Intelligent power grid fault rapid positioning and self-healing system and method thereof

Abstract

The invention discloses an intelligent power grid fault rapid positioning and self-healing system and method, and relates to the technical field of power grid automation control, and the method comprises the following steps: obtaining environment monitoring data and power grid state data; inputting the obtained data into a formula to obtain geological stress field data and a cable vulnerability index; generating a cable section-level geological stress field data set and a cable section-level vulnerability index data set according to the acquired data based on the power grid state data; fusing the cable section-level geological stress field data set and the vulnerability index data set to generate cable section-level coupling risk index data; when the coupling risk index data exceeds a preset threshold value, generating a fault early warning signal and extracting fault cable section positioning data from the power grid state data; and generating a self-healing scheme according to the acquired data, and triggering the power grid control terminal to execute. And cross-domain coupling modeling is carried out on the geomechanical stress field and the mechanical state of the cable, so that the accuracy of data is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid automatic control, in particular to a smart grid fault rapid positioning and self-healing system and method thereof. BACKGROUND

[0002] The smart grid fault rapid positioning and self-healing is to utilize advanced sensing technology, communication technology, information technology and control technology to endow the power grid with the ability of automatic sensing, rapid analysis, accurate positioning, intelligent decision-making and automatic execution after a fault occurs, so as to realize the minimum isolation of the fault area and the rapid recovery of power supply in the non-fault area. It is an important symbol of the intelligent and automated level of modern power grids, and has revolutionary significance for improving power supply reliability and ensuring the stable operation of the economy and society. Essentially, it enables the power grid to have the ability of "self-diagnosis" and "self-repair".

[0003] With the expansion of the smart grid and the frequent occurrence of extreme weather, the coupling effect of geological environmental factors (such as freeze-thaw cycle and ground deformation) and mechanical stress of the power grid has become a major cause of cable failure. The traditional system often processes environmental monitoring data (geological deformation, freeze-thaw index) and power grid state data (cable strain, topology) independently, and rarely performs cross-domain coupling modeling of the geomechanical stress field and the mechanical state of the cable. Even if cross-domain coupling modeling is performed, the precision of the data is often not enough due to the consideration of too few associated data. SUMMARY

[0004] In view of the problem that the existing system rarely performs cross-domain coupling modeling of the geomechanical stress field and the mechanical state of the cable, and even if cross-domain coupling modeling is performed, the precision of the data is often not enough due to the consideration of too few data, the present application provides a smart grid fault rapid positioning and self-healing system and method thereof.

[0005] In order to achieve the above-mentioned purpose, the technical scheme of the present application is as follows:

[0006] In the first aspect, the present application discloses a smart grid fault rapid positioning and self-healing method, comprising:

[0007] obtaining environmental monitoring data and power grid state data of a current collection period;

[0008] inputting the environmental monitoring data into a pre-constructed geomechanical formula to output geomechanical stress field data;

[0009] inputting the power grid state data into a pre-constructed cable stress formula to output a cable damage degree, and generating a cable vulnerability index by time-domain integration of the cable damage degree;

[0010] Based on the power grid state data, the geological stress field data and the cable vulnerability index are spatially interpolated to generate a cable segment level geological stress field dataset and a cable segment level vulnerability index dataset;

[0011] The cable segment level coupling risk index data is generated by fusing the cable segment level geological stress field dataset and the cable segment level vulnerability index dataset;

[0012] When the cable segment level coupling risk index data exceeds a preset threshold, a fault warning signal is generated and fault cable segment positioning data is extracted from the power grid state data;

[0013] According to the fault warning signal and the fault cable segment positioning data, a self-healing scheme is generated, and a power grid control terminal is triggered to execute.

[0014] In a second aspect, the present application introduces an intelligent power grid fault rapid positioning and self-healing system, which comprises the following modules:

[0015] A data acquisition module is configured to acquire environmental monitoring data and power grid state data in a current acquisition period;

[0016] A data processing module is configured to input the environmental monitoring data into a geomechanics formula to output geological stress field data, and to input the power grid state data into a pre-trained cable stress formula to output cable damage degree, and to generate a cable vulnerability index by time-domain integration of the cable damage degree, and to generate a cable segment level geological stress field dataset and a cable segment level vulnerability index dataset by spatial interpolation of the geological stress field data and the cable vulnerability index based on the power grid state data, and to generate cable segment level coupling risk index data by fusing the cable segment level geological stress field dataset and the cable segment level vulnerability index dataset;

[0017] A data analysis module is configured to generate a fault warning signal and extract fault cable segment positioning data from the power grid state data when the cable segment level coupling risk index data exceeds a preset threshold;

[0018] A data judgment module is configured to generate a self-healing scheme according to the fault warning signal and the fault cable segment positioning data, and to trigger a power grid control terminal to execute.

[0019] In a third aspect, the present application provides a computing device, comprising:

[0020] A memory is configured to store a program;

[0021] A processor is configured to execute the computer executable instructions, which, when executed by the processor, implement the steps of the intelligent power grid fault rapid positioning and self-healing method.

[0022] Fourthly, the present invention provides a computer-readable storage medium, comprising: when the program is executed by a processor, the steps of implementing the smart grid fault rapid location and self-healing method.

[0023] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0024] 1. Conduct cross-domain coupled modeling of geomechanical stress field and cable mechanical state, quantify the stress transmission of surface deformation to underground cables through geomechanical formulas, and detect hidden physical damage caused by geological activities in advance.

[0025] 2. Incorporate time-series data of surface deformation, geological parameters, cable strain, and power grid topology to improve data accuracy;

[0026] 3. Overlay the displacement gradient hotspot area (geological risk area) with the cable path coordinates (power grid topology) in geospatial space to achieve spatial coupling analysis and accurately locate high-risk cable sections;

[0027] 4. General self-healing strategies (such as topology reconstruction) are difficult to cope with physical damage caused by geological activities. Differentiated solutions should be dynamically generated based on the cause of the fault, such as foundation reinforcement for geological deformation and line switching for electrical isolation. Attached Figure Description

[0028] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts. Wherein:

[0029] Figure 1 This invention introduces a method for rapid fault location and self-healing in smart grids.

[0030] Figure 2 Based on Figure 1 A logical flowchart for integrating geological stress field data with cable vulnerability index;

[0031] Figure 3 This invention introduces a smart grid fault rapid location and self-healing system. Detailed Implementation

[0032] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0033] Example 1

[0034] As Figure 1 shown, the intelligent power grid fault rapid positioning and self-healing method is introduced, including:

[0035] S1. Obtain the environmental monitoring data and power grid state data of the current collection period;

[0036] The environmental monitoring data includes surface deformation time series data and geological parameter time series data.

[0037] The surface deformation time series data is collected by InSAR (Interferometric Synthetic Aperture Radar, a technology that uses radar satellite measurement values to map millimeter-level displacement of the Earth's surface) satellite, specifically including:

[0038] Receive Sentinel-1A satellite synthetic aperture radar interferometric image data.

[0039] Differential calculation is performed on the surface displacement values at adjacent time points to generate displacement gradient data, where the displacement value accuracy is ≤±1mm, and the differential time interval is 24 hours.

[0040] Output the structured time series data set containing geographic coordinates (latitude and longitude, EPSG: 4326 coordinate system), timestamp, and displacement gradient value (unit: mm / day).

[0041] The geological parameter time series data is collected by a ground sensor network, and the acquisition process specifically includes:

[0042] Deploy temperature sensors (accuracy ±0.5℃) and soil moisture sensors (accuracy ±3%vol) at 0.5 meters below the surface of the cable path, with a sampling frequency of 1 time / minute.

[0043] Based on the temperature and soil moisture data, calculate the freeze-thaw cycle index (FTI) according to the following logic:

[0044] (1) When the temperature is ≤0℃ and the soil moisture is >15%, mark as frost heaving state;

[0045] (2) When the temperature is >0℃ for 4 hours, mark as thaw settlement state;

[0046] (3) The number of daily frost heaving / thaw settlement state switching is recorded as the daily FTI value;

[0047] Output the time series data table containing sensor ID, geographic coordinates, timestamp, and FTI value (dimensionless).

[0048] The power grid state data includes cable strain time series data and power grid topology relationship data

[0049] The cable strain time series data is collected by a distributed optical fiber sensor, specifically including:

[0050] Single-mode sensing fiber is laid along the cable, 1550nm laser with pulse width of 10ns is emitted, and Brillouin scattering spectrum signal is collected.

[0051] Resolving the frequency offset of scattered spectrum , through the calibration curve ( The strain coefficient is 0.048 MHz / με, the data is divided according to the cable segment ID, and the strain time sequence of each cable segment is generated, with a sampling rate of 200 Hz.

[0052] Output time series data set containing cable segment ID, timestamp, strain value (unit: με).

[0053] The power grid topology relationship data is imported through the power grid management system, which specifically includes:

[0054] The electrical connection relationship table is exported from the SCADA system, which contains cable connection point ID, cable segment ID, impedance value, and rated current data.

[0055] Construct a graph structure storage model:

[0056] The node is the cable connection point, and the attributes include spatial coordinates (WGS84) and voltage level;

[0057] The edge is the cable segment, and the attributes include length, material, and electrical parameters (impedance, capacitance);

[0058] Output the graph structure file, support adjacency matrix traversal and shortest path analysis.

[0059] Perform spatio-temporal alignment and fusion processing on the data:

[0060] The data spatio-temporal alignment includes the following steps:

[0061] Uniformly use UTC timestamp for all time series data, and perform sliding average with 1 minute window to eliminate sensor sampling time deviation;

[0062] Convert the geographic coordinates of surface displacement gradient data, FTI data, and cable strain data to the same coordinate system (EPSG:3857), and generate 500m×500m grid data through Kriging interpolation;

[0063] Superimpose the spatial path (polyline coordinate string) of the cable segment with the grid data, extract the environmental monitoring data of the grid where the center point of the cable segment is located, and form the cable segment level fusion data table.

[0064]

[0065] S2. Input the environmental monitoring data into the geomechanical formula, and output the geostress field data;

[0066] The process of inputting environmental monitoring data into geomechanical formula and outputting geostress field data includes:

[0067] (1) Data acquisition stage

[0068] Acquire surface deformation time series data and geological parameter time series data: the acquisition method is similar to S1 step, which is not described here.

[0069] Extract displacement gradient data from surface deformation time series data:

[0070] Calculate the displacement change rate of the surface in the east-west, north-south, and vertical directions at adjacent time points to generate a displacement gradient tensor representing the acceleration trend of deformation, with a unit of millimeters per day.

[0071] Calculate the difference of surface displacement at adjacent time points to generate a displacement gradient tensor , the expression of which is:

[0072]

[0073] wherein, , , : east-west, north-south, and vertical direction displacement, , , : east-west, north-south, and vertical direction displacement change rate, reflecting horizontal extension / compression.

[0074] Calculate the freeze-thaw cycle index FTI(t) according to the geological parameter time series data:

[0075] Collect soil temperature sensor data and volumetric water content data, and calculate the freeze-thaw cycle index based on the freezing point temperature of frozen soil (the calibrated value is -0.5℃). This index combines temperature deviation and water content weight to quantify the severity of freeze-thaw action.

[0076] Calculate the freeze-thaw cycle index FTI(t), the expression of which is:

[0077]

[0078] wherein, is the freezing point temperature of soil, is the temperature sensor data, is the humidity sensor data.

[0079] (2) Data processing stage

[0080] Construct geomechanical formula:

[0081] A four-element mechanical model containing instantaneous elasticity, delayed elasticity and viscous flow component is adopted to describe the mechanical behavior of frozen soil through the stress-strain rate relationship equation, and its differential equation is:

[0082]

[0083] where, is stress, is strain, : instantaneous elastic modulus (MPa), representing the instantaneous deformation response of the soil, : delayed elastic modulus (MPa), reflecting the creep characteristics of the soil, : viscous coefficient (GPa·s), controlling the stress relaxation rate.

[0084] Dynamic parameter assignment:

[0085] Elastic modulus : Linear mapping is generated according to the freeze-thaw cycle index value, with a mapping relationship of 50 MPa modulus increase per unit index increment, and a base value of 100 MPa, expressed as .

[0086] Viscous coefficient : Calculated from the displacement gradient : Dynamically adjusted according to the displacement gradient amplitude, with a 10-fold decrease in the order of magnitude of the viscous coefficient for every 0.5 mm / day increase in the gradient, expressed as .

[0087] Elastic modulus : Set to 30% to reflect the creep characteristics of the soil.

[0088] (3) Data output stage

[0089] Stress field solution:

[0090] The displacement gradient is taken as the boundary condition, and the geomechanical model control equation is solved by the finite element method to generate a spatially continuous distribution of the geostress field, with the maximum principal stress as the key indicator for cable safety assessment, and the three-dimensional geostress field output.

[0091] The displacement gradient is calculated by difference to capture the acceleration stage of frost heaving / thawing settlement, solving the defects of traditional static deformation analysis; the dynamic mapping function FTI(t)→ is established, which takes into account the influence of water content, breaks through the limitations of empirical parameters, and realizes the accurate conversion of geological risks to power grid threats. The stress field data generated based on the above data has improved accuracy.

[0092] S3. Input the grid state data into the cable stress formula, output the cable damage degree, and generate the cable vulnerability index by time domain integration of the cable damage degree;

[0093] The process of inputting the grid state data into the cable stress formula to output the cable vulnerability index includes:

[0094] (1) Data acquisition stage

[0095] Acquire cable strain time series data: the acquisition method is similar to step S1, which is not repeated here.

[0096] Acquire cable strain time series data in real time through a distributed optical fiber sensor network with a sampling frequency ≥ 200 Hz The above data is generated by analyzing the Brillouin scattering spectrum signal, and the frequency shift amount and the strain conversion relationship is:

[0097]

[0098] Wherein, is the strain coefficient, and the value is .

[0099] Temperature compensation can also be based on environmental monitoring data:

[0100] Based on temperature sensor data , temperature compensation is performed on the Brillouin frequency shift:

[0101]

[0102] Wherein, is the temperature coefficient, and the value is , is the real-time temperature of the cable surface, is the reference reference temperature (sensor calibration temperature).

[0103] The deterministic relationship between the frequency shift amount and the strain after synchronous environmental temperature compensation is:

[0104]

[0105] Load the grid topology relationship data stored in the graph structure, extract the electrical parameters (load flow , voltage level ) and cable path space coordinates of the cable section .

[0106] (2) Data processing stage

[0107] Construct the cable stress formula:

[0108] Based on real-time strain amplitude, cable elastic modulus and average thermal stress calculated by ampacity, the dynamic equivalent stress amplitude is converted by modified Goodman criterion. The equivalent stress amplitude in each stress cycle is compared with the fatigue strength coefficient of the material, and the material index dynamically adjusted by the cable aging history is combined to iteratively calculate the cumulative damage.

[0109] Cumulative damage degree of cable is calculated by multi-axial fatigue cumulative model The expression is:

[0110]

[0111] Wherein, is the fatigue strength coefficient, is the material coefficient, is the equivalent stress amplitude.

[0112] Wherein the equivalent stress amplitude is generated by the modified Goodman criterion:

[0113]

[0114] Wherein, is the cable elastic modulus, is the ultimate tensile strength of the cable material, is the average stress of the cable, is the cable material index, is the equivalent strain.

[0115] Dynamic parameter assignment:

[0116] The average stress is calculated by the real-time ampacity of the cable : ;

[0117] The material index is dynamically adjusted by the cable aging history data:

[0118] ;

[0119] (3) Data output stage

[0120] Vulnerability index generation:

[0121] The cumulative damage is integrated in time domain, and through the preset damage threshold and steepness factor, the normalized damage degree index ranging from 0 to 1 is generated. The damage degree is integrated in time domain and normalized, and the formula is:

[0122]

[0123] Wherein, is the steepness factor, used to control the exponential growth slope; is the damage threshold, used to trigger the critical point of exponential growth.

[0124] The steepness factor can be dynamically adjusted, and its adjustment formula is:

[0125]

[0126] wherein, is the reference steepness value, reflecting the basic sensitivity of damage accumulation, which can be uniformly taken as 5.0 as the calculation reference of various cables; is the interlayer influence factor, quantifying the promotion / inhibition characteristics of the i-th layer material of the cable to damage propagation, determined by the material type (such as +0.8 for the insulating layer to promote damage, and -0.3 for the armor layer to inhibit damage, the armor layer refers to the metal material protective layer used in the cable); is the elastic modulus of the i-th layer, indicating the material's ability to resist deformation, and the higher the modulus, the more significant the stress transmission; is the thickness of the i-th layer, affecting its mechanical contribution proportion in the overall structure; is the reference elastic modulus, used as the reference modulus for normalized calculation, taking the value of the dominant material of the cable; is the total thickness of the cable, the sum of the thicknesses of all structural layers, used to calculate the proportion of the thickness of each layer.

[0127] The damage threshold can be dynamically adjusted, and its adjustment formula is:

[0128]

[0129] wherein, is the basic damage threshold, a critical damage value determined by the inherent properties of the cable insulation material, reflecting the material's fatigue resistance; is the terrain stress weight factor, quantifying the influence of geological deformation on the additional load of the cable, and the steeper the terrain, the higher the weight; is the geological deformation rate, indicating the surface displacement speed of the cable buried area, monitored in real time by the Beidou ground enhancement system; is the freeze-thaw correction coefficient, used to represent the attenuation coefficient of the fatigue strength of the material caused by a single freeze-thaw cycle, obtained by inversion from meteorological satellite data; is the cumulative freeze-thaw frequency, used to represent the total number of freeze-thaw cycles experienced by the environment in which the cable is located, reflecting the temperature alternation history; is the aging sensitivity coefficient, indicating the damage threshold decline rate caused by cable material aging per year, strongly related to the insulation type; is the cable operation age: the continuous service time since commissioning, automatically extracted from the system.

[0130] Considering the interference of temperature on Brillouin frequency shift, the influence of temperature change is eliminated by coefficient compensation; the transfer function of load flow→thermal stress→average stress is introduced, breaking the limitation of mechanical and electrical parameters, and upgrading the cable health assessment to predictive maintenance.

[0131] S4. Based on the power grid state data, the geological stress field data and the cable segment level vulnerability index are spatially interpolated to generate the cable segment level geological stress field data set and the cable segment level vulnerability index data set;

[0132] The process of generating the cable segment level geological stress field data set includes:

[0133] Generate the cable segment level stress field data:

[0134] Based on the cable path spatial coordinate set in the power grid topology relationship data, the continuous geological stress field is discretized along the cable direction using the inverse distance weighted interpolation algorithm, and the stress peak value on each cable segment path is extracted as the representative value. The geological stress field is spatially interpolated along the cable path and mapped to the cable segment number in the power grid topology relationship data to generate the cable segment level geological stress field data set:

[0135]

[0136] Wherein, is the maximum principal stress borne by the cable segment.

[0137] Data storage format:

[0138] Stored in the form of space-time matrix, the matrix row index is the cable segment ID, the column index is the timestamp, and the element value is the stress amplitude (unit: kPa).

[0139] The process of generating the cable segment level vulnerability index data set includes:

[0140] Generate the cable segment level vulnerability index:

[0141] Based on the cable path spatial coordinate set in the power grid topology relationship data, the continuous cable vulnerability index is discretized along the cable direction using the inverse distance weighted interpolation algorithm, and the vulnerability index peak value on each cable segment path is extracted as the representative value. The vulnerability index is mapped to the cable segment in the power grid topology to output the cable segment level vulnerability index data set:

[0142]

[0143] Wherein, is the predicted remaining time to reach the preset time.

[0144] The numerical range is defined as 0 to 1:

[0145] Close to 0 means the cable is in a healthy state; close to 1 means there is a risk of fracture.

[0146] Data storage format:

[0147] Stored in a time series database, the primary key is the cable segment ID (uniquely identifies the cable location and electrical properties), and the fields include timestamp, vulnerability index (reflecting the current damage risk level), and predicted remaining life (based on damage growth rate, calculating the countdown to the vulnerability index reaching the preset high-risk threshold).

[0148] 3. Remaining life prediction output

[0149] Based on Implement hierarchical early warning:

[0150]

[0151] The traditional scheme can start the self-healing scheme in advance.

[0152] S5. Fusion of geological stress field data and cable vulnerability index, generate cable segment level coupling risk index data;

[0153] As shown in Figure 2 , the process of fusing geological stress field data and cable vulnerability index to generate cable segment level coupling risk index data includes:

[0154] (1) Data acquisition stage

[0155] Acquire geological stress field data:

[0156] Acquire the cable segment level geological stress field data set in step S4 , where is the maximum principal stress (unit: MPa) borne by the cable segment ;

[0157] Acquire the cable vulnerability index:

[0158] Acquire the cable segment level vulnerability index data set in step S4 , where characterizes the mechanical damage degree of the cable segment ;

[0159] Load dynamic weight parameters:

[0160] Call the machine learning model trained by the historical failure database to output the weight coefficients under the current environmental state , , satisfying .

[0161] (2) Data processing stage

[0162] Spatial coupling analysis:

[0163] Geospatial overlay calculation for displacement gradient hotspots and cable path:

[0164]

[0165] where, is the displacement gradient modulus at the surface grid point, characterizing the surface deformation rate; is the spatial decay factor (default 0.1), controlling the decay rate of distance on deformation influence; denotes the Euclidean distance from coordinate point to the cable path centerline ( ); is the physical length of cable segment .

[0166] When 0.8, update the data and then calculate until .

[0167] When >0.8, activate the fusion process;

[0168] Dynamic weighted fusion:

[0169] Exponential weighting function is used to generate coupling risk indicators:

[0170]

[0171] where, is the dynamic weight coefficient ( ), driven by environmental state; denotes the maximum principal stress (frost heaving pressure / thawing subsidence shear) that cable segment suffers at time; is the critical stress of cable material (mapped from material strength database; denotes the vulnerability index of cable segment (0 = perfect, 1 = failure); is the time decay factor (default value ), controlling the risk sensitivity of remaining life ; is the cable remaining life prediction value.

[0172] Weight The environmental adaptability problem is solved by dynamically controlling the freeze-thaw cycle index FTI(t).

[0173] The calculation formula is:

[0174]

[0175] Dynamic threshold update:

[0176] Periodically adjust the risk threshold value through the Bayesian optimization algorithm :

[0177]

[0178] where, is the conditional probability, indicating the probability of failure when ; is the risk threshold value to be optimized; is the risk over-limit probability, i.e. the probability of exceeding the threshold ; is the failure prior probability (statistically derived from historical failure data).

[0179] (3) Data output step

[0180] Generate coupling risk indicators:

[0181] Output cable segment-level risk data set:

[0182]

[0183] Where the warning level is divided according to :

[0184]

[0185] Data storage and transmission:

[0186] In binary stream format, transmitted to edge computing nodes through 5G URLLC protocol, stored as a space-time matrix: risk matrix = [timestamp, cable segment ID, R value, warning level]

[0187] By introducing threshold filtering, false positive rate is reduced; threshold can be dynamically adjusted to achieve cold region environmental adaptability and improve accuracy. Weight The environmental adaptability problem is solved by dynamically controlling the freeze-thaw cycle index FTI(t).

[0188] S6. When the coupling risk indicator data exceeds the dynamic threshold, generate failure warning signal and failure cable segment positioning data;

[0189] The process of S6 generating failure warning signal and failure cable segment positioning data includes:

[0190] (1) Data acquisition stage

[0191] Acquire coupling risk indicator data:

[0192] Acquire cable segment-level risk dataset output by S4 ;

[0193] Acquire power grid state data:

[0194] Load cable path coordinates in power grid topology relationship data and electrical parameters ;

[0195] Load dynamic threshold parameters:

[0196] Call Bayesian optimization algorithm to periodically update dynamic risk threshold .

[0197] (2) Data processing stage

[0198] Dual threshold condition judgment:

[0199] Synchronize execution for each cable segment :

[0200] Step 1: Risk value judgment:

[0201]

[0202] Alarm logic activation:

[0203] When , execute:

[0204] Generate fault warning signal ;

[0205] Locate fault cable segment coordinates (accurate to meters).

[0206] (3) Data output stage

[0207] Structured warning signal:

[0208] Output JSON format warning data package:

[0209] The data package includes: event ID, cable segment number, coupling risk indicator, fault positioning data, spatial coordinates (latitude and longitude), deviation from deformation hotspots, self-healing strategy pre-judgment, backup line number, and reinforcement scheme code.

[0210] Transmission protocol:

[0211] Broadcast to edge computing nodes and power grid control terminals through 5G URLLC protocol.

[0212] Solve single index false triggering by filtering irrelevant deformation (such as livestock trampling) through spatial coupling threshold and adapting to environmental changes (such as increasing 0.15 during thawing period) by adjusting dynamic risk threshold; reduce coordinate mapping error by fault location optimization; preload line switching / strengthening scheme in early warning signal to reduce response delay.

[0213] S7. According to the fault warning signal and fault cable segment positioning data, generate a self-healing scheme and trigger the power grid control terminal to execute.

[0214] The process of generating a self-healing scheme and triggering the power grid control terminal to execute includes:

[0215] (1) Data acquisition stage

[0216] Obtain the JSON format warning data packet output in step S5, which contains fields: cable segment number, coupling risk index, fault location data, and self-healing strategy pre-judgment.

[0217] Obtain the dynamic parameters of the power grid topology: from the SCADA system, read the standby line load rate (in ) and the load transfer capacity of adjacent substations (unit: MW).

[0218] (2) Data processing stage

[0219] The self-healing scheme includes: load transfer, dispatching reinforcement robots for foundation reinforcement or control circuit breaker for line switching.

[0220] Generate a self-healing strategy according to the matching of the self-healing scheme according to the warning level.

[0221] Broadcast the self-healing strategy to edge computing nodes and power grid control terminals through 5G URLLC protocol.

[0222] Multiple repair schemes, improve the accuracy and efficiency of repair through scheme matching.

[0223] The details of each method step of the intelligent power grid fault rapid positioning and self-healing method are described in detail above, and the following describes a specific application scenario using this embodiment:

[0224] The following is a power grid technical solution embodiment in the background of high-cold regions:

[0225] The Sentinel-1A radar satellite continuously scans the surface of the permafrost zone, generating daily displacement gradient thermal maps with millimeter-level accuracy. When the surface undergoes uneven settlement during the spring thaw period, the system can capture single-day over-limit displacement areas along the cable path (such as stretching deformation caused by glacier movement). Anti-freezing temperature and humidity sensors buried along the cable trench monitor the transition between frost heaving (temperature ≤ 0°C and soil water saturation) and thawing settlement (continuous warming) in real time. For example, in early winter with a large diurnal temperature difference, 8 freeze-thaw state alternations (FTI=8) are recorded in a single day, triggering a geological risk warning. The distributed optical fiber sensing network embedded in the armored cable can still stably capture micro-strains in an environment of -40°C. When the frost heaving pressure squeezes the cable sheath, the system identifies that the strain value of a specific section fluctuates in a sawtooth pattern (reflecting periodic frost heaving stress).

[0226] The FTI index and displacement gradient are input into a four-element geomechanical model to simulate permafrost creep behavior. For example, in a permafrost degradation area, the model output shows that the maximum principal stress in the cable burial zone is concentrated in the front of the thawing landslide body (>120 kPa), which is highly consistent with the historical failure points. Based on strain data and load capacity, the aging damage is calculated through a multi-axial fatigue accumulation model. An old cable that has been in operation for 15 years has a 40% lower damage threshold than a new cable due to the brittleness of the insulation layer (aging sensitivity coefficient β=0.32), and the system marks it as an orange risk 72 hours in advance.

[0227] The geological stress field is mapped to the cable path using the inverse distance weighted interpolation algorithm to generate a segment-level risk matrix. When a segment of the cable is in a high geostress area (>100 kPa) and the vulnerability index is >0.6, the coupled risk indicator soars, triggering a red warning.

[0228] The system automatically associates with the power grid topology data to match the best self-healing solution for high-risk segments. For example:

[0229] Level III (yellow) warning: Start monitoring mode, mobilize unmanned aerial vehicle to inspect the cable tower foundation in suspected settlement area;

[0230] Level I (red) warning: Combined with real-time load data from SCADA, automatically switch to backup line (such as bypassing the permafrost landslide area through a redundant cable ring network).

[0231] In the active thawing area, cold-resistant reinforced robots spray rapid-setting geopolymer along the cable path to form a frost heaving protection layer. The construction coordinates are guided in real time by the GIS positioning data (accuracy ±1 meter) in the warning signal. When the main cable segment needs to be urgently isolated, the 5G URLLC low-latency communication sends load transfer instructions to adjacent substations to ensure uninterrupted power supply for critical loads such as hospitals and heating stations.

[0232] Through the geological-grid coupling analysis framework and the edge intelligent decision chain, the active defense capability of the high-cold power grid against freeze-thaw disasters is improved, and the safe and stable operation of the power grid in extreme environments is ensured.

[0233] Embodiment 2

[0234] As Figure 3 shown, the embodiment also provides a smart grid fault rapid positioning and self-healing system, which includes:

[0235] 100. A data acquisition module for acquiring environmental monitoring data and power grid state data of a current acquisition period;

[0236] 200. A data processing module for inputting the environmental monitoring data into a geomechanics formula and outputting geostress field data; further for inputting the power grid state data into a pre-trained cable stress formula and outputting a cable damage degree, generating a cable vulnerability index by time domain integration of the cable damage degree; further for performing spatial interpolation on the geostress field data and the cable vulnerability index based on the power grid state data, generating a cable segment-level geostress field data set and a cable segment-level vulnerability index data set; further for fusing the cable segment-level geostress field data set and the cable segment-level vulnerability index data set to generate a cable segment-level coupling risk index data;

[0237] 300. A data analysis module for generating a fault warning signal and extracting fault cable segment positioning data from the power grid state data when the cable segment-level coupling risk index data exceeds a preset threshold;

[0238] 400. A data judgment module for generating a self-healing scheme according to the fault warning signal and the fault cable segment positioning data, and triggering a power grid control terminal to execute.

[0239] Embodiment 3

[0240] The embodiment also provides a computing device, which includes:

[0241] a memory for storing a program;

[0242] a processor for executing the computer executable instructions, which, when executed by the processor, implement the smart grid fault rapid positioning and self-healing method.

[0243] Embodiment 4

[0244] The embodiment also provides a computer readable storage medium storing a program, which, when executed by a processor, implements the smart grid fault rapid positioning and self-healing method.

[0245] The storage medium proposed in the embodiment belongs to the same inventive concept as the smart grid fault rapid positioning and self-healing method proposed in the above embodiment, and the technical details not described in the embodiment can be seen from the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0246] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary general hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application are essentially or say the contributions to the prior art

[0247] Part of the technical solutions can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH, a hard disk or an optical disk, etc., including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method of each embodiment of the present application.

[0248] The technical scope of the present application is not limited to the above description, and those skilled in the art can make various modifications and changes to the above embodiments without departing from the technical idea of the present application, and these modifications and changes should all be within the protection scope of the present application.

Claims

1. A method for smart grid fault fast location and self-healing, characterized in that, The method comprises the following steps: acquiring environment monitoring data and power grid state data of a current collection period; inputting the environment monitoring data into a pre-constructed geomechanics formula to output geostress field data; inputting the power grid state data into a pre-constructed cable stress formula to output cable damage degree, and generating a cable vulnerability index by time-domain integration of the cable damage degree; based on the power grid state data, performing spatial interpolation on the geostress field data and the cable vulnerability index to generate a cable segment-level geostress field data set and a cable segment-level vulnerability index data set; fusing the cable segment-level geostress field data set and the cable segment-level vulnerability index data set to generate a cable segment-level coupling risk index data; when the cable segment-level coupling risk index data exceeds a preset threshold, generating a fault warning signal and extracting fault cable segment positioning data from the power grid state data; generating a self-healing scheme according to the fault warning signal and the fault cable segment positioning data, and triggering a power grid control terminal to execute.

2. The method of claim 1, wherein, The environment monitoring data comprises ground deformation time series data and geologic parameter time series data, and the power grid state data comprises cable strain time series data and power grid topology relationship data.

3. The method of claim 1, wherein, The geomechanics formula adopts a four-element mechanical model containing instantaneous elasticity, delayed elasticity and viscous flow components to describe the mechanical behavior of frozen soil through a stress-strain rate relationship equation.

4. The method of claim 1, wherein, The cable stress formula construction process comprises the following steps: based on the power grid state data, converting to obtain equivalent stress amplitude through the Goodman criterion, comparing the equivalent stress amplitude with the material fatigue strength coefficient, combining the cable aging material index, and iteratively calculating the cable damage degree to form the cable stress formula.

5. The method of claim 1, wherein, The next step of time-domain integration of the cable damage degree is: generating a normalized cable vulnerability index ranging from 0 to 1 through a preset damage threshold and a steepness factor.

6. The method of claim 2, wherein, The process of generating the cable segment-level geostress field data set and the cable segment-level vulnerability index data set is specifically as follows: based on the cable path spatial coordinate set in the power grid topology relationship data, the continuous geostress field and the cable vulnerability index are discretized along the cable trend by using the inverse distance weighted interpolation algorithm, and the stress peak value and the vulnerability index peak value on each cable segment path are extracted as the cable segment-level geostress field data set and the cable segment-level vulnerability index data set.

7. The method of claim 6, wherein, The process of fusing the geostress field data and the cable vulnerability index to generate the cable segment-level coupling risk index data comprises the following steps: acquiring the cable segment-level geostress field data set, the cable segment-level vulnerability index data set and a dynamic weight parameter, the weight coefficient being dynamically controlled by a freeze-thaw cycle index; performing geographic spatial overlay calculation on the displacement gradient hotspot area and the cable path according to the cable segment-level geostress field data set and the cable segment-level vulnerability index data set; when the spatial coupling number is greater than a threshold, activating the fusion process, and the threshold being periodically updated by a Bayesian optimization algorithm; generating the coupling risk index according to the dynamic weight parameter by using an exponential weighting function.

8. A smart grid fault fast location and self-healing system, characterized in that, The system is executed by the intelligent power grid fault rapid positioning and self-healing method of any one of claims 1-7, and the system comprises: a data acquisition module for acquiring environment monitoring data and power grid state data; a data processing module configured to input the environmental monitoring data into a geomechanics formula to output geostress field data, and to input the power grid state data into a pre-trained cable stress formula to output cable damage degree, and to generate a cable vulnerability index by time-domain integration of the cable damage degree, and to fuse the geostress field data and the cable vulnerability index to generate a coupling risk index data of a cable section; a data analysis module configured to generate a fault warning signal and fault cable section positioning data when the coupling risk index data exceeds a dynamic threshold and spatial coupling degree data output by spatial coupling analysis of the coupling risk index data and the power grid state data exceeds a preset threshold; a data judgment module configured to generate a self-healing scheme according to the fault warning signal and the fault cable section positioning data, and to trigger a power grid control terminal to execute the self-healing scheme.

9. An electronic device, comprising: comprise: a memory configured to store a program; a processor configured to load the program to execute steps of the intelligent power grid fault rapid positioning and self-healing method according to any one of claims 1-7.

10. A computer-readable storage medium storing a program, characterized in that, the program, when executed by the processor, implements steps of the intelligent power grid fault rapid positioning and self-healing method according to any one of claims 1-7.

Images