Power facility emergency response system based on earthquake early warning

Abstract

The present invention relates to the field of power emergency control technology, and discloses an electric power facility emergency response system based on earthquake early warning, comprising: a regional division module for acquiring power topology data and generating multiple regional sections; a data acquisition module for collecting earthquake early warning data, equipment operation data, and equipment environment data, and representing them through multi-source data sets; a fault risk assessment module for calculating the failure probability of each electric power device; an isolation decision and control module for calculating the regional reliability index of the sub-region and determining the target sub-region; an off-grid operation control module for switching the target sub-region to off-grid operation and adjusting control parameters; an operation status assessment module for generating an operation health score; and a reconnection recovery module for restoring the target sub-region to the main power grid. The present invention realizes intelligent isolation and safe reconnection control of power sub-regions driven by earthquake early warning.

Description

Technical Field

[0001] The present invention belongs to the technical field of power emergency control, and in particular relates to an electric power facility emergency processing system based on earthquake early warning. Background Art

[0002] In areas prone to natural disasters like earthquakes, power systems face severe challenges in operational stability and emergency response. Earthquake-induced mechanical vibration, equipment damage, and communication disruptions can lead to widespread faults in power facilities, localized frequency fluctuations, and voltage instability, severely impacting power supply continuity. To improve earthquake response efficiency, recent efforts have seen the integration of earthquake early warning systems with power systems. These systems provide early detection of earthquake magnitude, epicenter location, and wave propagation characteristics, providing power facilities with the opportunity to respond.

[0003] Although some existing technologies have introduced earthquake early warning information to trigger tripping protection, the current emergency response methods for power facilities still have shortcomings: first, there is a lack of multi-source data fusion, which cannot comprehensively characterize the electrical and environmental conditions of each region; second, there is insufficient judgment on the regional island operation capacity, and the isolation strategy lacks adaptability; third, the reconnection condition judgment mechanism is imperfect, which cannot guarantee the stability of the recovery process. Summary of the Invention

[0004] The present invention provides an electric power facility emergency response system based on earthquake early warning, which solves the technical problems of untimely emergency response, inaccurate isolation strategy and unstable reconnection process in related technologies.

[0005] The present invention provides an electric power facility emergency response system based on earthquake early warning, comprising:

[0006] A region division module is used to obtain power topology data and generate multiple region sections through multiple minimum cut algorithms. The region sections are used to divide the first power supply area into M sub-areas.

[0007] A data acquisition module, configured to collect earthquake early warning data, equipment operation data, and equipment environment data for a first preset time period at preset time intervals, and represent the data through a multi-source data set;

[0008] Fault risk assessment module, which is used to calculate the failure probability of each power device based on the logistic regression model according to the multi-source data set;

[0009] The isolation decision and control module is used to calculate the regional reliability index of the sub-regions isolated from each regional section based on the failure probability of the regional section and the power equipment, select the regional section with the largest regional reliability index as the optimal regional section, determine the corresponding sub-region as the target sub-region, and issue a trip command to the target sub-region;

[0010] The off-grid operation control module is used to switch the target sub-area to off-grid operation and adjust the control parameters of the power equipment in the target sub-area according to a preset ratio;

[0011] The operating status assessment module is used to calculate the frequency deviation standard deviation, voltage overlimit duration ratio, and load power fluctuation rate based on the equipment operating data in the multi-source dataset of the target sub-area, and generate the operating health score of the target sub-area through linear weighting;

[0012] The reconnection recovery module is used to determine whether the operation health score of the target sub-area reaches a first preset reconnection threshold, and when the operation health score is greater than the first preset reconnection threshold, restore the connection of the target sub-area to the main power grid.

[0013] Furthermore, earthquake early warning data includes: magnitude, epicenter location, wave velocity, and P-wave arrival time; equipment operation data includes: voltage, current, frequency, phase angle, and active power; equipment environment data includes: equipment location, installation method, seismic resistance level, and load level.

[0014] Furthermore, the power topology data includes: substation number, feeder branch point number, microgrid access point number, circuit breaker number and circuit breaker status;

[0015] The area division module is used to pre-zone the first power supply area in the pre-earthquake stage, and the specific steps include:

[0016] S201: constructing an undirected power graph based on the power topology data, wherein the undirected power graph includes nodes and edges, wherein the nodes are represented by substation numbers, feeder branch point numbers, and microgrid access point numbers, and the edges are represented by line connection relationships between nodes, wherein the line connection relationships are determined by line numbers;

[0017] S202, performing weighted calculation on each edge according to a preset line load capacity and line length to obtain an edge weight;

[0018] S203, using the minimum cut algorithm on the power undirected graph, each time removing a group of edges with the smallest total weight from the current graph to generate a regional section, and repeating this operation on the remaining part of the power undirected graph until the predetermined M sub-regions are obtained.

[0019] Furthermore, the process of determining the failure probability is as follows:

[0020] Extracting all feature values ​​corresponding to each power device from the multi-source data set, where the number of features is fixed to n;

[0021] Perform weighted processing on each eigenvalue, multiply the first eigenvalue by the first pre-trained regression coefficient, multiply the second eigenvalue by the second regression coefficient, and so on until the nth eigenvalue is multiplied by the nth regression coefficient. Add all the product results and superimpose a pre-trained first bias parameter on the sum to obtain the weighted sum result;

[0022] Taking the weighted sum result as a negative value, and calculating the natural exponential function value of the negative value;

[0023] The natural exponential function value is processed and then the inverse is taken to finally output a device failure probability value between 0 and 1.

[0024] Furthermore, the process of determining the regional reliability index is as follows:

[0025] Based on the selected regional section, identify all b pieces of power equipment contained in the sub-region isolated by the regional section; for the first piece of equipment in the sub-region: process the failure probability of the equipment to obtain its reliability; repeat this operation to calculate the reliability of the second to b-th pieces of equipment in sequence;

[0026] Add up the reliabilities of all b devices to get the total reliability;

[0027] Divide the total reliability by the total number of devices b to output the regional reliability index of the sub-region.

[0028] Furthermore, the control parameters include: a frequency-power droop coefficient and a voltage-excitation droop coefficient, wherein the frequency-power droop coefficient is calculated by the ratio between a preset frequency offset and the rated power of the power equipment, and the voltage-excitation droop coefficient is calculated by the ratio between a preset voltage offset and the maximum excitation current change of the power equipment.

[0029] Furthermore, the control parameters are adjusted using a multiplication scaling method to adjust the frequency-power droop coefficient and the voltage-excitation droop coefficient using a first preset adjustment ratio and a second preset adjustment ratio respectively.

[0030] Furthermore, the standard deviation of the frequency deviation is calculated by squaring the difference between the frequency of each sampling point and the average frequency, averaging all the results and then taking the square root;

[0031] The voltage exceeding time ratio is obtained by calculating the cumulative time during which the voltage exceeds the preset voltage threshold and comparing the total time of the first preset time period with the total time of the first preset time period.

[0032] The load power fluctuation rate is obtained by squaring the active power difference between adjacent sampling points, averaging all the results and taking the square root.

[0033] Furthermore, after the operation health score reaches the first preset reconnection threshold, the reconnection recovery module is also used to determine whether the frequency deviation between the main grid and the target sub-area is lower than the second preset frequency deviation threshold, and whether the phase angle deviation is lower than the third preset phase angle deviation threshold. If both conditions are met, the target sub-area is restored to the main grid; wherein the frequency deviation is the difference between the main grid frequency and the target sub-area frequency, and the phase angle deviation is the difference between the main grid phase angle and the target sub-area phase angle.

[0034] The beneficial effects of the present invention are as follows: the present invention integrates earthquake early warning data, equipment operation data and equipment environment data to construct a multi-source data set, thereby realizing comprehensive perception and dynamic analysis of pre-earthquake risks. By constructing an undirected power graph and executing the minimum cut algorithm, a structured division of sub-regions is achieved, and regions with high operational reliability are preferentially identified for pre-isolation, thereby improving island stability and system resilience. During operation, the present invention evaluates the status of the sub-region through an operational health score, and combines frequency and phase angle deviation criteria to intelligently determine whether the conditions for grid connection are met, thereby realizing adaptive and safe reconnection control. The overall solution supports closed-loop control of "prediction-isolation-operation-reconnection", which can significantly improve the rapid response capability and post-disaster recovery efficiency of the distribution system in earthquake scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a module schematic diagram of the power facility emergency processing system based on earthquake early warning of the present invention. DETAILED DESCRIPTION

[0036] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

[0037] like Figure 1 As shown in FIG, the power facility emergency response system based on earthquake early warning includes:

[0038] A region division module 101 is configured to obtain power topology data and generate multiple region sections using multiple minimum cut algorithms, wherein the region sections are used to divide a first power supply region into M sub-regions;

[0039] The data collection module 102 is used to collect earthquake early warning data, equipment operation data and equipment environment data of a first preset time period at preset time intervals, and represent them through a multi-source data set;

[0040] The failure risk assessment module 103 is used to calculate the failure probability of each power device based on the multi-source data set and the logistic regression model;

[0041] The isolation decision and control module 104 is used to calculate the regional reliability index of the sub-regions isolated from each regional section based on the failure probability of the regional section and the power equipment, select the regional section with the largest regional reliability index as the optimal regional section, determine the corresponding sub-region as the target sub-region, and issue a trip command to the target sub-region;

[0042] The off-grid operation control module 105 is used to switch the target sub-area to off-grid operation and adjust the control parameters of the power equipment in the target sub-area according to a preset ratio;

[0043] An operation status evaluation module 106 is configured to calculate the frequency deviation standard deviation, voltage overlimit duration ratio, and load power fluctuation rate based on the equipment operation data in the multi-source data set of the target sub-area, and generate an operation health score of the target sub-area through linear weighting;

[0044] The reconnection recovery module 107 is configured to determine whether the operation health score of the target sub-area reaches a first preset reconnection threshold, and when the operation health score is greater than the first preset reconnection threshold, restore the connection of the target sub-area to the main power grid.

[0045] In one embodiment of the present invention, earthquake warning data includes: magnitude, epicenter location, wave velocity, and P-wave arrival time; equipment operation data includes: voltage, current, frequency, phase angle, and active power; equipment environment data includes: equipment location, installation method, seismic resistance level, and load level.

[0046] Specifically, earthquake early warning data is obtained through the data interface of the China Earthquake Networks Center, equipment operation data is collected through smart meters installed on site, the phase angle is expressed in the form of voltage phase angle, and equipment environment data is obtained through the data center database; the unit of magnitude is degree, the epicenter position is expressed by latitude and longitude coordinates, the unit of wave speed is m / s, and the unit of P-wave arrival time is s.

[0047] In one embodiment of the present invention, in order to ensure that various indicators in multi-source data sets can be effectively integrated and calculated, the earthquake early warning data, equipment operation data and equipment environment data are normalized using the maximum and minimum normalization method.

[0048] In one embodiment of the present invention, the area cross section represents a trippable circuit breaker, which can divide the first power supply area into two sub-areas that are not connected to each other after being cut off.

[0049] In one embodiment of the present invention, the power topology structure data includes: substation number, feeder branch point number, microgrid access point number, circuit breaker number and circuit breaker status; wherein, the substation number is used to identify each substation node in the area; the feeder branch point number is used to describe the connection node and branch position in the feeder topology; the microgrid access point number is used to identify each distributed energy access location; the circuit breaker number and circuit breaker status are used to indicate the connection status between each node, and the circuit breaker status includes connected and disconnected; the power topology structure data is obtained by accessing the power distribution management system.

[0050] The area division module is used to pre-zone the first power supply area in the pre-earthquake stage, and the specific steps include:

[0051] S201: Constructing an undirected power graph based on the power topology data, wherein the undirected power graph includes nodes and edges, wherein the nodes are represented by substation numbers, feeder branch point numbers, and microgrid access point numbers, and the edges are represented by line connection relationships between nodes, and the line connection relationships are determined by line numbers. The edges are used to reflect the physical connectivity between devices, and each edge corresponds to a physical line. The undirected power graph is organized and stored using a graph database structure to improve access efficiency.

[0052] S202: Perform weighted calculation on each edge based on the preset line load capacity and line length to obtain the edge weight. The weight calculation formula is: ,in, Represents the weight of the edge, which is used for subsequent area division. Indicates the preset line load capacity, d indicates the line length, and represent the first weight coefficient and the second weight coefficient respectively;

[0053] S203, using a minimum cut algorithm on the power undirected graph, each time removing a group of edges with the smallest sum of weights from the current graph to generate a regional cross section, and repeating this operation for the remaining portion of the power undirected graph until the predetermined M sub-regions are obtained;

[0054] Specifically, based on the edge weights calculated in step S202, a minimum cut algorithm is used to identify a set of edges with the smallest total weight in the current power undirected graph, and the connected branches separated by the set are used as a new sub-region, whose boundary is the regional section. After completing a minimum cut operation, this embodiment removes the nodes and associated edges corresponding to the sub-region from the original power undirected graph, and repeatedly performs the minimum cut operation on the remaining graph until the power undirected graph is divided into a predetermined number M of sub-regions; this method can achieve target sub-regions with good boundary characteristics and controllable divisions without excessively affecting the connectivity of the main power grid.

[0055] In one embodiment of the present invention, the process of determining the failure probability is as follows:

[0056] Extracting all feature values ​​corresponding to each power device from the multi-source data set, where the number of features is fixed to n;

[0057] Perform weighted processing on each eigenvalue, multiply the first eigenvalue by the first pre-trained regression coefficient, multiply the second eigenvalue by the second regression coefficient, and so on until the nth eigenvalue is multiplied by the nth regression coefficient. Add all the product results and superimpose a pre-trained first bias parameter on the sum to obtain the weighted sum result;

[0058] Taking the weighted sum result as a negative value, and calculating the natural exponential function value of the negative value;

[0059] The natural exponential function value is processed and then the inverse is taken to finally output a device failure probability value between 0 and 1.

[0060] When applied in a specific application, the above calculation formula for failure probability can be implemented by the following formula, for example:

[0061] ;

[0062] Where P represents the failure probability, which is used to evaluate the possibility of functional failure of power equipment under earthquake disturbance, and exp represents the exponential function. represents the first bias parameter, n represents the number of features in the multi-source dataset. In this embodiment, n is 12, j represents the index of the feature, represents the value of the jth feature in the multi-source dataset, Represents the jth regression coefficient, which is obtained through offline training.

[0063] In one embodiment of the present invention, the process of determining the regional reliability index is as follows:

[0064] Based on the selected regional section, identify all b pieces of power equipment contained in the sub-region isolated by the regional section; for the first piece of equipment in the sub-region: process the failure probability of the equipment to obtain its reliability; repeat this operation to calculate the reliability of the second to b-th pieces of equipment in sequence;

[0065] Add up the reliabilities of all b devices to get the total reliability;

[0066] Divide the total reliability by the total number of devices b to output the regional reliability index of the sub-region.

[0067] When applied in practice, the calculation formula of the above regional reliability index can be implemented by the following formula, for example:

[0068] ;

[0069] in, represents the regional reliability index of the sub-region isolated by the regional section, b represents the number of power equipment in the sub-region, i represents the index of the power equipment, represents the failure probability of the i-th power equipment; the regional reliability index is used to quantify the overall operational reliability of the power equipment in the sub-region under earthquake disturbances, facilitating the priority selection of sub-regions with high operational stability for isolation, ensuring that the isolated sub-regions have strong off-grid operation capabilities and self-recovery capabilities, thereby maintaining local power supply stability when the main power grid undergoes large-scale disturbances or instability, and preventing the fault from spreading to stable areas.

[0070] Based on the calculated regional reliability index of the sub-regions isolated by each regional section, the regional section with the largest regional reliability index is selected as the optimal regional section, and the sub-region isolated by it is used as the target sub-region; the boundary circuit breaker between the target sub-region and the main power grid is further determined, and a tripping command is issued to the boundary circuit breaker, thereby achieving electrical isolation between the target sub-region and the main power grid.

[0071] In one embodiment of the present invention, the control parameters include: a frequency-power droop coefficient and a voltage-excitation droop coefficient, wherein the frequency-power droop coefficient is calculated by the ratio between a preset frequency offset and the rated power of the power equipment, and the voltage-excitation droop coefficient is calculated by the ratio between a preset voltage offset and the maximum excitation current change of the power equipment.

[0072] The frequency offset is the maximum frequency offset value allowed in the target sub-area in off-grid operation state, unit is Hz, and the rated power is the rated output active power of the power equipment in normal operation state, unit is kW; the voltage offset is the allowable bus voltage fluctuation range, unit is V, and the maximum excitation current change is the maximum value of the power equipment within the voltage offset range, unit is A.

[0073] After the target sub-region is disconnected from the main grid and enters off-grid operation, its frequency and voltage stability will no longer rely on the main grid inertia and reactive power support. Therefore, the control sensitivity of local equipment needs to be improved to enable faster frequency-voltage response capabilities. In other words, the control parameters of the power equipment in the target sub-region are adjusted using a multiplication and scaling method. The frequency-power droop coefficient is used to indicate the response sensitivity of the power equipment to frequency deviations in the offline operation state, and the voltage-excitation droop coefficient is used to control the response degree of the synchronous motor or reactive power regulation device to voltage deviations.

[0074] The control parameters are adjusted by a multiplication scaling method using a first preset adjustment ratio and a second preset adjustment ratio to adjust the frequency-power droop coefficient and the voltage-excitation droop coefficient respectively; specifically, the frequency-power droop coefficient and the voltage-excitation droop coefficient are multiplied by the first preset adjustment ratio and the second preset adjustment ratio respectively to obtain the adjusted control parameters; preferably, the first preset adjustment ratio is 0.7 and the second preset adjustment ratio is 0.75.

[0075] In one embodiment of the present invention, the frequency deviation standard deviation is calculated by squaring the difference between the frequency of each sampling point and the average frequency, averaging all the results, and then taking the square root. The standard deviation is used to represent the degree of frequency fluctuation in the target sub-region. The calculation formula of the frequency deviation standard deviation is: ,in, represents the standard deviation of frequency deviation, N represents the number of sampling points, k represents the sampling point index, represents the frequency of the kth sampling point, Represents the average value of the frequency of each sampling point;

[0076] The voltage exceeding time ratio is calculated by counting the cumulative time that the voltage exceeds the preset voltage threshold and calculating the ratio with the total time of the first preset time period. The voltage exceeding time ratio is used to reflect the degree of long-term voltage instability. The calculation formula of the voltage exceeding time ratio is: ,in, Indicates the voltage exceeding the limit duration ratio, Indicates the cumulative voltage over-limit time, that is, the total time that the voltage exceeds the preset voltage threshold. Indicates the total duration of the first preset time period;

[0077] The load power fluctuation rate is obtained by squaring the active power difference between adjacent sampling points, averaging all the results, and then taking the square root. It is used to measure the severity of the change in active load. The calculation formula of the load power fluctuation rate is: ,in, represents the load power fluctuation rate, o represents the sampling point index, and Represent the active power of the o+1th and oth sampling points respectively.

[0078] The operation health score is obtained by performing linear weighted calculation on the frequency deviation standard deviation, the voltage overlimit duration ratio, and the load power fluctuation rate.

[0079] In one embodiment of the present invention, after the operation health score reaches the first preset reconnection threshold, the reconnection recovery module is also used to determine whether the frequency deviation between the main grid and the target sub-area is lower than the second preset frequency deviation threshold, and whether the phase angle deviation is lower than the third preset phase angle deviation threshold. If both conditions are met, the target sub-area is restored to the main grid by controlling the circuit breaker to close; wherein the frequency deviation is the difference between the main grid frequency and the target sub-area frequency, and the phase angle deviation is the difference between the main grid phase angle and the target sub-area phase angle.

[0080] In one embodiment of the present invention, if the health score of a target sub-region does not reach the first preset reconnection threshold, this embodiment determines that the target sub-region does not currently meet the operating conditions for safe grid connection, and the reconnection recovery module does not perform the grid connection operation. At this time, the target sub-region will continue to remain in the offline operating state. This embodiment sets a reassessment period, for example, recalculating the health score every 10 seconds until the health score reaches the first preset reconnection threshold or other recovery conditions are met.

[0081] If the frequency and phase angle deviations between the main grid and the target sub-region, after reaching the first preset reconnection threshold, fail to meet the second and third preset frequency and phase angle deviation thresholds, the reconnection operation will be suspended and the system will enter a reconnection waiting state. Similarly, the system can set a monitoring duration threshold and a maximum number of waiting times, for example, 30 seconds of continuous monitoring with a maximum of five waiting times. During this period, the system maintains real-time monitoring of the frequency and phase angles of the main grid and the sub-region, and triggers a grid connection command if it detects a deviation within the allowable range. If the criteria are still not met after the maximum number of waiting times, an alarm can be generated, and manual intervention mode or the reconnection plan can be postponed to ensure the overall operational safety of the system.

[0082] In one embodiment of the present invention, the stability and safety of target sub-area reconnection are improved by introducing the operation health score and frequency and phase angle deviation as joint reconnection criteria.

[0083] It should be noted that the intervals and thresholds are set for ease of comparison. The threshold size depends on the amount of sample data and the cardinality set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless numerical calculations. These formulas are derived from software simulations of the most recent real-world conditions using large amounts of data. The preset parameters in these formulas are set by those skilled in the art based on actual conditions.

[0084] The above describes the embodiments of the present invention, but the present invention is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. The power facility emergency response system based on earthquake early warning is characterized by: include: The region division module is used to obtain power topology data and generate multiple region sections through multiple minimum cut algorithms. The region sections are used to divide the first power supply area into M sub-areas. The specific steps include: S201: Constructing an undirected power graph based on power topology data, wherein the power topology data includes: a substation number, a feeder branch point number, a microgrid access point number, a circuit breaker number, and a circuit breaker status; the undirected power graph includes nodes and edges, where nodes are represented by substation numbers, feeder branch point numbers, and microgrid access point numbers, and edges are represented by line connection relationships between nodes, where line connection relationships are determined by line numbers; S202, performing weighted calculation on each edge according to a preset line load capacity and line length to obtain an edge weight; S203, using a minimum cut algorithm on the power undirected graph, each time removing a group of edges with the smallest sum of weights from the current graph to generate a regional cross section, and repeating this operation for the remaining portion of the power undirected graph until the predetermined M sub-regions are obtained; A data acquisition module, configured to collect earthquake early warning data, equipment operation data, and equipment environment data for a first preset time period at preset time intervals, and represent the data through a multi-source data set; Fault risk assessment module, which is used to calculate the failure probability of each power device based on the logistic regression model according to the multi-source data set; The calculation formula for failure probability is: ； Where P represents the failure probability, exp represents the exponential function, represents the first bias parameter, n represents the number of features in the multi-source dataset, j represents the index of the feature, represents the value of the jth feature in the multi-source dataset, represents the j-th regression coefficient; The isolation decision and control module is used to calculate the regional reliability index of the sub-regions isolated from each regional section based on the failure probability of the regional section and the power equipment, select the regional section with the largest regional reliability index as the optimal regional section, determine the corresponding sub-region as the target sub-region, and issue a trip command to the target sub-region; The calculation formula of regional reliability index is: ； in, represents the regional reliability index of the sub-region isolated by the regional section, b represents the number of power equipment in the sub-region, i represents the index of the power equipment, represents the failure probability of the i-th power equipment; The off-grid operation control module is used to switch the target sub-area to off-grid operation and adjust the control parameters of the power equipment in the target sub-area according to a preset ratio; The operating status assessment module is used to calculate the frequency deviation standard deviation, voltage overlimit duration ratio, and load power fluctuation rate based on the equipment operating data in the multi-source dataset of the target sub-area, and generate the operating health score of the target sub-area through linear weighting; The reconnection recovery module is used to determine whether the operation health score of the target sub-area reaches a first preset reconnection threshold, and when the operation health score is greater than the first preset reconnection threshold, restore the connection of the target sub-area to the main power grid.

2. The power facility emergency response system based on earthquake early warning according to claim 1 is characterized in that: Earthquake early warning data includes: magnitude, epicenter location, wave velocity, and P-wave arrival time; equipment operation data includes: voltage, current, frequency, phase angle, and active power; equipment environment data includes: equipment location, installation method, seismic resistance level, and load level.

3. The power facility emergency response system based on earthquake early warning according to claim 1, characterized in that: The process of determining the failure probability is: Extracting all feature values ​​corresponding to each power device from the multi-source data set, where the number of features is fixed to n; Perform weighted processing on each eigenvalue, multiply the first eigenvalue by the first pre-trained regression coefficient, multiply the second eigenvalue by the second regression coefficient, and so on until the nth eigenvalue is multiplied by the nth regression coefficient. Add all the product results and superimpose a pre-trained first bias parameter on the sum to obtain the weighted sum result; Taking the weighted sum result as a negative value, and calculating the natural exponential function value of the negative value; The natural exponential function value is processed and then the inverse is taken to finally output a device failure probability value between 0 and 1.

4. The power facility emergency response system based on earthquake early warning according to claim 1, characterized in that: The process of determining the regional reliability index is as follows: Based on the selected regional section, identify all b pieces of power equipment contained in the sub-region isolated by the regional section; for the first piece of equipment in the sub-region: process the failure probability of the equipment to obtain its reliability; repeat this operation to calculate the reliability of the second to b-th pieces of equipment in sequence; Add up the reliabilities of all b devices to get the total reliability; Divide the total reliability by the total number of devices b to output the regional reliability index of the sub-region.

5. The power facility emergency response system based on earthquake early warning according to claim 1, characterized in that: The control parameters include: a frequency-power droop coefficient and a voltage-excitation droop coefficient, wherein the frequency-power droop coefficient is calculated by the ratio between a preset frequency offset and the rated power of the power equipment, and the voltage-excitation droop coefficient is calculated by the ratio between a preset voltage offset and the maximum excitation current change of the power equipment.

6. The power facility emergency response system based on earthquake early warning according to claim 1, characterized in that: The control parameters are adjusted using a multiplication scaling method to adjust the frequency-power droop coefficient and the voltage-excitation droop coefficient using a first preset adjustment ratio and a second preset adjustment ratio respectively.

7. The power facility emergency response system based on earthquake early warning according to claim 1, characterized in that: The standard deviation of the frequency deviation is calculated by squaring the difference between the frequency of each sampling point and the average frequency, averaging all the results and then taking the square root; The voltage exceeding time ratio is obtained by calculating the cumulative time during which the voltage exceeds the preset voltage threshold and comparing the total time of the first preset time period with the total time of the first preset time period. The load power fluctuation rate is obtained by squaring the active power difference between adjacent sampling points, averaging all the results and taking the square root.

8. The power facility emergency response system based on earthquake early warning according to claim 1, characterized in that: After the operation health score reaches a first preset reconnection threshold, the reconnection recovery module is further used to determine whether the frequency deviation between the main grid and the target sub-area is lower than a second preset frequency deviation threshold, and whether the phase angle deviation is lower than a third preset phase angle deviation threshold. If both conditions are met, the target sub-area is restored to the main grid; wherein the frequency deviation is the difference between the main grid frequency and the target sub-area frequency, and the phase angle deviation is the difference between the main grid phase angle and the target sub-area phase angle.

Images