Relay protection setting value sheet intelligent management system

Abstract

The invention discloses an intelligent management system for a relay protection setting value list, relates to the technical field of power system safety engineering, and is used for solving the technical problems of low working efficiency, slow response speed and poor adaptability caused by the fact that an existing relay protection setting value list depends on manual calculation and setting. The method comprises the steps of collecting basic data from a target area; the method comprises the following steps: acquiring basic data, preprocessing the basic data, converting the basic data into optimized data, and constructing an optimized curve capable of reflecting an electric energy characteristic change trend of a target area by utilizing the optimized data. And generating prediction data based on the optimization curve in combination with future clock data. The prediction data is combined with a pre-trained constant value list prediction model to predict a relay protection constant value list of the target area, the prediction data and the real-time data are compared, the prediction constant value list is corrected, and a more accurate real-time constant value list is generated. And finally, based on the real-time constant value list, the system automatically adjusts the relay protection constant value to ensure the stability and safety of the power system.

Description

Technical Field

[0001] The invention belongs to the field of electric power systems, relates to electric power system safety engineering technology, and specifically is an intelligent management system for relay protection setting values. Background Art

[0002] In modern power grids, the role of relay protection systems as the cornerstone of safe and stable operation of power grids is self-evident. However, the traditional management method of relay protection setting sheets, which relies on paper documents, telephone communication and emails to distribute and track setting sheets, has exposed many drawbacks. This inefficient management model not only consumes a lot of human resources and materials (such as paper), but also causes information transmission delays and data errors due to human factors, which seriously affects the overall efficiency of the power system.

[0003] What is more worrying is that with the acceleration of social electrification, especially the popularization of new energy vehicles and the large-scale deployment of charging piles, the power grid is facing unprecedented challenges. The randomness and intermittent nature of new energy vehicle charging behavior have brought unstable effects on the power grid load. The traditional static relay protection setting is difficult to cope with this dynamic change, thus increasing the risk of power grid failure, which may lead to unplanned power outages and adversely affect residents' lives and industrial production.

[0004] Therefore, with the continuous expansion of the scale of power systems and the continuous advancement of technology, there is an urgent need for an intelligent management system for relay protection setting values ​​to achieve automatic optimization and dynamic adjustment of relay protection setting values. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an intelligent management system for relay protection setting orders, which is used to solve the technical problems of low work efficiency, slow response speed and poor adaptability caused by the existing relay protection setting orders relying on manual calculation and setting. The present invention collects basic data from the target area; pre-processes the basic data, converts it into optimized data, and uses the optimized data to construct an optimized curve that can reflect the trend of changes in the electric energy characteristics of the target area. Based on the optimized curve, combined with future clock data, predictive data is generated. The predicted data is combined with a pre-trained setting order prediction model to predict the relay protection setting order of the target area, and the predicted data is compared with the real-time data to correct the predicted setting order to generate a more accurate real-time setting order to solve the above problems.

[0006] To achieve the above object, the first aspect of the present invention provides a relay protection setting value unit intelligent management system, comprising:

[0007] Data acquisition module: used to collect basic data of the target area; wherein the target area is the area that requires relay protection setting; the basic data includes power data and clock data; the power data includes voltage, current and power; the clock data is the time of collecting power data;

[0008] Data processing module: used to pre-process the electric energy data to obtain optimized data; perform data fitting based on the optimized data and clock data to obtain the optimized curve of the target area; obtain prediction data based on the optimized curve and the target clock; wherein the target clock is a specific future time point;

[0009] Data generation module: combining the predicted data with the fixed value order prediction model to predict the relay protection fixed value order of the target area to obtain the predicted fixed value order; wherein the fixed value order prediction model is obtained by training based on the artificial intelligence model; and,

[0010] Based on the real-time data and the predicted data, the predicted setting list is corrected to obtain the real-time setting list; based on the real-time setting list, the relay protection setting is set; wherein the real-time data is the basic data generated by the target area at the target clock.

[0011] The present application obtains a predicted custom order through forecast data and a custom order forecast model, and corrects the predicted custom order based on real-time data to obtain a real-time set value order; in this way, it solves the problem of low efficiency caused by the current relay protection set value order relying on manual calculation and review, as well as the problem that the power grid fluctuations caused by power facilities are relatively large and the relay protection set values ​​need to be frequently updated.

[0012] Preferably, basic data of the target area is collected, including:

[0013] The target area is divided into several target sub-areas according to the use attributes, and then the target sub-areas are divided into several unit areas according to the nature of electricity consumption; the use attributes include industrial electricity, civil electricity and commercial electricity; the nature of electricity consumption includes charging pile electricity, living electricity and production electricity;

[0014] The basic sub-data of several unit areas are collected by data collection equipment; the basic data of the target area are obtained by integrating the several basic sub-data.

[0015] Since there are differences in the consumption time and power demand of industrial, civil and commercial electricity, a preliminary division of the target area by purpose can obtain more regular data; whether it is industrial electricity, civil electricity or commercial electricity, there are electricity and charging piles used for production, work and life, so further division can better obtain the pattern of electricity consumption; especially with the current popularity and rising trend of new energy vehicles, the electricity consumption of charging piles is divided separately and in detail, which can further refine the electricity pattern.

[0016] Preferably, preprocessing the electric energy data to obtain optimized data includes:

[0017] Remove the data whose maintenance time is lower than the time threshold in the electric energy data to obtain the filtered data;

[0018] Arrange the filtered data in the order of the clock data to obtain a filtered sequence;

[0019] Optimized data is obtained by performing calculations based on the filtered data in the filtered series.

[0020] The data collected by the data acquisition device may contain some abnormal numbers, such as interference with the data acquisition device, impact current caused by power-on during power use, etc. These interference data need to be removed, otherwise it will affect the use of electric energy data.

[0021] Preferably, performing calculation processing based on the screening data in the screening series to obtain optimized data includes:

[0022] By formula Obtain optimized data YHSJi; wherein, i is the screening data number of the screening sequence and is a positive integer; j is a positive integer less than 10; and SXSJ is the screening data.

[0023] This formula can be used to cyclically process 10 adjacent groups of screening data to obtain optimized data. The obtained optimized data is more scientific and reasonable, and further avoids the impact caused by the low accuracy of the screening data.

[0024] Preferably, data fitting is performed based on the optimization data and the clock data to obtain an optimization curve of the target area; comprising:

[0025] Divide the clock data into a number of clock sub-data according to a preset time step;

[0026] Obtain the corresponding voltage, current and power in the optimized data according to the clock sub-data to obtain the corresponding clock sub-voltage, clock sub-current, clock sub-frequency and clock sub-power;

[0027] Based on the clock sub-duration and the corresponding clock sub-voltage, clock sub-current and clock sub-power, data fitting is performed to obtain a voltage prediction curve, a current prediction curve and a power prediction curve;

[0028] An optimization curve is obtained based on the voltage prediction curve, the current prediction curve and the power prediction curve.

[0029] By analyzing the changing trends of the optimization data, we can better predict the electric energy data and provide data support for the automatic generation of relay protection setting orders in the later stage.

[0030] Preferably, obtaining prediction data based on the optimization curve and the target clock includes:

[0031] Inputting the target clock into the voltage prediction curve, the current prediction curve and the power prediction curve to obtain the predicted current, predicted voltage and predicted power of the target clock;

[0032] Prediction data is obtained based on the predicted current, predicted voltage, predicted frequency and predicted power.

[0033] The predicted value is obtained through the prediction curve. The data is derived based on historical data and has a good data basis.

[0034] Preferably, the steps required before combining the forecast data with the fixed value single forecast model include:

[0035] Determine whether any one of the predicted current, predicted voltage and predicted power is less than the corresponding threshold; if yes, combine the predicted data with the fixed value single prediction model; if no, issue a risk warning.

[0036] The forecast data is derived based on historical data. Therefore, although the forecast data is reliable, there is also the question of whether it is reasonable. It is necessary to judge the forecast data to determine whether the forecast data will exceed the corresponding threshold to avoid unreasonable relay protection orders due to excessive forecast data, which will cause damage to the power grid.

[0037] Preferably, the steps of performing risk warning include:

[0038] A risk parameter is obtained based on any one of the predicted current, predicted voltage and predicted power being greater than a corresponding threshold, and the risk parameter is sent to a staff member;

[0039] Determine whether the staff has handled it; if yes, execute it according to the staff's handling method; if not, use the threshold corresponding to the risk value as the prediction data, combine the prediction data with the set value sheet prediction model, and predict the relay protection set value sheet of the target area to obtain the predicted set value sheet.

[0040] When risk parameters appear, they need to be sent to relevant staff to allow them to evaluate how to deal with them; this may be because the power of the power facilities is relatively large, and the maximum load capacity of the power grid lines may need to be increased.

[0041] Preferably, the fixed value single prediction model is obtained by training based on an artificial intelligence model, including:

[0042] Extracting standard training data, dividing the standard training data according to the target area, and obtaining standard input data and standard output data; wherein the standard data includes historical electric energy data and corresponding fixed value sheets;

[0043] The artificial intelligence model is trained by the standard input data and the standard output data to obtain a fixed value single prediction model; wherein the artificial intelligence model includes a BP neural network model or a RBF neural network model.

[0044] The relay protection custom order is used to protect the power grid and related electrical equipment. The relay protection custom order is obtained based on the power current, voltage and power. However, because the electric energy data of electrical components changes greatly during operation, the big data model is used for training to obtain a custom order prediction model. The custom order prediction model may be used to obtain the desired data faster and improve work efficiency.

[0045] Preferably, the predicted value list is modified based on the real-time data and the predicted data to obtain the real-time value list, including:

[0046] Determine whether the deviation between real-time data and predicted data exceeds the deviation threshold; if yes, proceed to the next step; if no, take the predicted value order as the real-time value order;

[0047] Determine whether the real-time data exceeds the corresponding threshold; if yes, proceed to the next step; if no, use the threshold corresponding to the real-time data as input data to obtain the real-time fixed value order through the fixed value order prediction model;

[0048] Determine whether the real-time data exceeds the predicted data; if yes, use the real-time data as input data to obtain the real-time fixed value order through the fixed value order prediction model; if no, use the predicted fixed value order as the real-time fixed value order.

[0049] The predicted setting list is corrected to make the relay protection setting more accurate and improve safety performance.

[0050] Preferably, the steps after setting the relay protection setting value based on the real-time setting value list include:

[0051] Randomly select a number of historical basic data and the corresponding real-time fixed value orders;

[0052] The calculated setting list is obtained by manually calculating the relay protection setting for the several historical basic data;

[0053] Compare several historical basic data corresponding to the real-time fixed value list and the calculated fixed value list to obtain the deviation coefficient;

[0054] Evaluate the accuracy attribute of the real-time value list based on the coefficient of deviation; the accuracy attribute includes accuracy and inaccuracy;

[0055] Optimize and train the fixed-value single prediction model based on the fact that the accurate attribute is inaccurate.

[0056] Compared with the prior art, the beneficial effects of the present invention are as follows: in view of the limitations of the traditional relay protection setting order process, which is inefficient and difficult to respond to power fluctuations in real time, the present application proposes a data-driven dynamic adjustment mechanism. The mechanism first uses historical power data to construct a prediction curve, predicts future power demand trends through the curve, and generates a preliminary relay protection setting order. This initial setting order is not fixed, but approaches the preset target time point over time, continuously self-optimizing and adjusting until the target time is reached, so as to achieve the final accurate configuration of the setting order. This method effectively overcomes the lag of traditional methods, improves the response speed and adaptability of the relay protection system, and shows greater flexibility and efficiency, especially when dealing with complex power fluctuations caused by household appliances, electric vehicle charging and industrial production. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic diagram of a method for using a relay protection setting value unit intelligent management system according to an embodiment of the present invention;

[0059] Figure 2 A schematic diagram of a customized single verification method flow chart of an embodiment of the present invention;

[0060] Figure 3 The invention discloses an intelligent management system for relay protection setting values ​​according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] See also Figure 1 The first aspect of the present invention provides a method for using a relay protection setting value unit intelligent management system, including:

[0063] S1: Collect basic data of the target area.

[0064] Among them, the target area is the area that requires relay protection settings; the basic data includes electric energy data and clock data; the electric energy data includes voltage, current and power; and the clock data is the time for collecting the electric energy data.

[0065] Among them, the basic data of the target area is collected, including:

[0066] The target area is divided into several target sub-areas according to the use attributes, and then the target sub-areas are divided into several unit areas according to the nature of electricity consumption; the use attributes include industrial electricity, civil electricity and commercial electricity; the nature of electricity consumption includes charging pile electricity, living electricity and production electricity;

[0067] The basic sub-data of several unit areas are collected by data collection equipment; the basic data of the target area are obtained by integrating the several basic sub-data.

[0068] For example, for the target area, multiple target sub-areas are obtained based on industrial electricity, residential electricity and commercial electricity, such as area A, area B, area, etc.;

[0069] If area A is a residential community that uses civilian electricity, part of the electricity in this residential community is used for daily life and part of it is used for charging piles; the basic data of area A can be obtained by collecting the electricity used for daily life and charging piles.

[0070] S2: Preprocess the electric energy data to obtain optimized data.

[0071] Among them, the electric energy data is preprocessed to obtain optimized data, including:

[0072] Remove the data whose maintenance time is lower than the time threshold in the electric energy data to obtain the filtered data;

[0073] Arrange the filtered data in the order of the clock data to obtain a filtered sequence;

[0074] Optimized data is obtained by performing calculations based on the filtered data in the filtered series.

[0075] For example: The current data in the basic data collected is as follows:

[0076] 1.30A, hold time 10s; clock data is 1:01:10s on January 1, 2023;

[0077] 2.40A, hold time 5s; clock data is 1:01:20 on January 1, 2023;

[0078] 3.30A, hold time 5s; clock data is 1:01:30 on January 1, 2023;

[0079] 4.40A, hold time 1s; clock data is 1:01:40 on January 1, 2023;

[0080] 5.40A, hold time 3s. Clock data is 1:01:50 on January 1, 2023.

[0081] Assuming that the time threshold is 2s, the data of No. 4 (40A, holding time 1s; clock data is 1:01:40 on January 1, 2023) needs to be removed to obtain optimized data, which is sorted as follows:

[0082] 1.30A, hold time 10s; clock data is 1:01:10s on January 1, 2023;

[0083] 2.40A, hold time 5s; clock data is 1:01:20 on January 1, 2023;

[0084] 3.30A, hold time 5s; clock data is 1:01:30 on January 1, 2023;

[0085] 4.40A, hold time 3s. Clock data is 1:01:50 on January 1, 2023.

[0086] The optimized data is obtained by performing calculation based on the filtered data in the filtered series, including:

[0087] By formula Obtain optimized data YHSJi; wherein, i is the screening data number of the screening sequence and is a positive integer; j is a positive integer less than 10; and SXSJ is the screening data.

[0088] For example: Assume i is 100,

[0089] Then YHSJ100={[(SXSJ100)2+(SXSJ99)2+…+(SXSJ91)2] / 10}1 / 2.

[0090] S3: Perform data fitting based on the optimization data and the clock data to obtain an optimization curve of the target area; obtain prediction data based on the optimization curve and the target clock.

[0091] It should be noted that:

[0092] Divide the clock data into a number of clock sub-data according to a preset time step;

[0093] Obtain the corresponding voltage, current and power in the optimized data according to the clock sub-data to obtain the corresponding clock sub-voltage, clock sub-current, clock sub-frequency and clock sub-power;

[0094] Based on the clock sub-duration and the corresponding clock sub-voltage, clock sub-current and clock sub-power, data fitting is performed to obtain a voltage prediction curve, a current prediction curve and a power prediction curve;

[0095] An optimization curve is obtained based on the voltage prediction curve, the current prediction curve and the power prediction curve.

[0096] Inputting the target clock into the voltage prediction curve, the current prediction curve and the power prediction curve to obtain the predicted current, predicted voltage and predicted power of the target clock;

[0097] Prediction data is obtained based on the predicted current, predicted voltage, predicted frequency and predicted power.

[0098] For example: The current data in the optimization data is as follows:

[0099] 1.10A, the clock data is 1:01:10 on January 1, 2023;

[0100] 2.10.1A, the clock data is 01:01:20 on January 1, 2023;

[0101] 3.10.2A, the clock data is 01:01:30 on January 1, 2023;

[0102] 5.10.4A, the clock data is 01:01:50 on January 1, 2023.

[0103] The formula F(X) is then fitted based on these data, and the current generated in the future can be predicted based on F(X).

[0104] S4: Combine the predicted data with the setting order prediction model to predict the relay protection setting order of the target area to obtain the predicted setting order.

[0105] The single prediction model obtaining step includes:

[0106] Extracting standard training data, dividing the standard training data according to the target area, and obtaining standard input data and standard output data; wherein the standard data includes historical electric energy data and corresponding fixed value sheets;

[0107] The artificial intelligence model is trained by the standard input data and the standard output data to obtain a fixed value single prediction model; wherein the artificial intelligence model includes a BP neural network model or a RBF neural network model.

[0108] S5: Based on the real-time data and the forecast data, the forecast fixed value list is modified to obtain the real-time fixed value list.

[0109] The detailed steps include:

[0110] Determine whether the deviation between real-time data and predicted data exceeds the deviation threshold; if yes, proceed to the next step; if no, take the predicted value order as the real-time value order;

[0111] Determine whether the real-time data exceeds the corresponding threshold; if yes, proceed to the next step; if no, use the threshold corresponding to the real-time data as input data to obtain the real-time fixed value order through the fixed value order prediction model;

[0112] Determine whether the real-time data exceeds the predicted data; if yes, use the real-time data as input data to obtain the real-time fixed value order through the fixed value order prediction model; if no, use the predicted fixed value order as the real-time fixed value order.

[0113] The predicted setting list is corrected to make the relay protection setting more accurate and improve safety performance.

[0114] For example: real-time voltage: 115kV;

[0115] Predicted voltage: 110kV;

[0116] Deviation threshold: 5%;

[0117] Voltage threshold upper limit: 120kV;

[0118] Deviation value check: The deviation between the real-time voltage and the predicted voltage is 4.5% (|115-110| / 110*100%), which just exceeds the deviation threshold (5%), so proceed to the next step.

[0119] Real-time data anomaly detection: The real-time voltage of 115kV does not exceed the upper voltage threshold of 120kV, but since this step has been entered, it continues to execute.

[0120] Comparison of real-time data with predicted data: The real-time voltage is higher than the predicted voltage, so the real-time setting order is recalculated using the real-time voltage as input.

[0121] Result: Since the real-time voltage exceeds the predicted value, the system will recalculate and set the relay protection setting based on the real-time voltage to ensure the safe operation of the power grid.

[0122] S6: Set the relay protection setting value based on the real-time setting value list.

[0123] See also Figure 2 , an embodiment of the present invention provides a customized single verification method, including:

[0124] S11: Randomly select a number of historical basic data and corresponding real-time fixed value orders.

[0125] S12: Obtain a calculated setting list by manually calculating the relay protection setting for the plurality of historical basic data.

[0126] S13: Compare several historical basic data corresponding to the real-time fixed value sheet and the calculated fixed value sheet to obtain the deviation coefficient, and evaluate the accurate properties of the real-time fixed value sheet based on the deviation coefficient.

[0127] S14: Determine whether the deviation coefficient is greater than the deviation threshold, if yes, proceed to S11; if no, proceed to S15;

[0128] S15: Optimize and train the fixed-value single prediction model based on the inaccuracy in the accurate attributes.

[0129] For example:

[0130] 100 sets of historical electric energy data, including voltage, current, power, etc., and the real-time set value orders corresponding to these data are randomly selected from the database.

[0131] An expert team was organized to independently calculate 100 calculation value sheets based on 100 sets of historical electricity data in accordance with relay protection theory and standard calculation methods.

[0132] Compare each pair of calculated fixed value sheets with the real-time fixed value sheets, calculate the deviation between the two, and quantify it as a deviation coefficient.

[0133] The coefficient of variation can be calculated using the following formula:

[0134] Deviation coefficient = | calculated set value - real-time set value | / real-time set value × 100%;

[0135] Statistical deviation coefficient distribution, identify samples with large deviations, and determine whether the deviation coefficient is greater than the deviation threshold.

[0136] When the deviation coefficient is greater than the deviation threshold, these samples are marked as the focus of optimization training.

[0137] The fixed-value single prediction model is iteratively optimized by adopting strategies such as enhancing the learning rate, increasing the amount of training data or adjusting the model structure.

[0138] Repeat the above steps until the data deviation coefficient predicted by the model is greater than the deviation threshold.

[0139] See also Figure 3 The present invention provides a relay protection setting value unit intelligent management system, comprising:

[0140] Data acquisition module: used to collect basic data of the target area; wherein the target area is the area that requires relay protection setting; the basic data includes power data and clock data; the power data includes voltage, current and power; the clock data is the time of collecting power data;

[0141] Data processing module: used to pre-process the electric energy data to obtain optimized data; perform data fitting based on the optimized data and clock data to obtain the optimized curve of the target area; obtain prediction data based on the optimized curve and the target clock; wherein the target clock is a specific future time point;

[0142] Data generation module: combining the predicted data with the fixed value order prediction model to predict the relay protection fixed value order of the target area to obtain the predicted fixed value order; wherein the fixed value order prediction model is obtained by training based on the artificial intelligence model; and,

[0143] Based on the real-time data and the predicted data, the predicted setting list is corrected to obtain the real-time setting list; based on the real-time setting list, the relay protection setting is set; wherein the real-time data is the basic data generated by the target area at the target clock.

[0144] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0145] The working principle of the present invention is as follows: the system automatically collects power data and clock data from the target area (where relay protection is required). The power data includes but is not limited to electrical parameters such as voltage, current and power, while the clock data records the specific time points at which these power data are collected. The collected basic data is preprocessed and converted into optimized data, which improves the data quality and makes it more suitable as input for subsequent analysis. Using the optimized data, the system performs data fitting to construct an optimization curve that can reflect the changing trend of the power characteristics of the target area. Based on the optimization curve, combined with future clock data (i.e., the predicted time point), the system predicts the power state of the target area at a specific future moment and generates predicted data. The predicted data is combined with a pre-trained set value order prediction model to predict the relay protection set value order required by the target area at the predicted moment. The system further compares the predicted data with the actual power data (real-time data) of the target area collected in real time, corrects the predicted set value order, and generates a more accurate real-time set value order. Finally, based on the real-time set value order, the system automatically adjusts the settings of the relay protection equipment to ensure the stability and safety of the power system.

[0146] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent management system for relay protection setting values, characterized in that: Data acquisition module: used to collect basic data of the target area; wherein the target area is the area that requires relay protection setting; the basic data includes power data and clock data; the power data includes voltage, current and power; the clock data is the time of collecting power data; Data processing module: used to pre-process the electric energy data to obtain optimized data; perform data fitting based on the optimized data and clock data to obtain the optimized curve of the target area; obtain prediction data based on the optimized curve and the target clock; wherein the target clock is a specific future time point; Data generation module: combining the predicted data with the fixed value order prediction model to predict the relay protection fixed value order of the target area to obtain the predicted fixed value order; wherein the fixed value order prediction model is obtained by training based on the artificial intelligence model; and, Based on the real-time data and the predicted data, the predicted setting list is corrected to obtain the real-time setting list; based on the real-time setting list, the relay protection setting is set; wherein the real-time data is the basic data generated by the target area at the target clock.

2. The intelligent management system for relay protection setting value list according to claim 1 is characterized in that: The basic data of the target area to be collected includes: The target area is divided into several target sub-areas according to the use attributes, and then the target sub-areas are divided into several unit areas according to the nature of electricity consumption; the use attributes include industrial electricity, civil electricity and commercial electricity; the nature of electricity consumption includes charging pile electricity, living electricity and production electricity; The basic sub-data of several unit areas are collected by data collection equipment; the basic data of the target area are obtained by integrating the several basic sub-data.

3. The intelligent management system for relay protection setting value list according to claim 2 is characterized in that: The preprocessing of the electric energy data to obtain optimized data includes: Remove the data whose maintenance time is lower than the time threshold in the electric energy data to obtain the filtered data; Arrange the filtered data in the order of the clock data to obtain a filtered sequence; Optimized data is obtained by performing calculations based on the filtered data in the filtered series.

4. The intelligent management system for relay protection setting value list according to claim 3 is characterized in that: The step of performing calculations based on the screening data in the screening series to obtain optimized data includes: By formula Obtain optimized data YHSJi; wherein, i is the screening data number of the screening sequence and is a positive integer; j is a positive integer less than 10; and SXSJ is the screening data.

5. The intelligent management system for relay protection setting value list according to claim 1 is characterized in that: The method of performing data fitting based on the optimization data and the clock data to obtain an optimization curve of the target area comprises: Divide the clock data into a number of clock sub-data according to a preset time step; Obtain the corresponding voltage, current and power in the optimized data according to the clock sub-data to obtain the corresponding clock sub-voltage, clock sub-current, clock sub-frequency and clock sub-power; Based on the clock sub-duration and the corresponding clock sub-voltage, clock sub-current and clock sub-power, data fitting is performed to obtain a voltage prediction curve, a current prediction curve and a power prediction curve; An optimization curve is obtained based on the voltage prediction curve, the current prediction curve and the power prediction curve.

6. The intelligent management system for relay protection setting value list according to claim 5 is characterized in that: The obtaining of prediction data based on the optimization curve and the target clock includes: Inputting the target clock into the voltage prediction curve, the current prediction curve and the power prediction curve to obtain the predicted current, predicted voltage and predicted power of the target clock; Prediction data is obtained based on the predicted current, predicted voltage, predicted frequency and predicted power.

7. The intelligent management system for relay protection setting value list according to claim 6 is characterized in that: The steps that need to be performed before combining the forecast data with the fixed value single forecast model include: Determine whether any one of the predicted current, predicted voltage and predicted power is less than the corresponding threshold; if yes, combine the predicted data with the fixed value single prediction model; if no, issue a risk warning.

8. The intelligent management system for relay protection setting value list according to claim 7 is characterized in that: The steps of conducting risk warning include: Obtaining a risk parameter based on any one of the predicted current, predicted voltage and predicted power being greater than a corresponding threshold, and sending the risk parameter to a staff member; Determine whether the staff has handled it; if yes, execute it according to the staff's handling method; if not, use the threshold corresponding to the risk value as the prediction data, combine the prediction data with the set value sheet prediction model, and predict the relay protection set value sheet of the target area to obtain the predicted set value sheet.

9. The intelligent management system for relay protection setting value list according to claim 1, characterized in that: The method of amending the predicted fixed value list based on the real-time data and the predicted data to obtain the real-time fixed value list includes: Determine whether the deviation between real-time data and predicted data exceeds the deviation threshold; if yes, proceed to the next step; if no, take the predicted value order as the real-time value order; Determine whether the real-time data exceeds the corresponding threshold; if yes, proceed to the next step; if no, use the threshold corresponding to the real-time data as input data to obtain the real-time fixed value order through the fixed value order prediction model; Determine whether the real-time data exceeds the predicted data; if yes, use the real-time data as input data to obtain the real-time fixed value order through the fixed value order prediction model; if no, use the predicted fixed value order as the real-time fixed value order.

10. The intelligent management system for relay protection setting value list according to claim 1, characterized in that: The steps after setting the relay protection setting value based on the real-time setting value list include: Randomly select a number of historical basic data and the corresponding real-time fixed value orders; The calculated setting list is obtained by manually calculating the relay protection setting for the several historical basic data; Compare several historical basic data corresponding to the real-time fixed value list and the calculated fixed value list to obtain the deviation coefficient; Evaluate the accuracy attribute of the real-time value list based on the coefficient of deviation; the accuracy attribute includes accuracy and inaccuracy; Optimize and train the fixed-value single prediction model based on the fact that the accurate attribute is inaccurate.

Images