Electric power dispatching automation safety detection system and method based on artificial intelligence

Abstract

The invention discloses a power dispatching automation safety detection system and method based on artificial intelligence, relates to the technical field of power safety detection, and solves the problem that power dispatching equipment and power dispatching instructions may be abnormal in actual power dispatching. And the safety risk of the power dispatching system due to abnormity is caused. According to the method, the operation state of the power dispatching equipment is monitored through the real-time operation data of the power dispatching equipment, and when the power dispatching equipment breaks down, the fault type is analyzed, and the fault equipment is checked; calculating the aging degree of the power dispatching equipment; scheduling information is obtained, a scheduling result is detected, and when power scheduling is abnormal, the abnormity is processed; integrating the fault data, the aging degree and the power dispatching abnormal information of the power dispatching equipment into evaluation indexes; the risk coefficient of power dispatching is analyzed, power dispatching is adjusted and optimized, and normal operation of a power dispatching instruction is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the field of electric power safety detection, and relates to electric power dispatching automation safety detection technology, and specifically to an electric power dispatching automation safety detection system and method based on artificial intelligence. Background Art

[0002] Power dispatching automation uses advanced computer technology, communication technology, control technology, etc. to automatically monitor, control and manage the power generation, transmission, transformation, distribution and other links of the power system to achieve safe, economical and high-quality operation of the power system; safety detection plays a vital role in power dispatching automation. Through comprehensive detection of the power dispatching automation system, potential safety hazards can be discovered and eliminated in a timely manner, accidents can be prevented, and the stable operation of the power system can be guaranteed; the power dispatching automation system faces the risk of network attacks; through safety detection, network attacks can be discovered and responded to in a timely manner to protect the system from malicious attacks; the safety detection system can ensure the security and integrity of data in the power dispatching automation system, and prevent security incidents such as data leakage or tampering.

[0003] The prior art (invention patent application with publication number CN107612927A) discloses a security detection method for an electric power dispatching automation system. The method uses attack instances to monitor various attributes of the electric power dispatching automation system, and collects monitoring behavior data generated during the attack process. By comparison, it is determined whether the electric power dispatching automation system is in an abnormal state, which is conducive to determining whether the electric power dispatching automation system is in a vulnerability attack state. When it is determined that the electric power system is in an attacked state, a risk assessment of the security threat to the electric power dispatching automation system can be performed; however, the prior art determines whether the electric power dispatching automation system is in a vulnerability attack state and performs a risk assessment; in actual electric power dispatching, there may also be abnormalities in the electric power dispatching equipment and the electric power dispatching instructions, causing the electric power dispatching system to have security risks due to abnormalities.

[0004] The present invention provides an artificial intelligence-based electric power dispatching automation safety detection system and method to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an artificial intelligence-based electric power dispatching automated safety detection system and method, which is used to solve the technical problem that in actual electric power dispatching, there may still be abnormalities in electric power dispatching equipment and electric power dispatching instructions, causing safety risks in the electric power dispatching system due to abnormalities.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides an artificial intelligence-based power dispatching automation safety detection system, comprising: a safety detection module, and a data acquisition module and a terminal processing module connected thereto; Data acquisition module: collects real-time operation data of power dispatching equipment through data sensors, and pre-processes the real-time operation data to obtain real-time equipment data; the real-time operation data includes equipment number, real-time current, real-time voltage and real-time temperature; Safety detection module: Determine whether the operation of the power dispatching equipment has a fault based on the real-time equipment data; if yes, generate a fault alarm signal and analyze the fault type to obtain fault data; if no, continue to analyze the real-time equipment data; obtain the use information of the power dispatching equipment and analyze the aging degree of the power dispatching equipment; and, Obtain dispatch information, dispatch electricity, and detect the dispatch results after a set time period to obtain detection data; determine whether the power dispatch is normal; if yes, continue to detect the power dispatch; if not, generate a dispatch abnormality signal and record the power dispatch abnormality information; integrate fault data, aging degree and power dispatch abnormality information to obtain evaluation indicators, and evaluate the risk of power dispatch to obtain a risk coefficient; Terminal processing module: inspect and repair power dispatching equipment according to fault alarm signals; replace power dispatching equipment according to the degree of aging; adjust power dispatching based on abnormal dispatching signals; adjust and optimize power dispatching according to risk factors.

[0007] Preferably, the preprocessing of the real-time operation data to obtain the real-time device data includes: Retrieve the real-time operation data and determine whether the device numbers in the real-time operation data are continuous. If yes, analyze the integrity of the real-time data; if no, supplement the corresponding real-time operation data; Determine whether the real-time operation data contains sub-data of all data types; if yes, keep the corresponding real-time operation data; if no, manually complete the real-time operation data; Determine whether the real-time operation data contains duplicate data. If yes, remove the duplicate data; if no, retain the corresponding real-time operation data; The retained real-time operation data and the supplemented real-time operation data are marked as real-time device data.

[0008] It should be noted that when collecting real-time operation data, it is necessary to collect the real-time operation data corresponding to all power equipment to ensure the integrity of the data.

[0009] The present invention pre-processes the collected real-time operation data, analyzes whether to collect the real-time operation data of all power equipment according to the equipment number, analyzes the integrity and repeatability of the real-time operation data, and obtains the real-time equipment data after processing the real-time operation data; the integrity of the data can be guaranteed, and duplicate data can be eliminated, and invalid data can be eliminated, so as to ensure the validity of the analysis data and help improve the efficiency of data processing.

[0010] Preferably, judging whether a fault occurs in the operation of the electric power dispatching equipment according to the real-time equipment data includes: Retrieve real-time device data and obtain the standard range of the real-time device data; match the device number in the real-time device data with the standard range; Determine whether the real-time device data exceeds the standard range; if so, determine that the operation of the corresponding electric power dispatching device fails; if not, determine that the operation of the corresponding electric power dispatching device does not fail.

[0011] It should be noted that, depending on the different device numbers in the real-time device data, the corresponding standard ranges are also different. Therefore, when analyzing the real-time device data, the device numbers in the real-time device data are first matched with the corresponding standard ranges, and then the real-time device data are judged.

[0012] The present invention determines the corresponding standard range according to the equipment number in the real-time equipment data, compares the real-time equipment data with the standard range, and when it exceeds the standard range, determines that the operation of the corresponding electric power dispatching equipment has failed; the electric power dispatching equipment can be inspected in time, laying the foundation for the subsequent analysis of the fault type.

[0013] Preferably, analyzing the fault type to obtain fault data includes: Retrieve the real-time equipment data judged to be faulty, and determine the type of the corresponding power dispatching equipment according to the equipment number in the real-time equipment data; Determine the corresponding fault type library according to the type of electric power dispatching equipment; match the real-time equipment data with the fault type library to obtain the corresponding fault type, and increase the number of faults of the corresponding electric power dispatching equipment by one; integrate the fault type and the number of faults into fault data.

[0014] The present invention determines the corresponding fault type library according to the equipment number in the real-time equipment data, matches the real-time equipment data with the corresponding fault type library to obtain the fault type, and adds one to the number of faults. The fault type can be determined for different types of power dispatching equipment, which is beneficial to improving the accuracy of identifying the fault type and provides a data basis for subsequent fault processing.

[0015] Preferably, the analyzing the aging degree of the electric power dispatching equipment includes: Retrieve the usage information of the power dispatching equipment; mark the service life and the number of failures in the usage information as SNi and GCi respectively; wherein the usage information includes the equipment number, service life and the number of failures; i represents the equipment number; Obtain the service life SMi corresponding to the electric power dispatching equipment; calculate the aging degree LCi corresponding to the electric power dispatching equipment through the formula LCi=α / (SMi-SNi+1)+β×ln(GCi+1); wherein α and β are both proportional coefficients greater than 0.

[0016] The present invention calculates the aging degree of the power dispatching equipment according to the usage information of the equipment, can analyze the aging of the power equipment, and replace the aged equipment in time, which is beneficial to ensure the normal operation of the power dispatching and avoid abnormal power dispatching due to equipment aging.

[0017] Preferably, the scheduling result is detected after the set time period to obtain detection data, including: Retrieve dispatch information; wherein the dispatch information includes dispatch equipment number, dispatch voltage and dispatch current; After setting the time period, real-time data of the corresponding power dispatching equipment is collected and marked as detection data; wherein the real-time data includes real-time voltage and real-time current; the time period is set manually according to the dispatching information.

[0018] It should be noted that the setting of the time period can be determined based on the voltage difference, current difference and power dispatching equipment before and after the call; different power dispatching equipment may set different time periods when facing the same voltage difference and current difference.

[0019] The present invention determines the corresponding power dispatching equipment according to the dispatching equipment number in the dispatching information, detects the real-time data of the power dispatching equipment after a set time period, obtains the detection data, and can analyze the results of power dispatching, laying a foundation for analyzing whether the power dispatching is normal.

[0020] Preferably, the determining whether the power dispatch is normal includes: Retrieve dispatch information and extract detection data of corresponding power dispatch equipment; Determine whether the detection data are consistent with the dispatch information; if yes, the power dispatch is determined to be normal; if not, the power dispatch is determined to be abnormal.

[0021] It should be noted that when the dispatching information contains several dispatching equipment numbers, the detection data of the power dispatching equipment corresponding to the several dispatching equipment numbers need to be compared one by one with the corresponding dispatching information. If the power dispatching of all power dispatching equipment is normal, the power dispatching is normal; otherwise, the power dispatching is abnormal.

[0022] The present invention compares the detection data of the electric power dispatching equipment with the dispatching information. When the detection data is consistent with the dispatching information, the electric power dispatching is normal; otherwise, the electric power dispatching is abnormal. The dispatching result can be analyzed, which is beneficial to ensure the normal operation of the electric power dispatching.

[0023] Preferably, the risk coefficient obtained by evaluating the risk of power dispatching includes: Retrieve the evaluation indicators corresponding to several power dispatching equipment and integrate the evaluation indicators into a risk detection sequence; The risk assessment model is called, and the risk detection sequence is input into the risk assessment model to obtain the risk coefficient; wherein the risk assessment model is constructed based on the artificial intelligence model.

[0024] It should be noted that the evaluation indicators include fault data, aging degree and power dispatching abnormal information; among them, the power dispatching abnormal information includes the abnormal dispatching equipment number and the corresponding number of abnormalities; when integrating into the evaluation indicators, the data of the same power dispatching equipment are integrated to obtain the evaluation indicators of the power dispatching equipment, and several evaluation indicators are integrated to obtain the risk detection sequence.

[0025] The present invention utilizes an artificial intelligence model to analyze the evaluation index data of electric power dispatching equipment and evaluate the risk of electric power dispatching, which can timely evaluate the risk of electric power dispatching and is conducive to making the evaluation results more accurate.

[0026] Preferably, the risk assessment model is constructed based on an artificial intelligence model, including: Obtain standard data that is consistent with the evaluation indicators and risk factor content attributes, and divide the standard data into training sets, validation sets, and test sets; Use the training set to train the artificial intelligence model, and use the validation set and test set to evaluate the trained artificial intelligence model to obtain the evaluation parameters; determine whether the evaluation parameters are greater than the parameter threshold; if yes, mark the artificial intelligence model as a risk assessment model; if not, retrain the artificial intelligence model.

[0027] The second aspect of the present invention provides an artificial intelligence-based power dispatching automation safety detection method, comprising: Step S1: collecting real-time operation data of the power dispatching equipment through data sensors, and preprocessing the real-time operation data to obtain real-time equipment data; Step S2: judging whether the operation of the power dispatching equipment fails according to the real-time equipment data; if yes, generating a fault alarm signal, and analyzing the fault type to obtain fault data; if no, continuously analyzing the real-time equipment data; obtaining the usage information of the power dispatching equipment, and analyzing the aging degree of the power dispatching equipment; Step S3: Obtain dispatch information, dispatch electricity according to the dispatch information, detect the dispatch result after a set time period to obtain detection data; determine whether the power dispatch is normal; if yes, continue to detect the power dispatch; if not, generate a dispatch abnormality signal and record the power dispatch abnormality information; Step S4: Integrate the fault data, aging degree and power dispatch abnormal information to obtain an evaluation index, and evaluate the risk of power dispatch to obtain a risk coefficient; Step S5: Inspect and repair the power dispatching equipment according to the fault alarm signal; replace the power dispatching equipment according to the degree of aging; adjust the power dispatching based on the abnormal dispatching signal; adjust and optimize the power dispatching according to the risk factor.

[0028] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention pre-processes the collected real-time operation data, analyzes whether the real-time operation data of all power equipment is collected according to the equipment number, analyzes the integrity and repeatability of the real-time operation data, and obtains the real-time equipment data after processing the real-time operation data; it can ensure the integrity of the data, eliminate duplicate data, eliminate invalid data, ensure the validity of the analysis data, and help improve the efficiency of data processing; determine the corresponding standard range according to the equipment number in the real-time equipment data, compare the real-time equipment data with the standard range, and when it exceeds the standard range, it is determined that the operation of the corresponding power dispatching equipment fails; determine the corresponding fault type library according to the equipment number in the real-time equipment data, match the real-time equipment data with the corresponding fault type library to obtain the fault type, and add one to the number of faults, so as to determine the fault type for different types of power dispatching equipment, which is conducive to improving the accuracy of identifying the fault type.

[0029] 2. The present invention calculates the aging degree of the electric power dispatching equipment according to the usage information of the equipment, can analyze the aging of the electric power equipment, and replace the aged equipment in time, which is beneficial to ensure the normal operation of the electric power dispatching and avoid abnormal electric power dispatching due to equipment aging; according to the dispatching equipment number in the dispatching information, the corresponding electric power dispatching equipment is determined according to the dispatching equipment number, and the real-time data of the electric power dispatching equipment is detected after a set time period to obtain the detection data, which can analyze the result of the electric power dispatching, laying the foundation for analyzing whether the electric power dispatching is normal; the detection data of the electric power dispatching equipment is compared with the dispatching information, and when the detection data is consistent with the dispatching information, the electric power dispatching is normal; otherwise, the electric power dispatching is abnormal; the dispatching results can be analyzed, which is beneficial to ensure the normal operation of the electric power dispatching; the evaluation index data of the electric power dispatching equipment is analyzed by using an artificial intelligence model, and the risk of the electric power dispatching is evaluated, which can evaluate the risk of the electric power dispatching in time, which is beneficial to make the evaluation result more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] 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.

[0031] Figure 1 A schematic diagram of the overall steps of the system of the present invention; Figure 2 A schematic diagram of the detection steps of the power dispatching equipment of the system of the present invention; Figure 3 A schematic diagram of the power dispatching instructions and risk assessment steps of the present invention; Figure 4 It is a schematic diagram of the specific steps of the method of the present invention. DETAILED DESCRIPTION

[0032] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] See also Figure 1 , the first aspect of the present invention provides an artificial intelligence-based power dispatching automation safety detection system and method, including: a safety detection module, and a data acquisition module and a terminal processing module connected thereto; Data acquisition module: collects real-time operation data of power dispatching equipment through data sensors, and pre-processes the real-time operation data to obtain real-time equipment data; the real-time operation data includes equipment number, real-time current, real-time voltage and real-time temperature; Safety detection module: Determine whether the operation of the power dispatching equipment has a fault based on the real-time equipment data; if yes, generate a fault alarm signal and analyze the fault type to obtain fault data; if no, continue to analyze the real-time equipment data; obtain the use information of the power dispatching equipment and analyze the aging degree of the power dispatching equipment; and, Obtain dispatch information, dispatch electricity according to the dispatch information, and detect the dispatch results after a set time period to obtain detection data; determine whether the power dispatch is normal; if yes, continue to detect the power dispatch; if not, generate a dispatch abnormality signal and record the power dispatch abnormality information; integrate fault data, aging degree and power dispatch abnormality information to obtain evaluation indicators, and evaluate the risk of power dispatch to obtain a risk coefficient; Terminal processing module: inspect and repair power dispatching equipment according to fault alarm signals; replace power dispatching equipment according to the degree of aging; adjust power dispatching based on abnormal dispatching signals; adjust and optimize power dispatching according to risk factors.

[0034] See also Figure 2 , collect real-time operation data of power dispatching equipment through data sensors, and judge whether the equipment numbers in the real-time operation data are continuous. If yes, analyze the integrity of the real-time data; if no, supplement the corresponding real-time operation data; judge whether the real-time operation data contains sub-data of all data types; if yes, retain the corresponding real-time operation data; if no, manually supplement the real-time operation data; judge whether the real-time operation data contains repeated data, if yes, remove the repeated data; if no, retain the corresponding real-time operation data; mark the retained real-time operation data and the supplemented real-time operation data as real-time equipment data.

[0035] For example: Assume that there are 5 existing power dispatching devices, and collect real-time operation data of the power dispatching devices at time T1; collect 5 sets of real-time operation data, analyze the real-time operation data according to the device number, and find that the real-time operation data of the power dispatching device 4 is missing, and supplement the real-time operation data of the power dispatching device 4 to obtain 6 sets of data; The integrity of the six sets of data was evaluated separately. If it was found that the electric power dispatching equipment 2 was missing real-time current data, the real-time current data was supplemented. The six sets of data were tested and it was found that there were two sets of duplicate real-time operation data of the electric power dispatching equipment 3. One of the sets of real-time operation data was eliminated, and five sets of real-time operation data were obtained. The five sets of real-time operation data were marked as real-time equipment data.

[0036] Obtain the standard range of real-time equipment data; match the equipment number in the real-time equipment data with the standard range; determine whether the real-time equipment data exceeds the standard range; if yes, generate a fault alarm signal, and analyze the fault type to obtain fault data; if no, continue to analyze the real-time equipment data; retrieve the real-time equipment data determined to be faulty, and determine the type of the corresponding electric power dispatching equipment according to the equipment number in the real-time equipment data; determine the corresponding fault type library according to the type of the electric power dispatching equipment; match the real-time equipment data with the fault type library to obtain the corresponding fault type, and increase the number of faults of the corresponding electric power dispatching equipment by one; integrate the fault type and the number of faults into fault data; inspect and repair the electric power dispatching equipment according to the fault alarm signal.

[0037] For example: suppose that a fault analysis is performed on 5 power dispatching devices, and the corresponding standard range is obtained according to the number analysis of the power dispatching devices. The real-time device data of the 5 power dispatching devices are analyzed respectively, and it is obtained that the real-time device data of power dispatching device 3 and power dispatching device 5 exceed the standard range; then the fault types of power dispatching device 3 and power dispatching device 5 are analyzed; Determine the corresponding fault type libraries 3 and 5 according to the equipment numbers of the power dispatching equipment 3 and the power dispatching equipment 5; match the real-time equipment data of the power dispatching equipment 3 with the fault type library 3 to obtain the fault type B; increase the number of faults by one to 4 times; match the real-time equipment data of the power dispatching equipment 5 with the fault type library 5 to obtain the fault type R; increase the number of faults by one to 3 times; inspect and repair the power dispatching equipment 3 and the power dispatching equipment 5 according to the fault type.

[0038] See also Figure 3 , obtain the usage information of the power dispatching equipment, and mark the service life and number of failures in the usage information as SNi and GCi respectively; wherein the usage information includes the equipment number, service life and number of failures; i represents the equipment number; obtain the service life SMi corresponding to the power dispatching equipment; calculate the aging degree LCi corresponding to the power dispatching equipment through the formula LCi=α / (SMi-SNi+1)+β×ln(GCi+1); wherein α and β are both proportional coefficients greater than 0; replace the power dispatching equipment according to the aging degree.

[0039] For example, suppose that the aging degree of power dispatching equipment 3 and power dispatching equipment 5 is calculated, α=10; β=10; the specific process is as follows: Power dispatching equipment 3: service life SN3 = 12 years; number of failures GC3 = 4 times; service life SM3 = 15 years; then the aging degree LC3 = 4.11; Power dispatching equipment 5: service life SN5 = 8 years; number of failures GC5 = 3 times; service life SM5 = 20 years; then the aging degree LC5 = 2.16; The power dispatching equipment 3 is replaced according to the aging degree, and the aging degree of the power dispatching equipment 5 is calculated regularly.

[0040] It should be noted that the steps for analyzing the aging degree of other power dispatching equipment are consistent with the steps in the above example. When performing the analysis, the aging degree of each power dispatching equipment needs to be calculated.

[0041] Obtain dispatch information, and dispatch electricity according to the dispatch information; after setting a time period, collect real-time data of the corresponding power dispatch equipment, and mark the real-time data as detection data; determine whether the detection data is consistent with the dispatch information; if yes, continue to detect the power dispatch; if not, generate a dispatch abnormality signal and record the power dispatch abnormality information; adjust the power dispatch based on the abnormal dispatch signal.

[0042] For example, assuming that two sets of dispatch information are currently obtained, the power is dispatched according to the two sets of dispatch information; the two sets of dispatch information are analyzed respectively, and the specific steps are as follows: The first group of dispatch information: adjust the voltage of the power dispatch device 2 to V1 and the current to I1; detect the real-time voltage and real-time current of the power dispatch device after 3 minutes; if the real-time data is consistent with the dispatch information, the dispatch of the power dispatch device 2 is normal; The second group of dispatch information: adjust the voltage of the power dispatch device 4 to V2, and the current remains unchanged; detect the real-time voltage and real-time current of the power dispatch device after 1 minute; if the real-time voltage is consistent with the dispatch information, but the real-time current has changed, the dispatch of the power dispatch device 4 is abnormal; Based on the above, it can be concluded that the power dispatch is abnormal.

[0043] Integrate fault data, aging degree and power dispatch abnormal information to obtain evaluation indicators, and integrate several evaluation indicators into a risk detection sequence; call the risk assessment model, input the risk detection sequence into the risk assessment model to obtain the risk coefficient; adjust and optimize the power dispatch according to the risk coefficient.

[0044] It should be noted that the fault data is obtained from the database, and the fault data of all power dispatching equipment must be integrated; the power abnormality information is classified according to the number of the power dispatching equipment, and the power abnormality information of the same power dispatching equipment is integrated into a set of evaluation indicators.

[0045] It is worth noting that the risk assessment model is built based on the artificial intelligence model, and the specific steps are as follows: Obtain standard data that is consistent with the evaluation indicators and risk factor content attributes, and divide the standard data into training sets, validation sets, and test sets; Use the training set to train the artificial intelligence model, and use the validation set and test set to evaluate the trained artificial intelligence model to obtain the evaluation parameters; determine whether the evaluation parameters are greater than the parameter threshold; if yes, mark the artificial intelligence model as a risk assessment model; if not, retrain the artificial intelligence model.

[0046] For example: suppose that the fault data, aging degree and abnormal information of power dispatching of 5 power dispatching equipment are integrated to obtain 5 groups of evaluation indicators; the 5 groups of evaluation indicators are arranged and integrated in the order of equipment numbers to obtain a risk detection sequence; The risk assessment model is called and the risk detection sequence is input into the risk assessment model. The risk coefficient is 34, which means that the risk coefficient of power dispatch is low and only some equipment needs to be adjusted.

[0047] See also Figure 4 The second aspect of the present invention provides an artificial intelligence-based power dispatching automation safety detection method, comprising: Step S1: collecting real-time operation data of the power dispatching equipment through data sensors, and preprocessing the real-time operation data to obtain real-time equipment data; Step S2: judging whether the operation of the power dispatching equipment fails according to the real-time equipment data; if yes, generating a fault alarm signal, and analyzing the fault type to obtain fault data; if no, continuously analyzing the real-time equipment data; obtaining the usage information of the power dispatching equipment, and analyzing the aging degree of the power dispatching equipment; Step S3: Obtain dispatch information, dispatch electricity according to the dispatch information, detect the dispatch result after a set time period to obtain detection data; determine whether the power dispatch is normal; if yes, continue to detect the power dispatch; if not, generate a dispatch abnormality signal and record the power dispatch abnormality information; Step S4: Integrate the fault data, aging degree and power dispatch abnormal information to obtain an evaluation index, and evaluate the risk of power dispatch to obtain a risk coefficient; Step S5: Inspect and repair the power dispatching equipment according to the fault alarm signal; replace the power dispatching equipment according to the degree of aging; adjust the power dispatching based on the abnormal dispatching signal; adjust and optimize the power dispatching according to the risk factor.

[0048] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0049] Working principle of the present invention: The present invention collects real-time operation data of electric power dispatching equipment through data sensors, pre-processes the real-time operation data to obtain real-time equipment data; judges whether the operation of the electric power dispatching equipment fails according to the real-time equipment data; if yes, generates a fault alarm signal, and analyzes the fault type to obtain fault data; if no, continuously analyzes the real-time equipment data; obtains the use information of the electric power dispatching equipment, analyzes the aging degree of the electric power dispatching equipment; inspects and repairs the electric power dispatching equipment according to the fault alarm signal; replaces the electric power dispatching equipment according to the aging degree; The present invention obtains dispatching information, dispatches electricity according to the dispatching information, detects the dispatching result after a set time period to obtain detection data; determines whether the power dispatching is normal; if yes, continuously detects the power dispatching; if not, generates a dispatching abnormality signal and records the power dispatching abnormality information; integrates fault data, aging degree and power dispatching abnormality information to obtain evaluation indicators, evaluates the risk of power dispatching to obtain a risk coefficient; adjusts the power dispatching based on the abnormal dispatching signal; and adjusts and optimizes the power dispatching according to the risk coefficient.

[0050] 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. Power dispatching automation safety detection system based on artificial intelligence, include: The safety detection module, and the data acquisition module and terminal processing module connected thereto are characterized in that: Data acquisition module: collects real-time operation data of power dispatching equipment through data sensors, and pre-processes the real-time operation data to obtain real-time equipment data; the real-time operation data includes equipment number, real-time current, real-time voltage and real-time temperature; Safety detection module: Determine whether the operation of the power dispatching equipment has a fault based on the real-time equipment data; if yes, generate a fault alarm signal and analyze the fault type to obtain fault data; if no, continue to analyze the real-time equipment data; obtain the use information of the power dispatching equipment and analyze the aging degree of the power dispatching equipment; and, Obtain dispatch information, dispatch electricity, and detect the dispatch results after a set time period to obtain detection data; determine whether the power dispatch is normal; if yes, continue to detect the power dispatch; if not, generate a dispatch abnormality signal and record the power dispatch abnormality information; integrate fault data, aging degree and power dispatch abnormality information to obtain evaluation indicators, and evaluate the risk of power dispatch to obtain a risk coefficient; Terminal processing module: inspect and repair power dispatching equipment according to fault alarm signals; replace power dispatching equipment according to the degree of aging; adjust power dispatching based on abnormal dispatching signals; adjust and optimize power dispatching according to risk factors.

2. According to the artificial intelligence-based power dispatching automation safety detection system of claim 1, It is characterized in that The preprocessing of the real-time operation data to obtain the real-time device data includes: Retrieve the real-time operation data and determine whether the device numbers in the real-time operation data are continuous. If yes, analyze the integrity of the real-time data; if no, supplement the corresponding real-time operation data; Determine whether the real-time operation data contains sub-data of all data types; if yes, keep the corresponding real-time operation data; if no, manually complete the real-time operation data; Determine whether the real-time operation data contains duplicate data. If yes, remove the duplicate data; if no, retain the corresponding real-time operation data; The retained real-time operation data and the supplemented real-time operation data are marked as real-time device data.

3. According to the artificial intelligence-based power dispatching automation safety detection system according to claim 2, It is characterized in that The determining whether a fault occurs in the operation of the electric power dispatching equipment according to the real-time equipment data includes: Retrieve real-time device data and obtain the standard range of the real-time device data; match the device number in the real-time device data with the standard range; Determine whether the real-time device data exceeds the standard range; if so, determine that the operation of the corresponding electric power dispatching device fails; if not, determine that the operation of the corresponding electric power dispatching device does not fail.

4. According to the artificial intelligence-based power dispatching automation safety detection system of claim 3, It is characterized in that The analyzing the fault type to obtain fault data includes: Retrieve the real-time equipment data judged to be faulty, and determine the type of the corresponding power dispatching equipment according to the equipment number in the real-time equipment data; Determine the corresponding fault type library according to the type of electric power dispatching equipment; match the real-time equipment data with the fault type library to obtain the corresponding fault type, and increase the number of faults of the corresponding electric power dispatching equipment by one; integrate the fault type and the number of faults into fault data.

5. According to the artificial intelligence-based power dispatching automation safety detection system of claim 1, It is characterized in that The analysis of the aging degree of the electric power dispatching equipment includes: Retrieve the usage information of the power dispatching equipment; mark the service life and the number of failures in the usage information as SNi and GCi respectively; wherein the usage information includes the equipment number, service life and the number of failures; i represents the equipment number; Obtain the service life SMi corresponding to the electric power dispatching equipment; calculate the aging degree LCi corresponding to the electric power dispatching equipment through the formula LCi=α / (SMi-SNi+1)+β×ln(GCi+1); wherein α and β are both proportional coefficients greater than 0.

6. According to claim 1, the power dispatching automation safety detection system based on artificial intelligence, It is characterized in that After the set time period, the scheduling result is detected to obtain detection data, including: Retrieve dispatch information; wherein the dispatch information includes dispatch equipment number, dispatch voltage and dispatch current; After setting the time period, real-time data of the corresponding power dispatching equipment is collected and marked as detection data; wherein the real-time data includes real-time voltage and real-time current; the time period is set manually according to the dispatching information.

7. According to the artificial intelligence-based power dispatching automation safety detection system of claim 6, It is characterized in that The determining whether the power dispatch is normal includes: Retrieve dispatch information and extract detection data of corresponding power dispatch equipment; Determine whether the detection data are consistent with the dispatch information; if yes, the power dispatch is determined to be normal; if not, the power dispatch is determined to be abnormal.

8. According to the artificial intelligence-based power dispatching automation safety detection system of claim 1, It is characterized in that The risk coefficient obtained by evaluating the risk of power dispatching includes: Retrieve the evaluation indicators corresponding to several power dispatching equipment and integrate the evaluation indicators into a risk detection sequence; The risk assessment model is called, and the risk detection sequence is input into the risk assessment model to obtain the risk coefficient; wherein the risk assessment model is constructed based on the artificial intelligence model.

9. According to the artificial intelligence-based power dispatching automation safety detection system of claim 8, It is characterized in that The risk assessment model is constructed based on an artificial intelligence model and includes: Obtain standard data that is consistent with the evaluation indicators and risk factor content attributes, and divide the standard data into training sets, validation sets, and test sets; Use the training set to train the artificial intelligence model, and use the validation set and test set to evaluate the trained artificial intelligence model to obtain the evaluation parameters; determine whether the evaluation parameters are greater than the parameter threshold; if yes, mark the artificial intelligence model as a risk assessment model; if not, retrain the artificial intelligence model.

10. An artificial intelligence-based power dispatching automation safety detection method, applied to an artificial intelligence-based power dispatching automation safety detection system as described in any one of claims 1 to 9, It is characterized in that include: Step S1: collecting real-time operation data of the power dispatching equipment through data sensors, and preprocessing the real-time operation data to obtain real-time equipment data; Step S2: judging whether the operation of the electric power dispatching equipment fails according to the real-time equipment data; if yes, generating a fault alarm signal, and analyzing the fault type to obtain fault data; if no, continuously analyzing the real-time equipment data; obtaining the usage information of the electric power dispatching equipment, and analyzing the aging degree of the electric power dispatching equipment according to the usage information; Step S3: Obtain dispatch information, dispatch electricity according to the dispatch information, and detect the dispatch result after a set time period to obtain detection data; determine whether the power dispatch is normal based on the detection data; if yes, continue to detect the power dispatch; if not, generate a dispatch abnormality signal and record the power dispatch abnormality information; Step S4: Integrate the fault data, aging degree and power dispatch abnormality information to obtain evaluation indicators, and evaluate the risk of power dispatch according to the evaluation indicators to obtain a risk coefficient; Step S5: Inspect and repair the power dispatching equipment according to the fault alarm signal; replace the power dispatching equipment according to the degree of aging; and adjust the power dispatching based on the abnormal dispatching signal.

Images