Method and system for predicting economic life of transformer based on multi-dimensional data

Abstract

The invention discloses a transformer economic life prediction method and system based on multi-dimensional data, and particularly relates to the field of electrical engineering, and the method comprises the steps: S1, transformer data collection, S2, data preprocessing, S3, unknown factor analysis, S4, multi-dimensional data fusion, S5, transformer economic life prediction, S6, transformer life prediction model evaluation, and S7, transformer life prediction report output. According to the method for predicting the economic life of the transformer based on the multi-dimensional data, risk grade division is carried out on first operation data and an unknown factor analysis model is optimized, so that the problem that various uncertain factors affect a prediction result of the life of the transformer in a complex operation environment is solved; by effectively fusing multi-source heterogeneous data and constructing a quality evaluation mechanism of data fusion, the accuracy and reliability of fusion and analysis of multi-dimensional data are improved; the preprocessing operation of verification storage is performed on the first operation data, so that the data collection quality and availability are improved, and the data processing time and resources are reduced.

Description

Technical Field

[0001] The present invention relates to the field of electrical engineering technology, and more particularly to a method and system for predicting the economic life of a transformer based on multidimensional data. Background Art

[0002] With the rapid development of the power industry and the continuous advancement of smart grid construction, the health status assessment and life prediction of transformers, as key equipment in the power system, have become particularly important. The demand for electricity continues to grow, the scale of the power system continues to expand, and the operating environment of transformers has become more complex.

[0003] With the rapid development of information technology, technologies such as big data and the Internet of Things provide new means and methods for transformer condition monitoring and life prediction. The prediction of the economic life of transformers can timely discover potential fault hazards, and provide a more economical and efficient asset management method for transformer operation and maintenance decisions and future substation planning and transformation.

[0004] However, it still has some shortcomings in actual use. For example, model prediction requires a large amount of historical data as support, and the collection and processing of this data will consume a lot of time and resources; for transformers in complex operating environments, the existing prediction methods cannot consider the impact of various uncertain factors; the fusion and analysis of multidimensional data are subject to certain limitations. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a transformer economic life prediction method and system based on multi-dimensional data, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solutions: Transformer economic life prediction method based on multi-dimensional data, including: S1: Collecting transformer data: Real-time monitoring of the transformer operating status and collecting multi-dimensional operating data of the transformer through sensor technology and data acquisition equipment to obtain first operating data; S2: Preprocessing data: performing a preprocessing operation on the first operating data, where the preprocessing operation is used to obtain a first key operating feature set corresponding to the first operating data; S3: Analyze unknown factors: Obtain an unknown factor analysis model, and obtain a first feature evaluation corresponding to the first operating data using the first key operating feature set according to the unknown factor analysis model; S4: Fusion of multi-dimensional data: Use fusion algorithms to effectively integrate multi-source heterogeneous data and build a quality assessment mechanism for data fusion to obtain secondary operation data; S5 predicts the economic life of the transformer: obtaining a transformer life prediction model, applying a first feature evaluation corresponding to the first operating data and a second operating data to the transformer life prediction model to obtain a second key operating feature set corresponding to the second operating data; S6: Evaluate the transformer life prediction model: evaluate the prediction capability of the transformer life prediction model and the failure risk of the transformer to obtain a second feature evaluation corresponding to the second operating data; S7: Output transformer life prediction report: Based on the second key operating feature set corresponding to the second operating data and the second feature evaluation, the life prediction result is presented in the form of a prediction report; Preferably, the first operating data in S1 includes winding temperature, core temperature, thermal state of the transformer, humidity of the transformer's surrounding environment, mechanical vibration frequency of the transformer, mechanical vibration amplitude of the transformer, dissolved gas content, and partial discharge amount.

[0007] Preferably, obtaining the unknown factor analysis model in S3 specifically includes: performing a risk level classification operation on the first operating data according to the first key operating feature set to obtain an unknown risk level corresponding to the first operating data, where the unknown risk level is a severity level of a potential transformer fault reflected by the first operating data, and the unknown risk levels include low risk, medium risk, and high risk; In a preset economic life assessment database, an unknown factor analysis model corresponding to the unknown risk level is obtained. The preset economic life assessment database is used to store the corresponding relationship between the unknown risk level and the unknown factor analysis model.

[0008] Preferably, in S3, the unknown factor analysis model is obtained, and before obtaining the first feature evaluation corresponding to the first operation data through the first key operation feature set according to the unknown factor analysis model, the unknown factor analysis model is constructed, specifically including: Obtain a historical risk data set corresponding to the unknown risk level. The historical risk data set includes the operating data of the transformer at different risk levels and the corresponding fault conditions. Based on the historical risk data set, obtain the risk characteristic map corresponding to the unknown risk level; According to the risk characteristic map, the unknown factor analysis model is optimized to improve the accuracy of transformer economic life prediction.

[0009] Preferably, obtaining the second operating data in S4 specifically includes: The first feature evaluation is fused according to the fuzzy logic fusion algorithm to obtain the fuzzy set and membership function corresponding to the first feature evaluation. The membership function is a measure of the degree to which the key feature in the first feature evaluation belongs to a fuzzy set, and the value range is usually between 0 and 1 to obtain the second operating data.

[0010] Preferably, a quality assessment mechanism for data fusion is constructed in S4, specifically including: The quality assessment mechanism of data fusion includes: Compare with the standard reference data and calculate the error range of the fused data; Check whether the fused data covers all key features; Analyze the difference between data from different data sources after fusion; Evaluate the real-time requirements of the fused data.

[0011] Preferably, obtaining the second key operating feature set in S5 specifically includes: performing a predictive evaluation operation based on the first feature evaluation corresponding to the first operating data and the second operating data to obtain a transformer operating status level corresponding to the second operating data, where the transformer operating status level is the level of the current operating condition of the transformer, and the operating status levels include good, fair, and poor; A relationship model between the transformer operating status and life, namely a transformer life prediction model, is established to obtain the second key operating feature set.

[0012] Preferably, the prediction report in S7 includes maintenance recommendations, maintenance plan, current status of the transformer, remaining life, and risk level.

[0013] To achieve the above-mentioned object, the present invention provides the following technical solution: a transformer economic life prediction system based on multidimensional data, comprising a system operation database, a system central processing module and a user information terminal, and implementing the above-mentioned transformer economic life prediction method based on multidimensional data, including: Transformer data acquisition module: used to monitor the operating status of the transformer in real time and collect multi-dimensional operating data of the transformer through sensor technology and data acquisition equipment to obtain first operating data; A data preprocessing module is configured to perform a preprocessing operation on the first operation data, wherein the preprocessing operation is configured to obtain a first key operation feature set corresponding to the first operation data; Unknown factor analysis module: used to obtain an unknown factor analysis model, and obtain a first feature evaluation corresponding to the first operation data through the first key operation feature set according to the unknown factor analysis model; Multidimensional data fusion module: used to effectively integrate multi-source heterogeneous data using fusion algorithms and to obtain secondary operating data by building a data fusion quality assessment mechanism; Economic life prediction module: used to obtain a transformer life prediction model, and pass the first feature evaluation corresponding to the first operating data and the second operating data through the transformer life prediction model to obtain a second key operating feature set corresponding to the second operating data; Prediction model evaluation module: used to evaluate the prediction ability of the transformer life prediction model and the failure risk of the transformer to obtain a second feature evaluation corresponding to the second operating data; Prediction report output module: presents the life prediction result in the form of a prediction report based on the second key operation feature set and the second feature evaluation corresponding to the second operation data; The system operation database includes all data texts of the transformer economic life prediction system and collects the information texts output by each module in real time. The system central processing module is used for the information text instructions output by each module in the central control method. The user information terminal is an information output device for receiving the transformer economic life prediction system.

[0014] Preferably, obtaining the second feature evaluation corresponding to the second operating data in the prediction model evaluation module includes: comparing the second key operating feature set with the first key operating feature set, analyzing the generalization ability and fault risk of the transformer life prediction model under different operating conditions through mean square error, and combining the historical data stored in the database to measure the degree of deviation between the predicted value and the actual value of the transformer life prediction model to obtain the second feature evaluation corresponding to the second operating data.

[0015] The technical effects and advantages of the present invention are as follows: The present invention solves the problem of various uncertain factors affecting the prediction result of transformer life in a complex operating environment by dividing the first operating data into risk levels and optimizing the unknown factor analysis model; The present invention improves the accuracy and reliability of multi-dimensional data fusion and analysis by effectively fusing multi-source heterogeneous data and building a data fusion quality assessment mechanism; The present invention improves data collection quality and availability and reduces data processing time and resources by performing a pre-processing operation of verifying and storing the first operating data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A diagram showing the steps of the method of the present invention.

[0017] Figure 2 Flow chart of the method of the present invention.

[0018] Figure 3 Schematic diagram of the method structure of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0020] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular expressions "a", "an", "the", "said", "the", and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more of the listed items.

[0021] In the following, the terms "first," "second," and "third" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, a feature defined as "first," "second," and "third" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0022] As attached Figure 1 The transformer economic life prediction method based on multi-dimensional data shown includes S1: collecting transformer data, S2: preprocessing data, S3: analyzing unknown factors, S4: fusing multi-dimensional data, S5: predicting the transformer economic life, S6: evaluating the transformer life prediction model, and S7: outputting a transformer life prediction report.

[0023] S1: Collecting transformer data: Monitor the transformer operating status in real time and collect multi-dimensional operating data of the transformer through sensor technology and data acquisition equipment to obtain first operating data.

[0024] In a possible implementation, multiple sensors are provided for the target transformer to monitor multi-dimensional data of the transformer in real time. The types of sensors include but are not limited to: temperature sensors, humidity sensors, vibration sensors, gas sensors, and partial discharge sensors.

[0025] Specifically, the temperature sensor is used to measure temperature changes inside the transformer, including winding temperature, core temperature, and thermal state of the transformer; the humidity sensor is used to detect the humidity of the environment surrounding the transformer; the vibration sensor is used to capture the mechanical vibration signal of the transformer, including vibration frequency and amplitude; the gas sensor is used to detect the dissolved gas content in the oil; and the partial discharge sensor is used to detect partial discharge phenomena in the transformer.

[0026] It should be noted that excessive humidity affects the insulation performance of the transformer; different types of gases and changes in their content reflect different types of failure modes. Among them, an increase in hydrogen content indicates partial discharge in the transformer, and acetylene content indicates a serious overheating fault inside the transformer. Specifically, the first operating data evaluates the thermal stability of the transformer and determines whether the transformer has an overheating risk based on the winding temperature, the core temperature, and the thermal state of the transformer; determines the operating reliability of the transformer based on the humidity of the environment surrounding the transformer; determines whether the internal mechanical structure of the transformer is normal based on the mechanical vibration frequency and the mechanical vibration amplitude of the transformer; indicates different types of failure modes inside the transformer based on the dissolved gas content in the transformer; and determines whether local defects occur in the transformer insulation system based on the amount of partial discharge.

[0027] S2: Preprocessing data: performing a preprocessing operation on the first operating data, where the preprocessing operation is used to obtain a first key operating feature set corresponding to the first operating data.

[0028] Specifically, after obtaining the first operating data, the transformer economic life prediction system obtains key features corresponding to the first operating data, i.e., a first key operating feature set, through a preprocessing operation. The preprocessing steps are as follows: Data cleaning: Remove outliers and noise data from the first run data, and eliminate obvious erroneous data that appears during sensor acquisition; Data standardization: Normalization is used to unify data of different dimensions into the same dimension and range; Feature extraction: extract features from the first running data and convert them into more representative feature forms; In this embodiment, for temperature data, the temperature change rate, maximum temperature, and average temperature are extracted; for gas content data, the ratio relationship of different gases and gas growth rate are extracted; Feature selection: using a feature selection algorithm, extracting multiple key operating features from the preprocessed first operating data as a first key operating feature set; Specifically, feature selection algorithms include variance selection method, mutual information method, recursive feature elimination method, and decision tree-based feature selection; Verification and storage: Verify, store and index the first key operating feature set through data compression technology and distributed storage architecture.

[0029] S3: Analyze unknown factors: Obtain an unknown factor analysis model, and obtain a first feature evaluation corresponding to the first operation data through the first key operation feature set according to the unknown factor analysis model.

[0030] Specifically, the unknown factor analysis model is a pre-built learning model. By inputting the first key operating feature set into the unknown factor analysis model, the unknown factor analysis model obtains a first feature evaluation according to the first key operating feature set.

[0031] In a possible implementation, step S3 includes: performing a risk level classification operation on the first operating data according to the first key operating feature set to obtain an unknown risk level corresponding to the first operating data, where the unknown risk level is the severity level of the potential fault of the transformer reflected by the first operating data, and the unknown risk level includes low risk, medium risk and high risk; obtaining an unknown factor analysis model corresponding to the unknown risk level in a preset economic life assessment database, where the preset economic life assessment database is used to save the correspondence between the unknown risk level and the unknown factor analysis model.

[0032] Specifically, based on the temperature characteristics in the first key operating feature set, the absolute value of the temperature, the changing trend in different time periods, the correlation with other characteristics, and the performance under different operating environments are analyzed; the humidity characteristics in the first key operating feature set are used to evaluate the potential impact on the insulation performance of the transformer and the interaction with factors such as temperature; the vibration characteristics in the first key operating feature set are used to analyze the frequency, amplitude, and the relationship with the internal mechanical structure state of the transformer; the characteristics provided by the gas sensor and partial discharge sensor in the first key operating feature set are used to conduct in-depth research on the changes in different gas components and the relationship between the size of partial discharge and potential transformer faults.

[0033] In one possible implementation, step S3 further includes obtaining a historical risk data set corresponding to the unknown risk level, the historical risk data set including operating data of the transformer at different risk levels and corresponding fault conditions; obtaining a risk characteristic map corresponding to the unknown risk level based on the historical risk data set; and optimizing the unknown factor analysis model based on the risk characteristic map to improve the accuracy of the transformer economic life prediction; It should be noted that the unknown factor analysis model uses probability analysis and risk assessment to predict the impact of various uncertain factors on the life of the transformer in a complex operating environment, so as to obtain the first characteristic evaluation corresponding to the first operating data, reveal the current operating status of the transformer, and predict the future development trend of the transformer under the influence of different unknown factors.

[0034] S4: Fusion of multi-dimensional data: Use fusion algorithms to effectively integrate multi-source heterogeneous data, and build a quality assessment mechanism for data fusion to obtain second-level operating data.

[0035] In one possible implementation, step S4 includes: fusing the first feature evaluation according to a fuzzy logic fusion algorithm to obtain a fuzzy set and a membership function corresponding to the first feature evaluation, wherein the membership function is a measure of the degree to which the key feature in the first feature evaluation belongs to a fuzzy set, and the value range is usually between 0 and 1, to obtain the second operating data.

[0036] In this embodiment, for the temperature characteristic evaluation of the transformer, different temperature intervals are set as fuzzy sets; for a specific temperature value, its membership degree in the low temperature, medium temperature and high temperature intervals is determined by the membership function.

[0037] In a possible embodiment, step S4 also includes: converting multiple first key operating feature sets into a group of unrelated operating feature sets according to a principal component analysis fusion algorithm to extract the main features corresponding to any first key operating feature set, and performing principal component analysis on different types of data to fuse the operating feature sets to obtain second operating data that highlights the main trends and key features.

[0038] In a possible implementation, step S4 also includes: constructing a quality assessment mechanism for data fusion, the quality assessment mechanism for data fusion including: comparing with standard reference data to calculate the error range of the fused data; checking whether the fused data covers all key features; analyzing the difference values ​​of data from different data sources after fusion; and evaluating the real-time requirements of the fused data.

[0039] S5: Predicting the economic life of the transformer: obtaining a transformer life prediction model, and passing the first feature evaluation corresponding to the first operating data and the second operating data through the transformer life prediction model to obtain a second key operating feature set corresponding to the second operating data.

[0040] Specifically, the transformer life prediction model is a pre-built learning model. The first feature evaluation corresponding to the first operating data and the second operating data are input into the transformer life prediction model. The transformer life prediction model obtains the second key operating feature set based on the first operating data and the second operating data.

[0041] In one possible embodiment, step S5 includes: performing a predictive evaluation operation based on a first feature evaluation corresponding to the first operating data and the second operating data to obtain a transformer operating status level corresponding to the second operating data, where the transformer operating status level is the level of the transformer's current operating condition, and the operating status levels include good, general, and poor; establishing a relationship model between the transformer operating status and life, i.e., a transformer life prediction model, to obtain a second key operating feature set.

[0042] S6: Evaluate the transformer life prediction model: evaluate the prediction capability of the transformer life prediction model and the failure risk of the transformer to obtain a second feature evaluation corresponding to the second operating data.

[0043] In one possible implementation, step S6 includes: comparing the second key operating feature set with the first key operating feature set, analyzing the generalization ability and fault risk of the transformer life prediction model under different operating conditions through mean square error, and combining the historical data stored in the database to measure the degree of deviation between the predicted value and the actual value of the transformer life prediction model to obtain a second feature evaluation corresponding to the second operating data.

[0044] S7: Output transformer life prediction report: Based on the second key operating feature set and the second feature evaluation corresponding to the second operating data, the life prediction result is presented in the form of a prediction report.

[0045] In a possible implementation, the prediction report in step S7 includes maintenance recommendations, an overhaul plan, the current status of the transformer, the remaining lifespan, and the risk level.

[0046] As attached Figure 2 The transformer economic life prediction system based on multidimensional data shown includes a system operation database, a system central processing module and a user information terminal, and also includes: a transformer data acquisition module, a data preprocessing module, an unknown factor analysis module, a multidimensional data fusion module, an economic life prediction module, a prediction model evaluation module, and a prediction report output module.

[0047] Transformer data acquisition module: used to monitor the operating status of the transformer in real time and collect multi-dimensional operating data of the transformer through sensor technology and data acquisition equipment to obtain first operating data; A data preprocessing module is configured to perform a preprocessing operation on the first operation data, wherein the preprocessing operation is configured to obtain a first key operation feature set corresponding to the first operation data; Unknown factor analysis module: used to obtain an unknown factor analysis model, and obtain a first feature evaluation corresponding to the first operation data through the first key operation feature set according to the unknown factor analysis model; Multidimensional data fusion module: used to effectively integrate multi-source heterogeneous data using fusion algorithms and to obtain secondary operating data by building a data fusion quality assessment mechanism; Economic life prediction module: used to obtain a transformer life prediction model, and pass the first feature evaluation corresponding to the first operating data and the second operating data through the transformer life prediction model to obtain a second key operating feature set corresponding to the second operating data; Prediction model evaluation module: used to evaluate the prediction ability of the transformer life prediction model and the failure risk of the transformer to obtain a second feature evaluation corresponding to the second operating data; Prediction report output module: presents the life prediction result in the form of a prediction report based on the second key operation feature set and the second feature evaluation corresponding to the second operation data; The system operation database includes all data texts of the transformer economic life prediction system and collects the information texts output by each module in real time. The system central processing module is used for the information text instructions output by each module in the central control method. The user information terminal is an information output device for receiving the transformer economic life prediction system.

[0048] In this embodiment, obtaining the second feature evaluation corresponding to the second operating data in the prediction model evaluation module includes: comparing the second key operating feature set with the first key operating feature set, analyzing the generalization ability and fault risk of the transformer life prediction model under different operating conditions through mean square error, and combining the historical data stored in the database to measure the degree of deviation between the predicted value and the actual value of the transformer life prediction model to obtain the second feature evaluation corresponding to the second operating data.

[0049] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict. Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A transformer economic life prediction method based on multidimensional data, characterized in that: include: S1: Collecting transformer data: Real-time monitoring of the transformer operating status and collecting multi-dimensional operating data of the transformer through sensor technology and data acquisition equipment to obtain first operating data; S2: Preprocessing data: performing a preprocessing operation on the first operating data, where the preprocessing operation is used to obtain a first key operating feature set corresponding to the first operating data; S3: Analyze unknown factors: Obtain an unknown factor analysis model, and obtain a first feature evaluation corresponding to the first operating data using the first key operating feature set according to the unknown factor analysis model; S4: Fusion of multi-dimensional data: Use fusion algorithms to effectively integrate multi-source heterogeneous data and build a quality assessment mechanism for data fusion to obtain secondary operation data; S5 predicts the economic life of the transformer: obtaining a transformer life prediction model, applying a first feature evaluation corresponding to the first operating data and a second operating data to the transformer life prediction model to obtain a second key operating feature set corresponding to the second operating data; S6: Evaluate the transformer life prediction model: evaluate the prediction capability of the transformer life prediction model and the failure risk of the transformer to obtain a second feature evaluation corresponding to the second operating data; S7: Output transformer life prediction report: Based on the second key operating feature set and the second feature evaluation corresponding to the second operating data, the life prediction result is presented in the form of a prediction report.

2. The transformer economic life prediction method based on multidimensional data according to claim 1 is characterized in that: The first operating data in S1 includes winding temperature, core temperature, thermal state of the transformer, humidity of the transformer's surrounding environment, mechanical vibration frequency of the transformer, mechanical vibration amplitude of the transformer, dissolved gas content, and partial discharge amount.

3. The transformer economic life prediction method based on multidimensional data according to claim 1 is characterized in that: The unknown factor analysis model is obtained in S3, specifically including: performing a risk level classification operation on the first operating data according to the first key operating feature set to obtain an unknown risk level corresponding to the first operating data, where the unknown risk level is a severity level of a potential transformer fault reflected by the first operating data, and the unknown risk levels include low risk, medium risk, and high risk; In a preset economic life assessment database, an unknown factor analysis model corresponding to the unknown risk level is obtained. The preset economic life assessment database is used to store the corresponding relationship between the unknown risk level and the unknown factor analysis model.

4. The transformer economic life prediction method based on multidimensional data according to claim 3 is characterized in that: The unknown factor analysis model is obtained in S3, and before obtaining the first feature evaluation corresponding to the first operation data through the first key operation feature set based on the unknown factor analysis model, the unknown factor analysis model is constructed, specifically including: Obtain a historical risk data set corresponding to the unknown risk level. The historical risk data set includes the operating data of the transformer at different risk levels and the corresponding fault conditions. Based on the historical risk data set, obtain the risk characteristic map corresponding to the unknown risk level; According to the risk characteristic map, the unknown factor analysis model is optimized to improve the accuracy of transformer economic life prediction.

5. The transformer economic life prediction method based on multidimensional data according to claim 1 is characterized in that: The step S4 of acquiring the second operating data specifically includes: The first feature evaluation is fused according to the fuzzy logic fusion algorithm to obtain the fuzzy set and membership function corresponding to the first feature evaluation. The membership function is a measure of the degree to which the key feature in the first feature evaluation belongs to a fuzzy set, and the value range is usually between 0 and 1 to obtain the second operating data.

6. The transformer economic life prediction method based on multidimensional data according to claim 1 is characterized in that: The quality assessment mechanism of data fusion constructed in S4 specifically includes: The quality assessment mechanism of data fusion includes: Compare with the standard reference data and calculate the error range of the fused data; Check whether the fused data covers all key features; Analyze the difference between data from different data sources after fusion; Evaluate the real-time requirements of the fused data.

7. The transformer economic life prediction method based on multidimensional data according to claim 1 is characterized in that: The second key operation feature set is obtained in S5, specifically including: performing a predictive evaluation operation based on the first feature evaluation corresponding to the first operating data and the second operating data to obtain a transformer operating status level corresponding to the second operating data, where the transformer operating status level is the level of the current operating condition of the transformer, and the operating status levels include good, fair, and poor; A relationship model between the transformer operating status and life, namely a transformer life prediction model, is established to obtain the second key operating feature set.

8. The transformer economic life prediction method based on multidimensional data according to claim 1 is characterized in that: The prediction report in S7 includes maintenance recommendations, overhaul plans, the current status of the transformer, the remaining life, and the risk level.

9. A transformer economic life prediction system based on multidimensional data, comprising a system operation database, a system central processing module, and a user information terminal, wherein the transformer economic life prediction method based on multidimensional data according to any one of claims 1 to 8 is characterized in that: Also includes: Transformer data acquisition module: used to monitor the operating status of the transformer in real time and collect multi-dimensional operating data of the transformer through sensor technology and data acquisition equipment to obtain first operating data; A data preprocessing module is configured to perform a preprocessing operation on the first operation data, wherein the preprocessing operation is configured to obtain a first key operation feature set corresponding to the first operation data; Unknown factor analysis module: used to obtain an unknown factor analysis model, and obtain a first feature evaluation corresponding to the first operation data through the first key operation feature set according to the unknown factor analysis model; Multidimensional data fusion module: used to effectively integrate multi-source heterogeneous data using fusion algorithms and to obtain secondary operating data by building a data fusion quality assessment mechanism; Economic life prediction module: used to obtain a transformer life prediction model, and pass the first feature evaluation corresponding to the first operating data and the second operating data through the transformer life prediction model to obtain a second key operating feature set corresponding to the second operating data; Prediction model evaluation module: used to evaluate the prediction capability of the transformer life prediction model and the failure risk of the transformer to obtain a second feature evaluation corresponding to the second operating data; Prediction report output module: presents the life prediction result in the form of a prediction report based on the second key operation feature set and the second feature evaluation corresponding to the second operation data; The system operation database includes all data texts of the transformer economic life prediction system and collects the information texts output by each module in real time. The system central processing module is used for the information text instructions output by each module in the central control method. The user information terminal is an information output device for receiving the transformer economic life prediction system.

10. The transformer economic life prediction system based on multidimensional data according to claim 9, characterized in that: Obtaining a second feature evaluation corresponding to the second operating data in the prediction model evaluation module includes: comparing the second set of key operating characteristics with the first set of key operating characteristics; The generalization ability and fault risk of the transformer life prediction model under different operating conditions are analyzed by mean square error and combined with the historical data stored in the database to measure the degree of deviation between the predicted value and the actual value of the transformer life prediction model to obtain the second feature evaluation corresponding to the second operating data.

Images