Grid power transmission safety risk assessment system and method based on artificial intelligence

Abstract

The invention discloses a power grid power transmission safety risk assessment system and method based on artificial intelligence, and belongs to the technical field of power grids. The data processing module is used for processing the historical power transmission data of the power grid; the model construction module is used for constructing a power grid power transmission safety risk assessment model; the test optimization module is used for carrying out test optimization on the power grid power transmission safety risk assessment model; and the risk assessment module is used for performing power grid power transmission safety risk assessment on the power grid power transmission real-time data and determining a power grid power transmission safety risk assessment result. The problems that real-time monitoring and safety risk assessment cannot be carried out on power transmission of the power grid, timely early warning cannot be carried out on power transmission faults of the power grid, and the power transmission safety management effect of the power grid is poor are solved. Real-time monitoring and safety risk assessment can be performed on the power transmission process of the power grid, timely early warning can be performed on power transmission faults of the power grid, and the power transmission safety management effect of the power grid can be improved.

Description

Technical Field

[0001] The present invention relates to the field of power grid technology, and in particular to a power grid transmission safety risk assessment system and method based on artificial intelligence. Background Art

[0002] The transmission of electric energy is an important part of the overall function of the power system. Power plants and power load centers are usually located in different regions. Power plants are built in places with suitable primary energy resources such as hydropower and coal. Through power transmission, electric energy can be transmitted to load centers far away from power plants, allowing the development and utilization of electric energy to transcend geographical limitations. Compared with other energy transmission methods, power transmission has the advantages of low loss, high efficiency, flexibility, convenience, easy adjustment and control, and reduced environmental pollution.

[0003] The Chinese patent with publication number CN112132528A discloses an artificial intelligence-based power grid infrastructure safety management system, which involves the field of power infrastructure, including a power grid infrastructure safety intelligent management and control module. The power grid infrastructure safety intelligent management and control module includes a hardware layer, a data acquisition layer, a data transmission layer, and an application layer. It can enable handheld terminals, industrial video equipment, high-support formwork detection equipment, foundation pit detection equipment, vehicle crane detection equipment, infrastructure safety gateway equipment and hardware equipment closely related to power grid infrastructure to be adjusted according to safety management instructions or early warnings. It is very convenient and can perform different work site management according to different network conditions. It has the potential for further development and wider adaptability. However, the patent has the following defects:

[0004] The existing system cannot conduct real-time monitoring and safety risk assessment of the power transmission process of the power grid, and cannot provide timely warning of power transmission failures, resulting in poor power transmission safety management effects. Summary of the invention

[0005] The purpose of the present invention is to provide an artificial intelligence-based power grid transmission safety risk assessment system and method, which can perform real-time monitoring and safety risk assessment of the power grid transmission process, can provide timely warning of power grid transmission failures, can improve the power grid transmission safety management effect, and solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The power grid transmission safety risk assessment system based on artificial intelligence includes:

[0008] A data acquisition module is used to collect power grid transmission environmental parameters and power grid transmission electrical parameters, and determine the power grid transmission historical data based on artificial intelligence;

[0009] A data processing module is used to process the historical data of power transmission of the power grid based on artificial intelligence and determine the characteristic data of power transmission of the power grid based on artificial intelligence;

[0010] A model building module is used to build an artificial intelligence-based power transmission safety risk assessment model according to the power transmission safety risk assessment requirements;

[0011] A test optimization module is used to test and optimize the power grid transmission safety risk assessment model to determine the optimal power grid transmission safety risk assessment model;

[0012] The risk assessment module is used to conduct power grid transmission safety risk assessment on real-time power grid transmission data and determine the power grid transmission safety risk assessment results based on artificial intelligence.

[0013] Preferably, the data acquisition module includes:

[0014] The environmental collection unit is used to collect the historical temperature, humidity and pressure conditions during the power transmission process of the power grid and obtain the power transmission environment parameters of the power grid;

[0015] The electrical data collection unit is used to collect the historical current, voltage and power conditions during the power transmission process of the power grid and obtain the electrical parameters of the power transmission of the power grid;

[0016] Among them, based on the power grid transmission environmental parameters and the power grid transmission electrical parameters, the artificial intelligence-based power grid transmission historical data is determined.

[0017] Preferably, the data processing module includes:

[0018] A data cleaning unit, used to clean historical data of power grid transmission based on artificial intelligence;

[0019] Obtain historical data on power grid transmission based on artificial intelligence;

[0020] Clean the historical data of power grid transmission based on artificial intelligence, including:

[0021] Conduct consistency checks on historical data of power grid transmission based on artificial intelligence;

[0022] Check whether the historical data of power transmission of power grid based on artificial intelligence meets the requirements according to the reasonable value range and mutual relationship of each parameter in the historical data of power transmission of power grid based on artificial intelligence;

[0023] Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the historical data of power grid transmission based on artificial intelligence;

[0024] Process invalid and missing values ​​of historical data of power grid transmission based on artificial intelligence;

[0025] Remove invalid and missing data that are of no value to the power transmission safety risk assessment in the historical data of power transmission based on artificial intelligence;

[0026] Determine the historical data of power grid transmission that is valuable for power grid transmission security risk assessment.

[0027] Preferably, the reasonable value range of each parameter in the power grid transmission history data based on artificial intelligence is obtained by the following formula:

[0028] Real-time monitoring of the value of each parameter in the power grid transmission history data;

[0029] Retrieve all parameter data corresponding to the data type of each parameter;

[0030] Retrieving a preset first threshold parameter and a second threshold parameter corresponding to the data type in the database; wherein the first threshold parameter is greater than the second threshold parameter, and the first threshold parameter is less than a preset upper limit value of the initial range corresponding to the data type; and the second threshold parameter is greater than a preset lower limit value of the initial range corresponding to the data type;

[0031] Extract parameter data corresponding to the data type in each unit time, and use the number of parameters corresponding to each unit time as a set of parameter data sets; wherein the value range of the unit time is 3min-5min;

[0032] Retrieve the numerical value corresponding to each set of parameter data sets, and extract the middle value of the data corresponding to each set of parameter data sets;

[0033] The data fluctuation coefficient corresponding to the data type of each parameter in the monitored power grid transmission history data is obtained by using the data intermediate value corresponding to each group of parameter data sets; wherein the data fluctuation coefficient is obtained by the following formula:

[0034]

[0035] Among them, B represents the data fluctuation coefficient; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X maxi and X mini represents the maximum and minimum values ​​of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X mmax represents the maximum value of the data in the parameter data set corresponding to the maximum value of the data intermediate value; λ represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0036]

[0037] Among them, λ represents the adjustment coefficient; n represents the total number of groups corresponding to the parameter data set; X zirepresents the middle value of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X zmin Indicates the minimum value of the data middle value appearing in n sets of parameter data sets;

[0038] The data fluctuation coefficient is used to dynamically adjust the initial range upper limit value and the initial range lower limit value.

[0039] Preferably, dynamically adjusting the initial range upper limit value and the initial range lower limit value by using the data fluctuation coefficient includes:

[0040] Comparing the data fluctuation coefficient with a preset fluctuation coefficient threshold;

[0041] When the data fluctuation coefficient exceeds a preset fluctuation coefficient threshold, an initial range upper limit value and an initial range lower limit value of the data type corresponding to the data fluctuation coefficient and a preset first threshold parameter and a second threshold parameter corresponding to the data type are retrieved as the first data information;

[0042] Retrieving the intermediate value of the data parameter corresponding to each set of parameter data sets as the second data information;

[0043] Using the first data information and the second data information, the initial range upper limit value and the initial range lower limit value are adjusted to obtain an adjusted reasonable value range upper limit value and a reasonable value range lower limit value;

[0044] Among them, the adjusted upper limit value of the reasonable value range and the lower limit value of the reasonable value range are obtained by the following formula:

[0045]

[0046]

[0047] Among them, X up and X down Respectively represent the upper limit and lower limit of the reasonable value range after adjustment; X up0 and X down0 Respectively represent the upper limit value and the lower limit value of the initial range; X y01 and X y02 represents the preset first threshold parameter and second threshold parameter corresponding to the data type respectively; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X zmin Indicates the minimum value of the data among n sets of parameter data.

[0048] Preferably, the data processing module further includes:

[0049] A data conversion unit, used for converting the cleaned historical data of power transmission of the power grid;

[0050] Obtaining the historical data of power grid transmission that is valuable for power grid transmission safety risk assessment after cleaning;

[0051] Convert historical data of power grid transmission that is valuable for power grid transmission safety risk assessment;

[0052] Eliminate the dimensional differences between historical data of power grid transmission;

[0053] Determine the historical data of power transmission of power grid with data standardization;

[0054] A feature extraction unit, used for extracting features from the converted historical data of power grid transmission;

[0055] Obtaining the converted and standardized historical data of power grid transmission;

[0056] Extract features from historical power transmission data of power grid with data standardization;

[0057] Extract features that can reflect the risk assessment of power grid transmission security;

[0058] Determine the power transmission characteristic data of the power grid based on artificial intelligence.

[0059] Preferably, the model building module includes:

[0060] A data division unit, used for dividing power grid transmission characteristic data based on artificial intelligence;

[0061] Obtaining AI-based power grid transmission characteristic data;

[0062] Divide the power transmission characteristic data of the power grid based on artificial intelligence;

[0063] Determine the training data set and the test data set;

[0064] Model training unit, used to build an AI-based power grid transmission security risk assessment model;

[0065] According to the needs of power grid transmission security risk assessment, a neural network model framework suitable for power grid transmission security risk assessment is selected;

[0066] Based on the training data set, the selected neural network model framework suitable for power grid transmission security risk assessment is trained;

[0067] Determine an artificial intelligence-based risk assessment model for power grid transmission security.

[0068] Preferably, the test optimization module includes:

[0069] A test and evaluation unit, used to test and evaluate the power grid transmission safety risk assessment model;

[0070] Obtain an AI-based power grid transmission security risk assessment model;

[0071] Based on the test data set, the power grid transmission security risk assessment model is tested and evaluated;

[0072] Determine the test evaluation results based on the power grid transmission security risk assessment model;

[0073] An adjustment and optimization unit, used to adjust and optimize the power grid transmission safety risk assessment model;

[0074] Obtain test evaluation results based on the power grid transmission safety risk assessment model;

[0075] Conduct mining and analysis on the test and evaluation results based on the power grid transmission safety risk assessment model;

[0076] Determine the parameter adjustment optimization scheme based on the power grid transmission security risk assessment model;

[0077] Optimize the parameters of the power transmission safety risk assessment model according to the parameter adjustment optimization scheme based on the power transmission safety risk assessment model;

[0078] Determine the optimal grid transmission security risk assessment model.

[0079] Preferably, the risk assessment module includes:

[0080] A data acquisition unit for acquiring real-time data of power grid transmission based on artificial intelligence;

[0081] According to the needs of power grid transmission safety risk assessment, the temperature, humidity, pressure, current, voltage and power conditions during power grid transmission are monitored and collected in real time to obtain real-time data on power grid transmission based on artificial intelligence;

[0082] A risk assessment unit, used to conduct a power grid transmission safety risk assessment on real-time power grid transmission data;

[0083] Obtain the optimal grid transmission security risk assessment model;

[0084] Inputting AI-based real-time data on power grid transmission into the optimal power grid transmission security risk assessment model;

[0085] Conduct power grid transmission security risk assessment based on the optimal power grid transmission security risk assessment model for real-time power grid transmission data based on artificial intelligence;

[0086] Determine the results of the power grid transmission security risk assessment based on artificial intelligence;

[0087] Among them, the results of the power grid transmission safety risk assessment based on artificial intelligence include the existence of safety risks in power grid transmission and the absence of safety risks in power grid transmission;

[0088] When there is a safety risk in power grid transmission, timely warning will be given to the power grid transmission process, and the warning information will be transmitted to the power grid transmission management personnel in real time. Power grid transmission safety management measures will be taken in time to maintain and manage the power grid transmission process. The power grid transmission management personnel can view the real-time power grid transmission safety risk assessment results and power grid transmission safety management and control measures through mobile terminals.

[0089] According to another aspect of the present invention, a method for assessing power transmission safety risk based on artificial intelligence is provided, which is implemented based on the above-mentioned power transmission safety risk assessment system based on artificial intelligence, and includes the following steps:

[0090] S1. Data collection and processing:

[0091] Collecting historical data of power grid transmission based on artificial intelligence, processing the historical data of power grid transmission based on artificial intelligence, and determining characteristic data of power grid transmission based on artificial intelligence;

[0092] S2. Model construction and optimization:

[0093] According to the needs of power grid transmission safety risk assessment, an artificial intelligence-based power grid transmission safety risk assessment model is constructed, and the power grid transmission safety risk assessment model is tested and optimized to determine the optimal power grid transmission safety risk assessment model;

[0094] S3. Risk assessment and management:

[0095] Based on the optimal power grid transmission safety risk assessment model, power grid transmission real-time data is used for power grid transmission safety risk assessment, the power grid transmission safety risk assessment results based on artificial intelligence are determined, and power grid transmission safety management measures are taken in time to maintain and manage the power grid transmission process.

[0096] Compared with the prior art, the present invention has the following beneficial effects:

[0097] The present invention collects historical data of power grid transmission based on artificial intelligence, processes the historical data of power grid transmission based on artificial intelligence, determines characteristic data of power grid transmission based on artificial intelligence, constructs a power grid transmission safety risk assessment model based on artificial intelligence according to the needs of power grid transmission safety risk assessment, tests and optimizes the power grid transmission safety risk assessment model, determines the optimal power grid transmission safety risk assessment model, performs power grid transmission safety risk assessment on real-time power grid transmission data based on the optimal power grid transmission safety risk assessment model, determines the power grid transmission safety risk assessment result based on artificial intelligence, and promptly takes power grid transmission safety management measures to maintain and manage the power grid transmission process, can perform real-time monitoring and safety risk assessment on the power grid transmission process, can give timely warning of power grid transmission failures, and can improve the power grid transmission safety management effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 It is a structural block diagram of the power grid transmission safety risk assessment system based on artificial intelligence of the present invention;

[0099] Figure 2 The present invention is a flowchart of the power transmission safety risk assessment method based on artificial intelligence. DETAILED DESCRIPTION

[0100] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0101] In order to solve the existing problems of being unable to conduct real-time monitoring and safety risk assessment of the power grid transmission process, and being unable to provide timely warnings of power grid transmission failures, resulting in poor power grid transmission safety management effects, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0102] The power transmission safety risk assessment system based on artificial intelligence includes: data acquisition module, data processing module, model building module, test optimization module and risk assessment module;

[0103] It should be noted that through the interactive communication between the data acquisition module, data processing module, model building module, test optimization module and risk assessment module, the power grid transmission process can be monitored in real time and the safety risk assessment can be carried out, and timely warnings can be given for power grid transmission failures, which can improve the safety management effect of power grid transmission.

[0104] Among them, the data acquisition module is used to collect power grid transmission environmental parameters and power grid transmission electrical parameters, and determine the power grid transmission historical data based on artificial intelligence;

[0105] In this embodiment, the data acquisition module includes:

[0106] The environmental collection unit is used to collect the historical temperature, humidity and pressure conditions during the power transmission process of the power grid and obtain the power transmission environment parameters of the power grid;

[0107] The electrical data collection unit is used to collect the historical current, voltage and power conditions during the power transmission process of the power grid and obtain the electrical parameters of the power transmission of the power grid;

[0108] Among them, based on the power grid transmission environmental parameters and the power grid transmission electrical parameters, the artificial intelligence-based power grid transmission historical data is determined.

[0109] Among them, the data processing module is used to process the historical data of power grid transmission based on artificial intelligence and determine the characteristic data of power grid transmission based on artificial intelligence;

[0110] In this embodiment, the data processing module includes:

[0111] A data cleaning unit, used to clean historical data of power grid transmission based on artificial intelligence;

[0112] Obtain historical data on power grid transmission based on artificial intelligence;

[0113] Clean the historical data of power grid transmission based on artificial intelligence, including:

[0114] Conduct consistency checks on historical data of power grid transmission based on artificial intelligence;

[0115] Check whether the historical data of power transmission of power grid based on artificial intelligence meets the requirements according to the reasonable value range and mutual relationship of each parameter in the historical data of power transmission of power grid based on artificial intelligence;

[0116] Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the historical data of power grid transmission based on artificial intelligence;

[0117] Process invalid and missing values ​​of historical data of power grid transmission based on artificial intelligence;

[0118] Remove invalid and missing data that are of no value to the power transmission safety risk assessment in the historical data of power transmission based on artificial intelligence;

[0119] Determine the historical data of power grid transmission that is valuable for power grid transmission security risk assessment;

[0120] A data conversion unit, used for converting the cleaned historical data of power transmission of the power grid;

[0121] Obtaining the historical data of power grid transmission that is valuable for power grid transmission safety risk assessment after cleaning;

[0122] Convert historical data of power grid transmission that is valuable for power grid transmission safety risk assessment;

[0123] Eliminate the dimensional differences between historical data of power grid transmission;

[0124] Determine the historical data of power transmission of power grid with data standardization;

[0125] A feature extraction unit, used for extracting features from the converted historical data of power grid transmission;

[0126] Obtaining the converted and standardized historical data of power grid transmission;

[0127] Extract features from historical power transmission data of power grid with data standardization;

[0128] Extract features that can reflect the risk assessment of power grid transmission security;

[0129] Determine the power transmission characteristic data of the power grid based on artificial intelligence.

[0130] Specifically, the reasonable value range of each parameter in the power grid transmission history data based on artificial intelligence is obtained by the following formula:

[0131] Real-time monitoring of the value of each parameter in the power grid transmission history data;

[0132] Retrieve all parameter data corresponding to the data type of each parameter;

[0133] Retrieving a preset first threshold parameter and a second threshold parameter corresponding to the data type in the database; wherein the first threshold parameter is greater than the second threshold parameter, and the first threshold parameter is less than a preset upper limit value of the initial range corresponding to the data type; and the second threshold parameter is greater than a preset lower limit value of the initial range corresponding to the data type;

[0134] Extract parameter data corresponding to the data type in each unit time, and use the number of parameters corresponding to each unit time as a set of parameter data sets; wherein the value range of the unit time is 3min-5min;

[0135] Retrieve the numerical value corresponding to each set of parameter data sets, and extract the middle value of the data corresponding to each set of parameter data sets;

[0136] The data fluctuation coefficient corresponding to the data type of each parameter in the monitored power grid transmission history data is obtained by using the data intermediate value corresponding to each group of parameter data sets; wherein the data fluctuation coefficient is obtained by the following formula:

[0137]

[0138] Among them, B represents the data fluctuation coefficient; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X maxi and X mini represents the maximum and minimum values ​​of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X mmax represents the maximum value of the data in the parameter data set corresponding to the maximum value of the data intermediate value; λ represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0139]

[0140] Among them, λ represents the adjustment coefficient; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X zmin Indicates the minimum value of the data middle value appearing in n sets of parameter data sets;

[0141] The data fluctuation coefficient is used to dynamically adjust the initial range upper limit value and the initial range lower limit value.

[0142] The technical effect of the above technical solution is: by real-time monitoring of the historical data of power grid transmission, the latest parameter values ​​can be obtained instantly, ensuring the timeliness of the data. By retrieving all parameter data corresponding to the data type to which each parameter belongs, the distribution characteristics of the data can be fully considered to improve the accuracy of the analysis.

[0143] The preset first threshold parameter and the second threshold parameter not only take into account the basic characteristics of the data type, but also provide a reasonable boundary for data fluctuations through the relative relationship with the preset upper and lower limits of the initial range. The above setting method makes the threshold parameters neither too loose (avoiding abnormal value interference) nor too strict (excluding normal fluctuations), which can more accurately identify abnormal data.

[0144] At the same time, finely divide the unit time and extract the middle value of the data: setting the unit time to 3min-5min can capture the changing trend of parameters in a short period of time and discover potential problems in time. Extracting the middle value of the data corresponding to each set of parameter data sets as the basis for data analysis can reduce the impact of extreme values ​​on the results and improve the robustness of the analysis.

[0145] By calculating the data fluctuation coefficient, the fluctuation degree of parameter data can be quantified, providing a basis for determining the reasonable value range. The introduction of the adjustment coefficient further considers the distribution characteristics of the data intermediate value, making the calculation of the data fluctuation coefficient more flexible and accurate. Using the data fluctuation coefficient to dynamically adjust the upper limit value and the lower limit value of the initial range can adapt to changes in the operating status of the power grid and ensure the timeliness and accuracy of the reasonable value range. This dynamic adjustment method can detect and handle abnormal situations in a timely manner, improving the reliability and safety of power grid operation.

[0146] In summary, this technical solution achieves accurate determination of the reasonable value range of each parameter in the historical data of power grid transmission through real-time monitoring, fine division of unit time, dynamic calculation of data fluctuation coefficient and dynamic adjustment of reasonable value range, which can improve the intelligence level and safety of power grid operation.

[0147] Specifically, dynamically adjusting the initial range upper limit value and the initial range lower limit value by using the data fluctuation coefficient includes:

[0148] Comparing the data fluctuation coefficient with a preset fluctuation coefficient threshold;

[0149] When the data fluctuation coefficient exceeds a preset fluctuation coefficient threshold, an initial range upper limit value and an initial range lower limit value of the data type corresponding to the data fluctuation coefficient and a preset first threshold parameter and a second threshold parameter corresponding to the data type are retrieved as the first data information;

[0150] Retrieving the intermediate value of the data parameter corresponding to each set of parameter data sets as the second data information;

[0151] Using the first data information and the second data information, the initial range upper limit value and the initial range lower limit value are adjusted to obtain an adjusted reasonable value range upper limit value and a reasonable value range lower limit value;

[0152] Among them, the adjusted upper limit value of the reasonable value range and the lower limit value of the reasonable value range are obtained by the following formula:

[0153]

[0154]

[0155] Among them, Xup and X down Respectively represent the upper limit and lower limit of the reasonable value range after adjustment; X up0 and X down0 Respectively represent the upper limit value and the lower limit value of the initial range; X y01 and X y02 represents the preset first threshold parameter and second threshold parameter corresponding to the data type respectively; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X zmin Indicates the minimum value of the data among n sets of parameter data.

[0156] The technical effect of the above technical solution is: by comparing the data fluctuation coefficient with the preset fluctuation coefficient threshold, it can be determined whether the fluctuation degree of the current data exceeds the normal range. The system can adaptively adjust the reasonable value range of the parameter to adapt to the changes in the operation status of the power grid.

[0157] When the data fluctuation coefficient exceeds the threshold, not only the upper and lower limits of the initial range are considered, but also the preset first threshold parameter and second threshold parameter corresponding to the data type, as well as the data intermediate value of each set of parameter data sets are introduced. The comprehensive use of this information makes the adjusted reasonable value range more accurate and reliable. The upper and lower limits of the adjusted reasonable value range are calculated by a specific formula, which comprehensively considers multiple factors, including the initial range, threshold parameters, data intermediate values ​​and their maximum and minimum values. The above calculation method can maintain the stability of the power grid operation and avoid failures or accidents caused by improper parameter value ranges. Dynamically adjusting the reasonable value range of the parameter can optimize the resource allocation of the power grid. For example, when the parameter value range is too large, the range can be appropriately narrowed to reduce unnecessary resource consumption; when the parameter value range is too small, the range can be appropriately expanded to ensure the normal operation of the power grid. Based on the idea of ​​artificial intelligence, the technical solution realizes the dynamic adjustment of the reasonable value range of each parameter in the historical data of power grid transmission through real-time monitoring and data analysis. The above technical solution can improve the intelligence level of the power grid and improve the safety and reliability of power grid operation.

[0158] In summary, this technical solution dynamically adjusts the upper and lower limits of the initial range through the data fluctuation coefficient, and realizes the accurate determination and optimization of the reasonable value range of each parameter in the historical data of power grid transmission. The above technical solution can enhance the adaptability, stability and intelligence level of the power grid, and improve the safety and reliability of power grid operation.

[0159] Among them, the model building module is used to build an artificial intelligence-based power transmission safety risk assessment model according to the power transmission safety risk assessment requirements;

[0160] In this embodiment, the model building module includes:

[0161] A data division unit, used for dividing power grid transmission characteristic data based on artificial intelligence;

[0162] Obtaining AI-based power grid transmission characteristic data;

[0163] Divide the power transmission characteristic data of the power grid based on artificial intelligence;

[0164] Determine the training data set and the test data set;

[0165] Model training unit, used to build an AI-based power grid transmission security risk assessment model;

[0166] According to the needs of power grid transmission security risk assessment, a neural network model framework suitable for power grid transmission security risk assessment is selected;

[0167] Based on the training data set, the selected neural network model framework suitable for power grid transmission security risk assessment is trained;

[0168] Determine an artificial intelligence-based risk assessment model for power grid transmission security.

[0169] Among them, the test optimization module is used to test and optimize the power grid transmission safety risk assessment model to determine the optimal power grid transmission safety risk assessment model;

[0170] In this embodiment, the test optimization module includes:

[0171] A test and evaluation unit, used to test and evaluate the power grid transmission safety risk assessment model;

[0172] Obtain an AI-based power grid transmission security risk assessment model;

[0173] Based on the test data set, the power grid transmission security risk assessment model is tested and evaluated;

[0174] Determine the test evaluation results based on the power grid transmission security risk assessment model;

[0175] An adjustment and optimization unit, used to adjust and optimize the power grid transmission safety risk assessment model;

[0176] Obtain test evaluation results based on the power grid transmission safety risk assessment model;

[0177] Conduct mining and analysis on the test and evaluation results based on the power grid transmission safety risk assessment model;

[0178] Determine the parameter adjustment optimization scheme based on the power grid transmission security risk assessment model;

[0179] Optimize the parameters of the power transmission safety risk assessment model according to the parameter adjustment optimization scheme based on the power transmission safety risk assessment model;

[0180] Determine the optimal grid transmission security risk assessment model.

[0181] Among them, the risk assessment module is used to conduct power grid transmission safety risk assessment on real-time power grid transmission data and determine the power grid transmission safety risk assessment results based on artificial intelligence.

[0182] In this embodiment, the risk assessment module includes:

[0183] A data acquisition unit for acquiring real-time data of power grid transmission based on artificial intelligence;

[0184] According to the needs of power grid transmission safety risk assessment, the temperature, humidity, pressure, current, voltage and power conditions during power grid transmission are monitored and collected in real time to obtain real-time data on power grid transmission based on artificial intelligence;

[0185] A risk assessment unit, used to conduct a power grid transmission safety risk assessment on real-time power grid transmission data;

[0186] Obtain the optimal grid transmission security risk assessment model;

[0187] Inputting AI-based real-time data on power grid transmission into the optimal power grid transmission security risk assessment model;

[0188] Conduct power grid transmission security risk assessment based on the optimal power grid transmission security risk assessment model for real-time power grid transmission data based on artificial intelligence;

[0189] Determine the results of the power grid transmission security risk assessment based on artificial intelligence;

[0190] Among them, the results of the power grid transmission safety risk assessment based on artificial intelligence include the existence of safety risks in power grid transmission and the absence of safety risks in power grid transmission;

[0191] When there is a safety risk in power grid transmission, timely warning will be given to the power grid transmission process, and the warning information will be transmitted to the power grid transmission management personnel in real time. Power grid transmission safety management measures will be taken in time to maintain and manage the power grid transmission process. The power grid transmission management personnel can view the real-time power grid transmission safety risk assessment results and power grid transmission safety management and control measures through mobile terminals.

[0192] In order to better demonstrate the power transmission safety risk assessment process based on artificial intelligence, this embodiment now provides a power transmission safety risk assessment method based on artificial intelligence, which is implemented based on the power transmission safety risk assessment system based on artificial intelligence as described above, and includes the following steps:

[0193] S1. Data collection and processing:

[0194] Collecting historical data of power grid transmission based on artificial intelligence, processing the historical data of power grid transmission based on artificial intelligence, and determining characteristic data of power grid transmission based on artificial intelligence;

[0195] S2. Model construction and optimization:

[0196] According to the needs of power grid transmission safety risk assessment, an artificial intelligence-based power grid transmission safety risk assessment model is constructed, and the power grid transmission safety risk assessment model is tested and optimized to determine the optimal power grid transmission safety risk assessment model;

[0197] S3. Risk assessment and management:

[0198] Based on the optimal power grid transmission safety risk assessment model, power grid transmission real-time data is used for power grid transmission safety risk assessment, the power grid transmission safety risk assessment results based on artificial intelligence are determined, and power grid transmission safety management measures are taken in time to maintain and manage the power grid transmission process.

[0199] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0200] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The power transmission safety risk assessment system based on artificial intelligence is characterized by: include: A data acquisition module is used to collect power grid transmission environmental parameters and power grid transmission electrical parameters, and determine the power grid transmission historical data based on artificial intelligence; A data processing module, used to process the power transmission history data of the power grid based on artificial intelligence, and determine the power transmission characteristic data of the power grid based on artificial intelligence; A model building module is used to build an artificial intelligence-based power transmission safety risk assessment model according to the power transmission safety risk assessment requirements; A test optimization module is used to test and optimize the power grid transmission safety risk assessment model to determine the optimal power grid transmission safety risk assessment model; The risk assessment module is used to conduct power grid transmission safety risk assessment on real-time power grid transmission data and determine the power grid transmission safety risk assessment results based on artificial intelligence.

2. The power grid transmission safety risk assessment system based on artificial intelligence according to claim 1 is characterized in that: The data acquisition module comprises: The environmental collection unit is used to collect the historical temperature, humidity and pressure conditions during the power transmission process of the power grid and obtain the power transmission environment parameters of the power grid; The electrical data collection unit is used to collect the historical current, voltage and power conditions during the power transmission process of the power grid and obtain the electrical parameters of the power transmission of the power grid; Among them, based on the power grid transmission environmental parameters and the power grid transmission electrical parameters, the artificial intelligence-based power grid transmission historical data is determined.

3. The power transmission safety risk assessment system based on artificial intelligence according to claim 2 is characterized in that: The data processing module comprises: A data cleaning unit, used to clean historical data of power grid transmission based on artificial intelligence; Obtain historical data on power transmission from the power grid based on artificial intelligence; Clean the historical data of power grid transmission based on artificial intelligence, including: Conduct consistency checks on historical data of power grid transmission based on artificial intelligence; According to the reasonable value range and mutual relationship of each parameter in the power transmission history data of the power grid based on artificial intelligence, check whether the power transmission history data of the power grid based on artificial intelligence meets the requirements; Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the historical data of power grid transmission based on artificial intelligence; Process invalid and missing values ​​of historical data of power grid transmission based on artificial intelligence; Remove invalid and missing data that are of no value to the power transmission safety risk assessment in the historical data of power transmission based on artificial intelligence; Determine the historical data of power grid transmission that is valuable for power grid transmission security risk assessment.

4. The power transmission safety risk assessment system based on artificial intelligence according to claim 3 is characterized in that: The reasonable value range of each parameter in the historical data of power grid transmission based on artificial intelligence is obtained by the following formula: Real-time monitoring of the value of each parameter in the power grid transmission history data; Retrieve all parameter data corresponding to the data type of each parameter; Retrieving a preset first threshold parameter and a second threshold parameter corresponding to the data type in the database; wherein the first threshold parameter is greater than the second threshold parameter, and the first threshold parameter is less than a preset upper limit value of the initial range corresponding to the data type; and the second threshold parameter is greater than a preset lower limit value of the initial range corresponding to the data type; Extract parameter data corresponding to the data type in each unit time, and use the number of parameters corresponding to each unit time as a set of parameter data sets; wherein the value range of the unit time is 3min-5min; Retrieve the numerical value corresponding to each set of parameter data sets, and extract the middle value of the data corresponding to each set of parameter data sets; The data fluctuation coefficient corresponding to the data type of each parameter in the monitored power grid transmission history data is obtained by using the data intermediate value corresponding to each group of parameter data sets; wherein the data fluctuation coefficient is obtained by the following formula: Among them, B represents the data fluctuation coefficient; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X maxi and X mini represents the maximum and minimum values ​​of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X mmax represents the maximum value of the data in the parameter data set corresponding to the maximum value of the data intermediate value; λ represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula: Among them, λ represents the adjustment coefficient; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X zmin Indicates the minimum value of the data middle value appearing in n sets of parameter data sets; The data fluctuation coefficient is used to dynamically adjust the initial range upper limit value and the initial range lower limit value.

5. The power transmission safety risk assessment system based on artificial intelligence according to claim 4 is characterized in that: The data fluctuation coefficient is used to dynamically adjust the initial range upper limit value and the initial range lower limit value, including: Comparing the data fluctuation coefficient with a preset fluctuation coefficient threshold; When the data fluctuation coefficient exceeds a preset fluctuation coefficient threshold, an initial range upper limit value and an initial range lower limit value of the data type corresponding to the data fluctuation coefficient and a preset first threshold parameter and a second threshold parameter corresponding to the data type are retrieved as the first data information; Retrieving the intermediate value of the data parameter corresponding to each set of parameter data sets as the second data information; Using the first data information and the second data information, the initial range upper limit value and the initial range lower limit value are adjusted to obtain an adjusted reasonable value range upper limit value and a reasonable value range lower limit value; Among them, the adjusted upper limit value of the reasonable value range and the lower limit value of the reasonable value range are obtained by the following formula: Among them, X up and X down Respectively represent the upper limit and lower limit of the reasonable value range after adjustment; X up0 and X down0 Respectively represent the upper limit value of the initial range and the lower limit value of the initial range; X y01 and X y02 represents the preset first threshold parameter and second threshold parameter corresponding to the data type respectively; n represents the total number of groups corresponding to the parameter data set; X zi represents the middle value of the data corresponding to the i-th parameter data set; X zmax Indicates the maximum value of the data in the n sets of parameter data sets; X zmin Indicates the minimum value of the data among n sets of parameter data.

6. The power transmission safety risk assessment system based on artificial intelligence according to claim 3 is characterized in that: The data processing module also includes: A data conversion unit, used for converting the cleaned historical data of power transmission of the power grid; Obtaining the historical data of power grid transmission that is valuable for power grid transmission safety risk assessment after cleaning; Convert historical data of power grid transmission that is valuable for power grid transmission safety risk assessment; Eliminate the dimensional differences between historical data of power grid transmission; Determine the historical data of power transmission of power grid with data standardization; A feature extraction unit, used for extracting features from the converted historical data of power grid transmission; Obtaining the converted and standardized historical data of power grid transmission; Extract features from historical power transmission data of power grid with data standardization; Extract features that can reflect the risk assessment of power grid transmission security; Determine the power transmission characteristic data of the power grid based on artificial intelligence.

7. The power transmission safety risk assessment system based on artificial intelligence according to claim 6 is characterized in that: The model building module includes: A data division unit, used for dividing power grid transmission characteristic data based on artificial intelligence; Obtaining AI-based power grid transmission characteristic data; Divide the power transmission characteristic data of the power grid based on artificial intelligence; Determine the training data set and the test data set; Model training unit, used to build an AI-based power grid transmission security risk assessment model; According to the needs of power grid transmission security risk assessment, a neural network model framework suitable for power grid transmission security risk assessment is selected; Based on the training data set, the selected neural network model framework suitable for power grid transmission security risk assessment is trained; Determine an artificial intelligence-based risk assessment model for power grid transmission security.

8. The power transmission safety risk assessment system based on artificial intelligence according to claim 7 is characterized in that: The test optimization module includes: A test and evaluation unit, used to test and evaluate the power grid transmission safety risk assessment model; Obtain an AI-based power grid transmission security risk assessment model; Based on the test data set, the power grid transmission security risk assessment model is tested and evaluated; Determine the test evaluation results based on the power grid transmission security risk assessment model; An adjustment and optimization unit, used to adjust and optimize the power grid transmission safety risk assessment model; Obtain test evaluation results based on the power grid transmission safety risk assessment model; Conduct mining and analysis on the test and evaluation results based on the power grid transmission safety risk assessment model; Determine the parameter adjustment optimization scheme based on the power grid transmission security risk assessment model; Optimize the parameters of the power transmission safety risk assessment model according to the parameter adjustment optimization scheme based on the power transmission safety risk assessment model; Determine the optimal grid transmission security risk assessment model.

9. The power transmission safety risk assessment system based on artificial intelligence according to claim 8 is characterized in that: The risk assessment module includes: A data acquisition unit for acquiring real-time data of power grid transmission based on artificial intelligence; According to the needs of power grid transmission safety risk assessment, the temperature, humidity, pressure, current, voltage and power conditions during power grid transmission are monitored and collected in real time to obtain real-time data on power grid transmission based on artificial intelligence; A risk assessment unit, used to conduct power grid transmission safety risk assessment on real-time power grid transmission data; Obtain the optimal grid transmission security risk assessment model; Inputting AI-based real-time data on power grid transmission into the optimal power grid transmission security risk assessment model; Conduct power grid transmission security risk assessment based on the optimal power grid transmission security risk assessment model for real-time data of power grid transmission based on artificial intelligence; Determine the results of the power grid transmission security risk assessment based on artificial intelligence; Among them, the results of the power grid transmission safety risk assessment based on artificial intelligence include the existence of safety risks in power grid transmission and the absence of safety risks in power grid transmission; When there is a safety risk in power grid transmission, timely warning will be given to the power grid transmission process, and the warning information will be transmitted to the power grid transmission management personnel in real time. Power grid transmission safety management measures will be taken in time to maintain and manage the power grid transmission process. The power grid transmission management personnel can view the real-time power grid transmission safety risk assessment results and power grid transmission safety management and control measures through mobile terminals.

10. A method for assessing power transmission safety risks based on artificial intelligence, implemented based on the power transmission safety risk assessment system based on artificial intelligence as claimed in claim 9, characterized in that: The steps include: S1. Data collection and processing: Collecting historical data of power grid transmission based on artificial intelligence, processing the historical data of power grid transmission based on artificial intelligence, and determining characteristic data of power grid transmission based on artificial intelligence; S2. Model construction and optimization: According to the needs of power grid transmission safety risk assessment, an artificial intelligence-based power grid transmission safety risk assessment model is constructed, and the power grid transmission safety risk assessment model is tested and optimized to determine the optimal power grid transmission safety risk assessment model; S3. Risk assessment and management: Based on the optimal power grid transmission safety risk assessment model, power grid transmission real-time data is used for power grid transmission safety risk assessment, the power grid transmission safety risk assessment results based on artificial intelligence are determined, and power grid transmission safety management measures are taken in time to maintain and manage the power grid transmission process.

Images