Intelligent operation and maintenance scheduling system and method for power equipment state perception

Abstract

The invention relates to the technical field of intelligent power grids, and discloses an intelligent operation and maintenance scheduling system and method for power equipment state perception, and the system comprises a data processing module, a feature extraction module, an index determination module, an abnormity analysis module, an operation and maintenance scheduling instruction generation module and an instruction execution module. Performing multi-source heterogeneous data fusion on the operation data of the power equipment collected in real time to obtain standardized real-time data; extracting material heat attenuation characteristics and load fluctuation working conditions; mapping the correlation factors of the material heat attenuation characteristics and the load fluctuation working conditions into equipment failure probabilities, and aggregating the equipment failure probabilities into an equipment health degree index; identifying abnormal equipment according to the equipment health degree index, and analyzing a node electrical association relationship; constructing an operation and maintenance task sequence of the power equipment by taking the optimal power supply reliability as a target; issuing the operation and maintenance task sequence to an execution terminal of the power equipment; the operation and maintenance scheduling efficiency of the power equipment can be improved.

Description

Technical Field

[0001] This invention relates to the field of smart grid technology, and in particular to an intelligent operation and maintenance scheduling system and method for power equipment status awareness. Background Technology

[0002] In the field of power equipment operation and maintenance, existing technologies suffer from low fusion efficiency when processing multi-source and heterogeneous equipment operation data, making it difficult to form a standardized and unified data foundation. This results in a one-sided and lagging perception of equipment status, failing to capture subtle changes during equipment operation in a timely and accurate manner. Furthermore, insufficient correlation analysis between equipment material characteristics and actual load conditions makes it difficult to accurately assess the health status of equipment, leading to a weak ability to predict potential faults.

[0003] Furthermore, existing operation and maintenance (O&M) scheduling methods largely rely on experience-based decision-making, failing to fully consider grid topology constraints and electrical interrelationships between equipment nodes. This makes it difficult to achieve optimal power supply reliability when formulating O&M task sequences. This not only leads to unreasonable allocation of O&M resources and increases unnecessary O&M costs, but also may cause power outage risks due to untimely scheduling or inadequate plans, seriously affecting the stable operation of the power system. Summary of the Invention

[0004] This invention provides an intelligent operation and maintenance scheduling system and method for power equipment status awareness, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides an intelligent operation and maintenance scheduling system for power equipment status awareness, characterized in that the system includes a data processing module, a feature extraction module, an indicator determination module, an anomaly analysis module, an operation and maintenance scheduling instruction generation module, and an instruction execution module, wherein: The data processing module is used to perform multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment. The feature extraction module is used to extract the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data; The index determination module is used to map the correlation factors between the thermal decay characteristics of the material and the load fluctuation conditions into the probability of equipment failure, and to aggregate the probability of equipment failure into the equipment health index of the power equipment. The anomaly analysis module is used to identify abnormal devices based on the device health indicators and to analyze the node electrical relationships of the abnormal devices. The operation and maintenance scheduling instruction generation module is used to construct the operation and maintenance task sequence of the power equipment based on the power grid topology constraints and the electrical association of the nodes, with the goal of optimizing power supply reliability. The instruction execution module is used to send the operation and maintenance task sequence to the execution terminal of the power equipment.

[0006] In a preferred embodiment, when the data processing module performs multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment, it is specifically used for: Receive heterogeneous data streams from monitoring devices in power equipment, wherein the heterogeneous data streams include electrical measurement data, equipment status signals, and environmental monitoring parameters; The electrical measurement data and the equipment status signal are timestamped to obtain the time synchronization data set of the power equipment. The time synchronization data set and the environmental monitoring parameters are unified in dimension through feature space mapping to obtain the intermediate fusion dataset of the power equipment. The intermediate fusion dataset is subjected to dimensional normalization to obtain standardized real-time data of the power equipment.

[0007] In a preferred embodiment, the feature extraction module, when extracting the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data, is specifically used for: The material thermal decay characteristics of the power equipment are retrieved from the preset equipment parameter library; Peak-valley characteristic analysis is performed on the current time-series waveform in the standardized real-time data to obtain the load fluctuation condition of the power equipment.

[0008] In a preferred embodiment, when the index determination module maps the correlation factor between the material thermal decay characteristics and the load fluctuation condition to the equipment failure probability, it is specifically used for: The thermal attenuation characteristics of the material are dynamically coupled and correlated with the load fluctuation conditions to obtain the material-condition correlation factor set of the power equipment. Construct a nonlinear relationship model between the material-operating condition correlation factor set and the thermal stress response of the equipment material of the power equipment; The parameters of the nonlinear relationship model are calibrated based on a historical fault sample database. After parameter calibration, the output value of the nonlinear relationship model is converted into a probability distribution to obtain the equipment failure probability of the power equipment.

[0009] In a preferred embodiment, when the index determination module performs the aggregation of the equipment failure probability into an equipment health index for the power equipment, it is specifically used for: Obtain the failure probabilities of multiple devices within a continuous time window for the power equipment; The failure probabilities of the multiple devices are dynamically fused to obtain the comprehensive failure probability value of the power equipment. The comprehensive failure probability value is mapped to the equipment health index of the power equipment based on the health conversion function, wherein the health conversion function is as follows: ; In the formula, for Real-time device health indicators The weighting coefficients for the current failure probability. for The probability value of device failure at any given time. The weighting coefficients for historical failure probabilities. The total number of sampling points. The sampling point ordinal number, for Time of the first The probability value of device failure at each sampling point.

[0010] In a preferred embodiment, when the anomaly analysis module identifies abnormal devices based on the device health indicators and analyzes the node electrical relationships of the abnormal devices, it is specifically used for: The health indicators of the equipment are graded and evaluated to obtain the abnormal status identifiers of the power equipment. The abnormal device set is filtered out based on the abnormal status identifier; Extract the electrical connection node information of each device in the abnormal device set; By analyzing the power flow transmission paths between the electrical connection nodes using the node association matrix, the electrical association relationships of the abnormal devices can be obtained.

[0011] In a preferred embodiment, when the operation and maintenance scheduling instruction generation module executes the construction of the operation and maintenance task sequence of the power equipment based on power grid topology constraints and the electrical relationships between nodes with the goal of optimizing power supply reliability, it is specifically used for: The electrical relationships between the nodes are transformed into a matrix of factors affecting equipment outages. The quantitative evaluation benchmark value of the power equipment is calculated based on the equipment outage impact factor matrix and the power supply reliability optimization objective function. An initial operation and maintenance sequence scheme set for the power equipment is generated based on the quantitative evaluation benchmark value; By overlaying power grid topology constraints onto the initial operation and maintenance sequence scheme set, the operation and maintenance task sequence of the power equipment is obtained.

[0012] In a preferred embodiment, the formula for calculating the quantitative evaluation benchmark value is as follows: ; In the formula, The quantitative evaluation benchmark value is... The total number of scheduling periods. As the scheduling period number, The reliability weights in the equipment downtime impact factor matrix are: For time period The power supply reliability benchmark value, The economic weights in the factor matrix affecting equipment downtime are... Let be the node ordinal number of the power equipment. The total number of nodes in the power equipment. For nodes During the period The amount of load loss, For nodes The load importance coefficient.

[0013] In a preferred embodiment, when the instruction execution module executes the distribution of the maintenance task sequence to the execution terminal of the power equipment, it is specifically used for: The operation and maintenance task sequence is structured and encapsulated according to a preset instruction protocol template to obtain standardized scheduling instructions for power equipment; The standardized dispatch instructions are transmitted to the execution terminal of the power equipment through the secure authentication channel of the power dispatch data network; The system receives the instruction execution confirmation signal returned by the execution terminal and generates a closed-loop response record.

[0014] To address the above problems, the present invention also provides an intelligent operation and maintenance scheduling method for power equipment status awareness, the method comprising: S1. Perform multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment; S2. Extract the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data; S3. Map the correlation factor between the thermal decay characteristics of the material and the load fluctuation condition to the equipment failure probability, and aggregate the equipment failure probability into the equipment health index of the power equipment; S4. Identify abnormal devices based on the device health indicators, and analyze the node electrical relationships of the abnormal devices; S5. With the goal of optimizing power supply reliability, construct the operation and maintenance task sequence of the power equipment based on the power grid topology constraints and the electrical relationships between the nodes; S6. The operation and maintenance task sequence is sent to the execution terminal of the power equipment.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention transforms electrical measurement data, status signals, and environmental parameters of power equipment into standardized real-time data through multi-source heterogeneous data fusion processing. Combined with the dynamic coupling analysis of material thermal decay characteristics and load fluctuation conditions, it accurately maps the probability of equipment failure and aggregates it into health indicators, significantly improving the comprehensiveness and accuracy of equipment status perception and providing a reliable basis for operation and maintenance decisions.

[0016] 2. This invention identifies abnormal equipment based on equipment health indicators and analyzes the electrical relationships between nodes. With the goal of optimizing power supply reliability, it constructs an operation and maintenance task sequence in conjunction with power grid topology constraints. Through standardized command issuance and closed-loop response mechanisms, it realizes intelligent and efficient operation and maintenance scheduling, effectively ensuring the stable operation of the power system and improving overall operation and maintenance efficiency. Attached Figure Description

[0017] Figure 1 This is a system architecture diagram of an intelligent operation and maintenance scheduling system for power equipment status awareness provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating an intelligent operation and maintenance scheduling method for power equipment status awareness, provided in an embodiment of the present invention.

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “the” and “the” as used in the embodiments of this invention are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0021] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0022] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0023] In practice, the server-side equipment deployed in an intelligent operation and maintenance scheduling system for power equipment status awareness may consist of one or more devices. This system can be implemented as a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node to provide intelligent operation and maintenance scheduling services for power equipment status awareness to various user terminals. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage various user terminals. Or, it can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide intelligent operation and maintenance scheduling services for power equipment status awareness to various user terminals.

[0024] In terms of implementation, the intelligent operation and maintenance scheduling system for power equipment status awareness and the user terminal are mutually compatible. That is, if the intelligent operation and maintenance scheduling system for power equipment status awareness is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the intelligent operation and maintenance scheduling system for power equipment status awareness is implemented as a website, then the user terminal is implemented as a webpage; or if the intelligent operation and maintenance scheduling system for power equipment status awareness is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0025] like Figure 1 The figure shown is a system architecture diagram of an intelligent operation and maintenance scheduling system for power equipment status awareness provided in an embodiment of the present invention.

[0026] The intelligent operation and maintenance scheduling system 100 for power equipment status awareness described in this invention can be located on a cloud server. In terms of implementation, it can be implemented as one or more service devices, or as an application installed on the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the intelligent operation and maintenance scheduling system 100 for power equipment status awareness may include a data processing module 101, a feature extraction module 102, an indicator determination module 103, an anomaly analysis module 104, an operation and maintenance scheduling instruction generation module 105, and an instruction execution module 106. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0027] In this embodiment of the invention, in the intelligent operation and maintenance scheduling system for power equipment status awareness, each of the above modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the intelligent operation and maintenance scheduling system for power equipment status awareness provided by this embodiment of the invention, the applicability of the system architecture can be adjusted by adding modules and directly calling them without modifying the program code, achieving cluster-based horizontal expansion to quickly and flexibly expand the intelligent operation and maintenance scheduling system for power equipment status awareness. In practical applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0028] The following describes, with reference to specific embodiments, each component and specific workflow of the intelligent operation and maintenance scheduling system for power equipment status awareness: The data processing module 101 is used to perform multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment. In this embodiment of the invention, when the data processing module performs multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment, it is specifically used for: Receive heterogeneous data streams from monitoring devices in power equipment, wherein the heterogeneous data streams include electrical measurement data, equipment status signals, and environmental monitoring parameters; The electrical measurement data and the equipment status signal are timestamped to obtain the time synchronization data set of the power equipment. The time synchronization data set and the environmental monitoring parameters are unified in dimension through feature space mapping to obtain the intermediate fusion dataset of the power equipment. The intermediate fusion dataset is subjected to dimensional normalization to obtain standardized real-time data of the power equipment.

[0029] Specifically, a data receiving interface is deployed, which can simultaneously access various heterogeneous data streams transmitted by monitoring devices in power equipment. Among these, electrical measurement data includes data reflecting the electrical characteristics of the power system operation, such as voltage, current, and power; equipment status signals cover signals reflecting the equipment's own operating status, such as equipment vibration, temperature, and insulation performance; and environmental monitoring parameters include data such as temperature, humidity, air pressure, and dust concentration of the environment in which the equipment is located. The interface classifies and stores all received data, establishing separate storage areas for electrical measurement data, equipment status signals, and environmental monitoring parameters to ensure that each type of data can be accurately identified and stored.

[0030] Furthermore, the timestamp information of all data is extracted from the electrical measurement data storage area and the equipment status signal storage area. The timestamp of the electrical measurement data is used as the reference time axis, and the timestamp of each equipment status signal is checked to see if it is consistent with the time point on the reference time axis. For data in the equipment status signal whose timestamp does not match the reference time axis, it is adjusted to the corresponding time point on the reference time axis by interpolation, so that each time point contains both electrical measurement data and equipment status signal, forming a time synchronization data set of power equipment.

[0031] Furthermore, a unified feature space is defined, which contains features that can describe the common characteristics of the time synchronization data set and the environmental monitoring parameters. For each data point in the time synchronization data set, it is mapped to the corresponding position in the unified feature space according to its own attributes. Similarly, for each parameter in the environmental monitoring parameters, it is also mapped to the corresponding position in the unified feature space according to its attributes, so that the time synchronization data set and the environmental monitoring parameters are presented in the same feature space with the same dimension, thus obtaining the intermediate fusion dataset of the power equipment.

[0032] Furthermore, the dimensions of all data in the intermediate fusion dataset are analyzed to determine the value range corresponding to each dimension. The value of each data in the intermediate fusion dataset is transformed according to the value range of its respective dimension. Specifically, the value of the data is subtracted from the minimum value of its respective dimension, and then divided by the difference between the maximum and minimum values ​​of its respective dimension. This ensures that the transformed data values ​​are all between 0 and 1, eliminating the influence of different dimensions on the data and obtaining standardized real-time data of power equipment.

[0033] In summary, multi-source heterogeneous data fusion of real-time collected power equipment operation data to obtain standardized real-time data can effectively integrate different types of data streams, such as electrical measurement data, equipment status signals, and environmental monitoring parameters transmitted from monitoring devices in power equipment.

[0034] In summary, data time synchronization is achieved through timestamp alignment, dimensional unification is achieved through feature space mapping, and standardized data is formed through dimensional normalization. This eliminates the heterogeneity and inconsistency between multi-source data, providing a unified and standardized data foundation for subsequent steps such as extracting material thermal decay characteristics and analyzing load fluctuation conditions. This ensures the reliability and consistency of the data, thus laying a solid data foundation for accurately assessing equipment health status and formulating reasonable operation and maintenance strategies.

[0035] The feature extraction module 102 is used to extract the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data. In this embodiment of the invention, when the feature extraction module extracts the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data, it is specifically used for: The material thermal decay characteristics of the power equipment are retrieved from the preset equipment parameter library; Peak-valley characteristic analysis is performed on the current time-series waveform in the standardized real-time data to obtain the load fluctuation condition of the power equipment.

[0036] Specifically, the preset equipment parameter library is categorized and stored according to the type of power equipment. Each type is further subdivided into multiple sub-entries based on information such as the manufacturer, model, and years of operation. Each sub-entry records in detail the material composition of the corresponding power equipment and the degree of material performance degradation in different temperature ranges. This information together constitutes the material thermal degradation characteristics of the equipment. During operation, first determine the specific type, manufacturer, model, and years of operation of the power equipment to be analyzed. Then, search the preset equipment parameter library according to the classification hierarchy to find a completely matching sub-entry. Extract the recorded material composition and performance degradation information in different temperature ranges from that sub-entry, thus completing the retrieval of the power equipment material thermal degradation characteristics.

[0037] Furthermore, all current-related data are filtered from standardized real-time data and arranged sequentially according to time to form a continuous current time-series waveform. The waveform is observed segment by segment to identify points where the value is higher than the adjacent data points; these points are called peaks. The time of each peak and its corresponding current value are recorded. Simultaneously, points where the value is lower than the adjacent data points are identified as troughs; the time of each trough and its corresponding current value are also recorded. The current difference between adjacent peaks and troughs is calculated, the number of peaks and troughs per unit time is counted, and the duration of each peak and trough is measured. These data are combined to determine the rise and fall of current over different time periods and the severity of these changes, thereby identifying the load fluctuation condition of the power equipment.

[0038] In summary, extracting the thermal degradation characteristics of power equipment materials and standardized real-time data on load fluctuations can accurately capture the thermal performance degradation patterns of the equipment's own materials over time and in response to environmental factors, as well as the dynamic changes in load during actual operation.

[0039] In summary, this process provides key feature basis for mapping the correlation factors between the two to the probability of equipment failure, making the assessment of equipment failure risk more in line with its physical attributes and actual operation, thus laying the foundation for accurately aggregating equipment health indicators, helping to improve the scientificity and pertinence of equipment status assessment, and providing reliable feature support for subsequent anomaly identification and operation and maintenance scheduling.

[0040] The index determination module 103 is used to map the correlation factor between the thermal decay characteristics of the material and the load fluctuation condition to the equipment failure probability, and to aggregate the equipment failure probability into the equipment health index of the power equipment. In this embodiment of the invention, when the index determination module maps the correlation factor between the material thermal decay characteristics and the load fluctuation condition to the equipment failure probability, it is specifically used for: The thermal attenuation characteristics of the material are dynamically coupled and correlated with the load fluctuation conditions to obtain the material-condition correlation factor set of the power equipment. Construct a nonlinear relationship model between the material-operating condition correlation factor set and the thermal stress response of the equipment material of the power equipment; The parameters of the nonlinear relationship model are calibrated based on a historical fault sample database. After parameter calibration, the output value of the nonlinear relationship model is converted into a probability distribution to obtain the equipment failure probability of the power equipment.

[0041] When the indicator determination module aggregates the equipment failure probability into an equipment health indicator for the power equipment, it is specifically used for: Obtain the failure probabilities of multiple devices within a continuous time window for the power equipment; The failure probabilities of the multiple devices are dynamically fused to obtain the comprehensive failure probability value of the power equipment. The comprehensive failure probability value is mapped to the equipment health index of the power equipment based on the health conversion function, wherein the health conversion function is as follows: ; In the formula, for Real-time device health indicators The weighting coefficients for the current failure probability. for The probability value of device failure at any given time. The weighting coefficients for historical failure probabilities. The total number of sampling points. The sampling point ordinal number, for Time of the first The probability value of device failure at each sampling point.

[0042] Specifically, the percentage of material performance degradation corresponding to different temperature values ​​is extracted from the material's thermal degradation characteristics. Simultaneously, the average current value and temperature change value for each time period are extracted from the load fluctuation conditions. Each temperature value is matched with the corresponding temperature change value for that time period to determine the correlation between the percentage of material performance degradation and the average current value for that time period under the influence of that temperature. A correlation coefficient is assigned to each successfully matched pair of degradation percentage and average current value. This coefficient is determined based on the degree of influence between the two; the greater the influence, the larger the coefficient. All these correlation coefficients, along with the corresponding degradation percentage and average current value, constitute the material-operating condition correlation factor group of the power equipment.

[0043] Furthermore, a large number of different material-operating condition correlation factor groups were collected, along with the specific values ​​of the thermal stress response of power equipment materials under the action of each factor group. The thermal stress response of the equipment materials is manifested as the magnitude of the stress generated inside the material. Each factor in each material-operating condition correlation factor group was treated as an independent variable, and the corresponding thermal stress response value was treated as a dependent variable. The correspondence between these variables and the dependent variable was recorded in a table. By observing the changes in the data in the table, it was found that when the factors in the correlation factor group changed, the thermal stress response value did not change linearly, but rather exhibited a complex curvilinear trend. Based on this curvilinear trend, the correspondence rules between factor changes and thermal stress response changes were determined, thereby constructing a nonlinear relationship model between the material-operating condition correlation factor group and the thermal stress response of the equipment materials.

[0044] Furthermore, the historical fault sample library stores historical data of power equipment categorized by fault type. Each fault type contains multiple sets of data, and each set of data includes a corresponding material-operating condition correlation factor group, the measured value of the thermal stress response of the equipment material, and a record of whether the fault occurred. Sufficient sample data covering various fault types are selected from the historical fault sample library. The material-operating condition correlation factor group of each sample is input into the constructed nonlinear relationship model to obtain the predicted value of thermal stress response calculated by the model. The predicted value is compared with the measured value of thermal stress response in the sample, and the difference between the two is calculated. If the difference exceeds the allowable range, the correspondence rules between the factors and thermal stress response in the model are adjusted. The process of inputting samples, calculating predicted values, comparing differences, and adjusting rules is repeated until the difference between the predicted value and the measured value of all samples is within the allowable range, thus completing the parameter calibration of the nonlinear relationship model.

[0045] Furthermore, the thermal stress response values ​​of all equipment materials output by the nonlinear relationship model after parameter calibration are organized and arranged in ascending order. They are then divided into several continuous and non-overlapping intervals, each with the same span. Samples with thermal stress response values ​​falling within each interval are found from the historical fault sample database. The total number of samples in each interval and the number of samples in which equipment failure occurs are counted. The failure rate of the interval is obtained by dividing the number of failure samples in each interval by the total number of samples in that interval. A distribution graph is plotted with the interval of thermal stress response values ​​as the horizontal axis and the corresponding failure rate as the vertical axis, which can intuitively show the probability of equipment failure under different thermal stress response values. The distribution presented in this graph is the equipment failure probability of the power equipment.

[0046] Specifically, a fixed-length continuous time window is set, such as 1 hour, and this time window is evenly divided into multiple equal time periods, such as each time period being 10 minutes. Within each time period, the equipment failure probability corresponding to the power equipment is calculated according to the previously determined method, ensuring that an independent equipment failure probability can be obtained for each time period. The equipment failure probabilities of all time periods are collected, and these probabilities together constitute multiple equipment failure probabilities of the power equipment within the continuous time window.

[0047] Furthermore, the failure probabilities of multiple devices within a continuous time window are analyzed to determine the importance of the time period corresponding to each failure probability within the entire time window, with the time period closer to the current moment having higher importance. Based on the importance, a corresponding weight is assigned to each device failure probability, with the failure probability weight corresponding to the time period with higher importance being larger. Each device failure probability is multiplied by its corresponding weight, and then all products are added together to obtain the comprehensive failure probability value of the power equipment.

[0048] Furthermore, the health conversion function is a pre-defined correspondence used to convert the comprehensive failure probability value into an equipment health index. This function stipulates that the smaller the comprehensive failure probability value, the higher the corresponding equipment health index, and the larger the comprehensive failure probability value, the lower the corresponding equipment health index. The obtained comprehensive failure probability value is substituted into this function, and the corresponding relationship set by the function is used to find the equipment health index that matches the comprehensive failure probability value. This index is the equipment health index of the power equipment.

[0049] Specifically, The device failure probability value at a given time is determined using a previously established method. The probability of failure of the power equipment is calculated at any time. The weighting coefficients of the historical failure probability and the current failure probability are preset based on the operating characteristics and historical data of the power equipment. The sum of the two is 1. Usually, the weighting coefficient of the current failure probability is greater than that of the historical failure probability to highlight the impact of the current state. The total number of sampling points is the number of time periods divided within the continuous time window, that is, the total number of multiple equipment failure probabilities obtained previously. Time of the first The device failure probability value at each sampling point is within a continuous time window. Before the moment The probability of equipment failure is calculated over a time period.

[0050] Furthermore, this formula is used to... The overall failure probability value at time t is converted to The device health index at any given time, where the weighting coefficient of the current failure probability is (1 minus) The product of the current failure probability value and the equipment failure probability value at any given time reflects the impact of the current failure probability on the health status. This is achieved by multiplying the historical failure probability by a weighting coefficient and (1 minus...) Time of the first The product of the average of the equipment failure probabilities at each sampling point reflects the comprehensive impact of historical failure probabilities on health. The sum of these two values ​​is the overall health score. The equipment health index at any given time comprehensively reflects the health status of power equipment in the current period and over a historical period.

[0051] Furthermore, when When the probability of device failure increases at a given time, (1 minus) The probability of device failure at any given time will decrease if other values ​​remain unchanged. The device health index will decrease at any given time; when the overall device failure probability value from multiple historical sampling points increases, the average value of (1 minus the device failure probability values ​​from these sampling points) will decrease, if other values ​​remain unchanged. The device health index will decrease at any given time; conversely, the current or historical failure probability value will decrease, corresponding to... The equipment health index will increase at any time, showing an overall trend of inverse change between the equipment failure probability value and the equipment health index.

[0052] In summary, mapping the correlation factors between material thermal decay characteristics and load fluctuation conditions to equipment failure probabilities and aggregating them into equipment health indicators enables a quantitative assessment of the operating status of power equipment. By transforming the dynamic coupling relationship between materials and operating conditions into failure probabilities and combining it with a nonlinear model calibrated from a historical fault sample library, the assessment of potential equipment failure risks becomes more scientific and accurate. Furthermore, the health transformation function dynamically fuses the failure probabilities within a continuous time window, forming an intuitive equipment health indicator that reflects both the current equipment status and historical operating trends. This provides a quantitative basis for accurately identifying abnormal equipment and formulating reasonable operation and maintenance strategies, effectively improving the comprehensiveness and reliability of equipment health status assessment.

[0053] The anomaly analysis module 104 is used to identify abnormal devices based on the device health indicators and to analyze the node electrical relationships of the abnormal devices. In this embodiment of the invention, when the anomaly analysis module identifies abnormal devices based on the device health indicators and analyzes the node electrical relationships of the abnormal devices, it is specifically used for: The health indicators of the equipment are graded and evaluated to obtain the abnormal status identifiers of the power equipment. The abnormal device set is filtered out based on the abnormal status identifier; Extract the electrical connection node information of each device in the abnormal device set; By analyzing the power flow transmission paths between the electrical connection nodes using the node association matrix, the electrical association relationships of the abnormal devices can be obtained.

[0054] Specifically, when setting the grading standards for equipment health indicators, first determine the value range of the health indicators, assuming it is between 0 and 100. Then, divide this range into four levels: a healthy level (90-100) corresponds to stable equipment operation with no obvious abnormalities; a slightly abnormal level (70-89) corresponds to slight parameter fluctuations in the equipment, requiring attention; a moderately abnormal level (40-69) corresponds to more obvious abnormal characteristics in the equipment, requiring maintenance; and a severely abnormal level (0-39) corresponds to an extremely high risk of equipment failure, requiring immediate shutdown. Each level is assigned a unique abnormal state identifier, such as "healthy," "slightly abnormal," "moderately abnormal," and "severely abnormal." By comparing the equipment health indicators with these level ranges to determine its level, the identifier corresponding to that level is extracted, which is the abnormal state identifier of the power equipment.

[0055] Furthermore, basic information and corresponding abnormal status identifiers of all power equipment in the power system are collected to establish a master table containing equipment names, models, and abnormal status identifiers; the abnormal status identifiers of each equipment in the master table are checked one by one, and all equipment whose identifiers are not "healthy" are selected. These equipment include all equipment identified as "minor abnormality", "moderate abnormality", and "serious abnormality"; the information of the selected equipment is organized into a new list, which clearly records the name, model and abnormal status identifier of each equipment. This list is the set of abnormal equipment.

[0056] Furthermore, the electrical connection node information for each device in the abnormal device set comes from the electrical design drawings and equipment installation records of the power system. This information details the specific connection location of the device in the circuit. For each abnormal device, the wiring diagram of the device is found in the electrical design drawings to determine the power supply node number connected to its input terminal, the load node number connected to its output terminal, and the connection node number of adjacent devices directly connected in series or parallel with the device. These node numbers and their corresponding node types (such as power supply node, load node, and adjacent device node) are organized into text information, which is the electrical connection node information extracted from the abnormal device.

[0057] Furthermore, the node association matrix is ​​constructed based on the overall topology of the power system. The number of rows and columns in the matrix is ​​equal to the total number of electrical nodes in the system, and each row and column number corresponds to the number of an electrical node. Each cell in the matrix represents the power flow relationship between the corresponding row and column nodes. If two nodes are directly connected by a conductor or other electrical component, and there is a power flow path, the cell is marked as 1. If there is no direct connection between two nodes, and there is no power flow path, the cell is marked as 0. The electrical connection node numbers of the abnormal equipment are found in the corresponding row and column of the node association matrix. The cell markings at the intersection of these rows and columns are checked. When the marking is 1, it indicates that there is a power flow path between the corresponding two nodes. Based on all node pairs with power flow paths, it is determined which nodes are directly connected to the connection nodes of the abnormal equipment, and the connection relationships between these connected nodes. The sum of these relationships is the node electrical association relationship of the abnormal equipment.

[0058] In summary, identifying abnormal equipment based on equipment health indicators and analyzing their node electrical relationships enables precise location of equipment with potential fault risks, ensuring timely detection of abnormal equipment. By grading and evaluating equipment health indicators, a set of abnormal equipment can be quickly identified, clarifying objectives for subsequent maintenance work. Simultaneously, extracting the electrical connection node information of abnormal equipment and analyzing power flow transmission paths using node correlation matrices clearly reveals the electrical relationships between abnormal equipment and other nodes, clarifying the potential scope and extent of fault impact. This provides crucial correlational evidence for constructing a maintenance task sequence aimed at optimizing power supply reliability, enhancing the targeting and effectiveness of maintenance decisions, and ensuring the stable operation of the power system.

[0059] The operation and maintenance scheduling instruction generation module 105 is used to construct the operation and maintenance task sequence of the power equipment based on the power grid topology constraints and the electrical association of the nodes, with the goal of optimizing power supply reliability. In this embodiment of the invention, when the operation and maintenance scheduling instruction generation module executes the construction of the operation and maintenance task sequence of the power equipment based on power grid topology constraints and the electrical relationships between nodes with the goal of optimizing power supply reliability, it is specifically used for: The electrical relationships between the nodes are transformed into a matrix of factors affecting equipment outages. The quantitative evaluation benchmark value of the power equipment is calculated based on the equipment outage impact factor matrix and the power supply reliability optimization objective function. An initial operation and maintenance sequence scheme set for the power equipment is generated based on the quantitative evaluation benchmark value; By overlaying power grid topology constraints onto the initial operation and maintenance sequence scheme set, the operation and maintenance task sequence of the power equipment is obtained.

[0060] The formula for calculating the quantitative evaluation benchmark value is as follows: ; In the formula, The quantitative evaluation benchmark value is... The total number of scheduling periods. As the scheduling period number, The reliability weights in the equipment downtime impact factor matrix are: For time period The power supply reliability benchmark value, The economic weights in the factor matrix affecting equipment downtime are... Let be the node ordinal number of the power equipment. The total number of nodes in the power equipment. For nodes During the period The amount of load loss, For nodes The load importance coefficient.

[0061] Specifically, the node electrical correlation records in detail the direct and indirect connections between the electrical connection nodes of abnormal equipment, as well as the strength of power flow transmission between each node. When these relationships are transformed into a device outage impact factor matrix, the rows of the matrix represent equipment that may be out of service, and the columns represent equipment affected by the outage. First, for each pair of equipment with a correlation, the basic impact value is determined according to their connection level in the node electrical correlation. The basic value for directly connected equipment is higher than that for indirectly connected equipment. Then, the basic value is adjusted based on the strength of power flow transmission between nodes. The stronger the power flow transmission, the higher the adjusted value. The final value is used as the element at the intersection of the corresponding row and column in the matrix. For equipment without a correlation, the value of the element at the corresponding position is set to 0, thus forming the device outage impact factor matrix.

[0062] Furthermore, the power supply reliability optimization objective function is pre-set based on the power supply demand of the power grid, clarifying the specific direction for evaluating power supply reliability, such as maximizing continuous power supply time and minimizing the number of power outages for users. The degree of influence represented by each element in the equipment outage impact factor matrix is ​​matched with the corresponding evaluation direction in the power supply reliability optimization objective function. For each power device, the degree of influence it has on all column devices when it is a row device is summarized. Then, combined with the weight allocation of these influences in the objective function, a comprehensive value is calculated. This value directly reflects the degree of influence of the equipment outage on the power supply reliability optimization objective. This comprehensive value is the quantitative evaluation benchmark value of the power device.

[0063] Furthermore, the magnitude of the quantitative assessment benchmark value directly reflects the urgency and importance of power equipment in operation and maintenance. The larger the value, the more significant the impact of equipment failure on the power supply system, requiring priority for operation and maintenance. Based on this, all power equipment is initially sorted from largest to smallest according to the quantitative assessment benchmark value. Then, considering the differences in equipment types, different types of equipment within the same benchmark value range are sorted again according to their functional priority in the power grid, such as transmission equipment taking precedence over distribution equipment. Multiple different operation and maintenance sequence schemes are generated according to this sorting method. Each scheme clearly lists the specific order of all equipment to be operated and maintained. These schemes together form the initial operation and maintenance sequence scheme set for the power equipment.

[0064] Furthermore, the power grid topology constraints include loop structure constraints, equipment energization constraints, and safety distance constraints. Loop structure constraints require that equipment in the same series loop must be maintained in the order from the power source to the load. Equipment energization constraints stipulate that before maintaining a piece of equipment, its upstream energized equipment must be de-energized. Safety distance constraints require that when maintaining high-altitude equipment, equipment within a certain range cannot be maintained simultaneously. Each scheme in the initial maintenance sequence scheme set is checked against these constraints one by one. If the maintenance order of two pieces of equipment in a scheme violates the loop structure constraints, the order of these two pieces of equipment is swapped. If the equipment energization constraints are violated, necessary de-energization steps are inserted between these two pieces of equipment and the order is adjusted. If the safety distance constraints are violated, the maintenance times of these two pieces of equipment are staggered to ensure that the adjusted scheme fully complies with all power grid topology constraints. The scheme obtained after adjustment is the maintenance task sequence of the power equipment.

[0065] Specifically, the total number of scheduling periods is determined based on the power grid's scheduling cycle. For example, if a day is divided into 24 scheduling periods, each lasting one hour, the total number of scheduling periods is 24. The scheduling period numbering is a sequential numbering of each scheduling period, starting from 1 and increasing sequentially until the total number of scheduling periods is reached. The reliability and economic weights in the equipment outage impact factor matrix are pre-set based on the power grid's emphasis on power supply reliability and economy; their sum is 1. The reliability weight measures the importance of power supply reliability in the assessment, and the economic weight measures the importance of economic efficiency in the assessment. The power supply reliability benchmark value is determined based on historical power supply data and power demand for that period, reflecting the expected level of power supply reliability for that period; the node ordinal number of the power equipment is the sequential numbering of all nodes of the power equipment; the total number of nodes of the power equipment is the total number of nodes contained in that equipment; nodes During the period The load loss refers to the amount of load loss during a certain period of time. Inside, due to the nodes The load that cannot be supplied normally due to problems is determined by statistical analysis of nodes during that period. The difference between the actual load and the normal load is obtained; node The load importance coefficient is based on the node. The importance of the load is determined; important loads have higher node coefficient values, while non-important loads have lower node coefficient values.

[0066] Furthermore, this formula is used to calculate the quantitative evaluation benchmark value of power equipment. It calculates the sum of the positive contribution related to reliability and the negative impact related to economics within each scheduling period, and then takes the maximum value of these sums as the quantitative evaluation benchmark value. The reliability weight is related to the time period. The product of the power supply reliability benchmark value reflects the positive impact of power supply reliability on the assessment during that period, along with economic weighting and node weighting. During the period Load loss and nodes The sum of the products of the load importance coefficients reflects the negative effect of load loss on the assessment during that period. The difference between the two is the assessment value for that period. The maximum value among all assessment values ​​for all periods is the quantitative assessment benchmark value, which comprehensively reflects the importance of the equipment in ensuring power supply reliability and reducing load loss.

[0067] Furthermore, at that time When the power supply reliability benchmark value increases, if other values ​​remain unchanged, the assessment value for that period will increase, potentially leading to an increase in the quantitative assessment benchmark value; when the node During the period Load loss or node When the load importance coefficient increases, if other values ​​remain unchanged, the evaluation value for that period will decrease, which may lead to a decrease in the quantitative evaluation benchmark value. When the reliability weight increases, the impact of power supply reliability on the quantitative evaluation benchmark value increases. When the economic weight increases, the impact of load loss on the quantitative evaluation benchmark value increases. Overall, the quantitative evaluation benchmark value will increase with the increase of positive effects and decrease with the increase of negative effects.

[0068] In summary, aiming for optimal power supply reliability, constructing a sequence of operation and maintenance (O&M) tasks for power equipment based on grid topology constraints and node electrical relationships enables precise and efficient O&M scheduling. By transforming node electrical relationships into a matrix of equipment outage impact factors, and combining this with quantitative evaluation benchmark calculation formulas to comprehensively consider factors such as power supply reliability benchmarks, load loss, and load importance, a scientifically sound initial O&M sequence can be generated. Furthermore, by overlaying grid topology constraints, the scheme is ensured to meet the actual operational requirements of the grid structure, thereby constructing the optimal O&M task sequence. This process maximizes power supply reliability, rationally plans O&M priorities and resource allocation, reduces the risk of power outages due to improper O&M, and improves the overall stability and economy of the power system.

[0069] The instruction execution module 106 is used to send the operation and maintenance task sequence to the execution terminal of the power equipment.

[0070] In this embodiment of the invention, when the instruction execution module executes the distribution of the maintenance task sequence to the execution terminal of the power equipment, it is specifically used for: The operation and maintenance task sequence is structured and encapsulated according to a preset instruction protocol template to obtain standardized scheduling instructions for power equipment; The standardized dispatch instructions are transmitted to the execution terminal of the power equipment through the secure authentication channel of the power dispatch data network; The system receives the instruction execution confirmation signal returned by the execution terminal and generates a closed-loop response record.

[0071] Specifically, the preset instruction protocol template contains a fixed structural framework, which is divided into three parts: instruction header, instruction body, and instruction tail. The instruction header records the number, generation time, and sender information of the dispatch instruction. The instruction body is used to fill in the specific content of the operation and maintenance task sequence, including the name of the equipment to be maintained, the maintenance sequence, operation steps, and completion time limit. The instruction tail reserves a signature area to confirm the validity of the instruction. The various information items in the operation and maintenance task sequence are filled in according to the structural framework of the template to ensure that each information item corresponds to the designated position in the template. After filling, the entire content is format-validated to check whether it meets the template's requirements for character length, field format, etc. The complete instruction formed after the validation passes is the standardized dispatch instruction for power equipment.

[0072] Furthermore, the security authentication channel of the power dispatch data network is a pre-built dedicated transmission channel. This channel uses identity authentication and data encryption mechanisms to ensure transmission security. Before transmitting standardized dispatch instructions, the sender's identity information is submitted to the security authentication channel. The channel verifies the identity information. After successful verification, the standardized dispatch instructions are encrypted. The encrypted instructions are transmitted to the execution terminal of the power equipment through the channel. During the transmission process, the channel continuously monitors the integrity of the data to prevent the instructions from being tampered with or lost, ensuring that the execution terminal can accurately receive the complete standardized dispatch instructions.

[0073] Furthermore, after receiving the standardized scheduling instruction, the execution terminal parses and prepares for execution. After completing the preparation, it generates an instruction execution confirmation signal. This signal contains the instruction number, the reception time, and the device identifier of the execution terminal, indicating that the terminal has successfully received the instruction and is ready to execute it. The scheduling system receives this confirmation signal, compares the instruction number in the signal with the number of the sent standardized scheduling instruction, and integrates the key information in the signal with the transmission record after confirming that they match, forming a closed-loop response record containing the instruction transmission time, reception time, and execution terminal information. This record is used to trace the transmission and reception status of the instruction.

[0074] In summary, the system distributes maintenance task sequences to the execution terminals of power equipment. By structurally encapsulating these sequences using pre-defined instruction protocol templates, standardized dispatch instructions are formed, ensuring the standardization and consistency of instruction transmission. Transmission is conducted through the secure authentication channel of the power dispatch data network, guaranteeing the security and reliability of the instruction transmission process and reducing the risk of information leakage or tampering. Simultaneously, receiving instruction execution confirmation signals from the execution terminals and generating closed-loop response records enables full tracking and feedback of the maintenance task execution process. This facilitates timely monitoring of task progress, ensures the effective execution of maintenance instructions, improves the closed-loop management efficiency of power equipment maintenance dispatch, and guarantees the orderly conduct of maintenance work.

[0075] Reference Figure 2 The diagram shown is a flowchart illustrating an intelligent operation and maintenance scheduling method for power equipment state awareness according to an embodiment of the present invention. In this embodiment, the intelligent operation and maintenance scheduling method for power equipment state awareness includes: S1. Perform multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment; S2. Extract the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data; S3. Map the correlation factor between the thermal decay characteristics of the material and the load fluctuation condition to the equipment failure probability, and aggregate the equipment failure probability into the equipment health index of the power equipment; S4. Identify abnormal devices based on the device health indicators, and analyze the node electrical relationships of the abnormal devices; S5. With the goal of optimizing power supply reliability, construct the operation and maintenance task sequence of the power equipment based on the power grid topology constraints and the electrical relationships between the nodes; S6. The operation and maintenance task sequence is sent to the execution terminal of the power equipment.

[0076] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0077] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent operation and maintenance scheduling system for power equipment status awareness, characterized in that, The system includes a data processing module, a feature extraction module, an indicator determination module, an anomaly analysis module, an operation and maintenance scheduling instruction generation module, and an instruction execution module, wherein: The data processing module is used to perform multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment. The feature extraction module is used to extract the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data; The index determination module is used to map the correlation factors between the thermal decay characteristics of the material and the load fluctuation conditions into the probability of equipment failure, and to aggregate the probability of equipment failure into the equipment health index of the power equipment. The anomaly analysis module is used to identify abnormal devices based on the device health indicators and to analyze the node electrical relationships of the abnormal devices. The operation and maintenance scheduling instruction generation module is used to construct the operation and maintenance task sequence of the power equipment based on the power grid topology constraints and the electrical association of the nodes, with the goal of optimizing power supply reliability. The instruction execution module is used to send the operation and maintenance task sequence to the execution terminal of the power equipment.

2. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 1, characterized in that, When the data processing module performs multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment, it is specifically used for: Receive heterogeneous data streams from monitoring devices in power equipment, wherein the heterogeneous data streams include electrical measurement data, equipment status signals, and environmental monitoring parameters; The electrical measurement data and the equipment status signal are timestamped to obtain the time synchronization data set of the power equipment. The time synchronization data set and the environmental monitoring parameters are unified in dimension through feature space mapping to obtain the intermediate fusion dataset of the power equipment. The intermediate fusion dataset is subjected to dimensional normalization to obtain standardized real-time data of the power equipment.

3. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 1, characterized in that, When the feature extraction module extracts the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data, it is specifically used for: The material thermal decay characteristics of the power equipment are retrieved from the preset equipment parameter library; Peak-valley characteristic analysis is performed on the current time-series waveform in the standardized real-time data to obtain the load fluctuation condition of the power equipment.

4. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 1, characterized in that, When the index determination module maps the correlation factor between the material's thermal decay characteristics and the load fluctuation condition to the equipment failure probability, it is specifically used for: The thermal attenuation characteristics of the material are dynamically coupled and correlated with the load fluctuation conditions to obtain the material-condition correlation factor set of the power equipment. Construct a nonlinear relationship model between the material-operating condition correlation factor set and the thermal stress response of the equipment material of the power equipment; The parameters of the nonlinear relationship model are calibrated based on a historical fault sample database. After parameter calibration, the output value of the nonlinear relationship model is converted into a probability distribution to obtain the equipment failure probability of the power equipment.

5. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 4, characterized in that, When the indicator determination module aggregates the equipment failure probability into an equipment health indicator for the power equipment, it is specifically used for: Obtain the failure probabilities of multiple devices within a continuous time window for the power equipment; The failure probabilities of the multiple devices are dynamically fused to obtain the comprehensive failure probability value of the power equipment. The comprehensive failure probability value is mapped to the equipment health index of the power equipment based on the health conversion function, wherein the health conversion function is as follows: ； In the formula, for Real-time device health indicators The weighting coefficients for the current failure probability. for The probability value of device failure at any given time. The weighting coefficients for historical failure probabilities. The total number of sampling points. The sampling point ordinal number, for Time of the first The probability value of device failure at each sampling point.

6. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 1, characterized in that, When the anomaly analysis module identifies abnormal devices based on the device health indicators and analyzes the node electrical relationships of the abnormal devices, it is specifically used for: The health indicators of the equipment are graded and evaluated to obtain the abnormal status identifiers of the power equipment. The abnormal device set is filtered out based on the abnormal status identifier; Extract the electrical connection node information of each device in the abnormal device set; By analyzing the power flow transmission paths between the electrical connection nodes using the node association matrix, the electrical association relationships of the abnormal devices can be obtained.

7. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 1, characterized in that, When the operation and maintenance scheduling instruction generation module executes the construction of the operation and maintenance task sequence of the power equipment based on power grid topology constraints and the electrical relationships between the nodes with the goal of optimizing power supply reliability, it is specifically used for: The electrical relationships between the nodes are transformed into a matrix of factors affecting equipment outages. The quantitative evaluation benchmark value of the power equipment is calculated based on the equipment outage impact factor matrix and the power supply reliability optimization objective function. An initial operation and maintenance sequence scheme set for the power equipment is generated based on the quantitative evaluation benchmark value; By overlaying power grid topology constraints onto the initial operation and maintenance sequence scheme set, the operation and maintenance task sequence of the power equipment is obtained.

8. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 7, characterized in that, The formula for calculating the quantitative evaluation benchmark value is as follows: ； In the formula, The quantitative evaluation benchmark value is... The total number of scheduling periods. As the scheduling period number, The reliability weights in the equipment downtime impact factor matrix are: For time period The power supply reliability benchmark value, The economic weights in the factor matrix affecting equipment downtime are... Let be the node ordinal number of the power equipment. The total number of nodes in the power equipment. For nodes During the period The amount of load loss, For nodes The load importance coefficient.

9. The intelligent operation and maintenance scheduling system for power equipment status awareness as described in claim 1, characterized in that, When the instruction execution module executes the distribution of the maintenance task sequence to the execution terminal of the power equipment, it is specifically used for: The operation and maintenance task sequence is structured and encapsulated according to a preset instruction protocol template to obtain standardized scheduling instructions for power equipment; The standardized dispatch instructions are transmitted to the execution terminal of the power equipment through the secure authentication channel of the power dispatch data network; The system receives the instruction execution confirmation signal returned by the execution terminal and generates a closed-loop response record.

10. A smart operation and maintenance scheduling method for power equipment status awareness, characterized in that, The method includes: S1. Perform multi-source heterogeneous data fusion on the real-time collected operating data of the power equipment to obtain standardized real-time data of the power equipment; S2. Extract the material thermal decay characteristics of the power equipment and the load fluctuation conditions of the standardized real-time data; S3. Map the correlation factor between the thermal decay characteristics of the material and the load fluctuation condition to the equipment failure probability, and aggregate the equipment failure probability into the equipment health index of the power equipment; S4. Identify abnormal devices based on the device health indicators, and analyze the node electrical relationships of the abnormal devices; S5. With the goal of optimizing power supply reliability, construct the operation and maintenance task sequence of the power equipment based on the power grid topology constraints and the electrical relationships between the nodes; S6. The operation and maintenance task sequence is sent to the execution terminal of the power equipment.

Images