An intelligent power operation monitoring and control method and system

Abstract

The present invention relates to the field of power control technology, and in particular to an intelligent power operation monitoring and control method and system. The method comprises the following steps: obtaining power site upload data; constructing a power site distribution network for the power site upload data to obtain a power site distribution network; using the power site distribution network to store data uploaded by the power site to generate standard power site distribution storage data; performing line integration on the power site distribution storage data to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module; performing dynamic power monitoring on the power site transmission network to generate power equipment monitoring data and power line monitoring data. The present invention improves the accuracy and comprehensiveness of power monitoring and control by constructing a power site network, dynamic monitoring, intelligent anomaly detection and automated fault recovery.

Description

Technical Field

[0001] The present invention relates to the field of power control technology, and in particular to an intelligent power operation monitoring and control method and system. Background Art

[0002] Early power systems relied on manual monitoring and operation, which was inefficient and difficult to deal with complex power grid failures. With the development of computer technology and electronic equipment, the SCADA (Supervisory Control and Data Acquisition) system was introduced in the mid-20th century to realize remote monitoring and control of power grid equipment. In the 21st century, advanced technologies such as information and communication technology (ICT), Internet of Things (IoT) and big data analysis have gradually been applied to power systems, promoting the intelligent upgrade of power monitoring and control systems. In recent years, with the rapid development of artificial intelligence (AI), cloud computing, 5G communication and edge computing technologies, intelligent power monitoring systems can collect, analyze and predict the operating status of power equipment in real time, and make adaptive adjustments and fault warnings, which not only improves the safety and stability of the power grid, but also reduces the cost of manual operation and maintenance. However, the existing technologies are mostly single-mode detection in terms of anomaly detection, which cannot capture complex abnormal situations in time. At the same time, they lack dynamic response capabilities in load adjustment and fault isolation, which leads to low accuracy and comprehensiveness of power monitoring and control. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent power operation monitoring and control method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent power operation monitoring and control method is provided, the method comprising the following steps:

[0005] Step S1: obtaining the power site uploaded data; constructing a power site distribution network for the power site uploaded data to obtain the power site distribution network; using the power site distribution network to store the power site uploaded data to generate standard power site distributed storage data; performing line integration on the power site distributed storage data to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module;

[0006] Step S2: Dynamically monitor the power transmission network of the power site to generate power equipment monitoring data and power line monitoring data; perform anomaly detection on the power equipment monitoring data and the power line monitoring data to generate single abnormal mode data and complex abnormal mode data; adjust the first abnormal operation control of the dynamic monitoring data of the power site according to the single abnormal mode data to generate single abnormal control adjustment data;

[0007] Step S3: Based on the complex abnormal pattern data, the power site module and the power line module are converted into a time-series change spectrum to generate abnormal change frequency data of the power site and abnormal change frequency data of the power line; the power site module and the power line module are divided into a first abnormal scenario according to the generated abnormal change frequency data of the power site and the abnormal change frequency data of the power line to obtain multi-point fault abnormal scenario data; based on the complex abnormal pattern data, the power site module and the power line module are analyzed for abnormal current of the phase conductor to generate abnormal current data of the phase conductor; the complex abnormal pattern data is divided into a second abnormal scenario according to the abnormal current data of the phase conductor to obtain abnormal scenario data of the phase short circuit;

[0008] Step S4: Formulate a load adjustment strategy for the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data to generate load adjustment strategy data; isolate the fault area of ​​the power site module and the power line module to generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data to generate complex abnormal control adjustment data;

[0009] Step S5: Continuously monitor the abnormal fault recovery of the power site transmission network according to the single abnormal control adjustment data and the complex abnormal control adjustment data to generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

[0010] The present invention constructs a power site distribution network, effectively integrates the data uploaded by the power site, realizes the systematic and standardized management of the site data, improves the organizational efficiency of the data, and after generating the power site transmission network, the relationship between the power site module and the power line module is clarified, providing a refined line integration foundation and providing support for subsequent monitoring and control. The standardized processing in the data storage process improves the operability and consistency of the data, laying a solid foundation for subsequent analysis and monitoring. Through the dynamic monitoring of power equipment and power lines, the real-time state of the system can be grasped, and the monitoring capability of the system can be greatly improved. Abnormal detection is subdivided into single abnormal mode and complex abnormal mode, which not only improves the accuracy of detection, but also can make targeted adjustments for different abnormal situations to prevent the expansion of potential hidden dangers. By generating single abnormal control adjustment data, small-scale abnormal problems can be quickly corrected and the overall fluctuation of the system can be reduced. By using the time-series change spectrum conversion technology of complex abnormal mode data, the abnormal change frequency of power sites and power lines can be more accurately captured and analyzed, and the accuracy of fault analysis can be improved. Through abnormal scenario division and phase conductor abnormal current analysis, in-depth analysis of complex scenarios such as multi-point faults and phase-to-phase short circuits is achieved, and the efficiency and accuracy of complex fault diagnosis are improved. The monitoring of the timing changes of power stations and line modules improves the ability to predict the development trend of faults and helps to prevent systemic faults in advance. According to the scenario data of multi-point faults and phase-to-phase short circuits, a load adjustment strategy is formulated to respond to abnormal situations under different loads in a timely manner and avoid system crashes caused by load imbalance. Through fault area isolation, the fault can be controlled within a local range to prevent the fault from spreading to the entire power grid, thereby improving the stability and operational reliability of the power grid. The dynamic load transfer strategy ensures the stable operation of the system and minimizes the impact of power outages or system paralysis by adjusting the load distribution in the fault area in real time. Abnormal fault recovery monitoring provides a continuous system monitoring function that can automatically adjust during the fault recovery process to ensure the adaptability and efficiency of the power system recovery process. Data archiving provides a detailed record for fault handling, and the feedback of these archived data helps to optimize future monitoring strategies and improve the long-term reliability of the system. Through the monitoring feedback mechanism, the recovery effect and operating status of the system can be monitored in real time, a continuous optimization scheme for the system status can be provided, and the intelligent level of system operation can be enhanced. Therefore, the present invention improves the accuracy and comprehensiveness of power monitoring and control by constructing a power station network, dynamic monitoring, intelligent anomaly detection and automated fault recovery.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: Obtaining data uploaded by the power station;

[0013] Step S12: performing power site upload addressing on the power site upload data to generate power site address data; constructing a power site distribution network for the power site upload data according to the power site address data to obtain a power site distribution network;

[0014] Step S13: using the power site distribution network to store the data uploaded by the power site, and generating power site distribution storage data; performing data preprocessing on the power site distribution storage data, and generating standard power site distribution storage data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0015] Step S14: Perform power transmission route analysis on the power site distribution storage data to generate power transmission route data; perform line integration on the power site distribution network based on the power transmission route data to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module.

[0016] The present invention can generate accurate power site address data by addressing the data uploaded by the power site, and construct a power site distribution network through the address data, so that the association between sites is more intuitive, which helps to improve the efficiency of data organization. The data uploaded by the power site is stored and preprocessed to ensure the quality of the data. Data cleaning, denoising, missing value filling and standardization steps can effectively eliminate abnormal data and noise, and ensure the accuracy and consistency of subsequent analysis. By analyzing the power transmission route, optimized power transmission route data can be generated. This analysis can identify the bottleneck and optimization direction of power transmission, thereby improving power transmission efficiency and reducing line losses. The power site transmission network constructed based on the power transmission route data not only integrates the power site module and the line module, but also realizes the overall optimization of the transmission path between power sites, effectively improving the operating efficiency and safety of the power grid. The power site distribution network is combined with storage to provide a distributed storage solution for power data, making the management of power data more flexible and reliable, and suitable for the data management needs of large-scale power grids.

[0017] Preferably, step S2 comprises the following steps:

[0018] Step S21: Dynamically monitor the power transmission network of the power site to generate dynamic monitoring data of the power site, wherein the dynamic monitoring data of the power site includes power equipment monitoring data and power line monitoring data;

[0019] Step S22: performing anomaly detection on the power equipment monitoring data and the power line monitoring data, and generating single abnormal pattern data when an abnormality is detected in the power equipment monitoring data or the power line monitoring data; generating complex abnormal pattern data when an abnormality is detected in the power equipment monitoring data and the power line monitoring data;

[0020] Step S23: Screening the power equipment monitoring data and the power line monitoring data for abnormal data according to the single abnormal pattern data to obtain abnormal power monitoring data;

[0021] Step S24: perform fault prediction on the power equipment monitoring data and the power line monitoring data through the power abnormality monitoring data to generate single abnormal fault prediction data; perform a first operation control adjustment on the single abnormal mode data through the single abnormal fault prediction data to generate single abnormal control adjustment data.

[0022] The present invention performs real-time dynamic power monitoring on the transmission network of the power site, and the collected monitoring data of the power equipment and power lines provide a solid data foundation for subsequent fault detection and prediction, which helps to capture the changes in the operating status of the equipment and lines in a timely manner, thereby improving the accuracy of monitoring. Through the abnormal detection of the monitoring data, it is possible to distinguish between a single abnormal mode and a complex abnormal mode, and accurately locate the type of abnormality. This classification detection method can reduce misjudgment and improve the accuracy and efficiency of abnormal detection. Through the abnormal data screening in step S23, the system can extract the power abnormality monitoring data, thereby ensuring that only the data that does have abnormalities is analyzed and processed, reducing unnecessary computing overhead and improving the pertinence of fault detection. The power abnormality monitoring data is further used for fault prediction, and the fault problem is identified in advance by generating single abnormal fault prediction data. Then, by controlling and adjusting the single abnormal mode data, the system can take preventive measures in advance to reduce the risk of faults and improve the stability and reliability of the power system.

[0023] Preferably, step S24 includes the following steps:

[0024] Step S241: extracting equipment status and operating parameters from the power equipment monitoring data and the power line monitoring data to obtain equipment status data and real-time operating parameter data, wherein the real-time operating parameter data includes voltage, current, temperature, vibration and frequency;

[0025] Step S242: performing anomaly matching analysis on the power abnormality monitoring data based on a preset historical fault database to generate abnormal type matching data; dividing the abnormal type matching data into data sets to generate a model training set and a model test set; performing model training on the model training set based on a support vector machine algorithm to generate a fault prediction pre-model;

[0026] Step S243: using the model test set to perform model optimization iteration on the fault prediction pre-model, thereby generating a fault prediction model; importing the equipment status data and real-time operation parameter data of the power equipment monitoring data or the power line monitoring data into the fault prediction pre-model to perform fault prediction, and generate single abnormal fault prediction data;

[0027] Step S244: adjusting the transformer voltage amplitude of the power equipment monitoring data based on the single abnormal fault prediction data to generate power equipment abnormal adjustment data; adjusting the power line transmission power of the power line monitoring data based on the single abnormal fault prediction data to generate power line abnormal adjustment data;

[0028] Step S245: integrating the power equipment abnormality adjustment data and the power line abnormality adjustment data into control data to generate single abnormality control adjustment data.

[0029] The present invention extracts the state and operation parameters of the monitoring data of the power equipment and the power line, including key indicators such as voltage, current, temperature, vibration and frequency. These multi-dimensional monitoring data provide real-time and accurate feedback for the health status of the equipment and the performance of the line, which helps to identify potential risks in a timely manner. Through the abnormal matching analysis based on the historical fault database, the abnormal situation in the power system can be quickly identified, and the model training is carried out using the support vector machine algorithm. Subsequently, through the model optimization iteration, the accuracy of the fault prediction model is continuously improved, providing a reliable basis for the fault warning of the power equipment and the line. Based on the equipment status data and the real-time operation parameter data, the optimized fault prediction model is used to predict the fault and generate a single abnormal fault prediction data. This accurate prediction helps to take preventive measures in time to avoid further expansion of the fault. The power equipment and the line are automatically adjusted according to the fault prediction results. For example, the voltage amplitude of the power equipment and the transmission power of the power line are adjusted to achieve timely response to the abnormal situation and reduce the impact of the fault on the system. By integrating the adjustment data of the power equipment and the power line, a single abnormal control adjustment data is generated, so as to achieve coordinated regulation between the equipment and the line. This integration not only improves the response speed of the system, but also ensures the effectiveness and consistency of the control measures. The entire chain of steps can effectively reduce the frequency of equipment failures and the instability of line transmission through fault prediction, real-time adjustment and control integration, and improve the overall stability and safety of the power grid system.

[0030] Preferably, step S3 comprises the following steps:

[0031] Step S31: Based on the complex abnormal pattern data, the power site module and the power line module are analyzed for abnormal time series changes to generate abnormal time series change data; the abnormal time series change data are analyzed for change frequency to generate power site abnormal change frequency data and power line abnormal change frequency data;

[0032] Step S32: Perform Fourier transformation on the abnormal change frequency data of the power site and the abnormal change frequency data of the power line to generate a power site abnormal change spectrum diagram and a power line abnormal change spectrum diagram; overlap the spectrum curves of the power site abnormal change spectrum diagram and the power line abnormal change spectrum diagram to generate a composite spectrum curve of abnormal power change;

[0033] Step S33: analyzing the abnormal change time interval of the power site module and the power line module through the power abnormal change composite spectrum curve to generate power node abnormal change time interval data; using the power node abnormal change time interval data to perform a first abnormal scenario division on the complex abnormal pattern data to obtain multi-point fault abnormal scenario data;

[0034] Step S34: Based on the complex abnormal pattern data, the power site module and the power line module are subjected to phase conductor abnormal current analysis to generate phase conductor abnormal current data; the complex abnormal pattern data is subjected to a second abnormal scenario division through the phase conductor abnormal current data to obtain phase-to-phase short circuit abnormal scenario data.

[0035] The present invention generates abnormal time series change data by analyzing the abnormal time series changes of the power site module and the power line module, and further extracts the abnormal change frequency data of the power site and the power line through the change frequency analysis. This method can identify the frequency of abnormal occurrence and its time series law, which helps the power system to identify potential problems in the early stage and make preventive responses. Fourier transform is used to perform spectrum analysis on the abnormal change frequency data to generate an abnormal change spectrum diagram, and a composite spectrum curve of abnormal power changes is generated by overlapping the spectrum curves. This process can reveal the spectral characteristics in abnormal changes, help analyze more complex frequency change patterns, and enhance the perception sensitivity of power system abnormalities. Through the composite spectrum curve of abnormal power changes, the abnormal change time intervals of power sites and lines are analyzed, and then the abnormal change time interval data of power nodes are generated. This analysis helps to accurately identify the time nodes when faults or abnormalities occur, making fault location more accurate, and the first scenario division of complex abnormal pattern data is performed through abnormal time interval data to identify multi-point fault abnormal scenarios. By using the abnormal current data of the phase conductor, the complex abnormal pattern is divided into the second scenario to obtain the phase-to-phase short circuit abnormal scenario data. This dual scenario division can effectively distinguish different types of fault scenarios, especially in the case of complex multi-point faults and phase-to-phase short circuits, providing a more accurate basis for fault prediction. Through multi-dimensional abnormal data analysis such as time series, spectrum and current, step S3 covers the operation of the power system from time, frequency to current changes. Such a comprehensive analysis helps to comprehensively and carefully detect and predict potential abnormal conditions in the power system, avoiding the limitations of single-dimensional analysis. This step chain from abnormal pattern recognition to scenario division can help the power system to perform more refined fault prediction and location, thereby formulating preventive maintenance measures. By discovering abnormal patterns early, the power system can respond faster, optimize maintenance and repair strategies, and reduce the impact of power system failures on overall operation.

[0036] Preferably, step S34 includes the following steps:

[0037] Step S341: performing three-phase current data monitoring processing on the power site module and the power line module to generate power site three-phase current monitoring data and power line three-phase current monitoring data;

[0038] Step S342: performing current balance comparison analysis on the three-phase current monitoring data of the power station and the three-phase current monitoring data of the power line to generate phase conductor current balance data; performing mutation detection on the phase conductor current balance data to generate phase conductor current mutation data;

[0039] Step S343: performing multi-dimensional mutation feature extraction on the phase conductor current mutation data to generate abnormal current mutation feature data, wherein the multi-dimensional mutation feature extraction includes current mutation time extraction, current mutation frequency range extraction and voltage change extraction;

[0040] Step S344: performing a time series analysis on the abnormal current mutation feature data to generate abnormal current mutation time series data; using the abnormal current mutation time series data to perform a second abnormal scenario division on the complex abnormal pattern data to obtain phase-to-phase short circuit abnormal scenario data.

[0041] The present invention monitors and processes the three-phase current of the power station and the power line to generate corresponding monitoring data, which can capture the dynamic changes of the current in real time, ensure that the system can obtain the current fluctuation information in the power system in time, and provide basic data for subsequent analysis. By comparing and analyzing the balance of the three-phase current, the phase conductor current balance data is generated, and further by mutation detection, the phase conductor current mutation data is generated. This process can quickly identify the situation where the current balance is broken, especially when the current suddenly changes, it can effectively discover potential fault signals. By performing multi-dimensional feature extraction on the phase conductor current mutation data, multiple key parameters such as current mutation time, current mutation frequency range and voltage change are covered. This multi-dimensional feature extraction ensures a comprehensive analysis of sudden anomalies in the power system, not limited to a single current change, and further improves the accuracy of anomaly detection. By time series analysis of abnormal current mutation feature data, abnormal current mutation time series data is generated. Time series analysis can reveal the frequency and change law of current anomalies, which helps to predict the time point of fault occurrence in advance, thereby providing early warning signals for the power system. Abnormal current mutation time series data is used to perform a second scenario division on complex abnormal patterns to generate phase-to-phase short circuit abnormal scenario data. This precise scenario division can not only effectively distinguish phase-to-phase short circuit faults, but also more accurately identify the location and nature of the fault, which helps to quickly take repair measures. Through real-time monitoring and mutation detection, feature extraction, time series analysis and other multi-step current anomaly analysis, step S34 can quickly identify and locate potential faults in the power system, reduce the impact of faults on the system, and enhance the stability and operational safety of the power system.

[0042] Preferably, step S4 comprises the following steps:

[0043] Step S41: Integrate and process the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data to generate comprehensive fault scenario data; perform spatial range and impact analysis on the comprehensive fault scenario data to generate fault range data;

[0044] Step S42: performing a fault level assessment on the comprehensive fault scenario data according to the fault range data to generate fault risk level data; performing a path topology analysis on the power site transmission network using the fault risk level data to generate transmission path analysis data;

[0045] Step S43: performing redundancy evaluation on the transmission path analysis data to generate network redundancy evaluation data; formulating a load adjustment strategy based on the network redundancy evaluation data to generate load adjustment strategy data;

[0046] Step S44: Isolate the fault areas of the power site module and the power line module according to the fault range data and the fault risk level data, and generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data, and generate complex abnormal control adjustment data.

[0047] The present invention integrates multi-point fault abnormal scenario data and phase-to-phase short circuit abnormal scenario data to generate comprehensive fault scenario data, and generates fault range data through spatial range and impact analysis, so that the system can comprehensively evaluate multiple fault types, ensure that potential hidden dangers are not missed, and accurately determine the impact range of the fault, which is helpful for the accuracy of subsequent processing. According to the fault range data, the comprehensive fault scenario is evaluated for fault level, fault risk level data is generated, and transmission path analysis data is generated in combination with the topological analysis of the transmission path. By accurately evaluating the fault risk, the system can better formulate emergency measures, optimize the transmission network according to the risk level, and reduce the impact of the fault on the overall power grid. By evaluating the redundancy of the transmission path, network redundancy evaluation data is generated, and a load adjustment strategy is further formulated. This step can identify the redundant parts in the network, ensure that there are enough transmission channels for load transfer when a fault occurs, and enhance the stability and risk resistance of the system. Based on the fault range and fault risk level data, the power station and the power line module are fault isolated, fault isolation control strategy data is generated, and dynamic load transfer is performed through the load adjustment strategy to generate complex abnormal control adjustment data. This process ensures that when a fault occurs, the affected area can be quickly isolated, and the load can be dynamically adjusted to a safe area to avoid the spread of the fault and ensure the continuous operation of the power system. Through real-time fault level assessment, redundancy assessment and load adjustment, step S4 enables the system to respond quickly to sudden faults, and effectively reduce the impact of faults through dynamic load transfer and isolation strategies to improve the system's recovery capabilities. The entire chain of steps, from fault scenario integration, risk assessment, redundancy analysis to isolation and adjustment strategy formulation, forms a closed-loop fault management mechanism. Through advance analysis and dynamic adjustment, the power system can quickly control the scope of the fault, reduce the impact on power supply, and ensure a stable supply of electricity.

[0048] Preferably, step S44 includes the following steps:

[0049] Step S441: performing regional division processing on the fault range data to generate fault region division data; performing fault severity analysis based on the fault risk level data and the fault region division data to generate fault priority data; performing fault isolation path analysis on the fault priority data to generate preliminary fault isolation path data;

[0050] Step S442: Perform isolation analysis on the power site module and the power line module based on the preliminary fault isolation path data to generate fault isolation point selection data; perform circuit breaker action analysis on the fault isolation point selection data to generate circuit breaker control instruction data; perform fault area hierarchical isolation control strategy analysis on the circuit breaker control instruction data to generate fault isolation control strategy data;

[0051] Step S443: matching the fault isolation control strategy data with the load adjustment strategy data to generate dynamic load transfer analysis data; performing transmission line load balancing evaluation on the dynamic load transfer analysis data to generate load transfer optimization data; dynamically distributing loads to each power site module and power line module based on the load transfer optimization data to generate real-time load distribution data;

[0052] Step S444: Integrate the fault isolation control strategy data and the real-time load distribution data to generate complex abnormal control adjustment data.

[0053] The present invention generates fault area division data by performing regional division processing on the fault range data, and performs fault severity analysis in combination with the fault risk level data to generate fault priority data. This refined regional division and priority analysis ensures the pertinence and effectiveness of fault processing, so that the most serious fault area can be processed first, optimizes resource allocation, and generates preliminary fault isolation path data. After fault isolation path analysis, it is ensured that the optimal isolation path can be accurately found, so that the fault area can be effectively isolated, the impact on the rest of the system can be reduced, and the efficiency of fault processing can be improved. By selecting the fault isolation point and analyzing the circuit breaker action, circuit breaker control instruction data is generated. The generation of this control instruction can ensure the precise operation of the circuit breaker, so that the fault area can be quickly isolated, and the stability of the system can be further guaranteed. The fault isolation control strategy analysis and the generated control strategy data can systematically isolate the fault area in a hierarchical manner, which helps to control the fault impact to a minimum while keeping the system running. By matching the fault isolation control strategy data with the load adjustment strategy data, dynamic load transfer analysis data is generated, and load balancing is evaluated to generate load transfer optimization data, which ensures that after a fault occurs, the load can be effectively transferred and balanced to reduce the impact on the power system. Dynamic load distribution is performed according to the load transfer optimization data to generate real-time load distribution data. Such real-time distribution can quickly adapt to changes in system load, optimize the use of power resources, and improve the stability and efficiency of the power system. By integrating the fault isolation control strategy data and the real-time load distribution data, complex abnormal control adjustment data is generated. This comprehensive adjustment strategy can effectively respond to various complex abnormal situations and ensure that the system can quickly recover and maintain stable operation when a fault occurs. Through sophisticated fault isolation, circuit breaker control and dynamic load adjustment, step S44 improves the system's resilience and flexibility, enabling the power system to quickly respond to various fault scenarios and ensure continuous and safe power supply.

[0054] Preferably, step S5 comprises the following steps:

[0055] Step S51: performing abnormal fault recovery on the power site transmission network according to the single abnormal control adjustment data and the complex abnormal control adjustment data, and generating fault recovery operation data;

[0056] Step S52: continuously monitor the power recovery of the fault recovery operation data to generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

[0057] The present invention performs abnormal fault recovery on the power site transmission network by using single abnormal control adjustment data and complex abnormal control adjustment data. This recovery operation can quickly repair abnormal faults, restore the normal operation of the power system, and minimize the impact of the fault on the system. The fault recovery operation data is continuously monitored to generate adaptive power operation monitoring data. This real-time monitoring can timely discover and respond to new problems arising in the recovery process to ensure the continuous and stable operation of the power system. The fault recovery operation data is archived to generate fault recovery archive data. This process not only records the entire process of fault recovery, but also provides valuable historical data for future fault analysis and system optimization. The fault recovery operation data is archived to generate fault recovery archive data. This process not only records the entire process of fault recovery, but also provides valuable historical data for future fault analysis and system optimization. The fault recovery operation and continuous monitoring of step S5 can improve the recovery ability and stability of the power system in the face of abnormal situations. Through real-time monitoring and feedback adjustment, the system can respond to faults more flexibly and improve the reliability of the overall operation. Through fault recovery archive data and monitoring feedback data, the system can continuously optimize the operation strategy based on historical data and real-time feedback to improve the efficiency and accuracy of fault handling. Effective fault recovery and continuous monitoring reduce the risk of power system operation, ensure the continuity and stability of power supply, and protect the safety of users' electricity use.

[0058] In this specification, an intelligent power operation monitoring and control system is provided, which is used to execute the above-mentioned intelligent power operation monitoring and control method, and the intelligent power operation monitoring and control system includes:

[0059] A network construction module is used to obtain data uploaded by power stations; construct a power station distribution network for the data uploaded by power stations to obtain a power station distribution network; use the power station distribution network to store data uploaded by power stations to generate standard power station distribution storage data; perform line integration on the power station distribution storage data to generate a power station transmission network, wherein the power station transmission network includes a power station module and a power line module;

[0060] A single fault control module is used to perform dynamic power monitoring on the power site transmission network, generate power equipment monitoring data and power line monitoring data; perform abnormality detection on the power equipment monitoring data and the power line monitoring data, generate single abnormal mode data and complex abnormal mode data; adjust the first abnormal operation control of the dynamic monitoring data of the power site according to the single abnormal mode data, and generate single abnormal control adjustment data;

[0061] A complex fault scenario analysis module is used to perform time-series change spectrum conversion on the power site module and the power line module based on the complex abnormal pattern data to generate power site abnormal change frequency data and power line abnormal change frequency data; perform a first abnormal scenario division on the power site module and the power line module according to the generated power site abnormal change frequency data and power line abnormal change frequency data to obtain multi-point fault abnormal scenario data; perform phase conductor abnormal current analysis on the power site module and the power line module based on the complex abnormal pattern data to generate phase conductor abnormal current data; perform a second abnormal scenario division on the complex abnormal pattern data through the phase conductor abnormal current data to obtain phase-to-phase short circuit abnormal scenario data;

[0062] The complex fault control module is used to formulate load adjustment strategies for multi-point fault abnormal scenario data and phase-to-phase short circuit abnormal scenario data, and generate load adjustment strategy data; isolate the fault area of ​​the power site module and the power line module, and generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data, and generate complex abnormal control adjustment data;

[0063] The monitoring feedback module is used to continuously monitor the abnormal fault recovery of the power site transmission network based on the single abnormal control adjustment data and the complex abnormal control adjustment data, and generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

[0064] The beneficial effect of the present invention is that by constructing a power site distribution network and a transmission network, the power site data can be effectively integrated, standardized data storage and management can be realized, and a basis for subsequent dynamic monitoring and fault handling is provided, and the standardization and efficiency of power system data processing are improved. Dynamic monitoring of power equipment and power lines is realized, and single or complex abnormal modes can be discovered in time, and real-time adjustments can be made, which improves the stability of the power system and its ability to cope with abnormal situations, and reduces the impact of faults. Through data processing and time-series spectrum conversion of complex abnormal modes, abnormal changes in power sites and lines can be accurately identified, and multi-point faults and interphase short circuit scenarios can be further divided and analyzed, thereby improving the accuracy of abnormal detection and multi-dimensional fault handling capabilities. According to abnormal scenario data, load adjustment strategies are formulated and fault isolation is performed, local isolation of faults and dynamic load transfer are realized, thereby reducing the scope of fault impact and improving the recovery speed of the power system and the flexibility of fault response. Through continuous monitoring and adaptive adjustment of abnormal faults, automatic recovery and monitoring feedback of the power system can be realized, and the subsequent monitoring and adjustment process is optimized through feedback of fault archive data, thereby improving the long-term operation efficiency of the power system and the intelligent level of fault handling. Therefore, the present invention improves the accuracy and comprehensiveness of power monitoring and control by constructing a power site network, dynamic monitoring, intelligent anomaly detection and automated fault recovery. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic diagram of the steps of an intelligent power operation monitoring and control method;

[0066] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0067] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0068] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0069] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 3 , an intelligent power operation monitoring and control method, the method comprising the following steps:

[0073] Step S1: obtaining the power site uploaded data; constructing a power site distribution network for the power site uploaded data to obtain the power site distribution network; using the power site distribution network to store the power site uploaded data to generate standard power site distributed storage data; performing line integration on the power site distributed storage data to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module;

[0074] Step S2: Dynamically monitor the power transmission network of the power site to generate power equipment monitoring data and power line monitoring data; perform anomaly detection on the power equipment monitoring data and the power line monitoring data to generate single abnormal mode data and complex abnormal mode data; adjust the first abnormal operation control of the dynamic monitoring data of the power site according to the single abnormal mode data to generate single abnormal control adjustment data;

[0075] Step S3: Based on the complex abnormal pattern data, the power site module and the power line module are converted into a time-series change spectrum to generate abnormal change frequency data of the power site and abnormal change frequency data of the power line; the power site module and the power line module are divided into a first abnormal scenario according to the generated abnormal change frequency data of the power site and the abnormal change frequency data of the power line to obtain multi-point fault abnormal scenario data; based on the complex abnormal pattern data, the power site module and the power line module are analyzed for abnormal current of the phase conductor to generate abnormal current data of the phase conductor; the complex abnormal pattern data is divided into a second abnormal scenario according to the abnormal current data of the phase conductor to obtain abnormal scenario data of the phase short circuit;

[0076] Step S4: Formulate a load adjustment strategy for the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data to generate load adjustment strategy data; isolate the fault area of ​​the power site module and the power line module to generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data to generate complex abnormal control adjustment data;

[0077] Step S5: Continuously monitor the abnormal fault recovery of the power site transmission network according to the single abnormal control adjustment data and the complex abnormal control adjustment data to generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

[0078] The present invention constructs a power site distribution network, effectively integrates the data uploaded by the power site, realizes the systematic and standardized management of the site data, improves the organizational efficiency of the data, and after generating the power site transmission network, the relationship between the power site module and the power line module is clarified, providing a refined line integration foundation and providing support for subsequent monitoring and control. The standardized processing in the data storage process improves the operability and consistency of the data, laying a solid foundation for subsequent analysis and monitoring. Through the dynamic monitoring of power equipment and power lines, the real-time state of the system can be grasped, and the monitoring capability of the system can be greatly improved. Abnormal detection is subdivided into single abnormal mode and complex abnormal mode, which not only improves the accuracy of detection, but also can make targeted adjustments for different abnormal situations to prevent the expansion of potential hidden dangers. By generating single abnormal control adjustment data, small-scale abnormal problems can be quickly corrected and the overall fluctuation of the system can be reduced. By using the time-series change spectrum conversion technology of complex abnormal mode data, the abnormal change frequency of power sites and power lines can be more accurately captured and analyzed, and the accuracy of fault analysis can be improved. Through abnormal scenario division and phase conductor abnormal current analysis, in-depth analysis of complex scenarios such as multi-point faults and phase-to-phase short circuits is achieved, and the efficiency and accuracy of complex fault diagnosis are improved. The monitoring of the timing changes of power stations and line modules improves the ability to predict the development trend of faults and helps to prevent systemic faults in advance. According to the scenario data of multi-point faults and phase-to-phase short circuits, a load adjustment strategy is formulated to respond to abnormal situations under different loads in a timely manner and avoid system crashes caused by load imbalance. Through fault area isolation, the fault can be controlled within a local range to prevent the fault from spreading to the entire power grid, thereby improving the stability and operational reliability of the power grid. The dynamic load transfer strategy ensures the stable operation of the system and minimizes the impact of power outages or system paralysis by adjusting the load distribution in the fault area in real time. Abnormal fault recovery monitoring provides a continuous system monitoring function that can automatically adjust during the fault recovery process to ensure the adaptability and efficiency of the power system recovery process. Data archiving provides a detailed record for fault handling, and the feedback of these archived data helps to optimize future monitoring strategies and improve the long-term reliability of the system. Through the monitoring feedback mechanism, the recovery effect and operating status of the system can be monitored in real time, a continuous optimization scheme for the system status can be provided, and the intelligent level of system operation can be enhanced. Therefore, the present invention improves the accuracy and comprehensiveness of power monitoring and control by constructing a power station network, dynamic monitoring, intelligent anomaly detection and automated fault recovery.

[0079] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of an intelligent power operation monitoring and control method of the present invention. In this example, the intelligent power operation monitoring and control method includes the following steps:

[0080] Step S1: obtaining the power site uploaded data; constructing a power site distribution network for the power site uploaded data to obtain the power site distribution network; using the power site distribution network to store the power site uploaded data to generate standard power site distributed storage data; performing line integration on the power site distributed storage data to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module;

[0081] In an embodiment of the present invention, the uploaded data is obtained from each power site, and the data includes power equipment status, power consumption, transmission line status, load status, etc. The data is usually uploaded in a distributed manner, including structured data (such as database records) and unstructured data (such as log files or sensor data). In a local or cloud system, the data uploaded by the power site is initially stored for subsequent processing and analysis. The uploaded power site data is parsed to identify the geographical location information, power equipment and line connection information related to each power site. According to the geographical location of the site, the type of equipment and the distribution of transmission lines, a spatial distribution model of the power site is constructed. Based on the parsed data, a distribution network of the power site is designed. The network includes each power site and the connection relationship between them. The generated power site distribution network is stored in the form of a data model, including detailed topological structure information of the site and the line. Using the constructed power site distribution network, the data uploaded by the power site is reasonably stored and allocated, and different site data is stored in the corresponding database or distributed storage system. Each power site and its related data are marked with a unique identifier to facilitate subsequent retrieval and processing. Noise and outliers in the data are removed to ensure data quality. Use algorithms to denoise the data and reduce errors during transmission. Filling missing values ​​in the data can be done using interpolation or other machine learning algorithms. All data are normalized according to unified standards to ensure the accuracy of subsequent analysis and calculations. After data cleaning, denoising, missing value filling and standardization, the data is stored as standard power site distribution storage data. Analyze the transmission line data between power sites to obtain information such as line length, load capacity, voltage level, etc. Optimize the design of transmission lines based on transmission efficiency and power demand to ensure the stability of power transmission from source to terminal. Integrate power site and line data to form a complete power site transmission network. The network includes power transmission lines at each site and covers the connection relationship between each line. The generated power site transmission network is divided into two modules, namely the power site module and the power line module. The power site module contains specific data of each site, such as equipment, load, etc.; the power line module contains the line connection between each site and its transmission properties.

[0082] Step S2: Dynamically monitor the power transmission network of the power site to generate power equipment monitoring data and power line monitoring data; perform anomaly detection on the power equipment monitoring data and the power line monitoring data to generate single abnormal mode data and complex abnormal mode data; adjust the first abnormal operation control of the dynamic monitoring data of the power site according to the single abnormal mode data to generate single abnormal control adjustment data;

[0083] In an embodiment of the present invention, the operation status and load conditions of power equipment including transformers, switches, relays, etc. in the power site are obtained by real-time dynamic monitoring. The voltage, current, load capacity, line temperature and other parameters of the power transmission line are dynamically monitored to ensure the stable transmission of power. Various data such as equipment operation status, power output, voltage and current fluctuations of the line are collected regularly through sensors installed on the power equipment and power lines. The collected power site data is uploaded to the monitoring center through the communication network for real-time analysis. The state data of the monitored power equipment, such as equipment load, voltage, current, temperature, etc., are summarized to generate power equipment monitoring data. Various indicators of the line are monitored and power line monitoring data, such as line voltage, current, load capacity, etc., are generated. The monitoring data of the equipment and line are compared in real time through the preset parameter threshold. If the data exceeds or falls below the set safety threshold, it is marked as abnormal. Potential fault signals are identified by historical trend analysis of the operation data of the equipment and line. When an abnormality is detected in a single part of the power equipment or power line (such as a failure of a certain power equipment or an excessive load on a certain section of the power line), a single abnormal mode data is generated. When multiple anomalies are detected in power equipment and power lines at the same time, or there is a correlation between the anomalies, complex anomaly pattern data is generated. Anomaly data related to a single anomaly pattern is screened out from the power equipment monitoring data and the power line monitoring data. The screened anomaly data will mark the specific location, type and possible cause of the anomaly. Detailed power anomaly monitoring data is generated through the data screening process, including the location of equipment anomalies, line fault sections, etc. According to the power anomaly monitoring data, the prediction model is used to analyze the fault development trend. For a single anomaly (such as a single device or line anomaly), a fault prediction is performed based on its historical operating data and current monitoring data. The fault prediction results are converted into single abnormal fault prediction data, including the predicted time, location and severity of the fault. According to the single abnormal fault prediction data, a corresponding operation control adjustment strategy is formulated to reduce the impact of the fault on the operation of the power grid. The adjustment strategy includes reducing the load, shutting down specific equipment or performing local line switching. After the adjustment strategy is executed, a single abnormal control adjustment data is generated, which contains the adjusted operating parameters and control operation records.

[0084] Step S3: Based on the complex abnormal pattern data, the power site module and the power line module are converted into a time-series change spectrum to generate abnormal change frequency data of the power site and abnormal change frequency data of the power line; the power site module and the power line module are divided into a first abnormal scenario according to the generated abnormal change frequency data of the power site and the abnormal change frequency data of the power line to obtain multi-point fault abnormal scenario data; based on the complex abnormal pattern data, the power site module and the power line module are analyzed for abnormal current of the phase conductor to generate abnormal current data of the phase conductor; the complex abnormal pattern data is divided into a second abnormal scenario according to the abnormal current data of the phase conductor to obtain abnormal scenario data of the phase short circuit;

[0085] In an embodiment of the present invention, the voltage, current, and power fluctuations of the equipment in different time periods are captured by monitoring the time series changes of the operating status of the equipment in the power site module. The operating parameters of the power line (such as current, voltage, line impedance, etc.) are analyzed in time series to track the abnormal fluctuations of the line in different time periods. The time series change data of the power site and the power line are converted into a spectrum to analyze the corresponding frequency components when the abnormal event occurs. The time domain signal is converted into a frequency domain signal by fast Fourier transform (FFT) or wavelet transform to identify the frequency characteristics of the abnormal fluctuation. The abnormal frequency of the equipment in the power site module is extracted to generate frequency data reflecting the abnormal changes in the operation of the equipment. The abnormal fluctuation frequency of the power line module is extracted to generate the frequency data of abnormal changes in the line. When a single abnormality occurs in a certain device or a certain section of the line in the power site or power line module, it is defined as a single point fault scenario. When multiple devices or lines are abnormal at the same time and the abnormalities have a certain correlation, it is defined as a multi-point fault scenario. According to the abnormal change frequency data of the power site and the abnormal change frequency data of the power line, the abnormal frequency distribution of the equipment and the line is analyzed. Different abnormal events are classified by the similarity or correlation of frequency characteristics. For abnormal frequency fluctuations of multiple devices or lines, the common abnormal frequency characteristics are identified, and the fault scenarios of these devices or lines are classified as multi-point fault abnormal scenarios, and the corresponding scenario data are generated. The current detection is performed on the phase conductors in the power site module and the power line module, focusing on abnormal conditions such as current imbalance and phase difference between the phase conductors. Combined with the complex abnormal pattern data, the current fluctuations in the phase conductors are further analyzed to identify the caused fault risks. By comparing the three-phase currents, the phase-to-phase current imbalance phenomenon is identified. In particular, in complex abnormal conditions, current imbalance leads to phase-to-phase short circuits. By analyzing the current anomalies of the phase conductors, the abnormal current data of the phase conductors is generated for further fault analysis. When the abnormal current between the phase conductors leads to a short circuit, the situation is defined as a phase-to-phase short circuit scenario. The abnormal current data of the phase conductors is further analyzed to identify the phase-to-phase short circuit situation. Different short circuit types are classified by the severity of current imbalance and phase difference. For detected phase-to-phase short circuit conditions, abnormal phase-to-phase short circuit scenario data is generated, including detailed information such as the short circuit location and abnormal phase current conditions.

[0086] Step S4: Formulate a load adjustment strategy for the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data to generate load adjustment strategy data; isolate the fault area of ​​the power site module and the power line module to generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data to generate complex abnormal control adjustment data;

[0087] In an embodiment of the present invention, by analyzing the load conditions of different equipment and lines in the power site module and the power line module according to the multi-point fault abnormal scenario data, the load imbalance phenomenon caused by the multi-point fault is identified. Combined with the phase-to-phase short circuit abnormal scenario data, the current distribution abnormality caused by the phase-to-phase short circuit is analyzed, and the load change of each phase conductor is evaluated. According to the load deviation caused by the monitored multi-point fault and phase-to-phase short circuit, a corresponding load adjustment strategy is formulated. This process involves adjusting the power distribution of different power site modules and line modules to balance the overall load. The adjusted load distribution scheme is used as the load adjustment strategy data for the subsequent implementation of dynamic load transfer. According to the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data, the fault points that need to be isolated are identified, which involve equipment failures in the power site or short circuits in the power line. The identified fault points are divided into regions, and fault isolation planning is performed according to the fault type and severity. The power site module and the power line module in the fault area are isolated. Path analysis is performed to determine how to cut off the power connection between the fault area and the normal area to ensure that the fault does not affect the operation of the overall power network. According to the results of the isolation path analysis, fault isolation control strategy data is generated for performing actual isolation operations. The load adjustment strategy data is matched with the fault isolation control strategy data to ensure that while isolating the fault area, the load of the fault area can be distributed to other normally operating areas through load transfer to avoid excessive pressure on the power grid. By analyzing the load conditions of each area, a dynamic load transfer plan is formulated to generate dynamic load transfer analysis data. Based on the dynamic load transfer analysis data, the load in the fault area is reasonably distributed to other normally operating power site modules and power line modules to ensure the stability of the power network. The execution results of the load transfer are recorded as real-time load distribution data for subsequent monitoring and adjustment. By integrating the load adjustment strategy data with the real-time load distribution data, global control adjustments are made to power sites and lines under complex abnormal modes. Finally, the adjustment results are summarized to generate complex abnormal control adjustment data for overall adjustment and optimization of the system.

[0088] Step S5: Continuously monitor the abnormal fault recovery of the power site transmission network according to the single abnormal control adjustment data and the complex abnormal control adjustment data to generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

[0089] In an embodiment of the present invention, a recovery operation is performed on an abnormal fault in a power site transmission network through single abnormal control adjustment data and complex abnormal control adjustment data. The recovery operation includes restarting power equipment, reconnecting lines, or gradually recovering a fault isolation area. According to the fault recovery operation performed, the process and results of the fault recovery are recorded, and fault recovery operation data is generated for subsequent continuous monitoring and use. After the fault is recovered, the recovered power site transmission network is continuously and dynamically monitored to ensure the normal operation of the restored power equipment and lines. According to the real-time power equipment status and line status, adaptive power operation monitoring data is generated to ensure the adaptability and stability of the power network. The fault recovery operation data is sorted and archived to record the fault recovery process in the power site transmission network, including abnormal detection, recovery measures and results. The archived data is sorted into fault recovery archived data for subsequent historical analysis and fault management. Based on the fault recovery archived data, the adaptive power operation monitoring data is analyzed to identify potential problems or improvement space in the recovery process. By analyzing the differences between the monitoring data and the archived data, power operation monitoring feedback data is generated to provide a reference for future abnormal detection, fault recovery and monitoring optimization.

[0090] Preferably, step S1 comprises the following steps:

[0091] Step S11: Obtaining data uploaded by the power station;

[0092] Step S12: performing power site upload addressing on the power site upload data to generate power site address data; constructing a power site distribution network for the power site upload data according to the power site address data to obtain a power site distribution network;

[0093] Step S13: using the power site distribution network to store the data uploaded by the power site, and generating power site distribution storage data; performing data preprocessing on the power site distribution storage data, and generating standard power site distribution storage data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0094] Step S14: Perform power transmission route analysis on the power site distribution storage data to generate power transmission route data; perform line integration on the power site distribution network based on the power transmission route data to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module.

[0095] In an embodiment of the present invention, real-time or historical uploaded data is collected from sensors or monitoring devices at each power site, and these data include power load, voltage, frequency, fault records, etc. Ensure that the data is transmitted to a central server or data storage system through a secure and stable network. Use a geographic information system (GIS) tool or a built-in positioning service to parse the physical address or GPS coordinates of each power site to generate power site address data. According to the address data, a geographical distribution network of power sites is constructed, which can be modeled by the representation of nodes and edges. The nodes represent power sites, and the edges represent power transmission lines or communication links between sites. In the constructed power site distribution network, the uploaded data is stored in a corresponding database to generate power site distribution storage data. Remove erroneous, duplicated or irrelevant records in the data. Apply filters or other denoising algorithms to remove random noise in the data. Use interpolation or other filling methods to process missing values ​​in the data. Convert the data to a unified standard range for subsequent analysis and processing. According to the connection relationship and transmission path between power sites, identify and analyze the main routes of power transmission, involving route optimization algorithms to ensure the efficiency of power transmission, and generate power transmission route data, including route length, transmission capacity, fault points and other information. Based on the power transmission route data, the power site distribution network is integrated. The power transmission route data is combined with the power site module (representing the equipment and information of the power site) and the power line module (representing the facilities of the power transmission line) to form a complete power site transmission network.

[0096] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0097] Step S21: Dynamically monitor the power transmission network of the power site to generate dynamic monitoring data of the power site, wherein the dynamic monitoring data of the power site includes power equipment monitoring data and power line monitoring data;

[0098] Step S22: performing anomaly detection on the power equipment monitoring data and the power line monitoring data, and generating single abnormal pattern data when an abnormality is detected in the power equipment monitoring data or the power line monitoring data; generating complex abnormal pattern data when an abnormality is detected in the power equipment monitoring data and the power line monitoring data;

[0099] Step S23: Screening the power equipment monitoring data and the power line monitoring data for abnormal data according to the single abnormal pattern data to obtain abnormal power monitoring data;

[0100] Step S24: perform fault prediction on the power equipment monitoring data and the power line monitoring data through the power abnormality monitoring data to generate single abnormal fault prediction data; perform a first operation control adjustment on the single abnormal mode data through the single abnormal fault prediction data to generate single abnormal control adjustment data.

[0101] In an embodiment of the present invention, monitoring sensors such as current sensors, voltage sensors, temperature sensors, etc. are installed on key equipment and lines at power sites. Data of power equipment and power lines are collected in real time, including parameters such as the operating status of the equipment, power load, current, voltage, temperature, etc. The power equipment monitoring data and the power line monitoring data are integrated into dynamic monitoring data of the power site for subsequent analysis and processing. Statistical analysis methods or machine learning algorithms (such as isolated forests, local anomaly factors, etc.) are applied to analyze the power equipment monitoring data and the power line monitoring data to identify abnormal patterns. Combined with the power equipment monitoring data and the power line monitoring data, multivariate anomaly detection methods (such as principal component analysis, cluster analysis, etc.) are applied to identify complex abnormal patterns. Single abnormal pattern data is generated when only the power equipment monitoring data or the power line monitoring data is detected to be abnormal. Complex abnormal pattern data is generated when both the power equipment monitoring data and the power line monitoring data are detected to be abnormal. Using the generated single abnormal pattern data, an abnormal data screening algorithm (such as threshold detection, data mining technology, etc.) is applied to screen the power equipment monitoring data and the power line monitoring data to identify abnormal data. Organize the screened abnormal data into power anomaly monitoring data, and mark the abnormal time point, anomaly type and severity. Based on the power anomaly monitoring data, use prediction models (such as time series analysis, machine learning prediction models, etc.) to predict potential failures of power equipment and power lines. Provide early warnings of possible future failures of equipment or lines based on the single abnormal fault prediction data generated by the fault prediction model. Adjust the operation of power equipment based on the single abnormal fault prediction data. Adjustment strategies include changing operating parameters, performing preventive maintenance or temporarily shutting down to avoid the expansion of faults, generating control adjustment results for single abnormal mode data, and recording the adjusted operating effects and improvement suggestions.

[0102] Preferably, step S24 includes the following steps:

[0103] Step S241: extracting equipment status and operating parameters from the power equipment monitoring data and the power line monitoring data to obtain equipment status data and real-time operating parameter data, wherein the real-time operating parameter data includes voltage, current, temperature, vibration and frequency;

[0104] Step S242: performing anomaly matching analysis on the power abnormality monitoring data based on a preset historical fault database to generate abnormal type matching data; dividing the abnormal type matching data into data sets to generate a model training set and a model test set; performing model training on the model training set based on a support vector machine algorithm to generate a fault prediction pre-model;

[0105] Step S243: using the model test set to perform model optimization iteration on the fault prediction pre-model, thereby generating a fault prediction model; importing the equipment status data and real-time operation parameter data of the power equipment monitoring data or the power line monitoring data into the fault prediction pre-model to perform fault prediction, and generate single abnormal fault prediction data;

[0106] Step S244: adjusting the transformer voltage amplitude of the power equipment monitoring data based on the single abnormal fault prediction data to generate power equipment abnormal adjustment data; adjusting the power line transmission power of the power line monitoring data based on the single abnormal fault prediction data to generate power line abnormal adjustment data;

[0107] Step S245: integrating the power equipment abnormality adjustment data and the power line abnormality adjustment data into control data to generate single abnormality control adjustment data.

[0108] In an embodiment of the present invention, real-time monitoring data including equipment status and operating parameters (such as voltage, current, temperature, vibration, and frequency) are collected from power equipment (such as substation equipment, generators, and transformers). Real-time monitoring data including line status and operating parameters are collected from power lines (such as transmission lines and distribution lines). Equipment status data (such as working status and fault indication) are extracted from the collected data. Real-time operating parameter data such as voltage, current, temperature, vibration, and frequency are extracted. Anomaly matching analysis is performed on power abnormal monitoring data using a preset historical fault database to identify potential abnormal types. The analysis results are summarized as abnormal type matching data to identify the type and characteristics of each abnormality. The abnormal type matching data is divided into a model training set and a model test set for support vector machine (SVM) algorithm training. The model training set is trained using the SVM algorithm to generate a preliminary fault prediction pre-model. The fault prediction pre-model is optimized and iterated using the model test set, the model parameters are adjusted, and the prediction accuracy is improved, thereby generating an optimized fault prediction model. The equipment status data and real-time operating parameter data in the power equipment monitoring data or the power line monitoring data are imported into the optimized fault prediction model for fault prediction. Generate single abnormal fault prediction data about equipment or lines based on the fault prediction model. According to the single abnormal fault prediction data, adjust the voltage amplitude of the power equipment (such as transformer) to generate power equipment abnormal adjustment data. Adjust the voltage amplitude to cope with the predicted abnormality to avoid equipment overload or failure. According to the single abnormal fault prediction data, adjust the transmission power of the power line to generate power line abnormal adjustment data. Adjust the power load of the line to reduce the abnormal load and maintain stable power transmission. Integrate the power equipment abnormal adjustment data and the power line abnormal adjustment data to generate single abnormal control adjustment data. Combine the adjustment data of equipment and lines to formulate a comprehensive adjustment strategy to optimize the operating status of the overall power system. According to the generated single abnormal control adjustment data, implement the adjustment strategy of power equipment and power lines to reduce the risk of failure and improve system stability.

[0109] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0110] Step S31: Based on the complex abnormal pattern data, the power site module and the power line module are analyzed for abnormal time series changes to generate abnormal time series change data; the abnormal time series change data are analyzed for change frequency to generate power site abnormal change frequency data and power line abnormal change frequency data;

[0111] Step S32: Perform Fourier transformation on the abnormal change frequency data of the power site and the abnormal change frequency data of the power line to generate a power site abnormal change spectrum diagram and a power line abnormal change spectrum diagram; overlap the spectrum curves of the power site abnormal change spectrum diagram and the power line abnormal change spectrum diagram to generate a composite spectrum curve of abnormal power change;

[0112] Step S33: analyzing the abnormal change time interval of the power site module and the power line module through the power abnormal change composite spectrum curve to generate power node abnormal change time interval data; using the power node abnormal change time interval data to perform a first abnormal scenario division on the complex abnormal pattern data to obtain multi-point fault abnormal scenario data;

[0113] Step S34: Based on the complex abnormal pattern data, the power site module and the power line module are subjected to phase conductor abnormal current analysis to generate phase conductor abnormal current data; the complex abnormal pattern data is subjected to a second abnormal scenario division through the phase conductor abnormal current data to obtain phase-to-phase short circuit abnormal scenario data.

[0114] In an embodiment of the present invention, complex abnormal pattern data including a power site module and a power line module is obtained, including time series data. The abnormal time series data of the power site module and the power line module are analyzed for changes, and the time series change characteristics of the abnormal pattern are identified. The change trend of the abnormal time series is recorded, and the abnormal time series change data of the power site and the abnormal time series change data of the power line are generated. The change frequency of the abnormal time series change data is calculated, the abnormal change frequency of the power site and the power line is analyzed, and the abnormal change frequency data of the power site and the abnormal change frequency data of the power line are generated to reflect the frequency of abnormal occurrence. The abnormal change frequency data of the power site and the abnormal change frequency data of the power line are Fourier transformed to obtain a spectrum diagram, and the abnormal change spectrum diagram of the power site and the abnormal change spectrum diagram of the power line are generated to show the distribution of frequency components. The spectrum curve overlap analysis of the abnormal change spectrum diagram of the power site and the abnormal change spectrum diagram of the power line is performed to identify commonalities and differences, and the composite spectrum curve of abnormal power changes is obtained to show the comprehensive frequency characteristics. The composite spectrum curve of abnormal power changes is used to analyze the abnormal change time interval of the power site module and the power line module, record the time interval of abnormal changes, and generate the abnormal change time interval data of the power node. According to the time interval data of abnormal changes in power nodes, complex abnormal pattern data are divided, abnormal scenarios of multi-point failures are identified, and abnormal scenario data describing multi-point failures are obtained for further analysis. The phase conductor current data of the power site module and the power line module are obtained, the abnormal current data of the phase conductors are analyzed, and the abnormal current characteristics are identified. Based on the abnormal current data of the phase conductors, the complex abnormal pattern data are analyzed, the abnormal scenarios of phase-to-phase short circuits are divided, and the abnormal scenario data describing phase-to-phase short circuits are obtained for further risk assessment and management.

[0115] Preferably, step S34 includes the following steps:

[0116] Step S341: performing three-phase current data monitoring processing on the power site module and the power line module to generate power site three-phase current monitoring data and power line three-phase current monitoring data;

[0117] Step S342: performing current balance comparison analysis on the three-phase current monitoring data of the power station and the three-phase current monitoring data of the power line to generate phase conductor current balance data; performing mutation detection on the phase conductor current balance data to generate phase conductor current mutation data;

[0118] Step S343: performing multi-dimensional mutation feature extraction on the phase conductor current mutation data to generate abnormal current mutation feature data, wherein the multi-dimensional mutation feature extraction includes current mutation time extraction, current mutation frequency range extraction and voltage change extraction;

[0119] Step S344: performing a time series analysis on the abnormal current mutation feature data to generate abnormal current mutation time series data; using the abnormal current mutation time series data to perform a second abnormal scenario division on the complex abnormal pattern data to obtain phase-to-phase short circuit abnormal scenario data.

[0120] In an embodiment of the present invention, three-phase current sensors are installed at key locations of power stations and power lines, and these sensors should have high precision and real-time data transmission capabilities. A data acquisition system (such as a SCADA system) is used to record the three-phase current data of power stations and power lines in real time to ensure that the frequency and timeliness of data acquisition meet the monitoring requirements. The collected data is preprocessed, including noise removal (such as using a filter) and data smoothing (such as a moving average method) to improve the reliability of the data, and generate three-phase current monitoring data of power stations and three-phase current monitoring data of power lines. The balance of the three-phase current of each power station and power line is calculated. For example, the mean and standard deviation of each phase current are calculated to detect whether there is a significant current imbalance. Current balance data of power stations and power lines are formed to display the deviation and imbalance degree of each phase current. A mutation detection algorithm (such as a CUSUM algorithm or a Z-Score algorithm) is applied to identify mutation points in current data. The time point and amplitude of the mutation are recorded, and phase conductor current mutation data are generated to mark the specific location and degree of abnormal current changes. Use time series analysis tools (such as Fourier transform or Wavelet transform) to extract the time characteristics of the mutation, and record the specific time point of the current mutation and its duration. Use spectrum analysis tools (such as power spectrum density analysis) to determine the frequency range of the mutation, and record the frequency range of the mutation and its changes. Simultaneously monitor voltage data, analyze the voltage changes when the current mutation occurs, record the voltage changes before and after the mutation, and combine the current mutation time, frequency range and voltage changes to generate abnormal current mutation feature data, including the characteristic values ​​of each dimension. Use time series analysis methods (such as autoregressive model ARIMA or long short-term memory network LSTM) to analyze the abnormal current mutation feature data, generate abnormal current mutation time series data, and show the change trend of current mutation characteristics over time. Based on the abnormal current mutation time series data, analyze complex abnormal patterns and identify potential abnormal patterns. Use abnormal scenario classification methods (such as model-based classification or cluster analysis) to divide complex abnormal patterns into different abnormal scenarios. According to the analysis results, determine whether there is an interphase short circuit abnormality, and generate interphase short circuit abnormal scenario data.

[0121] Preferably, step S4 comprises the following steps:

[0122] Step S41: Integrate and process the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data to generate comprehensive fault scenario data; perform spatial range and impact analysis on the comprehensive fault scenario data to generate fault range data;

[0123] Step S42: performing a fault level assessment on the comprehensive fault scenario data according to the fault range data to generate fault risk level data; performing a path topology analysis on the power site transmission network using the fault risk level data to generate transmission path analysis data;

[0124] Step S43: performing redundancy evaluation on the transmission path analysis data to generate network redundancy evaluation data; formulating a load adjustment strategy based on the network redundancy evaluation data to generate load adjustment strategy data;

[0125] Step S44: Isolate the fault areas of the power site module and the power line module according to the fault range data and the fault risk level data, and generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data, and generate complex abnormal control adjustment data.

[0126] In an embodiment of the present invention, information is extracted from multi-point fault abnormal scenario data and phase-to-phase short circuit abnormal scenario data. Data fusion technology (such as weighted average, principal component analysis PCA) is used to integrate the two data sets to generate comprehensive fault scenario data, covering all types of fault information. The comprehensive fault scenario data is mapped into a geographic information system. Spatial analysis tools (such as buffer analysis, spatial clustering) are used to determine the spatial scope of the fault. Based on the spatial scope data, the potential impact of the fault on different areas (such as power outage areas) is evaluated, and fault scope data is generated to describe the area and extent of the fault impact. Evaluation criteria (such as fault severity, impact range) are set according to the fault scope data. An evaluation model (such as a fault impact scoring model) is used to score the comprehensive fault scenario data to reflect the risk level (such as low, medium, and high risk) of each fault scenario. The fault risk level data is used to analyze the path of the power site transmission network. Network analysis tools (such as the shortest path algorithm and the optimization algorithm) are used to perform path topology analysis. The risk level and influencing factors of each path in the network are displayed. Based on the transmission path analysis data, the redundancy of the network (such as backup paths and backup devices) is evaluated. Calculate redundancy using redundancy assessment tools (e.g., network redundancy analysis, redundancy matrix). Use network redundancy assessment data to develop load adjustment strategies. Apply load balancing algorithms (e.g., load balancing algorithms, resource optimization models) to generate load adjustment strategies and generate load adjustment strategy data, including specific load adjustment plans, such as load transfer, enabling alternate paths, etc. Use fault range data and fault risk level data to develop isolation strategies. Apply fault isolation control technology (e.g., automatic switches, circuit breaker control) to perform fault area isolation, generate fault isolation control strategy data, and describe specific measures and operation steps for fault isolation. Dynamically adjust fault isolation control strategy data based on load adjustment strategy data. Perform dynamic load transfer (e.g., adjust load distribution, enable alternate network paths) to maintain system stability. Record the execution of dynamic load transfer and the adjusted system status.

[0127] Preferably, step S44 includes the following steps:

[0128] Step S441: performing regional division processing on the fault range data to generate fault region division data; performing fault severity analysis based on the fault risk level data and the fault region division data to generate fault priority data; performing fault isolation path analysis on the fault priority data to generate preliminary fault isolation path data;

[0129] Step S442: Perform isolation analysis on the power site module and the power line module based on the preliminary fault isolation path data to generate fault isolation point selection data; perform circuit breaker action analysis on the fault isolation point selection data to generate circuit breaker control instruction data; perform fault area hierarchical isolation control strategy analysis on the circuit breaker control instruction data to generate fault isolation control strategy data;

[0130] Step S443: matching the fault isolation control strategy data with the load adjustment strategy data to generate dynamic load transfer analysis data; performing transmission line load balancing evaluation on the dynamic load transfer analysis data to generate load transfer optimization data; dynamically distributing loads to each power site module and power line module based on the load transfer optimization data to generate real-time load distribution data;

[0131] Step S444: Integrate the fault isolation control strategy data and the real-time load distribution data to generate complex abnormal control adjustment data.

[0132] In an embodiment of the present invention, by obtaining fault range data, including the geographical location and impact range of the fault, the fault range data is spatially divided using a geographic information system (GIS) or a regional analysis tool. According to the degree of fault impact and the size of the region, multiple fault regions are divided, fault region division data is generated, the boundaries and characteristics of each region are clarified, and the fault region division data is generated to clarify the boundaries and characteristics of each region. Combined with the fault region division data and the fault risk level data, a weighted scoring model or a multi-standard decision analysis method (such as AHP) is used to perform a severity analysis of the fault, generate fault priority data, and sort the processing priority of the fault region. According to the fault priority data, a graph algorithm (such as a shortest path algorithm, a minimum spanning tree algorithm) or a network flow optimization algorithm is used to analyze and plan the path of fault isolation, and generate preliminary fault isolation path data, including recommended isolation points and paths. Using the preliminary fault isolation path data, the power site module and the power line module are isolated and analyzed. The most effective isolation point is determined to minimize the impact of the fault on the system, and fault isolation point selection data is generated, including detailed information and operation suggestions for each isolation point. Based on the fault isolation point selection data, the circuit breaker in the system is analyzed for action. Determine the circuit breakers that need to be operated and their action sequence, and generate circuit breaker control instruction data, including specific switch operation instructions and operation time. According to the circuit breaker control instruction data, formulate a hierarchical isolation control strategy for the fault area, which includes isolation control measures and priorities for different areas, and generate fault isolation control strategy data, including details of hierarchical control and strategy implementation plan. Match the fault isolation control strategy data with the load adjustment strategy data. Determine which loads need to be transferred and how to optimize load distribution to cope with faults, and generate dynamic load transfer analysis data, including detailed plans and implementation steps for load transfer. Evaluate the load balance of transmission lines based on the dynamic load transfer analysis data. Use load flow analysis tools or optimization algorithms to evaluate the impact of load transfer on line loads, and generate load transfer optimization data, including optimized load distribution and line load balancing recommendations. According to the load transfer optimization data, dynamically distribute loads to each power site module and power line module. Implement load distribution adjustment to ensure system load balance, generate real-time load distribution data, and provide current load distribution and adjustment results. Integrate the fault isolation control strategy data and real-time load distribution data. Evaluate the control effect and load adjustment effect under complex abnormal conditions, and generate complex abnormal control adjustment data, including comprehensive control strategies and implementation plans that comprehensively consider fault isolation and load adjustment.

[0133] Preferably, step S5 comprises the following steps:

[0134] Step S51: performing abnormal fault recovery on the power site transmission network according to the single abnormal control adjustment data and the complex abnormal control adjustment data, and generating fault recovery operation data;

[0135] Step S52: continuously monitor the power recovery of the fault recovery operation data to generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

[0136] In the embodiment of the present invention, by obtaining single abnormal control adjustment data and complex abnormal control adjustment data, these data include control measures and adjustment strategies for different abnormal situations. These control adjustment data are applied to the power site transmission network to analyze and determine the best fault recovery operation. According to the analysis results, the fault recovery operation is performed, including adjusting the operating status of the power equipment, reconfiguring the power line, starting the backup equipment, etc. The detailed information of all recovery operations is recorded, and the fault recovery operation data is generated. These data should include the time of the operation, the execution steps, the recovery effect, etc. A continuous monitoring system is established to monitor the power system after the fault recovery operation in real time. The monitoring content includes the operating status of the system, the power load, the health status of the equipment, etc., and the adaptive power operation monitoring data is generated. These data reflect the actual operation of the system after the fault recovery and the adaptability of the system. The fault recovery operation data is systematically archived. The data archive should include the records of all recovery operations, monitoring data and related documents, generate fault recovery archive data, and provide detailed data support for subsequent audits and analysis. The adaptive power operation monitoring data is monitored and fed back using the fault recovery archive data. Evaluate the effectiveness of fault recovery operations and make improvement suggestions based on actual operating conditions, generate power operation monitoring feedback data, provide evaluation of the fault recovery process, and point out any potential problems or optimization space in the system.

[0137] In this specification, an intelligent power operation monitoring and control system is provided, which is used to execute the above-mentioned intelligent power operation monitoring and control method, and the intelligent power operation monitoring and control system includes:

[0138] A network construction module is used to obtain data uploaded by power stations; construct a power station distribution network for the data uploaded by power stations to obtain a power station distribution network; use the power station distribution network to store data uploaded by power stations to generate standard power station distribution storage data; perform line integration on the power station distribution storage data to generate a power station transmission network, wherein the power station transmission network includes a power station module and a power line module;

[0139] A single fault control module is used to perform dynamic power monitoring on the power site transmission network, generate power equipment monitoring data and power line monitoring data; perform abnormality detection on the power equipment monitoring data and the power line monitoring data, generate single abnormal mode data and complex abnormal mode data; adjust the first abnormal operation control of the dynamic monitoring data of the power site according to the single abnormal mode data, and generate single abnormal control adjustment data;

[0140] A complex fault scenario analysis module is used to perform time-series change spectrum conversion on the power site module and the power line module based on the complex abnormal pattern data to generate power site abnormal change frequency data and power line abnormal change frequency data; perform a first abnormal scenario division on the power site module and the power line module according to the generated power site abnormal change frequency data and power line abnormal change frequency data to obtain multi-point fault abnormal scenario data; perform phase conductor abnormal current analysis on the power site module and the power line module based on the complex abnormal pattern data to generate phase conductor abnormal current data; perform a second abnormal scenario division on the complex abnormal pattern data through the phase conductor abnormal current data to obtain phase-to-phase short circuit abnormal scenario data;

[0141] The complex fault control module is used to formulate load adjustment strategies for multi-point fault abnormal scenario data and phase-to-phase short circuit abnormal scenario data, and generate load adjustment strategy data; isolate the fault area of ​​the power site module and the power line module, and generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data, and generate complex abnormal control adjustment data;

[0142] The monitoring feedback module is used to continuously monitor the abnormal fault recovery of the power site transmission network based on the single abnormal control adjustment data and the complex abnormal control adjustment data, and generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

[0143] The beneficial effect of the present invention is that by constructing a power site distribution network and a transmission network, the power site data can be effectively integrated, standardized data storage and management can be realized, and a basis for subsequent dynamic monitoring and fault handling is provided, and the standardization and efficiency of power system data processing are improved. Dynamic monitoring of power equipment and power lines is realized, and single or complex abnormal modes can be discovered in time, and real-time adjustments can be made, which improves the stability of the power system and its ability to cope with abnormal situations, and reduces the impact of faults. Through data processing and time-series spectrum conversion of complex abnormal modes, abnormal changes in power sites and lines can be accurately identified, and multi-point faults and interphase short circuit scenarios can be further divided and analyzed, thereby improving the accuracy of abnormal detection and multi-dimensional fault handling capabilities. According to abnormal scenario data, load adjustment strategies are formulated and fault isolation is performed, local isolation of faults and dynamic load transfer are realized, thereby reducing the scope of fault impact and improving the recovery speed of the power system and the flexibility of fault response. Through continuous monitoring and adaptive adjustment of abnormal faults, automatic recovery and monitoring feedback of the power system can be realized, and the subsequent monitoring and adjustment process is optimized through feedback of fault archive data, thereby improving the long-term operation efficiency of the power system and the intelligent level of fault handling. Therefore, the present invention improves the accuracy and comprehensiveness of power monitoring and control by constructing a power site network, dynamic monitoring, intelligent anomaly detection and automated fault recovery.

[0144] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0145] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent power operation monitoring and control method, characterized in that: The following steps are involved: Step S1: Obtaining data uploaded by the power station; Constructing a power site distribution network for the power site uploaded data to obtain a power site distribution network; using the power site distribution network to store data uploaded data from the power site to generate standard power site distribution storage data; Perform line integration on the distributed storage data of the power site to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module; Step S2: Dynamically monitor the power transmission network of the power site to generate power equipment monitoring data and power line monitoring data; Perform anomaly detection on power equipment monitoring data and power line monitoring data to generate single anomaly pattern data and complex anomaly pattern data; The first abnormal operation control adjustment of the dynamic monitoring data of the power site is performed according to the single abnormal mode data to generate single abnormal control adjustment data; when an abnormality is detected in a single part of the power equipment or the power line, a single abnormal mode data is generated; when multiple abnormalities are detected in the power equipment and the power line at the same time, or there is a correlation between the abnormalities, complex abnormal mode data is generated; Step S3: Based on the complex abnormal pattern data, the power site module and the power line module are converted into a time series change spectrum to generate abnormal change frequency data of the power site and abnormal change frequency data of the power line; According to the generated power site abnormal change frequency data and the power line abnormal change frequency data, the power site module and the power line module are divided into the first abnormal scenario to obtain multi-point fault abnormal scenario data; Based on the complex abnormal pattern data, the power site module and the power line module are analyzed for abnormal current of the phase conductors to generate abnormal current data of the phase conductors; The complex abnormal pattern data is divided into a second abnormal scenario by using the abnormal current data of the phase conductor to obtain the abnormal scenario data of the phase short circuit; Step S4: Formulate a load adjustment strategy for the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data to generate load adjustment strategy data; Isolate the fault area of ​​the power site module and the power line module to generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data to generate complex abnormal control adjustment data; Step S5: Performing continuous monitoring of abnormal fault recovery on the power site transmission network according to the single abnormal control adjustment data and the complex abnormal control adjustment data to generate adaptive power operation monitoring data; Archiving the fault recovery operation data to generate fault recovery archive data; Based on the fault recovery archived data, monitoring feedback is performed on the adaptive power operation monitoring data to generate power operation monitoring feedback data.

2. The intelligent power operation monitoring and control method according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtaining data uploaded by the power station; Step S12: performing power site upload addressing on the power site upload data to generate power site address data; constructing a power site distribution network for the power site upload data according to the power site address data to obtain a power site distribution network; Step S13: using the power site distribution network to store the data uploaded by the power site, and generating power site distribution storage data; performing data preprocessing on the power site distribution storage data, and generating standard power site distribution storage data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S14: Perform power transmission route analysis on the power site distribution storage data to generate power transmission route data; perform line integration on the power site distribution network based on the power transmission route data to generate a power site transmission network, wherein the power site transmission network includes a power site module and a power line module.

3. The intelligent power operation monitoring and control method according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Dynamically monitor the power transmission network of the power site to generate dynamic monitoring data of the power site, wherein the dynamic monitoring data of the power site includes power equipment monitoring data and power line monitoring data; Step S22: performing anomaly detection on the power equipment monitoring data and the power line monitoring data, and generating single abnormal pattern data when an abnormality is detected in the power equipment monitoring data or the power line monitoring data; generating complex abnormal pattern data when an abnormality is detected in the power equipment monitoring data and the power line monitoring data; Step S23: Screening the power equipment monitoring data and the power line monitoring data for abnormal data according to the single abnormal pattern data to obtain abnormal power monitoring data; Step S24: perform fault prediction on the power equipment monitoring data and the power line monitoring data through the power abnormality monitoring data to generate single abnormal fault prediction data; perform a first operation control adjustment on the single abnormal mode data through the single abnormal fault prediction data to generate single abnormal control adjustment data.

4. The intelligent power operation monitoring and control method according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: extracting equipment status and operating parameters from the power equipment monitoring data and the power line monitoring data to obtain equipment status data and real-time operating parameter data, wherein the real-time operating parameter data includes voltage, current, temperature, vibration and frequency; Step S242: performing anomaly matching analysis on the power abnormality monitoring data based on a preset historical fault database to generate abnormal type matching data; dividing the abnormal type matching data into data sets to generate a model training set and a model test set; performing model training on the model training set based on a support vector machine algorithm to generate a fault prediction pre-model; Step S243: using the model test set to perform model optimization iteration on the fault prediction pre-model, thereby generating a fault prediction model; importing the equipment status data and real-time operation parameter data of the power equipment monitoring data or the power line monitoring data into the fault prediction pre-model to perform fault prediction, and generate single abnormal fault prediction data; Step S244: adjusting the transformer voltage amplitude of the power equipment monitoring data based on the single abnormal fault prediction data to generate power equipment abnormal adjustment data; adjusting the power line transmission power of the power line monitoring data based on the single abnormal fault prediction data to generate power line abnormal adjustment data; Step S245: integrating the power equipment abnormality adjustment data and the power line abnormality adjustment data into control data to generate single abnormality control adjustment data.

5. The intelligent power operation monitoring and control method according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Based on the complex abnormal pattern data, the power site module and the power line module are analyzed for abnormal time series changes to generate abnormal time series change data; the abnormal time series change data are analyzed for change frequency to generate power site abnormal change frequency data and power line abnormal change frequency data; Step S32: Perform Fourier transformation on the abnormal change frequency data of the power site and the abnormal change frequency data of the power line to generate a power site abnormal change spectrum diagram and a power line abnormal change spectrum diagram; overlap the spectrum curves of the power site abnormal change spectrum diagram and the power line abnormal change spectrum diagram to generate a composite spectrum curve of abnormal power change; Step S33: analyzing the abnormal change time interval of the power site module and the power line module through the power abnormal change composite spectrum curve to generate power node abnormal change time interval data; using the power node abnormal change time interval data to perform a first abnormal scenario division on the complex abnormal pattern data to obtain multi-point fault abnormal scenario data; Step S34: Based on the complex abnormal pattern data, the power site module and the power line module are subjected to phase conductor abnormal current analysis to generate phase conductor abnormal current data; the complex abnormal pattern data is subjected to a second abnormal scenario division through the phase conductor abnormal current data to obtain phase-to-phase short circuit abnormal scenario data.

6. The intelligent power operation monitoring and control method according to claim 5 is characterized in that: Step S34 includes the following steps: Step S341: performing three-phase current data monitoring processing on the power site module and the power line module to generate power site three-phase current monitoring data and power line three-phase current monitoring data; Step S342: performing current balance comparison analysis on the three-phase current monitoring data of the power station and the three-phase current monitoring data of the power line to generate phase conductor current balance data; performing mutation detection on the phase conductor current balance data to generate phase conductor current mutation data; Step S343: performing multi-dimensional mutation feature extraction on the phase conductor current mutation data to generate abnormal current mutation feature data, wherein the multi-dimensional mutation feature extraction includes current mutation time extraction, current mutation frequency range extraction and voltage change extraction; Step S344: performing a time series analysis on the abnormal current mutation feature data to generate abnormal current mutation time series data; using the abnormal current mutation time series data to perform a second abnormal scenario division on the complex abnormal pattern data to obtain phase-to-phase short circuit abnormal scenario data.

7. The intelligent power operation monitoring and control method according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: Integrate and process the multi-point fault abnormal scenario data and the phase-to-phase short circuit abnormal scenario data to generate comprehensive fault scenario data; perform spatial range and impact analysis on the comprehensive fault scenario data to generate fault range data; Step S42: performing a fault level assessment on the comprehensive fault scenario data according to the fault range data to generate fault risk level data; performing a path topology analysis on the power site transmission network using the fault risk level data to generate transmission path analysis data; Step S43: performing redundancy evaluation on the transmission path analysis data to generate network redundancy evaluation data; formulating a load adjustment strategy based on the network redundancy evaluation data to generate load adjustment strategy data; Step S44: Isolate the fault areas of the power site module and the power line module according to the fault range data and the fault risk level data, and generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data, and generate complex abnormal control adjustment data.

8. The intelligent power operation monitoring and control method according to claim 7 is characterized in that: Step S44 includes the following steps: Step S441: performing regional division processing on the fault range data to generate fault region division data; performing fault severity analysis based on the fault risk level data and the fault region division data to generate fault priority data; performing fault isolation path analysis on the fault priority data to generate preliminary fault isolation path data; Step S442: Perform isolation analysis on the power site module and the power line module based on the preliminary fault isolation path data to generate fault isolation point selection data; perform circuit breaker action analysis on the fault isolation point selection data to generate circuit breaker control instruction data; perform fault area hierarchical isolation control strategy analysis on the circuit breaker control instruction data to generate fault isolation control strategy data; Step S443: matching the fault isolation control strategy data with the load adjustment strategy data to generate dynamic load transfer analysis data; performing transmission line load balancing evaluation on the dynamic load transfer analysis data to generate load transfer optimization data; dynamically distributing loads to each power site module and power line module based on the load transfer optimization data to generate real-time load distribution data; Step S444: Integrate the fault isolation control strategy data and the real-time load distribution data to generate complex abnormal control adjustment data.

9. The intelligent power operation monitoring and control method according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: performing abnormal fault recovery on the power site transmission network according to the single abnormal control adjustment data and the complex abnormal control adjustment data, and generating fault recovery operation data; Step S52: continuously monitor the power recovery of the fault recovery operation data to generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

10. An intelligent power operation monitoring and control system, characterized in that: Used to execute the intelligent power operation monitoring and control method as claimed in claim 1, the intelligent power operation monitoring and control system comprises: A network construction module is used to obtain data uploaded by power stations; construct a power station distribution network for the data uploaded by power stations to obtain a power station distribution network; use the power station distribution network to store data uploaded by power stations to generate standard power station distribution storage data; perform line integration on the power station distribution storage data to generate a power station transmission network, wherein the power station transmission network includes a power station module and a power line module; A single fault control module is used to perform dynamic power monitoring on the power site transmission network, generate power equipment monitoring data and power line monitoring data; perform abnormality detection on the power equipment monitoring data and the power line monitoring data, generate single abnormal mode data and complex abnormal mode data; adjust the first abnormal operation control of the dynamic monitoring data of the power site according to the single abnormal mode data, and generate single abnormal control adjustment data; A complex fault scenario analysis module is used to perform time-series change spectrum conversion on the power site module and the power line module based on the complex abnormal pattern data to generate power site abnormal change frequency data and power line abnormal change frequency data; perform a first abnormal scenario division on the power site module and the power line module according to the generated power site abnormal change frequency data and power line abnormal change frequency data to obtain multi-point fault abnormal scenario data; perform phase conductor abnormal current analysis on the power site module and the power line module based on the complex abnormal pattern data to generate phase conductor abnormal current data; perform a second abnormal scenario division on the complex abnormal pattern data through the phase conductor abnormal current data to obtain phase-to-phase short circuit abnormal scenario data; The complex fault control module is used to formulate load adjustment strategies for multi-point fault abnormal scenario data and phase-to-phase short circuit abnormal scenario data, and generate load adjustment strategy data; isolate the fault area of ​​the power site module and the power line module, and generate fault isolation control strategy data; dynamically transfer the load of the fault isolation control strategy data through the load adjustment strategy data, and generate complex abnormal control adjustment data; The monitoring feedback module is used to continuously monitor the abnormal fault recovery of the power site transmission network based on the single abnormal control adjustment data and the complex abnormal control adjustment data, and generate adaptive power operation monitoring data; archive the fault recovery operation data to generate fault recovery archive data; monitor and feedback the adaptive power operation monitoring data based on the fault recovery archive data to generate power operation monitoring feedback data.

Images