Substation electric power parameter real-time monitoring and analysis platform

Abstract

The invention discloses a transformer substation electric power parameter real-time monitoring and analysis platform, and relates to the technical field of electric power monitoring. The monitoring analysis platform is in communication connection with a real-time monitoring module, a data acquisition and processing module, a data storage and management module, a fault feature extraction module, an event early warning module, a fault diagnosis module and a data visualization module. The transformer station electric power parameter real-time monitoring and analysis platform timely discovers abnormal conditions of electric power equipment by collecting and analyzing key parameters of voltage, current, power, temperature and humidity in real time, so that potential faults and accidents are prevented, and the real-time monitoring and analysis of the electric power parameters of the transformer station is realized by learning historical fault data and identifying modes. The platform can predict and identify an abnormal trend which may cause a fault, gives out an early warning in advance, remarkably improves the reliability and safety of a power system, reduces the risks of accidental power failure and equipment damage, and guarantees the continuity and stability of power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power monitoring, and in particular to a real-time monitoring and analysis platform for electric power parameters of a substation. Background Art

[0002] With the continuous increase in energy consumption, the safe operation of the power system has become increasingly important. As an important part of the power system, the safety, reliability and economy of the substation directly affect the operating efficiency and stability of the entire power system. In recent years, computer technology, network communication technology and automation technology have developed rapidly. The widespread application of these technologies has provided strong support for the research and development of the real-time monitoring and analysis platform for substation power parameters. By integrating these advanced technologies, the platform can realize real-time monitoring of various parameters of the substation, data analysis and fault warning, thereby greatly improving the intelligence level of the power system.

[0003] With the development of power systems and the expansion of substation scale, a large amount of real-time monitoring data needs to be processed, which will lead to false alarms, missed alarms or inaccurate diagnosis in fault warning and diagnosis, affecting the decision-making and actions of operation and maintenance personnel. Therefore, how to explore the potential rules and correlations in substation power parameter monitoring data, discover the precursor characteristics of faults, and improve the sensitivity of fault warning is the problem we need to solve. To this end, a real-time monitoring and analysis platform for substation power parameters is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: a real-time monitoring and analysis platform for power parameters of a substation, comprising a monitoring and analysis platform, wherein the monitoring and analysis platform is communicatively connected with a real-time monitoring module, a data acquisition and processing module, a data storage and management module, a fault feature extraction module, an event warning module, a fault diagnosis module and a data visualization module, wherein the modules are connected by electrical signals;

[0005] The real-time monitoring module is used to monitor the operating status of various types of power equipment in the substation in real time, so that the operation and maintenance personnel can timely understand the operating status of the equipment and promptly discover and deal with potential problems;

[0006] The data acquisition and processing module is used to collect monitoring data of various power equipment in the substation, including key parameters such as voltage, current, power, temperature, and humidity, to ensure that the platform can obtain comprehensive and accurate monitoring data, provide a reliable basis for subsequent data analysis and fault warning, and perform pre-processing operations such as cleaning, denoising, and calibration on the collected monitoring data to improve the quality and availability of the data, reduce the interference of data errors and noise, and improve the accuracy and reliability of data analysis. The monitoring data includes historical fault data and real-time monitoring data;

[0007] The data storage and management module is used to store and manage pre-processed monitoring data, match data query and access functions, ensure data security and integrity, and facilitate operation and maintenance personnel to view and analyze historical fault data at any time;

[0008] The fault feature extraction module is used to perform feature analysis on the pre-processed monitoring data, analyze historical fault data to extract relevant fault features of the power equipment, and integrate them to obtain a fault feature sequence;

[0009] The event warning module, combined with machine learning algorithms and fault feature sequences, further analyzes monitoring data, evaluates abnormal trends in the operation of power equipment, determines the authenticity of faults in the operation of power equipment, improves the sensitivity and accuracy of fault warnings, reduces false alarms and missed alarms, and provides timely fault handling guidance for operation and maintenance personnel;

[0010] The fault diagnosis module, based on the event warning evaluation results, conducts in-depth analysis of the monitoring data of the real fault, determines the cause and location of the fault, and classifies the fault into different levels according to the severity of the fault, and provides corresponding fault diagnosis reports and suggestions to help operation and maintenance personnel quickly locate the fault point, formulate a reasonable fault handling plan, and shorten the fault recovery time;

[0011] The data visualization module is used to visualize the monitoring data and fault diagnosis results, assist operation and maintenance personnel in analyzing the operating status and performance changes of the equipment, provide intuitive data display and analysis results, and help operation and maintenance personnel make more scientific decisions and judgments.

[0012] Preferably, in the data collection and processing module, the collection process of the power equipment monitoring data specifically includes:

[0013] The monitoring data of the power equipment is collected through various sensors deployed on the power equipment of the substation, where the sensors include voltage sensors, current sensors, power sensors, temperature sensors and humidity sensors. The operating parameters of the power equipment are read through the sensors and the analog signals are converted into digital signals.

[0014] Preprocessing the collected power equipment monitoring data, wherein the preprocessing operation includes data cleaning, denoising and calibration steps;

[0015] Integrate the pre-processed data from different sensors to form a unified data format for easy storage and analysis, and add a timestamp to each data point to ensure the timing of the data.

[0016] Preferably, in the data storage and management module, the storage and management process of monitoring data includes:

[0017] According to the needs of monitoring data, the table structure and index of the database are designed. The table structure includes monitoring data table, equipment information table, user information table and role permission table. The monitoring data table is used to store pre-processed monitoring data, including equipment ID, monitoring time, voltage, current, power, temperature and humidity fields. The equipment information table records the basic information of the equipment, including equipment ID, equipment name, installation location and manufacturer. The user information table stores the basic information of the user, including user ID, user name, password (encrypted storage) and role. The role permission table defines the permissions of different roles, namely administrator and operation and maintenance personnel, and is associated with the user information table. Indexes are established for the key fields in the monitoring data table to improve query efficiency.

[0018] Establish a data access control mechanism and record user login and operation logs to facilitate tracing when security incidents occur;

[0019] Run data cleaning procedures regularly to identify and mark redundant data, such as duplicate records, invalid records, etc. After confirming the redundant data, delete it from the database to improve storage efficiency and query performance. Record the process and results of data cleaning for review when necessary;

[0020] The pre-processed monitoring data is stored in the database according to the designed database table structure to ensure the accuracy and completeness of the data during the storage process, and the database is backed up regularly to prevent data loss or damage. The backup data is stored in the cloud to ensure the security and reliability of storage. Recovery tests are performed regularly to ensure the availability and integrity of the backup data.

[0021] Preferably, in the fault feature extraction module, the process of acquiring the fault feature sequence specifically includes:

[0022] Verify the quality of pre-processed monitoring data to ensure the accuracy, completeness and consistency of the data, including checking the missing values, abnormal values, duplicate values ​​and the correctness of the data format, and organize and sort the verified data according to the device type and time range dimensions;

[0023] Extract historical fault data of various types of power equipment in the substation from the historical database, including the time of the fault, equipment type, fault type, fault phenomenon, and fault cause, and organize the collected historical fault data to remove duplicate, invalid or redundant data to ensure the accuracy and availability of the data;

[0024] Perform feature analysis on historical fault data to extract features related to power equipment failures, including voltage fluctuations, current anomalies, power changes, temperature rise, and humidity changes;

[0025] For voltage, current, and power data, a time series model is constructed to capture the characteristic changes before and after the fault occurs. For temperature and humidity data, they are converted into feature vectors and combined with time series features to comprehensively construct a fault feature sequence.

[0026] Preferably, in the event warning module, the evaluation process of abnormal operation trend of power equipment includes:

[0027] Based on the historical fault features of the fault feature sequence, such as voltage fluctuation, current anomaly, power change, temperature rise, and humidity change, the feature data set is integrated and obtained, and the feature data set is divided into a training set and a test set;

[0028] Using the training set data combined with the K-means clustering algorithm, an abnormal event recognition model is constructed to enable it to recognize the pattern of abnormal events. The abnormal event recognition model is tested using the test set data to adjust the model parameters, optimize the model performance, and improve the accuracy of anomaly detection.

[0029] The pre-processed monitoring data is input into the trained abnormal event recognition model. The model analyzes the matching degree with the abnormal event category based on the characteristics of the input data and determines whether there is an abnormal event.

[0030] Combine the fault feature sequence and abnormal event assessment results, compare the historical fault data and the characteristics of the current abnormal event, further analyze the duration, impact range, and degree of characteristic change of the abnormal event to calculate the abnormal event assessment index, and evaluate the abnormal trend of the power equipment operation to determine whether there is a real fault in the power equipment.

[0031] Preferably, the specific calculation process of the abnormal event assessment index is:

[0032] Traverse the current monitoring data and historical fault data, determine the current monitoring values ​​of the current voltage, current, power, temperature and humidity characteristics, and obtain the reference value of each characteristic based on the standard operating conditions, where for the temperature and humidity characteristics, determine their maximum safe values;

[0033] For each characteristic parameter, calculate the deviation between its current monitoring value and the reference value, and perform normalization on each characteristic parameter, where for voltage, current and power characteristics, divide each deviation by its corresponding reference value, and for temperature and humidity characteristics, divide each deviation by the difference between its maximum safe value and the reference value;

[0034] The normalized deviation values ​​are added together, divided by the number of characteristic parameters, the comprehensive deviation score is calculated, and the square root of the comprehensive deviation score is taken to obtain the abnormal event assessment index.

[0035] Preferably, the calculation expression of the abnormal event evaluation index is:

[0036]

[0037] Among them, A represents the abnormal event assessment index, V f Indicates the current voltage value, V b Indicates the reference value of voltage, I f Indicates the current value, I b Indicates the reference value of current, P f Indicates the current power value, P b Indicates the reference value of power, T f Indicates the current temperature value, T b Indicates the reference value of temperature, T max Indicates the maximum safe value of temperature, H f Indicates the current humidity value, H b Indicates the reference value of humidity, H max Indicates the maximum safe value of humidity. The value range of A is between 0 and 1.

[0038] Preferably, in the fault diagnosis module, the fault level classification and determination process includes:

[0039] Receive monitoring data and abnormal event assessment index results from the event warning module, identify abnormal conditions of substation power equipment, and analyze specific characteristic changes of abnormal events, and then compare the characteristics with the patterns in the historical fault database to identify the fault type and location;

[0040] Assess the severity of the fault based on the potential safety risks of the fault in historical fault data and its impact on system operation;

[0041] According to the severity of the fault and the abnormal event assessment index, the fault is divided into different fault levels, namely, level 1 fault level, level 2 fault level and level 3 fault level. The severity of the fault level increases from level 1 to level 3.

[0042] Combine the abnormal event assessment index and the classified fault levels, and set a corresponding fault assessment threshold for each fault level to determine whether the fault reaches the standard of the corresponding level;

[0043] Based on the results of fault mode identification and fault level classification, a detailed fault diagnosis report is generated, including the fault cause, location, severity, impact and recommended action plan. Based on the specific circumstances of the fault, targeted processing suggestions and maintenance strategies are provided to assist operation and maintenance personnel to quickly respond to and handle faults.

[0044] Preferably, the value of the abnormal event assessment index and the fault assessment threshold preset for the fault level are obtained to match three levels of fault levels, which are:

[0045] Primary fault level: 0 < A ≤ θ L ; A relatively minor fault, indicating that the monitored data deviates slightly from the reference value, with a slight abnormal situation, and can be arranged for handling during routine maintenance;

[0046] Secondary fault level: θ L < A ≤ θ H ; A fault of medium severity, indicating that the monitored data has a certain deviation from the reference value, with a medium abnormal situation, and requires response and handling within a certain period of time;

[0047] Tertiary fault level: θ H < A < 1; The most serious fault, indicating that the monitored data deviates greatly from the reference value, with a serious abnormal situation, and requires immediate response and handling;

[0048] Among them, A is the abnormal event evaluation index, and θ L is the lower threshold corresponding to the secondary fault level and the upper threshold corresponding to the primary fault level, and θ H is the lower threshold corresponding to the tertiary fault level and the upper threshold corresponding to the secondary fault level, and θ L = 0.5, and θ H = 0.8.

[0049] Preferably, in the data visualization module, the process of visually displaying the monitored data and the fault diagnosis results includes:

[0050] Collect the monitored data and the fault diagnosis results, including historical fault data, real-time monitored data, and the analysis results provided by the fault diagnosis module, and convert the data into a visual chart data format;

[0051] Use a chart form to display the real-time monitored data on the visualization screen. The charts include line charts, bar charts, and pie charts, showing the changing trends of the key parameters of the substation power equipment over time, and display the fault diagnosis results on the visualization screen, including key information such as fault type, location, and severity, and distinguish different types of faults through different colors, and then compare the current data with the historical data to discover potential problems and improvement points;

[0052] Use visualization tools to perform trend analysis on the data, identify abnormal points and fluctuations in the data, and predict the future operating state of the power equipment by analyzing the trends and changes of the data. According to the analysis results of the data, output targeted operation and maintenance suggestions.

[0053] The present invention provides a real-time monitoring and analysis platform for substation power parameters. It has the following beneficial effects:

[0054] 1. The substation power parameter real-time monitoring and analysis platform collects and analyzes key parameters such as voltage, current, power, temperature and humidity in real time, and promptly detects abnormal conditions of power equipment, thereby preventing potential failures and accidents. Through learning and pattern recognition of historical failure data, the platform can predict and identify abnormal trends that may lead to failures and issue early warnings, significantly improving the reliability and safety of the power system, reducing the risk of unexpected power outages and equipment damage, and ensuring the continuity and stability of power supply.

[0055] 2. The real-time monitoring and analysis platform for power parameters of the substation conducts in-depth analysis of the monitoring data through the fault diagnosis module, so as to accurately identify the type and location of the fault. It not only improves the accuracy and efficiency of fault handling, but also greatly reduces the maintenance cost and time waste caused by misjudgment or missed judgment. According to the fault diagnosis results, the problem can be quickly located and targeted maintenance measures can be taken. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a module structure diagram of a real-time monitoring and analysis platform for power parameters of a substation according to the present invention;

[0057] Figure 2 This is a flow chart for obtaining a fault feature sequence of the present invention;

[0058] Figure 3 It is a flow chart for evaluating abnormal operation trend of power equipment of the present invention;

[0059] Figure 4 This is a flow chart for classifying and determining fault levels of the present invention. DETAILED DESCRIPTION

[0060] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0061] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: a real-time monitoring and analysis platform for power parameters of a substation, including a monitoring and analysis platform, wherein the monitoring and analysis platform is communicatively connected with a real-time monitoring module, a data acquisition and processing module, a data storage and management module, a fault feature extraction module, an event warning module, a fault diagnosis module and a data visualization module, wherein the electrical signals between the modules are connected;

[0062] Real-time monitoring module, used to monitor the operating status of various power equipment in the substation in real time, so that operation and maintenance personnel can understand the operation status of the equipment in a timely manner and discover and deal with potential problems in a timely manner;

[0063] The data acquisition and processing module is used to collect monitoring data of various power equipment in the substation, including key parameters such as voltage, current, power, temperature, and humidity, to ensure that the platform can obtain comprehensive and accurate monitoring data, provide a reliable basis for subsequent data analysis and fault warning, and perform pre-processing operations such as cleaning, denoising, and calibration on the collected monitoring data to improve the quality and availability of the data, reduce the interference of data errors and noise, and improve the accuracy and reliability of data analysis. Among them, the monitoring data includes historical fault data and real-time monitoring data. The monitoring data of the power equipment is collected through various sensors deployed on the power equipment of the substation. Among them, the sensors include voltage sensors, current sensors, power sensors, temperature sensors, and humidity sensors. The operating parameters of the power equipment are read through the sensors, and the analog signals are converted into digital signals for subsequent processing. The voltage sensor is used to measure the voltage level of the power equipment, the current sensor is used to measure the current intensity flowing through the power equipment, and the power Sensors are used to measure the power consumed or output by power equipment. Temperature sensors are used to monitor the temperature of power equipment to prevent damage caused by overheating. Humidity sensors are used to monitor environmental humidity because humidity may affect the insulation performance of the equipment. The collected power equipment monitoring data is preprocessed, where the preprocessing operation includes data cleaning, denoising and calibration steps. In substation data collection, data anomalies may occur due to sensor failure, data transmission errors, etc. Data cleaning is used to remove invalid, redundant or erroneous information in the data to ensure data accuracy. Substation data contains noise caused by environmental factors, equipment vibration, etc. Noise is removed from the data through noise reduction algorithms to improve the signal-to-noise ratio of the data. The calibration process includes adjusting the sensitivity of the sensor and correcting data deviation steps to ensure data accuracy and consistency. Different sensor data after preprocessing are integrated to form a unified data format for easy storage and analysis, and timestamps are added to each data point to ensure data timing.

[0064] The data storage and management module is used to store and manage pre-processed monitoring data, match data query and access functions, ensure data security and integrity, and facilitate operation and maintenance personnel to view and analyze historical fault data at any time. According to the needs of monitoring data, the table structure and index of the database are designed. The table structure includes monitoring data table, equipment information table, user information table and role permission table. The monitoring data table is used to store pre-processed monitoring data, including equipment ID, monitoring time, voltage, current, power, temperature, and humidity fields. The equipment information table records the basic information of the equipment, including equipment ID, equipment name, installation location, and manufacturer. The user information table stores the basic information of the user, including user ID, user name, password (encrypted storage), and role. The role permission table defines the permissions of different roles, namely administrators and operation and maintenance personnel, and is associated with the user information table. Indexes are established for key fields in the monitoring data table to improve query efficiency. A data access control mechanism is established to ensure that only authorized personnel can access the data. Data is realized through identity authentication and permission management. Ensure secure access to data. When users log in, they are authenticated by username and password to ensure that only legitimate users can access the system. Strong password policies should be used for passwords and they should be changed regularly. Different permissions should be assigned according to user roles. For example, administrators can access all data and perform database management operations, while operation and maintenance personnel can only access data of specific devices. Login and operation logs of users should be recorded for tracing when security incidents occur. Data cleaning programs should be run regularly to identify and mark redundant data, such as duplicate records and invalid records. After confirming redundant data, they should be deleted from the database to improve storage efficiency and query performance. The process and results of data cleaning should be recorded for review when necessary. The pre-processed monitoring data should be stored in the database according to the designed database table structure to ensure the accuracy and integrity of the data during the storage process. The database should be backed up regularly to prevent data loss or damage. The backup data should be stored in the cloud to ensure the security and reliability of storage. Recovery tests should be performed regularly to ensure the availability and integrity of the backup data.

[0065] The fault feature extraction module is used to perform feature analysis on the pre-processed monitoring data, analyze the historical fault data to extract the relevant fault features of the power equipment, integrate them to obtain the fault feature sequence, and perform quality verification on the pre-processed monitoring data to ensure the accuracy, completeness and consistency of the data, including checking the missing values, abnormal values, duplicate values ​​and the correctness of the data format, and organize and sort the verified data according to the equipment type and time range dimensions, extract the historical fault data of various types of power equipment in the substation from the historical database, specifically including the time of the fault, equipment type, fault type, fault phenomenon, and fault cause, and sort the collected historical fault data to remove duplicate, invalid or redundant data to ensure the accuracy and availability of the data, perform feature analysis on the historical fault data, and extract the features related to the power equipment fault, specifically including voltage fluctuation, current anomaly, power change, temperature rise, humidity change, for voltage, current, and power data, build a time series model to capture the feature changes before and after the fault occurs, for temperature and humidity data, convert them into feature vectors, and combine them with time series features to comprehensively build a fault feature sequence;

[0066] The event warning module combines machine learning algorithms and fault feature sequences to further analyze monitoring data, evaluate abnormal trends in the operation of power equipment, determine the authenticity of faults in the operation of power equipment, improve the sensitivity and accuracy of fault warnings, reduce false alarms and missed alarms, and provide timely fault handling guidance for operation and maintenance personnel;

[0067] The fault diagnosis module, based on the event warning evaluation results, conducts in-depth analysis of the monitoring data of real faults, determines the cause and location of the fault, and classifies different fault levels according to the severity of the fault. It provides corresponding fault diagnosis reports and suggestions to help operation and maintenance personnel quickly locate the fault point, formulate reasonable fault handling plans, and shorten the fault recovery time;

[0068] The data visualization module is used to visualize the monitoring data and fault diagnosis results, assist operation and maintenance personnel in analyzing the operating status and performance changes of the equipment, provide intuitive data display and analysis results, and help operation and maintenance personnel make more scientific decisions and judgments.

[0069] The second embodiment is based on the first embodiment. Figure 3 , Figure 4 As shown, in the event warning module, the evaluation process of abnormal operation trend of power equipment includes:

[0070] Based on the historical fault features of voltage fluctuation, current anomaly, power change, temperature rise, and humidity change in the fault feature sequence, the feature data set is integrated and obtained, and the feature data set is divided into a training set and a test set. The data of the training set is combined with the K-means clustering algorithm to build an abnormal event recognition model so that it can recognize the pattern of abnormal events. The abnormal event recognition model is tested using the test set data to adjust the model parameters, optimize the model performance, and improve the accuracy of abnormal detection. The pre-processed monitoring data is input into the trained abnormal event recognition model. The model analyzes the matching degree with the abnormal event category based on the characteristics of the input data to determine whether there is an abnormal event. Combined with the fault feature sequence and the abnormal event evaluation results, the characteristics of the historical fault data and the current abnormal event are compared. The duration, impact range, and degree of feature change of the abnormal event are further analyzed to calculate the abnormal event evaluation index, and the abnormal trend of the power equipment operation is evaluated to determine whether there is a real fault in the power equipment.

[0071] Furthermore, the specific calculation process of the abnormal event assessment index is as follows:

[0072] Traverse the current monitoring data and historical fault data, determine the current monitoring values ​​of the current voltage, current, power, temperature and humidity characteristics, and obtain the reference value of each characteristic based on the standard operating conditions, wherein for the temperature and humidity characteristics, determine their maximum safety values, and for each characteristic parameter, calculate the deviation between its current monitoring value and the reference value, and normalize each characteristic parameter, wherein for the voltage, current and power characteristics, divide each deviation by its corresponding reference value, and for the temperature and humidity characteristics, divide each deviation by the difference between its maximum safety value and the reference value, add the normalized deviation values, divide by the number of characteristic parameters, calculate the comprehensive deviation score, and take the square root of the comprehensive deviation score to obtain the abnormal event assessment index;

[0073] Furthermore, the calculation expression of the abnormal event evaluation index is:

[0074]

[0075] Among them, A represents the abnormal event assessment index, V f Indicates the current voltage value, V b Indicates the reference value of voltage, I f Indicates the current value, I b Indicates the reference value of current, P f Indicates the current power value, P b Indicates the reference value of power, T f Indicates the current temperature value, T b Indicates the reference value of temperature, T max Indicates the maximum safe value of temperature, H fIndicates the current humidity value, H b Indicates the reference value of humidity, H max Indicates the maximum safe value of humidity. The value range of A is between 0 and 1. When all parameters are near their baseline values, A is close to 0, indicating no abnormality. The more any parameter deviates from its baseline value, the closer the value of A is to 1, indicating a higher possibility of abnormal events. The risk level of abnormal events is assessed by calculating the deviation of voltage, current, power, temperature and humidity from their respective baseline values ​​and combining them with the maximum safe value. The influence of each parameter is balanced through the radical formula to ensure that the change of each parameter can have a reasonable impact on the final evaluation index, providing a quantitative evaluation method for abnormal trend analysis of power equipment.

[0076] In the fault diagnosis module, the fault level classification and determination process includes:

[0077] Receive monitoring data and abnormal event evaluation index results from the event warning module, identify abnormal conditions of power equipment in substations, analyze specific characteristic changes of abnormal events, and then compare characteristics with patterns in historical fault databases to identify fault types and locations. Evaluate the severity of faults based on potential safety risks of faults in historical fault data and their impact on system operation. According to the severity of the faults and the abnormal event evaluation index, classify faults into different fault levels, namely, level 1 fault level, level 2 fault level, and level 3 fault level. The severity of fault levels increases from level 1 to level 3. Combined with the abnormal event evaluation index and the divided fault levels, set corresponding fault evaluation thresholds for each fault level to determine whether the fault meets the standards of the corresponding level. Generate a detailed fault diagnosis report based on the results of fault pattern recognition and fault level classification, including fault cause, location, severity, impact, and recommended action plan. Provide targeted processing suggestions and maintenance strategies based on the specific situation of the fault to assist operation and maintenance personnel in quickly responding to and handling faults.

[0078] Furthermore, the value of the abnormal event assessment index and the fault assessment threshold preset by the fault level are obtained to match the three levels of fault levels, which are:

[0079] Level 1 fault level: 0 <A≤θ L A minor fault means that the monitoring data deviates slightly from the baseline value and there is a minor abnormality, which can be handled during routine maintenance.

[0080] Secondary fault level: θ L <A≤θ H A fault of medium severity means that the monitoring data deviates from the baseline value to a certain extent, and there is a medium degree of abnormality, which requires response and processing within a certain period of time;

[0081] Three levels of fault level: θH <A < 1 represents the most serious fault, indicating that the monitored data deviates greatly from the reference value, there are serious abnormal situations, and immediate response and handling are required;

[0082] where A is the abnormal event evaluation index, and θ L is the lower threshold corresponding to the secondary fault level and the upper threshold corresponding to the primary fault level, and θ H is the lower threshold corresponding to the tertiary fault level and the upper threshold corresponding to the secondary fault level, and θ L = 0.5, and θ H = 0.8;

[0083] In the data visualization module, the process of visually displaying the monitored data and the fault diagnosis results includes:

[0084] Collect the monitored data and the fault diagnosis results, including historical fault data, real-time monitoring data, and the analysis results provided by the fault diagnosis module, and convert the data into a visual chart data format. Use charts to display the real-time monitoring data on the visualization big screen. The charts include line charts, bar charts, and pie charts, showing the changing trends of the key parameters of the substation power equipment over time, and display the fault diagnosis results on the visualization big screen, including key information such as the fault type, location, and severity. Different types of faults are distinguished by different colors, and then the current data is compared with the historical data to discover potential problems and improvement points. Use visualization tools to perform trend analysis on the data, identify abnormal points and fluctuations in the data, and predict the future operating status of the power equipment by analyzing the trends and changes of the data. According to the analysis results of the data, output targeted operation and maintenance suggestions.

[0085] Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art and related fields without creative efforts shall fall within the protection scope of the present invention. The structures, devices, and operation methods not specifically described and explained in the present invention, unless otherwise specified and limited, are implemented according to the conventional means in the art.

Claims

1. A real-time monitoring and analysis platform for power parameters of a substation, comprising a monitoring and analysis platform, characterized in that: The monitoring and analysis platform is communicatively connected with a real-time monitoring module, a data acquisition and processing module, a data storage and management module, a fault feature extraction module, an event warning module, a fault diagnosis module and a data visualization module, wherein the modules are connected by electrical signals; The real-time monitoring module is used to monitor the operating status of various power equipment in the substation in real time; The data acquisition and processing module is used to collect monitoring data of various types of power equipment in the substation, including key parameters such as voltage, current, power, temperature, and humidity, and pre-process the collected monitoring data, wherein the monitoring data includes historical fault data and real-time monitoring data; The data storage and management module is used to store and manage the pre-processed monitoring data; The fault feature extraction module is used to perform feature analysis on the pre-processed monitoring data, analyze historical fault data to extract relevant fault features of the power equipment, and integrate them to obtain a fault feature sequence; The event warning module, combined with machine learning algorithms and fault feature sequences, further analyzes monitoring data, evaluates abnormal trends in the operation of power equipment, and determines the authenticity of faults in the operation of power equipment; The fault diagnosis module, based on the event warning evaluation results, conducts in-depth analysis of the monitoring data of the real fault, determines the cause and location of the fault, and divides the fault into different levels according to the severity of the fault; The data visualization module is used to visualize the monitoring data and fault diagnosis results.

2. A substation power parameter real-time monitoring and analysis platform according to claim 1, characterized in that: In the data collection and processing module, the collection process of the power equipment monitoring data specifically includes: The monitoring data of the power equipment is collected through various sensors deployed on the power equipment of the substation, where the sensors include voltage sensors, current sensors, power sensors, temperature sensors and humidity sensors. The operating parameters of the power equipment are read through the sensors and the analog signals are converted into digital signals. Preprocessing the collected power equipment monitoring data, wherein the preprocessing operation includes data cleaning, denoising and calibration steps; Integrate the pre-processed data from different sensors into a unified data format and add a timestamp to each data point.

3. A real-time monitoring and analysis platform for power parameters of a substation according to claim 2, characterized in that: In the data storage and management module, the storage and management process of monitoring data includes: According to the needs of monitoring data, the table structure and index of the database are designed. The table structure includes monitoring data table, equipment information table, user information table and role permission table. The monitoring data table is used to store pre-processed monitoring data, including equipment ID, monitoring time, voltage, current, power, temperature, and humidity fields. The equipment information table records the basic information of the equipment, including equipment ID, equipment name, installation location, and manufacturer. The user information table stores the basic information of the user, including user ID, user name, password, and role. The role permission table defines the permissions of different roles, namely administrators and operation and maintenance personnel, and is associated with the user information table to establish indexes for key fields in the monitoring data table; Establish a data access control mechanism and record user login and operation logs; Run data cleaning procedures regularly to identify and mark redundant data, delete it from the database, and record the process and results of data cleaning; The pre-processed monitoring data is stored in the database according to the designed database table structure, and the database is backed up regularly and recovery tests are performed regularly.

4. A substation power parameter real-time monitoring and analysis platform according to claim 3, characterized in that: In the fault feature extraction module, the process of acquiring the fault feature sequence specifically includes: Verify the quality of pre-processed monitoring data, and organize and sort the verified data according to equipment type and time range dimensions; Extract historical fault data of various power equipment in the substation from the historical database, including the time of fault occurrence, equipment type, fault type, fault phenomenon, and fault cause, and organize the collected historical fault data; Perform feature analysis on historical fault data to extract features related to power equipment failures, including voltage fluctuations, current anomalies, power changes, temperature rise, and humidity changes; For voltage, current, and power data, a time series model is constructed to capture the characteristic changes before and after the fault occurs. For temperature and humidity data, they are converted into feature vectors and combined with time series features to comprehensively construct a fault feature sequence.

5. A real-time monitoring and analysis platform for power parameters of a substation according to claim 4, characterized in that: In the event warning module, the evaluation process of abnormal operation trend of power equipment includes: Based on the historical fault features of the fault feature sequence, such as voltage fluctuation, current anomaly, power change, temperature rise, and humidity change, the feature data set is integrated and obtained, and the feature data set is divided into a training set and a test set; The abnormal event recognition model is constructed by combining the training set data with the K-means clustering algorithm, and the abnormal event recognition model is tested using the test set data to adjust the model parameters; The pre-processed monitoring data is input into the trained abnormal event recognition model. The model analyzes the matching degree with the abnormal event category based on the characteristics of the input data and determines whether there is an abnormal event. Combine the fault feature sequence and abnormal event assessment results, compare the historical fault data and the characteristics of the current abnormal event, further analyze the duration, impact range, and degree of characteristic change of the abnormal event to calculate the abnormal event assessment index, and evaluate the abnormal trend of the power equipment operation to determine whether there is a real fault in the power equipment.

6. A substation power parameter real-time monitoring and analysis platform according to claim 5, characterized in that: The specific calculation process of the abnormal event evaluation index is as follows: Traverse the current monitoring data and historical fault data, determine the current monitoring values ​​of the current voltage, current, power, temperature and humidity characteristics, and obtain the reference value of each characteristic based on the standard operating conditions, where for the temperature and humidity characteristics, determine their maximum safe values; For each characteristic parameter, calculate the deviation between its current monitoring value and the reference value, and perform normalization on each characteristic parameter, where for voltage, current and power characteristics, divide each deviation by its corresponding reference value, and for temperature and humidity characteristics, divide each deviation by the difference between its maximum safe value and the reference value; The normalized deviation values ​​are added together, divided by the number of characteristic parameters, the comprehensive deviation score is calculated, and the square root of the comprehensive deviation score is taken to obtain the abnormal event assessment index.

7. A substation power parameter real-time monitoring and analysis platform according to claim 6, characterized in that: The calculation expression of the abnormal event evaluation index is: Among them, A represents the abnormal event assessment index, V f Indicates the current voltage value, V b Indicates the reference value of voltage, I f Indicates the current value, I b Indicates the reference value of current, P f Indicates the current power value, P b Indicates the reference value of power, T f Indicates the current temperature value, T b Indicates the reference value of temperature, T max Indicates the maximum safe value of temperature, H f Indicates the current humidity value, H b Indicates the reference value of humidity, H max Indicates the maximum safe value of humidity. The value range of A is between 0 and 1.

8. A substation power parameter real-time monitoring and analysis platform according to claim 7, characterized in that: In the fault diagnosis module, the fault level classification and determination process includes: Receive monitoring data and abnormal event assessment index results from the event warning module, identify abnormal conditions of substation power equipment, and analyze specific characteristic changes of abnormal events, and then compare the characteristics with the patterns in the historical fault database to identify the fault type and location; Assess the severity of the fault based on the potential safety risks of the fault in historical fault data and its impact on system operation; According to the severity of the fault and the abnormal event assessment index, the fault is divided into different fault levels, namely, level 1 fault level, level 2 fault level and level 3 fault level. The severity of the fault level increases from level 1 to level 3. Combine the abnormal event assessment index and the classified fault levels, and set a corresponding fault assessment threshold for each fault level to determine whether the fault reaches the standard of the corresponding level; Based on the results of fault mode identification and fault level classification, a fault diagnosis report is generated, including the cause, location, severity, impact and recommended action plan of the fault. Based on the specific circumstances of the fault, targeted processing suggestions and maintenance strategies are provided to assist operation and maintenance personnel to quickly respond to and handle the fault.

9. A substation power parameter real-time monitoring and analysis platform according to claim 8, characterized in that: The value of the abnormal event assessment index and the fault assessment threshold preset for the fault level are obtained to match the three levels of fault levels, which are: Level 1 fault level: 0 <A≤θ L ; Secondary fault level: θ L <A≤θ H ; Three levels of fault level: θ H <A<1; Among them, A is the abnormal event assessment index, θ L is the lower threshold corresponding to the second-level fault level and the upper threshold corresponding to the first-level fault level, θ H is the lower threshold corresponding to the third-level fault level and the upper threshold corresponding to the second-level fault level, θ L =0.5,θ H =0.

8.

10. A substation power parameter real-time monitoring and analysis platform according to claim 9, characterized in that: In the data visualization module, the process of visually displaying monitoring data and fault diagnosis results includes: Gather monitoring data and fault diagnosis results, including historical fault data and real-time monitoring data as well as analysis results provided by the fault diagnosis module, and convert the data into a visual chart data format; Real-time monitoring data is displayed on a visualization screen in the form of charts, including line charts, bar charts, and pie charts, showing the changing trends of key parameters of substation power equipment over time. Fault diagnosis results are also displayed on the visualization screen, including key information such as fault type, location, and severity. Different types of faults are distinguished by different colors, and current data is compared with historical data to identify potential problems and improvement points. Use visualization tools to perform trend analysis on data, identify anomalies and fluctuations in the data, and predict the future operating status of power equipment by analyzing the trends and changes in the data. Based on the analysis results of the data, output targeted operation and maintenance suggestions.

Images