An intelligent management and control system for distribution boxes based on main control chip

Abstract

The present invention discloses an intelligent management and control system for a distribution box based on a main control chip, which belongs to the technical field of intelligent management and control of distribution boxes, and comprises a monitoring module, a safety module and a regional analysis module; the monitoring module is used for real-time monitoring of the distribution box, establishing a monitoring model, partitioning the monitoring model, and obtaining a plurality of monitoring areas; acquiring monitoring data of each monitoring point in real time, and inputting the monitoring data into the monitoring model for real-time display; the safety module is used for performing safety analysis on the distribution box, performing a baseline safety analysis on the distribution cabinet according to the monitoring model, and obtaining corresponding baseline safety analysis results; establishing a prediction model for each monitoring item, performing analysis through the prediction model, and obtaining prediction results corresponding to each monitoring item; when the prediction result is an over-standard warning, a safety warning is performed, and corresponding risk handling measures are generated, and risk handling is performed according to the obtained risk handling measures; the regional analysis module is used for analyzing each monitoring area in the monitoring model.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent management and control of distribution boxes, and specifically is an intelligent management and control system for distribution boxes based on a main control chip. Background Art

[0002] With the rapid development of the power industry and the in-depth promotion of smart grid construction, the safety and reliability of distribution boxes, as an important part of the power system, are crucial to the stable operation of the entire power system. However, the traditional management method of distribution boxes mainly relies on manual inspections and on-site operations, which has problems such as low efficiency, slow response speed, and untimely fault detection.

[0003] In recent years, with the rapid development of technologies such as the Internet of Things, cloud computing, and big data, intelligent control and management technologies have been widely used in the field of distribution boxes. These technologies use sensors, communication modules, and other devices to achieve real-time monitoring and remote control of various parameters of distribution boxes, effectively improving the management efficiency and safety of distribution boxes.

[0004] However, the existing intelligent management and control systems for distribution boxes still have some limitations; existing systems usually only focus on the monitoring and control of basic parameters of distribution boxes, and lack in-depth analysis and optimization of power quality, energy efficiency evaluation and other aspects; in addition, some systems also have problems such as poor communication stability and high data security risks.

[0005] Therefore, in order to overcome the limitations of the prior art and improve the overall performance and safety of the intelligent management and control system of a distribution box, the present invention proposes an intelligent management and control system for a distribution box based on a main control chip. Summary of the invention

[0006] In order to solve the problems existing in the above-mentioned solutions, the present invention provides an intelligent management and control system for distribution boxes based on a main control chip.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent management and control system for distribution boxes based on a main control chip, including a monitoring module, a safety module and a regional analysis module;

[0009] The monitoring module is used to monitor the distribution box in real time, obtain the distribution box information, establish a monitoring model according to the distribution box information, partition the monitoring model, obtain several monitoring areas, and set monitoring items for each monitoring area;

[0010] The monitoring data of each monitoring point in the distribution box is obtained in real time, and the obtained monitoring data is input into the monitoring model for real-time display.

[0011] Furthermore, the method for partitioning the monitoring model includes:

[0012] Step SA1: Identify the distribution box information, and input the distribution box information into a preset regional information library for matching;

[0013] When a corresponding regional case is matched, partitioning is performed according to the regional case;

[0014] When no regional case is matched, go to step SA2;

[0015] Step SA2: identifying each monitoring point in the distribution box, marking each monitoring point in the monitoring model, and marking the monitoring attribute of each monitoring point; obtaining the line distribution information of the distribution box, and dividing the distribution box line into a plurality of unit lines according to the line distribution information;

[0016] Step SA3: merging and analyzing each adjacent unit line to determine whether the merging requirements are met;

[0017] When it is judged that the merger requirements are not met, no merger will be carried out;

[0018] When it is determined that the merging requirements are met, the merging is performed to obtain a new unit line;

[0019] Step SA4: loop step SA3 until there are no adjacent unit lines that meet the merging requirements; mark each unit line as a monitoring area;

[0020] Step SA5: Integrate the corresponding distribution box information and the corresponding monitoring area into a regional case and store it in the regional information library.

[0021] Furthermore, the method for merging and analyzing adjacent unit lines includes:

[0022] Establish a merger judgment model, the expression of the merger judgment model is Where: s is the input data;

[0023] Each adjacent unit line is judged by combining the judgment model to obtain a corresponding judgment result.

[0024] The safety module is used to perform real-time safety analysis on the distribution box based on the monitoring model, perform baseline safety analysis on the distribution cabinet according to the monitoring model, and obtain corresponding baseline safety analysis results;

[0025] Establish a prediction model for each monitoring item, and perform analysis through the prediction model to obtain the prediction results corresponding to each monitoring item;

[0026] When the prediction result is normal, no corresponding operation is performed

[0027] When the prediction result is an over-standard warning, a safety warning is issued, and corresponding risk handling measures are generated, and risk handling is carried out according to the obtained risk handling measures.

[0028] Furthermore, the method for performing a baseline safety analysis on the power distribution cabinet according to the monitoring model includes:

[0029] Identify the monitoring items of each monitoring area in the monitoring model, set a single verification standard corresponding to each monitoring item, and set emergency measures corresponding to each single verification standard;

[0030] The data of each monitoring item is verified by using the single verification standard of each monitoring item to obtain the corresponding single verification result, which includes verification pass and verification fail;

[0031] When a single verification result is verification passed, no corresponding operation is performed;

[0032] When a single verification result is failure, handle it according to the corresponding emergency measures.

[0033] Furthermore, the risk treatment measures may include:

[0034] Establishing a risk preparation library, the risk preparation library is used to store various risk preparation data, the risk preparation data includes candidate measures, impact areas and impact values ​​corresponding to corresponding monitoring items; and sorting multiple candidate measures for the same monitoring item;

[0035] Mark the monitoring items whose prediction results are over-standard warning as warning items; match the corresponding risk preparation data from the risk preparation library according to the warning items; identify the impact area, candidate measures and impact value corresponding to the warning items according to the risk preparation data;

[0036] Acquire influence region data corresponding to the influence region, analyze the influence region data, and obtain a corresponding influence region value, where the influence region value has a value range of [0, 100];

[0037] Calculate the impact value of the corresponding candidate measure according to the formula PH = λ × YZ × QZ;

[0038] Where: PH is the impact value of the measure; YZ is the impact value; QZ is the impact area value; λ is the adjustment coefficient, and its value range is [1, 1.5];

[0039] The candidate measures whose impact values ​​are greater than the threshold value X1 are eliminated, and the first ranked of the remaining candidate measures is marked as the risk treatment measure.

[0040] The regional analysis module is used to analyze each monitoring area in the monitoring model, identify each monitoring item corresponding to the monitoring area, establish an abnormality recognition model, and perform real-time analysis on each monitoring item in the monitoring area through the abnormality recognition model to obtain corresponding abnormal values;

[0041] According to the formula Calculate the regional monitoring value of each monitoring area at the corresponding time;

[0042] Where: QW is the regional monitoring value; bi is the proportional coefficient of the corresponding monitoring item, and its value range is (0, 1]; Y(gi) is the anomaly recognition model;

[0043] Generate a monitoring curve corresponding to the monitoring area according to the regional monitoring values ​​at each time; fit the monitoring curve to obtain a corresponding curve function, marked as W(t), where t is time;

[0044] Calculate the corresponding comprehensive value according to the curve function;

[0045] When the comprehensive value is greater than the threshold value X2, the power distribution in the monitoring area is evaluated to be abnormal;

[0046] When the comprehensive value is not greater than the threshold value X2, no corresponding operation is performed.

[0047] Furthermore, the expression of the anomaly recognition model is

[0048] In the formula: gi is the input data, i = 1, 2, ..., n, n is a positive integer; Ai is the excess value; the output data is the abnormal value.

[0049] Furthermore, the calculation method of the comprehensive value includes:

[0050] Set the evaluation duration, and mark the evaluation interval [t1, t2] in the monitoring curve according to the evaluation duration, where t2 is the current time;

[0051] According to the formula Calculate the corresponding comprehensive value;

[0052] Where: PF is the comprehensive value.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] Through the cooperation between the monitoring module, safety module and regional analysis module, intelligent management and control of the distribution box is realized; by generating risk treatment measures when an over-standard warning occurs and conducting emergency treatment in accordance with the risk treatment measures, possible risk losses can be reduced before the staff takes action; by not affecting current production and life as much as possible; intelligent emergency risk treatment can be achieved; excessive treatment that affects production and life is avoided when the standard is not exceeded; and by evaluating whether the power distribution in each monitoring area is reasonable, abnormal power distribution can be discovered in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] 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.

[0056] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0057] 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, not 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.

[0058] like Figure 1 As shown, a distribution box intelligent management and control system based on a main control chip includes a monitoring module, a safety module and a regional analysis module;

[0059] The monitoring module is used to monitor the distribution box in real time and establish a monitoring model for the distribution box. The monitoring model is a data display model established based on existing visualization technology and is used to display the received monitoring data. Because the distribution box will be equipped with corresponding monitoring equipment, such as current, voltage, temperature, etc., it is generally not necessary to set up additional corresponding monitoring equipment, and the corresponding docking reception can be performed; if additional monitoring is required according to the actual situation, the corresponding monitoring equipment can be supplemented as needed;

[0060] Obtain distribution box information, including specifications, models, brands, line distribution, working modes and other corresponding data; partition the monitoring model according to the obtained distribution box information, obtain several monitoring areas, set monitoring items for each monitoring area, and set them according to the monitoring data corresponding to the monitoring area to display the monitoring data corresponding to the monitoring area;

[0061] The monitoring data of each monitoring point in the distribution box is obtained in real time, and the obtained monitoring data is input into the monitoring model for real-time display.

[0062] The method for partitioning the monitoring model according to the distribution box information includes:

[0063] Step SA1: Identify the distribution box information, and input the identified distribution box information into a preset regional information database for matching;

[0064] When the corresponding regional cases are matched, partitioning is performed according to the obtained regional cases;

[0065] When no regional case is matched, go to step SA2.

[0066] Step SA2: Identify the corresponding monitoring positions in the distribution box, mark them as monitoring points, mark each monitoring point in the monitoring model, and mark the monitoring attributes of each monitoring point. The monitoring attributes are related information such as what data the monitoring point is used to monitor and which line ranges it corresponds to;

[0067] According to the line distribution information, the line is divided into several unit lines, which can be used as independent minimum lines. The simplest method is to directly regard the lines between the corresponding devices and components as a unit line. In actual applications, the possible line distribution conditions are manually summarized, and the corresponding unit lines are set according to various line distribution conditions. The corresponding unit statistical table is summarized and then identified and marked according to the unit statistical table.

[0068] Step SA3: merging and analyzing each adjacent unit line to determine whether the merging requirements are met;

[0069] When it is judged that the merger requirements are not met, no merger will be carried out;

[0070] When it is determined that the merging requirements are met, the merging is performed to obtain a new unit line;

[0071] Step SA4: loop step SA3 until there are no adjacent unit lines that meet the merging requirements; mark each unit line as a monitoring area;

[0072] Step SA5: Integrate the corresponding distribution box information and the corresponding monitoring area into a regional case and store it in the regional information library.

[0073] The method of merging and analyzing adjacent unit lines includes:

[0074] Obtain various possible adjacent unit lines, and manually mark the unit lines that meet the merging requirements according to the corresponding monitoring data. For example, if the adjacent unit lines are 1, 2, 3, and 4, and a certain monitoring data corresponds to 2 and 3, then 2 and 3 meet the merging requirements. Another monitoring data corresponds to 1, 2, and 3, then 1 and 2 are evaluated to meet the merging requirements, and then evaluated with 3, and still meet the merging requirements, forming a monitoring area corresponding to 123, that is, a unit line may be distributed in different monitoring areas; however, this is based on the situation that the monitoring data of 1, 2, and 3 cannot be clearly identified. If the independent corresponding monitoring data of the unit area can be clearly identified according to the monitoring data, then there is no need to merge, that is, the merging requirements are not met; establish a corresponding training set based on the labeled data, and establish a corresponding merging judgment model through the established training set, and the expression is Where: s is the input data, i.e. the corresponding unit line information and the corresponding monitoring point attributes;

[0075] The adjacent unit lines are judged by combining the judgment models to obtain corresponding judgment results.

[0076] The safety module is used to perform real-time safety analysis on the distribution box based on the monitoring model, and perform baseline safety analysis on the distribution cabinet according to the monitoring model; and obtain corresponding baseline safety analysis results;

[0077] Establish a prediction model for each monitoring item. The prediction model is established based on existing technology and is used to predict the change trend of the monitoring item data. When it is predicted that the data will exceed the standard in the future, a corresponding warning is issued; exemplary, it is established based on a CNN network or a DNN network, and a corresponding training set is established manually for training. The training set includes input data and output data. The input data is the corresponding monitoring item data, and the output data is the prediction data; the corresponding monitoring item is analyzed through the prediction model to obtain the corresponding prediction result, that is, whether an early warning is needed, including normal prediction and over-standard warning;

[0078] When the prediction result is normal, no corresponding operation is performed

[0079] When the prediction result is an over-standard warning, a safety warning is issued, and corresponding risk handling measures are generated, and risk handling is carried out according to the obtained risk handling measures.

[0080] By generating risk management measures when an over-standard warning occurs and conducting emergency treatment in accordance with the risk management measures, possible risk losses can be reduced before staff take action; by minimizing the impact on current production and life as much as possible; and by achieving intelligent emergency risk management; avoiding excessive processing when the standard is not exceeded, which affects production and life.

[0081] The baseline security analysis method is:

[0082] Identify the monitoring items of each monitoring area in the monitoring model, set the corresponding single calibration standards for each monitoring item. The single calibration standard is used to calibrate the corresponding single factors such as voltage, current, temperature, etc. Set the single calibration standard for each monitoring item according to the design standard; and set the corresponding emergency measures when each single calibration standard fails to pass the calibration, that is, when it is determined that the data exceeds the standard, how to perform emergency treatment, which can be set according to the existing method, such as power off;

[0083] Mark the displayed data of the monitoring item as monitoring item data; calibrate the data of each monitoring item through the single calibration standard of each monitoring item to obtain the corresponding single calibration result, including calibration pass and calibration fail, and make corresponding comparisons; perform corresponding safety processing according to the obtained single calibration result, that is, when the single calibration result is calibration pass, do not perform corresponding operations; when the single calibration result is calibration fail, handle it according to the preset emergency measures.

[0084] The methods for setting up risk treatment measures include:

[0085] Identify the monitoring items that have, obtain the impact data corresponding to each monitoring item, that is, when the monitoring item has a problem, which areas' production, life, etc. will be affected, and set the corresponding impact area; obtain the historical data of each monitoring item, determine the various risk treatment measures that can be taken for the monitoring item based on the historical data and existing technical conditions, and mark them as candidate measures; and determine the degree of impact of each candidate measure on the impact area based on the historical data, that is, the impact of electricity consumption after the application of the candidate measure compared with the normal state, marked as the impact value, such as the impact value of 0.1, indicating that the impact on electricity consumption is 10%; if the power-off measure does not allow electricity to be used, the impact value is 1; or a simulation experiment can be conducted in combination with the actual situation to obtain the impact value of each candidate measure; integrate the impact area, candidate measures and impact value corresponding to each monitoring item into risk preparation data, and establish a risk preparation library based on the risk preparation data; and for multiple candidate measures for the same monitoring item, rank them according to the quality of the emergency treatment effect, with the best effect ranked first;

[0086] Identify the monitoring items whose prediction results are over-standard warnings, and mark them as warning items; match the corresponding risk preparation data from the risk preparation library according to the warning items; identify the impact area corresponding to the warning item, obtain the status data of the current impact area, such as production status, living status, etc., and mark them as impact area data; analyze the impact area data to obtain the corresponding impact area value; the impact area value range is [0, 100]. For example, for industrial production, if the impact area is not in production, the impact area value is 0, and if the impact area is running at full load, the impact area value is 100; set the corresponding impact area value according to its actual situation; specifically, a corresponding impact analysis model can be established based on a neural network such as a CNN network or a DNN network, and a corresponding training set training can be established manually. The training set includes input data and output data, and the input data is the impact area data; the output data is the impact area value; analyze the impact analysis model after successful training to obtain the corresponding impact area value;

[0087] Calculate the impact value of the corresponding candidate measure according to the formula PH = λ × YZ × QZ;

[0088] Where: PH is the impact value of the measure; YZ is the impact value; QZ is the impact area value; λ is the adjustment coefficient, the value range is [1, 1.5], and it is set by the user according to the importance of the impact area. If the user does not make any adjustment, the default value is λ = 1;

[0089] The candidate measures whose impact values ​​are greater than the threshold value X1 are eliminated, and the first ranked of the remaining candidate measures is marked as the risk treatment measure.

[0090] The regional analysis module is used to analyze each monitoring area in the monitoring model to understand whether the power distribution in the monitoring area is reasonable and to detect abnormal power distribution in time; identify each monitoring item corresponding to the monitoring area and establish an abnormal identification model. The abnormal identification model is used to identify whether the current monitoring data deviates from the normal state. If an abnormal situation occurs, such as the difference between the monitoring item data and the corresponding single calibration standard is less than the preset value, it can be regarded as the first abnormality. For the exceeding standard situation, it is regarded as the second abnormality; in actual applications, the data range corresponding to the first abnormality of each monitoring item will be preset; and then the corresponding abnormal judgment will be made; the expression of the abnormal identification model is Where: gi is the input data, i.e. the corresponding monitoring item data, i=1, 2, ..., n, n is a positive integer; Ai is the preset value, marked as an exceeded value, which is set by the user according to the loss of the exceeded value, and the platform will preset a default value. When the user does not set a value, the default value is directly applied; the output data is an abnormal value 1, 0 or Ai;

[0091] Through the abnormal recognition model, each monitoring item in the monitoring area is analyzed in real time to obtain the corresponding abnormal value;

[0092] According to the formula Calculate the regional monitoring value of each monitoring area at the corresponding time;

[0093] Where: QW is the regional monitoring value; bi is the proportional coefficient of the corresponding monitoring item, and its value range is (0, 1];

[0094] Generate a monitoring curve corresponding to the monitoring area according to the regional monitoring values ​​at each time; fit the monitoring curve to obtain a corresponding curve function, marked as W(t), where t is time;

[0095] Set the evaluation duration, that is, how long the comprehensive evaluation will take, such as one week, one month, etc. The specific evaluation is set by the platform according to the information of the distribution box; the evaluation interval [t1, t2] is marked in the monitoring curve according to the evaluation duration, where t2 is the current time;

[0096] According to the formula Calculate the corresponding comprehensive value;

[0097] Where: PF is the comprehensive value;

[0098] When the comprehensive value is greater than the threshold value X2, the power distribution in the monitoring area is evaluated to be abnormal, such as unreasonable power distribution, unreasonable lines, etc.

[0099] When the comprehensive value is not greater than the threshold value X2, no corresponding operation is performed.

[0100] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0101] 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 and control system for distribution boxes based on a main control chip, characterized in that: Includes monitoring module, security module and regional analysis module; The monitoring module is used to monitor the distribution box in real time, obtain the distribution box information, establish a monitoring model according to the distribution box information, partition the monitoring model, obtain several monitoring areas, and set monitoring items for each monitoring area; Acquire the monitoring data of each monitoring point in the distribution box in real time, and input the acquired monitoring data into the monitoring model for real-time display; The safety module is used to perform real-time safety analysis on the distribution box based on the monitoring model, perform baseline safety analysis on the distribution cabinet according to the monitoring model, and obtain corresponding baseline safety analysis results; Establish a prediction model for each monitoring item, and perform analysis through the prediction model to obtain the prediction results corresponding to each monitoring item; When the prediction result is normal, no corresponding operation is performed When the prediction result is an over-standard warning, a safety warning is issued, and corresponding risk treatment measures are generated, and risk treatment is carried out according to the obtained risk treatment measures; The regional analysis module is used to analyze each monitoring area in the monitoring model, identify each monitoring item corresponding to the monitoring area, establish an abnormality recognition model, and perform real-time analysis on each monitoring item in the monitoring area through the abnormality recognition model to obtain corresponding abnormal values; According to the formula Calculate the regional monitoring value of each monitoring area at the corresponding time; Where: QW is the regional monitoring value; bi is the proportional coefficient of the corresponding monitoring item, and its value range is (0, 1]; Y(gi) is the anomaly recognition model; Generate a monitoring curve corresponding to the monitoring area according to the regional monitoring values ​​at each time; fit the monitoring curve to obtain a corresponding curve function, marked as W(t), where t is time; Calculate the corresponding comprehensive value according to the curve function; When the comprehensive value is greater than the threshold value X2, the power distribution in the monitoring area is evaluated to be abnormal; When the comprehensive value is not greater than the threshold value X2, no corresponding operation is performed; The methods for setting up risk treatment measures include: Establishing a risk preparation library, the risk preparation library is used to store various risk preparation data, the risk preparation data includes candidate measures, impact areas and impact values ​​corresponding to corresponding monitoring items; and sorting multiple candidate measures for the same monitoring item; Mark the monitoring items whose prediction results are over-standard warning as warning items; match the corresponding risk preparation data from the risk preparation library according to the warning items; identify the impact area, candidate measures and impact value corresponding to the warning items according to the risk preparation data; Acquire influence region data corresponding to the influence region, analyze the influence region data, and obtain a corresponding influence region value, where the influence region value has a value range of [0, 100]; Calculate the impact value of the corresponding candidate measure according to the formula PH = λ × YZ × QZ; Where: PH is the impact value of the measure; YZ is the impact value; QZ is the impact area value; λ is the adjustment coefficient, and the value range is [1, 1.5]; The candidate measures whose impact values ​​are greater than the threshold value X1 are eliminated, and the first ranked of the remaining candidate measures is marked as the risk treatment measure.

2. According to claim 1, a distribution box intelligent management and control system based on a main control chip is characterized in that: Methods for partitioning the monitor model include: Step SA1: Identify the distribution box information, and input the distribution box information into a preset regional information library for matching; When a corresponding regional case is matched, partitioning is performed according to the regional case; When no regional case is matched, go to step SA2; Step SA2: identifying each monitoring point in the distribution box, marking each monitoring point in the monitoring model, and marking the monitoring attribute of each monitoring point; obtaining the line distribution information of the distribution box, and dividing the distribution box line into a plurality of unit lines according to the line distribution information; Step SA3: merging and analyzing each adjacent unit line to determine whether the merging requirements are met; When it is judged that the merger requirements are not met, no merger will be carried out; When it is determined that the merging requirements are met, the merging is performed to obtain a new unit line; Step SA4: loop step SA3 until there are no adjacent unit lines that meet the merging requirements; mark each unit line as a monitoring area; Step SA5: Integrate the corresponding distribution box information and the corresponding monitoring area into a regional case and store it in the regional information library.

3. According to claim 2, a distribution box intelligent management and control system based on a main control chip is characterized in that: The method of merging and analyzing adjacent unit lines includes: Establish a merger judgment model, the expression of the merger judgment model is Where: s is the input data; Each adjacent unit line is judged by combining the judgment model to obtain a corresponding judgment result.

4. According to claim 1, a distribution box intelligent management and control system based on a main control chip is characterized in that: The methods for performing baseline safety analysis of power distribution cabinets based on monitoring models include: Identify the monitoring items of each monitoring area in the monitoring model, set a single verification standard corresponding to each monitoring item, and set emergency measures corresponding to each single verification standard; The data of each monitoring item is verified by using the single verification standard of each monitoring item to obtain the corresponding single verification result, which includes verification pass and verification fail; When a single verification result is verification passed, no corresponding operation is performed; When a single verification result is failure, handle it according to the corresponding emergency measures.

5. According to claim 1, a distribution box intelligent management and control system based on a main control chip is characterized in that: The expression of the anomaly recognition model is: In the formula: gi is the input data, i = 1, 2, ..., n, n is a positive integer; Ai is the excess value; the output data is the abnormal value.

6. According to claim 1, a distribution box intelligent management and control system based on a main control chip is characterized in that: The calculation method of the comprehensive value includes: Set the evaluation duration, and mark the evaluation interval [t1, t2] in the monitoring curve according to the evaluation duration, where t2 is the current time; According to the formula Calculate the corresponding comprehensive value; Where: PF is the comprehensive value.

Images