the target temperature mutation dataset as the location of interest in order to continuously monitor the location of interest.

[0075] Thus, the processing equipment can analyze and process n temperature mutation datasets according to the processing method of the target temperature mutation dataset, and determine the abnormal temperature dataset that meets the first preset condition from the n temperature mutation datasets. This allows for the identification of abnormal temperature data during transformer operation within a preset time period, enabling early warning of abnormal temperature data, improving the safety and stability of transformer operation. Furthermore, by analyzing each target temperature data in each temperature mutation dataset, the accuracy of abnormal early warning for the transformer can be improved.

[0076] For example, the method may further include:

[0077] Determine the highest temperature value in the target temperature mutation dataset based on the temperature curve;

[0078] If the highest temperature value is higher than the second threshold, then the target temperature mutation dataset is determined to be one of the i abnormal temperature datasets.

[0079] In this embodiment, the processing device further determines the highest temperature value within a preset time period at the location corresponding to the target temperature mutation dataset of the transformer based on the temperature curve corresponding to the target temperature mutation dataset. If the highest temperature value is higher than a second threshold, it indicates that the temperature at that location has abnormally increased within the preset time period, and the target temperature mutation dataset is determined to be one of the i abnormal temperature datasets.

[0080] In this way, the processing equipment can analyze the n temperature curves corresponding to the n temperature mutation datasets according to the processing method of the target temperature mutation dataset, determine the abnormal temperature dataset from the n temperature mutation datasets, and use the temperature mutation dataset with excessively high temperature during transformer operation as the abnormal temperature dataset to issue an early warning for the abnormal temperature dataset, thereby improving the safety and stability of the transformer operation. Analyzing the n temperature curves corresponding to the n temperature mutation datasets in sequence can improve the accuracy of abnormal early warning for the transformer.

[0081] It should be noted that, in the embodiments of this application, the temperature change reference rate range and the second threshold can be obtained by temperature evolution based on the preset temperature rise relationship of the transformer.

[0082] For example, the method may also include the following steps:

[0083] Obtain the temperature rise parameters of the transformer;

[0084] Based on the transformer winding resistance and electrical data, determine the load power loss of the transformer during a preset time period;

[0085] Obtain the no-load power loss of the transformer within a preset time period;

[0086] Based on load power loss and no-load power loss, determine the power loss of the transformer within a preset time period.

[0087] Based on the heat dissipation surface area, heat dissipation coefficient, power loss, and the preset temperature rise relationship of the transformer, the temperature change reference rate range and the second threshold are determined.

[0088] In the embodiments of this application, the temperature rise parameters include the heat dissipation surface area and heat dissipation coefficient of the transformer windings.

[0089] Specifically, the processing equipment first obtains the heat dissipation surface area, heat dissipation coefficient, and winding resistance of the transformer windings. Based on the transformer winding resistance and electrical data, the load power loss of the transformer during a preset time period is determined. For example, the transformer's heat generation power can be determined based on the transformer's current data and winding resistance during the preset time period, and this heat generation power can be used as the transformer's load power loss during the preset time period.

[0090] Then, the processing equipment acquires the no-load power loss of the transformer within a preset time period. The no-load power loss is related to the shape and quality of the transformer core, and the no-load power loss of each transformer is determined during the production process. The processing equipment can directly acquire the no-load power loss of the transformer. Next, the sum of the load power loss and the no-load power loss of the transformer within the preset time period is taken as the total power loss of the transformer within the preset time period.

[0091] Temperature evolution is performed based on the heat dissipation surface area, heat dissipation coefficient, power loss, and a preset temperature rise relationship of the transformer to determine the temperature change reference rate range and the second threshold. The preset temperature rise relationship can be expressed by the following formula (1):

[0092] ΔT=P L / (S×α) formula (1)

[0093] Where ΔT represents the temperature rise of the transformer, that is, the temperature change of the transformer, and P L This represents the power loss of the transformer within a preset time period, where S represents the heat dissipation surface area of ​​the transformer windings, and α represents the heat dissipation coefficient of the transformer windings. Based on the temperature data of the transformer at the beginning of the preset time period, the processing equipment can analyze the temperature evolution of the transformer's temperature changes using the aforementioned preset temperature rise formula, thereby determining the temperature change reference rate range and the second threshold.

[0094] As can be seen from the embodiments of this application, the processing device can determine the load power loss of the transformer within a preset time period based on the winding resistance and electrical data of the transformer, and obtain the no-load power loss of the transformer within the preset time period. Based on the load power loss and no-load power loss of the transformer within the preset time period, the power loss of the transformer within the preset time period can be determined. Based on the heat dissipation surface area, heat dissipation coefficient, power loss, and the preset temperature rise relationship of the transformer, the temperature evolution of the transformer can be analyzed to determine the temperature change reference rate range and the second threshold. Therefore, it is possible to determine whether the temperature change dataset is an abnormal temperature dataset based on the temperature change reference rate range and the second threshold, thereby improving the accuracy of abnormal early warning for the transformer.

[0095] 204: Send the first warning information for the i abnormal temperature datasets to the monitoring equipment.

[0096] In this embodiment, after determining i abnormal temperature datasets, the processing device can generate first warning information for the i abnormal temperature datasets. The first warning information includes i locations corresponding to the i abnormal temperature datasets out of m locations. Each abnormal temperature dataset corresponds to one location. The first warning information also includes the temperature curve corresponding to the abnormal temperature dataset, as well as the aforementioned temperature change reference rate range and second threshold.

[0097] Therefore, users can obtain the first warning information for i abnormal temperature datasets from the monitoring device. This allows them to obtain the abnormal temperature datasets that occur in the transformer within a preset time period, as well as the location of each abnormal temperature dataset. Based on the abnormal temperature datasets and their corresponding locations, anomalies can be located and repaired, improving the safety and stability of the transformer during operation.

[0098] 205: Determine the k-segment electrical abrupt change data of the transformer in the electrical dataset.

[0099] In this embodiment of the application, the processing device can divide the electrical dataset into multiple segments of electrical data and analyze each segment of electrical data to determine k segments of electrical mutation data in the electrical dataset.

[0100] For example, an electrical dataset may include a current dataset and a voltage dataset. Determining k electrical abrupt changes in the transformer from the electrical dataset may include, for example, the following steps:

[0101] The preset time period is divided into multiple segments based on the second preset duration to obtain multiple second time periods;

[0102] Determine the current data corresponding to multiple second time periods in the current dataset to obtain multiple segments of current data;

[0103] Determine the current change value corresponding to each segment of current data in multiple current data to obtain multiple current change values;

[0104] The current data with current change values ​​greater than or equal to the third threshold in the multi-segment current data are identified as current abrupt change data, thus obtaining multi-segment current abrupt change data;

[0105] Determine the voltage data corresponding to multiple second time periods in the voltage dataset to obtain multiple voltage data segments;

[0106] Determine the current change value corresponding to each voltage data segment in the multiple voltage data segments to obtain multiple voltage change values;

[0107] Voltage data with voltage changes greater than or equal to the fourth threshold in multiple voltage data segments are identified as voltage abrupt change data, thus obtaining multiple voltage abrupt change data segments.

[0108] Multiple segments of current and voltage change data are used as k segments of electrical change data.

[0109] In this embodiment, the current change value is the difference between the current data at the start time and the current data at the end time of the second time period. The voltage change value is the difference between the voltage data at the start time and the voltage data at the end time of the second time period.

[0110] Specifically, the processing device can divide the preset time period into multiple segments according to the second preset duration, resulting in multiple second time periods. The second preset duration can be pre-set based on the acquisition time of each electrical data point in the electrical dataset and the accuracy required to determine electrical mutation data.

[0111] Then, the processing device determines the current data corresponding to multiple second time periods in the current dataset, obtaining multiple current data segments, with each second time period corresponding to one of the multiple current data segments. Next, the difference between the current data corresponding to the start time and the current data corresponding to the end time of each second time period is determined, obtaining the current change value for each second time period, thus obtaining multiple current change values. Current data segments with current change values ​​greater than or equal to a third threshold are considered as current abrupt change data, thus obtaining multiple current abrupt change data segments. If multiple current change values ​​are all less than the third threshold, it indicates that the transformer's current data within the preset time period is abnormal. The third threshold can be preset according to the actual operating state of the transformer.

[0112] Similarly, the processing device determines the voltage data corresponding to multiple second time periods in the voltage dataset, obtaining multiple voltage data segments, with each second time period corresponding one-to-one with the multiple voltage data segments. Next, the difference between the voltage data corresponding to the start time and the voltage data corresponding to the end time of each second time period is determined, obtaining the voltage change value for each second time period, thus obtaining multiple voltage change values. Voltage data segments with voltage change values ​​greater than or equal to a fourth threshold are considered as voltage abrupt change data, thus obtaining multiple voltage abrupt change data segments. If multiple voltage change values ​​are all less than the fourth threshold, it indicates that the transformer's voltage data within the preset time period is not abnormal. The fourth threshold can be preset according to the actual operating state of the transformer.

[0113] Finally, the processing device uses the multiple segments of current change data and the multiple segments of voltage change data as k segments of electrical change data.

[0114] Therefore, the processing equipment can divide the current dataset and voltage dataset into multiple segments of current data and multiple segments of voltage data, and analyze each segment of current data and each segment of voltage data separately to identify multiple segments of current change data and multiple segments of voltage change data, thereby obtaining k segments of electrical change data. By analyzing the k segments of electrical change data, it can be determined whether the electrical data of the transformer has abnormalities within a preset time period, thereby improving the accuracy of abnormal early warning for the transformer.

[0115] 206: Determine that the electrical mutation data in segment k that meets the second preset condition is abnormal electrical data, and obtain segment p abnormal electrical data.

[0116] In this embodiment of the application, the processing device can determine whether each segment of electrical mutation data in the k segments of electrical mutation data meets the second preset condition, so as to determine the p segment of abnormal electrical data in the k segments of electrical mutation data.

[0117] For example, electrical mutation data that meets the second preset condition in k segments of electrical mutation data is determined to be abnormal electrical data, thus obtaining p segments of abnormal electrical data, which may include, for example:

[0118] Determine the current change range corresponding to the target current abrupt change data;

[0119] Determine the target voltage change range corresponding to the current change range;

[0120] Determine the first target time period corresponding to the target current mutation data;

[0121] If the voltage data within the first target time period does not fall within the target voltage change range, then the target current mutation data is determined to be abnormal current data.

[0122] Determine the voltage change range corresponding to the target voltage abrupt change data;

[0123] Determine the target current variation range corresponding to the target voltage abrupt change data;

[0124] Determine the second target time period corresponding to the target voltage mutation data;

[0125] If the current data within the second target time period does not fall within the target current change range, then the target voltage change data is determined to be abnormal voltage data.

[0126] Abnormal current data from multiple current surge data segments and abnormal voltage data from multiple voltage surge data segments are used as abnormal electrical data to obtain p-segment abnormal electrical data.

[0127] In this embodiment, the target current change data is any segment of current change data from multiple current change data segments. The target voltage change data is any segment of voltage change data from multiple voltage change data segments.

[0128] Specifically, the processing equipment first obtains the target current change data from the k segments of electrical change data, and then obtains the maximum and minimum currents from the current data corresponding to the target current change data to obtain the current change range corresponding to the target current change data. Based on the current change range, the target voltage change range corresponding to the current change range can be determined. The correspondence between the current change range and the target voltage change range can be preset based on the actual operating state of the transformer.

[0129] Then, the processing equipment determines the first target time period corresponding to the target current mutation data. If the voltage data within the first target time period does not fall within the target voltage change range, it indicates that the change trends of the current and voltage data within the first target time period are not within the normal range, and the target current mutation data is determined to be abnormal current data. Therefore, by analyzing and processing multiple segments of current mutation data based on the target current mutation data, abnormal current data can be obtained from the multiple segments of current mutation data.

[0130] Similarly, the processing equipment first obtains the target voltage change data from the k segments of electrical change data, and then obtains the maximum and minimum voltages from the corresponding voltage data to determine the voltage change range corresponding to the target voltage change data. Based on the voltage change range, the target current change range corresponding to the voltage change range can be determined. The correspondence between the voltage change range and the target current change range can be preset based on the actual operating state of the transformer.

[0131] Then, the processing equipment determines the second target time period corresponding to the target voltage mutation data. If the current data within the second target time period does not fall within the target current change range, it indicates that the change trends of the voltage and current data within the second target time period are not within the normal range, and the target voltage mutation data is determined to be abnormal voltage data. Therefore, by analyzing and processing multiple voltage mutation data segments based on the target voltage mutation data, abnormal voltage data can be obtained from the multiple voltage mutation data segments.

[0132] Finally, the processing device uses the abnormal current data from the multi-segment current mutation data and the abnormal voltage data from the multi-segment voltage mutation data as abnormal electrical data to obtain the p-segment abnormal electrical data.

[0133] It can be seen that the processing equipment can analyze the current and voltage mutation data in the k-segment electrical mutation data separately to determine the abnormal current data in the multi-segment current mutation data and the abnormal voltage data in the multi-segment voltage mutation data. Thus, the abnormal current data and abnormal voltage data can be used together as abnormal electrical data to provide early warning of abnormal electrical data, thereby improving the accuracy of abnormal early warning for transformers.

[0134] 207: Send a second early warning message to the monitoring equipment regarding abnormal electrical data in segment p.

[0135] In this embodiment, after determining the abnormal electrical data of segment p, the processing device can generate a second early warning message for the abnormal electrical data of segment p and send the second early warning message to the monitoring device. The second early warning message includes the current data and voltage data corresponding to the abnormal electrical data of segment p. The user can obtain the second early warning message from the monitoring device to handle and repair the transformer anomaly.

[0136] In summary, in this embodiment, firstly, m temperature datasets at m locations within the transformer within a preset time period, and an electrical dataset of the transformer within the preset time period are obtained, where each location corresponds to one temperature dataset. Then, the temperature datasets containing temperature abrupt changes are identified as temperature abrupt change datasets, resulting in n temperature abrupt change datasets, where temperature abrupt changes are temperature data whose temperature change over a first preset time period is greater than or equal to a first threshold. Next, the temperature abrupt change datasets satisfying a first preset condition among the n temperature abrupt change datasets are identified as abnormal temperature datasets, resulting in i abnormal temperature datasets. Further, a first warning message for the i abnormal temperature datasets is sent to the monitoring device. The first warning message includes the i locations corresponding to the i abnormal temperature datasets among the m locations, with each abnormal temperature dataset corresponding to one location. Therefore, based on the m temperature datasets at m locations within the transformer within a preset time period, abnormal temperature datasets can be determined, and a first warning message can be sent to the monitoring device to improve the safety and stability of the transformer during operation. The first warning message also includes the location corresponding to each abnormal temperature dataset, which can improve the accuracy of transformer anomaly warnings. Furthermore, this application can identify k segments of electrical mutation data of the transformer from the electrical dataset, and then determine the electrical mutation data that meets the second preset condition among the k segments of electrical mutation data as abnormal electrical data, thus obtaining p segments of abnormal electrical data. Finally, a second early warning message for the p segments of abnormal electrical data is sent to the monitoring equipment. Therefore, based on the electrical dataset of the transformer within a preset time period, abnormal electrical data of the transformer can be determined, and a second early warning message can be sent to the monitoring equipment, thereby improving the safety and stability of the transformer during operation. Compared to determining whether an anomaly has occurred during transformer operation solely through electrical data, this application can combine temperature data and electrical data to more accurately determine whether the transformer is abnormal, improving the accuracy of transformer anomaly early warning.

[0137] See Figure 3 , Figure 3 This is a schematic diagram of a transformer anomaly early warning device provided in an embodiment of this application. The transformer anomaly early warning device 300 includes an acquisition module 301, a data processing module 302, and an early warning module 303;

[0138] The data acquisition module 301 is used to acquire m temperature datasets at m locations within the transformer within a preset time period, as well as electrical datasets of the transformer within the preset time period; each location corresponds to one temperature dataset; m is an integer greater than 1;

[0139] Data processing module 302 is used to determine the temperature dataset containing temperature abrupt changes among m temperature datasets as temperature abrupt change datasets, and to obtain n temperature abrupt change datasets; temperature abrupt change data is temperature data whose temperature change value for a first preset time period is greater than or equal to a first threshold; n is a positive integer less than or equal to m;

[0140] Among the n temperature mutation datasets, the temperature mutation datasets that satisfy the first preset condition are identified as abnormal temperature datasets, resulting in i abnormal temperature datasets; i is a positive integer less than or equal to n.

[0141] The early warning module 303 is used to send a first early warning message to the monitoring device for i abnormal temperature datasets; the first early warning message includes i locations corresponding to the i abnormal temperature datasets in m locations; each abnormal temperature dataset corresponds to one location;

[0142] Data processing module 302 is used to determine k segments of electrical abrupt change data of the transformer in the electrical dataset;

[0143] The electrical mutation data in segment k that meets the second preset condition is identified as abnormal electrical data, thus obtaining segment p of abnormal electrical data;

[0144] The early warning module 303 is used to send a second early warning message to the monitoring equipment for abnormal electrical data in segment p.

[0145] In one possible embodiment, regarding determining that a temperature dataset containing temperature abrupt changes is a temperature abrupt change dataset among m temperature datasets, and obtaining n temperature abrupt change datasets, the data processing module 302 is specifically used for:

[0146] Obtain the target temperature dataset; the target temperature dataset includes multiple temperature data points, each temperature data point corresponding to a collection time; the target temperature dataset is any one of the m temperature datasets.

[0147] The preset time period is divided into multiple segments based on the first preset duration, resulting in multiple first time periods;

[0148] Determine the temperature data corresponding to multiple first time periods in the target temperature dataset to obtain multiple temperature data segments;

[0149] Determine the temperature change value corresponding to each temperature data segment in multiple temperature data segments to obtain multiple temperature change values; the temperature change value is the difference between the temperature data corresponding to the start time and the temperature data corresponding to the end time of the first time segment.

[0150] If at least one of the multiple temperature change values ​​is greater than or equal to the first threshold, then the target temperature dataset is determined to be one of the n temperature mutation datasets.

[0151] In one possible embodiment, regarding determining that the temperature mutation datasets satisfying a first preset condition among n temperature mutation datasets are abnormal temperature datasets, and obtaining i abnormal temperature datasets, the data processing module 302 is specifically used for:

[0152] Multiple temperature data points are obtained from the target temperature mutation dataset to obtain multiple target temperature data points; the target temperature mutation dataset can be any one of the n temperature mutation datasets.

[0153] By fitting multiple target temperature data, temperature curves corresponding to the target temperature abrupt change dataset are obtained;

[0154] Determine the slope of the temperature curve corresponding to multiple target temperature data points to obtain multiple slopes; each target temperature data point corresponds to one slope.

[0155] Multiple slopes are used as multiple temperature change rates corresponding to multiple target temperature data; each target temperature data corresponds to one temperature change rate.

[0156] If there are temperature abrupt changes that do not fall within the temperature change reference rate range among multiple temperature change rates, then the target temperature abrupt change dataset is determined to be one of the i abnormal temperature datasets.

[0157] In one possible embodiment, the data processing module 302 is further configured to:

[0158] Determine the highest temperature value in the target temperature mutation dataset based on the temperature curve;

[0159] If the highest temperature value is higher than the second threshold, then the target temperature mutation dataset is determined to be one of the i abnormal temperature datasets.

[0160] In one possible embodiment, the data processing module 302 is further configured to:

[0161] Obtain the temperature rise parameters of the transformer, including the heat dissipation surface area and heat dissipation coefficient of the transformer windings;

[0162] Based on the transformer winding resistance and electrical data, determine the load power loss of the transformer during a preset time period;

[0163] Obtain the no-load power loss of the transformer within a preset time period;

[0164] Based on load power loss and no-load power loss, determine the power loss of the transformer within a preset time period.

[0165] Based on the heat dissipation surface area, heat dissipation coefficient, power loss, and the preset temperature rise relationship of the transformer, the temperature change reference rate range and the second threshold are determined.

[0166] In one possible embodiment, the electrical dataset includes a current dataset and a voltage dataset; regarding the determination of k-segment electrical abrupt change data of the transformer within the electrical dataset, the data processing module 302 is specifically used for:

[0167] The preset time period is divided into multiple segments based on the second preset duration to obtain multiple second time periods;

[0168] Determine the current data corresponding to multiple second time periods in the current dataset to obtain multiple segments of current data;

[0169] Determine the current change value corresponding to each current data segment in the multiple current data segments to obtain multiple current change values; the current change value is the difference between the current data corresponding to the start time and the current data corresponding to the end time of the second time segment.

[0170] The current data with current change values ​​greater than or equal to the third threshold in the multi-segment current data are identified as current abrupt change data, thus obtaining multi-segment current abrupt change data;

[0171] Determine the voltage data corresponding to multiple second time periods in the voltage dataset to obtain multiple voltage data segments;

[0172] Determine the current change value corresponding to each voltage data segment in the multiple voltage data segments to obtain multiple voltage change values; the voltage change value is the difference between the voltage data corresponding to the start time and the voltage data corresponding to the end time of the second time segment.

[0173] Voltage data with voltage changes greater than or equal to the fourth threshold in multiple voltage data segments are identified as voltage abrupt change data, thus obtaining multiple voltage abrupt change data segments.

[0174] Multiple segments of current and voltage change data are used as k segments of electrical change data.

[0175] In one possible embodiment, regarding determining that electrical mutation data satisfying a second preset condition in k segments of electrical mutation data is abnormal electrical data, and obtaining p segments of abnormal electrical data, the data processing module 302 is specifically used for:

[0176] Determine the current change range corresponding to the target current mutation data; the target current mutation data is any segment of current mutation data from multiple segments of current mutation data.

[0177] Determine the target voltage change range corresponding to the current change range;

[0178] Determine the first target time period corresponding to the target current mutation data;

[0179] If the voltage data within the first target time period does not fall within the target voltage change range, then the target current mutation data is determined to be abnormal current data.

[0180] Determine the voltage change range corresponding to the target voltage mutation data; the target voltage mutation data is any segment of voltage mutation data from multiple voltage mutation data segments.

[0181] Determine the target current variation range corresponding to the target voltage abrupt change data;

[0182] Determine the second target time period corresponding to the target voltage mutation data;

[0183] If the current data within the second target time period does not fall within the target current change range, then the target voltage change data is determined to be abnormal voltage data.

[0184] Abnormal current data from multiple current surge data segments and abnormal voltage data from multiple voltage surge data segments are used as abnormal electrical data to obtain p-segment abnormal electrical data.

[0185] See Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a transceiver 401, a processor 402, and a memory 403. These are connected via a bus 404. The memory 403 stores computer programs and data, and can transmit data stored in the memory 403 to the processor 402. The electronic device 400 can be a transformer fault warning device 300. The electronic device 400 can also be a processing device according to any of the above embodiments.

[0186] Processor 402 is used to read the computer program in memory 403 and perform the following operations:

[0187] Obtain m temperature datasets at m locations within a preset time period, as well as an electrical dataset of the transformer within the preset time period; each location corresponds to one temperature dataset; m is an integer greater than 1;

[0188] The temperature dataset containing temperature abrupt changes among m temperature datasets is identified as the temperature abrupt change dataset, resulting in n temperature abrupt change datasets; the temperature abrupt change data is the temperature data whose temperature change value is greater than or equal to a first threshold over a first preset time period; n is a positive integer less than or equal to m;

[0189] Among the n temperature mutation datasets, the temperature mutation datasets that satisfy the first preset condition are identified as abnormal temperature datasets, resulting in i abnormal temperature datasets; i is a positive integer less than or equal to n.

[0190] Send a first warning message to the monitoring equipment for i abnormal temperature datasets; the first warning message includes i locations corresponding to the i abnormal temperature datasets in m locations; each abnormal temperature dataset corresponds to one location;

[0191] Identify k segments of electrical abrupt changes in the transformer data set;

[0192] The electrical mutation data in segment k that meets the second preset condition is identified as abnormal electrical data, thus obtaining segment p of abnormal electrical data;

[0193] Send a second early warning message to the monitoring equipment regarding abnormal electrical data in segment p.

[0194] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device 400 includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0195] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement some or all of the steps of any of the methods described in the above method embodiments.

[0196] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments.

[0197] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0198] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0199] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0200] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0201] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0202] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0203] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0204] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for early warning of transformer anomalies, characterized in that, include: Obtain m temperature datasets at m locations within a preset time period, and obtain electrical datasets of the transformer within the preset time period; Each location corresponds to a temperature dataset; m is an integer greater than 1; The temperature dataset containing temperature abrupt changes among the m temperature datasets is identified as the temperature abrupt change dataset, resulting in n temperature abrupt change datasets; the temperature abrupt change data is temperature data whose temperature change value for a first preset time period is greater than or equal to a first threshold; n is a positive integer less than or equal to m; Determine the temperature mutation dataset that meets the first preset condition from the n temperature mutation datasets as the abnormal temperature dataset, and obtain i abnormal temperature datasets; i is a positive integer less than or equal to n; Send a first warning message to the monitoring equipment for the i abnormal temperature datasets; The first warning information includes the i abnormal temperature datasets corresponding to the i locations among the m locations; each abnormal temperature dataset corresponds to one location; Determine k segments of electrical abrupt change data for the transformer from the electrical dataset; The electrical mutation data that meets the second preset condition among the k segments of electrical mutation data is identified as abnormal electrical data, and p segments of abnormal electrical data are obtained; Send a second early warning message to the monitoring device regarding the abnormal electrical data in segment p.

2. The method according to claim 1, characterized in that, The temperature dataset containing temperature abrupt changes among the m temperature datasets is defined as the temperature abrupt change dataset, resulting in n temperature abrupt change datasets, including: Obtain the target temperature dataset; the target temperature dataset includes multiple temperature data points, each temperature data point corresponding to a collection time; the target temperature dataset is any one of the m temperature datasets. The preset time period is divided into multiple segments according to the first preset duration to obtain multiple first time periods; Determine the temperature data corresponding to the multiple first time periods in the target temperature dataset to obtain multiple temperature data segments; Determine the temperature change value corresponding to each segment of temperature data in the multiple temperature data segments to obtain multiple temperature change values; the temperature change value is the difference between the temperature data corresponding to the start time and the temperature data corresponding to the end time of the first time period. If at least one of the multiple temperature change values ​​is greater than or equal to the first threshold, then the target temperature dataset is determined to be one of the n temperature mutation datasets.

3. The method according to claim 1 or 2, characterized in that, The step of determining the temperature mutation dataset that meets the first preset condition among the n temperature mutation datasets as abnormal temperature datasets, and obtaining i abnormal temperature datasets, includes: Multiple temperature data points are obtained from the target temperature mutation dataset to obtain multiple target temperature data points; the target temperature mutation dataset is any one of the n temperature mutation datasets. The multiple target temperature data are fitted to obtain the temperature curve corresponding to the target temperature abrupt change dataset; Determine the slope of the temperature curve corresponding to the multiple target temperature data to obtain multiple slopes; each target temperature data corresponds to one slope; The multiple slopes are used as multiple temperature change rates corresponding to the multiple target temperature data; each target temperature data corresponds to a temperature change rate. If there are temperature abrupt changes in the multiple temperature change rates that do not fall within the temperature change reference rate range, then the target temperature abrupt change dataset is determined to be one of the i abnormal temperature datasets.

4. The method according to claim 3, characterized in that, The method further includes: Determine the highest temperature value of the target temperature mutation dataset based on the temperature curve; If the highest temperature value is higher than the second threshold, then the target temperature mutation dataset is determined to be one of the i abnormal temperature datasets.

5. The method according to claim 4, characterized in that, The method further includes: The temperature rise parameters of the transformer are obtained, including the heat dissipation surface area and heat dissipation coefficient of the transformer windings; Based on the winding resistance of the transformer and the electrical data, the load power loss of the transformer during the preset time period is determined. Obtain the no-load power loss of the transformer during the preset time period; Based on the load power loss and the no-load power loss, the power loss of the transformer during the preset time period is determined; Based on the heat dissipation surface area, the heat dissipation coefficient, the power loss, and the preset temperature rise relationship of the transformer, the temperature change reference rate range and the second threshold are determined.

6. The method according to claim 1, characterized in that, The electrical dataset includes a current dataset and a voltage dataset; determining the k segments of electrical abrupt changes in the transformer from the electrical dataset includes: The preset time period is divided into multiple segments according to the second preset duration to obtain multiple second time periods; Determine the current data corresponding to the multiple second time periods in the current dataset to obtain multiple segments of current data; The current change value corresponding to each segment of current data is determined to obtain multiple current change values; the current change value is the difference between the current data corresponding to the start time and the current data corresponding to the end time of the second time period. The current data with current change values ​​greater than or equal to the third threshold in the multi-segment current data are identified as current abrupt change data, thus obtaining multi-segment current abrupt change data; Determine the voltage data corresponding to the multiple second time periods in the voltage dataset to obtain multiple voltage data segments; The current change value corresponding to each voltage data segment in the multiple voltage data segments is determined to obtain multiple voltage change values; the voltage change value is the difference between the voltage data corresponding to the start time and the voltage data corresponding to the end time of the second time period. Voltage data with voltage changes greater than or equal to the fourth threshold in multiple voltage data segments are identified as voltage abrupt change data, thus obtaining multiple voltage abrupt change data segments. The multiple segments of current change data and the multiple segments of voltage change data are used as the k-segment electrical change data.

7. The method according to claim 6, characterized in that, The step of determining that electrical mutation data satisfying the second preset condition in the k segments of electrical mutation data is abnormal electrical data, and obtaining p segments of abnormal electrical data, includes: Determine the current change range corresponding to the target current mutation data; the target current mutation data is any segment of current mutation data among the multiple segments of current mutation data. Determine the target voltage change range corresponding to the current change range; Determine the first target time period corresponding to the target current mutation data; If the voltage data within the first target time period does not fall within the target voltage change range, then the target current mutation data is determined to be abnormal current data. Determine the voltage change range corresponding to the target voltage mutation data; the target voltage mutation data is any segment of voltage mutation data among the multiple segments of voltage mutation data. Determine the target current variation range corresponding to the target voltage mutation data; Determine the second target time period corresponding to the target voltage mutation data; If the current data within the second target time period does not fall within the target current change range, then the target voltage change data is determined to be abnormal voltage data. The abnormal current data and abnormal voltage data in the multi-segment current mutation data are used as the abnormal electrical data to obtain the p-segment abnormal electrical data.

8. An abnormality early warning device for a transformer, characterized in that, The device includes a data acquisition module, a data processing module, and an early warning module; The data acquisition module is used to acquire m temperature datasets at m locations within the transformer within a preset time period, as well as electrical datasets of the transformer within the preset time period; each location corresponds to one temperature dataset; m is an integer greater than 1; The data processing module is used to determine the temperature dataset containing temperature abrupt changes among the m temperature datasets as temperature abrupt change datasets, and to obtain n temperature abrupt change datasets; the temperature abrupt change data is temperature data whose temperature change value for a first preset time period is greater than or equal to a first threshold; n is a positive integer less than or equal to m; Determine the temperature mutation dataset that meets the first preset condition from the n temperature mutation datasets as the abnormal temperature dataset, and obtain i abnormal temperature datasets; i is a positive integer less than or equal to n; The early warning module is used to send a first early warning message to the monitoring equipment for the i abnormal temperature datasets; The first warning information includes the i abnormal temperature datasets corresponding to the i locations among the m locations; each abnormal temperature dataset corresponds to one location; The data processing module is used to determine k segments of electrical mutation data of the transformer in the electrical dataset; The electrical mutation data that meets the second preset condition among the k segments of electrical mutation data is identified as abnormal electrical data, and p segments of abnormal electrical data are obtained; The early warning module is used to send a second early warning message to the monitoring equipment regarding the abnormal electrical data of segment p.

9. An electronic device, characterized in that, include: A processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1-7.

Images