Method, device and equipment for determining seismic fortification intensity of power grid equipment

Abstract

The embodiment of the invention discloses a method, a device and equipment for determining the seismic fortification intensity of power grid equipment. The method comprises the following steps: acquiring various seismic oscillation parameters; preprocessing the plurality of seismic oscillation parameters to obtain a plurality of preprocessed target seismic oscillation parameters; establishing a target model based on the multiple target seismic oscillation parameters and a preset regression model, wherein the target model is a multiple regression model related to different seismic oscillation parameter combinations and instrument intensity; and determining the seismic fortification intensity of the power grid equipment according to the target model. According to the method, the accurate multiple regression model is established, and the model reflects the relationship between different seismic oscillation parameter combinations and the instrument intensity, so that the seismic fortification intensity of the power grid equipment can be determined in a targeted manner. According to the method, the prediction accuracy is improved, the data processing flow is optimized, the adaptability of the model is enhanced, the effectiveness of the seismic design of the power grid equipment is ensured, and the protection capability of the power grid equipment in an earthquake is further improved.

Description

Technical Field

[0001] The present invention relates to earthquake detection technology, and in particular to a method, device and equipment for determining the seismic fortification intensity of power grid equipment. Background Art

[0002] In today's context of frequent earthquakes, it is particularly important to effectively manage earthquake disasters and ensure the stable operation of power grid equipment. In this field, earthquake observation instruments have become an indispensable technical means. These high-precision instruments can capture seismic data in real time and convert them through complex algorithms to obtain instrument intensity values, which are the key basis for determining the seismic fortification intensity of power grid equipment.

[0003] However, the reality is that there is a large deviation between the instrument intensity calculated by different seismic motion parameters in different intensity areas and the actual earthquake intensity. The existence of this deviation makes it difficult for the seismic fortification intensity of power grid equipment set according to the instrument intensity to accurately correspond to the actual earthquake impact, resulting in the problem of insufficient or excessive protection. This mismatch not only affects the protection effect of power grid equipment during an earthquake and increases the risk of equipment damage, but also poses a threat to the stable operation of the power system, which may lead to the interruption of power supply after the earthquake and affect the rescue and recovery work in the disaster area. In actual operation, although we set the seismic fortification intensity of power grid equipment based on the data recorded by seismic observation instruments, the difference in the consistency ratio between seismic motion parameters and actual intensity in different intensity areas greatly reduces the accuracy of the instrument intensity, which in turn affects the safe use and seismic performance of power grid equipment in earthquake disaster areas. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device and equipment for determining the seismic fortification intensity of power grid equipment, which is used to solve the technical problem that the matching degree between instrument intensity and actual intensity is not high.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a method for determining the seismic fortification intensity of power grid equipment, the method comprising:

[0006] Obtain various ground motion parameters;

[0007] Preprocessing the multiple seismic motion parameters to obtain the multiple target seismic motion parameters after preprocessing;

[0008] Establishing a target model based on the multiple target seismic parameters and a preset regression model, wherein the target model is a multivariate regression model related to different seismic parameter combinations and instrument intensity;

[0009] According to the target model, the seismic fortification intensity of the power grid equipment is determined.

[0010] Optionally, determining the seismic fortification intensity of power grid equipment according to the target model includes: obtaining a first seismic motion parameter, which is an observed value; inputting the first seismic motion parameter into the target model to obtain a first predicted instrument intensity value output by the target model; and determining the seismic fortification intensity of power grid equipment according to the first predicted instrument intensity value.

[0011] Optionally, determining the seismic fortification intensity of power grid equipment based on the first predicted instrument intensity value includes: using the first predicted instrument intensity value as a query identifier, querying in a preset seismic fortification intensity standard database to obtain the seismic fortification intensity of the power grid equipment, the preset seismic fortification intensity standard database containing a correspondence between multiple instrument intensity values ​​and seismic fortification intensities.

[0012] Optionally, the target model is established based on the multiple target seismic motion parameters and the preset regression model, and the target model is a multiple regression model that relates different seismic motion parameter combinations to the instrument intensity, including: obtaining a regression equation based on the multiple target seismic motion parameters and the preset regression model, the regression equation containing dependent variables, independent variables, regression coefficients and fitting standard deviations, the independent variables including the multiple target seismic motion parameters, and the dependent variable corresponding to the instrument intensity; constructing data matrices for the dependent variables and the independent variables respectively to obtain a first matrix corresponding to the dependent variable and a second matrix corresponding to the independent variable; solving the first matrix and the second matrix according to the least squares method to obtain estimated values ​​of the regression coefficients; obtaining the target model based on the estimated values ​​of the regression coefficients and the preset regression model.

[0013] Optionally, solving the first matrix and the second matrix according to the least squares method to obtain an estimated value of the regression coefficient includes: using the least squares method to calculate the first matrix and the second matrix by minimizing the sum of squared errors to obtain a system of linear equations; solving the system of linear equations to obtain an estimated value of the regression coefficient.

[0014] Optionally, after establishing the target model based on the multiple target seismic motion parameters and the preset regression model, the method also includes: obtaining a target test set, the target test set including multiple historical seismic motion parameters and corresponding preset instrument intensity values; inputting the target test set into the target model to obtain a second instrument intensity value; comparing the second instrument intensity value with the preset instrument intensity value to obtain a performance index; judging whether the target model meets the preset standard based on the performance index; if it does not meet the preset standard, readjusting the model parameters in the target model; or, if it meets the preset standard, determining the seismic fortification intensity of the power grid equipment based on the target model.

[0015] Optionally, the preprocessing of the multiple seismic motion parameters to obtain the preprocessed multiple target seismic motion parameters includes: performing data cleaning on the multiple seismic motion parameters to obtain the cleaned multiple seismic motion parameters; and performing standardization on the cleaned multiple seismic motion parameters to obtain multiple target seismic motion parameters.

[0016] On the other hand, the present application also provides a device for determining the seismic fortification intensity of power grid equipment, the device comprising:

[0017] An acquisition module, used to obtain various ground motion parameters;

[0018] A processing module, used for preprocessing the multiple seismic parameters to obtain the multiple target seismic parameters after preprocessing;

[0019] An establishing module, used for establishing a target model based on the multiple target seismic parameters and a preset regression model, wherein the target model is a multivariate regression model related to different seismic parameter combinations and instrument intensity;

[0020] The determination module is used to determine the seismic fortification intensity of the power grid equipment according to the target model.

[0021] On the other hand, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the first aspect and any possible implementation method thereof.

[0022] On the other hand, the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes each step of the method described in the first aspect.

[0023] The present application provides a method for determining the seismic fortification intensity of power grid equipment, firstly obtaining a plurality of seismic motion parameters, secondly preprocessing the plurality of seismic motion parameters to obtain the plurality of target seismic motion parameters after the preprocessing, then establishing a target model based on the plurality of target seismic motion parameters and a preset regression model, wherein the target model is a multiple regression model related to different seismic motion parameter combinations and instrument intensity, and finally, determining the seismic fortification intensity of power grid equipment according to the target model. The method obtains a plurality of seismic motion parameters, thereby comprehensively understanding the impact of earthquakes on power grid equipment, thereby improving the accuracy of predicting the impact of earthquakes; preprocessing the seismic motion parameters can remove noise and outliers, improve the quality of data, thereby ensuring the accuracy and reliability of subsequent analysis; establishing a multiple regression model based on the preprocessed target seismic motion parameters, so that the model can better adapt to different seismic motion parameter combinations and improve the generalization ability of the model; since the target model can accurately reflect the relationship between different seismic motion parameters and instrument intensity, the seismic fortification intensity of power grid equipment can be determined through the target model, providing a more scientific and reasonable seismic design standard for power grid equipment, enhancing the seismic resistance of equipment, and reducing the losses caused by earthquakes. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] in:

[0026] Figure 1 A flow chart of a method for determining the seismic fortification intensity of power grid equipment provided in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of the structure of a device for determining the seismic fortification intensity of power grid equipment provided in an embodiment of the present application;

[0028] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0030] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0031] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The technical solution of the present application can be applied to various scenarios based on the determination of the seismic fortification intensity of power grid equipment.

[0033] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0034] See also Figure 1 , is a flow chart of a method for determining the seismic fortification intensity of power grid equipment provided in an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0035] 101. Obtain various seismic motion parameters.

[0036] Among them, multiple seismic motion parameters are different types of data generated when an earthquake occurs. A single seismic motion parameter may not fully reflect the impact of an earthquake on power grid equipment. Therefore, obtaining multiple seismic motion parameters helps to more comprehensively assess the potential threat of earthquakes to power grid equipment.

[0037] The types of earthquake motion parameters may include, but are not limited to: peak acceleration (PGA), peak velocity (PGV), peak displacement (PGD), response spectrum parameters, frequency spectrum characteristic parameters, and duration parameters.

[0038] Specifically, peak acceleration (PGA) is the maximum acceleration value of ground motion during seismic motion, which is an important indicator for measuring earthquake intensity; peak velocity (PGV) is the maximum velocity value of ground motion during seismic motion, which has an important influence on the dynamic response of the structure; peak displacement (PGD) is the maximum displacement value of ground motion during seismic motion, reflecting the influence of earthquake on structural deformation; response spectrum parameters include acceleration response spectrum, velocity response spectrum and displacement response spectrum, which are used to describe the response characteristics of the structure at different frequencies; spectral characteristic parameters include spectral amplitude, spectral peak frequency, etc., which reflect the frequency component and energy distribution of seismic motion; duration parameters include effective duration (the time period when the seismic intensity is greater than a certain threshold), which affects the cumulative damage of the structure.

[0039] Among them, various ground motion parameters can be obtained through seismic observatories, mobile seismic monitoring vehicles, satellite data, seismic recorders, earthquake simulation experiments and numerical simulations, etc. The above data sources provide detailed information on real-time or historical earthquake events.

[0040] Specifically, when an earthquake occurs, a seismic recorder is installed on the ground or in a building to record the time history data of seismic motion; an earthquake simulation test is to simulate seismic motion in the laboratory through a shaking table to obtain the response data of the structure under different seismic motion parameters; and a numerical simulation is to simulate the distribution and changes of seismic motion parameters through seismic wave propagation models and site response analysis.

[0041] It can be seen that in this example, the target model is further obtained more accurately through comprehensive and accurate seismic parameters.

[0042] 102. Preprocess the multiple seismic motion parameters to obtain the multiple target seismic motion parameters after preprocessing.

[0043] Preprocessing may include but is not limited to data cleaning and standardization.

[0044] Data cleaning refers to identifying and processing errors, outliers, missing values, etc. in the original data to ensure the consistency and accuracy of the data. In this solution, data caused by instrument failure, environmental interference or other non-seismic factors are removed.

[0045] Standardization refers to converting data into a uniform scale so that different parameters can be compared and analyzed. In practice, the data is subtracted from its mean and divided by its standard deviation, or scaled to a specific range.

[0046] It can be seen that in this example, preprocessing can improve the quality and availability of data, thus providing a reliable foundation for subsequent analysis and model building.

[0047] In one embodiment, the preprocessing of the multiple seismic motion parameters to obtain the preprocessed multiple target seismic motion parameters includes: performing data cleaning on the multiple seismic motion parameters to obtain the cleaned multiple seismic motion parameters; and standardizing the cleaned multiple seismic motion parameters to obtain multiple target seismic motion parameters.

[0048] Among them, data cleaning methods include filtering, outlier detection and elimination, etc. For example, high-pass filtering is used to remove low-frequency noise, and low-pass filtering is used to remove high-frequency noise; statistical methods are used to detect and eliminate outliers that significantly deviate from the normal range.

[0049] Optionally, in the earthquake record, there may be some missing data. Methods for filling missing data include interpolation, mean filling, etc. For example, linear interpolation is used to fill missing data according to the values ​​of adjacent data points, or the mean of the data set is used to fill missing values.

[0050] Different ground motion parameters may have different dimensions and magnitudes, and directly using these parameters for analysis may lead to unreasonable results. Standardization can convert different parameters to the same dimension and magnitude to ensure their comparability in subsequent analysis.

[0051] Among them, the commonly used methods of standardization processing include normalization and mean-variance standardization. When choosing a standardization method, it should be determined according to the specific seismic parameters and application scenarios. For example, for parameters with significant extreme values, normalization may be more appropriate; for parameters with relatively uniform data distribution, mean-variance standardization may be more appropriate.

[0052] For example, multiple seismic motion parameters are filtered to remove high-frequency and low-frequency noise, and outliers are further identified and eliminated using outlier detection methods (such as box plot method, 3σ method, etc.). Then, missing data are filled using linear interpolation or mean filling method to complete data cleaning.

[0053] For example, the cleaned seismic parameters are normalized to scale the data to the interval [0,1]; or the cleaned seismic parameters are mean-variance standardized to convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0054] It can be seen that in this example, the cleaned and standardized data can reduce the deviation in the model training process, that is, it is easier to compare the impact of different seismic parameters on the instrument intensity, thereby selecting the most important parameters for the model and improving the prediction performance of the model.

[0055] 103. Establish a target model based on the multiple target seismic parameters and a preset regression model, wherein the target model is a multiple regression model related to different seismic parameter combinations and instrument intensity.

[0056] Among them, the purpose of establishing the target model is to predict or estimate the instrumental intensity of the earthquake through a variety of seismic motion parameters.

[0057] Among them, instrumental intensity is an indicator that quantifies the impact of an earthquake and is usually used to describe the extent of damage caused by an earthquake to buildings and infrastructure.

[0058] Among them, the multivariate regression model is a commonly used statistical method that predicts a dependent variable (here, the instrumental intensity) through multiple independent variables (here, the seismic parameters).

[0059] Among them, the preset regression model is an initial model established based on historical data and experience, which is used to describe the relationship between seismic motion parameters and instrumental intensity. The preset regression model can be a linear regression model, a nonlinear regression model or other statistical models. The specific choice depends on the characteristics of the data and application requirements.

[0060] Among them, the target model is the final model obtained through training and optimization based on multiple target seismic motion parameters and preset regression models. The target model can comprehensively consider the influence of different seismic motion parameters and accurately predict the instrumental intensity of earthquakes.

[0061] Optionally, the preprocessed seismic parameter data is divided into a training set and a test set, the training set is used for model training, and the test set is used for model verification; according to the importance and relevance of the seismic parameters, the most representative parameters are selected as independent variables of the model.

[0062] Optionally, the training set data is used for regression analysis to fit a preset regression model. Commonly used methods include least squares method, ridge regression, Lasso regression, etc.

[0063] Optionally, use the test set data to evaluate the performance of the model. Common evaluation indicators include mean square error (MSE), root mean square error (RMSE), coefficient of determination (R 2 )wait.

[0064] For example, the preprocessed seismic parameter data is segmented to obtain the training set and the test set, and the peak acceleration (PGA), peak velocity (PGV), peak displacement (PGD) and other parameters are selected as the independent variables of the model. The training set data is used for linear regression analysis, the preset regression model is fitted, the model parameters are optimized through cross-validation, the optimal regression coefficient is selected, the model performance is evaluated using the test set data, and the mean square error (MSE) and determination coefficient (R 2), adjust the model structure and parameters according to the evaluation results to ensure the accuracy and stability of the model, use the trained target model to predict the new ground motion parameter data and estimate the instrumental intensity of the earthquake.

[0065] It can be seen that the target model established based on the multiple target seismic motion parameters and the preset regression model in this example can effectively use the multiple seismic motion parameters to accurately predict the instrumental intensity of earthquakes.

[0066] 104. Determine the seismic fortification intensity of the power grid equipment according to the target model.

[0067] Among them, seismic fortification intensity refers to the earthquake intensity that needs to be considered during the design and construction of power grid equipment to ensure that the equipment can operate safely or recover quickly when an earthquake occurs. The fortification intensity is usually determined based on historical earthquake data, earthquake hazard analysis, and the importance level of the equipment.

[0068] In specific implementation, the target model is used to predict the seismic parameter data to obtain the instrumental seismic intensity under different scenarios; the seismic hazard level of the area where the power grid equipment is located is determined in combination with the results of the seismic hazard analysis; the seismic fortification intensity requirements for different types of power grid equipment are determined according to national or industry standards (such as the "Electric Power Facilities Seismic Design Code"); the fortification intensity is adjusted considering the importance level of the power grid equipment (such as main substations, transmission lines, distribution equipment, etc.); further, based on the determined fortification intensity, the power grid equipment is seismically designed, including structural reinforcement, equipment layout optimization and foundation design, or the seismic performance of the power grid equipment is verified through earthquake simulation and experiments to ensure its safe operation under the fortification intensity.

[0069] It can be seen that in this example, according to the prediction of the target model, the seismic fortification intensity of the power grid equipment is determined according to the prediction results, thereby ensuring that the power grid equipment has sufficient seismic resistance when an earthquake occurs, reducing the impact of the earthquake on the power grid system, and improving the safety and reliability of the power grid.

[0070] This method obtains a variety of seismic motion parameters to fully understand the impact of earthquakes on power grid equipment, thereby improving the accuracy of earthquake impact prediction; preprocessing of seismic motion parameters can remove noise and outliers, improve data quality, and ensure the accuracy and reliability of subsequent analysis; a multivariate regression model is established based on the preprocessed target seismic motion parameters, so that the model can better adapt to different seismic motion parameter combinations and improve the generalization ability of the model; because the target model can accurately reflect the relationship between different seismic motion parameters and instrument intensity, the seismic fortification intensity of power grid equipment can be determined through the target model, providing a more scientific and reasonable seismic design standard for power grid equipment, enhancing the seismic resistance of equipment, and reducing losses caused by earthquakes.

[0071] In one embodiment, determining the seismic fortification intensity of power grid equipment based on the target model includes: obtaining a first seismic motion parameter, which is an observed value; inputting the first seismic motion parameter into the target model to obtain a first predicted instrument intensity value output by the target model; and determining the seismic fortification intensity of power grid equipment based on the first predicted instrument intensity value.

[0072] The first seismic parameters are observation values ​​directly measured by seismic observation equipment (such as a seismograph), and include but are not limited to acceleration, velocity, and displacement of seismic waves.

[0073] Optionally, the acquired first seismic parameter is preprocessed to remove noise and abnormal values ​​to ensure the accuracy and reliability of the data.

[0074] The target model outputs a first predicted instrument intensity value according to the input seismic parameters, and the first predicted instrument intensity value reflects the possible impact of the earthquake on the power grid equipment under the current seismic parameters.

[0075] Optionally, the first predicted instrument intensity value is converted into the seismic fortification intensity of the power grid equipment according to national or industry standards (such as the "Code for Seismic Design of Electric Power Facilities").

[0076] Optionally, according to the determined fortification intensity, the power grid equipment is subjected to earthquake-resistant design, including structural reinforcement, equipment layout optimization and foundation design.

[0077] It can be seen that in this example, the seismic parameters and the target model are used to accurately and quickly obtain the seismic fortification intensity of the power grid equipment, and further guide the seismic fortification work of the power grid equipment, thereby protecting the safety and stability of the power grid facilities when an earthquake occurs.

[0078] In one embodiment, determining the seismic fortification intensity of power grid equipment based on the first predicted instrument intensity value includes: using the first predicted instrument intensity value as a query identifier, querying in a preset seismic fortification intensity standard database to obtain the seismic fortification intensity of the power grid equipment, the preset seismic fortification intensity standard database containing a correspondence between multiple instrument intensity values ​​and seismic fortification intensities.

[0079] Among them, the corresponding relationship can be established based on historical earthquake data and defense standards.

[0080] The data in the database can be derived from national or industry standards, historical earthquake data, earthquake engineering research results, etc., and the database is updated regularly to reflect the latest earthquake research results and fortification standards. The database may also include other relevant information, such as the probability of earthquake occurrence, site conditions, design life, etc.

[0081] Specifically, the database may adopt a relational database structure, including two columns: instrument intensity value and corresponding seismic fortification intensity.

[0082] For example: instrument intensity value: 5.0, seismic fortification intensity: 6; instrument intensity value: 6.0, seismic fortification intensity: 7; instrument intensity value: 7.0, seismic fortification intensity: 8.

[0083] The query process is to find the closest corresponding seismic fortification intensity by comparing the predicted instrumental intensity value with the intensity value in the database.

[0084] It can be seen that in this example, according to the corresponding relationship in the preset seismic fortification intensity standard database, the seismic fortification intensity of the power grid equipment is quickly and accurately determined to ensure the safety and reliability of the power grid when an earthquake occurs.

[0085] In one embodiment, the target model is established based on the multiple target seismic motion parameters and the preset regression model, and the target model is a multiple regression model that relates different seismic motion parameter combinations to the instrument intensity, including: based on the multiple target seismic motion parameters and the preset regression model, a regression equation is obtained, the regression equation includes dependent variables, independent variables, regression coefficients and fitting standard deviations, the independent variables include the multiple target seismic motion parameters, and the dependent variable corresponds to the instrument intensity; data matrices are constructed for the dependent variables and the independent variables respectively to obtain a first matrix corresponding to the dependent variable and a second matrix corresponding to the independent variable; according to the least squares method, the first matrix and the second matrix are solved to obtain estimated values ​​of the regression coefficients; according to the estimated values ​​of the regression coefficients and the preset regression model, the target model is obtained.

[0086] For example, the default regression model can be as follows:

[0087] I=a+b log A+c log B+σ

[0088] In the above formula, I is the intensity; a, b, c are regression coefficients; A and B represent two seismic motion parameter values ​​respectively; σ is the fitting standard deviation.

[0089] Among them, the dependent variable corresponds to the instrument intensity; the independent variables are a variety of target seismic parameters; the regression coefficient is the coefficient describing the relationship between the independent variable and the dependent variable, and the fitting standard deviation is a measure of the error of the regression model fitting data.

[0090] The regression equation can be X is a known n×(m+1) constant matrix, β is an unknown parameter vector, I n is the n×n unit matrix, σ 2 is the unknown parameter and m is the number of independent variables.

[0091] Among them, the first matrix can be shown as follows:

[0092]

[0093] Y1-Y n is the observed value of the instrumental intensity.

[0094] The second matrix can be shown as follows:

[0095]

[0096] Among them, data matrices are constructed for the dependent variable and the independent variable respectively. The dependent variable matrix (Y) contains the instrument intensity values ​​measured in different earthquake events; the independent variable matrix (X) contains a variety of seismic motion parameters measured in different earthquake events.

[0097] Among them, the least squares method is a statistical method used to fit the regression model, and its goal is to find the optimal regression coefficient by minimizing the sum of squares of errors between the predicted value and the actual value.

[0098] Among them, the least squares method is used to solve the dependent variable matrix (Y) and the independent variable matrix (X) to obtain the estimated value of the regression coefficient.

[0099] The least squares formula is as follows:

[0100]

[0101] in, is the estimated value of the regression coefficient, X T is the transpose of the independent variable matrix, (X T Y) -1 is the matrix X T The inverse matrix of Y.

[0102] Furthermore, we get the estimated value of the regression coefficient Then, substitute it into the regression equation to get the target model:

[0103] For example, the regression model is selected as follows:

[0104] I=a+b log A+c log B+σ (1)

[0105] In the above formula, I is the intensity; a, b, c are regression coefficients; A and B represent two seismic parameters respectively; σ is the fitting standard deviation. The solution process is as follows: Assume that the random variable η is related to m (m≥2) independent variables x1, x2,…, x mThere is a phase relationship between them, where the random variable η corresponds to the instrument intensity, and the m independent variables x1, x2, …, x m Corresponding to multiple observable ground motion parameter values. The random variable η and m (m ≥ 2) independent variables x1, x2, …, x m The correlation between them satisfies the following formula:

[0106] η=b0+b1x1+b2x2+…+b m x m +ε

[0107] ε~N(0,σ 2 )(0)

[0108] Right now

[0109] η~N(b0+b1x1+b2x2+…+b m x m ,σ 2 ) (3)

[0110] Among them, b0, b1, b2, …, b m ,σ 2 is related to x1,x2,…,x m irrelevant unknown parameters, ε is an unobservable random variable.

[0111] Eη=b0+b1x1+…+b m x m (4)

[0112] η for x1,x2,…,x m The regression function, or m-dimensional linear regression equation. When x1, x2, …, x m Take n different values ​​(x in ,x i2 ,…,x im ), when i=1,2,…n, the samples η1,η2,…,η of the formula n satisfy

[0113] η i =b0+b1x i1 +b2x i2 +…+b m x im +ε i

[0114] ε i ~N(0,σ 2 ) (5)

[0115] Now let's express the above formula in vector form,

[0116]

[0117] The formula can be expressed as:

[0118]

[0119] X is a known n×(m+1) constant matrix, β is an unknown parameter vector, I n is the n×n unit matrix, σ 2 is an unknown parameter, and the determined relationship is an m-dimensional linear regression model, which is also called η=(η1,…,η n ) T Obey the linear model, abbreviated as (η,Xβ,σ 2 I N ). From formula (4), we know:

[0120] Eη=Xβ (8)

[0121] set up They are b0, b1, b2, …, b m By estimating , we can get an m-dimensional equation:

[0122]

[0123] Then this formula can be called the m-variable linear regression equation.

[0124] With the regression equation, when the independent variables x1, x2, …, x m Take the values ​​of x i1 ,x i2 ,…,x sm When , the value determined by the above formula:

[0125]

[0126] As η i The estimated regression value of is the value of m To predict the value of the dependent variable η. As with the univariate linear regression model, for the m-variate linear model (η, Xβ, σ 2 I N ), we can also use the least squares method to find the parameters b0, b1, b2, …, b m Estimate of So that:

[0127]

[0128] Estimation of β This is called the least squares estimate of β.

[0129] set up make j=0,1,2,…m, we get:

[0130]

[0131] Arrange about b0,b1,b2,…,b n The linear equations are:

[0132]

[0133] The matrix expression of the above formula is:

[0134]

[0135] Further we can get:

[0136]

[0137] Thus:

[0138] X 1 Xβ=X T Y (16)

[0139] In the formula, Y=(y1,y2,…,y n ) 0 , since R(X T X) = R (X) = m + 1, so X T X is a full rank matrix, so there exists an inverse matrix,

[0140]

[0141] It can be seen that in this example, a target model based on seismic parameters and regression model is constructed to predict instrumental intensity. This target model can not only be used for earthquake early warning, but also provide a scientific basis for the seismic fortification design of power grid equipment.

[0142] In one embodiment, solving the first matrix and the second matrix according to the least squares method to obtain an estimated value of the regression coefficient includes: using the least squares method to calculate the first matrix and the second matrix by minimizing the sum of squared errors to obtain a system of linear equations; solving the system of linear equations to obtain an estimated value of the regression coefficient.

[0143] Among them, according to the principle of least squares method, the estimated value of the regression coefficient can be obtained by differentiating the sum of squared errors and setting it to zero.

[0144] The constructed linear equation can be the same as X in the previous embodiment. T Xβ=X T Y.

[0145] The estimated values ​​of the regression coefficients are:

[0146]

[0147] It can be seen that in this example, the least squares method can be used to minimize the sum of squared errors between the predicted value and the actual value, and the estimated value of the regression coefficient can be obtained. The estimated value of the regression coefficient is further used to predict the instrument intensity, which can ensure that the seismic performance of the power grid equipment is set according to the accurate prediction of the actual seismic parameters, thereby improving the safety and reliability of the power grid equipment when an earthquake occurs.

[0148] In one embodiment, after the target model is established based on the multiple target seismic motion parameters and the preset regression model, the method further includes: obtaining a target test set, the target test set including multiple historical seismic motion parameters and corresponding preset instrument intensity values; inputting the target test set into the target model to obtain a second instrument intensity value; comparing the second instrument intensity value with the preset instrument intensity value to obtain a performance index; judging whether the target model meets the preset standard based on the performance index; if it does not meet the preset standard, readjusting the model parameters in the target model; or, if it meets the preset standard, determining the seismic fortification intensity of the power grid equipment based on the target model.

[0149] Among them, the target test set is a data set used to verify and evaluate the performance of the target model. It includes a variety of historical ground motion parameters (such as acceleration, velocity, displacement, etc.) and the corresponding preset instrument intensity values ​​(usually determined based on actual observations or empirical data).

[0150] The second instrumental intensity value is the instrumental intensity value predicted by the target model based on the input seismic parameters.

[0151] Among them, the preset instrument intensity value is the actual instrument intensity value corresponding to the historical earthquake event known in the target test set.

[0152] Among them, performance indicators are used to measure the prediction accuracy and reliability of the model. Commonly used performance indicators include mean square error (MSE), root mean square error (RMSE), determination coefficient (R 2 )wait.

[0153] Among them, according to the preset performance standards, it is judged whether the performance indicators of the model meet the requirements. If the performance indicators meet or exceed the preset standards, the model is considered qualified; otherwise, the model parameters need to be readjusted; if the model does not meet the preset standards, it is necessary to improve the performance of the model by adjusting the model parameters (such as regression coefficients, regularization parameters, etc.). The adjusted model needs to be re-verified until it meets the preset standards; if the model meets the preset standards, the seismic fortification intensity of the power grid equipment can be determined based on the prediction results of the model. The seismic fortification intensity refers to the maximum intensity that the power grid equipment can withstand in an earthquake to ensure the safety and stability of the equipment.

[0154] Specifically, the second instrument intensity value predicted by the model is compared with the instrument intensity value preset in the target test set, and the error is calculated. The error can be calculated by absolute error, relative error or mean square error. According to the calculated error, the performance index of the model is obtained. For example, the mean square error (MSE) is used to measure the average square error between the predicted value and the true value; the root mean square error (RMSE) is the square root of the mean square error, reflecting the standard deviation of the error; the mean absolute error (MAE) is used to measure the average absolute error between the predicted value and the true value; the coefficient of determination (R 2 ) reflects the degree of fit of the model to the data. The closer the value is to 1, the better the fit is.

[0155] It can be seen that in this example, the target model is verified through the test set, and then the prediction effect of the model is evaluated to ensure the reliability and accuracy of the model, and further ensure the safety and reliability of power grid equipment in the face of earthquake disasters.

[0156] As another aspect of the embodiment of the present application, the embodiment of the present application provides a device for determining the seismic fortification intensity of power grid equipment. The device for determining the seismic fortification intensity of power grid equipment can be a software module, which includes several instructions stored in a memory, and the processor can access the memory and call the instructions for execution to complete the method for determining the seismic fortification intensity of power grid equipment described in the above-mentioned various embodiments.

[0157] See also Figure 2 , Figure 2 Schematic diagram of a structure of a device for determining the seismic fortification intensity of power grid equipment provided in an embodiment of the present application. Figure 2 As shown, the determination device based on the seismic fortification intensity of power grid equipment includes:

[0158] An acquisition module 201 is used to acquire multiple ground motion parameters;

[0159] A processing module 202 is used to pre-process the multiple seismic parameters to obtain the multiple target seismic parameters after pre-processing;

[0160] Establishing module 203, used to establish a target model based on the multiple target seismic parameters and the preset regression model, wherein the target model is a multivariate regression model related to different seismic parameter combinations and instrument intensity;

[0161] The determination module 204 is used to determine the seismic fortification intensity of the power grid equipment according to the target model.

[0162] This method obtains a variety of seismic motion parameters to fully understand the impact of earthquakes on power grid equipment, thereby improving the accuracy of earthquake impact prediction; preprocessing of seismic motion parameters can remove noise and outliers, improve data quality, and ensure the accuracy and reliability of subsequent analysis; a multivariate regression model is established based on the preprocessed target seismic motion parameters, so that the model can better adapt to different seismic motion parameter combinations and improve the generalization ability of the model; because the target model can accurately reflect the relationship between different seismic motion parameters and instrument intensity, the seismic fortification intensity of power grid equipment can be determined through the target model, providing a more scientific and reasonable seismic design standard for power grid equipment, enhancing the seismic resistance of equipment, and reducing losses caused by earthquakes.

[0163] It can be understood that the relevant contents of each module in the above device have been described in detail in the aforementioned method embodiment, and the specific contents can be referred to the method embodiment; that is, a determination device based on the seismic fortification intensity of power grid equipment provided in this application can be executed as follows Figure 1 Any steps in the illustrated embodiment will not be described in detail here.

[0164] See also Figure 3 , Figure 3 3 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. The computer device includes one or more processors 31 and a memory 32. The memory 32 is connected to the one or more processors 31, for example, connected to the processor 31 via a bus.

[0165] The processor 31 is configured to support the computer device to perform the corresponding functions in the method in the above method embodiment. The processor 31 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0166] The memory 32 is used to store program codes, etc. The memory 32 may include a volatile memory (VM), such as a random access memory (RAM); the memory 32 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory 32 may also include a combination of the above-mentioned types of memories.

[0167] The memory 32 can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the method for determining the seismic fortification intensity of power grid equipment in the embodiment of the present application. The processor 31 executes the method for determining the seismic fortification intensity of power grid equipment and various functional applications and data processing based on the device for determining the seismic fortification intensity of power grid equipment by running the non-volatile software programs, instructions and modules stored in the memory 32, that is, to realize the functions of the various modules or units of the method for determining the seismic fortification intensity of power grid equipment and the device for determining the seismic fortification intensity of power grid equipment provided in the above method embodiment.

[0168] The memory 32 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function. The data storage area may store data created based on the use of a determination device based on the seismic fortification intensity of power grid equipment, etc. In some embodiments, the memory 32 may optionally include a memory 32 remotely arranged relative to the processor 31, and these remote memories 32 may be connected to the determination device based on the seismic fortification intensity of power grid equipment via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The one or more modules are stored in the memory 32, and when executed by the one or more processors 31, they execute the method for determining the seismic fortification intensity of power grid equipment in any of the above-mentioned method embodiments, for example, execute the method steps described in the above-mentioned method embodiments to realize the functions of the modules described in the above-mentioned device embodiments.

[0170] In one embodiment, a computer-readable storage medium is further provided. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor executes any step in the above method embodiment.

[0171] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0172] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0173] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining the seismic fortification intensity of power grid equipment, characterized in that: The method comprises: Obtain various ground motion parameters; Preprocessing the multiple seismic motion parameters to obtain the multiple target seismic motion parameters after preprocessing; Establishing a target model based on the multiple target seismic parameters and a preset regression model, wherein the target model is a multivariate regression model related to different seismic parameter combinations and instrument intensity; According to the target model, the seismic fortification intensity of the power grid equipment is determined.

2. The method for determining the seismic fortification intensity of power grid equipment according to claim 1, characterized in that: Determining the seismic fortification intensity of power grid equipment according to the target model includes: Acquire a first seismic parameter, where the first seismic parameter is an observed value; inputting the first earthquake motion parameter into the target model to obtain a first predicted instrument intensity value output by the target model; The seismic fortification intensity of the power grid equipment is determined according to the intensity value of the first prediction instrument.

3. The method for determining the seismic fortification intensity of power grid equipment according to claim 2, characterized in that: Determining the seismic fortification intensity of power grid equipment according to the first prediction instrument intensity value includes: The first predicted instrument intensity value is used as a query identifier, and a query is performed in a preset seismic fortification intensity standard database to obtain the seismic fortification intensity of the power grid equipment. The preset seismic fortification intensity standard database contains a correspondence between multiple instrument intensity values ​​and seismic fortification intensities.

4. The method for determining the seismic fortification intensity of power grid equipment according to claim 1, characterized in that: The target model is established based on the multiple target seismic parameters and the preset regression model, and the target model is a multivariate regression model related to different seismic parameter combinations and instrument intensity, including: Based on the multiple target seismic parameters and the preset regression model, a regression equation is obtained, wherein the regression equation includes a dependent variable, an independent variable, a regression coefficient and a fitting standard deviation, the independent variable includes the multiple target seismic parameters, and the dependent variable corresponds to the instrument intensity; Constructing data matrices for the dependent variable and the independent variable respectively, to obtain a first matrix corresponding to the dependent variable and a second matrix corresponding to the independent variable; Solving the first matrix and the second matrix according to the least square method to obtain estimated values ​​of regression coefficients; A target model is obtained according to the estimated value of the regression coefficient and the preset regression model.

5. The method for determining the seismic fortification intensity of power grid equipment according to claim 4, characterized in that: The step of solving the first matrix and the second matrix according to the least square method to obtain estimated values ​​of regression coefficients includes: Using the least square method, the first matrix and the second matrix are calculated by minimizing the sum of square errors to obtain a linear equation system; Solve the linear equations to obtain estimated values ​​of the regression coefficients.

6. The method for determining the seismic fortification intensity of power grid equipment according to claim 1, characterized in that: After establishing the target model based on the multiple target seismic parameters and the preset regression model, the method further includes: Acquire a target test set, wherein the target test set includes a plurality of historical ground motion parameters and corresponding preset instrument intensity values; Inputting the target test set into the target model to obtain a second instrument intensity value; Comparing the second instrument intensity value with the preset instrument intensity value to obtain a performance indicator; According to the performance indicator, determining whether the target model meets the preset standard; If the preset standard is not met, the model parameters in the target model are readjusted; or, If the preset standard is met, the seismic fortification intensity of the power grid equipment is determined according to the target model.

7. The method for determining the seismic fortification intensity of power grid equipment according to claim 1, characterized in that: The preprocessing of the multiple seismic motion parameters to obtain the preprocessed multiple target seismic motion parameters includes: performing data cleaning on the multiple seismic motion parameters to obtain multiple cleaned seismic motion parameters; The cleaned multiple seismic parameters are standardized to obtain multiple target seismic parameters.

8. A device for determining the seismic fortification intensity of power grid equipment, characterized in that: The device comprises: An acquisition module, used to obtain various ground motion parameters; A processing module, used for preprocessing the multiple seismic parameters to obtain the multiple target seismic parameters after preprocessing; An establishing module, used for establishing a target model based on the multiple target seismic parameters and a preset regression model, wherein the target model is a multivariate regression model related to different seismic parameter combinations and instrument intensity; The determination module is used to determine the seismic fortification intensity of the power grid equipment according to the target model.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory. When the processor executes the one or more computer programs, the computer device implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images