Asset monitoring system and method applied to power grid data

Abstract

The present invention discloses an asset monitoring system and method applied to power grid data, relates to the technical field of power grid data monitoring, and is used to solve the problem that the data acquisition method of the existing power grid monitoring system cannot be adaptively adjusted to the specific conditions of different acquisition nodes, which reduces the quality of the acquired data and is also easy to cause the problem of system load. The present invention includes a data acquisition module, a data transmission module, a data processing module and a status evaluation module; the data acquisition module is used to collect various types of data from key nodes in the power grid; the present invention, by installing sensors at key nodes of the power grid and establishing an adaptive data acquisition mechanism, the system can monitor the operating status of the power grid in real time, including key parameters such as voltage, current, frequency and temperature. This adaptive adjustment mechanism can dynamically adjust the data acquisition frequency according to parameters such as power grid load changes, voltage and current stability, and equipment temperature, so as to optimize data quality and system resource usage.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid data monitoring, and in particular to an asset monitoring system and method applied to power grid data. Background Art

[0002] With the continuous growth of global energy demand and the widespread application of renewable energy, the scale and complexity of power grid systems are also increasing. Modern power grids not only need to deal with the generation, transmission and distribution of traditional energy, but also need to adapt to the access of distributed energy such as wind power and solar energy, while ensuring the stability of the power grid and the reliability of power supply. In this context, power grid asset management has become particularly important, which involves multiple aspects such as status monitoring, performance evaluation, maintenance strategy formulation and risk warning of various assets in the power grid.

[0003] Traditional power grid asset management relies on manual inspections and regular maintenance, which is inefficient and difficult to cope with real-time changes and emergencies in power grid operation. In addition, with the expansion of power grid scale and the surge in data volume, manual processing and analysis of data has become impractical. Therefore, there is a need for an asset monitoring system and method that can monitor and intelligently analyze power grid data in real time to improve the operating efficiency and reliability of the power grid, reduce the probability of failures, and optimize maintenance costs.

[0004] In recent years, with the rapid development of information technology and artificial intelligence, machine learning, big data analysis and Internet of Things technologies have provided new solutions for power grid asset management. By deploying smart sensors and using advanced data analysis algorithms, real-time monitoring and evaluation of power grid asset status can be achieved, and potential failures and performance degradation can be predicted, thereby achieving optimal asset configuration and maintenance strategy formulation.

[0005] However, although some power grid monitoring systems have adopted data analysis technology, most of these systems collect data at a preset collection frequency. This method cannot adaptively adjust the specific conditions of different collection nodes, which reduces the quality of collected data and easily causes system load. At the same time, there are no protective measures for data transmission of power grid data assets, which are easily attacked and stolen by criminals. Therefore, an asset monitoring system for power grid data is designed;

[0006] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0007] The purpose of the present invention is to solve the problem that the data collection method of the existing power grid monitoring system cannot be adaptively adjusted to the specific conditions of different collection nodes, which reduces the quality of the collected data and easily causes the problem of system load, and proposes an asset monitoring system and method applied to power grid data.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] Asset monitoring systems for power grid data, including:

[0010] The data acquisition module is used to collect various data from key nodes in the power grid. The specific steps are as follows:

[0011] First, sensors are installed at key nodes of the power grid, including transformers, circuit breakers and transmission lines, to collect key parameters such as voltage, current, frequency and temperature;

[0012] Then, an adaptive data collection mechanism is established to dynamically adjust the data collection frequency according to the node parameters to optimize the data quality and system resource usage. The node parameters include: grid load changes, voltage and current stability, equipment temperature, fault conditions and historical performance data. The negative variable value FBZ, pressure flow value YLZ, temperature difference value YWZ, barrier evaluation value ZPZ and performance value XSZ are analyzed respectively through the node parameters. After normalization, the negative variable value FBZ is used as the bottom circle radius to establish a bottom circle, the temperature difference value YWZ is used as the height to establish a cone, and then the bottom circle of the cone is used as the center and the barrier evaluation value ZPZ is used as the radius to establish concentric circles. The performance value XSZ is used as the diameter to establish a cylinder in the opposite direction of the cone. Then, the bottom circle of the cone is used as the center and the pressure flow value YLZ is used as the radius to establish a cylinder that is transversely cut in a direction perpendicular to the cylinder and the cone, and the volume of the irregular body after cutting is calculated and recorded as the adaptive value.

[0013] The obtained adaptation value is then compared with a plurality of preset adaptation value intervals, and different frequency adjustment levels are respectively set corresponding to the plurality of adaptation value intervals. When the adaptation value interval to which the adaptation value belongs is determined, the corresponding frequency adjustment level is obtained, and adaptive adjustment is performed according to the percentage on the preset standard data acquisition frequency according to the frequency adjustment level;

[0014] A data transmission module, used to upload the data collected by the sensor through a wired or wireless communication network;

[0015] Data processing module, used to clean, integrate and store the collected data;

[0016] The status assessment module is used to evaluate the status of power grid assets and identify abnormal situations and potential risks using data analysis algorithms.

[0017] Furthermore, the process of uploading the data collected by the sensor through the communication network by the data transmission module is as follows:

[0018] In the process of uploading the collected data, a security mechanism is used to ensure the security of the data during transmission and storage to prevent data leakage and tampering. The specific steps are as follows:

[0019] First, we analyze the data security requirements of key nodes in detail, including the data sensitivity, data value, data loss and physical security measures of key nodes, and obtain the data sensitivity value sm, value value js, damage assessment value pz and physical protection value wf respectively. After normalization, they are entered into the following formula: The digital safety value AXZ is obtained, and this digital safety value is used as the standard for measuring the data security requirements of key node transmission; where α, β, ε, φ are the preset weight coefficients of the digital sensitivity value, the price value, the damage assessment value and the physical protection value respectively;

[0020] The obtained digital safety value is then compared with the three preset digital safety value intervals. The three digital safety value intervals correspond to different security policy levels, namely the first security policy, the second security policy and the third security policy. The larger the digital safety value, the higher the corresponding security policy level, and vice versa.

[0021] Furthermore, the specific processes of different security policies in the data transmission module are as follows:

[0022] The first security strategy includes: selecting encryption algorithms and key management schemes. For data transmission at key nodes, select SSL or TLS security protocols for end-to-end encryption; for data storage, select AES symmetric encryption algorithm or RSA asymmetric encryption algorithm for encryption;

[0023] The second security strategy also includes, based on the first security strategy: implementing a two-way authentication mechanism to ensure mutual authentication between the data collection end and the data receiving end, preventing unauthorized devices from accessing the system, and verifying the integrity of the transmitted data through hash functions and digital signature technology;

[0024] The third security strategy also includes, based on the second security strategy: setting up access control policies, granting access rights to authorized users and systems, and deploying intrusion detection systems and security information event management systems.

[0025] Furthermore, the analysis process of the data sensitivity value sm, the price value js, the damage evaluation value pz and the physical protection value wf in the data transmission module is as follows:

[0026] The data sensitivity is determined by checking whether the data transmitted by the key nodes contains sensitive data such as the grid topology structure, real-time load data, and user electricity consumption information, and analyzing the components of the transmitted data. When the above sensitive data exists, the proportion of sensitive data is analyzed, and the analyzed proportion is recorded as the digital sensitivity value sm;

[0027] Data value is determined by analyzing the importance and value of the transmitted data to business operations, assigning a score of 1-5 to both the importance and value, and then normalizing and summing the two scores to obtain the value js;

[0028] Data loss loss is assessed by evaluating the degree of damage caused by data loss or leakage to the power grid system, including economic loss, time loss and reputation damage, and assigning a score of 1-10, recorded as the loss evaluation value pz. The higher the loss evaluation value, the greater the corresponding data loss loss.

[0029] Physical security measures analyze the physical security of the operating environment of key nodes. Specifically, the security measures and physical protection are scored, and the score is calculated and recorded as the physical protection value wf.

[0030] Furthermore, the specific process of the data acquisition module to obtain the negative variable value FBZ, the pressure flow value YLZ, the temperature difference value YWZ, the barrier evaluation value ZPZ and the property value XSZ through the node parameters is as follows:

[0031] Grid load changes in node parameters: collect real-time load data of the grid, and establish a load curve based on the real-time load data. Calculate the difference between the peak and valley of the load according to the load curve, record it as the negative difference, and then calculate the ratio of the maximum load to the average load, record it as the load mean, and after normalization, multiply the load mean by a constant l and sum it with the negative difference to obtain the negative change value FBZ;

[0032] Voltage and current stability: Get real-time voltage and current data, and analyze them to get voltage deviation, current deviation, voltage fluctuation rate and load flow, and calibrate them as yp, lp, yb and fl respectively. After normalization, enter the following formula: To obtain the pressure flow value YLZ;

[0033] Equipment temperature: By monitoring the real-time temperature of the equipment, a temperature curve is established according to the real-time temperature data, and upper and lower standard lines are established in the temperature curve according to the preset upper and lower limits of the standard. Then, the closed area formed by the temperature curve above the upper standard line and below the lower standard line is analyzed, and the area of ​​all closed areas is summed up and recorded as the different temperature value YWZ;

[0034] Fault situation: By counting the number of times the node equipment is used and the number of times the fault occurs, where the number of times the node equipment is used is counted as one time, and the ratio of the number of times the fault occurs to the number of times used is calculated, recorded as the fault occupancy value, and then the ratio of the time when the node equipment fails to the time when it is in normal operation is obtained, recorded as the fault time value, and then the fault occupancy value and the fault time value are normalized, multiplied by the constants q and t respectively, and summed to obtain the fault evaluation value ZPZ;

[0035] Historical performance data: The operation status, maintenance records and equipment efficiency of node equipment in historical data are measured. The operation status is analyzed by obtaining the total operation time, shutdown times and fault interval time. The total operation time, shutdown times and fault interval time are calibrated as gz, cs and gj respectively, and then normalized and entered into the following formula: To obtain the current evaluation value SP, and use this current evaluation value as the standard for measuring the operation status;

[0036] Maintenance records retrieve the maintenance data of node equipment to obtain the total number of maintenance times, average maintenance time, and average economic cost of maintenance. After normalization, the total number of maintenance times is used as the radius of the bottom circle to establish a bottom circle, and the average maintenance time and average economic cost of maintenance are used as the height to establish a cylinder. The volume of the cylinder is calculated and recorded as the dimension record value WJ, and this dimension record value is used as the standard for maintenance records;

[0037] Equipment efficiency is obtained by obtaining the energy conversion efficiency and the historical comprehensive efficiency of the equipment, normalizing them and summing them up to obtain the set efficiency value SX, which is used as the standard for measuring equipment efficiency;

[0038] Then, the obtained time evaluation value SP, dimension value WJ and set effectiveness value SX are normalized and then entered into the following formula: To obtain the data value XSZ.

[0039] Furthermore, the specific operation steps of the data processing module for cleaning, integrating and storing the collected data are as follows:

[0040] First, the format of the raw data is converted and data cleaning techniques are applied, including noise removal, smoothing, and outlier detection and processing;

[0041] Then merge the data from different sources into a unified data store;

[0042] The cleaned and integrated data is then stored in a database;

[0043] Choose a storage solution based on the importance and frequency of data use, including relational databases, non-relational databases, or data warehouses;

[0044] Then regularly check the data quality, including accuracy, completeness, consistency, and timeliness;

[0045] Apply data quality rules and standards to continuously monitor and evaluate data;

[0046] Finally, the data is updated regularly to reflect the latest status of power grid operation and to maintain the data storage and processing systems.

[0047] Furthermore, the specific operation steps of the status assessment module to assess the status of the power grid assets are as follows:

[0048] First, relevant features of condition assessment, including statistics, trends, and patterns, are extracted from the raw data, and feature selection techniques are used to determine the features;

[0049] Then, according to the characteristics of power grid data assets and the evaluation objectives, appropriate machine learning algorithms are selected, including classification, regression and clustering; historical data is used to train the model and adjust the model parameters;

[0050] Use validation sets or cross-validation methods to evaluate the accuracy and generalization ability of the model; use model evaluation metrics including accuracy, recall, and F1 score to determine the predictive performance of the model;

[0051] Then, anomaly detection algorithms are applied to identify abnormal patterns in the data. When the data has abnormal patterns, it indicates that there are potential problems with the key node data. The power grid data is monitored in real time, and when an abnormal situation is detected, an alarm is triggered immediately;

[0052] The trained model is then used to evaluate the current status of grid assets and predict potential risks and future trends. Based on the evaluation results, decision support is provided for grid operation and maintenance, including maintenance plans and load adjustments.

[0053] Furthermore, the asset monitoring method applied to power grid data includes the following steps:

[0054] S1: First, various types of data are collected through sensors installed at key nodes of the power grid, and an adaptive data collection mechanism is established to dynamically adjust the data collection frequency according to node parameters;

[0055] S2: The data collected by the sensor is then uploaded through the communication network. During the uploading process, the security mechanism is used to conduct a detailed analysis of the data security requirements of key nodes, and different security strategies are adopted for the data security requirements of different key nodes.

[0056] S3: The collected data is then cleaned, integrated and stored to ensure data quality and availability;

[0057] S4: Finally, data analysis algorithms are used to evaluate the status of power grid assets by combining processed data with historical data to identify abnormal situations and potential risks.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] (1) The present invention installs sensors at key nodes of the power grid and establishes an adaptive data acquisition mechanism. The system can monitor the operation status of the power grid in real time, including key parameters such as voltage, current, frequency and temperature. This adaptive adjustment mechanism can dynamically adjust the data acquisition frequency according to parameters such as power grid load changes, voltage and current stability, and equipment temperature, thereby optimizing data quality and system resource usage.

[0060] (2) In the present invention, the data transmission module adopts a security mechanism to ensure the security of data during transmission and storage. By conducting a detailed analysis of the data security requirements of key nodes and adopting different security strategies according to the analysis results, including encryption algorithms, two-way authentication mechanisms, and access control strategies, data leakage and tampering can be effectively prevented;

[0061] (3) The present invention uses data analysis algorithms to evaluate the status of power grid assets and identify abnormal situations and potential risks. Through steps such as feature engineering, model selection and training, model verification and evaluation, and anomaly detection, the system can predict the future status of power grid assets and provide support for maintenance and operation decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0063] Figure 1 It is a general block diagram of the asset monitoring system applied to power grid data in the present invention;

[0064] Figure 2 This is a flow chart of the asset monitoring method applied to power grid data in the present invention. DETAILED DESCRIPTION

[0065] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] It should be understood that the terms "include" and "comprising" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0067] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0068] like Figure 1 As shown, the asset monitoring system and method applied to power grid data include a data acquisition module, a data transmission module, a data processing module and a status evaluation module;

[0069] The data acquisition module is used to collect various types of data from key nodes in the power grid;

[0070] The data collected includes real-time operation data and historical data; real-time operation data includes voltage, current, frequency, and load; historical data includes the age and maintenance records of equipment; the specific steps are as follows: first, install sensors at key nodes of the power grid, including transformers, circuit breakers, and transmission lines to collect key parameters such as voltage, current, frequency, and temperature;

[0071] Then establish an adaptive data collection mechanism to dynamically adjust the data collection frequency according to the node parameters to optimize data quality and system resource usage. The node parameters include:

[0072] Grid load change: collect real-time load data of the grid, and establish a load curve based on the real-time load data. Calculate the difference between the peak and valley of the load according to the load curve, record it as the negative difference, and then calculate the ratio of the maximum load to the average load, record it as the average load. After normalization, multiply the average load by a constant l and sum it with the negative difference. The constant l is 20.31 to obtain the negative change value FBZ, and use the negative change value as the standard for measuring grid load changes;

[0073] Voltage and current stability: Get real-time voltage and current data, and analyze them to get voltage deviation, current deviation, voltage fluctuation rate and load flow, and calibrate them as yp, lp, yb and fl respectively. After normalization, enter the following formula: To obtain the voltage-current value YLZ, and use this voltage-current value as a standard to measure the stability of voltage and current;

[0074] Equipment temperature: By monitoring the real-time temperature of the equipment, a temperature curve is established according to the real-time temperature data, and upper and lower standard lines are established in the temperature curve according to the preset upper and lower limits of the standard. Then, the closed area formed by the temperature curve above the upper standard line and below the lower standard line is analyzed, and the area of ​​all closed areas is summed up and recorded as the different temperature value YWZ, which is used as the standard for measuring the temperature stability of the equipment;

[0075] Fault situation: By counting the number of times the node equipment is used and the number of times the fault occurs, where the number of times the node equipment is used is counted as one time, and the ratio of the number of times the fault occurs to the number of times used is calculated, recorded as the fault occupancy value, and then the ratio of the time when the node equipment fails to the time when it is in normal operation is obtained, recorded as the fault time value, and then the fault occupancy value and the fault time value are normalized, multiplied by constants q and t respectively, and summed to obtain the fault evaluation value ZPZ. The constants q and t are taken as 10.22 and 11.54 respectively. The obtained fault evaluation value is used as the standard for measuring the fault situation of the node equipment;

[0076] Historical performance data: The operation status, maintenance records and equipment efficiency of node equipment in historical data are measured. The operation status is analyzed by obtaining the total operation time, shutdown times and fault interval time. The total operation time, shutdown times and fault interval time are calibrated as gz, cs and gj respectively, and then normalized and entered into the following formula: To obtain the time evaluation value SP, and use this time evaluation value as the standard for measuring the operation status; the maintenance record retrieves the maintenance data of the node equipment to obtain the total number of maintenance times, the average maintenance time and the average economic cost of maintenance. After normalization, the total number of maintenance times is used as the radius of the bottom circle to establish the bottom circle, and the average maintenance time and the average economic cost of maintenance are used as the height to establish the cylinder, and the volume of the cylinder is calculated and recorded as the dimension record value WJ, and this dimension record value is used as the standard for maintenance records; the equipment efficiency is obtained by obtaining the energy conversion efficiency and the historical comprehensive efficiency of the equipment, and the sum is normalized to obtain the set value SX, and this set value is used as the standard for measuring equipment efficiency; the obtained time evaluation value SP, dimension record value WJ and set value SX are normalized and then inserted into the following formula: To obtain the performance value XSZ, and use this performance value as a standard for measuring historical performance data;

[0077] Then normalize the negative variable value FBZ, pressure flow value YLZ, different temperature value YWZ, barrier evaluation value ZPZ and performance value XSZ respectively, and use the negative variable value FBZ as the radius of the bottom circle to establish a bottom circle, and the different temperature value YWZ as the height to establish a cone, and then use the bottom circle of the cone as the center and the barrier evaluation value ZPZ as the radius to establish concentric circles, and use the performance value XSZ as the diameter to establish a cylinder in the opposite direction of the cone, and then use the bottom circle of the cone as the center and the pressure flow value YLZ as the radius to establish a horizontally cut cylinder perpendicular to the cylinder and the cone, and calculate the volume of the irregular shape after cutting, which is recorded as the adaptation value;

[0078] The obtained adaptation value is then compared with several preset adaptation value intervals. Several adaptation value intervals correspond to different frequency adjustment levels. When the adaptation value interval to which the adaptation value belongs is determined, the corresponding frequency adjustment level is obtained, and adaptive adjustment is performed according to the percentage on the preset standard data acquisition frequency based on the frequency adjustment level.

[0079] The data transmission module is used to upload the data collected by the sensor through a wired or wireless communication network;

[0080] During the upload process, security mechanisms are used to ensure the security of data during transmission and storage to prevent data leakage and tampering. The specific steps are as follows: First, a detailed analysis of the data security requirements of key nodes is conducted, including analysis of the data sensitivity, data value, data loss and physical security measures of key nodes;

[0081] The data sensitivity is determined by checking whether the data transmitted by the key nodes contains sensitive data such as the grid topology structure, real-time load data, and user electricity consumption information, and analyzing the components of the transmitted data. When the above sensitive data exists, the proportion of sensitive data is analyzed, and the analyzed proportion is recorded as the digital sensitivity value sm, which is used as a standard for measuring data sensitivity. The data value is analyzed by analyzing the importance and value of the transmitted data to the business operation, and the importance and value are assigned a score of 1-5. After normalization, the two scores are summed to obtain the value js, which is used as a standard for measuring data value. The data loss loss is evaluated by assessing the degree of damage caused by data loss or leakage to the grid system, including economic loss, time loss, and reputation damage, and is assigned a score of 1-10, recorded as the loss evaluation value pz. The higher the loss evaluation value, the greater the corresponding data loss loss. The physical security measures are analyzed by the physical security of the operating environment of the key nodes, specifically by scoring the security measures and physical protection, and calculating the score sum, which is recorded as the physical protection value wf, and the physical protection value is used as a standard for measuring physical security measures.

[0082] Then, the obtained digital sensitivity value sm, price value js, damage evaluation value pz and physical protection value wf are normalized and entered into the following formula: The digital safety value AXZ is obtained, and this digital safety value is used as the standard for measuring the data security requirements of key node transmission; where α, β, ε, φ are the preset weight coefficients of the digital sensitivity value, the price value, the damage assessment value and the physical protection value, and the values ​​are 1.293, 0.943, 1.154 and 1.032 respectively;

[0083] The obtained digital safety value is then compared with the three preset digital safety value intervals. The three digital safety value intervals correspond to different security policy levels, namely the first security policy, the second security policy and the third security policy. The larger the digital safety value, the higher the corresponding security policy level, and vice versa.

[0084] The first security strategy includes: selecting encryption algorithms and key management schemes. For data transmission at key nodes, select SSL or TLS security protocols for end-to-end encryption; for data storage, select AES symmetric encryption algorithm or RSA asymmetric encryption algorithm for encryption;

[0085] The second security strategy, based on the first security strategy, also includes: implementing a two-way authentication mechanism to ensure mutual authentication between the data acquisition end and the data receiving end, preventing unauthorized devices from accessing the system, and verifying the integrity of the transmitted data, and ensuring that the data has not been tampered with during transmission by using hash functions and digital signature technology;

[0086] The third security strategy, based on the second security strategy, also includes: setting up access control policies so that only authorized users and systems can access and operate data to avoid data leakage, and deploying intrusion monitoring systems and security information event management systems to monitor the security status of the data acquisition system in real time and promptly detect and respond to security incidents.

[0087] The data processing module is used to clean, integrate and store the collected data to ensure the quality and availability of the data; the specific steps are as follows:

[0088] First, the raw data is converted into a new format for further processing, and data cleaning techniques are applied, including noise removal, smoothing, and outlier detection and processing. Then, data from different sources are merged into a unified data storage to resolve data redundancy and inconsistency issues and ensure data integrity and consistency. The cleaned and integrated data is then stored in a database. Based on the importance and frequency of use of the data, a storage solution is selected, including relational databases, non-relational databases, or data warehouses. Data quality is regularly checked, including accuracy, completeness, consistency, and timeliness. Data quality rules and standards are applied to continuously monitor and evaluate data. Finally, data is regularly updated to reflect the latest status of power grid operation, and data storage and processing systems are maintained to ensure their stable operation.

[0089] The status assessment module is used to evaluate the status of power grid assets and identify abnormal conditions and potential risks using advanced data analysis algorithms, including machine learning and artificial intelligence technologies. The specific steps are as follows:

[0090] Feature engineering: Extract relevant features for status assessment from raw data, including statistics, trends, and patterns, and use feature selection techniques to determine the most influential features, reduce dimensions, and improve model performance;

[0091] Model selection and training: Select appropriate machine learning algorithms, including classification, regression, and clustering, based on the characteristics of power grid data assets and assessment objectives; use historical data to train the model and adjust model parameters to achieve optimal performance;

[0092] Model validation and evaluation: Use validation sets or cross-validation methods to evaluate the accuracy and generalization ability of the model; use model evaluation indicators including accuracy, recall, and F1 score to determine the predictive performance of the model;

[0093] Anomaly detection: Apply anomaly detection algorithms to identify abnormal patterns in data, which indicate potential problems with key node data. Monitor power grid data in real time and trigger alarms immediately if an abnormal situation is detected.

[0094] Risk assessment: Use the trained model to assess the current status of grid assets and predict potential risks and future trends; based on the assessment results, provide decision support for grid operation and maintenance, including maintenance planning and load adjustment;

[0095] Result interpretation and reporting: Interpret the model's prediction results to ensure that grid operation and maintenance personnel can understand and take appropriate measures, and generate a detailed status assessment report including assessment results, risk levels, and recommended measures;

[0096] Continuous optimization: Regularly review and update the model to adapt to changes in grid operating conditions and newly collected data, collect feedback information, continuously optimize feature engineering and model selection, and improve the accuracy and efficiency of state assessment;

[0097] Prediction and decision support module: Based on historical data and real-time data, it predicts the future status of power grid assets and provides support for maintenance and operation decisions;

[0098] User Interface Module: Provides an intuitive user interface that enables operators to easily view the status of grid assets and receive system-generated reports and recommendations.

[0099] refer to Figure 2 , the asset monitoring method applied to power grid data class includes the following steps:

[0100] S1: First, various types of data are collected through sensors installed at key nodes of the power grid, and an adaptive data collection mechanism is established to dynamically adjust the data collection frequency according to node parameters;

[0101] S2: The data collected by the sensor is then uploaded through the communication network. During the uploading process, the security mechanism is used to conduct a detailed analysis of the data security requirements of key nodes, and different security strategies are adopted for the data security requirements of different key nodes.

[0102] S3: The collected data is then cleaned, integrated and stored to ensure data quality and availability;

[0103] S4: Finally, data analysis algorithms are used to evaluate the status of power grid assets by combining processed data with historical data to identify abnormal situations and potential risks.

[0104] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An asset monitoring system applied to power grid data, characterized in that: include; The data acquisition module is used to collect various data from key nodes in the power grid. The specific steps are as follows: First, sensors are installed at key nodes of the power grid, including transformers, circuit breakers and transmission lines, to collect key parameters such as voltage, current, frequency and temperature; Then establish an adaptive data collection mechanism, dynamically adjust the data collection frequency according to the node parameters, optimize the data quality and system resource usage, where the node parameters include: grid load changes, voltage and current stability, equipment temperature, fault conditions and historical performance data, and analyze the node parameters to obtain negative change value, pressure flow value, temperature difference value, barrier evaluation value and performance value. After normalization, use the negative change value as the radius of the bottom circle to establish a bottom circle, and the temperature difference value as the height to establish a cone. Then use the bottom circle of the cone as the center and the barrier evaluation value as the radius to establish concentric circles. Use the performance value as the diameter to establish a cylinder in the opposite direction of the cone. Then use the bottom circle of the cone as the center and the pressure flow value as the radius to establish a cylinder that is transversely cut in a direction perpendicular to the cylinder and the cone, and calculate the volume of the irregular body after cutting, which is recorded as the adaptation value. The obtained adaptation value is then compared with a plurality of preset adaptation value intervals, and different frequency adjustment levels are respectively set corresponding to the plurality of adaptation value intervals. When the adaptation value interval to which the adaptation value belongs is determined, the corresponding frequency adjustment level is obtained, and adaptive adjustment is performed according to the percentage on the preset standard data acquisition frequency according to the frequency adjustment level; A data transmission module, used to upload the data collected by the sensor through a wired or wireless communication network; Data processing module, used to clean, integrate and store the collected data; The status assessment module is used to evaluate the status of power grid assets and identify abnormal situations and potential risks using data analysis algorithms.

2. The asset monitoring system applied to power grid data according to claim 1 is characterized in that: The process of uploading the data collected by the sensor through the communication network by the data transmission module is as follows: In the process of uploading the collected data, a security mechanism is used to ensure the security of the data during transmission and storage to prevent data leakage and tampering. The specific steps are as follows: First, we analyze the data security requirements of key nodes in detail, including the data sensitivity, data value, data loss and physical security measures of key nodes, and obtain the data sensitivity value sm, value value js, damage assessment value pz and physical protection value wf respectively. After normalization, they are entered into the following formula: The digital safety value AXZ is obtained, and this digital safety value is used as the standard for measuring the data security requirements of key node transmission; where α, β, ε, φ are the preset weight coefficients of the digital sensitivity value, the price value, the damage assessment value and the physical protection value respectively; The obtained digital safety value is then compared with the three preset digital safety value intervals. The three digital safety value intervals correspond to different security policy levels, namely the first security policy, the second security policy and the third security policy. The larger the digital safety value, the higher the corresponding security policy level, and vice versa.

3. The asset monitoring system applied to power grid data according to claim 2 is characterized in that: The specific process of different security policies in the data transmission module is as follows: The first security strategy includes: selecting encryption algorithms and key management schemes. For data transmission at key nodes, select SSL or TLS security protocols for end-to-end encryption; for data storage, select AES symmetric encryption algorithm or RSA asymmetric encryption algorithm for encryption; The second security strategy also includes, based on the first security strategy: implementing a two-way authentication mechanism to ensure mutual authentication between the data collection end and the data receiving end, preventing unauthorized devices from accessing the system, and verifying the integrity of the transmitted data through hash functions and digital signature technology; The third security strategy also includes, based on the second security strategy: setting up access control policies, granting access rights to authorized users and systems, and deploying intrusion detection systems and security information event management systems.

4. The asset monitoring system applied to power grid data according to claim 2 is characterized in that: The analysis process of the data sensitivity value sm, the price value js, the damage evaluation value pz and the physical protection value wf in the data transmission module is as follows: The data sensitivity is determined by checking whether the data transmitted by the key nodes contains sensitive data such as the grid topology structure, real-time load data, and user electricity consumption information, and analyzing the components of the transmitted data. When the above sensitive data exists, the proportion of sensitive data is analyzed, and the analyzed proportion is recorded as the digital sensitivity value sm; Data value is determined by analyzing the importance and value of the transmitted data to business operations, assigning a score of 1-5 to both the importance and value, and then normalizing and summing the two scores to obtain the value js; Data loss loss is assessed by evaluating the degree of damage caused by data loss or leakage to the power grid system, including economic loss, time loss and reputation damage, and assigning a score of 1-10, recorded as the loss evaluation value pz. The higher the loss evaluation value, the greater the corresponding data loss loss. Physical security measures analyze the physical security of the operating environment of key nodes. Specifically, the security measures and physical protection are scored, and the score is calculated and recorded as the physical protection value wf.

5. The asset monitoring system applied to power grid data according to claim 1 is characterized in that: The specific process of the data acquisition module to obtain the negative change value, pressure flow value, temperature difference value, barrier evaluation value and property value through analyzing the node parameters is as follows: Grid load changes in node parameters: collect real-time load data of the grid, and establish a load curve based on the real-time load data. Calculate the difference between the peak and valley of the load according to the load curve, record it as the negative difference, and then calculate the ratio of the maximum load to the average load, record it as the load mean, and after normalization, multiply the load mean by a constant l and sum it with the negative difference to obtain the negative change value FBZ; Voltage and current stability: Get real-time voltage and current data, and analyze them to get voltage deviation, current deviation, voltage fluctuation rate and load flow, and calibrate them as yp, lp, yb and fl respectively. After normalization, enter the following formula: To obtain the pressure flow value YLZ; Equipment temperature: By monitoring the real-time temperature of the equipment, a temperature curve is established according to the real-time temperature data, and upper and lower standard lines are established in the temperature curve according to the preset upper and lower limits of the standard. Then, the closed area formed by the temperature curve above the upper standard line and below the lower standard line is analyzed, and the area of ​​all closed areas is summed up and recorded as the different temperature value YWZ; Fault situation: By counting the number of times the node equipment is used and the number of times the fault occurs, where the number of times the node equipment is used is counted as one time, and the ratio of the number of times the fault occurs to the number of times used is calculated, recorded as the fault occupancy value, and then the ratio of the time when the node equipment fails to the time when it is in normal operation is obtained, recorded as the fault time value, and then the fault occupancy value and the fault time value are normalized, multiplied by the constants q and t respectively, and summed to obtain the fault evaluation value ZPZ; Historical performance data: The operation status, maintenance records and equipment efficiency of node equipment in historical data are measured. The operation status is analyzed by obtaining the total operation time, shutdown times and fault interval time. The total operation time, shutdown times and fault interval time are calibrated as gz, cs and gj respectively, and then normalized and entered into the following formula: To obtain the current evaluation value SP, and use this current evaluation value as the standard for measuring the operation status; Maintenance records retrieve the maintenance data of node equipment to obtain the total number of maintenance times, average maintenance time, and average economic cost of maintenance. After normalization, the total number of maintenance times is used as the radius of the bottom circle to establish a bottom circle, and the average maintenance time and average economic cost of maintenance are used as the height to establish a cylinder. The volume of the cylinder is calculated and recorded as the dimension record value WJ, and this dimension record value is used as the standard for maintenance records; Equipment efficiency is obtained by obtaining the energy conversion efficiency and the historical comprehensive efficiency of the equipment, normalizing them and summing them up to obtain the set efficiency value SX, which is used as the standard for measuring equipment efficiency; Then, the obtained time evaluation value SP, dimension value WJ and set effectiveness value SX are normalized and then entered into the following formula: To obtain the data value XSZ.

6. The asset monitoring system applied to power grid data according to claim 1, characterized in that: The specific operation steps of the data processing module for cleaning, integrating and storing the collected data are as follows: First, the original data is formatted and data cleaning techniques are applied, including noise removal, smoothing, and outlier detection and processing; Then merge the data from different sources into a unified data store; The cleaned and integrated data is then stored in a database; Choose a storage solution based on the importance and frequency of data use, including relational databases, non-relational databases, or data warehouses; Then regularly check the data quality, including accuracy, completeness, consistency, and timeliness; Apply data quality rules and standards to continuously monitor and evaluate data; Finally, the data is updated regularly to reflect the latest status of power grid operation and to maintain the data storage and processing systems.

7. The asset monitoring system applied to power grid data according to claim 1, characterized in that: The specific operation steps of the status assessment module to assess the status of power grid assets are as follows: First, relevant features of condition assessment, including statistics, trends, and patterns, are extracted from the raw data, and feature selection techniques are used to determine the features; Then, according to the characteristics of power grid data assets and the evaluation objectives, appropriate machine learning algorithms are selected, including classification, regression and clustering; historical data is used to train the model and adjust the model parameters; Use validation sets or cross-validation methods to evaluate the accuracy and generalization ability of the model; use model evaluation metrics including accuracy, recall, and F1 score to determine the predictive performance of the model; Then, anomaly detection algorithms are applied to identify abnormal patterns in the data. When the data has abnormal patterns, it indicates that there are potential problems with the key node data. The power grid data is monitored in real time, and when an abnormal situation is detected, an alarm is triggered immediately; The trained model is then used to evaluate the current status of grid assets and predict potential risks and future trends. Based on the evaluation results, decision support is provided for grid operation and maintenance, including maintenance plans and load adjustments.

8. An asset monitoring method applied to power grid data class using the asset monitoring system applied to power grid data class according to any one of claims 1 to 7, characterized in that: The following steps are involved: S1: First, various types of data are collected through sensors installed at key nodes of the power grid, and an adaptive data collection mechanism is established to dynamically adjust the data collection frequency according to node parameters; S2: The data collected by the sensor is then uploaded through the communication network. During the uploading process, the security mechanism is used to conduct a detailed analysis of the data security requirements of key nodes, and different security strategies are adopted for the data security requirements of different key nodes. S3: The collected data is then cleaned, integrated and stored to ensure data quality and availability; S4: Finally, data analysis algorithms are used to evaluate the status of power grid assets by combining processed data with historical data to identify abnormal situations and potential risks.

Images