Power equipment operation and maintenance management system

Abstract

This application discloses a power equipment operation and maintenance management system, belonging to the field of power management technology, including: a data detection module, used to periodically detect the operating status of the power equipment and classify the detected status data to obtain the priority of the operating status of the power equipment, wherein the operating status of the power equipment includes load status, voltage status and power supply status; and an operating status control model, which uses the classified status data to obtain the operating status control model of the power equipment through a neural network, thereby realizing the prediction of the operating status of the power equipment, determining whether the operating status of the power equipment is within the normal range, and if it is not within the normal range, locating the fault status of the power equipment and analyzing the fault factors caused by the fault status, and processing the operating status of the power equipment in batches according to the priority.

Description

Technical Field

[0001] This application relates to a power equipment operation and maintenance management system, belonging to the field of power management technology. Background Technology

[0002] The development of power equipment operation and maintenance management systems (O&M) primarily stems from the power industry's increasing demands for improved O&M efficiency, safety, and reliability. With continuous technological advancements and deeper applications, O&M management systems will play an increasingly important role in the power industry, providing strong support for the stable operation and sustainable development of the power system. As the power industry rapidly develops and the power grid structure becomes increasingly complex, traditional O&M management models are no longer sufficient to meet current needs. To address this challenge, power equipment O&M management systems have emerged, potentially integrating cutting-edge technologies such as the Internet of Things (IoT), big data, cloud computing, and artificial intelligence to achieve efficient and intelligent management of power equipment. Summary of the Invention

[0003] According to one aspect of this application, a power equipment operation and maintenance management system is provided. This method enables real-time monitoring and prediction of the operating status of power equipment, timely detection and handling of potential faults, and ensures the stable operation of power equipment.

[0004] A power equipment operation and maintenance management system, characterized in that it includes: The data detection module is used to periodically detect the operating status of the power equipment and classify the detected status data to obtain the priority of the operating status of the power equipment. The operating status of the power equipment includes load status, voltage status and power supply status. The operation status control model uses the classified status data to obtain the operation status control model of the power equipment through a neural network, thereby realizing the prediction of the operation status of the power equipment, determining whether the operation status of the power equipment is within the normal range, and if it is not within the normal range, locating the fault status of the power equipment and analyzing the fault factors caused by the fault status, and processing the operation status of the power equipment in batches according to the priority. The normal range includes a first threshold range, a second threshold range, and a third threshold range, wherein the minimum value of the first threshold range is not less than the maximum value of the second threshold range, and the minimum value of the second threshold range is not less than the maximum value of the third threshold range.

[0005] Furthermore, the operating status of the power equipment is periodically monitored, including: The operating status of the power equipment is collected to obtain the time characteristic curve of the operating status; Modal decomposition is performed on the time characteristics of the operating state to extract the periodic intrinsic mode function component signal, thereby obtaining the periodic characteristic curve of the operating state; Establish and update the operating status cycle characteristic database of the power equipment.

[0006] Furthermore, the conditions for the periodic detection include: The detection cycle is T; The required testing frequency within the testing cycle is N; The interval time is D. Starting from the inspection time point t0, all inspection records {tn, ..., t-2, t-1} that meet the interval time requirement are inspected within one period T. Starting from t0, N tests are allocated within the next cycle T.

[0007] Furthermore, the detected state data is classified and processed, including: The periodically detected state data is classified to obtain classified state data; The classified status data includes at least load status data, voltage status data, and power supply status data; Abnormal data in the classification status data is removed to obtain various types of valid classification status data, and the priority of each type of valid classification status data is determined to obtain the priority of each type of valid classification status.

[0008] Furthermore, when determining the priority of each type of valid classification state data, the changes in each type of valid classification state are used as a benchmark to set the priority.

[0009] Furthermore, the operating status of the power equipment is processed in batches according to the aforementioned priority, including: When the operating state of the power equipment is within the first threshold range, the devices inside the power equipment are controlled to close in a first number; When the operating state of the power equipment is within the second threshold range, the devices inside the power equipment are controlled to close in a second quantity, wherein the second quantity is greater than the first quantity; When the operating state of the power equipment is within the third threshold range, control all devices within the power equipment to close.

[0010] Furthermore, the abnormal data in the classification status data is removed, including: The classification status data obtained by the sending device is split, and then identified by sequence number and encrypted to obtain N split classification status data, where N is an integer greater than 0; The receiving device receives the N split and classification status data to obtain N split and classification status data. After decryption, the N split and classification status data are restored and integrated according to the sequence number to obtain integrated classification status data. Data association analysis is performed based on the integrated classification status data. If the association is not qualified, abnormal data is removed.

[0011] The beneficial effects that this application can produce include: This application provides a power equipment operation and maintenance management system that periodically detects the operating status of power equipment, including load status, voltage status, and power supply status. The detected status data is classified, and the priority of the power equipment's operating status is determined based on the classification results. A predictive model is trained using the classified status data. The model predicts the operating status of the power equipment and determines whether it is within a normal range (including a first threshold range, a second threshold range, and a third threshold range, with the range increasing progressively). If the status is abnormal, the fault status is located and the fault factors are analyzed. Simultaneously, the operating status of the power equipment is processed in batches according to priority. Through periodic data detection and the application of a neural network model, real-time monitoring and prediction of the power equipment's operating status are achieved, enabling timely detection and handling of potential faults and ensuring the stable operation of the power equipment. Attached Figure Description

[0012] Figure 1 This is an overall framework diagram of a power equipment operation and maintenance management system according to one embodiment of this application. Detailed Implementation

[0013] The present application is described in detail below with reference to the embodiments, but the present application is not limited to these embodiments.

[0014] See Figure 1 A power equipment operation and maintenance management system, characterized in that it includes: The data detection module is used to periodically detect the operating status of the power equipment and classify the detected status data to obtain the priority of the operating status of the power equipment. The operating status of the power equipment includes load status, voltage status and power supply status. The operation status control model uses the classified status data to obtain the operation status control model of the power equipment through a neural network, thereby realizing the prediction of the operation status of the power equipment, determining whether the operation status of the power equipment is within the normal range, and if it is not within the normal range, locating the fault status of the power equipment and analyzing the fault factors caused by the fault status, and processing the operation status of the power equipment in batches according to the priority. The normal range includes a first threshold range, a second threshold range, and a third threshold range, wherein the minimum value of the first threshold range is not less than the maximum value of the second threshold range, and the minimum value of the second threshold range is not less than the maximum value of the third threshold range.

[0015] Specifically, the power equipment operation and maintenance management system is an advanced system integrating data detection, status prediction, and fault analysis, designed to improve the operating efficiency and safety of power equipment. The data detection module periodically monitors the operating status of the power equipment, which is fundamental to ensuring stable equipment operation. Regular monitoring allows for the timely detection of potential problems. The detected data is categorized, which helps to better understand the equipment's operating status. Categorization may be based on data type (e.g., load status, voltage status, power supply status) and the degree of data anomaly. Based on the categorization results, the system assigns different priorities to different operating states. This helps the system quickly identify and prioritize the most serious or critical problems when equipment malfunctions. The operating status control model can construct a control model for the operating status of the power equipment. This model can predict the future operating status of the equipment based on historical and current status data. Using the operating status control model, the system can determine whether the equipment's operating status is within the normal range. This normal range is subdivided into three threshold ranges (first threshold range, second threshold range, and third threshold range), each with clear boundaries to ensure the accuracy and reliability of the judgment. The first threshold range indicates that the equipment's operating status is in a minor fault stage. Although the equipment is still running, some signs of performance degradation or minor anomalies have appeared. The second threshold range indicates that the equipment has entered a moderate fault stage. Equipment performance has significantly degraded, and frequent alarms or unstable operation may occur. Maintenance personnel should immediately take measures for inspection or maintenance to prevent the fault from escalating and affecting the normal operation of the equipment. The third threshold range indicates that the equipment is approaching or has reached an unsafe, unstable, or imminent failure state. The equipment may have experienced a serious fault, is unable to operate normally, or poses a safety hazard. Maintenance personnel should immediately shut down the equipment for inspection and maintenance, and take emergency measures to prevent equipment damage, prolonged downtime, or safety accidents caused by the fault. If the equipment status is outside the normal range, the system will locate the fault status and analyze the fault factors. This helps to quickly identify the problem and take appropriate remedial measures. Based on priority, the system will process the equipment's operating status in batches. This ensures efficient use of resources and also ensures that the most urgent or critical issues are addressed first.

[0016] In summary, this power equipment operation and maintenance management system, by integrating functions such as data monitoring, condition prediction, and fault analysis, provides strong support for the stable operation of power equipment. Its intelligent processing flow and efficient resource utilization make equipment maintenance more timely, accurate, and effective.

[0017] Periodic monitoring of the operating status of the power equipment includes: The operating status of the power equipment is collected to obtain the time characteristic curve of the operating status; Modal decomposition is performed on the time characteristics of the operating state to extract the periodic intrinsic mode function component signal, thereby obtaining the periodic characteristic curve of the operating state; Establish and update the operating status cycle characteristic database of the power equipment.

[0018] Specifically, the starting point of the power equipment operation status monitoring process is to acquire real-time operation status data of the power equipment. This data may include various parameters such as load, current, voltage, power factor, and temperature. Through sensors or other monitoring equipment, we can continuously or periodically collect and record this data, forming an operation status time characteristic curve. Mode decomposition is a signal processing technique that can decompose complex signals into a series of simple, independent components, called modes or intrinsic mode functions (IMFs). Here, we perform mode decomposition on the operation status time characteristic curve to extract the IMF component signals related to the periodic changes in the equipment's operation status. These component signals can more clearly reflect the periodic characteristics of the equipment's operation status, providing strong support for subsequent analysis and prediction. Based on mode decomposition, we need to further filter out the IMF component signals most relevant to periodic changes. These signals usually have obvious periodic characteristics, such as a fixed period length and stable amplitude. By extracting these signals, we can obtain the periodic characteristic curve of the equipment's operation status, which can intuitively show the periodic change pattern of the equipment's operation status. After obtaining the periodic characteristic curve of the operating status, we need to store it in a database along with other relevant equipment information (such as equipment model, installation location, operating environment, etc.). This database is called the operating status periodic characteristic database, and it records the periodic characteristics of the equipment's operating status over different time periods. As time progresses and the equipment continues to operate, this database needs to be continuously updated to ensure it contains the latest and most accurate information.

[0019] It is worth noting that through modal decomposition and periodic feature extraction, we can more accurately capture the periodic changes in equipment operating status, thereby improving the accuracy and reliability of monitoring. The establishment of a database of periodic operating status features provides rich data support for fault prediction. By analyzing historical data in the database, we can discover abnormal patterns in equipment operating status, thus predicting potential faults in advance. Based on monitoring results and database information, we can formulate more scientific and reasonable operation and maintenance strategies. For example, based on the periodic changes in equipment operating status, we can rationally arrange equipment inspection and maintenance plans to reduce downtime and operation and maintenance costs.

[0020] Therefore, periodic monitoring of the operating status of power equipment is a complex and important process. By using scientific data acquisition, mode decomposition, and feature extraction methods, a database containing the periodic characteristics of equipment operating status can be established and updated, providing strong support for subsequent fault prediction and operation and maintenance strategy optimization.

[0021] The conditions for the periodic detection include: The detection cycle is T; The required testing frequency within the testing cycle is N; The interval time is D. Starting from the inspection time point t0, all inspection records {tn, ..., t-2, t-1} that meet the interval time requirement are inspected within one period T. Starting from t0, N tests are allocated within the next cycle T.

[0022] Specifically, the detection cycle T refers to the time interval for periodic detection. Within this time interval, the device will be monitored and its operating status or related data will be recorded. For example, if the detection cycle T is set to daily, it means that the device needs to be detected once or multiple times each day. The detection frequency requirement N refers to the number of times detection needs to be performed within each detection cycle T. For example, if N is set to 3, it means that the device needs to be detected 3 times within each detection cycle T. The interval time D refers to the time difference between two adjacent detections. This can be understood as, under certain circumstances, ensuring that the time interval between two adjacent detections is not less than D.

[0023] It should be noted that the interval time D usually does not exist independently, but is combined with the detection frequency N and the detection period T to jointly determine the detection plan.

[0024] The inspection time point t0 is the starting point of the periodic inspection. From this time point, we will perform inspections according to the set inspection period T and inspection frequency N. Within one inspection period T, starting from t0, we need to inspect all inspection records that meet the interval requirement D. These records can be represented as {tn, ..., t-2, t-1}, where n is a positive integer less than N, representing the number of inspections completed within the current period T.

[0025] It's important to note that tn, ..., t-2, t-1 here do not refer to specific points in time, but rather to the detection records within a certain time interval relative to t0. In practical applications, these time intervals need to be converted into specific points in time, and detection should be performed based on these points in time.

[0026] Detection allocation within the next cycle T: Starting from t0, after completing all detections within one detection cycle T, we need to plan the detection schedule for the next cycle T. Within the next cycle T, N detections need to be performed according to the set detection frequency N. These detections can be evenly distributed within cycle T, or flexibly adjusted according to actual needs.

[0027] The implementation steps of periodic testing are as follows: 1. Determine the testing cycle T and testing frequency N: Based on the characteristics of the equipment and maintenance requirements, determine a suitable testing cycle T and testing frequency N. 2. Set the starting time point t0: Select a suitable starting time point t0 as the starting point for periodic testing. 3. Plan the testing schedule: Plan the testing schedule based on the testing cycle T, testing frequency N, and interval D (if necessary). 4. Determine the testing time points within each cycle T and record them in the testing record table. 5. Execute the testing: Execute the testing tasks according to the planned testing schedule, recording the equipment's operating status or related data. 6. Update the testing record table: After each testing is completed, update the testing record table, i.e., the database of the periodic characteristics of the status.

[0028] Based on the analysis results and actual needs, parameters such as the detection cycle T, detection frequency N, and interval time D are adjusted in a timely manner to optimize the detection plan.

[0029] By following the above conditions and implementation steps, we can effectively carry out periodic inspections of power equipment, ensuring its normal operation and timely detection of potential problems.

[0030] The detected state data is categorized and processed, including: The periodically detected state data is classified to obtain classified state data; The classified status data includes at least load status data, voltage status data, and power supply status data; Abnormal data in the classification status data is removed to obtain various types of valid classification status data, and the priority of each type of valid classification status data is determined to obtain the priority of each type of valid classification status.

[0031] Specifically, the first step is to classify the periodically detected status data. This status data may include various operating parameters of the equipment, such as current, voltage, power, and temperature. The purpose of classification is to divide this complex data according to its nature or function to facilitate subsequent analysis and processing. In this step, at least three categories of status data will be obtained: load status data, voltage status data, and power status data. These classifications are based on key parameters of the equipment's operating status. After obtaining the classified status data, further filtering and processing are required. In particular, abnormal data, which may be caused by equipment failure, sensor errors, or data transmission errors, needs to be removed. In one embodiment, the removal of abnormal data can be achieved by setting a reasonable threshold or using data cleaning techniques. For example, for voltage status data, we can set a reasonable voltage range; data outside this range can be considered abnormal and removed. The purpose of removing abnormal data is to ensure the accuracy and reliability of the data in subsequent analysis. After removing abnormal data, various types of valid classified status data are obtained. This data is crucial for equipment operating status analysis and fault prediction. However, since different categories of status data have different degrees of impact on the equipment's operating status, we need to determine their priorities. Prioritization can be determined by comprehensively considering factors such as the criticality of the equipment, the reliability of the data, and historical fault data. For example, for power equipment, voltage status data and power status data may have higher priority because anomalies in these data are often directly related to the operational safety and stability of the equipment. After prioritizing, we can formulate subsequent data analysis and processing strategies based on these priorities to ensure that potential equipment problems can be identified and addressed in a timely manner.

[0032] It's worth noting that by classifying status data and removing outliers, we can reduce interference from invalid data and improve the efficiency and accuracy of data analysis. Effectively categorized status data and priority information can provide strong support for fault prediction. By analyzing the trends and correlations of these data, we can identify potential equipment failure modes and take preventative measures in advance. Based on categorized status data and priority information, we can formulate more scientific and reasonable operation and maintenance strategies. For example, for high-priority data, we can increase the detection frequency or use more sensitive monitoring methods to ensure accuracy; for low-priority data, we can appropriately reduce the detection frequency or use more cost-effective monitoring methods. This can be achieved by optimizing or updating the detection cycle.

[0033] Therefore, by classifying, removing outliers, and prioritizing periodically detected status data, we can effectively improve the efficiency and accuracy of data analysis, providing strong support for equipment fault prediction and operation and maintenance strategy optimization.

[0034] When determining the priority of each type of valid classification state data, the change of each type of valid classification state is used as the benchmark to set the priority.

[0035] Specifically, prioritizing data based on changes in various valid classification states allows for the assessment of the importance and urgency of different data based on actual changes in equipment status, thus guiding maintenance personnel to make more informed decisions. The priority changes arising from variations in the three types of status data require monitoring and analysis of their states. First, it's necessary to define the specific change indicators for each type of valid classification state data, such as load fluctuation range, voltage deviation, and power supply stability. Based on the results of the status change analysis, one or more benchmarks are set to differentiate the importance and urgency of different status data. Benchmarks can be specific numerical values ​​(such as load fluctuation thresholds, voltage deviation percentages, etc.) or assessments based on data change trends (such as a continuous upward or downward trend). Based on the set benchmarks, various valid classification state data are divided into different priority levels. For example, data with status changes exceeding a set threshold can be marked as high priority, data with status changes within an acceptable range but close to the threshold can be marked as medium priority, and data with stable status far from the threshold can be marked as low priority. Priority classification can be dynamically adjusted according to actual conditions. For example, when the equipment is in a critical operating phase, the priority of certain status data can be temporarily increased.

[0036] It's worth noting that as equipment operating status and maintenance needs change, the priorities of various valid categorized status data need to be updated periodically or in real-time. Priorities can be updated by re-analyzing status change data, adjusting baselines, or reclassifying priority levels. Setting priorities based on status changes reflects the equipment's operating status in real time, helping maintenance personnel make timely decisions. By quantifying status change indicators and setting baselines, the importance and urgency of different status data can be assessed more accurately. Priority setting methods can be flexibly adjusted according to actual needs to adapt to changes in different equipment and maintenance scenarios.

[0037] The operating status of the power equipment is processed in batches according to the aforementioned priority, including: When the operating state of the power equipment is within the first threshold range, the devices inside the power equipment are controlled to close in a first number; When the operating state of the power equipment is within the second threshold range, the devices inside the power equipment are controlled to close in a second quantity, wherein the second quantity is greater than the first quantity; When the operating state of the power equipment is within the third threshold range, control all devices within the power equipment to close.

[0038] Specifically, when the operating status of electrical equipment is within the first threshold range, it means that the operating status is relatively stable, but a certain degree of vigilance is still required. In this case, we control the closure of devices within the electrical equipment with a first quantity. The first quantity is usually a small value, designed to ensure the operation of critical components while avoiding unnecessary energy consumption and heat accumulation. In this way, we can reduce operating costs and risks while ensuring the basic functions of the equipment. When the operating status of electrical equipment enters the second threshold range, in one implementation, the operating status, such as voltage status, may begin to fluctuate or become abnormal, which may adversely affect the performance and lifespan of the equipment. In this case, we control the closure of devices within the electrical equipment with a second quantity. The second quantity is greater than the first quantity, aiming to improve the stability and performance of the equipment by increasing the number of closed devices. In this way, we can better cope with the challenges posed by voltage fluctuations and ensure the stable operation of the equipment in complex environments. When the operating status of electrical equipment reaches the third threshold range, in one implementation, the operating status, such as load status, may have reached or exceeded the equipment's carrying capacity, which may cause serious damage to the equipment. In this case, we control the closure of all devices within the electrical equipment. This is an emergency measure designed to protect the equipment from further damage by reducing the operating load on the equipment. It should be noted that this approach may cause the equipment to temporarily stop or malfunction, so the pros and cons should be weighed and relevant personnel notified before implementation.

[0039] The threshold range needs to be set comprehensively based on the specific characteristics of the equipment and its operating environment. Through historical data analysis, equipment testing, and experience summarization, we can determine a reasonable threshold range to ensure the effectiveness and accuracy of the batch processing strategy. In practical applications, we need to flexibly adjust the number of closed devices according to the real-time operating status and priority order of the equipment. By monitoring and analyzing equipment data in real time, we can promptly detect and handle abnormal situations, ensuring the stable operation and safety of the equipment. Therefore, a batch processing strategy based on the priority of power equipment operating status is an effective equipment management and maintenance method. By flexibly adjusting the number of closed devices, we can ensure the stability and safety of the equipment under different operating conditions, improving the reliability and service life of the equipment. It is worth noting that any operational state can experience abnormal situations, and these will be handled in batches according to their priority.

[0040] The process of removing outlier data from the classification status data includes: The classification status data obtained by the sending device is split, and then identified by sequence number and encrypted to obtain N split classification status data, where N is an integer greater than 0; The receiving device receives the N split and classification status data to obtain N split and classification status data. After decryption, the N split and classification status data are restored and integrated according to the sequence number to obtain integrated classification status data. Data association analysis is performed based on the integrated classification status data. If the association is not qualified, abnormal data is removed.

[0041] In another embodiment, during the removal of anomalous data, the sending device first splits the acquired classification status data. This is typically done to facilitate data transmission and processing, breaking the data down into smaller, more manageable parts. Simultaneously, each split data point is assigned a unique sequence number. This sequence number is used to maintain the order and consistency of the data during reception and integration. Next, the split data is encrypted. Encryption aims to ensure the security and privacy of the data during transmission, preventing unauthorized access or tampering by third parties. The receiving device receives N split classification status data points from the sending device. The received data is first decrypted to restore its original form. After decryption, the split data is reassembled based on the sequence number. This step ensures the integrity and order of the data, allowing the split data to be recombined into complete classification status data. After obtaining the integrated classification status data, data correlation analysis is performed. Data correlation analysis aims to check the logical relationships, consistency, and completeness between data points. If the data correlation analysis reveals data inconsistencies (e.g., inconsistencies, missing values, or outliers), these anomalous data points are removed. The purpose of removing outlier data is to ensure the accuracy and reliability of subsequent analysis and processing.

[0042] It is important to ensure data integrity and security throughout the entire processing flow. Especially during data splitting, encryption, and decryption, appropriate techniques and measures must be taken to prevent data loss, tampering, or leakage. Data correlation analysis is a crucial step in removing outliers. Therefore, suitable data correlation analysis methods and techniques need to be selected to ensure accurate identification of outliers. After removing outliers, the remaining data needs further analysis and processing. This includes steps such as data cleaning, data transformation, and data mining to extract useful information and knowledge to support subsequent decision-making and actions. This approach aims to ensure the accuracy and integrity of categorized status data. Through steps such as data splitting, encryption, decryption, restoration and integration, and data correlation analysis, outliers can be effectively removed, providing a reliable foundation for subsequent data analysis and processing.

[0043] The above description is merely a few embodiments of this application and is not intended to limit this application in any way. Although this application discloses preferred embodiments as described above, it is not intended to limit this application. Any changes or modifications made by those skilled in the art without departing from the scope of the technical solution of this application using the disclosed technical content are equivalent to equivalent implementation cases and fall within the scope of the technical solution.

Claims

1. A power equipment operation and maintenance management system, characterized in that, include: The data detection module is used to periodically detect the operating status of the power equipment and classify the detected status data to obtain the priority of the operating status of the power equipment. The operating status of the power equipment includes load status, voltage status and power supply status. The operation status control model uses the classified status data to obtain the operation status control model of the power equipment through a neural network, thereby realizing the prediction of the operation status of the power equipment, determining whether the operation status of the power equipment is within the normal range, and if it is not within the normal range, locating the fault status of the power equipment and analyzing the fault factors caused by the fault status, and processing the operation status of the power equipment in batches according to the priority. The normal range includes a first threshold range, a second threshold range, and a third threshold range, wherein the minimum value of the first threshold range is not less than the maximum value of the second threshold range, and the minimum value of the second threshold range is not less than the maximum value of the third threshold range.

2. The power equipment operation and maintenance management system according to claim 1, characterized in that, Periodic monitoring of the operating status of the power equipment includes: The operating status of the power equipment is collected to obtain the time characteristic curve of the operating status; Modal decomposition is performed on the time characteristics of the operating state to extract the periodic intrinsic mode function component signal, thereby obtaining the periodic characteristic curve of the operating state; Establish and update the operating status cycle characteristic database of the power equipment.

3. The power equipment operation and maintenance management system according to claim 1, characterized in that, The conditions for the periodic detection include: The detection cycle is T; The required testing frequency within the testing cycle is N; The interval time is D. Starting from the inspection time point t0, all inspection records {tn, ..., t-2, t-1} that meet the interval time requirement are inspected within one period T. Starting from t0, N tests are allocated within the next cycle T.

4. The power equipment operation and maintenance management system according to claim 1, characterized in that, The detected state data is categorized and processed, including: The periodically detected state data is classified to obtain classified state data; The classified status data includes at least load status data, voltage status data, and power supply status data; Abnormal data in the classification status data is removed to obtain various types of valid classification status data, and the priority of each type of valid classification status data is determined to obtain the priority of each type of valid classification status.

5. The power equipment operation and maintenance management system according to claim 4, characterized in that, When determining the priority of each type of valid classification state data, the change of each type of valid classification state is used as the benchmark to set the priority.

6. The power equipment operation and maintenance management system according to claim 4, characterized in that, The operating status of the power equipment is processed in batches according to the aforementioned priority, including: When the operating state of the power equipment is within the first threshold range, the devices inside the power equipment are controlled to close in a first number; When the operating state of the power equipment is within the second threshold range, the devices inside the power equipment are controlled to close in a second quantity, wherein the second quantity is greater than the first quantity; When the operating state of the power equipment is within the third threshold range, control all devices within the power equipment to close.

7. The power equipment operation and maintenance management system according to claim 4, characterized in that, The process of removing outlier data from the classification status data includes: The classification status data obtained by the sending device is split, and then identified by sequence number and encrypted to obtain N split classification status data, where N is an integer greater than 0; The receiving device receives the N split and classification status data to obtain N split and classification status data. After decryption, the N split and classification status data are restored and integrated according to the sequence number to obtain integrated classification status data. Data association analysis is performed based on the integrated classification status data. If the association is not qualified, abnormal data is removed.

Images