A method for collecting electric energy in a distribution network

Abstract

The present invention relates to the technical field of electric energy collection in distribution networks, and in particular to an electric energy collection method for distribution networks. The method comprises the following steps: collecting electrical data of the distribution network and collecting electromagnetic field data of the distribution network transmission lines and transformers in operation, respectively obtaining transmission electromagnetic data and electromagnetic transformer data; performing three-dimensional surface graph conversion according to the transmission electromagnetic data and performing electromagnetic fluctuation fault identification to obtain electromagnetic fluctuation fault data; performing fluctuation anomaly identification on the electromagnetic fluctuation fault data and performing abnormal voltage fluctuation interval calculation and impact effect analysis and performing performance loss analysis on the distribution network transformer and performing automated electromagnetic abnormality analysis mode design to obtain an automated electromagnetic analysis module; performing electric energy loss compensation design on the automated electromagnetic analysis module to obtain an automated electric energy collection and analysis module. The present invention enables electric energy collection to accurately detect abnormal conditions by improving the electric energy collection technology.

Description

A method for collecting electric energy in a distribution network Technical Field

[0001] The present invention relates to the technical field of electric energy collection in a distribution network, and in particular to an electric energy collection method in a distribution network. Background Art

[0002] The smart grid management system is the core of power collection in the distribution network. It monitors, manages and dispatches the power grid through data analysis, optimization control and prediction models. It can monitor power collection in real time, optimize energy distribution and dispatch, and improve energy efficiency and system reliability. However, the traditional power collection method of the distribution network has the problem of inaccurate detection of circuit abnormal points and inaccurate analysis of power performance loss. Summary of the invention

[0003] Based on this, it is necessary to provide a method for collecting electric energy in a distribution network to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for collecting electric energy from a distribution network is provided, the method comprising the following steps:

[0005] Step S1: Collect electrical data of the distribution network to obtain electrical data of the distribution network; collect electromagnetic field data of the distribution network transmission lines and transformers in operation based on the electrical data of the distribution network to obtain transmission electromagnetic data and electromagnetic transformation data respectively;

[0006] Step S2: performing three-dimensional surface map conversion according to the transmission electromagnetic data to obtain a transmission electromagnetic three-dimensional surface map; performing electromagnetic wave fault identification according to the transmission electromagnetic three-dimensional surface map to obtain electromagnetic wave fault data; performing fluctuation anomaly identification on the electromagnetic wave fault data to obtain electromagnetic abnormal fluctuation report data;

[0007] Step S3: Calculate the abnormal voltage fluctuation interval of the electromagnetic abnormal fluctuation report data to obtain abnormal voltage interval data; analyze the impact effect of the electromagnetic transformation data according to the abnormal voltage interval data to obtain electromagnetic transformation impact effect data; analyze the performance loss of the distribution network transformer according to the electromagnetic transformation impact effect data to obtain transformer performance loss data;

[0008] Step S4: Design an automated electromagnetic anomaly analysis model based on the electromagnetic anomaly fluctuation report data to obtain an automated electromagnetic analysis module; design power loss compensation for the automated electromagnetic analysis module to obtain an automated power collection and analysis module.

[0009] The present invention can obtain the electrical parameters of each transmission line and transformer of the distribution network through electrical data collection, provide comprehensive operating status information, and can obtain the electrical parameters of current, voltage, and power factor of each key point, which provides basic data for comprehensive monitoring of the system operating status and helps to understand the actual working conditions of the power system. By collecting electromagnetic field data of the transmission line based on electrical data, transmission electromagnetic data is obtained, which helps to understand the strength and distribution of the electromagnetic field on the transmission line and on the transformer; by converting the transmission electromagnetic data into a three-dimensional surface diagram, an intuitive visual representation of the electromagnetic field is provided. This visual presentation helps engineers and researchers quickly understand the distribution and characteristics of the electromagnetic field. On the basis of the transmission electromagnetic three-dimensional surface diagram On the electromagnetic fluctuation fault identification, these faults may represent abnormal or mutation areas of the electromagnetic field, which are related to potential faults or irregular operations. The electromagnetic fluctuation fault data is further analyzed and processed to generate electromagnetic abnormal fluctuation report data. These reports provide a detailed description of abnormal electromagnetic behavior, including location, intensity and duration. The electromagnetic fluctuation fault data is used to identify fluctuation anomalies, which helps to capture possible electromagnetic abnormal events in the system. The generated electromagnetic abnormal fluctuation report data provides decision makers with important information about the health of the electromagnetic environment. These data can be used to optimize operation strategies, formulate preventive maintenance plans and make system improvements; by analyzing the electromagnetic abnormal fluctuation report data, the interval of abnormal voltage fluctuation is calculated. This helps to determine the period and range of abnormal voltage, provides a temporal and spatial context for further analysis, and analyzes the impact effect of electromagnetic transformer data. This includes the impact of electromagnetic field anomalies on transformer performance, involving electromagnetic induction and hysteresis factors. This analysis provides the specific impact mechanism of abnormal electromagnetic fields on transformers, and performs performance loss analysis on transformers in distribution networks, including the impact on rated capacity loss, temperature rise, and energy efficiency reduction of transformers. Performance loss analysis helps to evaluate the health status and performance degradation of transformers, and generate detailed transformer performance loss data, which includes transformer losses, temperature rise, and rated capacity reduction. By understanding the actual impact of electromagnetic anomalies on transformer performance, preventive maintenance plans can be formulated to avoid potential equipment failures and system interruptions. In addition, operational strategies can be optimized based on performance loss data to maximize the normal operation of equipment. Through the automated electromagnetic anomaly analysis mode, the system can intelligently process a large amount of electromagnetic anomaly fluctuation report data, including automatic identification of abnormal patterns, extraction of key features, and establishment of electromagnetic anomaly models. The automation module can monitor electromagnetic anomalies in real time to make the system more responsive.This helps to discover potential problems early, reduces dependence on manual intervention, and improves the automation level of the system. Based on the design of the electromagnetic anomaly analysis mode, the system can more accurately predict potential electromagnetic anomalies, help take preventive maintenance measures, and reduce system downtime. Through the design of the power loss compensation of the automated electromagnetic analysis module, the system can reduce power loss and improve the overall efficiency of the system, which is particularly important for the power supply system, because the improvement of energy efficiency means less waste of resources and lower operating costs. Through the use of the power collection and analysis module, the system can have an in-depth understanding of the flow direction and loss of power, so as to make improved decisions, involving system upgrades, equipment replacements, or adjustments to operating strategies to improve the performance of the entire system. Therefore, the power collection method of a distribution network of the present invention is an optimization process made on the traditional power collection method of the distribution network, which solves the problems of inaccurate detection of circuit abnormal points and inaccurate analysis of power performance loss in the traditional power collection method of the distribution network, improves the accuracy of circuit abnormal point detection, and improves the accuracy of power performance loss analysis.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: collecting electrical data of the distribution network to obtain electrical data of the distribution network; wherein the electrical data of the distribution network includes power transmission line data and power transformation node data;

[0012] Step S12: Based on the power transmission line data and the power transformation node data, electromagnetic field data of the distribution network transmission line and the transformer in operation are collected to obtain transmission electromagnetic data and electromagnetic transformation data respectively.

[0013] The present invention can monitor the operating status of the distribution network in real time through electrical data collection. This includes power transmission line data and power transformer node data, providing comprehensive electrical information for system operation. Through the collection of distribution network electrical data, the system can track the abnormalities of power transmission lines and transformer nodes, which helps to find potential faults early and make accurate diagnosis. Understanding the electrical data of power transmission lines and transformer nodes helps to optimize load management and ensure the efficient operation of the system under different load conditions. Through electromagnetic field data collection, the electromagnetic field of the distribution network transmission line and transformer in the operating state can be monitored. This helps to understand the actual working conditions of power equipment and prevent potential electromagnetic interference and failures. The collection of electromagnetic field data enables the system to perform electromagnetic compatibility analysis, ensure that electromagnetic interference between different devices is minimized, and improve the reliability and stability of the entire system. Through the analysis of electromagnetic field data, the health of power transmission lines and transformers can be monitored, and potential problems can be found early, thereby improving the maintainability and reliability of the system.

[0014] Preferably, step S2 comprises the following steps:

[0015] Step S21: performing time series analysis on the transmission electromagnetic data to obtain transmission electromagnetic time series data; performing three-dimensional surface graph conversion according to the transmission electromagnetic time series data to obtain a transmission electromagnetic three-dimensional surface graph;

[0016] Step S22: marking the characteristic surface of the transmission electromagnetic three-dimensional surface image to obtain the transmission electromagnetic characteristic surface; calculating the curvature of the transmission electromagnetic characteristic surface to obtain a characteristic curvature data set;

[0017] Step S23: Calculate the skewness of the characteristic curvature data set to obtain characteristic curvature skewness data;

[0018] Step S24: performing electromagnetic wave fault identification according to the transmitted electromagnetic characteristic surface and characteristic curvature skewness data to obtain electromagnetic wave fault data;

[0019] Step S25: using a preset electromagnetic anomaly recognition model to perform fluctuation anomaly recognition on the electromagnetic fluctuation fault data to obtain electromagnetic anomaly fluctuation report data.

[0020] Through time series analysis, the present invention can capture the time-related dynamic characteristics of the transmitted electromagnetic data, which is helpful for detecting transient events, periodic changes or instability in the power system, and provides more detailed time information. The conversion into a three-dimensional surface diagram can visualize the spatial distribution of the electromagnetic data, provide intuitive spatial information for subsequent analysis, and make it easier to identify and understand the overall shape and change trend of the electromagnetic field. Combining time series analysis and three-dimensional surface diagrams, the characteristics of the transmitted electromagnetic data can be fully understood in both time and space dimensions, which improves the recognition of key features in the electromagnetic data and helps to accurately locate potential problems in the power system. Curvature calculation can quantify the curvature of the characteristic surface and provide information about the rate of change of the electromagnetic field. Through curvature calculation, the system can more accurately describe the local characteristics of the electromagnetic field and lay the foundation for anomaly detection. The combination of characteristic surface marking and curvature calculation increases the in-depth understanding of the electromagnetic field structure and provides more powerful feature data for subsequent anomaly identification. Skewness calculation can quantify the skewness of the characteristic curvature data set and provides information about the shape of the characteristic curvature distribution, which helps to identify specific electromagnetic fields. The non-uniformity of the characteristics indicates potential problems in the electromagnetic field. The characteristic curvature skewness data provides additional statistical information for the subsequent electromagnetic fluctuation fault identification, enhancing the comprehensive understanding of the electromagnetic field characteristics. Based on the characteristic surface and characteristic curvature skewness data, the system can identify the fluctuation fault in the electromagnetic field, that is, the local or global electromagnetic anomaly area, which improves the accurate perception of electromagnetic field changes and makes the system more sensitive to anomalies. The electromagnetic fluctuation fault data provides a qualitative and quantitative description of sudden anomalies or atypical patterns in the electromagnetic field, which helps to more accurately identify potential problems in the power system. Using the preset electromagnetic anomaly recognition model, the system can conduct a deeper analysis of the electromagnetic fluctuation fault data based on experience or previous training data, improve the automatic recognition and classification capabilities of electromagnetic anomalies, and reduce the risk of misjudgment. Through fluctuation anomaly recognition, the system can screen out truly important electromagnetic anomalies, reduce the false alarm burden on operators, and generate electromagnetic abnormal fluctuation report data, which contains the identified abnormal information, providing a clear and practical reference for operation and maintenance personnel, and facilitating rapid response and problem solving.

[0021] Preferably, step S24 comprises the following steps:

[0022] Step S241: performing contour drawing according to the transmission electromagnetic characteristic surface and characteristic curvature skewness data to obtain the electromagnetic contour surface;

[0023] Step S242: performing contour interpolation calculation on the electromagnetic contour surface to obtain electromagnetic contour interpolation data;

[0024] Step S243: performing contour deformation analysis on the electromagnetic contour surface according to the electromagnetic contour interpolation data to obtain contour deformation data;

[0025] Step S244: performing contour deformation interval calculation on the contour deformation data to obtain contour deformation interval data; performing dynamic evolution process analysis on the contour deformation interval data to obtain contour dynamic evolution data;

[0026] Step S245: performing multi-scale evolution correlation analysis according to the contour line dynamic evolution data and the contour line deformation interval data to obtain multi-scale evolution correlation data;

[0027] Step S246: Perform electromagnetic wave fault identification based on the multi-scale evolution correlation data and the contour line deformation interval data to obtain electromagnetic wave fault data.

[0028] The present invention can more clearly display the distribution of the electromagnetic field by drawing contour lines based on the transmission electromagnetic characteristic surface and characteristic curvature skewness data, provide spatial visualization of the change in electromagnetic field intensity, and help to understand the characteristics of the electromagnetic field as a whole. By interpolating the electromagnetic contour line surface, more precise electromagnetic contour line interpolation data can be obtained to fill the blank areas between sampling points, thereby improving the spatial resolution of electromagnetic field changes and enabling the system to better capture subtle features and anomalies. By performing deformation analysis on the electromagnetic contour line surface, the system can detect deformation phenomena occurring in the electromagnetic field, namely the existence of abnormal changes or fluctuating faults, providing detailed insights into local changes in the electromagnetic field and helping to more accurately locate abnormal areas. By calculating the contour line deformation intervals, the system can quantify different electromagnetic fields. The deformation degree of the region provides a quantitative indicator of the degree of anomaly, which helps to identify the areas with the most significant changes in the electromagnetic field and guide the subsequent dynamic evolution process analysis. The dynamic evolution process analysis combined with the contour deformation interval data provides detailed data support for understanding the trend of electromagnetic field changes and the evolution process of anomalies. Multi-scale evolution correlation analysis using contour dynamic evolution data and contour deformation interval data can identify the evolution correlation relationship of electromagnetic fields at different scales, provide a multi-angle interpretation of electromagnetic field changes, and help to more comprehensively understand the formation and propagation of anomalies. By integrating multi-scale evolution correlation data, the system can more accurately identify electromagnetic fluctuation faults, that is, the key areas of abnormal changes, provide accurate positioning of fluctuation faults in the electromagnetic field, and provide strong support for subsequent problem positioning and processing.

[0029] Preferably, step S3 comprises the following steps:

[0030] Step S31: calculating the abnormal voltage fluctuation interval of the electromagnetic abnormal fluctuation report data to obtain abnormal voltage interval data;

[0031] Step S32: evaluating the impact hysteresis of the electromagnetic transformation data according to the abnormal voltage interval data to obtain abnormal voltage impact delay data;

[0032] Step S33: analyzing the electromagnetic voltage transformation data for impact effects according to the abnormal voltage interval data and the abnormal voltage impact delay data to obtain electromagnetic voltage transformation impact effect data;

[0033] Step S34: performing performance loss analysis on the distribution network transformer according to the electromagnetic transformer influence effect data to obtain transformer performance loss data.

[0034] By calculating the electromagnetic abnormal fluctuation report data, the present invention can accurately determine the fluctuation range of abnormal voltage, provide the time and space range of abnormal voltage fluctuation, help to quickly locate the occurrence area of ​​abnormal voltage, and improve the sensitivity to electromagnetic field abnormalities. By evaluating the abnormal voltage interval data, the system can analyze the hysteresis of the impact of abnormal voltage on electromagnetic transformation data, that is, the response delay caused by abnormal voltage, provide an understanding of the dynamic response characteristics of electromagnetic field abnormalities, and help understand the timing relationship between voltage fluctuations and electromagnetic field changes. By integrating the abnormal voltage interval data and the impact delay data, the system can deeply analyze the impact effect of electromagnetic transformation data, that is, the specific impact mechanism of abnormal voltage on electromagnetic transformation data, provide a detailed understanding of the electromagnetic field changes caused by abnormal voltage, and provide a basis for further problem location and resolution. By performing performance loss analysis on distribution network transformers according to electromagnetic transformation impact effect data, the system can evaluate the actual impact of electromagnetic anomalies on equipment performance, provide a quantitative analysis of transformer performance loss, and provide a scientific basis for equipment maintenance and replacement decisions.

[0035] Preferably, step S33 includes the following steps:

[0036] Step S331: evaluating the voltage drop amplitude on the abnormal voltage interval data to obtain voltage drop amplitude data; performing drop cycle analysis on the voltage drop amplitude data to obtain voltage drop cycle data;

[0037] Step S332: extracting the peak voltage of the abnormal voltage interval data according to the voltage drop cycle data to obtain abnormal peak voltage data; performing time distribution characteristic analysis on the abnormal peak voltage data to obtain abnormal peak voltage time distribution data;

[0038] Step S333: calculating the peak voltage dispersion degree of the abnormal peak voltage time distribution data to obtain abnormal peak voltage dispersion data;

[0039] Step S334: Calculate the potential risk level according to the abnormal peak voltage discrete data and the voltage drop cycle data to obtain abnormal voltage potential risk data;

[0040] Step S335: analyzing the electromagnetic transformation data for impact effects according to the abnormal voltage potential risk data and the abnormal voltage impact delay data to obtain electromagnetic transformation impact effect data.

[0041] By evaluating the voltage drop amplitude of the abnormal voltage interval data, the present invention can quantify the amplitude change of the abnormal voltage and provide the specific value of the voltage fluctuation, which is helpful to describe the characteristics of the abnormal voltage more accurately. By performing periodic analysis on the voltage drop amplitude data, the system can obtain the periodic information of the voltage fluctuation, that is, the repetitive occurrence pattern of the voltage fluctuation, which is helpful to understand the time characteristics of the voltage fluctuation and provides a time series basis for subsequent analysis. By extracting the peak voltage of the abnormal voltage interval according to the voltage drop periodic data, the system can capture the maximum amplitude of the abnormal voltage and provide the peak information of the abnormal voltage, which is helpful to identify the extreme situation in the voltage fluctuation and provides key data for subsequent analysis. By performing time distribution feature analysis on the abnormal peak voltage data, the system can deeply understand the time distribution pattern of the abnormal voltage, including the appearance time and duration of the peak, and provides a basis for the analysis of the abnormal voltage. A detailed understanding of the voltage timing characteristics helps to identify the critical moments of voltage fluctuations. The system calculates the peak voltage discreteness of the abnormal peak voltage time distribution data, and can quantify the fluctuation degree of the abnormal voltage, providing discrete information of the abnormal voltage fluctuation, which helps to judge the stability and predictability of the voltage fluctuation. The system calculates the potential risk level based on the abnormal peak voltage discrete data and the voltage drop period data, and can quantify the potential threat of abnormal voltage to system stability, providing an overall risk assessment of the impact of abnormal voltage, which helps to prioritize areas with potentially higher risks. The system analyzes the impact effects of electromagnetic transformation data based on the abnormal voltage potential risk data and the abnormal voltage impact delay data. The system can comprehensively consider the amplitude, period, peak characteristics and potential risks of voltage fluctuations, provide a comprehensive understanding of electromagnetic field anomalies, and help to more accurately predict the impact of electromagnetic field changes on the system.

[0042] Preferably, the potential risk degree is calculated based on the abnormal peak voltage discrete data and the voltage drop period data by using an abnormal voltage potential risk algorithm, wherein the abnormal voltage potential risk algorithm is as follows:

[0043]

[0044] Among them, y represents the result value of the potential risk degree of abnormal voltage, n represents the abnormal voltage value, x represents the amplitude coefficient of abnormal voltage, a represents the interval value of abnormal voltage, b represents the peak voltage dispersion, θ represents the abnormal voltage fluctuation frequency, t represents the time interval of threat calculation, c represents the voltage drop cycle stability coefficient, d represents the voltage drop average value, and R represents the error correction value of the abnormal voltage potential risk algorithm.

[0045] The present invention constructs an abnormal voltage potential risk algorithm, which fully considers the abnormal voltage value n, and a higher abnormal voltage value will increase the potential risk degree; the abnormal voltage amplitude coefficient x adjusts the amplitude of the abnormal voltage value, and a higher amplitude coefficient will increase the potential risk degree; the abnormal voltage interval value a represents the range of the abnormal voltage, and a larger interval value indicates that the voltage fluctuation is large, and insufficient stability increases the potential risk degree; the peak voltage dispersion b represents the dispersion degree of the peak voltage, and a higher dispersion degree will increase the potential risk degree; the abnormal voltage fluctuation frequency θ represents the fluctuation frequency of the abnormal voltage, and a higher frequency will increase the potential risk degree; the time interval t of threat calculation represents the time range for threat calculation, and a longer time interval indicates that the voltage is more complex and will increase the potential risk degree; the voltage drop cycle stability coefficient c adjusts the stability of the voltage drop cycle, and a higher stability coefficient will reduce the potential risk degree; the voltage drop average value d represents the average value of the voltage drop, and a higher average value will increase the potential risk degree; the error correction value R of the abnormal voltage potential risk algorithm is used to perform error correction on the result, so that the risk result obtained is more accurate.

[0046] Preferably, step S34 includes the following steps:

[0047] Step S341: Calculate transformer winding current according to electromagnetic transformer influence effect data to obtain transformer winding current data;

[0048] Step S342: performing electromagnetic field distribution simulation according to transformer winding current data and electromagnetic transformation effect data to obtain electromagnetic field simulation distribution data; performing magnetic coupling effect analysis on the electromagnetic field simulation distribution data to obtain electromagnetic field coupling effect data;

[0049] Step S343: Calculate the magnetic flux density based on the electromagnetic field coupling effect data to obtain the electromagnetic field magnetic flux density data; calculate the magnetic field force based on the electromagnetic field magnetic flux density data to obtain the magnetic field force data;

[0050] Step S344: evaluating the operating state vibration frequency of the distribution network transformer according to the electromagnetic transformer influence effect data to obtain vibration frequency evaluation data; performing mechanical resonance simulation based on the vibration frequency evaluation data and the magnetic field force data to obtain mechanical resonance simulation data;

[0051] Step S345: performing density continuity analysis on the electromagnetic field magnetic flux density data to obtain magnetic flux density continuous data; performing magnetic flux density saturation evaluation based on the magnetic flux density continuous data to obtain magnetic flux density saturation data;

[0052] Step S346: Calculate harmonic intensity according to the magnetic flux density saturation data, the electromagnetic field coupling effect data, and the transformer winding current data to obtain harmonic intensity data;

[0053] Step S347: Perform performance loss analysis on the distribution network transformer according to the mechanical resonance simulation data and the harmonic intensity data to obtain transformer performance loss data.

[0054] The present invention can more accurately understand the current distribution inside the transformer by calculating the winding current according to the electromagnetic transformer influence effect data, which is crucial for evaluating the electromagnetic performance of the transformer and helps to detect potential current anomalies or overload conditions. Through electromagnetic field simulation and magnetic coupling effect analysis, the electromagnetic field distribution data inside the transformer can be obtained, which helps to understand the complexity of the electromagnetic field, detect potential coupling effects, and provide information for improving electromagnetic design. By calculating the magnetic flux density and magnetic field force, the magnetic properties of the transformer under different working conditions can be evaluated. This helps to detect potential magnetic field problems, such as saturation or excessive magnetic field force, thereby improving the reliability of the transformer. By evaluating the vibration frequency of the operating state and performing mechanical resonance simulation, problems that cause mechanical resonance can be detected. This helps to prevent damage to the equipment caused by vibration and improve the life of the transformer. The continuity analysis of the electromagnetic field magnetic flux density and the evaluation of the saturation of the magnetic flux density can help determine the magnetic performance of the transformer under different working conditions. This helps to avoid the influence of abnormal magnetic flux density on the performance of the transformer. By calculating the harmonic intensity, the harmonic response of the transformer in the power grid can be evaluated. This helps detect potential harmonic problems and improve the equipment's tolerance to harmonics. Through comprehensive analysis of mechanical resonance simulation data and harmonic intensity data, the performance loss of the transformer can be evaluated. This helps prevent potential performance problems and take necessary maintenance and improvement measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] FIG1 is a schematic flow chart of the steps of a method for collecting electric energy in a distribution network;

[0056] FIG2 is a schematic diagram of a detailed implementation process of step S2 in FIG1 ;

[0057] FIG3 is a schematic diagram of a detailed implementation process of step S24 in FIG2 ;

[0058] 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

[0059] The following is a clear and complete description of the technical method of the present invention 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.

[0060] 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.

[0061] 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 unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0062] To achieve the above object, please refer to Figures 1 to 3, a method for collecting electric energy from a distribution network, the method comprising the following steps:

[0063] Step S1: Collect electrical data of the distribution network to obtain electrical data of the distribution network; collect electromagnetic field data of the distribution network transmission lines and transformers in operation based on the electrical data of the distribution network to obtain transmission electromagnetic data and electromagnetic transformation data respectively;

[0064] Step S2: performing three-dimensional surface map conversion according to the transmission electromagnetic data to obtain a transmission electromagnetic three-dimensional surface map; performing electromagnetic wave fault identification according to the transmission electromagnetic three-dimensional surface map to obtain electromagnetic wave fault data; performing fluctuation anomaly identification on the electromagnetic wave fault data to obtain electromagnetic abnormal fluctuation report data;

[0065] Step S3: Calculate the abnormal voltage fluctuation interval of the electromagnetic abnormal fluctuation report data to obtain abnormal voltage interval data; analyze the impact effect of the electromagnetic transformation data according to the abnormal voltage interval data to obtain electromagnetic transformation impact effect data; analyze the performance loss of the distribution network transformer according to the electromagnetic transformation impact effect data to obtain transformer performance loss data;

[0066] Step S4: Design an automated electromagnetic anomaly analysis model based on the electromagnetic anomaly fluctuation report data to obtain an automated electromagnetic analysis module; design power loss compensation for the automated electromagnetic analysis module to obtain an automated power collection and analysis module.

[0067] In the embodiment of the present invention, referring to FIG. 1 , a schematic flow chart of a method for collecting electric energy in a distribution network of the present invention is shown. In this example, the method for collecting electric energy in a distribution network includes the following steps:

[0068] Step S1: Collect electrical data of the distribution network to obtain electrical data of the distribution network; collect electromagnetic field data of the distribution network transmission lines and transformers in operation based on the electrical data of the distribution network to obtain transmission electromagnetic data and electromagnetic transformation data respectively;

[0069] In the embodiment of the present invention, dedicated data acquisition equipment, such as current sensors, voltage sensors, and power meters, are installed on key nodes and key equipment of the distribution network. According to a predetermined acquisition plan and schedule, the data acquisition equipment is started to collect electrical data in real time or at a fixed time, and data is collected from each installed sensor and meter. These data include but are not limited to current value, voltage value, power factor, and power consumption. Real-time or historical data is transmitted to a central data processing system or database through wired or wireless communication. Electromagnetic field sensors are installed on transmission lines and transformers in the distribution network. These sensors can measure and record various parameters of the electromagnetic field, such as magnetic induction intensity, electric field intensity, and frequency. Under different operating conditions, electromagnetic field data is collected continuously or at a fixed time.

[0070] Step S2: performing three-dimensional surface map conversion according to the transmission electromagnetic data to obtain a transmission electromagnetic three-dimensional surface map; performing electromagnetic wave fault identification according to the transmission electromagnetic three-dimensional surface map to obtain electromagnetic wave fault data; performing fluctuation anomaly identification on the electromagnetic wave fault data to obtain electromagnetic abnormal fluctuation report data;

[0071] In an embodiment of the present invention, mathematical modeling technology or data processing software is used to convert the transmission electromagnetic data into a three-dimensional surface graph, and the electromagnetic field data is converted into a visualized three-dimensional surface graph, so as to intuitively display the electromagnetic field distribution. The transmission electromagnetic three-dimensional surface graph is analyzed and processed, and an algorithm or technology is used to identify the electromagnetic fluctuation fault, including image processing, signal processing or pattern recognition-based technology to identify the area with abnormal fluctuations in the electromagnetic field. Based on the identified electromagnetic fluctuation faults, more in-depth abnormality identification work is carried out to detect and analyze abnormal fluctuation patterns. Statistical methods, machine learning techniques or pattern recognition algorithms in professional fields are used to identify and distinguish abnormal fluctuation patterns.

[0072] Step S3: Calculate the abnormal voltage fluctuation interval of the electromagnetic abnormal fluctuation report data to obtain abnormal voltage interval data; analyze the impact effect of the electromagnetic transformation data according to the abnormal voltage interval data to obtain electromagnetic transformation impact effect data; analyze the performance loss of the distribution network transformer according to the electromagnetic transformation impact effect data to obtain transformer performance loss data;

[0073] In an embodiment of the present invention, the abnormal fluctuation information in the electromagnetic abnormal fluctuation report data is used to calculate the time interval of the abnormal voltage fluctuation, and the start time and end time of the abnormal voltage fluctuation are determined by using time series analysis or other suitable methods to obtain the abnormal voltage fluctuation interval. Within the abnormal voltage fluctuation interval, the electromagnetic transformer data is subjected to a detailed impact effect analysis, and the impact of the electromagnetic field change on the transformer is considered. The fluctuation of parameters such as current, voltage, and power is analyzed to understand the specific impact of the electromagnetic field abnormality on the voltage. The impact effect data corresponding to the abnormal voltage fluctuation interval is extracted from the electromagnetic transformer data. The impact effect data may include current fluctuation amplitude, voltage distortion, and power factor change index, which are used to quantify the impact of abnormal electromagnetic fluctuations on the performance of the electromagnetic transformer. The electromagnetic transformer impact effect data is used to perform a performance loss analysis on the transformer in the distribution network. The rated parameters of the transformer are considered to analyze the impact of abnormal electromagnetic fluctuations on the loss, efficiency, and temperature performance indicators of the transformer. The power system simulation software or other engineering analysis tools are used to simulate the actual impact of the abnormal electromagnetic field on the transformer. The results of the performance loss analysis are integrated to generate a transformer performance loss data report caused by electromagnetic abnormal fluctuations, including specific numerical changes in performance indicators and potential impact information of abnormal electromagnetic fluctuations on the life of the transformer.

[0074] Step S4: Design an automated electromagnetic anomaly analysis model based on the electromagnetic anomaly fluctuation report data to obtain an automated electromagnetic analysis module; design power loss compensation for the automated electromagnetic analysis module to obtain an automated power collection and analysis module.

[0075] In the embodiment of the present invention, electromagnetic abnormal fluctuation report data is collected and prepared, including the time series, frequency, and amplitude of abnormal fluctuations, and the functions and requirements of the automated electromagnetic abnormal analysis module are determined. Considering the depth, frequency, and degree of automation of the analysis, a suitable algorithm model is selected or a customized algorithm is developed to process abnormal electromagnetic fluctuation data, so as to automatically detect, identify, and analyze abnormal patterns. According to the characteristics of the actual data, the model parameters are set to ensure that the model can accurately and efficiently identify and analyze electromagnetic abnormal patterns. Considering the impact of abnormal electromagnetic fluctuations on the loss of electric energy, it is used to compensate or correct the electric energy loss caused by abnormal electromagnetic fluctuations to restore or optimize the system's electric energy transmission efficiency. The designed compensation method is verified and adjusted to ensure its robustness and effectiveness under different circumstances. The results of the electromagnetic abnormal analysis module and the electric energy loss compensation design are integrated. An automated electric energy collection and analysis module is developed or built, integrating the electromagnetic abnormal analysis and electric energy loss compensation functions. The integrated module is tested to verify whether its functions meet expectations, and necessary optimization and adjustment are performed according to the test results.

[0076] The present invention can obtain the electrical parameters of each transmission line and transformer of the distribution network through electrical data collection, provide comprehensive operating status information, and can obtain the electrical parameters of current, voltage, and power factor of each key point, which provides basic data for comprehensive monitoring of the system operating status and helps to understand the actual working conditions of the power system. By collecting electromagnetic field data of the transmission line based on electrical data, transmission electromagnetic data is obtained, which helps to understand the strength and distribution of the electromagnetic field on the transmission line and on the transformer; by converting the transmission electromagnetic data into a three-dimensional surface diagram, an intuitive visual representation of the electromagnetic field is provided. This visual presentation helps engineers and researchers quickly understand the distribution and characteristics of the electromagnetic field. On the basis of the transmission electromagnetic three-dimensional surface diagram On the electromagnetic fluctuation fault identification, these faults may represent abnormal or mutation areas of the electromagnetic field, which are related to potential faults or irregular operations. The electromagnetic fluctuation fault data is further analyzed and processed to generate electromagnetic abnormal fluctuation report data. These reports provide a detailed description of abnormal electromagnetic behavior, including location, intensity and duration. The electromagnetic fluctuation fault data is used to identify fluctuation anomalies, which helps to capture possible electromagnetic abnormal events in the system. The generated electromagnetic abnormal fluctuation report data provides decision makers with important information about the health of the electromagnetic environment. These data can be used to optimize operation strategies, formulate preventive maintenance plans and make system improvements; by analyzing the electromagnetic abnormal fluctuation report data, the interval of abnormal voltage fluctuation is calculated. This helps to determine the period and range of abnormal voltage, provides a temporal and spatial context for further analysis, and analyzes the impact effect of electromagnetic transformer data. This includes the impact of electromagnetic field anomalies on transformer performance, involving electromagnetic induction and hysteresis factors. This analysis provides the specific impact mechanism of abnormal electromagnetic fields on transformers, and performs performance loss analysis on transformers in distribution networks, including the impact on rated capacity loss, temperature rise, and energy efficiency reduction of transformers. Performance loss analysis helps to evaluate the health status and performance degradation of transformers, and generate detailed transformer performance loss data, which includes transformer losses, temperature rise, and rated capacity reduction. By understanding the actual impact of electromagnetic anomalies on transformer performance, preventive maintenance plans can be formulated to avoid potential equipment failures and system interruptions. In addition, operational strategies can be optimized based on performance loss data to maximize the normal operation of equipment. Through the automated electromagnetic anomaly analysis mode, the system can intelligently process a large amount of electromagnetic anomaly fluctuation report data, including automatic identification of abnormal patterns, extraction of key features, and establishment of electromagnetic anomaly models. The automation module can monitor electromagnetic anomalies in real time to make the system more responsive.This helps to discover potential problems early, reduces dependence on manual intervention, and improves the automation level of the system. Based on the design of the electromagnetic anomaly analysis mode, the system can more accurately predict potential electromagnetic anomalies, help take preventive maintenance measures, and reduce system downtime. Through the design of the power loss compensation of the automated electromagnetic analysis module, the system can reduce power loss and improve the overall efficiency of the system, which is particularly important for the power supply system, because the improvement of energy efficiency means less waste of resources and lower operating costs. Through the use of the power collection and analysis module, the system can have an in-depth understanding of the flow direction and loss of power, so as to make improved decisions, involving system upgrades, equipment replacements, or adjustments to operating strategies to improve the performance of the entire system. Therefore, the power collection method of a distribution network of the present invention is an optimization process made on the traditional power collection method of the distribution network, which solves the problems of inaccurate detection of circuit abnormal points and inaccurate analysis of power performance loss in the traditional power collection method of the distribution network, improves the accuracy of circuit abnormal point detection, and improves the accuracy of power performance loss analysis.

[0077] Preferably, step S1 comprises the following steps:

[0078] Step S11: collecting electrical data of the distribution network to obtain electrical data of the distribution network; wherein the electrical data of the distribution network includes power transmission line data and power transformation node data;

[0079] Step S12: Based on the power transmission line data and the power transformation node data, electromagnetic field data of the distribution network transmission line and the transformer in operation are collected to obtain transmission electromagnetic data and electromagnetic transformation data respectively.

[0080] In an embodiment of the present invention, a collection plan is formulated, the time, location and frequency of data collection are determined, information related to the transmission line is collected, such as line topology, length, material, current load, electrical parameters of the transmission line, such as voltage, current, frequency, are measured or obtained, the location and type of the transformer are determined, and the parameters of the transformer, such as rated power, transformation ratio, current, are measured or obtained. Suitable sensors or measuring equipment are used. In the operating state, electromagnetic field data are collected for the transmission line of the distribution network using an electromagnetic field sensor or measuring equipment, the electromagnetic field strength and frequency on the transmission line are measured, and electromagnetic field data are collected for the transformer and its surrounding environment. The electromagnetic field strength and frequency of the transformer in the operating state are recorded, a database or file system is established, and the collected data is organized and stored according to factors such as type and time for subsequent analysis and use.

[0081] The present invention can monitor the operating status of the distribution network in real time through electrical data collection. This includes power transmission line data and power transformer node data, providing comprehensive electrical information for system operation. Through the collection of distribution network electrical data, the system can track the abnormalities of power transmission lines and transformer nodes, which helps to find potential faults early and make accurate diagnosis. Understanding the electrical data of power transmission lines and transformer nodes helps to optimize load management and ensure the efficient operation of the system under different load conditions. Through electromagnetic field data collection, the electromagnetic field of the distribution network transmission line and transformer in the operating state can be monitored. This helps to understand the actual working conditions of power equipment and prevent potential electromagnetic interference and failures. The collection of electromagnetic field data enables the system to perform electromagnetic compatibility analysis, ensure that electromagnetic interference between different devices is minimized, and improve the reliability and stability of the entire system. Through the analysis of electromagnetic field data, the health of power transmission lines and transformers can be monitored, and potential problems can be found early, thereby improving the maintainability and reliability of the system.

[0082] Preferably, step S2 comprises the following steps:

[0083] Step S21: performing time series analysis on the transmission electromagnetic data to obtain transmission electromagnetic time series data; performing three-dimensional surface graph conversion according to the transmission electromagnetic time series data to obtain a transmission electromagnetic three-dimensional surface graph;

[0084] Step S22: marking the characteristic surface of the transmission electromagnetic three-dimensional surface image to obtain the transmission electromagnetic characteristic surface; calculating the curvature of the transmission electromagnetic characteristic surface to obtain a characteristic curvature data set;

[0085] Step S23: Calculate the skewness of the characteristic curvature data set to obtain characteristic curvature skewness data;

[0086] Step S24: performing electromagnetic wave fault identification according to the transmitted electromagnetic characteristic surface and characteristic curvature skewness data to obtain electromagnetic wave fault data;

[0087] Step S25: using a preset electromagnetic anomaly recognition model to perform fluctuation anomaly recognition on the electromagnetic fluctuation fault data to obtain electromagnetic anomaly fluctuation report data.

[0088] As an example of the present invention, referring to FIG. 2 , in this example, step S2 includes:

[0089] Step S21: performing time series analysis on the transmission electromagnetic data to obtain transmission electromagnetic time series data; performing three-dimensional surface graph conversion according to the transmission electromagnetic time series data to obtain a transmission electromagnetic three-dimensional surface graph;

[0090] In an embodiment of the present invention, electromagnetic data is prepared for transmission to ensure data quality and integrity. Time series analysis techniques, such as sliding windows and Fourier transforms, are used to analyze the transmitted electromagnetic data to identify periodicity and trends in the data. The time series data is converted into a three-dimensional surface graph, and mathematical modeling or data visualization techniques are required to map the time series data into a three-dimensional space.

[0091] Step S22: marking the characteristic surface of the transmission electromagnetic three-dimensional surface image to obtain the transmission electromagnetic characteristic surface; calculating the curvature of the transmission electromagnetic characteristic surface to obtain a characteristic curvature data set;

[0092] In an embodiment of the present invention, surfaces with special significance or importance are identified and extracted from the conveying electromagnetic three-dimensional surface map, including spit-out surfaces, surfaces with large curvature, and surfaces with high density. Each characteristic surface is marked and distinguished, which may involve identifying and marking the edge, shape, and inflection point features of the surface for subsequent analysis and calculation. For each marked characteristic surface, its curvature is calculated using a mathematical method, and the data obtained from the curvature calculation is recorded and organized to generate a characteristic curvature data set, which includes the curvature values ​​of different parts of the surface and the changing trend of the curvature.

[0093] Step S23: Calculate the skewness of the characteristic curvature data set to obtain characteristic curvature skewness data;

[0094] In an embodiment of the present invention, for each characteristic curvature data set, its skewness is calculated. Skewness is a statistic that describes the data distribution pattern and reflects the degree of asymmetry of the data distribution relative to the mean value. The skewness calculation can use a standard mathematical formula involving the mean value, standard deviation and data volume of the data set.

[0095] Step S24: performing electromagnetic wave fault identification according to the transmitted electromagnetic characteristic surface and characteristic curvature skewness data to obtain electromagnetic wave fault data;

[0096] In an embodiment of the present invention, the transmission electromagnetic characteristic surface data of step S22 and the characteristic curvature skewness data of step S23 are used as input, and the characteristic curvature skewness data and the transmission electromagnetic characteristic surface data are combined to determine the corresponding association rules or models to identify possible electromagnetic fluctuation faults. Considering the relationship between the characteristic surface and the curvature skewness, the transmission electromagnetic characteristic surface is analyzed and identified to determine the electromagnetic fluctuation faults that may exist therein.

[0097] Step S25: using a preset electromagnetic anomaly recognition model to perform fluctuation anomaly recognition on the electromagnetic fluctuation fault data to obtain electromagnetic anomaly fluctuation report data.

[0098] In an embodiment of the present invention, historical geomagnetic anomaly data is obtained, and a preset electromagnetic anomaly recognition model is established based on machine learning, deep learning or other related technologies. The model is trained using labeled electromagnetic anomaly data during the training phase to learn the patterns and characteristics of electromagnetic anomalies. The electromagnetic fluctuation fault data is input into the preset electromagnetic anomaly recognition model, and based on the model output, electromagnetic anomaly fluctuation report data is generated, including the location, intensity, and duration information of the anomaly, as well as the model's confidence in the anomaly or other related indicators. The anomaly data is classified according to its characteristics for further analysis and processing. The classification includes different types of electromagnetic anomalies, such as voltage anomalies and current anomalies. The electromagnetic anomaly fluctuation report data is output, which can be in file format or database record.

[0099] Through time series analysis, the present invention can capture the time-related dynamic characteristics of the transmitted electromagnetic data, which is helpful for detecting transient events, periodic changes or instability in the power system, and provides more detailed time information. The conversion into a three-dimensional surface diagram can visualize the spatial distribution of the electromagnetic data, provide intuitive spatial information for subsequent analysis, and make it easier to identify and understand the overall shape and change trend of the electromagnetic field. Combining time series analysis and three-dimensional surface diagrams, the characteristics of the transmitted electromagnetic data can be fully understood in both time and space dimensions, which improves the recognition of key features in the electromagnetic data and helps to accurately locate potential problems in the power system. Curvature calculation can quantify the curvature of the characteristic surface and provide information about the rate of change of the electromagnetic field. Through curvature calculation, the system can more accurately describe the local characteristics of the electromagnetic field and lay the foundation for anomaly detection. The combination of characteristic surface marking and curvature calculation increases the in-depth understanding of the electromagnetic field structure and provides more powerful feature data for subsequent anomaly identification. Skewness calculation can quantify the skewness of the characteristic curvature data set and provides information about the shape of the characteristic curvature distribution, which helps to identify specific electromagnetic fields. The non-uniformity of the characteristics indicates potential problems in the electromagnetic field. The characteristic curvature skewness data provides additional statistical information for the subsequent electromagnetic fluctuation fault identification, enhancing the comprehensive understanding of the electromagnetic field characteristics. Based on the characteristic surface and characteristic curvature skewness data, the system can identify the fluctuation fault in the electromagnetic field, that is, the local or global electromagnetic anomaly area, which improves the accurate perception of electromagnetic field changes and makes the system more sensitive to anomalies. The electromagnetic fluctuation fault data provides a qualitative and quantitative description of sudden anomalies or atypical patterns in the electromagnetic field, which helps to more accurately identify potential problems in the power system. Using the preset electromagnetic anomaly recognition model, the system can conduct a deeper analysis of the electromagnetic fluctuation fault data based on experience or previous training data, improve the automatic recognition and classification capabilities of electromagnetic anomalies, and reduce the risk of misjudgment. Through fluctuation anomaly recognition, the system can screen out truly important electromagnetic anomalies, reduce the false alarm burden on operators, and generate electromagnetic abnormal fluctuation report data, which contains the identified abnormal information, providing a clear and practical reference for operation and maintenance personnel, and facilitating rapid response and problem solving.

[0100] Preferably, step S24 comprises the following steps:

[0101] Step S241: performing contour drawing according to the transmission electromagnetic characteristic surface and characteristic curvature skewness data to obtain the electromagnetic contour surface;

[0102] Step S242: performing contour interpolation calculation on the electromagnetic contour surface to obtain electromagnetic contour interpolation data;

[0103] Step S243: performing contour deformation analysis on the electromagnetic contour surface according to the electromagnetic contour interpolation data to obtain contour deformation data;

[0104] Step S244: performing contour deformation interval calculation on the contour deformation data to obtain contour deformation interval data; performing dynamic evolution process analysis on the contour deformation interval data to obtain contour dynamic evolution data;

[0105] Step S245: performing multi-scale evolution correlation analysis according to the contour line dynamic evolution data and the contour line deformation interval data to obtain multi-scale evolution correlation data;

[0106] Step S246: Perform electromagnetic wave fault identification based on the multi-scale evolution correlation data and the contour line deformation interval data to obtain electromagnetic wave fault data.

[0107] As an example of the present invention, referring to FIG. 3 , in this example, step S24 includes:

[0108] Step S241: performing contour drawing according to the transmission electromagnetic characteristic surface and characteristic curvature skewness data to obtain the electromagnetic contour surface;

[0109] In the embodiment of the present invention, the transmission electromagnetic characteristic surface data of step S22 and the characteristic curvature skewness data of step S23 are used as input, and the contour line surface is drawn according to the numerical data of the transmission electromagnetic characteristic surface. It can be implemented using professional data visualization tools or corresponding libraries in programming languages. Considering the characteristic curvature skewness data, different contour lines can be drawn according to different skewness values ​​to highlight abnormal areas on the surface.

[0110] Step S242: performing contour interpolation calculation on the electromagnetic contour surface to obtain electromagnetic contour interpolation data;

[0111] In an embodiment of the present invention, an appropriate interpolation method is selected, such as linear interpolation and cubic spline interpolation. The selected interpolation method should be able to accurately reflect the changing trend of the contour surface, and interpolate the data on the electromagnetic contour surface to fill the gaps between the data points and obtain a more continuous and smooth curve. The accuracy and efficiency of the interpolation calculation depend on the selected interpolation method and calculation algorithm to generate electromagnetic contour interpolation data after interpolation calculation. These data can be data points evenly distributed on the surface, or they can be density adjusted as needed. Using the interpolated data, the electromagnetic contour interpolation surface is drawn. Ensure that the drawing results can clearly show the distribution and changes of the electromagnetic characteristic surface.

[0112] Step S243: performing contour deformation analysis on the electromagnetic contour surface according to the electromagnetic contour interpolation data to obtain contour deformation data;

[0113] In the embodiment of the present invention, the electromagnetic contour line interpolation data obtained in step S242 is used as input to perform deformation analysis on the electromagnetic contour line surface in order to understand the morphological changes of the contour lines in space, and to calculate and analyze parameters such as the distance, angle, and curvature between different points on the surface to explore the deformation on the surface. Mathematical or geometric methods can be used to analyze the characteristics of the surface deformation and record the deformation data.

[0114] Step S244: performing contour deformation interval calculation on the contour deformation data to obtain contour deformation interval data; performing dynamic evolution process analysis on the contour deformation interval data to obtain contour dynamic evolution data;

[0115] In an embodiment of the present invention, based on the contour deformation data, the deformation interval between each part of the contour is calculated. This can be a distance, curvature or any other measure that describes the degree of deformation. The deformation interval calculation can involve pairing the points of different contours on the surface, and then calculating the amount of change between them. The deformation interval data is used to analyze the dynamic evolution of the contour deformation. This may involve processing time series data or comparing different states. The changing trend and rate of the contour deformation, as well as the appearance or disappearance of abnormal deformation points can be observed. Visualization tools or animations can be used to display the dynamic evolution of the contour deformation, so as to more intuitively understand the characteristics and trends of the deformation.

[0116] Step S245: performing multi-scale evolution correlation analysis according to the contour line dynamic evolution data and the contour line deformation interval data to obtain multi-scale evolution correlation data;

[0117] In an embodiment of the present invention, the window size for multi-scale analysis is determined. Different sizes of windows can be tried to capture the evolutionary correlation at different scales, ensuring that the window size can capture subtle changes and extract overall evolutionary features at a larger scale. The window is applied to contour line dynamic evolution data and contour line deformation interval data, and correlation analysis is performed on the data in each window. A suitable correlation analysis method, such as cross-correlation analysis or other correlation metrics, is used to calculate the correlation between the data in the current window, and the window size is iteratively adjusted to repeat the steps at different scales to obtain multi-scale evolutionary correlation data. A step-by-step increase or decrease method can be used to carefully explore the correlation at different scales, integrate the correlation data obtained at each scale, and generate multi-scale evolutionary correlation data, which is represented in matrix form, in which rows and columns correspond to different scales, and element values ​​represent the correlation at the corresponding scale.

[0118] Step S246: Perform electromagnetic wave fault identification based on the multi-scale evolution correlation data and the contour line deformation interval data to obtain electromagnetic wave fault data.

[0119] In the embodiment of the present invention, the multi-scale evolution correlation data obtained in step S245 is used as input to ensure that the format and structure of the data are suitable for subsequent operations, and the contour deformation interval data obtained in step S244 is used as another input to ensure that these data can provide specific information of the contour deformation to provide support for fault identification. The multi-scale evolution correlation data and the contour deformation interval data are subjected to feature extraction using traditional threshold methods, pattern matching algorithms, machine learning algorithms or deep learning methods, and the specific selection depends on the nature of the data and the requirements of the problem. This may include statistical features, frequency domain features, and spatial domain features to capture key information in the data, and the electromagnetic wave fault is identified on the multi-scale evolution correlation data and the contour deformation interval data to obtain the position, shape, and strength of the electromagnetic wave fault, and generate the final electromagnetic wave fault data. This may be a data file containing the coordinates of the fault position, or an image of visual representation.

[0120] The present invention can more clearly display the distribution of the electromagnetic field by drawing contour lines based on the transmission electromagnetic characteristic surface and characteristic curvature skewness data, provide spatial visualization of the change in electromagnetic field intensity, and help to understand the characteristics of the electromagnetic field as a whole. By interpolating the electromagnetic contour line surface, more precise electromagnetic contour line interpolation data can be obtained to fill the blank areas between sampling points, thereby improving the spatial resolution of electromagnetic field changes and enabling the system to better capture subtle features and anomalies. By performing deformation analysis on the electromagnetic contour line surface, the system can detect deformation phenomena occurring in the electromagnetic field, namely the existence of abnormal changes or fluctuating faults, providing detailed insights into local changes in the electromagnetic field and helping to more accurately locate abnormal areas. By calculating the contour line deformation intervals, the system can quantify different electromagnetic fields. The deformation degree of the region provides a quantitative indicator of the degree of anomaly, which helps to identify the areas with the most significant changes in the electromagnetic field and guide the subsequent dynamic evolution process analysis. The dynamic evolution process analysis combined with the contour deformation interval data provides detailed data support for understanding the trend of electromagnetic field changes and the evolution process of anomalies. Multi-scale evolution correlation analysis using contour dynamic evolution data and contour deformation interval data can identify the evolution correlation relationship of electromagnetic fields at different scales, provide a multi-angle interpretation of electromagnetic field changes, and help to more comprehensively understand the formation and propagation of anomalies. By integrating multi-scale evolution correlation data, the system can more accurately identify electromagnetic fluctuation faults, that is, the key areas of abnormal changes, provide accurate positioning of fluctuation faults in the electromagnetic field, and provide strong support for subsequent problem positioning and processing.

[0121] Preferably, step S3 comprises the following steps:

[0122] Step S31: calculating the abnormal voltage fluctuation interval of the electromagnetic abnormal fluctuation report data to obtain abnormal voltage interval data;

[0123] Step S32: evaluating the impact hysteresis of the electromagnetic transformation data according to the abnormal voltage interval data to obtain abnormal voltage impact delay data;

[0124] Step S33: analyzing the electromagnetic voltage transformation data for impact effects according to the abnormal voltage interval data and the abnormal voltage impact delay data to obtain electromagnetic voltage transformation impact effect data;

[0125] Step S34: performing performance loss analysis on the distribution network transformer according to the electromagnetic transformer influence effect data to obtain transformer performance loss data.

[0126] In an embodiment of the present invention, raw data is obtained from an electromagnetic abnormal fluctuation report, including time series data of voltage values, and a suitable algorithm or method, such as threshold detection, sliding window analysis, and statistical methods, is used to identify the time period of voltage fluctuation. According to the detection result of the voltage fluctuation, the start and end points of the abnormal voltage are determined to form a continuous abnormal voltage interval, and the voltage value corresponding to the abnormal voltage interval is extracted from the raw data to form abnormal voltage interval data; electromagnetic transformer data, including time series data of current and voltage, is obtained, corresponding to the abnormal voltage interval data, to ensure that the abnormal voltage interval data and the electromagnetic transformer data are aligned in time. This can be achieved through timestamps or other time markers, and each abnormal voltage interval is evaluated to analyze the time lag of the corresponding electromagnetic transformer data. Correlation analysis, cross-correlation functions, and lag correlation can be used to extract the delay information of the impact of abnormal voltage on electromagnetic transformer data from the evaluation results. This includes lag time and lag steps; the abnormal voltage interval data obtained in step S31 is used as input data for analyzing the impact effect, and the abnormal voltage impact delay data obtained in step S32 is used as the basis for analyzing the impact effect of electromagnetic transformer data. Electromagnetic transformer data, including time series data of current and voltage, are obtained, corresponding to the abnormal voltage interval data and the impact delay data, to ensure that the abnormal voltage interval data, the abnormal voltage impact delay data and the electromagnetic transformer data are aligned in time. This is a key step to ensure the accuracy of the analysis. For each abnormal voltage interval and its corresponding impact delay data, the impact effect of the corresponding electromagnetic transformer data is analyzed, and the impact effect information of the electromagnetic transformer data is extracted from the analysis results. This includes amplitude changes, phase changes, and spectrum changes; the electromagnetic transformer impact effect data obtained in step S33 is used as the basic data for analyzing the performance loss of the distribution network transformer, and the performance parameter data of the distribution network transformer, such as the rated capacity, efficiency curve, temperature rise data, loss model, etc., are collected for performance loss analysis, and the electromagnetic transformer impact effect data is correlated with the performance parameters of the distribution network transformer to explore the possible relationship between the two. This requires building a model or conducting statistical analysis based on data, and simulating or calculating performance loss based on the associated results of the analysis. This includes using loss models, efficiency calculations, and temperature change simulations to extract performance loss data of distribution network transformers from simulation or calculation results, including loss values, efficiency changes, and temperature rise increase data indicators.

[0127] By calculating the electromagnetic abnormal fluctuation report data, the present invention can accurately determine the fluctuation range of abnormal voltage, provide the time and space range of abnormal voltage fluctuation, help to quickly locate the occurrence area of ​​abnormal voltage, and improve the sensitivity to electromagnetic field abnormalities. By evaluating the abnormal voltage interval data, the system can analyze the hysteresis of the impact of abnormal voltage on electromagnetic transformation data, that is, the response delay caused by abnormal voltage, provide an understanding of the dynamic response characteristics of electromagnetic field abnormalities, and help understand the timing relationship between voltage fluctuations and electromagnetic field changes. By integrating the abnormal voltage interval data and the impact delay data, the system can deeply analyze the impact effect of electromagnetic transformation data, that is, the specific impact mechanism of abnormal voltage on electromagnetic transformation data, provide a detailed understanding of the electromagnetic field changes caused by abnormal voltage, and provide a basis for further problem location and resolution. By performing performance loss analysis on distribution network transformers according to electromagnetic transformation impact effect data, the system can evaluate the actual impact of electromagnetic anomalies on equipment performance, provide a quantitative analysis of transformer performance loss, and provide a scientific basis for equipment maintenance and replacement decisions.

[0128] Preferably, step S33 includes the following steps:

[0129] Step S331: evaluating the voltage drop amplitude on the abnormal voltage interval data to obtain voltage drop amplitude data; performing drop cycle analysis on the voltage drop amplitude data to obtain voltage drop cycle data;

[0130] Step S332: extracting the peak voltage of the abnormal voltage interval data according to the voltage drop cycle data to obtain abnormal peak voltage data; performing time distribution characteristic analysis on the abnormal peak voltage data to obtain abnormal peak voltage time distribution data;

[0131] Step S333: calculating the peak voltage dispersion degree of the abnormal peak voltage time distribution data to obtain abnormal peak voltage dispersion data;

[0132] Step S334: Calculate the potential risk level according to the abnormal peak voltage discrete data and the voltage drop cycle data to obtain abnormal voltage potential risk data;

[0133] Step S335: analyzing the electromagnetic transformation data for impact effects according to the abnormal voltage potential risk data and the abnormal voltage impact delay data to obtain electromagnetic transformation impact effect data.

[0134] In an embodiment of the present invention, the original data of the abnormal voltage interval, including the voltage value and the timestamp, is obtained from the power system or related equipment, and the voltage values ​​at adjacent time points are calculated to obtain the voltage drop amplitude. The calculated voltage drop amplitude data is stored as a time series for subsequent analysis, and signal processing technology, such as Fourier transform or sliding window analysis, is used to determine the periodicity of the voltage drop. This helps to find the frequency and period of the voltage drop, and the analyzed voltage drop period data is stored as a time series for further processing and analysis; the voltage drop period data obtained in step S331 is used to determine the periodic characteristics of the peak voltage in the abnormal voltage interval, and the peak voltage in the abnormal voltage interval is identified and extracted based on the voltage drop period data.A threshold method, a differential method or other signal processing technology can be used to determine the peak value, and the extracted abnormal peak voltage data is saved as a time series for subsequent analysis and recording, including the time point of occurrence of the peak voltage, the duration of the peak voltage, and the change trend of the peak voltage in different periods. The abnormal peak voltage time distribution data obtained by analysis is stored as a time series for further analysis and report generation; the abnormal peak voltage time distribution data obtained in step S332 is used to calculate the standard deviation of the abnormal peak voltage data to reflect the dispersion of the data, and the mean value is divided by the standard deviation to consider the relative dispersion of the data, and the percentile difference of the data is compared to detect the distribution difference of the abnormal peak voltage in time. The abnormal peak voltage time distribution data is calculated accordingly, and the calculated abnormal peak voltage discrete data is stored as a single value or time series for further analysis and recording, and the calculation results are reviewed to ensure that the discrete data reflects the distribution characteristics of the abnormal peak voltage in time; the abnormal peak voltage discrete data calculated in step S333 is used, and the voltage drop periodic data, which includes the periodic data of voltage fluctuations, such as the periodic changes in the time series, is comprehensively considered. The voltage discrete degree and voltage drop cycle data are used to evaluate the potential risk degree. The abnormal peak voltage discrete degree and the voltage drop cycle are combined to calculate the comprehensive index by weighing and calculating. The abnormal peak voltage discrete degree and the voltage drop cycle are considered separately, and then the potential risk degree is obtained by combining them. The abnormal voltage potential risk algorithm is used to calculate the potential risk degree of the abnormal peak voltage discrete data and the voltage drop cycle data. The abnormal voltage potential risk data calculated in step S334 is used. The abnormal voltage impact delay data is used. The data describes the impact delay of the abnormal voltage on the electromagnetic transformer. An appropriate impact effect analytical model is selected. The model should be able to consider the abnormal voltage potential risk data and the impact delay data to evaluate the impact effect of the electromagnetic transformer. The impact effect of the electromagnetic transformer is derived by establishing a transfer function between the voltage potential risk and the impact delay. The abnormal voltage potential risk and delay data are used to perform statistical regression analysis to identify the relationship between them and the electromagnetic transformer effect. The abnormal voltage potential risk data and the abnormal voltage impact delay data are input into the calculation model to perform analytical calculation of the impact effect. The calculated electromagnetic transformer impact effect data is stored as a single value or a time series for subsequent analysis and recording.

[0135] By evaluating the voltage drop amplitude of the abnormal voltage interval data, the present invention can quantify the amplitude change of the abnormal voltage and provide the specific value of the voltage fluctuation, which is helpful to describe the characteristics of the abnormal voltage more accurately. By performing periodic analysis on the voltage drop amplitude data, the system can obtain the periodic information of the voltage fluctuation, that is, the repetitive occurrence pattern of the voltage fluctuation, which is helpful to understand the time characteristics of the voltage fluctuation and provides a time series basis for subsequent analysis. By extracting the peak voltage of the abnormal voltage interval according to the voltage drop periodic data, the system can capture the maximum amplitude of the abnormal voltage and provide the peak information of the abnormal voltage, which is helpful to identify the extreme situation in the voltage fluctuation and provides key data for subsequent analysis. By performing time distribution feature analysis on the abnormal peak voltage data, the system can deeply understand the time distribution pattern of the abnormal voltage, including the appearance time and duration of the peak, and provides a basis for the analysis of the abnormal voltage. A detailed understanding of the voltage timing characteristics helps to identify the critical moments of voltage fluctuations. The system calculates the peak voltage discreteness of the abnormal peak voltage time distribution data, and can quantify the fluctuation degree of the abnormal voltage, providing discrete information of the abnormal voltage fluctuation, which helps to judge the stability and predictability of the voltage fluctuation. The system calculates the potential risk level based on the abnormal peak voltage discrete data and the voltage drop period data, and can quantify the potential threat of abnormal voltage to system stability, providing an overall risk assessment of the impact of abnormal voltage, which helps to prioritize areas with potentially higher risks. The system analyzes the impact effects of electromagnetic transformation data based on the abnormal voltage potential risk data and the abnormal voltage impact delay data. The system can comprehensively consider the amplitude, period, peak characteristics and potential risks of voltage fluctuations, provide a comprehensive understanding of electromagnetic field anomalies, and help to more accurately predict the impact of electromagnetic field changes on the system.

[0136] Preferably, the potential risk degree is calculated based on the abnormal peak voltage discrete data and the voltage drop period data by using an abnormal voltage potential risk algorithm, wherein the abnormal voltage potential risk algorithm is as follows:

[0137]

[0138] Among them, y represents the result value of the potential risk degree of abnormal voltage, n represents the abnormal voltage value, x represents the amplitude coefficient of abnormal voltage, a represents the interval value of abnormal voltage, b represents the peak voltage dispersion, θ represents the abnormal voltage fluctuation frequency, t represents the time interval of threat calculation, c represents the voltage drop cycle stability coefficient, d represents the voltage drop average value, and R represents the error correction value of the abnormal voltage potential risk algorithm.

[0139] The present invention constructs an abnormal voltage potential risk algorithm, which fully considers the abnormal voltage value n, and a higher abnormal voltage value will increase the potential risk degree; the abnormal voltage amplitude coefficient x adjusts the amplitude of the abnormal voltage value, and a higher amplitude coefficient will increase the potential risk degree; the abnormal voltage interval value a represents the range of the abnormal voltage, and a larger interval value indicates that the voltage fluctuation is large, and insufficient stability increases the potential risk degree; the peak voltage dispersion b represents the dispersion degree of the peak voltage, and a higher dispersion degree will increase the potential risk degree; the abnormal voltage fluctuation frequency θ represents the fluctuation frequency of the abnormal voltage, and a higher frequency will increase the potential risk degree; the time interval t of threat calculation represents the time range for threat calculation, and a longer time interval indicates that the voltage is more complex and will increase the potential risk degree; the voltage drop cycle stability coefficient c adjusts the stability of the voltage drop cycle, and a higher stability coefficient will reduce the potential risk degree; the voltage drop average value d represents the average value of the voltage drop, and a higher average value will increase the potential risk degree; the error correction value R of the abnormal voltage potential risk algorithm is used to perform error correction on the result, so that the risk result obtained is more accurate.

[0140] Preferably, step S34 includes the following steps:

[0141] Step S341: Calculate transformer winding current according to electromagnetic transformer influence effect data to obtain transformer winding current data;

[0142] Step S342: performing electromagnetic field distribution simulation according to transformer winding current data and electromagnetic transformation effect data to obtain electromagnetic field simulation distribution data; performing magnetic coupling effect analysis on the electromagnetic field simulation distribution data to obtain electromagnetic field coupling effect data;

[0143] Step S343: Calculate the magnetic flux density based on the electromagnetic field coupling effect data to obtain the electromagnetic field magnetic flux density data; calculate the magnetic field force based on the electromagnetic field magnetic flux density data to obtain the magnetic field force data;

[0144] Step S344: evaluating the operating state vibration frequency of the distribution network transformer according to the electromagnetic transformer influence effect data to obtain vibration frequency evaluation data; performing mechanical resonance simulation based on the vibration frequency evaluation data and the magnetic field force data to obtain mechanical resonance simulation data;

[0145] Step S345: performing density continuity analysis on the electromagnetic field magnetic flux density data to obtain magnetic flux density continuous data; performing magnetic flux density saturation evaluation based on the magnetic flux density continuous data to obtain magnetic flux density saturation data;

[0146] Step S346: Calculate harmonic intensity according to the magnetic flux density saturation data, the electromagnetic field coupling effect data, and the transformer winding current data to obtain harmonic intensity data;

[0147] Step S347: Perform performance loss analysis on the distribution network transformer according to the mechanical resonance simulation data and the harmonic intensity data to obtain transformer performance loss data.

[0148] In the embodiment of the present invention, the electromagnetic transformer influence effect data calculated in step S335 is used to prepare the basic data of the structural parameters and electrical parameters of the transformer, and the electromagnetic transformer influence effect data is considered to evaluate the transformer winding current. The transformer circuit model is used to calculate the winding current according to the electromagnetic transformer influence effect. The transformer magnetic circuit parameters are considered and the winding current is calculated in combination with the electromagnetic field influence effect. According to the selected model, the electromagnetic transformer influence effect data is input into the calculation model to calculate the winding current. The calculated transformer winding current data is stored as a single value or a time series for subsequent analysis and recording. The transformer winding current data calculated in step S341 is used to prepare the geometric structure, material and structure of the transformer. The material characteristics are used for electromagnetic field simulation data, and a numerical model of the electromagnetic field distribution is established using the finite element method. The magnetic circuit parameters of the electromagnetic field distribution are combined for analysis. According to the selected model, the transformer winding current data is input into the calculation model to perform simulation calculation of the electromagnetic field distribution. The calculated electromagnetic field simulation distribution data is stored as a single value or spatial distribution for subsequent analysis and recording. Based on the electromagnetic field simulation distribution data, a magnetic coupling effect analysis is performed, and the influence of the transformer winding current on the adjacent parts is considered. The electromagnetic field coupling effect data obtained by the analysis is stored as a single value or spatial distribution for subsequent analysis and recording; the electromagnetic field coupling effect data calculated in step S342 is used to prepare the material magnetic properties, The geometric structure is used for the data of magnetic flux density and magnetic field force calculation. An appropriate magnetic flux density calculation model is selected. The model should be able to consider the electromagnetic field coupling effect data to simulate the electromagnetic field magnetic flux density. The numerical model of magnetic flux density is established using the finite element method. The magnetic flux density is calculated by analytical methods based on the physical equations and boundary conditions. According to the selected model, the electromagnetic field coupling effect data is input into the calculation model to calculate the magnetic flux density. The calculated electromagnetic field magnetic flux density data is stored as a single value or spatial distribution for subsequent analysis and recording. The expression of the Lorentz force is used to calculate the magnetic field force by considering the relationship between the magnetic flux density and the current. The calculated magnetic field force data is stored as a single value or spatial distribution to obtain the transformer in different The electromagnetic transformer effect data under working conditions, including current and magnetic flux density, are used to establish a structural model of the transformer using the finite element method, taking into account the influence of the electromagnetic field on the structure, taking into account the natural vibration frequency of the transformer through modal analysis, inputting the electromagnetic transformer effect data into the selected model, estimating and analyzing the vibration frequency, collecting the mechanical structural parameters of the transformer, such as material properties and geometric structure, obtaining the magnetic field force data obtained in step S343, simulating the mechanical resonance behavior of the transformer based on the vibration frequency evaluation data and the magnetic field force data, establishing a multi-body dynamics model of the transformer, taking into account the influence of the electromagnetic force and the vibration frequency on the system, inputting the vibration frequency evaluation data and the magnetic field force data into the selected model, and performing mechanical resonance simulation.Simulate the resonance conditions that may occur in the transformer under different working conditions, record the simulated mechanical resonance simulation data, including the resonance frequency, amplitude, and stress distribution, obtain the electromagnetic field flux density data, ensure that the data covers the entire transformer area, and includes data under different working conditions, use mathematical interpolation or fitting methods to obtain a continuous representation of the electromagnetic field flux density, such as linear interpolation and quadratic interpolation, use curve fitting algorithms, such as polynomial fitting, perform density continuity analysis, obtain a continuous representation of the electromagnetic field flux density, record the obtained continuous flux density data, including the density value and corresponding coordinates of each point, and evaluate the performance based on the density continuous data. Estimate the saturation state of the transformer magnetic flux density, consider the hysteresis characteristics of the core material, evaluate the magnetic flux density saturation, record the magnetic flux density saturation data obtained by the evaluation, including the saturation magnetic flux density and the saturation magnetic permeability, obtain the magnetic flux density saturation data obtained in step S345, collect and prepare data related to the electromagnetic field coupling inside the transformer, including the transformer structure, material properties, and circuit parameters, obtain the measured or simulated data of the transformer winding current, ensure that the current changes under different working conditions of the transformer are covered, use the electromagnetic harmonic intensity algorithm to calculate the harmonic intensity, combine the transformer winding current data and the coupling model, and perform coupling calculation. This calculation may be to solve the electromagnetic field distribution, magnetic flux density distribution and magnetic circuit characteristics, record the obtained harmonic intensity data, including the amplitude, phase and frequency of different harmonic components; based on the physical structure and characteristics of the transformer, establish a mechanical resonance model. This may include the mass, elastic modulus, and damping of the mechanical part, determine the conditions for mechanical resonance simulation, such as external excitation frequency and amplitude, which are based on actual operating conditions or standard specifications, obtain the vibration response data of the transformer under mechanical resonance conditions, couple the mechanical resonance simulation data with the harmonic intensity data, consider the impact of harmonics on the mechanical structure of the transformer, extract the performance parameters of the transformer from the coupled data, including mechanical vibration amplitude, transformer loss, and temperature rise, calculate the performance loss of the transformer under mechanical resonance and harmonics based on the extracted performance parameters, including mechanical loss, iron loss, and copper loss, and record the obtained transformer performance loss data, including performance indicators and loss amounts under different conditions.

[0149] The present invention can more accurately understand the current distribution inside the transformer by calculating the winding current according to the electromagnetic transformer influence effect data, which is crucial for evaluating the electromagnetic performance of the transformer and helps to detect potential current anomalies or overload conditions. Through electromagnetic field simulation and magnetic coupling effect analysis, the electromagnetic field distribution data inside the transformer can be obtained, which helps to understand the complexity of the electromagnetic field, detect potential coupling effects, and provide information for improving electromagnetic design. By calculating the magnetic flux density and magnetic field force, the magnetic properties of the transformer under different working conditions can be evaluated. This helps to detect potential magnetic field problems, such as saturation or excessive magnetic field force, thereby improving the reliability of the transformer. By evaluating the vibration frequency of the operating state and performing mechanical resonance simulation, problems that cause mechanical resonance can be detected. This helps to prevent damage to the equipment caused by vibration and improve the life of the transformer. The continuity analysis of the electromagnetic field magnetic flux density and the evaluation of the saturation of the magnetic flux density can help determine the magnetic performance of the transformer under different working conditions. This helps to avoid the influence of abnormal magnetic flux density on the performance of the transformer. By calculating the harmonic intensity, the harmonic response of the transformer in the power grid can be evaluated. This helps detect potential harmonic problems and improve the equipment's tolerance to harmonics. Through comprehensive analysis of mechanical resonance simulation data and harmonic intensity data, the performance loss of the transformer can be evaluated. This helps prevent potential performance problems and take necessary maintenance and improvement measures.

[0150] Preferably, the harmonic intensity is calculated based on the magnetic flux density saturation data, the electromagnetic field coupling effect data and the transformer winding current data, wherein the harmonic intensity is calculated by an electromagnetic harmonic intensity algorithm, wherein the electromagnetic harmonic intensity algorithm is as follows:

[0151]

[0152] Where G represents the harmonic intensity value, represents the magnetic flux density value, β represents the electromagnetic field coupling effect intensity coefficient, γ represents the floating range of the transformer winding current, δ represents the continuous characteristic coefficient of the magnetic flux density, ∈ represents the maximum load value of the transformer, represents the magnetic field force value, λ represents the complexity of electromagnetic field distribution, ω represents the mechanical resonance estimation value, and T represents the deviation adjustment value of the electromagnetic harmonic intensity algorithm.

[0153] The present invention constructs an electromagnetic harmonic intensity algorithm that fully considers the magnetic flux density value Represents the calculation of different magnetic flux density values, which can evaluate the change of harmonic intensity; electromagnetic field coupling effect intensity coefficient β, this parameter represents the coupling effect intensity of the electromagnetic field, that is, the degree of interaction between different parts of the electromagnetic field. A larger β value means a stronger coupling effect, resulting in an increase in harmonic intensity; the floating interval of the transformer winding current γ, this parameter represents the size and floating range of the transformer winding current. A larger γ value means a larger current floating range, which will cause an increase in harmonic intensity; the continuous characteristic coefficient δ of the magnetic flux density, this parameter represents the continuity characteristic of the magnetic flux density, that is, the smoothness of the magnetic field. A smaller δ value means a larger change in the magnetic flux density, which will lead to an increase in harmonic intensity; the maximum load value of the transformer ∈, a larger ∈ value means that the transformer is working closer to its maximum capacity under load, which will lead to an increase in harmonic intensity; the magnetic field force value Indicates the strength or intensity of the magnetic field, the larger the The value will cause the harmonic intensity to increase; electromagnetic field distribution complexity λ, this parameter indicates the complexity of the electromagnetic field distribution. A larger λ value indicates a more complex electromagnetic field distribution, which will lead to an increase in harmonic intensity; mechanical resonance estimation ω, this parameter indicates the estimation of mechanical resonance, that is, the situation where the system resonates at a specific frequency. A larger ω value will lead to an increase in harmonic intensity; electromagnetic harmonic intensity algorithm deviation adjustment value T, this parameter indicates the algorithm deviation adjustment value, which is used to correct errors in calculations or adjust results. The value of T can be adjusted according to actual conditions to obtain a more accurate estimate of harmonic intensity.

[0154] Preferably, step S4 comprises the following steps:

[0155] Step S41: formulating a loss compensation strategy for the transformer performance loss data to obtain a loss compensation strategy;

[0156] Step S42: Designing an automated electromagnetic anomaly analysis model according to the electromagnetic anomaly fluctuation report data to obtain an automated electromagnetic analysis module;

[0157] Step S43: Designing power loss compensation for the automated electromagnetic analysis module according to the loss compensation strategy to obtain an automated power collection and analysis module.

[0158] In the embodiment of the present invention, the transformer performance loss data obtained in step S347 is prepared, and a detailed transformer performance loss data analysis is performed to understand the extent of different loss components, determine the loss compensation goals, including reducing mechanical losses and improving efficiency, and formulate loss compensation strategies based on data analysis and goals, which may include optimizing working conditions and improving maintenance strategies, obtain a final loss compensation strategy document, and describe in detail the implementation steps and the expected effects of the strategy, obtain electromagnetic abnormal fluctuation report data from the monitoring system or sensor network, ensure the integrity and accuracy of the data, eliminate invalid or abnormal data points, ensure the quality of input data, use Fourier transform and other technologies to perform spectrum analysis on electromagnetic fluctuation data, obtain frequency characteristics, and analyze the time characteristics of fluctuations, such as fluctuations. The start time and duration are used to extract the amplitude information of the fluctuation and understand the intensity of the fluctuation. Based on domain knowledge and feature analysis, normal and abnormal electromagnetic fluctuation patterns are defined. The appropriate model is selected, which can be a rule-based model or a machine learning model (such as a support vector machine or a neural network). The selected model is trained using labeled data to enable it to recognize normal and abnormal patterns. The designed automated electromagnetic anomaly analysis module is integrated into the system to ensure seamless integration with other modules. The data on power loss is obtained through the monitoring system or sensor, including the type, period and degree of loss. The power loss data is analyzed to extract the characteristics of the loss, such as frequency, amplitude and duration. Based on the loss characteristics and previous analysis results, a compensation plan for power loss is formulated. This involves adjusting the power transmission path, improving equipment efficiency or introducing compensating energy. According to the formulated loss compensation plan, an energy loss compensation module is designed, which can automatically apply the loss compensation strategy. The energy loss compensation module is integrated into the automated electromagnetic analysis module to ensure that the two modules work together. According to the actual scenario and loss compensation effect, the performance of the entire system is optimized to ensure the stability and efficiency of the system during the loss compensation process. The effect of the energy loss compensation module is verified using actual data to ensure its effectiveness in different scenarios. After completing the energy loss compensation design, the final automated energy collection analysis module is obtained. This module has the function of energy loss compensation and can improve the system's energy collection efficiency.

[0159] The present invention can minimize the performance loss of the transformer, improve its efficiency, reduce energy waste, extend the equipment life, and reduce operating costs by formulating an effective loss compensation strategy. The automated electromagnetic anomaly analysis module can monitor electromagnetic anomalies in real time and discover potential problems in a timely manner, thereby reducing the risk of equipment damage and improving the reliability and stability of the system. Through the power loss compensation design, effective compensation for power loss can be achieved, further improving the operating efficiency of the equipment, reducing power waste, and reducing energy costs.

[0160] The beneficial effects of the present invention are as follows: through electrical data collection, the electrical parameters of each transmission line and transformer of the distribution network can be obtained, and comprehensive operating status information can be provided; the electrical parameters of current, voltage, and power factor of each key point can be obtained, which provides basic data for comprehensive monitoring of the system operating status and helps to understand the actual working conditions of the power system; by collecting electromagnetic field data of the transmission line based on electrical data, transmission electromagnetic data is obtained, which helps to understand the strength and distribution of the electromagnetic field on the transmission line and on the transformer; by converting the transmission electromagnetic data into a three-dimensional surface diagram, an intuitive visual representation of the electromagnetic field is provided, and this visual presentation helps engineers and researchers to quickly understand the distribution and characteristics of the electromagnetic field, and in the transmission electromagnetic three-dimensional surface diagram On the basis of electromagnetic fluctuation fault identification, these faults may represent abnormal or mutation areas of the electromagnetic field, which are related to potential faults or irregular operations. The electromagnetic fluctuation fault data is further analyzed and processed to generate electromagnetic abnormal fluctuation report data. These reports provide a detailed description of abnormal electromagnetic behavior, including location, intensity and duration. The electromagnetic fluctuation fault data is used to identify fluctuation anomalies, which helps to capture possible electromagnetic abnormal events in the system. The generated electromagnetic abnormal fluctuation report data provides decision makers with important information about the health of the electromagnetic environment. These data can be used to optimize operation strategies, formulate preventive maintenance plans and make system improvements; by analyzing the electromagnetic abnormal fluctuation report data, the interval of abnormal voltage fluctuation is calculated. This helps to determine the period and range of abnormal voltage, provides a temporal and spatial context for further analysis, and analyzes the impact effect of electromagnetic transformer data. This includes the impact of electromagnetic field anomalies on transformer performance, involving electromagnetic induction and hysteresis factors. This analysis provides the specific impact mechanism of abnormal electromagnetic fields on transformers, and performs performance loss analysis on transformers in distribution networks, including the impact on rated capacity loss, temperature rise, and energy efficiency reduction of transformers. Performance loss analysis helps to evaluate the health status and performance degradation of transformers, and generate detailed transformer performance loss data, which includes transformer losses, temperature rise, and rated capacity reduction. By understanding the actual impact of electromagnetic anomalies on transformer performance, preventive maintenance plans can be formulated to avoid potential equipment failures and system interruptions. In addition, operational strategies can be optimized based on performance loss data to maximize the normal operation of equipment. Through the automated electromagnetic anomaly analysis mode, the system can intelligently process a large amount of electromagnetic anomaly fluctuation report data, including automatic identification of abnormal patterns, extraction of key features, and establishment of electromagnetic anomaly models. The automation module can monitor electromagnetic anomalies in real time to make the system more responsive.This helps to discover potential problems early, reduces dependence on manual intervention, and improves the automation level of the system. Based on the design of the electromagnetic anomaly analysis mode, the system can more accurately predict potential electromagnetic anomalies, help take preventive maintenance measures, and reduce system downtime. Through the design of the power loss compensation of the automated electromagnetic analysis module, the system can reduce power loss and improve the overall efficiency of the system, which is particularly important for the power supply system, because the improvement of energy efficiency means less waste of resources and lower operating costs. Through the use of the power collection and analysis module, the system can have an in-depth understanding of the flow direction and loss of power, so as to make improved decisions, involving system upgrades, equipment replacements, or adjustments to operating strategies to improve the performance of the entire system. Therefore, the power collection method of a distribution network of the present invention is an optimization process made on the traditional power collection method of the distribution network, which solves the problems of inaccurate detection of circuit abnormal points and inaccurate analysis of power performance loss in the traditional power collection method of the distribution network, improves the accuracy of circuit abnormal point detection, and improves the accuracy of power performance loss analysis.

[0161] 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.

[0162] 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. A method for collecting electric energy in a distribution network, characterized in that: The following steps are involved: Step S1: Collect electrical data of the distribution network to obtain electrical data of the distribution network; collect electromagnetic field data of the distribution network transmission lines and transformers in operation based on the electrical data of the distribution network to obtain transmission electromagnetic data and electromagnetic transformation data respectively; Step S2: Convert the transmission electromagnetic data into a three-dimensional surface map to obtain a transmission electromagnetic three-dimensional surface map; identify electromagnetic fluctuation faults based on the transmission electromagnetic three-dimensional surface map to obtain electromagnetic fluctuation fault data; identify fluctuation anomalies on the electromagnetic fluctuation fault data to obtain electromagnetic abnormal fluctuation report data; Step S3: Calculate the abnormal voltage fluctuation interval of the electromagnetic abnormal fluctuation report data to obtain abnormal voltage interval data; analyze the impact effect of the electromagnetic transformation data based on the abnormal voltage interval data to obtain electromagnetic transformation impact effect data; analyze the performance loss of the distribution network transformer based on the electromagnetic transformation impact effect data to obtain transformer performance loss data; Step S4: Design an automated electromagnetic anomaly analysis mode based on the electromagnetic abnormal fluctuation report data to obtain an automated electromagnetic analysis module; The power loss compensation design is performed on the automated electromagnetic analysis module to obtain an automated power collection and analysis module.

2. The method for collecting electric energy in a distribution network according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Collect electrical data of the distribution network to obtain electrical data of the distribution network; wherein the electrical data of the distribution network includes power transmission line data and power transformation node data; Step S12: Based on the power transmission line data and the power transformation node data, collect electromagnetic field data of the distribution network transmission line and transformer in operation state to obtain transmission electromagnetic data and electromagnetic transformation data respectively.

3. The method for collecting electric energy in a distribution network according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: Perform time series analysis on the transmission electromagnetic data to obtain transmission electromagnetic time series data; perform three-dimensional surface graph conversion based on the transmission electromagnetic time series data to obtain a transmission electromagnetic three-dimensional surface graph; Step S22: Mark the transmission electromagnetic three-dimensional surface graph with characteristic surfaces to obtain a transmission electromagnetic characteristic surface; perform curvature calculation on the transmission electromagnetic characteristic surface to obtain a characteristic curvature data set; Step S23: Perform skewness calculation on the characteristic curvature data set to obtain characteristic curvature skewness data; Step S24: Perform electromagnetic fluctuation fault identification based on the transmission electromagnetic characteristic surface and the characteristic curvature skewness data to obtain electromagnetic fluctuation fault data; Step S25: Perform fluctuation anomaly identification on the electromagnetic fluctuation fault data using a preset electromagnetic anomaly identification model to obtain electromagnetic abnormal fluctuation report data.

4. The method for collecting electric energy in a distribution network according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: Contour drawing is performed according to the transmission electromagnetic characteristic surface and characteristic curvature skewness data to obtain the electromagnetic contour line surface; Step S242: Contour interpolation calculation is performed on the electromagnetic contour line surface to obtain electromagnetic contour line interpolation data; Step S243: Contour deformation analysis is performed on the electromagnetic contour line surface according to the electromagnetic contour line interpolation data to obtain contour line deformation data; Step S244: Contour deformation interval calculation is performed on the contour line deformation data to obtain contour line deformation interval data; Dynamic evolution process analysis is performed on the contour line deformation interval data to obtain contour line dynamic evolution data; Step S245: Multi-scale evolution correlation analysis is performed according to the contour line dynamic evolution data and the contour line deformation interval data to obtain multi-scale evolution correlation data; Step S246: Electromagnetic wave fault identification is performed based on the multi-scale evolution correlation data and the contour line deformation interval data to obtain electromagnetic wave fault data.

5. The method for collecting electric energy in a distribution network according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Calculate the abnormal voltage fluctuation interval of the electromagnetic abnormal fluctuation report data to obtain abnormal voltage interval data; Step S32: Evaluate the impact hysteresis of the electromagnetic transformation data based on the abnormal voltage interval data to obtain abnormal voltage impact delay data; Step S33: Analyze the impact effect of the electromagnetic transformation data based on the abnormal voltage interval data and the abnormal voltage impact delay data to obtain electromagnetic transformation impact effect data; Step S34: Analyze the performance loss of the distribution network transformer based on the electromagnetic transformation impact effect data to obtain transformer performance loss data.

6. The method for collecting electric energy in a distribution network according to claim 5, characterized in that: Step S33 includes the following steps: Step S331: Evaluate the voltage drop amplitude of the abnormal voltage interval data to obtain voltage drop amplitude data; perform drop cycle analysis on the voltage drop amplitude data to obtain voltage drop cycle data; Step S332: Extract the peak voltage of the abnormal voltage interval data according to the voltage drop cycle data to obtain abnormal peak voltage data; perform time distribution characteristic analysis on the abnormal peak voltage data to obtain abnormal peak voltage time distribution data; Step S333: Calculate the peak voltage discrete degree of the abnormal peak voltage time distribution data to obtain abnormal peak voltage discrete data; Step S334: Calculate the potential risk degree according to the abnormal peak voltage discrete data and the voltage drop cycle data to obtain abnormal voltage potential risk data; Step S335: Analyze the impact effect of the electromagnetic transformer data according to the abnormal voltage potential risk data and the abnormal voltage impact delay data to obtain electromagnetic transformer impact effect data.

7. The method for collecting electric energy in a distribution network according to claim 6, characterized in that: The potential risk degree is calculated based on the abnormal peak voltage discrete data and the voltage drop cycle data, and is calculated by the abnormal voltage potential risk algorithm, wherein the abnormal voltage potential risk algorithm is as follows: Among them, y represents the result value of the potential risk degree of abnormal voltage, n represents the abnormal voltage value, x represents the amplitude coefficient of abnormal voltage, a represents the interval value of abnormal voltage, b represents the peak voltage dispersion, θ represents the abnormal voltage fluctuation frequency, t represents the time interval of threat calculation, c represents the voltage drop cycle stability coefficient, d represents the voltage drop average value, and R represents the error correction value of the abnormal voltage potential risk algorithm.

8. The method for collecting electric energy in a distribution network according to claim 7, characterized in that: Step S34 includes the following steps: Step S341: Calculate the transformer winding current according to the electromagnetic transformer influence effect data to obtain the transformer winding current data; Step S342: Simulate the electromagnetic field distribution according to the transformer winding current data and the electromagnetic transformer influence effect data to obtain the electromagnetic field simulation distribution data; Perform magnetic coupling effect analysis on the electromagnetic field simulation distribution data to obtain the electromagnetic field coupling effect data; Step S343: Calculate the magnetic flux density according to the electromagnetic field coupling effect data to obtain the electromagnetic field magnetic flux density data; Calculate the magnetic field force based on the electromagnetic field magnetic flux density data to obtain the magnetic field force data; Step S344: Operate the distribution network transformer according to the electromagnetic transformer influence effect data State vibration frequency evaluation is performed to obtain vibration frequency evaluation data; mechanical resonance simulation is performed based on the vibration frequency evaluation data and the magnetic field force data to obtain mechanical resonance simulation data; step S345: density continuity analysis is performed on the electromagnetic field flux density data to obtain continuous flux density data; flux density saturation evaluation is performed based on the continuous flux density data to obtain saturated flux density data; step S346: harmonic intensity calculation is performed based on the flux density saturation data, the electromagnetic field coupling effect data and the transformer winding current data to obtain harmonic intensity data; step S347: performance loss analysis is performed on the distribution network transformer based on the mechanical resonance simulation data and the harmonic intensity data to obtain transformer performance loss data.

9. The method for collecting electric energy in a distribution network according to claim 8, characterized in that: The harmonic intensity is calculated based on the magnetic flux density saturation data, the electromagnetic field coupling effect data and the transformer winding current data. The harmonic intensity is calculated by the electromagnetic harmonic intensity algorithm, and the electromagnetic harmonic intensity algorithm is as follows: Where G represents the harmonic intensity value, represents the magnetic flux density value, β represents the electromagnetic field coupling effect intensity coefficient, γ represents the floating range of the transformer winding current, δ represents the continuous characteristic coefficient of the magnetic flux density, ∈ represents the maximum load value of the transformer, represents the magnetic field force value, λ represents the complexity of electromagnetic field distribution, ω represents the mechanical resonance estimation value, and T represents the deviation adjustment value of the electromagnetic harmonic intensity algorithm.

10. The method for collecting electric energy in a distribution network according to claim 7, characterized in that: Step S4 includes the following steps: Step S41: Formulate a loss compensation strategy for the transformer performance loss data to obtain a loss compensation strategy; Step S42: Design an automated electromagnetic anomaly analysis model based on the electromagnetic abnormality fluctuation report data to obtain an automated electromagnetic analysis module; Step S43: Design power loss compensation for the automated electromagnetic analysis module based on the loss compensation strategy to obtain an automated power collection and analysis module.

Images