Power grid geological disaster monitoring and early warning method and system based on real-time index parameters

Abstract

The invention discloses a power grid geological disaster monitoring and early warning method and system based on real-time index parameters, and the method comprises the steps: collecting power grid region environment data, and carrying out the preprocessing of the data, and obtaining geological disaster influence indexes; after geological disaster influence indexes are standardized, surface objects are formed on a map, and ArcGIS is used for superposing surface object data to divide prediction units; calculating a dynamic parameter of each geological disaster influence index; and constructing a prediction model to carry out disaster early warning. The geological disaster influence factors can be monitored in real time. And in combination with the dynamic parameter model, the geological disaster risk can be evaluated in real time and early warning can be issued, so that the timeliness and accuracy of early warning are remarkably improved. The system integrates various geological disaster influence indexes, and provides comprehensive risk assessment through data standardization and comprehensive analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of geological disaster monitoring, and in particular to a method and system for monitoring and early warning of geological disasters in a power grid based on real-time indicator parameters. Background Art

[0002] High-frequency geological disasters are a major test for the safety and protection of power grids. Therefore, it is of great significance to carry out geological disaster early warning work in power grid areas, so that the geological disaster early warning areas of power grids can take preventive and avoidance measures in a timely manner, maximize the protection of my country's power resource supply capacity, and reduce the property and economic losses of the power energy support industry. Since geological disasters have a very important impact on human production and life, many experts at home and abroad have studied the causes of geological disasters. Among the many causes of geological disasters, the soil conditions themselves are the internal influencing factors, while rainfall is the most important external factor, which often directly induces the occurrence of geological disasters. Through the analysis of the factors that generate geological disasters, as well as the time difference between the influence of the generating factors and the occurrence of geological disasters, people can better warn of geological disasters. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is: how to solve the problems of insufficient real-time performance, limited data integration and analysis capabilities, and insufficient spatial accuracy of disaster prediction in the prior art.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a power grid geological disaster monitoring and early warning method based on real-time indicator parameters, comprising:

[0006] Collect environmental data of the power grid area and pre-process to obtain geological disaster impact indicators;

[0007] After the geological disaster impact indicators are standardized, they are formed into surface objects on the map, and ArcGIS is used to overlay the surface object data and divide the prediction units;

[0008] Calculate the dynamic parameters of each geological hazard impact indicator;

[0009] Build prediction models for disaster warning.

[0010] As a preferred solution of the power grid geological disaster monitoring and early warning method based on real-time indicator parameters described in the present invention, the power grid area environmental data includes soil conditions P, precipitation Q, surface creep R, slope S, and surface vegetation T; soil conditions include topography, stratum lithology, slope type, and geological structure.

[0011] As a preferred solution of the power grid geological disaster monitoring and early warning method based on real-time index parameters described in the present invention, wherein: the geological disaster impact index includes preprocessing the collected environmental data to obtain the geological disaster impact index;

[0012] According to the information index, the disaster-prone areas are divided into four categories: high-prone areas, medium-prone areas, low-prone areas, and low-prone areas. The most prone index of soil conditions P = 100 points is used to quantitatively evaluate the land conditions. The formula is expressed as:

[0013]

[0014] Among them, P represents the soil condition evaluation index; N represents the number of influencing factors; A i represents the surface area of ​​the ith factor; Indicates that the i-th factor is in position The influence function at V i represents the volume of the i-th factor; Indicates that the i-th factor is in position The influence function at κ is the normalization constant; σ i represents the standardized value of the i-th factor; μ represents the mean of the influencing factor;

[0015] The mathematical modeling formula of daily comprehensive rainfall is used to conduct quantitative analysis of precipitation, which is expressed as follows:

[0016]

[0017] Among them, Q represents the current day's comprehensive rainfall; Q0 represents the baseline precipitation; Q i represents the precipitation on the past i-th day; a i represents the attenuation parameter of precipitation on the i-th day, which gradually decreases as i increases; for the quantitative expression of rainfall, the minimum and maximum daily comprehensive rainfall in the local history are selected as 0 and 100 respectively to convert the current daily comprehensive rainfall Q;

[0018] GPS and other monitoring technologies can be used to regularly monitor the landslide body and the bank slope section. A professional geological disaster monitoring network can be established to monitor two monitoring points every half a month to obtain the point displacement, and draw a displacement map of the detection point for quantitative analysis.

[0019] Using DEM data to generate patches with different slopes to obtain slope maps, disaster prediction is performed at the slope patch level. The formula is expressed as:

[0020]

[0021] Among them, z represents the elevation value; represents the rate of change of elevation along the x direction; It represents the rate of change of elevation along the y direction; let the standard value of slope be S, when the slope is 90°, S=100; when the slope is 0, S=0;

[0022] The forest coverage rate is used as the surface vegetation index T for geological disaster early warning; 100% forest coverage rate T=100 and 0 forest coverage rate T=0 are used as the standard score for quantitative analysis.

[0023] As a preferred solution of the power grid geological disaster monitoring and early warning method based on real-time indicator parameters described in the present invention, wherein: the division of prediction units includes converting the standardized indicator data into a GIS supported format, and managing each indicator as a layer; using ArcGIS tools to generate a surface object from the standardized indicator data; superimposing each layer to generate a comprehensive layer containing all influencing indicators; dividing the area into a number of prediction units according to the superimposed comprehensive layer; each unit contains the standardized value of each influencing indicator;

[0024] The collected data are standardized to ensure that the indicators are compared at the same scale. Each geographical unit is regarded as a node in the network. The edges between nodes are defined according to the similarity or proximity of the indicators of geological hazards. The weight of the edge is calculated based on the similarity of the indicators. The similarity calculation formula is expressed as:

[0025]

[0026] Among them, X ik and X jk Respectively represent the values ​​of node i and node j on the kth standardized index; n represents the number of influencing indicators; S ij Represents the similarity between nodes i and j;

[0027] Use community detection algorithm to identify community structure. Initially, each node is assigned to an independent community. Calculate the modularity gain after moving a node to its neighbor community. Try to move each node to the community of the neighbor node one by one, and select the moving plan with the largest modularity gain. Treat each community as a supernode, build a new network, and repeat the community modularity gain step until the modularity no longer increases significantly.

[0028] Modularity Q is an indicator to measure the quality of community structure in the network; the modularity calculation formula is expressed as:

[0029]

[0030] Among them, A ij represents the edge weight between nodes i and j; k i and k jdenote the degrees of nodes i and j respectively; m denotes the total weight of the edges in the graph; δ(c i ,c j ) represents the indicator function, which takes the value 1 when nodes i and j belong to the same community, and takes the value 0 otherwise;

[0031] After the community detection algorithm is run, the nodes in the network are divided into different communities. According to the results of community detection, each community is regarded as a prediction unit; each prediction unit contains similar geological disaster impact indicators.

[0032] As a preferred scheme of the power grid geological disaster monitoring and early warning method based on real-time indicator parameters described in the present invention, the dynamic parameters of the geological disaster impact index include initializing the impact index; soil conditions, precipitation, surface creep, slope, and surface vegetation have different degrees of influence on geological disasters, and an initial impact proportional coefficient is set, including soil condition weight coefficient α, precipitation weight coefficient β, surface creep weight coefficient γ, slope weight coefficient δ, and surface vegetation weight coefficient ε.

[0033] As a preferred solution of the power grid geological disaster monitoring and early warning method based on real-time indicator parameters described in the present invention, the prediction model includes: assuming that the model adjusts the weight coefficient through the past n prediction data, the geological disaster assessment formula is expressed as:

[0034] M=αP+βQ+γR+δS+εT

[0035] A dynamic adjustment mechanism is introduced to update the weight coefficients using historical data; the weight coefficients are initialized to α0, β0, γ0, δ0, ∈0; the initialization covariance matrix formula is expressed as:

[0036] P0=λ -1 I

[0037] Among them, λ represents the forgetting factor, I represents the unit matrix; for each new observation data (P t ,Q t ,R t ,S t ,T t ,M t ), the prediction error calculation formula is expressed as:

[0038] e t =M t -(α t-1 P t +β t-1 Q t +γ t-1 R t +δ t-1 S t +∈ t-1 Tt )

[0039] Among them, e t represents the error of the t-th prediction;

[0040] The formula for calculating the gain vector is expressed as:

[0041]

[0042] Among them, X t =[P t ,Q t ,R t ,S t ,T t ] T ;

[0043] The formula for updating the weight coefficient is expressed as:

[0044] θ t =θ t-1 +K t e t

[0045] Among them, θ t =[α t ,β t ,γ t ,δ t ,ε t ] T ; α t ,β t ,γ t ,δ t ,ε t It represents the impact ratio coefficient of each geological disaster impact index after iterative update;

[0046] The formula for updating the covariance matrix is ​​expressed as:

[0047]

[0048] Use the dynamic prediction model formula to calculate and update the geological disaster risk value M0 for each prediction unit:

[0049] M0=α t P+β t Q+γ t R+δ t S+∈ t T

[0050] A quantitative analysis is conducted on the geological disasters that have occurred in the region, and scores are given according to the degree of damage, with the most severe degree of damage being M=100. The impact proportional coefficient of the geological disaster impact index is updated after each prediction.

[0051] As a preferred solution of the power grid geological disaster monitoring and early warning method based on real-time indicator parameters described in the present invention, wherein: the disaster early warning includes determining the threshold range of the M value based on historical geological disaster risk data;

[0052] When M>80, it means that the prediction unit area is a high-risk area, which is very prone to geological disasters and needs to take immediate preventive and emergency measures; when 60≤M≤80, it means that the prediction unit area is a medium-high risk area, with a high risk of geological disasters, and needs close monitoring and geological disaster prevention measures; when 40≤M<60, it means that the prediction unit area is a medium-low risk area, with a certain risk of geological disasters, and needs routine monitoring and prevention measures; when M<40, it means that the prediction unit area is a low-risk area, with a low risk of geological disasters, and maintains routine monitoring;

[0053] Through sensor networks, meteorological stations, remote sensing technology and other means, geological disaster impact indicator data are collected in real time, and early warning information is updated in real time based on the latest data and calculation results.

[0054] A power grid geological disaster monitoring and early warning system based on real-time indicator parameters using any method as described in the present invention, wherein:

[0055] The data collection and preprocessing module collects environmental data of the power grid area, including soil conditions, precipitation, surface creep, slope, and surface vegetation; cleans and standardizes the collected data to ensure data quality and consistency;

[0056] The geological disaster impact index standardization and map display module forms surface objects on the map with the standardized geological disaster impact index, and uses ArcGIS to overlay the surface object data and divide the prediction units;

[0057] Dynamic parameter calculation module calculates the dynamic parameters of each geological disaster impact indicator; establishes a database for recording historical geological disaster data, regularly updates the database, and recalculates dynamic parameters to ensure the real-time and accuracy of the model;

[0058] The prediction model and early warning module builds a prediction model for geological disaster early warning; generates early warning information including risk level, specific impact indicator values ​​and recommended measures; releases early warning information through multiple channels; establishes a user feedback mechanism, receives on-site feedback information, and corrects and improves the prediction model.

[0059] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0060] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0061] Beneficial effects of the present invention: Based on GPS technology and real-time data collection, the present invention can realize real-time monitoring of geological disaster influencing factors. Combined with the dynamic parameter model, it can evaluate the geological disaster risk in real time and issue early warnings, which significantly improves the timeliness and accuracy of the early warning. The system integrates a variety of geological disaster influencing indicators (such as soil conditions, precipitation, surface creep, slope and surface vegetation, etc.), and provides a comprehensive risk assessment through data standardization and comprehensive analysis. This multi-source data fusion improves the accuracy and reliability of the prediction. The present invention introduces a dynamic parameter calculation method, which can adaptively adjust the model parameters through historical data analysis and real-time adjustment. This dynamic adjustment capability improves the flexibility and adaptability of the prediction model, and can better cope with complex and changeable geological disaster risks. The system realizes the automated process of data collection, processing, analysis and early warning, reducing human intervention and operational errors. Combined with machine learning and big data analysis technology, the system can continuously optimize and improve the performance of the early warning model and has intelligent characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0063] Figure 1 An overall flow chart of a power grid geological disaster monitoring and early warning method based on real-time indicator parameters provided by the first embodiment of the present invention;

[0064] Figure 2 A detection point displacement map in a power grid geological disaster monitoring and early warning method based on real-time indicator parameters provided in a second embodiment of the present invention;

[0065] Figure 3 A five-factor superposition division prediction unit diagram of a power grid geological disaster monitoring and early warning method based on real-time indicator parameters provided in the second embodiment of the present invention;

[0066] Figure 4 A prediction unit M0 value classification diagram of a power grid geological disaster monitoring and early warning method based on real-time indicator parameters is provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0068] Example 1

[0069] Reference Figure 1 , which is an embodiment of the present invention, provides a power grid geological disaster monitoring and early warning method based on real-time indicator parameters, comprising:

[0070] S1: Collect environmental data of the power grid area and pre-process to obtain geological disaster impact indicators.

[0071] Furthermore, the grid area environmental data include soil conditions P, precipitation Q, surface creep R, slope S, and surface vegetation T; soil conditions include topography, stratum lithology, slope type, and geological structure.

[0072] Furthermore, the geological disaster impact index includes preprocessing the collected environmental data to obtain the geological disaster impact index.

[0073] Furthermore, the occurrence of geological disasters in mountainous power grids is greatly affected by soil conditions, precipitation, surface creep, slope, surface vegetation (human influence) and other factors along the power grid. However, each factor has different effects in different periods. When geological action is active, the degree of influence of each factor on geological disasters will change to a certain extent. It is of great significance to add this situation to geological disaster warning. As an important condition, soil quality can be quantified as a fixed parameter to affect the occurrence of geological disasters in early warning. Rainfall can quantify the rainfall data collected by the meteorological department and the expected rainfall in 48 hours to predict the occurrence of geological disasters. The occurrence of geological disasters is not synchronized with the precipitation process, but has a certain lag, and generally occurs within 72 hours after precipitation. Therefore, the factors that cause geological disasters are selected as soil conditions, precipitation, surface creep, slope, and surface vegetation (human influence).

[0074] Furthermore, soil conditions: topography, stratum lithology, slope type, geological structure, etc., as well as different soil viscosity and friction between soil and rock, each place has different influence on geological disasters.

[0075] Furthermore, precipitation: precipitation is the most important factor causing geological disasters, and most disaster research starts with precipitation.

[0076] Furthermore, surface creep: surface creep can cause landslides, collapses, unstable slopes, bank collapses, mudslides and other geological disasters.

[0077] Furthermore, slope: slope is an important influencing condition for landslides and mudslides.

[0078] Furthermore, surface vegetation: vegetation plays an important role in natural disasters such as soil erosion and debris flow, and its impact should be considered when establishing a geological disaster early warning system.

[0079] Furthermore, soil conditions. According to information indicators such as topography, soil fragmentation, and weathering layer depth, disaster-prone areas are divided into four categories: high-prone areas (80-100), medium-prone areas (60-80), low-prone areas (40-60), and low-prone areas (0-40). Soil experts make quantitative evaluations of land conditions based on the soil condition's most probable index P = 100 points according to the susceptibility of geological disasters.

[0080] Furthermore, according to the information indicators, the disaster-prone areas are divided into four categories: high-prone areas, medium-prone areas, low-prone areas, and low-prone areas. The most prone index of soil conditions P = 100 points is used to quantitatively evaluate the land conditions. The formula is expressed as:

[0081]

[0082] Among them, P represents the soil condition evaluation index; N represents the number of influencing factors; A i represents the surface area of ​​the ith factor; Indicates that the i-th factor is in position The influence function at V i represents the volume of the i-th factor; Indicates that the i-th factor is in position The influence function at κ is the normalization constant; σ i represents the standardized value of the i-th factor; μ represents the mean of the influencing factors.

[0083] Furthermore, the mathematical modeling formula of daily comprehensive rainfall is used to conduct quantitative analysis of precipitation, which is expressed as follows:

[0084]

[0085] Among them, Q represents the current day's comprehensive rainfall; Q0 represents the baseline precipitation; Q i represents the precipitation on the past i-th day; a i It represents the attenuation parameter of precipitation on the i-th day, which gradually decreases as i increases. For the quantitative expression of rainfall, the minimum and maximum daily comprehensive rainfall in local history are selected as 0 and 100 respectively to convert the current daily comprehensive rainfall Q.

[0086] Furthermore, GPS and other monitoring technologies can be used to implement regular monitoring of landslide bodies and slope sections, and a professional geological disaster monitoring network can be established to monitor two monitoring points every half a month to obtain point displacements, and draw detection point displacement maps for quantitative analysis.

[0087] Furthermore, DEM data is used to generate patches with different slopes to obtain slope maps for disaster prediction at the slope patch level. The formula is expressed as:

[0088]

[0089] Among them, z represents the elevation value; represents the rate of change of elevation along the x direction; It represents the rate of change of elevation along the y direction; let the standard slope value S be S, when the slope is 90°, S=100; when the slope is 0, S=0.

[0090] Furthermore, the forest coverage rate is used as the surface vegetation index T for geological disaster early warning; with 100% forest coverage rate T=100 and 0 forest coverage rate as the standard score T=0, a quantitative analysis is conducted.

[0091] It should be noted that the landslide high-prone area. The distribution density is greater than 0.03 / km2. The terrain is a high mountainous area. The cut and broken rock and soil types are mainly clastic rocks. The depth of the slope weathering layer is greater than 5m. The landslide medium-prone area: the distribution density is 0.01-0.03 / km2. The terrain is a high mountainous area. The cut and broken rock and soil types are mainly clastic rocks. The landslide low-prone area: there are sporadic landslides. The distribution density is less than 0.01 / km2. The landslide-unlikely area: no landslide geological disasters have been found so far. The terrain is gentle and the rock slopes are relatively stable.

[0092] S2: After the geological disaster impact indicators are standardized, they are formed into surface objects on the map, and ArcGIS is used to overlay the surface object data and divide the prediction units.

[0093] Furthermore, dividing the prediction units includes converting the standardized indicator data into a GIS-supported format and managing each indicator as a layer; using ArcGIS tools to generate surface objects from the standardized indicator data; overlaying each layer to generate a comprehensive layer containing all influencing indicators; dividing the area into several prediction units based on the overlaid comprehensive layer; each unit contains the standardized value of each influencing indicator.

[0094] Furthermore, the collected data are standardized to ensure that the indicators are compared on the same scale, and each geographical unit is regarded as a node in the network; the edges between nodes are defined according to the similarity or proximity of the geological hazard impact indicators; the weight of the edge is calculated based on the similarity of the impact indicators; the similarity calculation formula is expressed as:

[0095]

[0096] Among them, X ik and X jk Respectively represent the values ​​of node i and node j on the kth standardized index; n represents the number of influencing indicators; S ij Represents the similarity between nodes i and j.

[0097] Furthermore, a community detection algorithm is used to identify community structure. Initially, each node is assigned to an independent community. The modularity gain after moving a node to its neighbor community is calculated. Each node tries to move to the community of the neighbor node one by one, and the movement plan with the largest modularity gain is selected. Each community is regarded as a supernode, a new network is constructed, and the community modularity gain step is repeated until the modularity no longer increases significantly.

[0098] Furthermore, modularity Q is an indicator to measure the quality of the community structure in the network; the modularity calculation formula is expressed as:

[0099]

[0100] Among them, A ij represents the edge weight between nodes i and j; k i and k j denote the degrees of nodes i and j respectively; m denotes the total weight of the edges in the graph; δ(c i ,c j ) represents the indicator function, which takes the value 1 when nodes i and j belong to the same community and 0 otherwise.

[0101] It should be noted that after the community detection algorithm is run, the nodes in the network are divided into different communities. According to the results of community detection, each community is regarded as a prediction unit; each prediction unit contains similar geological disaster impact indicators.

[0102] S3: Calculate the dynamic parameters of each geological hazard impact indicator.

[0103] Furthermore, the dynamic parameters of the geological disaster impact index include initializing the impact index; soil conditions, precipitation, surface creep, slope, and surface vegetation have different degrees of influence on geological disasters, setting the initial impact proportional coefficient, soil condition weight coefficient α, precipitation weight coefficient β, surface creep weight coefficient γ, slope weight coefficient δ, and surface vegetation weight coefficient ε.

[0104] Furthermore, the debris flow is highly prone to occur. Gravity erosion such as gully landslides is serious, with many deep landslides and large bank collapses; the loose rock and soil reserves along the gully river channel are greater than the development of alluvial fans. Medium-prone areas for debris flow: gully landslides are mostly shallow landslides and small and medium-sized bank collapses; the river channel along the gully is loose, and the rock and soil reserves are greater than 105m2 / km2; the longitudinal gradient of gully development is greater than 20%, and alluvial fans are developed. Medium-prone areas for debris flow: gully landslides are mostly shallow, layer landslides and small and medium-sized bank collapses; the loose rock and soil reserves along the gully river channel are (5-10) 1104m2 / km2.

[0105] Furthermore, in the area with low debris flow risk, there are sporadic landslides, bank collapses, and loose rock and soil reserves along the ditch and river channels are (5-1)×104m3 / km2. In the area with low debris flow risk, there are no landslides, bank collapses, and loose rock and soil reserves along the ditch and river channels are less than 1×104m3 / km2; the slope is relatively stable.

[0106] Furthermore, precipitation data is obtained. The present invention adopts the concept of daily comprehensive rainfall. Daily comprehensive rainfall refers to the equivalent rainfall in the rainfall process that affects the formation of landslides, landslides and flows on that day, and its value is equal to the sum of the rainfall on that day and the product of the rainfall on each day of the previous 10 days (obtained by empirical statistics) and its influencing parameters.

[0107] Furthermore, since the impact of a certain day's precipitation on disasters gradually weakens over time until it disappears, which is a weakening process, the attenuation parameter λ can be introduced and it is assumed that ai = λi, where λ = 0.75. For the quantitative expression of rainfall, the minimum and maximum daily comprehensive rainfall in the local history are selected as 0 and 100 respectively, and the current daily comprehensive rainfall Q is converted on this basis.

[0108] Furthermore, surface creep increases the probability of geological disasters. GPS and other monitoring technologies can be used to regularly monitor landslides and bank slopes (the number of tests can be increased during periods of frequent geological disasters). A professional geological disaster monitoring network is established to monitor two monitoring points every half a month to obtain point displacement. A detection point displacement map can be drawn as follows: Figure 1 As shown. Figure 1 It is easy to see that the probability of geological disasters occurring at point D2 is much greater than that at D1. As a condition for geological disaster warning, it is quantified and represented by R. The displacement of 2m is set as R = 100 standard points, and the remaining displacement quantities are converted according to standard points.

[0109] Furthermore, slope is a mechanical factor affecting the occurrence of geological disasters. Steep slopes with loose soil are areas where geological disasters often occur. Use DEM data to generate patches with different slopes to obtain slope maps to predict disasters at the slope patch level. Set the slope standard value S when the slope is 90° S = 100; when the slope is 0, S = 0. Use this as the standard to convert the slope data to the standard value.

[0110] Furthermore, surface vegetation can effectively prevent the occurrence of geological disasters, especially mudslides and landslides. The forest coverage rate is used as an indicator of geological disaster warning, and its value is T. With 100% forest coverage rate, T = 100 points, and 0 forest coverage rate as the standard score T = 0.

[0111] It should be noted that the impact of a certain day's precipitation on disasters gradually weakens and disappears over time, that is, a weakening process, so an attenuation parameter can be introduced. For the quantitative expression of rainfall, the maximum and minimum daily comprehensive rainfall in the local history are selected as 100 and 0 respectively, and the current daily comprehensive rainfall Q is converted on this basis.

[0112] S4: Build a prediction model for disaster warning.

[0113] Furthermore, the prediction model includes, assuming that the model adjusts the weight coefficient through the past n prediction data, and the geological disaster assessment formula is expressed as:

[0114] M=αP+βQ+γR+δS+εT

[0115] Furthermore, a dynamic adjustment mechanism is introduced to update the weight coefficients using historical data; the weight coefficients are initialized α0, β0, γ0, δ0, ∈ 0; the initialization covariance matrix formula is expressed as:

[0116] P0=λ -1 I

[0117] Among them, λ represents the forgetting factor, I represents the unit matrix; for each new observation data (P t ,Q t ,R t ,S t ,T t ,M t ), the prediction error calculation formula is expressed as:

[0118] e t =M t -(α t-1 P t +β t-1 Q t +γ t-1 R t +δ t-1 S t +∈ t-1 T t )

[0119] Among them, e t represents the error of the t-th prediction.

[0120] Furthermore, the formula for calculating the gain vector is expressed as:

[0121]

[0122] Among them, X t =[P t ,Q t ,R t ,S t ,T t ] T .

[0123] Furthermore, the formula for updating the weight coefficient is expressed as:

[0124] θ t =θ t-1 +K t e t

[0125] Among them, θ t =[α t ,β t ,γ t ,δ t ,∈ t ] T ; α t ,β t ,γ t ,δ t ,ε t It represents the impact proportion coefficient of each geological disaster impact indicator after iterative update.

[0126] Furthermore, the formula for updating the covariance matrix is ​​expressed as:

[0127]

[0128] Furthermore, the dynamic prediction model formula is used to calculate and update the geological disaster risk value M0 for each prediction unit:

[0129] M0=α t P+β t Q+γ t R+δ t S+∈ t T

[0130] Furthermore, a quantitative analysis is conducted on the geological disasters that have occurred in the region, and the damage is scored according to the degree of damage, with the most severe damage M = 100. The impact ratio coefficient of the geological disaster impact index is updated after each prediction. Disaster warning includes determining the threshold range of the M value based on historical geological disaster risk data.

[0131] Furthermore, when M>80, it indicates that the prediction unit area is a high-risk area, which is very prone to geological disasters and requires immediate prevention and emergency measures; when 60≤M≤80, it indicates that the prediction unit area is a medium-high risk area, with a high risk of geological disasters, requiring close monitoring and geological disaster prevention measures; when 40≤M<60, it indicates that the prediction unit area is a medium-low risk area, with a certain risk of geological disasters, requiring routine monitoring and prevention measures; when M<40, it indicates that the prediction unit area is a low-risk area, with a low risk of geological disasters, and requires routine monitoring.

[0132] Furthermore, through sensor networks, weather stations, remote sensing technology and other means, data on geological disaster impact indicators are collected in real time, and warning information is updated in real time based on the latest data and calculation results.

[0133] It should be noted that the impact index is initialized first. The influence of soil conditions, precipitation, surface creep, slope, and surface vegetation (human influence) on geological disasters varies. The initial impact ratios are set to 30%, 40%, 10%, 10%, and 10%, respectively. Dynamic impact parameters are then generated. A quantitative analysis of the geological disasters that have occurred in the region is performed, and the scores are given according to the degree of damage, with the most severe degree of damage being M = 100.

[0134] On the other hand, this embodiment also provides a power grid geological disaster monitoring and early warning system based on real-time indicator parameters, which includes:

[0135] The data collection and preprocessing module collects environmental data of the power grid area, including soil conditions, precipitation, surface creep, slope and surface vegetation; cleans and standardizes the collected data to ensure data quality and consistency.

[0136] The geological disaster impact index standardization and map display module converts the standardized geological disaster impact indicators into surface objects on the map, uses ArcGIS to overlay the surface object data, and divides the prediction units.

[0137] The dynamic parameter calculation module calculates the dynamic parameters of each geological disaster impact indicator; establishes a database for recording historical geological disaster data, regularly updates the database, and recalculates the dynamic parameters to ensure the real-time and accuracy of the model.

[0138] The prediction model and early warning module builds a prediction model for geological disaster early warning; generates early warning information including risk level, specific impact indicator values ​​and recommended measures; releases early warning information through multiple channels; establishes a user feedback mechanism, receives on-site feedback information, and corrects and improves the prediction model.

[0139] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0140] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0141] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0142] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0143] Example 2

[0144] Reference Figure 2-4 , which is an embodiment of the present invention, provides a power grid geological disaster monitoring and early warning method based on real-time indicator parameters. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0145] For administrative regions, geological disaster prediction is carried out in the small areas divided into them. Figure 2 As shown. The present invention selects five geological disaster impact indicators, among which soil conditions, slope, and vegetation coverage are all surface objects, and the collection results of surface creep and precipitation data are all point objects. The interpolation scheme is used to interpolate the entire area, and the level is set and then expressed as a surface object. At this time, each indicator impact value can be standardized to form a surface object on the map. Use ArcGIS to overlay its surface layer data and divide it into smaller areas as prediction units, such as Figure 3 shown.

[0146] Calculation of dynamic parameters: The calculation of dynamic parameters is realized by computer programming. First, a database table is established to record historical geological disasters (this part of the records will be kept as part of the system for historical disaster queries). Then the most recent N records are selected to form C 5 N Programs are written to solve these equations, and finally the influencing parameters α, β, γ, δ, ε are calculated by averaging.

[0147] Model implementation: After the prediction units are divided, each prediction unit has the standard values ​​of five factors: soil conditions, precipitation, surface creep, slope, and surface vegetation (human influence). The influencing parameters α, β, γ, δ, and ε are added to calculate the possible value of geological disasters according to the formula, namely:

[0148] M0=αP0×30%+βQ0×40%+γR0×10%+δS×10%+εT0×10%

[0149] According to the value of M0, the possibility of geological disasters can be determined and geological disaster warnings can be issued. Figure 4shown. Figure 4 The black area is where the M0 value is greater than 80, which is the most prone to geological disasters; the gray area is where the M0 value is between 60 and 80, where geological disasters are likely to occur. Based on the above predictions, the administrative area to which the prediction unit belongs can be analyzed and targeted warnings can be issued for the administrative area.

[0150] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power grid geological disaster monitoring and early warning method based on real-time indicator parameters, characterized in that: include: Collect environmental data of the power grid area and pre-process to obtain geological disaster impact indicators; After the geological disaster impact indicators are standardized, they are formed into surface objects on the map, and ArcGIS is used to overlay the surface object data and divide the prediction units; Calculate the dynamic parameters of each geological hazard impact indicator; Build prediction models for disaster warning.

2. The power grid geological disaster monitoring and early warning method based on real-time indicator parameters as claimed in claim 1 is characterized by: The grid area environmental data include soil conditions P, precipitation Q, surface creep R, slope S, and surface vegetation T; soil conditions include topography, stratum lithology, slope type, and geological structure.

3. The power grid geological disaster monitoring and early warning method based on real-time indicator parameters as claimed in claim 2 is characterized by: The geological disaster impact index includes preprocessing the collected environmental data to obtain the geological disaster impact index; According to the information index, the disaster-prone areas are divided into four categories: high-prone areas, medium-prone areas, low-prone areas, and low-prone areas. The most prone index of soil conditions P = 100 points is used to quantitatively evaluate the land conditions. The formula is expressed as: Among them, P represents the soil condition evaluation index; N represents the number of influencing factors; A i represents the surface area of ​​the ith factor; Indicates that the i-th factor is in position The influence function at V i represents the volume of the i-th factor; Indicates that the i-th factor is in position The influence function at κ is the normalization constant; σ i represents the standardized value of the i-th factor; μ represents the mean of the influencing factor; The mathematical modeling formula of daily comprehensive rainfall is used to conduct quantitative analysis of precipitation, which is expressed as follows: Among them, Q represents the current day's comprehensive rainfall; Q0 represents the baseline precipitation; Q i represents the precipitation on the past i-th day; a i represents the attenuation parameter of precipitation on the i-th day, which gradually decreases as i increases; for the quantitative expression of rainfall, the minimum and maximum daily comprehensive rainfall in the local history are selected as 0 and 100 respectively to convert the current daily comprehensive rainfall Q; GPS and other monitoring technologies can be used to regularly monitor the landslide body and the bank slope section. A professional geological disaster monitoring network can be established to monitor two monitoring points every half a month to obtain the point displacement, and draw a displacement map of the detection point for quantitative analysis. Using DEM data to generate patches with different slopes to obtain slope maps, disaster prediction is performed at the slope patch level. The formula is expressed as: Among them, z represents the elevation value; It represents the rate of change of elevation along the x direction; It represents the rate of change of elevation along the y direction; let the standard value of slope be S, when the slope is 90°, S=100; when the slope is 0, S=0; The forest coverage rate is used as the surface vegetation index T for geological disaster early warning; 100% forest coverage rate T=100 and 0 forest coverage rate T=0 are used as the standard score for quantitative analysis.

4. The power grid geological disaster monitoring and early warning method based on real-time indicator parameters as claimed in claim 3 is characterized by: The division of the prediction units includes converting the standardized indicator data into a GIS supported format, managing each indicator as a layer; using ArcGIS tools to generate a surface object from the standardized indicator data; superimposing each layer to generate a comprehensive layer containing all influencing indicators; dividing the area into a number of prediction units according to the superimposed comprehensive layer; each unit contains the standardized value of each influencing indicator; The collected data are standardized to ensure that the indicators are compared at the same scale. Each geographical unit is regarded as a node in the network. The edges between nodes are defined according to the similarity or proximity of the indicators of geological hazards. The weight of the edge is calculated based on the similarity of the indicators. The similarity calculation formula is expressed as: Among them, X ik and X jk Respectively represent the values ​​of node i and node j on the kth standardized index; n represents the number of influencing indicators; S ij Represents the similarity between nodes i and j; Use community detection algorithm to identify community structure. Initially, each node is assigned to an independent community. Calculate the modularity gain after moving a node to its neighbor community. Try to move each node to the community of the neighbor node one by one, and select the moving plan with the largest modularity gain. Treat each community as a supernode, build a new network, and repeat the community modularity gain step until the modularity no longer increases significantly. Modularity Q is an indicator to measure the quality of community structure in the network; the modularity calculation formula is expressed as: Among them, A ij represents the edge weight between nodes i and j; k i and k j denote the degrees of nodes i and j respectively; m denotes the total weight of the edges in the graph; δ(c i ,c j ) represents the indicator function, which takes the value 1 when nodes i and j belong to the same community, and takes the value 0 otherwise; After the community detection algorithm is run, the nodes in the network are divided into different communities. According to the results of community detection, each community is regarded as a prediction unit; each prediction unit contains similar geological disaster impact indicators.

5. The power grid geological disaster monitoring and early warning method based on real-time indicator parameters as claimed in claim 4 is characterized by: The dynamic parameters of the geological disaster impact index include initializing the impact index; the soil conditions, precipitation, surface creep, slope, and surface vegetation have different degrees of influence on geological disasters, setting the initial impact proportional coefficient, soil condition weight coefficient α, precipitation weight coefficient β, surface creep weight coefficient γ, slope weight coefficient δ, and surface vegetation weight coefficient ε.

6. The power grid geological disaster monitoring and early warning method based on real-time indicator parameters as claimed in claim 5 is characterized by: The prediction model includes: assuming that the model adjusts the weight coefficient through the past n prediction data, the geological disaster assessment formula is expressed as: M=αP+βQ+γR+δS+εT A dynamic adjustment mechanism is introduced to update the weight coefficients using historical data; the weight coefficients are initialized to α0, β0, γ0, δ0, ∈0; the initialization covariance matrix formula is expressed as: P0=λ -1 I Among them, λ represents the forgetting factor, I represents the unit matrix; for each new observation data (P t ,Q t ,R t ,S t ,T t ,M t ), the prediction error calculation formula is expressed as: e t =M t -(a t-1 P t +b t-1 Q t +g t-1 R t +d t-1 S t +e t-1 T t ) Among them, e t represents the error of the t-th prediction; The formula for calculating the gain vector is expressed as: Among them, X t =[P t ,Q t ,R t ,S t ,T t ] T ; The formula for updating the weight coefficient is expressed as: i t =θ t-1 +K t e t Among them, θ t =[α t ,β t ,γ t ,δ t ,∈ t ] T ; α t ,β t ,γ t ,δ t ,ε t It represents the impact ratio coefficient of each geological disaster impact index after iterative update; The formula for updating the covariance matrix is ​​expressed as: Use the dynamic prediction model formula to calculate and update the geological disaster risk value M0 for each prediction unit: M0=α t P+β t Q+γ t R+δ t S+∈ t T A quantitative analysis is conducted on the geological disasters that have occurred in the region, and scores are given according to the degree of damage, with the most severe degree of damage being M=100. The impact proportional coefficient of the geological disaster impact index is updated after each prediction.

7. The power grid geological disaster monitoring and early warning method based on real-time indicator parameters as claimed in claim 6 is characterized by: The disaster warning includes determining the threshold range of the M value based on historical geological disaster risk data; When M>80, it means that the prediction unit area is a high-risk area, which is very prone to geological disasters and needs to take immediate preventive and emergency measures; when 60≤M≤80, it means that the prediction unit area is a medium-high risk area, with a high risk of geological disasters, and needs close monitoring and geological disaster prevention measures; when 40≤M<60, it means that the prediction unit area is a medium-low risk area, with a certain risk of geological disasters, and needs routine monitoring and prevention measures; when M<40, it means that the prediction unit area is a low-risk area, with a low risk of geological disasters, and maintains routine monitoring; Through sensor networks, meteorological stations, remote sensing technology and other means, geological disaster impact indicator data are collected in real time, and early warning information is updated in real time based on the latest data and calculation results.

8. A power grid geological disaster monitoring and early warning system based on real-time indicator parameters using the method according to any one of claims 1 to 7, characterized in that: The data collection and preprocessing module collects environmental data of the power grid area, including soil conditions, precipitation, surface creep, slope, and surface vegetation; cleans and standardizes the collected data to ensure data quality and consistency; The geological disaster impact index standardization and map display module forms surface objects on the map with the standardized geological disaster impact index, and uses ArcGIS to overlay the surface object data and divide the prediction units; Dynamic parameter calculation module calculates the dynamic parameters of each geological disaster impact indicator; establishes a database for recording historical geological disaster data, regularly updates the database, and recalculates dynamic parameters to ensure the real-time and accuracy of the model; Prediction model and early warning module, build prediction model for geological disaster early warning; generate early warning information including risk level, specific impact index value and recommended measures; Release early warning information through multiple channels; establish a user feedback mechanism, receive on-site feedback information, and correct and improve the prediction model.

9. A computer device comprising: Memory and processor; The memory stores a computer program, which is characterized in that when the processor executes the computer program, it implements the steps of a power grid geological disaster monitoring and early warning method based on real-time indicator parameters.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a power grid geological disaster monitoring and early warning method based on real-time indicator parameters are implemented.

Images