High arch dam earthquake vulnerability analysis method and system based on extreme gradient lifting tree theory

Abstract

The invention provides a high arch dam earthquake vulnerability analysis method and system based on an extreme gradient lifting tree theory, and the method comprises the steps: obtaining a plurality of pieces of earthquake vibration data meeting the feature requirements of a high arch dam site, and constructing an engineering demand parameter set and an earthquake vibration intensity parameter set; constructing a high arch dam probability earthquake demand model based on an extreme gradient lifting tree model, and fitting a non-linear relationship between engineering demand parameters and earthquake intensity parameters; fitting a change curve of the engineering demand parameters with respect to the acceleration response spectrum value in the first-order natural vibration period based on a scalar model, and extracting boundary values divided by different anti-seismic performance levels; and on the basis of an engineering demand parameter logarithmic normal distribution hypothesis, using the fitted high arch dam probability earthquake demand model to construct an earth surface vulnerability function, and inputting an earth vibration strength parameter and boundary values of different anti-seismic performance levels for calculation to obtain earthquake vulnerability probabilities of the high arch dam under the different anti-seismic performance levels.

Description

Technical Field

[0001] This invention belongs to the field of seismic performance research of arch dams, specifically involving a method and system for analyzing the seismic vulnerability of high arch dams based on the extreme gradient lifting tree theory. Background Technology

[0002] Structural seismic vulnerability analysis is used to assess the probability that a structure will reach or exceed a certain performance level under different seismic motions. By establishing a statistical relationship between the response parameters obtained from structural dynamic analysis and the seismic intensity parameters, seismic performance prediction under different probabilities of seismic action can be achieved. As an important component of performance-based seismic design, seismic vulnerability analysis has been widely applied in various engineering fields. Compared to buildings and bridges, seismic vulnerability analysis of arch dams started relatively late. Existing research results on the seismic vulnerability analysis of high arch dams are limited, mainly focusing on model optimization and sensitivity analysis. Currently, the seismic vulnerability analysis of high arch dams relies on the traditional log-normal probability seismic demand model. If the seismic intensity parameters and the structural engineering demand parameters do not satisfy the assumed log-linear relationship, the calculation results of structural seismic vulnerability analysis will be biased. The extreme gradient boosting tree algorithm, because it can better characterize the complex nonlinear relationship between structural dynamic response and seismic parameters, has received considerable attention in the field of earthquake engineering; however, it is still rare in the field of seismic vulnerability analysis of high arch dams. Summary of the Invention

[0003] To overcome the limitations of existing methods for analyzing the seismic vulnerability of high arch dams, which assume a log-linear relationship between ground motion intensity parameters and engineering requirement parameters, this invention provides a method and system for analyzing the seismic vulnerability of high arch dams based on extreme gradient boosting tree theory. By constructing a probabilistic seismic demand model for high arch dams that considers the nonlinear relationship between ground motion intensity parameters and engineering requirement parameters using extreme gradient boosting tree theory, this invention more accurately realizes the seismic vulnerability analysis of high arch dams and provides an effective tool for assessing seismic damage to high arch dams.

[0004] According to one aspect of this specification, a method for analyzing the seismic vulnerability of high arch dams based on extreme gradient boosting tree theory is provided, comprising:

[0005] Acquire several ground motion data that meet the site characteristics requirements of the high arch dam site, perform dynamic time history analysis, and construct a set of engineering requirement parameters;

[0006] Seismic intensity parameters are calculated based on several seismic ground motion data that meet the site characteristics requirements of high arch dam sites, and a set of seismic intensity parameters is constructed; the seismic intensity parameters include the acceleration response spectrum value and root mean square velocity under the first natural period;

[0007] A probabilistic earthquake demand model for high arch dams is constructed based on an extreme gradient boosting tree model, and the nonlinear relationship between the engineering demand parameters and the seismic intensity parameters is fitted based on the engineering demand parameter set and the seismic intensity parameter set. The probabilistic earthquake demand model for high arch dams includes a scalar model with the acceleration response spectrum value under the first natural period as a single variable as an input variable and a vector model with two seismic intensity parameters as input variables. The outputs of the scalar model and the vector model are both engineering demand parameters.

[0008] Based on the scalar model, the curves of the change of engineering requirement parameters with respect to the acceleration response spectrum value under the first natural vibration period are fitted, and the boundary values ​​for different seismic performance levels are extracted.

[0009] Based on the assumption of a log-normal distribution of engineering demand parameters, a surface vulnerability function is constructed using a fitted probabilistic seismic demand model for high arch dams. The seismic ground motion intensity parameters and the boundary values ​​of different seismic performance levels are input for calculation to obtain the seismic vulnerability probability of high arch dams under different seismic performance levels.

[0010] As a further technical solution, the steps for constructing the engineering requirement parameter set include:

[0011] A three-dimensional nonlinear finite element model of the high arch dam-foundation system was established. Several ground motion data that meet the site characteristics requirements of the high arch dam were used as inputs to the finite element model for dynamic time history analysis. Damage index data of the high arch dam were selected from the dynamic time history analysis results as engineering requirement parameters to construct a set of engineering requirement parameters.

[0012] As a further technical solution, the training process of the probabilistic seismic demand model for high arch dams includes:

[0013] The engineering requirement parameter set and the seismic ground motion intensity parameter set are matched one-to-one according to the corresponding seismic ground motion data, and the data are divided into training and validation sets according to a preset ratio. The probabilistic seismic demand model for high arch dams is trained using the training set data. The iterative objective function during the training process is:

[0014]

[0015] In the formula, represents the iterative objective function; i represents the seismic data number, and N represents the total number of seismic data; The loss function; For regularization terms; The predicted engineering demand parameters for the corresponding i-th seismic ground motion data point, output by the probabilistic seismic demand model for high arch dams. These are the actual values ​​of the engineering requirements parameters; For a single regression decision tree, j is the regression decision tree number. The number of all regression decision trees; Let be the number of leaf nodes in the k-th regression decision tree; The output score of the l-th leaf node of the regression decision tree; The penalty term is the number of leaf nodes; This is an L2 regularization penalty term;

[0016] Iterative training employs a gradient boosting strategy, adding a new regression decision tree to the existing model in each iteration. After each iteration, the existing model is validated using a validation set. Training terminates when the evaluation metrics on the validation set fail to improve further in a preset number of iterations or when the preset maximum number of training iterations is reached, and the trained high arch dam probabilistic earthquake demand model is output.

[0017] As a further technical solution, the training process for scalar and vector models is as follows:

[0018] According to the training process of the high arch dam probabilistic earthquake demand model, the acceleration response spectrum value under the first natural period is used as the single input variable of the high arch dam probabilistic earthquake demand model to obtain a scalar model. At the same time, the acceleration response spectrum value under the first natural period and the root mean square velocity are used as two ground motion intensity parameters to obtain a vector model.

[0019] As a further technical solution, the process of classifying the seismic performance levels of engineering requirements parameters includes:

[0020] Based on the scalar model, the change curve of the acceleration response spectrum value of the engineering demand parameters with respect to the first natural vibration period is obtained. Under the condition that the engineering demand parameters meet the preset seismic damage assessment level, the stage of the slope of the change curve abruptly changes three times. The critical value of the engineering demand parameters at each abrupt change is used as the boundary value for the seismic performance level division, and the four levels of seismic performance of the engineering demand parameters are divided.

[0021] As a further technical solution, the mathematical expression of the seismic vulnerability function is as follows:

[0022]

[0023] In the formula, This indicates that the condition exceeds the probability. This indicates the input of engineering requirement parameters; Indicates when the scalar seismic intensity parameter At that time, the engineering demand parameters output by the probabilistic seismic demand model for high arch dams; The limit value representing the seismic performance level of high arch dams; This indicates that the probabilistic earthquake demand model for high arch dams is in Logarithmic standard deviation under the given conditions.

[0024] As a further technical solution, it also includes: based on the limit value of a certain seismic performance level of a high arch dam, calculating the condition exceedance probability of the engineering demand parameters reaching the seismic performance level using the seismic vulnerability function, plotting the seismic vulnerability curve of the high arch dam under the seismic performance level using the corresponding scalar model, and / or plotting the seismic vulnerability surface of the high arch dam under the seismic performance level using the corresponding vector model, thereby obtaining the seismic vulnerability curves and / or surfaces of the high arch dam under different seismic performance levels.

[0025] According to one aspect of this specification, a seismic vulnerability analysis system for high arch dams based on extreme gradient boosting tree theory is provided, comprising:

[0026] The engineering requirement parameter acquisition module is used to acquire several ground motion data that meet the site characteristics requirements of the high arch dam site, and to perform dynamic time history analysis to construct a set of engineering requirement parameters.

[0027] The seismic intensity parameter acquisition module is used to calculate seismic intensity parameters based on several seismic data that meet the site characteristics requirements of the high arch dam site, and to construct a seismic intensity parameter set; the seismic intensity parameters include the acceleration response spectrum value and root mean square velocity under the first natural period;

[0028] The module for constructing and training a probabilistic earthquake demand model for high arch dams is used to construct a probabilistic earthquake demand model for high arch dams based on an extreme gradient boosting tree model, and to fit the nonlinear relationship between the engineering demand parameters and the seismic intensity parameters based on the engineering demand parameter set and the seismic intensity parameter set. The probabilistic earthquake demand model for high arch dams includes a scalar model with the acceleration response spectrum value under the first natural period as a single variable as an input variable and a vector model with two seismic intensity parameters as input variables. The outputs of the scalar model and the vector model are both engineering demand parameters.

[0029] The seismic performance level classification module is used to fit the variation curve of the acceleration response spectrum value of the engineering requirement parameters with respect to the first natural vibration period based on the scalar model, and extract the boundary values ​​for different seismic performance level classifications.

[0030] The seismic vulnerability analysis module is used to construct a surface vulnerability function based on the log-normal distribution assumption of engineering demand parameters and the fitted probabilistic seismic demand model of high arch dams. It calculates the seismic vulnerability probability of high arch dams under different seismic performance levels by inputting seismic ground motion intensity parameters and boundary values ​​of different seismic performance levels.

[0031] According to another aspect of this specification, an electronic device is provided, including a memory and a processor, the memory storing program instructions executed by the processor, the processor invoking the program instructions to perform a seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory.

[0032] According to another aspect of this specification, a non-transitory computer-readable storage medium is provided, the non-transitory computer-readable storage medium storing computer instructions that cause the computer to execute a method for analyzing the seismic vulnerability of high arch dams based on extreme gradient boosting tree theory.

[0033] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0034] (1) This invention provides a method for analyzing the seismic vulnerability of high arch dams based on the extreme gradient boosting tree theory, which can provide an important reference for the seismic damage assessment of high arch dams;

[0035] (2) This invention proposes a probabilistic earthquake demand model for high arch dams that considers the nonlinear relationship between ground motion intensity parameters and engineering demand parameters. This model overcomes the limitation of the existing high arch dam earthquake vulnerability analysis method which assumes that ground motion intensity parameters and engineering demand parameters follow a logarithmic linear relationship. This model more accurately realizes the earthquake vulnerability analysis of high arch dams.

[0036] (3) The method of the present invention considers the influence of scalar strength parameters and vector strength parameters on the vulnerability model at the same time. By using the extreme gradient boosting tree model and the seismic vulnerability function, the conditional exceedance probability of the engineering demand parameters reaching a certain performance level is obtained, which can provide a new idea for the seismic vulnerability analysis of high arch dams. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart illustrating a seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory, provided for an embodiment of the present invention;

[0039] Figure 2 This is a flowchart of an example of seismic vulnerability analysis of a high arch dam based on extreme gradient boosting tree theory in an embodiment of the present invention;

[0040] Figure 3 This is a three-dimensional nonlinear finite element model diagram of the high arch dam-foundation system in an embodiment of the present invention;

[0041] Figure 4 This is the acceleration response spectrum of the selected ground motion data in this embodiment of the invention;

[0042] Figure 5This is a distribution diagram of engineering requirement parameters in an embodiment of the present invention;

[0043] Figure 6 This is the result of the probabilistic earthquake demand model for high arch dams in this embodiment of the invention;

[0044] Figure 7 In this embodiment of the invention, the engineering requirement parameters vary with the earthquake intensity parameter S. a The changes in (T1);

[0045] Figure 8 This is the seismic damage vulnerability curve of the high arch dam in this embodiment of the invention;

[0046] Figure 9 This is an embodiment of the invention showing the vulnerable surface of a high arch dam under slight damage during earthquakes;

[0047] Figure 10 This is the seismic damage vulnerability surface of a high arch dam under moderate damage in an embodiment of the present invention;

[0048] Figure 11 This is an embodiment of the invention showing the vulnerable surface of a high arch dam under severe earthquake damage.

[0049] Figure 12 A schematic diagram of a seismic vulnerability analysis system for high arch dams based on extreme gradient boosting tree theory is provided in an embodiment of the present invention.

[0050] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0051] It should be noted that:

[0052] The terms “comprising” and “having”, and any variations thereof, in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, product, or apparatus that includes a series of steps or units, not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0053] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices. The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be decomposed, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. In addition, the technical features of the various embodiments or individual embodiments provided by the present invention can be arbitrarily combined to form new technical solutions. Such combinations are not bound by the order of steps and / or structural composition patterns, but must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0055] like Figure 1 As shown, a seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory includes the following steps:

[0056] Step 1: Obtain several ground motion data that meet the site characteristics requirements of the high arch dam, establish a three-dimensional nonlinear finite element model of the high arch dam-foundation system, use the ground motion data as input to the finite element model for dynamic time history analysis, and construct a set of engineering requirement parameters.

[0057] Step 2: Calculate the seismic intensity parameters based on several seismic ground motion data that meet the site characteristics requirements of the high arch dam site, and construct a set of seismic intensity parameters; the seismic intensity parameters include the acceleration response spectrum value and root mean square velocity under the first natural period;

[0058] Step 3: Construct a probabilistic earthquake demand model for high arch dams based on the extreme gradient boosting tree model, and fit the nonlinear relationship between the engineering demand parameters and the ground motion intensity parameters based on the engineering demand parameter set and the ground motion intensity parameter set; the probabilistic earthquake demand model for high arch dams includes a scalar model with the acceleration response spectrum value under the first natural period as a single variable as an input variable and a vector model with two ground motion intensity parameters as input variables. The outputs of the scalar model and the vector model are both engineering demand parameters.

[0059] Step 4: Fit the variation curve of the acceleration response spectrum value of the engineering requirement parameters with respect to the first natural vibration period based on the scalar model, and extract the boundary value for the division of different seismic performance levels;

[0060] Step 5: Based on the assumption of log-normal distribution of engineering demand parameters, construct the surface vulnerability function using the fitted high arch dam probabilistic seismic demand model, input the ground motion intensity parameters and the boundary values ​​of different seismic performance levels for calculation, and obtain the seismic vulnerability probability of high arch dam under different seismic performance levels.

[0061] In step 1, the process of acquiring the ground motion data is as follows: using acceleration response spectrum matching, ground motion data that meets the site characteristics requirements of the high arch dam site are selected from the ground motion database.

[0062] Step 1, the steps for constructing the engineering requirement parameter set include:

[0063] A three-dimensional nonlinear finite element model of the high arch dam-foundation system was established. Several ground motion data that meet the site characteristics requirements of the high arch dam were used as inputs to the finite element model for dynamic time history analysis. Damage index data of the high arch dam were selected from the dynamic time history analysis results as engineering requirement parameters to construct a set of engineering requirement parameters.

[0064] Among them, the engineering requirement parameters are used to reflect the overall damage of high arch dams under seismic action. In this invention, the damage index data of high arch dams uses a single index, namely the volumetric damage ratio (SVD) of the high arch dam body.

[0065] The construction process of the three-dimensional nonlinear finite element model of the high arch dam-foundation system is as follows: based on the geometric parameters of the high arch dam and the foundation, a three-dimensional geometric model of the high arch dam-foundation system is constructed in Abaqus software, and the finite element model is divided to establish a three-dimensional nonlinear finite element model of the high arch dam-foundation system.

[0066] For example, obtain Seismic ground motion data meeting the site characteristics requirements of the high arch dam were used as input to the finite element model of the high arch dam for dynamic time history analysis. The damage volume ratio of the high arch dam body was selected from the dynamic time history analysis results as the engineering requirement parameter, and finally, the set of engineering requirement parameters was obtained. (i=1,2,...,N), where i represents the seismic ground motion data number and N represents the total number of seismic ground motion data. This represents the engineering requirement parameters corresponding to the i-th seismic ground motion data.

[0067] Step 2, the steps for constructing the set of seismic motion intensity parameters, include:

[0068] Acceleration response spectrum analysis was performed on several ground motion data that met the site characteristics requirements of the high arch dam. The acceleration response spectrum value S under the first natural period of the high arch dam structure was selected. a (T1) and root mean square velocity V RMS Construct a set of ground motion intensity parameters.

[0069] Among them, the set of ground motion intensity parameters is , (i=1,2,...,N), where, For the ground motion intensity parameter corresponding to the i-th ground motion data, using and , representing the acceleration response spectrum value and the corresponding root mean square velocity of the i-th ground motion data, respectively.

[0070] The formula for calculating the root mean square velocity is as follows:

[0071] (1)

[0072] In the formula: Represents the time history of ground motion velocity; It represents the total time history of earthquake motion.

[0073] In step 3, the extreme gradient boosting tree (Xboost) model is used to analyze the engineering requirement parameters. and seismic intensity parameters Nonlinear fitting was performed to construct a probabilistic earthquake demand model for high arch dams that reflects the nonlinear relationship between the two.

[0074] Specifically, the reasoning process of the probabilistic earthquake demand model for high arch dams is as follows:

[0075] In the probabilistic earthquake demand model for high arch dams, the predicted value of the engineering demand parameter under the action of the i-th seismic ground motion data can be expressed as follows:

[0076] (2)

[0077] In the formula, The predicted values ​​of engineering demand parameters for the corresponding i-th ground motion data point are output by the probabilistic earthquake demand model for high arch dams. For a single regression decision tree, j is the regression decision tree number. The number of all regression decision trees; The set of all regression decision trees; Let i be the seismic intensity parameter of the i-th earthquake. Let be the calculated score of the j-th regression decision tree for the i-th sample of ground motion intensity parameters.

[0078] Furthermore, in step 3, the training process of the probabilistic seismic demand model for high arch dams includes:

[0079] The data in the engineering requirement parameter set and the seismic intensity parameter set are matched one by one according to the corresponding seismic data, and the training set and validation set are divided according to a preset ratio. The training set data is used to train the high arch dam probabilistic earthquake requirement model.

[0080] Among them, the iterative objective function of the high arch dam probabilistic seismic demand model training process is the core of the algorithm, as shown in the following formula:

[0081] (3)

[0082] In the formula, Describe the iterative objective function; This is the loss function used to evaluate the predicted values ​​of engineering demand parameters resulting from model fitting. Compared with the true value The losses between; This is a regularization term used to penalize complex models and avoid overfitting; Let be the number of leaf nodes in the k-th regression decision tree; The output score of the l-th leaf node of the regression decision tree; The penalty term is the number of leaf nodes; This is an L2 regularization penalty term.

[0083] During iterative training, a gradient boosting strategy is employed, adding a new regression decision tree to the existing model in each iteration. Assume the i-th seismic intensity parameter sample is the predicted value of the dynamic response of the high arch dam in the (t-1)-th iteration. The objective function for the t-th iteration can be expressed as follows:

[0084] (4)

[0085] In the formula, This refers to the decision tree newly added in the t-th iteration; This is a constant term.

[0086] After performing a second-order Taylor expansion on the above equation and removing the constant term, Convert to a topic about The problem of finding the minimum value of a quadratic equation in one variable, and considering the objective function with respect to... The optimal objective value can be calculated by taking the first derivative. for:

[0087] (5)

[0088] After each iteration, the existing model is validated using a validation set. When the evaluation metrics on the validation set (such as mean squared error) do not improve further in a preset number of iterations, or when the preset maximum number of training iterations is reached, training terminates and the trained model is output.

[0089] In step 3, the high arch dam probabilistic earthquake demand model includes a scalar model with the acceleration response spectrum value under the first natural period as a single input variable and a vector model with two seismic intensity parameters as input variables.

[0090] Specifically, following the training steps described above, a scalar model is trained by using the acceleration response spectrum value under the first natural period as the single input variable of the probabilistic earthquake demand model for high arch dams. At the same time, a vector model is trained by using the acceleration response spectrum value under the first natural period and the root mean square velocity as two ground motion intensity parameters as input variables of the probabilistic earthquake demand model for high arch dams.

[0091] In step 4, the change curve of the acceleration response spectrum value of the engineering requirement parameters with respect to the first natural vibration period is obtained according to the scalar model. Under the condition that the engineering requirement parameters meet the preset seismic damage assessment level, the stage of the slope of the change curve abruptly changes three times. The critical value of the engineering requirement parameters at each abrupt change is used as the boundary value for the seismic performance level division, and the four levels of seismic performance of the engineering requirement parameters are divided.

[0092] Among them, as the engineering requirements parameters gradually increase, the four seismic resistance levels are basically intact, slightly damaged, moderately damaged, and severely damaged, respectively.

[0093] Optionally, the engineering requirement parameters are fitted with the seismic intensity parameters, i.e., S, according to the scalar model. a The curve (T1) reflects the trend of change. Abrupt changes in the slope of the curve are considered abrupt changes in the trend. The critical values ​​of the engineering demand parameters at each stage are used as the limit values ​​LS of the engineering demand parameters, which are then used as the boundary values ​​for classifying the seismic performance levels. This classifies the engineering demand parameters into four performance levels under seismic loading: basically intact, slightly damaged, moderately damaged, and severely damaged. The trend of change can also be presented in other forms, such as in a table.

[0094] In step 5, based on engineering requirement parameters The log-normal distribution assumption, that is, assuming that the engineering demand parameters at a specific seismic intensity level follow a log-normal distribution: the mean is... Sum of standard deviation The seismic vulnerability function of high arch dams can be determined as follows:

[0095] (6)

[0096] In the formula, Represents the parameterized seismic vulnerability function of high arch dams; This indicates the input of ground motion intensity parameters. Indicates the values ​​of the seismic motion intensity parameters; Represents a probability function; and Let represent the mean and logarithmic standard deviation of the seismic motion intensity parameter, respectively. Indicates leading to The median of the limit state value.

[0097] Furthermore, the seismic vulnerability function is constructed using the trained probabilistic seismic demand model for high arch dams, mathematically expressed as:

[0098] (7)

[0099] In the formula, This indicates that the condition exceeds the probability. This indicates the input of engineering requirement parameters; Indicates the limit values ​​of engineering requirement parameters. The two values ​​represent the threshold values ​​for the seismic performance level of high arch dams. In this invention, they are numerically equal. When studying different seismic performance levels, It will change accordingly; Indicates when the scalar seismic intensity parameter At that time, the engineering demand parameters output by the probabilistic seismic demand model for high arch dams; This indicates that the probabilistic earthquake demand model for high arch dams is in Logarithmic standard deviation under the given conditions.

[0100] For scalar models , The expression is:

[0101] (8)

[0102] In the formula, Indicates when the scalar seismic intensity parameter The actual engineering requirements parameters under the given conditions, here corresponding to the elements in the engineering requirements parameter set. ; This indicates the number of seismic waves used in dynamic time history analysis.

[0103] Similarly, for vector models, , The expression is:

[0104] (9)

[0105] In the formula, Indicates when the vector seismic intensity parameter Engineering requirements parameters under the i-th seismic motion.

[0106] Furthermore, in step 5, the process of plotting the seismic vulnerability curves and / or surfaces of the high arch dam under different seismic performance levels includes:

[0107] Based on the threshold value of a certain seismic performance level of a high arch dam, the probability of exceeding the conditions for the engineering demand parameters to reach that seismic performance level is calculated by the seismic vulnerability function. The seismic vulnerability curve of the high arch dam under that seismic performance level is plotted using the corresponding scalar model, and / or the seismic vulnerability surface of the high arch dam under that seismic performance level is plotted using the corresponding vector model. Based on this, the seismic vulnerability curves and / or surfaces of the high arch dam under different seismic performance levels are obtained.

[0108] Specifically, the conditional exceedance probability (different LS values) of the engineering demand parameters reaching a certain performance level can be calculated by equation (7), and the seismic vulnerability curve or surface of the high arch dam can be plotted respectively.

[0109] like Figure 2 As shown, this is an example of seismic vulnerability analysis of a high arch dam based on the extreme gradient boosting tree theory. Taking a certain high arch dam as an example, the main steps are as follows.

[0110] Step 1: Based on the geometric parameters of the high arch dam and foundation, construct a three-dimensional geometric model of the high arch dam-foundation system in Abaqus software, and use C3D8 elements to mesh the finite element model to establish a three-dimensional nonlinear finite element model of the high arch dam-foundation system (e.g., Figure 3 It comprises 34,555 units and 40,520 nodes.

[0111] Based on the site characteristics of the high arch dam, 250 seismic motion data points meeting the site requirements were selected using acceleration response spectrum matching. The selected acceleration response spectra are as follows: Figure 4 As shown, the dynamic time history analysis was performed using it as input to the finite element model of the high arch dam to obtain the dynamic response results of the high arch dam. The damage volume ratio (DVR) of the high arch dam body was selected to quantitatively reflect the overall damage of the arch dam under seismic loading, and this was used as the set of engineering requirement parameters. The distribution of engineering requirement parameters is as follows: Figure 5As shown, the median value of the damage volume ratio (DVR) of the high arch dam body is 0.04, while the DVR value for a cumulative proportion of 90% is 0.16.

[0112] Step 2: Calculate the seismic intensity parameters that meet the site characteristics requirements of the high arch dam. Select the acceleration response spectrum and root-mean-square velocity corresponding to the first natural period T1 of the high arch dam structure, i.e., S. a (T1) and V RMS The set of ground motion intensity parameters used to construct probabilistic earthquake demand models .

[0113] Step 3: Use an extreme gradient boosting tree model to evaluate the engineering requirement parameters. and seismic intensity parameters Perform nonlinear fitting to construct a reflection and seismic intensity parameters Probabilistic Seismic Demand Model for High Arch Dams with Nonlinear Relationships .

[0114] From this, the scalar parameter [single S] can be obtained. a (T1)] and vector parameters [S] a (T1) and V RMS The probabilistic seismic demand model for high arch dams constructed with engineering demand parameters (such as...) Figure 6 The models are defined as scalar and vector models, respectively. It can be seen that the prediction results are generally within the 1:2 range, indicating that the earthquake demand model for high arch dam damage probability (nonlinear) constructed using the extreme gradient boosting tree algorithm is reliable.

[0115] Step 4: Based on the earthquake damage DVR of high arch dams and the ground motion intensity parameter S a (T1) abrupt changes (e.g.) Figure 7 This study identifies three stages of slope variation in the seismic damage curve of high arch dams, using 0.03, 0.1, and 0.2 as the limit values ​​LS for engineering requirement parameters (points in the figure where the slope changes significantly, at 10 on the vertical axis). -3 The significant slope change at the magnitude level does not reach the level of earthquake damage assessment and is not considered a threshold value. The engineering requirement parameters are divided into four performance levels (seismic performance levels) under earthquake action, namely, basically intact, slightly damaged, moderately damaged and severely damaged.

[0116] Step 5: Based on engineering requirement parameters The log-normal distribution assumption, i.e., following a mean of 1 / 2, is true. Sum of standard deviation That is, the seismic vulnerability function of high arch dams can be determined as:

[0117]

[0118] Based on the probabilistic earthquake demand model for high arch dams, the corresponding earthquake vulnerability function is obtained:

[0119]

[0120] Therefore, the conditional exceedance probability of the engineering requirement parameters reaching a certain performance level can be calculated. Figure 7 Seismic vulnerability curves for high arch dams can be plotted (calculated using a seismic vulnerability function based on a scalar model, such as...). Figure 8 ) and vulnerability surfaces (calculated from a vector-based seismic vulnerability function, such as Figure 9-11 (These are the seismic vulnerability surfaces of high arch dams under slight, moderate, and severe damage, respectively).

[0121] To further compare the necessity of the nonlinear relationship between seismic damage and seismic motion intensity parameters of high arch dams, the seismic vulnerability curve based on linear regression and the seismic vulnerability curve of the method of this invention are compared. Figure 8 A comparison was made. It can be seen that the conditional exceedance probability calculated based on the probabilistic earthquake demand model differs significantly by more than 20% from the conditional exceedance probability calculated based on the linear probabilistic earthquake demand model, and is more consistent with reality. Furthermore, compared to the vulnerability curve, the vulnerability curve constructed based on vector strength parameters can better characterize the failure state of high arch dams.

[0122] The implementation of the various embodiments of this invention is based on programmed processing through a system with processor functionality. Therefore, in practical engineering, the technical solutions and functions of the various embodiments of this invention are encapsulated into various modules. Based on this reality, and building upon the above embodiments, this invention provides a seismic vulnerability analysis system for high arch dams based on extreme gradient boosting tree theory. This system is used to execute a seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory from the above method embodiments.

[0123] See Figure 12 The system includes:

[0124] The engineering requirement parameter acquisition module is used to acquire several ground motion data that meet the site characteristics requirements of the high arch dam site, and to perform dynamic time history analysis to construct a set of engineering requirement parameters.

[0125] The seismic intensity parameter acquisition module is used to calculate seismic intensity parameters based on several seismic data that meet the site characteristics requirements of the high arch dam site, and to construct a seismic intensity parameter set; the seismic intensity parameters include the acceleration response spectrum value and root mean square velocity under the first natural period;

[0126] The module for constructing and training a probabilistic earthquake demand model for high arch dams is used to construct a probabilistic earthquake demand model for high arch dams based on an extreme gradient boosting tree model, and to fit the nonlinear relationship between the engineering demand parameters and the seismic intensity parameters based on the engineering demand parameter set and the seismic intensity parameter set. The probabilistic earthquake demand model for high arch dams includes a scalar model with the acceleration response spectrum value under the first natural period as a single variable as an input variable and a vector model with two seismic intensity parameters as input variables. The outputs of the scalar model and the vector model are both engineering demand parameters.

[0127] The seismic performance level classification module is used to fit the variation curve of the acceleration response spectrum value of the engineering requirement parameters with respect to the first natural vibration period based on the scalar model, and extract the boundary values ​​for different seismic performance level classifications.

[0128] The seismic vulnerability analysis module is used to construct a surface vulnerability function based on the log-normal distribution assumption of engineering demand parameters and the fitted probabilistic seismic demand model of high arch dams. It calculates the seismic vulnerability probability of high arch dams under different seismic performance levels by inputting seismic ground motion intensity parameters and boundary values ​​of different seismic performance levels.

[0129] It should be noted that the system embodiments provided by the present invention are used not only to implement the methods in the above method embodiments, but also to implement the methods in other method embodiments provided by the present invention. The only difference is that corresponding functional modules are set. The principle is basically the same as that of the above system embodiments provided by the present invention. As long as those skilled in the art can improve the modules in the above system embodiments by referring to the specific technical solutions in other method embodiments and combining technical features to obtain corresponding technical means and technical solutions composed of these technical means, on the basis of the above system embodiments, and on the premise of ensuring the practicality of the technical solutions, they can obtain corresponding system-like embodiments for implementing the methods in other method-like embodiments.

[0130] The method in this embodiment of the invention is implemented using an electronic device; therefore, it is necessary to introduce the relevant electronic device. For this purpose, embodiments of the present invention provide an electronic device, such as... Figure 13 As shown, the electronic device includes: at least one processor, a communication interface, at least one memory, and a communication bus, wherein the at least one processor, the communication interface, and the at least one memory communicate with each other via the communication bus. The at least one processor invokes logical instructions stored in the at least one memory to execute all or part of the steps of the methods provided in the foregoing method embodiments.

[0131] Furthermore, when the logical instructions in at least one of the aforementioned memories are implemented as software functional units and sold or used as independent products, they are 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 a part of the technical solution, is embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (a personal computer, server, or network device) to execute all or part of the steps of the methods described in the various method embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks—various media for storing program code.

[0132] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, located in one place, or distributed across multiple network units. The purpose of this embodiment is achieved by selecting some or all of the modules according to actual needs. Those skilled in the art will understand and implement this without any inventive effort.

[0133] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0135] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0136] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0137] Based on the same technical concept as the foregoing embodiments, the present invention provides a non-transitory computer-readable storage medium that stores computer instructions that cause the computer to execute a seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory.

[0138] In summary, this invention discloses a seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory. This method, based on extreme gradient boosting tree theory, realizes seismic vulnerability analysis of high arch dams considering the nonlinear relationship between ground motion intensity parameters and engineering requirement parameters. First, a three-dimensional nonlinear finite element model of the high arch dam-foundation system is established, and dynamic time history analysis is performed using ground motion data that meets the site characteristics of the high arch dam site to obtain a set of engineering requirement parameters. Simultaneously, ground motion intensity parameters that meet the site characteristics of the high arch dam site are calculated, and a set of ground motion intensity parameters for constructing a probabilistic seismic requirement model is selected. Second, based on the extreme gradient boosting tree model, the engineering requirement parameters and ground motion intensity parameters are fitted to reflect the nonlinear relationship between them, thus establishing a probabilistic seismic requirement model for the high arch dam. Finally, based on the abrupt changes in engineering requirement parameters with ground motion intensity parameters, different performance levels of the engineering requirement parameters under seismic loading are classified, the conditional exceedance probability of the engineering requirement parameters reaching a certain performance level is calculated, and the seismic vulnerability curve or surface of the high arch dam is plotted. This invention develops a seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory. It overcomes the limitation of existing methods for seismic performance analysis of high arch dams that assume a log-linear relationship between ground motion intensity parameters and engineering requirement parameters, and provides a new approach for seismic vulnerability analysis of high arch dams.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing the seismic vulnerability of high arch dams based on extreme gradient boosting tree theory, characterized in that, include: Acquire several ground motion data that meet the site characteristics requirements of the high arch dam site, perform dynamic time history analysis, and construct a set of engineering requirement parameters; Seismic intensity parameters are calculated based on several seismic ground motion data that meet the site characteristics requirements of high arch dam sites, and a set of seismic intensity parameters is constructed; the seismic intensity parameters include the acceleration response spectrum value and root mean square velocity under the first natural period; A probabilistic earthquake demand model for high arch dams is constructed based on an extreme gradient boosting tree model, and the nonlinear relationship between the engineering demand parameters and the seismic intensity parameters is fitted based on the engineering demand parameter set and the seismic intensity parameter set. The probabilistic earthquake demand model for high arch dams includes a scalar model with the acceleration response spectrum value under the first natural period as a single variable as an input variable and a vector model with two seismic intensity parameters as input variables. The outputs of the scalar model and the vector model are both engineering demand parameters. Based on the scalar model, the curves of the change of engineering requirement parameters with respect to the acceleration response spectrum value under the first natural vibration period are fitted, and the boundary values ​​for different seismic performance levels are extracted. Based on the assumption of a log-normal distribution of engineering demand parameters, a surface vulnerability function is constructed using a fitted probabilistic seismic demand model for high arch dams. The seismic ground motion intensity parameters and the boundary values ​​of different seismic performance levels are input for calculation to obtain the seismic vulnerability probability of high arch dams under different seismic performance levels.

2. The seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory as described in claim 1, characterized in that, The steps for constructing the engineering requirement parameter set include: A three-dimensional nonlinear finite element model of the high arch dam-foundation system was established. Several ground motion data that meet the site characteristics requirements of the high arch dam were used as inputs to the finite element model for dynamic time history analysis. Damage index data of the high arch dam were selected from the dynamic time history analysis results as engineering requirement parameters to construct a set of engineering requirement parameters.

3. The seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory as described in claim 1, characterized in that, The training process of the probabilistic seismic demand model for high arch dams includes: The engineering requirement parameter set and the seismic ground motion intensity parameter set are matched one-to-one according to the corresponding seismic ground motion data, and the data are divided into training and validation sets according to a preset ratio. The probabilistic seismic demand model for high arch dams is trained using the training set data. The iterative objective function during the training process is: ； In the formula, represents the iterative objective function; i represents the seismic data number, and N represents the total number of seismic data; The loss function; For regularization terms; The predicted engineering demand parameters for the corresponding i-th seismic ground motion data point, output by the probabilistic seismic demand model for high arch dams. These are the actual values ​​of the engineering requirements parameters; For a single regression decision tree, j is the regression decision tree number. The number of all regression decision trees; Let be the number of leaf nodes in the k-th regression decision tree; The output score of the l-th leaf node of the regression decision tree; The penalty term is the number of leaf nodes; This is an L2 regularization penalty term; Iterative training employs a gradient boosting strategy, adding a new regression decision tree to the existing model in each iteration. After each iteration, the existing model is validated using a validation set. Training terminates when the evaluation metrics on the validation set fail to improve further in a preset number of iterations or when the preset maximum number of training iterations is reached, and the trained high arch dam probabilistic earthquake demand model is output.

4. The seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory as described in claim 3, characterized in that, The training process for scalar and vector models includes: According to the training process of the high arch dam probabilistic earthquake demand model, the acceleration response spectrum value under the first natural period is used as the single input variable of the high arch dam probabilistic earthquake demand model to obtain a scalar model. At the same time, the acceleration response spectrum value under the first natural period and the root mean square velocity are used as two ground motion intensity parameters to obtain a vector model.

5. The seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory as described in claim 1, characterized in that, The process of extracting the boundary values ​​for different seismic performance levels includes: Based on the scalar model, the change curve of the acceleration response spectrum value of the engineering demand parameters with respect to the first natural vibration period is obtained. Under the condition that the engineering demand parameters meet the preset seismic damage assessment level, the stage of the slope of the change curve abruptly changes three times. The critical value of the engineering demand parameters at each abrupt change is used as the boundary value for the seismic performance level division, and the four levels of seismic performance of the engineering demand parameters are divided.

6. The seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory as described in claim 1, characterized in that, The mathematical expression of the seismic vulnerability function is as follows: ； In the formula, This indicates that the condition exceeds the probability. This indicates the input of engineering requirement parameters; Indicates when the scalar seismic intensity parameter At that time, the engineering demand parameters output by the probabilistic seismic demand model for high arch dams; The limit value representing the seismic performance level of high arch dams; This indicates that the probabilistic earthquake demand model for high arch dams is in Logarithmic standard deviation under the given conditions.

7. The seismic vulnerability analysis method for high arch dams based on extreme gradient boosting tree theory as described in claim 1, characterized in that, Also includes: Based on the threshold value of a certain seismic performance level of a high arch dam, the probability of exceeding the conditions for the engineering demand parameters to reach that seismic performance level is calculated by the seismic vulnerability function. The seismic vulnerability curve of the high arch dam under that seismic performance level is plotted using the corresponding scalar model, and / or the seismic vulnerability surface of the high arch dam under that seismic performance level is plotted using the corresponding vector model. Based on this, the seismic vulnerability curves and / or surfaces of the high arch dam under different seismic performance levels are obtained.

8. A seismic vulnerability analysis system for high arch dams based on extreme gradient boosting tree theory, characterized in that, include: The engineering requirement parameter acquisition module is used to acquire several ground motion data that meet the site characteristics requirements of the high arch dam site, and to perform dynamic time history analysis to construct a set of engineering requirement parameters. The seismic intensity parameter acquisition module is used to calculate seismic intensity parameters based on several seismic data that meet the site characteristics requirements of the high arch dam site, and to construct a seismic intensity parameter set; the seismic intensity parameters include the acceleration response spectrum value and root mean square velocity under the first natural period; The module for constructing and training a probabilistic earthquake demand model for high arch dams is used to construct a probabilistic earthquake demand model for high arch dams based on an extreme gradient boosting tree model, and to fit the nonlinear relationship between the engineering demand parameters and the seismic intensity parameters based on the engineering demand parameter set and the seismic intensity parameter set. The probabilistic earthquake demand model for high arch dams includes a scalar model with the acceleration response spectrum value under the first natural period as a single variable as an input variable and a vector model with two seismic intensity parameters as input variables. The outputs of the scalar model and the vector model are both engineering demand parameters. The seismic performance level classification module is used to fit the variation curve of the acceleration response spectrum value of the engineering requirement parameters with respect to the first natural vibration period based on the scalar model, and extract the boundary values ​​for different seismic performance level classifications. The seismic vulnerability analysis module is used to construct a surface vulnerability function based on the log-normal distribution assumption of engineering demand parameters and the fitted probabilistic seismic demand model of high arch dams. It calculates the seismic vulnerability probability of high arch dams under different seismic performance levels by inputting seismic ground motion intensity parameters and boundary values ​​of different seismic performance levels.

9. An electronic device, characterized in that, The method includes a memory and a processor, the memory storing program instructions that are executed by the processor, the processor invoking the program instructions to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the method described in any one of claims 1 to 7.

Images