Intelligent power transformer data analysis method and system, terminal and storage medium
Through the intelligent power transformer data analysis method, the problem of inefficiency of traditional monitoring methods is solved, real-time and accurate state evaluation and fault warning are realized, operation and maintenance efficiency and energy efficiency are improved, and by building Bayesian network model and gradient descent algorithm, Optimized data processing and fault warning capabilities.
Patent Information
- Application Number
- CN202410975853.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-12
AI Technical Summary
Traditional power transformer monitoring methods are inefficient and difficult to detect and deal with potential problems in a timely manner. Existing data processing methods are difficult to cope with the processing needs of massive data, resulting in limited data processing efficiency and accuracy and lack in-depth fault warning capabilities.
It provides an intelligent power transformer data analysis method, including obtaining historical and real-time monitoring data, performing data cleaning and preprocessing, extracting key features, building analysis models, performing real-time analysis and fault warning, and optimizing the model based on feedback. Specific methods include feature calculation, standardization processing, dimensionality reduction processing, construction of Bayesian network models, adjust model parameters using gradient descent algorithm, generate detailed analysis reports, and design feedback mechanism dynamic adjustment model.
Real-time and accurate status evaluation and fault warning are realized, operation and maintenance efficiency is improved, downtime and maintenance time is reduced, operation and maintenance costs are reduced, and transformer operation and energy efficiency is improved through optimization suggestions.
Smart Images

Figure CN118939941A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of power system data management, and in particular relates to an intelligent power transformer data analysis method, system, terminal and storage medium. Background Art
[0002] With the rapid development of the power industry, power transformers, as core equipment in the power grid, are crucial to the safe and stable operation of power transformers to ensure the continuity and reliability of power supply. However, power transformers are affected by many factors during operation, such as load changes, environmental factors, material aging, etc., which may cause transformer performance degradation or failure. Traditional power transformer monitoring methods mainly rely on manual inspections and regular testing, which is not only inefficient, but also difficult to detect and deal with potential problems in a timely manner.
[0003] In recent years, with the rapid development of sensor technology, Internet of Things technology and big data technology, the monitoring method of power transformers is gradually changing from manual to intelligent. By installing various sensors, key parameters such as transformer voltage, current, temperature, oil level and insulation resistance can be collected in real time, providing rich data support for transformer status assessment. However, in the face of massive monitoring data, how to efficiently process and analyze these data and extract valuable information has become a problem that needs to be solved.
[0004] Traditional data processing methods are unable to cope with the processing needs of massive data, resulting in limited efficiency and accuracy of data processing. Existing analysis methods can only provide simple status assessment results, lack in-depth fault warning capabilities, and cannot provide comprehensive guidance for transformer maintenance management. Summary of the invention
[0005] In view of the above-mentioned deficiencies in the prior art, the present invention provides an intelligent power transformer data analysis method, system, terminal and storage medium to solve the above-mentioned technical problems.
[0006] In a first aspect, the present invention provides an intelligent power transformer data analysis method, comprising:
[0007] Obtain historical and real-time monitoring data of power transformers;
[0008] Clean and preprocess the collected data to remove noise, outliers and redundant data;
[0009] Extract key features that can reflect the operating status and performance of the power transformer from the preprocessed data;
[0010] Based on the extracted key features, a transformer analysis model is constructed;
[0011] Use the built transformer analysis model to analyze and predict the real-time monitoring data of power transformers, including operation status evaluation and fault warning;
[0012] Generate a detailed power transformer data analysis report based on the analysis results;
[0013] The generated analysis report is pushed to the staff, and the transformer analysis model is optimized based on the feedback.
[0014] A further improvement of the technical solution is to extract key features that can reflect the operating status and performance of the power transformer from the preprocessed data, and the specific method includes:
[0015] Based on the operating principles of power transformers, determine key characteristics including but not limited to insulation resistance, oil temperature, winding temperature, and load current;
[0016] Obtain monitoring data of power transformers and perform feature calculations;
[0017] Standardize or normalize the features to scale the feature values to a preset range;
[0018] Check the number of features after standardization / normalization to determine whether dimensionality reduction is needed;
[0019] If so, the feature dimension is reduced by principal component analysis or linear discriminant analysis, and a preset feature combination is extracted as the key feature;
[0020] Verify whether the extracted key features effectively reflect the operating status and performance of the power transformer, and adjust and optimize the feature extraction process based on the verification results.
[0021] A further improvement of the technical solution is to construct a transformer analysis model based on the extracted key features, and the method specifically includes:
[0022] Divide the extracted key features into training data set, verification data set and test data set;
[0023] Select the initial analysis model based on the analysis requirements;
[0024] The initial analysis model is trained using the training data set, and the model parameters are adjusted through the gradient descent algorithm to minimize the loss function. During the training process, the analysis model in training is verified using the validation data set or the test data set until a transformer analysis model capable of analyzing and predicting the real-time monitoring data of the power transformer is obtained.
[0025] A further improvement of this technical solution is that the loss function of the initial analysis model is:
[0026]
[0027] Where N is the number of samples, M is the total number of categories, and y ic is an indicator variable indicating whether the i-th sample belongs to the c-th class, p ic is the probability that the model predicts that the i-th sample belongs to the c-th class, w c is the weight of the cth class.
[0028] A further improvement of the technical solution is that the formula of the gradient descent algorithm includes:
[0029]
[0030] Among them, m t is the first-order moment estimate; v t is the second-order moment estimate; β1 and β2 are attenuation factors; represents the gradient with respect to the variable θ; θ t represents the parameter vector of the model at time step t; θ t+1 represents the parameter vector of the model at time step t; m t+1 represents the first-order moment estimate for the next time step; v t+1 represents the second-order moment estimate for the next time step; is the corrected first-order moment estimate; is the corrected second-order moment estimate; It represents the (t+1)th power of the attenuation factor β1. As the number of iterations increases, the value will gradually decrease. represents the (t+1)th power of the attenuation factor β2, which will gradually decrease as the number of iterations increases; α is the learning rate, which controls the amplitude of each parameter update; ε is a small constant used to avoid division by zero.
[0031] A further improvement of the technical solution is that the step of generating the analysis report also includes quantitative evaluation of the energy efficiency of the power transformer and proposing optimization suggestions for energy saving and consumption reduction.
[0032] A further improvement of the technical solution is that the transformer analysis model also includes a feedback mechanism for dynamically adjusting and optimizing the model according to actual operating data and feedback results.
[0033] In a second aspect, the present invention provides an intelligent power transformer data analysis system, comprising:
[0034] Data acquisition module, used to obtain historical monitoring data and real-time monitoring data of power transformers;
[0035] Data preprocessing module, used to clean and preprocess the collected data to remove noise, outliers and redundant data;
[0036] A feature extraction module is used to extract key features that can reflect the operating status and performance of the power transformer from the preprocessed data;
[0037] An analysis model building module is used to build a transformer analysis model based on the extracted key features;
[0038] The data analysis and prediction module is used to analyze and predict the real-time monitoring data of power transformers using the constructed transformer analysis model, including operation status evaluation and fault warning;
[0039] Report generation module, used to generate detailed power transformer data analysis report based on analysis results;
[0040] The report push and feedback module is used to push the generated analysis report to the staff and optimize the transformer analysis model based on the feedback.
[0041] In a third aspect, the present invention provides a terminal, comprising:
[0042] processor, memory, wherein:
[0043] The memory is used to store computer programs.
[0044] The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.
[0045] In a fourth aspect, the present invention provides a computer storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the methods described in the above aspects.
[0046] The beneficial effects of the present invention are:
[0047] Real-time and accurate status assessment: This method can instantly reflect the operating status of the transformer by collecting and processing multi-dimensional data of the power transformer in real time (such as voltage, current, temperature, oil level, insulation resistance, etc.). After data cleaning and preprocessing, the extracted key features ensure the accuracy and reliability of the status assessment, allowing staff to quickly understand the health status of the transformer.
[0048] Early warning and fault prevention: Based on the constructed analysis model, this method can deeply explore the potential patterns in the data and realize early warning of faults. Through the analysis of real-time monitoring data, once an abnormal trend is found or the warning threshold is about to be reached, fault warning information is immediately generated, providing maintenance personnel with sufficient time to intervene, effectively avoiding major faults and reducing power outage losses.
[0049] Optimization suggestions: In addition to status assessment and fault warning, this method can evaluate the operation level of transformers through comprehensive analysis of transformer operation data and put forward targeted optimization suggestions. These suggestions will help improve the operation efficiency of transformers, reduce energy consumption costs, and promote the green and sustainable development of the power industry.
[0050] Improve operation and maintenance efficiency and reduce costs: Intelligent data analysis methods replace traditional manual inspections and regular testing modes, greatly reducing manpower input and improving operation and maintenance efficiency. At the same time, since potential problems can be discovered and handled in a timely manner, downtime caused by failures can be avoided, further reducing operation and maintenance costs.
[0051] Continuous optimization and self-improvement: This method also designs a model optimization mechanism that can continuously adjust and improve the analysis model based on the feedback from the staff. This self-learning and optimization ability enables the data analysis method to keep pace with the development of power transformer technology and always maintain efficient and accurate performance.
[0052] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0054] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.
[0055] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.
[0056] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention.
[0057] 210 is a data collection module, 220 is a data preprocessing module, 230 is a feature extraction module, 240 is an analysis model building module, 250 is a data analysis and prediction module, 260 is a report generation module, and 270 is a report push and feedback module. DETAILED DESCRIPTION
[0058] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.
[0060] The intelligent power transformer data analysis method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the intelligent power transformer data analysis system runs in the computer device.
[0061] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be an intelligent power transformer data analysis system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.
[0062] like Figure 1 As shown, the method includes:
[0063] Step 110, obtaining historical monitoring data and real-time monitoring data of the power transformer;
[0064] Step 120, cleaning and preprocessing the collected data to remove noise, outliers and redundant data;
[0065] Step 130, extracting key features that can reflect the operating status and performance of the power transformer from the preprocessed data;
[0066] Step 140, constructing a transformer analysis model based on the extracted key features;
[0067] Step 150, using the constructed transformer analysis model to analyze and predict the real-time monitoring data of the power transformer, including operating status evaluation and fault warning;
[0068] Step 160, generating a detailed power transformer data analysis report based on the analysis results, the report content including the operation status assessment results, fault warning information and optimization suggestions;
[0069] Step 170: Push the generated analysis report to the staff, and optimize the transformer analysis model based on the feedback.
[0070] To facilitate understanding of the present invention, the intelligent power transformer data analysis method provided by the present invention is further described below based on the principle of the intelligent power transformer data analysis method of the present invention and in combination with the process of analyzing the intelligent power transformer data in the embodiment.
[0071] Specifically, the intelligent power transformer data analysis method includes:
[0072] The collected data is cleaned and preprocessed to remove noise, outliers and redundant data. The specific steps include:
[0073] S121, performing noise filtering on the collected data to reduce random errors in the data;
[0074] S122. Use statistical methods to identify and remove outliers to ensure data accuracy;
[0075] S123. Remove redundant data through data compression or dimensionality reduction technology to improve data processing efficiency.
[0076] In addition, key features that can reflect the operating status and performance of the power transformer are extracted from the preprocessed data. The specific methods include:
[0077] S131. Based on the operating principle of the power transformer, determine key characteristics, including but not limited to insulation resistance, oil temperature, winding temperature and load current;
[0078] S132, obtaining monitoring data of the power transformer and performing characteristic calculation;
[0079] S133, standardize or normalize the feature, and scale the feature value to a preset range; such as between 0 and 1, or make its mean 0 and standard deviation 1;
[0080] S134, check the number of features after standardization / normalization processing, and determine whether dimensionality reduction processing is required; if so, go to S135;
[0081] S135, reducing the dimension of the features by a principal component analysis method or a linear discriminant analysis method, and extracting a preset feature combination as a key feature;
[0082] S136. Verify whether the extracted key features effectively reflect the operating status and performance of the power transformer, and adjust and optimize the feature extraction process based on the verification results.
[0083] Specifically, insulation resistance is an important indicator for measuring the insulation performance of transformers. It is usually measured by an insulation resistance tester when the transformer is out of service. However, in real-time monitoring, it can be indirectly evaluated by analyzing the changing trend of historical insulation resistance data. Oil temperature and winding temperature are selected as key features because these two parameters directly reflect the thermal state of the transformer and are crucial for evaluating its operating stability and preventing overheating failures. If necessary, the temperature change rate can be calculated, such as the oil temperature change per minute (or the maximum winding temperature change per hour, etc.) to capture the dynamic trend of temperature changes.
[0084] Secondly, based on the extracted key features, a transformer analysis model is constructed. The specific method includes:
[0085] S141, dividing the extracted key features into a training data set, a verification data set, and a test data set;
[0086] S142, selecting an initial analysis model according to analysis requirements;
[0087] S143. Use the training data set to train the initial analysis model, and adjust the model parameters through the gradient descent algorithm to minimize the loss function; during the training process, use the verification data set or the test data set to verify the analysis model in training until a transformer analysis model capable of analyzing and predicting the real-time monitoring data of the power transformer is obtained.
[0088] First, the Bayesian network model is selected as the initial analysis model. The nodes in the Bayesian network are defined according to the key features. For transformer fault monitoring, the nodes can include various operating parameters, such as oil level, group temperature, voltage, current, as well as insulation resistance and load current. Based on expert knowledge and historical data, the directed edges and conditional probability tables (CPTs) between nodes are determined. These edges represent the dependencies between variables, and the CPT defines the probability distribution of child nodes given the state of the parent node. After that, the Bayesian network model is trained using the training data set.
[0089] In the Bayesian network for transformer fault monitoring, we can define the following nodes and directed edges between them: Oil temperature (node A): represents the temperature of the transformer oil, winding temperature (node B): represents the temperature of the transformer winding, load current (node C): represents the current carried by the transformer; based on common sense in physics, we know that an increase in load current will cause an increase in winding temperature, and an increase in winding temperature may cause an increase in oil temperature (although oil temperature is also affected by other factors, such as the efficiency of the cooling system). Therefore, in this network, we can define a directed edge from load current (C) to winding temperature (B), and a directed edge from winding temperature (B) to oil temperature (A). This structure reflects the causal dependency between these variables.
[0090] Assume that we have a node about winding temperature (B), and its parent node is load current (C). We can create a CPT for the winding temperature (B) node based on historical data or expert evaluation, as shown in Table 1. Assume that load current (C) has three possible states: low, medium, and high, and winding temperature (B) also has three states: normal, high, and too high.
[0091] Table 1 is the conditional probability table between winding temperature and load current:
[0092]
[0093] This CPT represents the probability of the winding temperature being in different states under different conditions of a given load current. For example, when the load current is high, the winding temperature has a 50% probability of being too high, a 40% probability of being too high, and only a 10% probability of remaining normal. By constructing such directed edges and CPTs, the Bayesian network can capture the complex relationships between the operating parameters of the transformer and perform fault prediction and status assessment based on these relationships.
[0094] In addition, since the classification data of power transformers may be imbalanced, a weighted cross entropy loss function can be used to evaluate the model performance more fairly. Assume that there are C categories in total, among which category c has a small number of samples and can be given a larger weight w c The loss function is defined as follows:
[0095]
[0096] Where N is the number of samples, M is the total number of categories, and y ic is an indicator variable indicating whether the i-th sample belongs to the c-th class (if so, y ic =1; otherwise, y ic =0), p ic is the probability that the model predicts that the i-th sample belongs to the c-th class, w c is the weight of the cth class.
[0097] The Adam optimizer is chosen to adjust the model parameters because it can automatically adjust the learning rate and usually converges faster than the basic gradient descent method. The formula for the gradient descent algorithm corresponding to the Adam optimizer includes:
[0098]
[0099] Among them, m t is the first-order moment estimate, which tracks the direction of the gradient and is used to adjust the direction of parameter update; tis the second-order moment estimate, which is used to measure the change in the size of the gradient and helps to adjust the scale of the learning rate; β1 is the attenuation factor of the first-order moment, which is usually close to but less than 1 (for example, 0.9), and controls the influence of the past gradient on the current estimate; β2 is the attenuation factor of the second-order moment, which is also close to but less than 1 (for example, 0.999), and determines the speed at which the historical gradient square value is forgotten in the current estimate; represents the gradient with respect to the variable θ; θ t represents the parameter vector of the model at time step t; θ t+1 represents the parameter vector of the model at time step t; m t+1 represents the first-order moment estimate for the next time step; v t+1 represents the second-order moment estimate for the next time step; is the corrected first-order moment estimate; is the corrected second-order moment estimate; Represents the attenuation factor β1 to the (t+1)th power. As the number of iterations increases, this value will gradually decrease, which means that the gradient effect of the early iterations will decrease exponentially; represents the attenuation factor β2 to the (t+1)th power. As the number of iterations increases, the value will gradually decrease. α is the learning rate, which controls the amplitude of each parameter update. ε is a constant with a small value, such as 10 -8 , for numerical stability, to prevent the denominator from being zero, especially in v t When close to 0, avoid division by zero errors.
[0100] In addition, the steps of generating the analysis report also include quantitative evaluation of the energy efficiency of the power transformer and making optimization suggestions for energy saving and consumption reduction.
[0101] Finally, the transformer analysis model also includes a feedback mechanism to dynamically adjust and optimize the model based on actual operating data and feedback results.
[0102] In some embodiments, the intelligent power transformer data analysis system 200 may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the intelligent power transformer data analysis system 200 may be stored in a memory of a computer device and executed by at least one processor to execute (see Figure 1 Description) Function of intelligent power transformer data analysis.
[0103] In this embodiment, the intelligent power transformer data analysis system 200 can be divided into multiple functional modules according to the functions it performs, such as Figure 2As shown. The functional modules may include: a data acquisition module 210, a data preprocessing module 220, a feature extraction module 230, an analysis model building module 240, a data analysis and prediction module 250, a report generation module 260 and a report push and feedback module 270. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.
[0104] Among them, the data acquisition module is used to obtain the historical monitoring data and real-time monitoring data of the power transformer; the data preprocessing module is used to clean and preprocess the collected data to remove noise, outliers and redundant data; the feature extraction module is used to extract key features that can reflect the operating status and performance of the power transformer from the preprocessed data; the analysis model construction module is used to build a transformer analysis model based on the extracted key features; the data analysis and prediction module is used to use the constructed transformer analysis model to analyze and predict the real-time monitoring data of the power transformer, including operating status evaluation and fault warning; the report generation module is used to generate a detailed power transformer data analysis report based on the analysis results; the report push and feedback module is used to push the generated analysis report to the staff and optimize the transformer analysis model based on the feedback.
[0105] Figure 3 The present invention provides a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the intelligent power transformer data analysis method provided in an embodiment of the present invention.
[0106] The terminal 300 may include: a processor 310, a memory 320 and a communication module 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.
[0107] The memory 320 can be used to store the execution instructions of the processor 310, and the memory 320 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 can perform some or all of the steps in the following method embodiments.
[0108] The processor 310 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of a plurality of packaged ICs with the same or different functions. For example, the processor 310 can include only a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.
[0109] The communication module 330 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.
[0110] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).
[0111] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention.
[0112] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.
[0113] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.
[0114] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0115] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0116] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.
Claims
1. An intelligent power transformer data analysis method, characterized in that: include: Obtain historical and real-time monitoring data of power transformers; Clean and preprocess the collected data to remove noise, outliers and redundant data; Extract key features that can reflect the operating status and performance of the power transformer from the preprocessed data; Based on the extracted key features, a transformer analysis model is constructed; Use the built transformer analysis model to analyze and predict the real-time monitoring data of power transformers, including operation status evaluation and fault warning; Generate a detailed power transformer data analysis report based on the analysis results; The generated analysis report is pushed to the staff, and the transformer analysis model is optimized based on the feedback.
2. The intelligent power transformer data analysis method according to claim 1 is characterized in that: The key features that can reflect the operating status and performance of the power transformer are extracted from the preprocessed data. The specific methods include: Based on the operating principles of power transformers, determine key characteristics including but not limited to insulation resistance, oil temperature, winding temperature, and load current; Obtain monitoring data of power transformers and perform feature calculations; Standardize or normalize the features to scale the feature values to a preset range; Check the number of features after standardization / normalization to determine whether dimensionality reduction is needed; If so, the feature dimension is reduced by principal component analysis or linear discriminant analysis, and a preset feature combination is extracted as the key feature; Verify whether the extracted key features effectively reflect the operating status and performance of the power transformer, and adjust and optimize the feature extraction process based on the verification results.
3. The intelligent power transformer data analysis method according to claim 1 is characterized in that: Based on the extracted key features, a transformer analysis model is constructed, and the specific method includes: Divide the extracted key features into training data set, verification data set and test data set; Select the initial analysis model based on the analysis requirements; The initial analysis model is trained using the training data set, and the model parameters are adjusted through the gradient descent algorithm to minimize the loss function. During the training process, the analysis model in training is verified using the validation data set or the test data set until a transformer analysis model capable of analyzing and predicting the real-time monitoring data of the power transformer is obtained.
4. The intelligent power transformer data analysis method according to claim 3 is characterized in that: The loss function of the initial analysis model is: Where N is the number of samples, M is the total number of categories, and y ic is an indicator variable indicating whether the i-th sample belongs to the c-th class, p ic is the probability that the model predicts that the i-th sample belongs to the c-th class, w c is the weight of the cth class.
5. The intelligent power transformer data analysis method according to claim 4 is characterized in that: The formula for the gradient descent algorithm includes: Among them, m t is the first-order moment estimate; v t is the second-order moment estimate; β1 and β2 are attenuation factors; represents the gradient with respect to the variable θ; θ t represents the parameter vector of the model at time step t; θ t+1 represents the parameter vector of the model at time step t; m t+1 represents the first-order moment estimate for the next time step; v t+1 represents the second-order moment estimate for the next time step; is the corrected first-order moment estimate; is the corrected second-order moment estimate; It represents the (t+1)th power of the attenuation factor β1. As the number of iterations increases, the value will gradually decrease. It represents the (t+1)th power of the attenuation factor β2. As the number of iterations increases, the value will gradually decrease. α is the learning rate, which controls the amplitude of each parameter update. ε is a small constant used to avoid division by zero.
6. The intelligent power transformer data analysis method according to claim 1 is characterized in that: The steps of generating the analysis report also include quantitative evaluation of the energy efficiency of the power transformer and making optimization suggestions for energy saving and consumption reduction.
7. The intelligent power transformer data analysis method according to claim 1 is characterized in that: The transformer analysis model also includes a feedback mechanism for dynamically adjusting and optimizing the model based on actual operating data and feedback results.
8. An intelligent power transformer data analysis system, characterized in that: include: Data acquisition module, used to obtain historical monitoring data and real-time monitoring data of power transformers; Data preprocessing module, used to clean and preprocess the collected data to remove noise, outliers and redundant data; A feature extraction module is used to extract key features that can reflect the operating status and performance of the power transformer from the preprocessed data; An analysis model building module is used to build a transformer analysis model based on the extracted key features; The data analysis and prediction module is used to analyze and predict the real-time monitoring data of power transformers using the constructed transformer analysis model, including operation status evaluation and fault warning; Report generation module, used to generate detailed power transformer data analysis report based on analysis results; The report push and feedback module is used to push the generated analysis report to the staff and optimize the transformer analysis model based on the feedback.
9. A terminal, characterized in that: include: processor; A memory for storing execution instructions of the processor; The processor is configured to execute the method according to any one of claims 1 to 4.
10. A computer-readable storage medium storing a computer program, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
Transformer monitoring method and system based on immune mechanism, terminal and storage medium
CN117216495A
Power transformer fault early warning method
CN117741288A
Transformer fault prediction method and system considering uneven aging
CN118033266A
Substation communication network equipment monitoring and fault early warning method and system
CN118200118A
Wind turbine generator fault diagnosis method and system based on deep learning
CN118332442A
Cited By
Digital monitoring platform and monitoring method for axial flow fan, terminal and storage medium
CN119496802A
