A large-scale model-based intelligent management and decision-making system for power grid faults

Abstract

The invention discloses a large-model-based intelligent management decision system for power grid faults, which relates to the technical field of power grid fault decision-making, and comprises: a closing data detection module, which obtains electrical values, obtains equipment values, obtains hardware safety factors through electrical values ​​and equipment values, obtains personnel risk values, obtains execution values, and obtains personnel safety factors through personnel risk values ​​and execution values; obtains a protection factor by combining the electrical equipment status with the maintenance personnel situation, and then determines whether to close the circuit breaker through the protection factor and a preset threshold value of the protection factor, thereby facilitating a comprehensive judgment of the safety risk after closing the circuit breaker, and further facilitating risk assessment for management personnel before closing the circuit breaker, and further facilitating decision-making assistance for the management personnel's closing operation, and establishing a risk closing database to facilitate recording of data for each closing decision, and further facilitating the decision-making system to optimize and adjust the decision according to historical data.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid fault decision-making, and in particular to a power grid fault intelligent management decision-making system based on a large model. Background Art

[0002] The power grid fault decision system is an advanced intelligent solution dedicated to ensuring the stable operation of the power grid. When a power grid fault occurs, it can respond quickly and accurately determine the location, type and severity of the fault through precise analysis of a large amount of real-time data. Using advanced algorithms and models, the power grid fault decision system can generate the optimal fault handling solution in a short time, guide maintenance personnel to carry out emergency repairs quickly and efficiently, and minimize the impact of faults on power supply. It not only improves the reliability and safety of the power grid, but also improves the efficiency of fault handling, providing continuous and stable power guarantee for people's production and life.

[0003] Today's power grid fault decision-making systems are mostly integrated through the linkage of the power grid fault diagnosis association system and the big model. The two-way data flow between the fault diagnosis association and the big model system is realized through the general interface and data interaction. The association system transmits the real-time monitoring data and the preliminary results of the fault diagnosis to the big model. The big model feeds back the optimized disposal decision and supplementary fault analysis information to the association system. Then, by establishing a collaborative working mechanism, when the association system detects signs of faults that trigger the big model, both parties start the workflow synchronously. Based on knowledge understanding and reasoning, the big model combines the real-time data details provided by the association system, such as the instantaneous current and voltage waveform data of the fault, to further refine the fault diagnosis and disposal plan. Finally, the association system performs corresponding control operations based on the decision recommendations of the big model, such as remote tripping, switching of backup lines, etc., and feeds back the operation results to the big model in real time, so that the model can continuously optimize subsequent decisions, realize closed-loop linkage, and ensure the stable operation of the power grid.

[0004] The existing power grid fault decision-making system still has some defects. When judging whether to close the circuit breaker and restart the power grid after a short circuit fault, due to the wide coverage area of ​​the power grid, the large number of maintenance personnel involved, and the large number of electrical equipment involved, if the power grid is restarted rashly, it will not only easily cause secondary impact damage to the electrical equipment that has not been fully repaired, but also easily cause the maintenance personnel to be electrocuted. In addition, there is no timely feedback on the results of the decision-making system after the power grid fault decision-making process, which affects the autonomous learning and optimization ability of the decision-making system, and further affects the accurate judgment of the subsequent intelligent decision-making of the decision-making system. To this end, we propose a power grid fault intelligent management decision-making system based on a large model. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the deficiencies in the prior art, the present invention provides a large-model-based intelligent management decision system for power grid faults to solve the above-mentioned problems in the prior art.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a large model-based power grid fault intelligent management decision system, comprising:

[0009] The closing data detection module obtains electrical values, obtains equipment values, obtains hardware safety factors through electrical values ​​and equipment values, obtains personnel risk values, obtains execution values, and obtains personnel safety factors through personnel risk values ​​and execution values;

[0010] The closing decision judgment module obtains the security factor through the hardware safety factor and the personnel safety factor, sets the preset threshold of the security factor, judges whether to close the circuit breaker through the security factor and the preset threshold of the security factor, establishes a risk closing database, and stores the security factor and the closing judgment result in the risk closing database;

[0011] The closing feedback optimization module obtains the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing. The closing score is obtained according to the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing, and the value of the protection coefficient is adjusted according to the closing score.

[0012] Preferably, the electrical value is obtained in the closing data detection module, specifically:

[0013] Step 1: obtaining the pre-fault voltage of the power grid, obtaining the post-fault voltage of the power grid, obtaining a voltage value by taking the absolute value of the post-fault voltage and the pre-fault voltage, setting a voltage preset threshold, obtaining a voltage difference by taking the difference of the voltage preset threshold and the post-fault voltage, and obtaining a voltage reference value by summing the voltage value and the voltage difference;

[0014] Step 2: Obtain the insulation resistance of the power grid, set a preset insulation resistance threshold, and obtain an insulation resistance reference value by subtracting the preset insulation resistance threshold from the insulation resistance;

[0015] Step 3: Obtain the fault current of the power grid, set a preset fault current threshold, and obtain a fault current reference value by subtracting the preset fault current threshold from the fault current;

[0016] Step 4: Obtain the electrical value through the fault current reference value, voltage reference value and insulation resistance reference value of the power grid;

[0017] The electrical value is calculated as follows:

[0018] ;

[0019] Among them, Dq represents the electrical value, Gz represents the fault current reference value, Dy represents the voltage reference value, and Dz represents the insulation resistance reference value. , and are weights, , , .

[0020] Preferably, the device value is obtained in the closing data detection module, specifically:

[0021] Step 1: Take photos of the appearance of each electrical device in the power grid to obtain multiple reference pictures. Use the AOI system to identify the burnt, cracked and deformed electrical devices in each reference picture, and mark the number of defects of each electrical device.

[0022] Step 2: Obtain the temperature of each electrical device, and obtain the device value through the temperature of each electrical device and the number of defects of the corresponding electrical device;

[0023] The device value is calculated as follows:

[0024] ;

[0025] Where Bs represents the equipment value, Wd represents the temperature of the electrical equipment, Qx represents the number of defects of the electrical equipment, and n represents the number of electrical equipment. .

[0026] Preferably, the calculation method of the hardware safety factor in the closing data detection module is specifically as follows:

[0027] ;

[0028] Among them, Yj represents the hardware safety factor, Dq represents the electrical value, and Bs represents the device value. and are weights, , .

[0029] Preferably, the personnel risk value is obtained in the closing data detection module, specifically:

[0030] Step 1: Obtain the working hours of each maintenance personnel, obtain the number of historical operation accidents of each maintenance personnel, obtain the reference number of accidents by summing the number of historical operation accidents of each maintenance personnel and 1, obtain the experience value of each maintenance personnel by dividing the working hours of each maintenance personnel by the reference number of accidents, and sum and average the experience values ​​of each maintenance personnel to obtain the maintenance personnel value;

[0031] Step 2: Obtain the grounding resistance before the accident, obtain the grounding resistance after the accident, and obtain the absolute value of the difference between the grounding resistance before the accident and the grounding resistance after the accident to obtain the grounding resistance change value;

[0032] Step 3: The grounding resistance value is obtained by summing the grounding resistance change value and 1, and the personnel risk value is obtained by taking the weighted quotient of the maintenance personnel value and the grounding resistance value.

[0033] Preferably, the execution value is obtained in the closing data detection module, specifically:

[0034] Step 1: The maintenance personnel goes to repair the electrical equipment and presses the maintenance button before leaving the office to start the timing. After the maintenance, the maintenance personnel returns to the office and presses the maintenance button to end the timing. The maintenance time is obtained through the timing.

[0035] Step 2: Get the time when the maintenance button is pressed for the second time, get the current time, and get the interval time by subtracting the current time from the time when the maintenance button is pressed for the second time;

[0036] Step 3: Obtain the execution status of the second maintenance button pressing. If the execution status of the second maintenance button pressing is pressed, execute step 4. If the execution status of the second maintenance button pressing is not pressed, execute step 2.

[0037] Step 4: Get the maintenance time, set the preset threshold of the maintenance time, obtain the maintenance reference time by subtracting the maintenance time from the preset threshold of the maintenance time, get the interval time, get the interval reference time by summing the interval time and 1, and get the execution value by dividing the maintenance reference time by the interval reference time.

[0038] Preferably, the calculation method of the personnel safety factor in the closing data detection module is specifically as follows:

[0039] ;

[0040] Among them, Ry represents the personnel safety factor, Rf represents the personnel risk value, and Zx represents the execution value. and are weights, , .

[0041] Preferably, in the closing decision judgment module, a security factor is obtained by using the hardware safety factor and the personnel safety factor, a preset threshold of the security factor is set, and whether to close the circuit breaker is determined by using the security factor and the preset threshold of the security factor, specifically:

[0042] Step 1: Obtain the hardware safety factor, set the hardware safety factor weight, obtain the hardware safety reference factor by multiplying the hardware safety factor weight by the hardware safety factor, obtain the personnel safety factor, set the personnel safety factor weight, obtain the personnel safety reference factor by multiplying the personnel safety factor by the personnel safety factor weight, and obtain the protection factor by summing the hardware safety reference factor and the personnel safety reference factor;

[0043] Step 2: Set the preset threshold of the security factor, determine the relationship between the security factor and the preset threshold of the security factor, if the security factor is greater than or equal to the preset threshold of the security factor, it is recommended to execute the grid closing, if the security factor is less than the preset threshold of the security factor, it is recommended to confirm the safety of the grid closing and repeat the measurement of the security factor.

[0044] Preferably, in the feedback incentive optimization module, a closing score is obtained according to the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing, specifically:

[0045] Step 1: Obtain the number of electrical equipment burnouts after closing the circuit breaker, obtain the safety feedback of personnel after closing the circuit breaker, and obtain the number of dangerous accidents through the safety feedback of personnel before and after closing the circuit breaker;

[0046] Step 2: Set a preset threshold value for the maintenance time, and obtain the continuous operation time of the power grid after closing. If the continuous operation time of the power grid after closing is greater than or equal to the preset threshold value for the maintenance time, the operation state of the power grid after closing is recorded as 1; if the continuous operation time of the power grid after closing is less than the preset threshold value for the maintenance time, the operation state of the power grid after closing is recorded as 0;

[0047] Step 3: Obtain the post-gate coefficient by weighted summing the number of electrical equipment burnouts and the number of dangerous accidents, set a preset threshold for the closing score, obtain the post-gate score by multiplying the post-gate coefficient by the preset threshold for the closing score, and obtain the closing score by multiplying the post-gate score by the operating status of the power grid after closing.

[0048] Preferably, in the feedback incentive optimization module, the value of the protection factor is adjusted according to the closing score, specifically:

[0049] Step 1: Set the preset threshold of the hardware safety factor weight, set the preset threshold of the personnel safety factor weight, and obtain the closing score;

[0050] Step 2: Determine whether the closing score is 0. If the closing score is 0, the hardware safety factor weight is subtracted from the preset threshold of the hardware safety factor weight to obtain the hardware safety factor quadratic weight when the assurance factor is measured next time. The hardware safety factor is multiplied by the hardware safety factor and the hardware safety factor quadratic weight to obtain the hardware safety reference factor. The personnel safety factor weight is subtracted from the preset threshold of the personnel safety factor weight to obtain the personnel safety reference factor. The personnel safety factor is multiplied by the personnel safety factor and the personnel safety factor quadratic weight to obtain the personnel safety reference factor. The assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the closing score is not 0, execute step 3.

[0051] Step 3: Set a preset threshold value for the number of electrical equipment burnouts, and determine whether the number of electrical equipment burnouts is greater than the preset threshold value for the number of electrical equipment burnouts. If the number of electrical equipment burnouts is greater than or equal to the preset threshold value for the number of electrical equipment burnouts, then the personnel safety factor weight is subtracted from the personnel safety factor weight preset threshold value when the assurance factor is measured next time to obtain the personnel safety factor quadratic weight, and the personnel safety reference factor is obtained by multiplying the personnel safety factor by the personnel safety factor quadratic weight, and the assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the number of electrical equipment burnouts is less than the preset threshold value for the number of electrical equipment burnouts, execute step 4:

[0052] Step 4: Set a preset threshold for the number of dangerous accidents, and determine whether the number of dangerous accidents is greater than or equal to the preset threshold. If the number of dangerous accidents is greater than or equal to the preset threshold, then the next time the assurance factor is measured, the hardware safety factor weight is subtracted from the preset threshold of the hardware safety factor weight to obtain the hardware safety factor quadratic weight. The hardware safety reference factor is obtained by multiplying the hardware safety factor by the hardware safety factor quadratic weight. The assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the number of dangerous accidents is less than the preset threshold, the assurance factor value remains unchanged and is fed back to the management personnel.

[0053] (III) Beneficial effects

[0054] The present invention provides a large-scale model-based intelligent management and decision-making system for power grid faults, which has the following beneficial effects:

[0055] In the closing decision judgment module, this solution obtains the protection factor by combining the status of electrical equipment and the situation of maintenance personnel, and then determines whether to close the circuit breaker based on the protection factor and the preset threshold of the protection factor, so as to facilitate a comprehensive judgment of the safety risk after closing the circuit breaker, and then facilitate risk assessment for management personnel before closing the circuit breaker, and then facilitate decision-making assistance for management personnel's closing operations. By establishing a risk closing database, it is convenient to record the data of each closing decision, and then facilitate the decision-making system to optimize and adjust the decision according to historical data.

[0056] In the closing feedback optimization module, this solution scores the closing decision by collecting the equipment status, maintenance personnel status and grid operation status after closing. The closing score facilitates a comprehensive judgment on the estimated accuracy of the closing decision, and then adjusts the value and calculation method of the protection coefficient according to the result of the closing score, so as to further reduce the risk of closing failure in the next closing decision, thereby further ensuring the safety of electrical equipment and maintenance personnel, and facilitating targeted adjustment of the closing decision according to the historical closing situation, so as to provide more accurate closing decision suggestions to management personnel at the next closing operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a structural schematic diagram of a large-model-based power grid fault intelligent management decision-making system of the present invention;

[0058] Figure 2 The present invention is a flowchart of a large-model-based intelligent management and decision-making system for power grid faults. DETAILED DESCRIPTION

[0059] 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.

[0060] See also Figure 1-Figure 2 The present invention provides a large-model-based intelligent management and decision-making system for power grid faults, comprising the following modules:

[0061] The closing data detection module obtains electrical values, obtains equipment values, obtains hardware safety factors through electrical values ​​and equipment values, obtains personnel risk values, obtains execution values, and obtains personnel safety factors through personnel risk values ​​and execution values;

[0062] The closing decision judgment module obtains the security factor through the hardware safety factor and the personnel safety factor, sets the preset threshold of the security factor, judges whether to close the circuit breaker through the security factor and the preset threshold of the security factor, establishes a risk closing database, and stores the security factor and the closing judgment result in the risk closing database;

[0063] The closing feedback optimization module obtains the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing. The closing score is obtained according to the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing, and the value of the protection coefficient is adjusted according to the closing score.

[0064] The calculation method of the hardware safety factor in the closing data detection module is as follows:

[0065] ;

[0066] Among them, Yj represents the hardware safety factor, Dq represents the electrical value, and Bs represents the device value. and are weights, , ;

[0067] The calculation method of the personnel safety factor in the closing data detection module is as follows:

[0068] ;

[0069] Among them, Ry represents the personnel safety factor, Rf represents the personnel risk value, and Zx represents the execution value. and are weights, , .

[0070] In this embodiment, in the closing data detection module, this solution judges whether there is a risk in continuing to work after closing the electrical equipment by combining the current state and damage of the electrical equipment, and then judges whether there is a risk after closing the maintenance personnel by combining the experience state of the power grid maintenance personnel and the operation state during the maintenance process. The maintenance progress and maintenance situation of the maintenance personnel are combined to determine whether there is a risk after closing the circuit, so as to facilitate the subsequent comprehensive decision-making based on the electrical equipment state and maintenance state before the power grid is closed to determine whether to recommend closing the circuit, which is beneficial to avoid secondary impact damage to the electrical equipment after rash closing, and also helps to avoid risk accidents such as electric shock caused by maintenance personnel not evacuating in time;

[0071] In the closing decision judgment module, this solution obtains the protection factor by combining the electrical equipment status and the maintenance personnel situation, and then determines whether to close the circuit breaker based on the protection factor and the preset threshold of the protection factor, so as to facilitate the comprehensive judgment of the safety risk after closing the circuit breaker, and then facilitate the risk assessment of the management personnel before the closing operation, and then facilitate the decision-making assistance of the management personnel's closing operation. By establishing a risk closing database, it is convenient to record the data of each closing decision, and then facilitate the decision-making system to optimize the decision-making according to historical data;

[0072] In the closing feedback optimization module, this solution scores the closing decision by collecting the equipment status, maintenance personnel status and grid operation status after closing. The closing score is used to comprehensively judge the estimated accuracy of the closing decision, and then the value and calculation method of the protection coefficient are adjusted according to the closing score result, so as to further reduce the risk of closing failure in the next closing decision, thereby further ensuring the safety of electrical equipment and maintenance personnel, and adjusting the closing decision in a targeted manner according to the historical closing situation, so as to provide more accurate closing decision suggestions to managers in the next closing operation;

[0073] It is worth mentioning that the weight values ​​in this scheme can be obtained through the hierarchical analysis method, and the value of the preset threshold can be obtained through the weight analysis method, which will not be elaborated here.

[0074] The electrical values ​​are obtained in the closing data detection module, specifically:

[0075] Step 1: obtaining the pre-fault voltage of the power grid, obtaining the post-fault voltage of the power grid, obtaining a voltage value by taking the absolute value of the post-fault voltage and the pre-fault voltage, setting a voltage preset threshold, obtaining a voltage difference by taking the difference of the voltage preset threshold and the post-fault voltage, and obtaining a voltage reference value by summing the voltage value and the voltage difference;

[0076] Step 2: Obtain the insulation resistance of the power grid, set a preset insulation resistance threshold, and obtain an insulation resistance reference value by subtracting the preset insulation resistance threshold from the insulation resistance;

[0077] Step 3: Obtain the fault current of the power grid, set a preset fault current threshold, and obtain a fault current reference value by subtracting the preset fault current threshold from the fault current;

[0078] Step 4: Obtain the electrical value through the fault current reference value, voltage reference value and insulation resistance reference value of the power grid;

[0079] The electrical value is calculated as follows:

[0080] ;

[0081] Among them, Dq represents the electrical value, Gz represents the fault current reference value, Dy represents the voltage reference value, and Dz represents the insulation resistance reference value. , and are weights, , , .

[0082] In this embodiment, the greater the fault current in the power grid, the greater the abnormal voltage fluctuation or the voltage is too low after the fault, and the smaller the insulation resistance, the greater the possibility that the fault in the power grid has not been eliminated, the greater the possibility of a short circuit when the power grid is closed, and the greater the possibility that the closed electrical equipment will be damaged by secondary impact. Therefore, it is not suitable to close the power grid at this time. The state of the power grid at this time is comprehensively judged by combining the fault current, voltage change and insulation resistance in the power grid, which facilitates the subsequent accurate closing auxiliary decision to the management personnel.

[0083] Get the device value in the closing data detection module, specifically:

[0084] Step 1: Take photos of the appearance of each electrical device in the power grid to obtain multiple reference pictures. Use the AOI system to identify the burnt, cracked and deformed electrical devices in each reference picture, and mark the number of defects of each electrical device.

[0085] Step 2: Obtain the temperature of each electrical device, and obtain the device value through the temperature of each electrical device and the number of defects of the corresponding electrical device;

[0086] The device value is calculated as follows:

[0087] ;

[0088] Where Bs represents the equipment value, Wd represents the temperature of the electrical equipment, Qx represents the number of defects of the electrical equipment, and n represents the number of electrical equipment. .

[0089] In this embodiment, by taking a photo of the electrical equipment and then using the AOI system to identify the appearance of the electrical equipment, it is convenient to judge the risk of the power grid failing again after closing the switch according to the burning condition of the electrical equipment surface, and then combined with the temperature of the electrical equipment, it is convenient to comprehensively judge whether the electrical equipment is damaged and whether it can meet the requirements of closing the switch again, so as to facilitate the auxiliary decision-making of the manager's closing operation;

[0090] It is worth mentioning that optical inspection and defect identification through AOI is an existing technology, and the specific defect identification steps will not be described in detail here.

[0091] The personnel risk value is obtained in the closing data detection module, specifically:

[0092] Step 1: Obtain the working hours of each maintenance personnel, obtain the number of historical operation accidents of each maintenance personnel, obtain the reference number of accidents by summing the number of historical operation accidents of each maintenance personnel and 1, obtain the experience value of each maintenance personnel by dividing the working hours of each maintenance personnel by the reference number of accidents, and sum and average the experience values ​​of each maintenance personnel to obtain the maintenance personnel value;

[0093] Step 2: Obtain the grounding resistance before the accident, obtain the grounding resistance after the accident, and obtain the absolute value of the difference between the grounding resistance before the accident and the grounding resistance after the accident to obtain the grounding resistance change value;

[0094] Step 3: The grounding resistance value is obtained by summing the grounding resistance change value and 1, and the personnel risk value is obtained by taking the weighted quotient of the maintenance personnel value and the grounding resistance value.

[0095] In this embodiment, the longer the maintenance personnel work, the fewer the number of historical operation accidents, which means that the maintenance personnel's error rate in this maintenance is lower, the self-protection ability is stronger, and the probability of safety risks is lower. The greater the fluctuation of the grounding resistance, the greater the risk of the connection of the grounding equipment, and the greater the possibility of electric shock to the maintenance personnel after closing the switch. Therefore, by combining the maintenance personnel's experience with the fluctuation state of the grounding resistance, it is convenient to judge the safety risk of closing the switch at this time, and then it is convenient to make auxiliary decisions on the closing operation of the management personnel.

[0096] Obtain the execution value in the closing data detection module, specifically:

[0097] Step 1: The maintenance personnel goes to repair the electrical equipment and presses the maintenance button before leaving the office to start the timing. After the maintenance, the maintenance personnel returns to the office and presses the maintenance button to end the timing. The maintenance time is obtained through the timing.

[0098] Step 2: Get the time when the maintenance button is pressed for the second time, get the current time, and get the interval time by subtracting the current time from the time when the maintenance button is pressed for the second time;

[0099] Step 3: Obtain the execution status of the second maintenance button pressing. If the execution status of the second maintenance button pressing is pressed, execute step 4. If the execution status of the second maintenance button pressing is not pressed, execute step 2.

[0100] Step 4: Get the maintenance time, set the preset threshold of the maintenance time, obtain the maintenance reference time by subtracting the maintenance time from the preset threshold of the maintenance time, get the interval time, get the interval reference time by summing the interval time and 1, and get the execution value by dividing the maintenance reference time by the interval reference time.

[0101] In this embodiment, the maintenance personnel go to repair the electrical equipment and press a button after the maintenance is completed, so as to facilitate the understanding of the maintenance personnel's current status, which is beneficial to avoid the danger of closing the switch when the maintenance personnel is in the maintenance state. It is also convenient to record the maintenance time of the maintenance personnel, so as to facilitate the judgment based on the maintenance time whether the maintenance personnel is just a simple visual inspection, and thus facilitate the accuracy of the maintenance results. The longer the time from the maintenance personnel finishing the maintenance to the present, the greater the probability that the maintenance personnel returns to the vicinity of the electrical equipment or someone passes by the electrical equipment. Therefore, the greater the risk of electric shock accidents when closing the switch, which facilitates the auxiliary decision-making of the management personnel's closing operation.

[0102] In the closing decision-making module, the security factor is obtained by the hardware safety factor and the personnel safety factor, and the preset threshold of the security factor is set. Whether to close the circuit breaker is determined by the security factor and the preset threshold of the security factor. Specifically:

[0103] Step 1: Obtain the hardware safety factor, set the hardware safety factor weight, obtain the hardware safety reference factor by multiplying the hardware safety factor weight by the hardware safety factor, obtain the personnel safety factor, set the personnel safety factor weight, obtain the personnel safety reference factor by multiplying the personnel safety factor by the personnel safety factor weight, and obtain the protection factor by summing the hardware safety reference factor and the personnel safety reference factor;

[0104] Step 2: Set the preset threshold of the security factor, determine the relationship between the security factor and the preset threshold of the security factor, if the security factor is greater than or equal to the preset threshold of the security factor, it is recommended to execute the grid closing, if the security factor is less than the preset threshold of the security factor, it is recommended to confirm the safety of the grid closing and repeat the measurement of the security factor.

[0105] In this embodiment, the protection factor is calculated by hardware safety factor, hardware safety factor weight, personnel safety factor and personnel safety factor weight, so as to facilitate the comprehensive analysis of the risk protection level of the closing by combining the status of the electrical equipment and the maintenance status and safety status of the maintenance personnel, and then judge the safety of the closing according to the protection factor and the preset threshold of the protection factor, so as to facilitate the combination of a large number of data to provide auxiliary feedback on the closing safety to the management personnel, which is beneficial to improve the safety of the power grid closing.

[0106] In the feedback incentive optimization module, the closing score is obtained according to the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing. Specifically, it is:

[0107] Step 1: Obtain the number of electrical equipment burnouts after closing the circuit breaker, obtain the safety feedback of personnel after closing the circuit breaker, and obtain the number of dangerous accidents through the safety feedback of personnel before and after closing the circuit breaker;

[0108] Step 2: Set a preset threshold value for the maintenance time, and obtain the continuous operation time of the power grid after closing. If the continuous operation time of the power grid after closing is greater than or equal to the preset threshold value for the maintenance time, the operation state of the power grid after closing is recorded as 1; if the continuous operation time of the power grid after closing is less than the preset threshold value for the maintenance time, the operation state of the power grid after closing is recorded as 0;

[0109] Step 3: Obtain the post-gate coefficient by weighted summing the number of electrical equipment burnouts and the number of dangerous accidents, set a preset threshold for the closing score, obtain the post-gate score by multiplying the post-gate coefficient by the preset threshold for the closing score, and obtain the closing score by multiplying the post-gate score by the operating status of the power grid after closing.

[0110] In this embodiment, the state of the equipment after closing is grasped by the number of burnt electrical equipment after closing, the safety state of personnel after closing is grasped by the occurrence of safety accidents such as electric shock in the power grid after closing, and the operation state of the power grid is grasped by the smooth operation time of the power grid after closing. Finally, the closing operation is scored according to various feedback states after closing. The closing score facilitates comprehensive judgment on the estimated accuracy of the closing decision, which in turn facilitates subsequent optimization and adjustment of the decision calculation method of the decision-making system.

[0111] In the feedback incentive optimization module, the value of the protection factor is adjusted according to the closing score, specifically:

[0112] Step 1: Set the preset threshold of the hardware safety factor weight, set the preset threshold of the personnel safety factor weight, and obtain the closing score;

[0113] Step 2: Determine whether the closing score is 0. If the closing score is 0, the hardware safety factor weight is subtracted from the preset threshold of the hardware safety factor weight to obtain the hardware safety factor quadratic weight when the assurance factor is measured next time. The hardware safety factor is multiplied by the hardware safety factor and the hardware safety factor quadratic weight to obtain the hardware safety reference factor. The personnel safety factor weight is subtracted from the preset threshold of the personnel safety factor weight to obtain the personnel safety reference factor. The personnel safety factor is multiplied by the personnel safety factor and the personnel safety factor quadratic weight to obtain the personnel safety reference factor. The assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the closing score is not 0, execute step 3.

[0114] Step 3: Set a preset threshold value for the number of electrical equipment burnouts, and determine whether the number of electrical equipment burnouts is greater than the preset threshold value for the number of electrical equipment burnouts. If the number of electrical equipment burnouts is greater than or equal to the preset threshold value for the number of electrical equipment burnouts, then the personnel safety factor weight is subtracted from the personnel safety factor weight preset threshold value when the assurance factor is measured next time to obtain the personnel safety factor quadratic weight, and the personnel safety reference factor is obtained by multiplying the personnel safety factor by the personnel safety factor quadratic weight, and the assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the number of electrical equipment burnouts is less than the preset threshold value for the number of electrical equipment burnouts, execute step 4:

[0115] Step 4: Set a preset threshold for the number of dangerous accidents, and determine whether the number of dangerous accidents is greater than or equal to the preset threshold. If the number of dangerous accidents is greater than or equal to the preset threshold, then the next time the assurance factor is measured, the hardware safety factor weight is subtracted from the preset threshold of the hardware safety factor weight to obtain the hardware safety factor quadratic weight. The hardware safety reference factor is obtained by multiplying the hardware safety factor by the hardware safety factor quadratic weight. The assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the number of dangerous accidents is less than the preset threshold, the assurance factor value remains unchanged and is fed back to the management personnel.

[0116] In this embodiment, the number of electrical equipment burns and the number of dangerous accidents are used to determine whether the cause of the current closing failure is related to the maintenance of the electrical equipment or the safety of the maintenance personnel, thereby facilitating targeted adjustments to the hardware safety factor weight or the personnel safety factor weight in the process of calculating the protection factor, thereby facilitating grasping the focus of historical accidents in the process of calculating the protection factor at the next closing, thereby facilitating more accurate decision-making assistance suggestions to management personnel next time.

[0117] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A large-scale model-based intelligent management and decision-making system for power grid faults, characterized in that include: The closing data detection module obtains electrical values, obtains equipment values, obtains hardware safety factors through electrical values ​​and equipment values, obtains personnel risk values, obtains execution values, and obtains personnel safety factors through personnel risk values ​​and execution values; The closing decision judgment module obtains the security factor through the hardware safety factor and the personnel safety factor, sets the preset threshold of the security factor, judges whether to close the circuit breaker through the security factor and the preset threshold of the security factor, establishes a risk closing database, and stores the security factor and the closing judgment result in the risk closing database; The closing feedback optimization module obtains the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing. The closing score is obtained according to the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing, and the value of the protection coefficient is adjusted according to the closing score. The electrical value is calculated as follows: ； Among them, Dq represents the electrical value, Gz represents the fault current reference value, Dy represents the voltage reference value, and Dz represents the insulation resistance reference value. , and are weights, , , ; The device value is calculated as follows: ; Where Bs represents the equipment value, Wd represents the temperature of the electrical equipment, Qx represents the number of defects of the electrical equipment, and n represents the number of electrical equipment. ; The calculation method of the hardware safety factor in the closing data detection module is as follows: ; Among them, Yj represents the hardware safety factor, Dq represents the electrical value, and Bs represents the device value. and are weights, , ; The calculation method of the personnel safety factor in the closing data detection module is as follows: ; Among them, Ry represents the personnel safety factor, Rf represents the personnel risk value, and Zx represents the execution value. and are weights, , .

2. The large model-based intelligent management and decision-making system for power grid faults according to claim 1 is characterized by: The electrical values ​​are obtained in the closing data detection module, specifically: Step 1: obtaining the pre-fault voltage of the power grid, obtaining the post-fault voltage of the power grid, obtaining a voltage value by taking the absolute value of the post-fault voltage and the pre-fault voltage, setting a voltage preset threshold, obtaining a voltage difference by taking the difference of the voltage preset threshold and the post-fault voltage, and obtaining a voltage reference value by summing the voltage value and the voltage difference; Step 2: Obtain the insulation resistance of the power grid, set a preset insulation resistance threshold, and obtain an insulation resistance reference value by subtracting the preset insulation resistance threshold from the insulation resistance; Step 3: Obtain the fault current of the power grid, set a preset fault current threshold, and obtain a fault current reference value by subtracting the preset fault current threshold from the fault current; Step 4: Obtain the electrical value through the fault current reference value, voltage reference value and insulation resistance reference value of the power grid.

3. The large-model-based intelligent management and decision-making system for power grid faults according to claim 1 is characterized by: Get the device value in the closing data detection module, specifically: Step 1: Take photos of the appearance of each electrical device in the power grid to obtain multiple reference pictures. Use the AOI system to identify the burnt, cracked and deformed electrical devices in each reference picture, and mark the number of defects of each electrical device. Step 2: Obtain the temperature of each electrical device, and obtain the device value through the temperature of each electrical device and the number of defects of the corresponding electrical device.

4. The large model-based intelligent management and decision-making system for power grid faults according to claim 1 is characterized by: The personnel risk value is obtained in the closing data detection module, specifically: Step 1: Obtain the working hours of each maintenance personnel, obtain the number of historical operation accidents of each maintenance personnel, obtain the reference number of accidents by summing the number of historical operation accidents of each maintenance personnel and 1, obtain the experience value of each maintenance personnel by dividing the working hours of each maintenance personnel by the reference number of accidents, and sum and average the experience values ​​of each maintenance personnel to obtain the maintenance personnel value; Step 2: Obtain the grounding resistance before the accident, obtain the grounding resistance after the accident, and obtain the absolute value of the difference between the grounding resistance before the accident and the grounding resistance after the accident to obtain the grounding resistance change value; Step 3: The grounding resistance value is obtained by summing the grounding resistance change value and 1, and the personnel risk value is obtained by taking the weighted quotient of the maintenance personnel value and the grounding resistance value.

5. The large-model-based intelligent management and decision-making system for power grid faults according to claim 1 is characterized by: Obtain the execution value in the closing data detection module, specifically: Step 1: The maintenance personnel goes to repair the electrical equipment and presses the maintenance button before leaving the office to start the timing. After the maintenance, the maintenance personnel returns to the office and presses the maintenance button to end the timing. The maintenance time is obtained through the timing. Step 2: Get the time when the maintenance button is pressed for the second time, get the current time, and get the interval time by subtracting the current time from the time when the maintenance button is pressed for the second time; Step 3: Obtain the execution status of the second maintenance button pressing. If the execution status of the second maintenance button pressing is pressed, execute step 4. If the execution status of the second maintenance button pressing is not pressed, execute step 2. Step 4: Get the maintenance time, set the preset threshold of the maintenance time, obtain the maintenance reference time by subtracting the maintenance time from the preset threshold of the maintenance time, get the interval time, get the interval reference time by summing the interval time and 1, and get the execution value by dividing the maintenance reference time by the interval reference time.

6. The large-model-based intelligent management and decision-making system for power grid faults according to claim 1 is characterized by: In the closing decision-making module, the security factor is obtained by the hardware safety factor and the personnel safety factor, and the preset threshold of the security factor is set. Whether to close the circuit breaker is determined by the security factor and the preset threshold of the security factor. Specifically: Step 1: Obtain the hardware safety factor, set the hardware safety factor weight, obtain the hardware safety reference factor by multiplying the hardware safety factor weight by the hardware safety factor, obtain the personnel safety factor, set the personnel safety factor weight, obtain the personnel safety reference factor by multiplying the personnel safety factor by the personnel safety factor weight, and obtain the protection factor by summing the hardware safety reference factor and the personnel safety reference factor; Step 2: Set the preset threshold of the security factor, determine the relationship between the security factor and the preset threshold of the security factor, if the security factor is greater than or equal to the preset threshold of the security factor, it is recommended to execute the grid closing, if the security factor is less than the preset threshold of the security factor, it is recommended to confirm the safety of the grid closing and repeat the measurement of the security factor.

7. The large model-based intelligent management and decision-making system for power grid faults according to claim 6 is characterized by: In the feedback incentive optimization module, the closing score is obtained according to the equipment status after closing, the personnel safety status after closing, and the grid operation status after closing. Specifically, it is: Step 1: Obtain the number of electrical equipment burnouts after closing the circuit breaker, obtain the safety feedback of personnel after closing the circuit breaker, and obtain the number of dangerous accidents through the safety feedback of personnel before and after closing the circuit breaker; Step 2: Set a preset threshold value for the maintenance time, and obtain the continuous operation time of the power grid after closing. If the continuous operation time of the power grid after closing is greater than or equal to the preset threshold value for the maintenance time, the operation state of the power grid after closing is recorded as 1; if the continuous operation time of the power grid after closing is less than the preset threshold value for the maintenance time, the operation state of the power grid after closing is recorded as 0; Step 3: Obtain the post-gate coefficient by weighted summing the number of electrical equipment burnouts and the number of dangerous accidents, set a preset threshold for the closing score, obtain the post-gate score by multiplying the post-gate coefficient by the preset threshold for the closing score, and obtain the closing score by multiplying the post-gate score by the operating status of the power grid after closing.

8. The large model-based intelligent management and decision-making system for power grid faults according to claim 7 is characterized by: In the feedback incentive optimization module, the value of the protection factor is adjusted according to the closing score, specifically: Step 1: Set the preset threshold of the hardware safety factor weight, set the preset threshold of the personnel safety factor weight, and obtain the closing score; Step 2: Determine whether the closing score is 0. If the closing score is 0, the hardware safety factor weight is subtracted from the preset threshold of the hardware safety factor weight to obtain the hardware safety factor quadratic weight when the assurance factor is measured next time. The hardware safety factor is multiplied by the hardware safety factor and the hardware safety factor quadratic weight to obtain the hardware safety reference factor. The personnel safety factor weight is subtracted from the preset threshold of the personnel safety factor weight to obtain the personnel safety reference factor. The personnel safety factor is multiplied by the personnel safety factor and the personnel safety factor quadratic weight to obtain the personnel safety reference factor. The assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the closing score is not 0, execute step 3. Step 3: Set a preset threshold value for the number of electrical equipment burnouts, and determine whether the number of electrical equipment burnouts is greater than the preset threshold value for the number of electrical equipment burnouts. If the number of electrical equipment burnouts is greater than or equal to the preset threshold value for the number of electrical equipment burnouts, then the personnel safety factor weight is subtracted from the personnel safety factor weight preset threshold value when the assurance factor is measured next time to obtain the personnel safety factor quadratic weight, and the personnel safety reference factor is obtained by multiplying the personnel safety factor by the personnel safety factor quadratic weight, and the assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the number of electrical equipment burnouts is less than the preset threshold value for the number of electrical equipment burnouts, execute step 4: Step 4: Set a preset threshold for the number of dangerous accidents, and determine whether the number of dangerous accidents is greater than or equal to the preset threshold. If the number of dangerous accidents is greater than or equal to the preset threshold, then the next time the assurance factor is measured, the hardware safety factor weight is subtracted from the preset threshold of the hardware safety factor weight to obtain the hardware safety factor quadratic weight. The hardware safety reference factor is obtained by multiplying the hardware safety factor by the hardware safety factor quadratic weight. The assurance factor is obtained by summing the hardware safety reference factor and the personnel safety reference factor. If the number of dangerous accidents is less than the preset threshold, the assurance factor value remains unchanged and is fed back to the management personnel.

Images