Power transmission and transformation project data comprehensive analysis and treatment method and system

Abstract

The invention relates to the technical field of data analysis, in particular to a comprehensive analysis and treatment method and system for transmission and transformation project data, and the method comprises the following steps: collecting multi-source transmission and transformation project data, including voltage, current, frequency and environment data collected from a sensor network, a historical record and a real-time monitoring unit; preprocessing the collected data, including data cleaning and format unification, and identifying key performance indexes; performing environmental factor analysis, and analyzing how different environmental conditions influence the performance of the power transmission and transformation equipment so as to judge the influence on the data of the power transmission and transformation project; and performing data feature analysis by applying a machine learning algorithm, and mining a potential fault mode and a performance degradation trend. The method disclosed by the invention reveals how the environmental change affects the operation of the equipment, helps to identify the equipment or components more sensitive to the specific environmental conditions, not only helps to discover potential risk points in advance, but also can optimize the design and operation strategies of the equipment for the specific environmental conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for comprehensive analysis and management of power transmission and transformation engineering data. Background Art

[0002] In the field of modern power transmission and transformation engineering, efficient and stable operation of equipment and systems is the key to ensuring the reliability of power supply. With the development of technology, more and more data are collected from various links of the power transmission and transformation system, including equipment performance data, environmental monitoring data and real-time operation data. These data contain rich information and are of great value for optimizing equipment performance, predicting and preventing failures.

[0003] However, faced with such a large and complex data set, how to effectively analyze and process the data has become a major challenge. Traditional data processing methods can often only process a single data source or perform simple data analysis, and it is difficult to cope with the comprehensive analysis and in-depth mining of multi-source data. In addition, there is still limited understanding of how environmental factors (such as temperature, humidity, and geographic location) affect equipment performance and stability. These limitations have led to insufficient identification and prevention of potential problems in the transmission and transformation system, which may increase the system's operating risks and maintenance costs.

[0004] Therefore, there is an urgent need for a new method to comprehensively process and analyze multi-source data in power transmission and transformation projects to improve the accuracy and efficiency of data analysis. At the same time, by in-depth analysis of the impact of environmental factors on equipment performance and the application of advanced machine learning algorithms to explore failure modes and performance degradation trends, it can provide more scientific and effective support for the maintenance and optimization of power transmission and transformation systems. Summary of the invention

[0005] Based on the above objectives, the present invention provides a method and system for comprehensive analysis and management of power transmission and transformation engineering data.

[0006] The comprehensive analysis and management method of power transmission and transformation engineering data includes the following steps:

[0007] S1: Collect multi-source power transmission and transformation project data, including voltage, current, frequency and environmental data collected from sensor networks, historical records and real-time monitoring units;

[0008] S2: Preprocess the collected data, including data cleaning, format unification, and identification of key performance indicators;

[0009] S3: Conduct environmental factor analysis to analyze how different environmental conditions affect the performance of power transmission and transformation equipment, so as to determine the impact on power transmission and transformation engineering data, and apply principal component analysis (PCA) to extract the main change components;

[0010] S4: Apply machine learning algorithms to analyze data features of major changing components and explore potential failure modes and performance degradation trends.

[0011] Furthermore, the S1 specifically includes a plurality of sensors for capturing voltage, current, frequency and environmental parameters in real time;

[0012] The sensors include pressure sensors, temperature sensors, humidity sensors, and current and voltage sensors;

[0013] An integrated historical record database includes past power transmission and transformation project data, including historical fault records, maintenance records, and performance evaluation reports;

[0014] The S1 uses a real-time monitoring unit to monitor the operating status of the power transmission and transformation equipment.

[0015] Furthermore, the key performance indicators in S2 include:

[0016] Power grid stability index: By analyzing frequency deviation and voltage fluctuation, the frequency deviation rate and voltage stability index are calculated;

[0017] Equipment operation efficiency index: Combine the input and output voltage and current data of the transformer to calculate the transformer efficiency, and use the input and output power of the transmission line to calculate the transmission loss rate;

[0018] Maintenance and failure indicators: Through the failure record data, the failure frequency is counted, and combined with the maintenance records, the average maintenance cycle of the equipment is calculated;

[0019] Environmental adaptability index: Analyze the relationship between equipment performance data and environmental parameters (such as temperature and humidity) to evaluate the adaptability of equipment under different environmental conditions;

[0020] Safety and reliability indicators: Utilize accident records and equipment operation logs to calculate accident rates and equipment aging rates.

[0021] Furthermore, the environmental conditions in S3 include temperature fluctuations, humidity changes, and geographical locations, specifically including:

[0022] The temperature fluctuation analysis is as follows:

[0023] Integrate temperature sensor data with power transmission and transformation equipment operation data (such as load, voltage, current, and frequency) in a time-synchronous manner, and use data window technology (such as a sliding average window) to smooth temperature fluctuations and reduce the impact of short-term fluctuations;

[0024] Statistical analysis: Multiple linear regression was used to analyze the relationship between temperature and key performance indicators of the equipment. The equipment efficiency E was expressed as: E = a1×T+a2×V+a3×I+…+b, where T is temperature, V and I are voltage and current respectively, a1, a2, a3 are regression coefficients, and b is a constant term.

[0025] The humidity change analysis is as follows:

[0026] Data preparation: Collect humidity data and equipment failure records (failure / no failure), divide the data set into features (humidity) and labels (failure / no failure),

[0027] Build a logistic regression model: Use humidity data as features and fault occurrence as labels to train a logistic regression model. The model form is: Where P(failure) is the probability of failure, β0 and β1 are model parameters;

[0028] Use the maximum likelihood estimation method to estimate the model parameters β0 and β1, evaluate the performance of the model through accuracy, recall or ROC curve indicators, and use the model to guide equipment maintenance plans and failure prevention measures;

[0029] The geographical location analysis is as follows:

[0030] Data preparation: Collect the geographic location data (coordinates, altitude) and performance data (failure rate, maintenance frequency, and operating efficiency) of power transmission and transformation equipment, and establish a spatial data point for each power transmission and transformation equipment, including the geographic location and performance indicators;

[0031] Create a spatial weight matrix: Create a spatial weight matrix based on geographic location. The weights are determined based on distance (closer devices have higher weights). The weight creation method is based on inverse distance weighting.

[0032] Calculate the spatial autocorrelation index: Use the Moran's I index to measure the spatial autocorrelation metric. The Moran's I index calculation formula is:

[0033] Where N is the number of observation points, w ij is the weight between devices i and j in the weight matrix, X i is the performance index of device i, It is the average value of all equipment performance indicators;

[0034] A high Moran's I index value indicates positive spatial autocorrelation, that is, similar or related values ​​tend to cluster in space; a low or negative Moran's I index value indicates negative spatial autocorrelation, that is, dissimilar values ​​cluster in space; based on the Moran's I index analysis results, similar patterns or abnormal patterns of equipment performance in a specific geographic area can be identified.

[0035] Furthermore, S3 also includes a comprehensive impact assessment, which combines the analysis results of temperature fluctuations, humidity changes and geographical locations to assess the comprehensive impact of environmental factors on the overall performance of power transmission and transformation equipment, specifically including:

[0036] Data aggregation: Aggregate the analysis results of temperature fluctuation, humidity change and geographical location into one data set, including the data on the relationship between equipment performance and temperature obtained from the temperature fluctuation analysis, the data on the relationship between failure probability and humidity obtained from the humidity change analysis, and the data on the difference in equipment performance between different geographical locations obtained from the geographical location factor analysis;

[0037] Build a comprehensive data matrix: Create a data matrix where each row represents a device and each column represents an analysis result (temperature impact score, humidity failure probability, geographic location impact score). Standardize each column in the data matrix to have a mean of 0 and a standard deviation of 1 to make data at different scales comparable.

[0038] Principal component analysis (PCA) was applied to the standardized data matrix to extract the main variation components, which would reveal the relative importance of different environmental factors on device performance.

[0039] Furthermore, the S4 specifically includes:

[0040] Data preparation: Use the results of principal component analysis PCA as input,

[0041] Select the machine learning model: select support vector machine (SVM) for classification problems (fault pattern recognition) and select ridge regression for regression problems (performance degradation trend prediction);

[0042] Model optimization and validation: Use cross-validation and hyperparameter adjustment methods to optimize the model;

[0043] Evaluate the accuracy and reliability of the model by calculating precision, recall, and F1 score;

[0044] Use trained models to analyze real-time data to identify potential failure modes and performance degradation trends.

[0045] Furthermore, the support vector machine (SVM) is used for fault mode classification, specifically including:

[0046] The principal component analysis PCA results are used as input features, including the impact of temperature fluctuations, humidity changes, and geographic location on equipment failure rates. The formula is:

[0047] Among them, x is the input feature (i.e. PCA analysis result), w is the weight vector, and b is the bias term. It is a function that maps input features to a high-dimensional space. For a binary classification problem, the goal is to find the best hyperplane that separates the two categories.

[0048] The radial basis function kernel is introduced to deal with the nonlinear separable situation. The kernel function is:

[0049] K(x i ,x j )=exp(-γ‖x i -x j ‖ 2 ), where γ is the parameter of the kernel function, x i and x j is the eigenvector.

[0050] Furthermore, the ridge regression is used to predict the performance degradation trend, specifically including:

[0051] The principal component analysis PCA results are used as input feature ridge regression to regularize the standard linear regression. The formula is: f(x) = w T x+b, the optimization objective includes a regularization term to reduce model complexity: min w Xw-y‖ 2 +α‖w‖ 2 , where X is the input feature matrix, y is the target variable, i.e., the equipment performance index, and α is the regularization parameter.

[0052] Furthermore, it also includes the generation of a comprehensive governance report, which is based on the results of environmental factor analysis and data feature analysis, and provides decision support, including maintenance recommendations, optimization strategies and visual display of results.

[0053] The power transmission and transformation project data comprehensive analysis and management system is used to implement the above-mentioned power transmission and transformation project data comprehensive analysis and management method, and is characterized by comprising the following modules:

[0054] Data collection module: responsible for collecting multi-source power transmission and transformation project data, including voltage, current, frequency and environmental parameters;

[0055] Data preprocessing module: performs preprocessing operations on the collected data, including data cleaning, format unification, and identification of key performance indicators;

[0056] Environmental factor analysis module: Analyzes the impact of temperature fluctuations, humidity changes and geographical location factors on the performance of power transmission and transformation equipment, as well as the comprehensive impact on power transmission and transformation engineering data;

[0057] Data feature analysis module: applies machine learning algorithms, including support vector machines and ridge regression, to analyze data features and mine potential failure modes and performance degradation trends;

[0058] Decision support and report generation module: Generates comprehensive governance reports based on analysis results to provide decision support;

[0059] User interface: Allows users to query specific data, customize reports, and view visual analysis results.

[0060] Beneficial effects of the present invention:

[0061] The present invention, by comprehensively utilizing multi-source data (including sensor networks, historical records and real-time monitoring system data), can provide a more comprehensive perspective to analyze the operating status of power transmission and transformation equipment. Combined with data preprocessing and cross-domain data fusion, this method can effectively improve the accuracy and efficiency of data analysis and ensure the reliability and practicality of the analysis results.

[0062] The present invention, through the environmental factor analysis module, deeply explores the specific impact of environmental factors such as temperature fluctuations, humidity changes and geographical location on the performance of power transmission and transformation equipment. This analysis can reveal how environmental changes affect equipment operation and help identify those devices or components that are more sensitive to specific environmental conditions. It not only helps to discover potential risk points in advance, but also optimizes the design and operation strategies of equipment according to specific environmental conditions, thereby improving the adaptability and reliability of the entire system.

[0063] The present invention, by applying machine learning algorithms such as support vector machines and ridge regression, can effectively mine potential failure modes and performance degradation trends from the comprehensive analysis data. The algorithm can process large amounts of data and identify complex patterns and trends, thereby providing a powerful analysis tool for predictive maintenance and fault prevention of power transmission and transformation equipment. Accurate fault prediction and trend analysis help reduce unexpected downtime, extend equipment life, reduce maintenance costs, and improve the operating efficiency and stability of the entire power transmission and transformation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A schematic diagram of a treatment method flow chart of an embodiment of the present invention;

[0066] Figure 2 Schematic diagram of the functional modules of the governance system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0068] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0069] like Figure 1 As shown, the comprehensive analysis and management method of power transmission and transformation engineering data includes the following steps:

[0070] S1: Collect multi-source power transmission and transformation project data, including voltage, current, frequency and environmental data collected from sensor networks, historical records and real-time monitoring units;

[0071] S2: Preprocess the collected data, including data cleaning, format unification, and identification of key performance indicators;

[0072] S3: Conduct environmental factor analysis to analyze how different environmental conditions affect the performance of power transmission and transformation equipment, so as to determine the impact on power transmission and transformation engineering data, and apply principal component analysis (PCA) to extract the main change components;

[0073] S4: Apply machine learning algorithms to analyze data features of major changing components and explore potential failure modes and performance degradation trends.

[0074] S1 specifically includes multiple sensors for capturing voltage, current, frequency, and environmental parameters in real time;

[0075] Sensors include pressure sensors, temperature sensors, humidity sensors, and current and voltage sensors;

[0076] Integrated historical record database, which includes past power transmission and transformation project data, including historical fault records, maintenance records and performance evaluation reports;

[0077] It also includes real-time monitoring of the operating status of power transmission and transformation equipment.

[0078] This comprehensive data collection method ensures that the collected data is comprehensive and accurate, and provides a solid data foundation for subsequent analysis steps. In addition, this method can also capture and respond to any abnormalities in the power transmission and transformation project in real time, increasing operational safety and reliability.

[0079] S2 specifically includes:

[0080] Data cleaning: Use time series analysis to identify and remove outliers. By comparing historical data within the same time period, data points that do not conform to normal operating patterns are identified. For missing data points, interpolation methods are used to fill them, such as linear interpolation or the average value based on adjacent data points. For duplicate data, deduplication operations are performed to retain the initial records and delete subsequent duplicates.

[0081] Format unification: All data are converted into a unified time format, such as "YYYY-MM-DDHH:MM:SS", to ensure the consistency of time data. For numerical data, such as voltage and current, they are uniformly converted to the International System of Units standard, for example, the voltage unit is unified as "kilovolt (kV)", and the current unit is unified as "ampere (A)". For data from different data sources, the field names are unified, for example, the fields representing voltage in all data sources are uniformly named "Voltage".

[0082] Key performance indicators in S2 include:

[0083] Power grid stability index: By analyzing frequency deviation and voltage fluctuation, the frequency deviation rate and voltage stability index are calculated;

[0084] Equipment operation efficiency index: Combine the input and output voltage and current data of the transformer to calculate the transformer efficiency, and use the input and output power of the transmission line to calculate the transmission loss rate;

[0085] Maintenance and failure indicators: Through the failure record data, the failure frequency is counted, and combined with the maintenance records, the average maintenance cycle of the equipment is calculated;

[0086] Environmental adaptability index: Analyze the relationship between equipment performance data and environmental parameters (such as temperature and humidity) to evaluate the adaptability of equipment under different environmental conditions;

[0087] Safety and reliability indicators: Utilize accident records and equipment operation logs to calculate accident rates and equipment aging rates.

[0088] Environmental conditions in S3 include temperature fluctuations, humidity changes, and geographic location, including:

[0089] The temperature fluctuation analysis is as follows:

[0090] Integrate temperature sensor data with power transmission and transformation equipment operation data (such as load, voltage, current, and frequency) in a time-synchronous manner, and use data window technology (such as a sliding average window) to smooth temperature fluctuations and reduce the impact of short-term fluctuations;

[0091] Statistical analysis: Multiple linear regression was used to analyze the relationship between temperature and key performance indicators of the equipment. The equipment efficiency E is expressed as: E = a1×T+a2×V+a3×I+…+b, where T is temperature, V and I are voltage and current respectively, a1, a2, a3 are regression coefficients, and b is a constant term;

[0092] Use the random forest algorithm to identify the nonlinear impact of temperature fluctuations on device performance. The random forest algorithm is an integrated learning method that is suitable for dealing with nonlinear problems. The following are the steps to use the random forest algorithm to identify the impact of temperature fluctuations on device performance:

[0093] Collect equipment performance data (such as voltage, current, load rate) and corresponding temperature readings, and divide the dataset into training and testing sets.

[0094] Build a random forest model: Use the training set data to train a random forest model, in which temperature readings are used as input features and device performance parameters are used as outputs.

[0095] Each tree uses a different subset of data and features during training.

[0096] Feature Importance Analysis: After model training is completed, the importance of the temperature feature for predicting device performance is evaluated. The importance is calculated by analyzing the average reduced impurity of the split points in each tree.

[0097] Model evaluation: Use the test set data to evaluate the accuracy of the model, using indicators such as mean squared error (MSE) or R 2 The model is used to measure the predictive performance of the model, and then the relationship between temperature and key performance indicators of the equipment is analyzed using the model.

[0098] The humidity change analysis is as follows:

[0099] Data preparation: Collect humidity data and equipment failure records (failure / no failure), divide the data set into features (humidity) and labels (failure / no failure),

[0100] Build a logistic regression model: Use humidity data as features and fault occurrence as labels to train a logistic regression model. The model form is: Where P(failure) is the probability of failure, β0 and β1 are model parameters;

[0101] Use the maximum likelihood estimation method to estimate the model parameters β0 and β1, evaluate the performance of the model through accuracy, recall or ROC curve indicators, and use the model to guide equipment maintenance plans and failure prevention measures;

[0102] The geographical location analysis is as follows:

[0103] Data preparation: Collect the geographic location data (coordinates, altitude) and performance data (failure rate, maintenance frequency, and operating efficiency) of power transmission and transformation equipment, and establish a spatial data point for each power transmission and transformation equipment, including the geographic location and performance indicators;

[0104] Create a spatial weight matrix: Create a spatial weight matrix based on geographic location. The weights are determined based on distance (closer devices have higher weights). The weight creation method is based on inverse distance weighting.

[0105] Calculate the spatial autocorrelation index: Use the Moran's I index to measure the spatial autocorrelation metric. The Moran's I index calculation formula is:

[0106] Where N is the number of observation points, w ij is the weight between devices i and j in the weight matrix, X i is the performance index of device i, It is the average value of all equipment performance indicators;

[0107] A high Moran's I index value indicates positive spatial autocorrelation, that is, similar or related values ​​tend to cluster in space; a low or negative Moran's I index value indicates negative spatial autocorrelation, that is, dissimilar values ​​cluster in space; based on the Moran's I index analysis results, similar patterns or abnormal patterns of equipment performance in a specific geographic area can be identified.

[0108] To measure performance differences between different geographic locations, you can take the following steps:

[0109] Geographical division: devices are divided into different groups according to their geographical locations (such as different regions, different altitudes).

[0110] Performance indicator comparison: Statistical analysis of equipment performance indicators within each geographic area group, such as calculation of average failure rate, average operating efficiency, etc.

[0111] An analysis of variance (ANOVA) test was used to determine whether there were statistically significant differences in device performance indicators between different geographic regions. ANOVA can determine whether the between-group variation is significantly greater than the within-group variation, thereby determining whether there are significant differences in performance between different geographic locations.

[0112] By combining spatial autocorrelation analysis and ANOVA tests, the impact of different geographical locations on the performance of power transmission and transformation equipment can be effectively identified and quantified, providing strong data support for the optimized operation and maintenance of equipment.

[0113] S3 also includes comprehensive impact assessment, which combines the analysis results of temperature fluctuations, humidity changes and geographical location to evaluate the comprehensive impact of environmental factors on the overall performance of power transmission and transformation equipment, including:

[0114] Data aggregation: Aggregate the analysis results of temperature fluctuation, humidity change and geographical location into one data set, including the data on the relationship between equipment performance and temperature obtained from the temperature fluctuation analysis, the data on the relationship between failure probability and humidity obtained from the humidity change analysis, and the data on the difference in equipment performance between different geographical locations obtained from the geographical location factor analysis;

[0115] Build a comprehensive data matrix: Create a data matrix where each row represents a device and each column represents an analysis result (temperature impact score, humidity failure probability, geographic location impact score). Standardize each column in the data matrix to have a mean of 0 and a standard deviation of 1 to make data at different scales comparable.

[0116] Principal component analysis (PCA) was applied to the standardized data matrix to extract the main variation components, which would reveal the relative importance of different environmental factors on device performance.

[0117] Computational steps for principal component analysis (PCA).

[0118] Data preparation: Extract data from the previous analysis, the correlation score T between equipment performance and temperature obtained from the temperature fluctuation analysis, the correlation score H between failure probability and humidity obtained from the humidity change analysis, and the correlation score G between equipment performance and geographic location obtained from the geographic location factor analysis.

[0119] Data normalization: Normalize all data to have zero mean and unit variance. The formula for normalized data Z is: Among them, X i are the variables (T, H, G) in the original dataset, μ i is the mean value of the variable, σ i is the standard deviation.

[0120] Construct a covariance matrix: Construct a covariance matrix to quantify the correlation between variables. The element C of the covariance matrix C ij The calculation formula is:

[0121] Where n is the number of samples, and is the mean of the standardized data.

[0122] Calculate eigenvalues ​​and eigenvectors: Perform eigenvalue decomposition on the covariance matrix C to obtain eigenvalues ​​and corresponding eigenvectors. The eigenvalues ​​represent the variance of each principal component, while the eigenvectors define the direction of the principal component.

[0123] Select principal components: Select principal components based on the size of the eigenvalues. Usually, the principal components selected should be able to explain most of the total variance of the data.

[0124] Data transformation: Use the selected principal components to transform the original data into a new low-dimensional space. The new data point Y is calculated as follows: Y = PX, where P is the matrix containing the selected principal components and X is the original data matrix.

[0125] S4 specifically includes:

[0126] Data preparation: Use the results of principal component analysis PCA as input,

[0127] Select the machine learning model: select support vector machine (SVM) for classification problems (fault pattern recognition) and select ridge regression for regression problems (performance degradation trend prediction);

[0128] Model optimization and validation: Use cross-validation and hyperparameter adjustment methods to optimize the model;

[0129] Evaluate the accuracy and reliability of the model by calculating precision, recall, and F1 score;

[0130] Use trained models to analyze real-time data to identify potential failure modes and performance degradation trends.

[0131] In the present invention, PCA and machine learning algorithms are combined to more effectively identify and predict potential problems in power transmission and transformation equipment. PCA helps reduce the data dimension and highlight the most important features, while machine learning algorithms can deeply analyze these features and identify specific patterns and trends that may lead to failures or performance degradation. This comprehensive approach helps to detect and solve problems in advance, thereby reducing downtime and improving the overall reliability and efficiency of the system.

[0132] Support vector machine (SVM) is used for fault mode classification, including:

[0133] The principal component analysis PCA results are used as input features, including the impact of temperature fluctuations, humidity changes, and geographic location on equipment failure rates. The formula is:

[0134] Among them, x is the input feature (i.e. PCA analysis result), w is the weight vector, and b is the bias term. It is a function that maps input features to a high-dimensional space. For a binary classification problem, the goal is to find the best hyperplane that separates the two categories.

[0135] The radial basis function kernel is introduced to deal with the nonlinear separable situation. The kernel function is:

[0136] K(x i ,x j )=exp(-γ‖x i -x j ‖ 2 ), where γ is the parameter of the kernel function, x i and x j is the eigenvector.

[0137] Ridge regression is used to predict performance degradation trends, including:

[0138] The principal component analysis PCA results are used as input feature ridge regression to regularize the standard linear regression. The formula is: f(x) = w T x+b, the optimization objective includes a regularization term to reduce model complexity: min w Xw-y‖ 2 +α‖w‖ 2 , where X is the input feature matrix, y is the target variable, i.e., the equipment performance index, and α is the regularization parameter.

[0139] In the present invention, SVM and ridge regression models are used to analyze and predict the performance and health of power transmission and transformation equipment. With the main components extracted by PCA as input features, SVM can help identify and classify different equipment failure modes, while ridge regression can be used to predict the degradation trend of equipment performance. This method helps to identify potential problems in advance, so as to take preventive measures, reduce failures and improve the overall reliability and efficiency of the power transmission and transformation system.

[0140] It also includes the generation of a comprehensive governance report, which is based on the results of environmental factor analysis and data feature analysis, and provides decision support, including maintenance recommendations, optimization strategies and visual display of results.

[0141] Report Contents:

[0142] Maintenance recommendations: Based on the failure modes and performance degradation trends identified by the machine learning model, targeted maintenance recommendations are made. For example, for equipment that is sensitive to high temperature fluctuations, it is recommended to enhance the cooling system.

[0143] Optimization strategy: Combine PCA and machine learning analysis results to propose optimization strategies for device configuration and operation. For example, adjust the device's operating parameters to adapt to a specific environment based on geographic location factors.

[0144] Visualization of results:

[0145] Use charts and graphs to display PCA analysis results, scatter plots of principal component scores to intuitively show the impact of different environmental factors on device performance, display the prediction results of machine learning models, such as failure mode classification diagrams or time series prediction diagrams of performance degradation trends, and use heat maps or maps to display the performance and failure distribution of devices in different geographical locations.

[0146] Decision support information: Provides specific decision support information based on data analysis, such as a list of equipment that may require more frequent maintenance under certain conditions, or environmental factors that require special monitoring, and provides customized maintenance and optimization suggestions for different equipment types and operating environments.

[0147] like Figure 2 As shown, the power transmission and transformation project data comprehensive analysis and management system is used to implement the above-mentioned power transmission and transformation project data comprehensive analysis and management method, and is characterized by including the following modules:

[0148] Data collection module: responsible for collecting multi-source power transmission and transformation project data, including voltage, current, frequency and environmental parameters;

[0149] Data preprocessing module: performs preprocessing operations on the collected data, including data cleaning, format unification, and identification of key performance indicators;

[0150] Environmental factor analysis module: Analyzes the impact of temperature fluctuations, humidity changes and geographical location factors on the performance of power transmission and transformation equipment, as well as the comprehensive impact on power transmission and transformation engineering data;

[0151] Data feature analysis module: applies machine learning algorithms, including support vector machines and ridge regression, to analyze data features and mine potential failure modes and performance degradation trends;

[0152] Decision support and report generation module: Generates comprehensive governance reports based on analysis results to provide decision support;

[0153] User interface: Allows users to query specific data, customize reports, and view visual analysis results.

[0154] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0155] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A comprehensive analysis and management method for power transmission and transformation engineering data, characterized in that: The following steps are involved: S1: Collect multi-source power transmission and transformation project data, including sensor networks, historical records and real-time monitoring units; S2: Preprocess the collected data, including data cleaning, format unification, and identification of key performance indicators; S3: Conduct environmental factor analysis to analyze how different environmental conditions affect the performance of power transmission and transformation equipment, so as to determine the impact on power transmission and transformation engineering data, and apply principal component analysis to extract the main change components; S4: Apply machine learning algorithms to analyze data features of major changing components and explore potential failure modes and performance degradation trends.

2. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 1 is characterized in that: The sensor network in S1 is used to capture voltage, current, frequency and environmental parameters in real time; The sensor network includes a pressure sensor, a temperature sensor, a humidity sensor, and a current and voltage sensor; An integrated history record database including historical fault records, maintenance records and performance evaluation reports; The S1 uses a real-time monitoring unit to monitor the operating status of the power transmission and transformation equipment.

3. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 2 is characterized in that: The key performance indicators of S2 include: Power grid stability index: By analyzing frequency deviation and voltage fluctuation, the frequency deviation rate and voltage stability index are calculated; Equipment operation efficiency index: Combine the input and output voltage and current data of the transformer to calculate the transformer efficiency, and use the input and output power of the transmission line to calculate the transmission loss rate; Maintenance and failure indicators: Through the failure record data, the failure frequency is counted, and combined with the maintenance records, the average maintenance cycle of the equipment is calculated; Environmental adaptability index: Analyze the relationship between equipment performance data and environmental parameters, and evaluate the adaptability of equipment under different environmental conditions; Safety and reliability indicators: Utilize accident records and equipment operation logs to calculate accident rates and equipment aging rates.

4. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 3 is characterized in that: The environmental conditions in S3 include temperature fluctuations, humidity changes, and geographical locations, specifically including: The temperature fluctuation analysis is as follows: The temperature sensor data is integrated with the operation data of the power transmission and transformation equipment in a time-synchronous manner, and the temperature fluctuation is smoothed using data window technology to reduce the impact of short-term fluctuations; Statistical analysis: Multiple linear regression was used to analyze the relationship between temperature and key performance indicators of the equipment. The equipment efficiency E is expressed as: E = a1×T+a2×V+a3×I+…+b, where T is temperature, V and I are voltage and current respectively, a1, a2, a3 are regression coefficients, and b is a constant term; The humidity change analysis is as follows: Data preparation: Collect humidity data and equipment failure records, divide the data set into features and labels, Build a logistic regression model: Use humidity data as features and fault occurrence as labels to train a logistic regression model. The model form is: Where P(failure) is the probability of failure, β0 and β1 are model parameters; Use the maximum likelihood estimation method to estimate the model parameters β0 and β1, and evaluate the performance of the model through accuracy, recall or ROC curve indicators; The geographical location analysis is as follows: Data preparation: Collect the geographic location data and performance data of power transmission and transformation equipment, and establish a spatial data point for each power transmission and transformation equipment, including the geographic location and performance indicators; Create a spatial weight matrix: Create a spatial weight matrix based on geographic location, with weights based on distance, and the weight creation method is based on inverse distance weighting; Calculate the spatial autocorrelation index: Use the Moran's I index to measure the spatial autocorrelation metric. The Moran's I index calculation formula is: Where N is the number of observation points, w ij is the weight between devices i and j in the weight matrix, X i is the performance index of device i, It is the average value of all equipment performance indicators; A high Moran's I index value indicates positive spatial autocorrelation, that is, similar or related values ​​tend to cluster in space; a low or negative Moran's I index value indicates negative spatial autocorrelation, that is, dissimilar values ​​cluster in space; based on the Moran's I index analysis results, similar patterns or abnormal patterns of equipment performance in a specific geographic area can be identified.

5. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 4 is characterized in that: S3 also includes comprehensive impact assessment, which combines the analysis results of temperature fluctuations, humidity changes and geographical location to evaluate the comprehensive impact of environmental factors on the overall performance of power transmission and transformation equipment, including: Data aggregation: Aggregate the analysis results of temperature fluctuation, humidity change and geographical location into one data set, including the data on the relationship between equipment performance and temperature obtained from the temperature fluctuation analysis, the data on the relationship between failure probability and humidity obtained from the humidity change analysis, and the data on the difference in equipment performance between different geographical locations obtained from the geographical location factor analysis; Build a comprehensive data matrix: Create a data matrix in which each row represents a device and each column represents an analysis result. Standardize each column in the data matrix to have a mean of 0 and a standard deviation of 1 to make data at different scales comparable. Principal component analysis was applied to the standardized data matrix to extract the main components of variation.

6. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 5 is characterized in that: The S4 specifically includes: Data preparation: Use the results of principal component analysis as input, Choose a machine learning model: Support vector machine for classification problems and ridge regression for regression problems; Model optimization and validation: Use cross-validation and hyperparameter adjustment methods to optimize the model; Evaluate the accuracy and reliability of the model by calculating precision, recall, and F1 score; Use trained models to analyze real-time data to identify potential failure modes and performance degradation trends.

7. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 6 is characterized in that: The support vector machine is used for fault mode classification, specifically including: Using the principal component analysis results as input features, including the impact of temperature fluctuations, humidity changes, and geographic location on equipment failure rates, the formula is: Among them, x is the input feature, w is the weight vector, b is the bias term, It is a function that maps input features to a high-dimensional space. For a binary classification problem, the goal is to find the best hyperplane that separates the two categories. The radial basis function kernel is introduced to deal with the nonlinear separable situation. The kernel function is: K(x i ,x j )=exp(-γ‖x i -x j ‖ 2 ), where γ is the parameter of the kernel function, x i and x j is the eigenvector.

8. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 6 is characterized in that: The ridge regression is used to predict the performance degradation trend, specifically including: The results of principal component analysis are used as input features to regularize the standard linear regression. The formula is: f(x) = w T x+b, the optimization objective includes a regularization term to reduce model complexity: min w Xw-y‖ 2 +α‖w‖ 2 , where X is the input feature matrix, y is the target variable, i.e., the equipment performance index, and α is the regularization parameter.

9. The method for comprehensive analysis and management of power transmission and transformation engineering data according to claim 8 is characterized in that: It also includes the generation of a comprehensive governance report, which is based on the results of environmental factor analysis and data feature analysis, and provides decision support, including maintenance recommendations, optimization strategies and visual display of results.

10. A system for comprehensive analysis and management of power transmission and transformation engineering data, used to implement the method for comprehensive analysis and management of power transmission and transformation engineering data as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Data collection module: responsible for collecting multi-source power transmission and transformation project data, including voltage, current, frequency and environmental parameters; Data preprocessing module: performs preprocessing operations on the collected data, including data cleaning, format unification, and identification of key performance indicators; Environmental factor analysis module: Analyzes the impact of temperature fluctuations, humidity changes and geographical location factors on the performance of power transmission and transformation equipment, as well as the comprehensive impact on power transmission and transformation engineering data; Data feature analysis module: applies machine learning algorithms, including support vector machines and ridge regression, to analyze data features and mine potential failure modes and performance degradation trends; Decision support and report generation module: Generates comprehensive governance reports based on analysis results to provide decision support; User interface: Allows users to query specific data, customize reports, and view visual analysis results.

Images