Transformer micro-water data prediction method and system

Abstract

The invention discloses a transformer micro-water data prediction method and system, and the method comprises the steps: obtaining micro-water sample data, and carrying out the preprocessing of the micro-water sample data; time features in the preprocessed micro-water sample data are extracted, and a data change rule is obtained based on the time features; and according to the preprocessed micro-water sample data and the data change rule, utilizing an extreme gradient lifting model to obtain a prediction result of the micro-water data. According to the method, the time features are extracted, the data change rule is analyzed, the extreme gradient lifting model is combined for prediction, the weight is distributed for the micro-water sample data so as to improve the prediction precision, and the generalization ability of the model is enhanced; according to the method, the micro-water data change rule graph and the prediction graph are generated, the data dynamic state and the prediction trend are visually displayed, a scientific basis is provided for maintenance and management of the transformer, the fault risk caused by the fact that the micro-water content exceeds the standard is effectively reduced, and the overall stability and safety of a power system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer data prediction, and in particular to a transformer micro-water data prediction method and system. Background Art

[0002] Micro-water data plays a vital role in the power system. It is directly related to the performance of insulating materials and the stable operation of transformers. Specifically, the micro-water content is an intuitive indicator for evaluating the degree of moisture in insulating materials. Under ideal conditions, when the micro-water content is maintained at a low level, the insulation resistance of the insulating material will remain at a higher value, which can effectively prevent accidental leakage of current and ensure the safe and reliable operation of the transformer under rated parameters. However, once the micro-water content exceeds the preset safety threshold, the insulation performance of the insulating material will drop sharply, which will not only weaken its ability to block current, but also greatly increase the probability of transformer failure, and may even cause serious power accidents.

[0003] In view of this, how to accurately and efficiently predict the micro-water data in transformers has become a key issue that needs to be solved in the current power technology field. This not only requires researchers to deeply understand the complex relationship between micro-water and insulation performance, but also requires the development of advanced and reliable monitoring and prediction technologies to achieve real-time and accurate control of transformer micro-water content, thereby ensuring the overall safety and stability of the power system. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a transformer micro-water data prediction method to solve the problem that the accuracy of the existing transformer micro-water data prediction is not high.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a transformer micro-water data prediction method, comprising:

[0008] Acquire trace water sample data, and pre-process the trace water sample data;

[0009] Extracting time features from the preprocessed micro-water sample data, and obtaining data variation rules based on the time features;

[0010] According to the pre-processed trace water sample data and the data variation law, the prediction result of the trace water data is obtained by using the extreme gradient lifting model.

[0011] As a preferred solution of the transformer micro-water data prediction method described in the present invention, the prediction result of micro-water data obtained by using the extreme gradient lifting model includes:

[0012] The pre-processed trace water sample data and the data variation rule are input into the extreme gradient boosting model, and weights are assigned to the pre-processed trace water sample data.

[0013] As a preferred solution of the transformer micro-water data prediction method described in the present invention, it also includes:

[0014] Dividing the preprocessed trace water sample data and the data variation law into a training set and a test set in the extreme gradient boosting model according to a first preset ratio;

[0015] Selecting part of the trace water sample data and the data variation law from the training set according to a second preset ratio as a sampling set;

[0016] The extreme gradient boosting model is trained by the training set, and the trained extreme gradient boosting model is used for evaluating the test set;

[0017] Constructing a plurality of decision trees based on the training set, the sampling set and the test set, and outputting a plurality of prediction values ​​through the plurality of decision trees;

[0018] The plurality of predicted values ​​are integrated through the extreme gradient boosting model to output a prediction result of the micro-water data.

[0019] As a preferred solution of the transformer micro-water data prediction method described in the present invention, the prediction results include:

[0020] Detect the real-time temperature information, real-time operating parameter information and real-time micro-water data of the transformer;

[0021] Analyzing the correlation between the real-time temperature information and the real-time micro-water data;

[0022] Analyzing the relationship between the real-time operating parameter information and the real-time micro-water data;

[0023] Based on the correlation between the real-time temperature information and the real-time trace water data, and the relationship between the real-time operating parameter information and the real-time trace water data, the prediction result is optimized.

[0024] As a preferred solution of the transformer micro-water data prediction method described in the present invention, wherein: extracting the time characteristics of the pre-processed micro-water sample data, and obtaining the data change law based on the time characteristics includes:

[0025] Recording the timestamp in the pre-processed micro-water sample data;

[0026] Acquire the time interval between the pre-processed micro-water sample data according to the timestamp;

[0027] A data variation rule is obtained based on the timestamp and the time interval.

[0028] As a preferred solution of the transformer micro-water data prediction method described in the present invention, it also includes:

[0029] Generate a trace water data variation law graph according to the pre-processed trace water sample data and the data variation law;

[0030] After the step of obtaining the prediction result of the micro-water data based on the extreme gradient lifting model, the method further includes:

[0031] A micro-water data prediction graph is generated according to the prediction results.

[0032] As a preferred solution of the transformer micro-water data prediction method of the present invention, the pre-processing of the micro-water sample data includes:

[0033] Testing the micro-water sample data;

[0034] If there are duplicate values ​​in the micro-water sample data, the duplicate values ​​are deleted;

[0035] If there are missing values ​​in the micro-water sample data, the missing values ​​are deleted, or the mean of the values ​​before and after the missing values ​​is taken to fill the missing values;

[0036] If there is an abnormal value in the micro-water sample data, the abnormal value is deleted, or the average of the values ​​before and after the abnormal value is taken to replace the abnormal value.

[0037] In a second aspect, the present invention provides a system for predicting transformer micro-water data, comprising:

[0038] A data acquisition module, used for acquiring micro-water sample data;

[0039] A preprocessing module, used for preprocessing the micro-water sample data;

[0040] A feature extraction module is used to extract the time features in the pre-processed micro-water sample data and obtain the data change law based on the time features;

[0041] The prediction module is used to obtain the prediction result of the trace water data by using the extreme gradient lifting model according to the pre-processed trace water sample data and the data change law.

[0042] In a third aspect, the present invention provides a computing device, comprising:

[0043] Memory and processor;

[0044] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the transformer micro-water data prediction method are implemented.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the transformer micro-water data prediction method.

[0046] Compared with the prior art, the present invention has the following beneficial effects: the present invention extracts time features and analyzes data change laws, combines the extreme gradient boosting model for prediction, not only assigns weights to micro-water sample data to improve prediction accuracy, but also divides the training set, test set and sampling set to construct a multi-decision tree integrated prediction result, thereby enhancing the generalization ability of the model; the present invention also considers the correlation between the real-time temperature information and operating parameter information of the transformer and the micro-water data, and further optimizes the prediction results; generates a micro-water data change law diagram and a prediction diagram, intuitively displays data dynamics and prediction trends, provides a scientific basis for transformer maintenance and management, effectively reduces the risk of failures caused by excessive micro-water content, and improves the overall stability and safety of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0048] Figure 1 The figure is a schematic diagram of the overall process of a transformer micro-water data prediction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0052] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0053] At the same time, in the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0054] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] Example 1

[0056] Reference Figure 1, is an embodiment of the present invention, and provides a transformer micro-water data prediction method, comprising:

[0057] S100: Acquire trace water sample data and pre-process the trace water sample data;

[0058] It should be noted that micro-water refers to the trace amount of water contained in transformer insulating oil and solid insulating materials. These waters exist in dissolved, emulsified or free forms, while micro-water sample data refers to the relatively accurate and complete data recorded in the micro-water historical data recorded and saved by various methods. It is understandable that some historical data may have problems such as inaccurate or incomplete records. These low-quality sample data will affect the accuracy and reliability of the prediction model. For example, during the data recording process, if human errors or equipment failures occur, it may lead to errors in the recording of micro-water data, thereby affecting the prediction of subsequent micro-water data, so the data needs to be preprocessed.

[0059] Preferably, the trace water sample data is tested; if there are duplicate values ​​in the trace water sample data, the duplicate values ​​are deleted; if there are missing values ​​in the trace water sample data, the missing values ​​are deleted, or the missing values ​​are filled with the mean of the values ​​before and after the missing values; if there are outliers in the trace water sample data, the outliers are deleted, or the mean of the values ​​before and after the outliers is taken to replace the outliers;

[0060] In a possible embodiment, the appearance of repeated values ​​usually includes repeated values ​​caused by measurement errors. For example, some traditional sensors may only be accurate to a certain extent, such as ±5ppm (parts per million). When the actual micro-water content fluctuates within the measurement accuracy range, repeated measurement values ​​may appear. In addition, if the stability of the sensor is poor, after a long period of operation, its zero drift or measurement sensitivity changes, which may also cause repeated inaccurate measurement values ​​to appear; the appearance of repeated values ​​also includes repeated values ​​caused by the internal stable state of the transformer, such as a transformer that runs under a stable load and is well sealed, and its micro-water content may remain at a fixed value for a period of time; the appearance of repeated values ​​also includes repeated values ​​caused by data recording and processing, such as a write error in the storage database or an abnormal data cache mechanism, which may write the previous data to the storage unit again. During the data transmission process, signal loss or repeated transmission may also cause the receiving end to receive repeated micro-water data. It is understandable that the appearance of repeated values ​​includes but is not limited to the reasons described above.

[0061] In a possible embodiment, the occurrence of missing values ​​generally includes missing values ​​caused by sensor failure, such as in a harsh electromagnetic environment, the communication line is disturbed, the signal transmission is interrupted, and the micro-water data cannot be transmitted from the sensor to the data storage device; the occurrence of missing values ​​also includes missing values ​​caused by environmental factors, such as at extremely low temperatures, the battery performance of the sensor decreases or the performance of the electronic components becomes unstable, which may cause incomplete or missing data collection; the occurrence of missing values ​​also includes missing values ​​caused by environmental factors, such as at extremely low temperatures, the battery performance of the sensor decreases or the performance of the electronic components becomes unstable, which may cause incomplete or missing data collection; the occurrence of missing values ​​also includes missing values ​​caused by human factors, such as accidentally deleting the file containing the micro-water data when cleaning the data storage device, or in the data migration process, some data are not successfully migrated due to operational errors. It is understandable that the occurrence of missing values ​​includes but is not limited to the reasons described above.

[0062] In a possible embodiment, the occurrence of abnormal values ​​generally includes abnormal values ​​caused by measurement errors, such as inaccurate standard materials used for calibration or non-compliance with the calibration process, which will cause deviations in the measurement results of the sensor. After incorrect calibration, the sensor may measure the actual normal micro-water content as a value that is too high or too low; the occurrence of abnormal values ​​also includes abnormal values ​​caused by internal faults of the transformer, such as problems with the sealing structure of the transformer, such as aging, cracking of the sealing gasket, or cracks in the sealing weld, and a large amount of external moisture will enter the transformer, causing the micro-water content to rise sharply and abnormal values ​​to appear. This situation may cause the micro-water data to far exceed the normal range, posing a serious threat to the insulation performance of the transformer; the occurrence of abnormal values ​​also includes abnormal values ​​in the data processing or transmission process, such as signal attenuation of the transmission line, noise interference, or data transmission protocol errors, which may cause errors in the received data and produce abnormal values. It is understandable that the occurrence of abnormal values ​​includes but is not limited to the reasons described above.

[0063] In an embodiment of the present application, the step of preprocessing the trace water sample data includes counting the proportion of missing values. If the total amount of data is large and the proportion of missing values ​​is extremely small, the record where the missing value is located can be directly deleted. If you want to retain it, you can use the average of the previous and next values ​​to fill the missing value; mark the values ​​that violate the business prior knowledge as outliers, such as the total hydrocarbon content cannot be negative, and count the proportion of outliers. If the total amount of data is large and the proportion of outliers is extremely small, the record where the outlier is located can be directly deleted. If you want to retain it, you can use the average of the previous and next values ​​to fill the outlier; for duplicate values, delete the duplicate values.

[0064] S102: extracting the time features in the pre-processed micro-water sample data, and obtaining the data variation law based on the time features;

[0065] It should be noted that time characteristics can be divided into continuous time characteristics and discrete time characteristics. In actual working conditions, time characteristics are mainly discrete time characteristics;

[0066] In a possible embodiment, in order to understand the changing trend of micro-water data in the next week, the time decomposition method is used to divide the collection time into: the week number, day number, hour number of each day, the week number of each month, the day number of each month and the day number of each week. These data can capture the data change pattern in a short period of time.

[0067] In the embodiment of the present application, the time feature includes at least a timestamp and a time interval. A timestamp is a number representing a specific moment, usually in seconds or milliseconds, calculated from a certain reference point, and used to record the exact time of the specific content of the micro-water data in the transformer at a certain moment; while a time interval refers to a period of time between two different moments, which can be regarded as a line segment with a beginning and an end. In data analysis and data science, understanding the time interval is crucial for analyzing trends, patterns, and behaviors over a period of time. Therefore, the timestamp in the pre-processed micro-water sample data can be recorded; the time interval between the pre-processed micro-water sample data can be obtained according to the timestamp; and the data change law can be obtained based on the timestamp and the time interval.

[0068] Preferably, the timestamps in the pre-processed micro-water sample data are recorded; the time intervals between the pre-processed micro-water sample data are obtained according to the timestamps; and the data variation pattern is obtained based on the timestamps and the time intervals.

[0069] Preferably, a micro-water data variation law graph is generated according to the pre-processed micro-water sample data and the data variation law;

[0070] Preferably, a micro-water data prediction graph is generated based on the prediction results.

[0071] Specifically, the timestamp in each pre-processed micro-water sample data is recorded, and the micro-water sample data with the same time interval is filtered out by the recorded timestamp, for example: the timestamp of the first data filtered out by the timestamp is 0:00 on January 1, 2024, the timestamp of the second data is 0:00 on January 2, 2024, and the timestamp of the third data is 0:00 on January 3, 2024, and so on, and the time interval of these data is 1 day; for another example: the timestamp of the first data filtered out by the timestamp is 0:00 on January 1, 2024, the timestamp of the second data is 8:00 on January 1, 2024, and the timestamp of the third data is 16:00 on January 1, 2024, and so on, and the time interval of these data is 8 hours. It can be understood that by recording the timestamp and the micro-water sample data with the same time interval, a time-based data change law can be obtained, and a time-based micro-water data change law diagram can also be generated according to the pre-processed micro-water sample data and the time-based data change law.

[0072] S104: according to the pre-processed trace water sample data and the data variation law, using the extreme gradient lifting model to obtain the prediction result of the trace water data;

[0073] It should be noted that the extreme gradient boosting model is an algorithm based on the gradient boosting decision tree. It implements the gradient boosting tree model internally and makes many optimizations to the algorithm in the model, achieving high accuracy while maintaining extremely fast speed.

[0074] In an embodiment of the present application, establishing an extreme gradient boosting model includes initializing the parameters of the extreme gradient boosting model according to business requirements and data characteristics; inputting the preprocessed trace water sample data and data change rules into the extreme gradient boosting model, and assigning weights to the preprocessed trace water sample data.

[0075] In a possible embodiment, the extreme gradient boosting model can accept various data as input; for example, when predicting the trend of micro-water data in a transformer, continuous variables such as the oil temperature of the transformer (because the oil temperature affects the solubility of micro-water), operating time, load rate, etc. can be used as input features. These numerical features can provide the model with rich information to establish the relationship between input and output. In this application, the pre-processed micro-water sample data and the law of data change are input.

[0076] In an embodiment of the present application, a weight is assigned to each trace water sample data, which is very useful in some cases, such as when there is an imbalance problem in the data; for example, if when collecting transformer trace water data, the data collected in the normal state of the transformer is far more than the data collected in the abnormal state of the transformer, in order to make the model pay more attention to the data in the abnormal state, a higher weight can be assigned to the samples in the abnormal state, so that the model will pay more attention to these samples during the training process, so as to better learn the patterns of abnormal situations.

[0077] In an embodiment of the present application, the preprocessed micro-water sample data and data change rules are input into the extreme gradient boosting model, and a series of algorithms are used to obtain the prediction results of the micro-water data. The prediction results include at least the micro-water prediction data for a period of time in the future. It can be understood that after obtaining the prediction results, a micro-water data prediction graph can be generated based on the prediction results.

[0078] Preferably, the pre-processed trace water sample data and data variation rules are input into the extreme gradient boosting model, and weights are assigned to the pre-processed trace water sample data.

[0079] Preferably, the pre-processed trace water sample data and data variation law are divided into a training set and a test set in the extreme gradient boosting model according to a first preset ratio; part of the trace water sample data and data variation law are selected from the training set according to a second preset ratio as a sampling set; the extreme gradient boosting model is trained through the training set, and the trained extreme gradient boosting model is used for evaluation of the test set; a number of decision trees are constructed based on the training set, the sample set and the test set, and a number of prediction values ​​are output through the decision trees; the number of prediction values ​​are integrated through the extreme gradient boosting model, and the prediction result of the trace water data is output;

[0080] In the embodiment of the present application, the training set is a data set used to train the model, which includes input features and corresponding labels. The model discovers patterns and relationships in the data by learning these data; while the test set is another part of data independent of the training set, which is used to evaluate the generalization ability of the model. The test set should contain data that does not appear in the training set;

[0081] In the embodiment of the present application, the first preset ratio is the ratio of dividing the sample data into a training set and a test set. For example, the first preset ratio can be set to 8 to 2.

[0082] In the embodiment of the present application, the sampling set refers to a part of the data set randomly selected from the training set when constructing each tree, including sample sampling, i.e., a part of the micro-water sample data selected from the training set, and feature sampling, i.e., the corresponding sample features extracted from the data variation law;

[0083] In the embodiment of the present application, the second preset ratio is to randomly extract a certain ratio (for example, 70%) of sample data and sample features from the training set as a sampling set before each iteration of building the decision tree.

[0084] Specifically, the training set data is used to iteratively construct multiple decision trees, and each tree attempts to correct the prediction error of the previous tree. This process is called gradient boosting. After the extreme gradient boosting model is trained, the trained extreme gradient boosting model can be used to predict the test set data to obtain the prediction results of the test set. The prediction results are compared with the sample data of the test set. Various performance indicators are calculated, such as the mean square error and mean absolute error in regression tasks, and the accuracy and recall rate in classification tasks to evaluate the performance of the model on unseen data, so as to determine whether the model is overfitting or has good generalization ability.

[0085] In an embodiment of the present application, a decision tree runs through the training and prediction processes. During the training process, the decision tree starts to grow from the root node, and selects the best splitting features and splitting points by calculating the gain according to the data in the training set (or sampling set) and the objective function information, and gradually constructs the internal nodes of the decision tree; the nodes are continuously split until the stopping condition is met to form a complete decision tree structure, including leaf nodes, and the values ​​of the leaf nodes are updated according to the training set (or sampling set) data, so that the decision tree can make reasonable predictions for the training data; multiple decision trees are constructed in sequence through an iterative training process, and each decision tree learns the rules in the training data to a certain extent, and is constrained by hyperparameters during the construction process to avoid overfitting.

[0086] It should be noted that the specific way of outputting several prediction values ​​through several decision trees is as follows: when a new data sample (such as sample data in the test set) is input, each decision tree starts from the root node, and according to the characteristics of the sample and the splitting rules of its internal nodes, the sample is gradually guided to a leaf node, and each leaf node of the decision tree will output a prediction value.

[0087] In an embodiment of the present application, the prediction results of all decision trees are integrated (such as weighted summation or voting) to obtain the prediction results of the extreme gradient boosting model for the micro-water data. It can be understood that the integration method improves the generalization ability and prediction accuracy of the model by combining multiple prediction results.

[0088] Preferably, real-time temperature information, real-time operating parameter information and real-time micro-water data of the transformer are detected; the correlation between the real-time temperature information and the real-time micro-water data is analyzed; the relationship between the real-time operating parameter information and the real-time micro-water data is analyzed; based on the correlation between the real-time temperature information and the real-time micro-water data, and the relationship between the real-time operating parameter information and the real-time micro-water data, the prediction result is optimized;

[0089] It should be noted that temperature has a great influence on the existence form and content of trace water in transformer oil. Generally speaking, when the temperature rises, the solubility of water in the oil increases, and the trace water content may rise; when the temperature decreases, the solubility of water decreases, and the trace water content may decrease. Therefore, it is necessary to collect real-time temperature information during the operation of the transformer and analyze the correlation between temperature and trace water content.

[0090] It should also be noted that the operating state of the transformer will also affect the generation and accumulation of micro-water. For example, load changes, partial discharge, insulation aging, etc. of the transformer may lead to changes in micro-water content. Monitoring the operating parameters of the transformer, such as load current, voltage, partial discharge, etc., and analyzing the relationship between these parameters and micro-water content can help predict the trend of micro-water data. If the transformer is in a high-load operation state for a long time, it may accelerate the aging of the insulation material, thereby generating more micro-water.

[0091] In an embodiment of the present application, based on the correlation between real-time temperature information and real-time micro-water data, as well as the relationship between real-time operating parameter information and real-time micro-water data, inappropriate or unreasonable prediction data in the prediction results can be found. For example, in the next 6 hours, the transformer temperature will increase due to the decrease in heat dissipation capacity. The increase in transformer temperature will usually cause the micro-water data to increase, but the prediction data for the next 6 hours in the prediction results shows a downward trend. In this way, unreasonable prediction data in the prediction results are found, and these unreasonable prediction data can be optimized.

[0092] It should be noted that a transformer micro-water data prediction method is provided, which obtains a number of micro-water sample data; pre-processes the micro-water sample data; extracts the time features in the pre-processed micro-water sample data, and obtains the data change law based on the time features, and the time features at least include timestamps and time intervals; and obtains the prediction results of the micro-water data based on the extreme gradient lifting model according to the pre-processed micro-water sample data and the data change law. By pre-processing the micro-water sample data, the time features therein are obtained, and the prediction results of the micro-water data are obtained based on the extreme gradient lifting model, thereby improving the accuracy of the prediction.

[0093] The above is a schematic scheme of a transformer micro-water data prediction method of this embodiment. It should be noted that the technical scheme of the transformer micro-water data prediction system and the technical scheme of the transformer micro-water data prediction method described above belong to the same concept, and the details of the technical scheme of the transformer micro-water data prediction system not described in detail in this embodiment can all be referred to the description of the technical scheme of the transformer micro-water data prediction method described above.

[0094] The transformer micro-water data prediction system in this embodiment includes:

[0095] A data acquisition module, used for acquiring micro-water sample data;

[0096] A preprocessing module, used for preprocessing the micro-water sample data;

[0097] A feature extraction module is used to extract the time features in the pre-processed micro-water sample data and obtain the data change law based on the time features;

[0098] The prediction module is used to obtain the prediction results of the micro-water data by using the extreme gradient boosting model according to the pre-processed micro-water sample data and the data change law.

[0099] This embodiment further provides a computing device, which is applicable to transformer micro-water data prediction, and includes:

[0100] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the transformer micro-water data prediction method proposed in the above embodiment.

[0101] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for predicting transformer micro-water data as proposed in the above embodiment is implemented.

[0102] The storage medium proposed in this embodiment and the method for realizing transformer micro-water data prediction proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0103] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

Claims

1. A transformer micro-water data prediction method, characterized in that: include: Acquire trace water sample data, and pre-process the trace water sample data; Extracting time features from the preprocessed micro-water sample data, and obtaining data variation rules based on the time features; According to the pre-processed trace water sample data and the data variation law, the prediction result of the trace water data is obtained by using the extreme gradient lifting model.

2. The transformer micro-water data prediction method according to claim 1, characterized in that: The prediction results of micro-water data obtained using the extreme gradient lifting model include: The pre-processed trace water sample data and the data variation rule are input into the extreme gradient boosting model, and weights are assigned to the pre-processed trace water sample data.

3. The transformer micro-water data prediction method according to claim 1 or 2, characterized in that: Also includes, Dividing the preprocessed trace water sample data and the data variation law into a training set and a test set in the extreme gradient boosting model according to a first preset ratio; Selecting part of the trace water sample data and the data variation law from the training set according to a second preset ratio as a sampling set; The extreme gradient boosting model is trained by the training set, and the trained extreme gradient boosting model is used for evaluating the test set; Constructing a plurality of decision trees based on the training set, the sampling set and the test set, and outputting a plurality of prediction values ​​through the plurality of decision trees; The plurality of predicted values ​​are integrated through the extreme gradient boosting model to output a prediction result of the micro-water data.

4. The transformer micro-water data prediction method according to claim 3, characterized in that: The prediction results include: Detect the real-time temperature information, real-time operating parameter information and real-time micro-water data of the transformer; Analyzing the correlation between the real-time temperature information and the real-time micro-water data; Analyzing the relationship between the real-time operating parameter information and the real-time micro-water data; Based on the correlation between the real-time temperature information and the real-time trace water data, and the relationship between the real-time operating parameter information and the real-time trace water data, the prediction result is optimized.

5. The transformer micro-water data prediction method according to claim 4, characterized in that: Extracting the time features from the pre-processed micro-water sample data, and obtaining the data change rules based on the time features include: Recording the timestamp in the pre-processed micro-water sample data; Acquire the time interval between the pre-processed micro-water sample data according to the timestamp; A data variation rule is obtained based on the timestamp and the time interval.

6. The transformer micro-water data prediction method according to claim 5, characterized in that: Also includes, Generate a trace water data variation law graph according to the pre-processed trace water sample data and the data variation law; After the step of obtaining the prediction result of the micro-water data based on the extreme gradient lifting model, the method further includes: A micro-water data prediction graph is generated according to the prediction results.

7. The transformer micro-water data prediction method according to claim 1, characterized in that: Preprocessing the micro-water sample data includes: Testing the micro-water sample data; If there are duplicate values ​​in the micro-water sample data, the duplicate values ​​are deleted; If there are missing values ​​in the micro-water sample data, the missing values ​​are deleted, or the mean of the values ​​before and after the missing values ​​is taken to fill the missing values; If there is an abnormal value in the micro-water sample data, the abnormal value is deleted, or the average of the values ​​before and after the abnormal value is taken to replace the abnormal value.

8. A system for transformer micro-water data prediction, characterized in that: include, A data acquisition module, used for acquiring micro-water sample data; A preprocessing module, used for preprocessing the micro-water sample data; A feature extraction module is used to extract the time features in the pre-processed micro-water sample data and obtain the data change law based on the time features; The prediction module is used to obtain the prediction result of the trace water data by using the extreme gradient lifting model according to the pre-processed trace water sample data and the data change law.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the transformer micro-water data prediction method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the steps of the transformer micro-water data prediction method according to any one of claims 1 to 7.

Images