Hydropower engineering rock mass permeability prediction analysis method

Abstract

The invention provides a hydroelectric engineering rock mass permeability prediction analysis method which comprises the following steps: determining four rock mass permeability analysis indexes, namely a rock mass burial depth RD, a rock core quality index RQD, a rock core structural surface density characteristic FSD and a rock mass integrity index RID, the correlation between the four rock mass permeability analysis indexes and a rock mass permeability coefficient K exceeds a threshold value, and the four rock mass permeability analysis indexes are respectively a rock mass burial depth RD, a rock core quality index RQD, a rock core structural surface density characteristic FSD and a rock mass integrity index RID; constructing a plurality of training samples, and training a pre-constructed permeability prediction analysis model to obtain a trained permeability prediction analysis model; and predicting the rock mass permeability coefficient K by adopting the trained permeability prediction analysis model. According to the hydroelectric engineering rock mass permeability prediction analysis method provided by the invention, the permeability of various rock masses can be accurately and completely predicted and analyzed, and the design reference value of the hydroelectric engineering is effectively improved.

Description

Technical Field

[0001] The invention belongs to the technical field of rock mass permeability prediction and analysis, and in particular relates to a method for predicting and analyzing rock mass permeability in a hydropower project. Background Art

[0002] During the survey and design phase of hydropower engineering, it is necessary to obtain the permeability of geological rock masses at dam sites, water transfer tunnels, powerhouses, surge tanks, shafts, traffic tunnels and other building sites, so as to obtain the water permeability of underground rock masses and provide basic data for subsequent anti-seepage, structural stability and other design work. Therefore, it is necessary to carry out geological exploration and testing to obtain the permeability of geological rock masses.

[0003] The permeability of geological rock mass is affected by many factors such as burial depth and rock mass fracture structure, and often shows significant anisotropy and spatial variability characteristics, with large uncertainty, making it difficult to accurately obtain permeability performance parameter values. At present, geological survey professionals generally arrange exploration drilling and water pressure testing to calculate and statistically recommend rock mass permeability values. However, due to complex geological conditions and limitations of funds and construction period, the relevant data obtained by the water pressure test may be scattered and incomplete, especially the completion of deep hole water pressure testing work has the risk of contract performance, and the current permeability of various underground rock masses can generally only be combined with the recommended values ​​of the specifications, expert experience and some water pressure test values ​​to give the recommended rock mass permeability values. Therefore, it is currently difficult to accurately and completely obtain the permeability performance parameters of geological rock masses. Summary of the invention

[0004] In view of the defects in the prior art, the present invention provides a method for predicting and analyzing the permeability of rock masses in hydropower projects, which can effectively solve the above problems.

[0005] The technical solution adopted by the present invention is as follows:

[0006] The present invention provides a method for predicting and analyzing rock mass permeability of a hydropower project, comprising the following steps:

[0007] Step S1, preliminarily determining a plurality of rock mass permeability analysis indices related to the rock mass permeability coefficient K;

[0008] Step S2, performing correlation analysis on various rock mass permeability analysis indicators and rock mass permeability coefficient K determined initially, and obtaining four rock mass permeability analysis indicators having correlation with rock mass permeability coefficient K exceeding a threshold, namely: rock mass burial depth RD, core quality index RQD, core structural surface density feature FSD and rock mass integrity index RID;

[0009] Step S3, constructing multiple training samples, and normalizing each training sample to obtain multiple normalized training samples to form a training sample set;

[0010] Each training sample in the training sample set is represented by s = (X, Y); where X is the rock mass permeability analysis index vector, X = (x1, x2, x3, x4), x1, x2, x3, x4, respectively represent the sample values ​​of rock mass burial depth RD, core quality index RQD, core structure surface density feature FSD and rock mass integrity index RID; Y represents the corresponding value of rock mass permeability coefficient K;

[0011] Step S4, using the training sample set to train the pre-built permeability prediction and analysis model to obtain a trained permeability prediction and analysis model;

[0012] Step S5, for the rock mass that currently needs to be predicted and analyzed for permeability, obtain the measured values ​​of the rock mass burial depth RD, the core quality index RQD, the core structure surface density characteristic FSD and the rock mass integrity index RID that need to be interpolated and calculated, and input them into the trained permeability prediction and analysis model, and the trained permeability prediction and analysis model outputs the corresponding predicted value of the rock mass permeability coefficient K.

[0013] Preferably, in step S2, a correlation analysis is performed on the various rock mass permeability analysis indicators and the rock mass permeability coefficient K that are initially determined, specifically:

[0014] Step S2.1, denote any rock mass permeability analysis index as C, obtain the measured values ​​of M rock mass permeability analysis indexes C, expressed as: C1, C2, ..., C M ; Obtain the rock mass permeability coefficient K corresponding to the measured value of each rock mass permeability analysis index C, which is expressed as: K1, K2, …, K M ;

[0015] For the measured value sequence of rock permeability analysis index C, C1, C2, ..., C M The measured values ​​of each rock mass permeability analysis index C are expressed in descending order in the measured value sequence of the rock mass permeability analysis index C: Q1, Q2, …, Q M ;

[0016] For the rock mass permeability coefficient K sequence K1, K2, ..., K M The value of the permeability coefficient K of each rock mass is in the sequence of the permeability coefficient K of the rock mass K1, K2, …, K M The descending numbers in are represented as: P1, P2, ..., P M ;

[0017] Calculate the difference between sequence number Q1 and sequence number P1 to obtain d1;

[0018] Calculate the difference between sequence number Q2 and sequence number P2 to obtain d2;

[0019] And so on

[0020] Calculate the sequence number Q M and serial number P M The difference between M ;

[0021] Step S2.2, using the following formula, obtain the correlation coefficient r between the rock mass permeability analysis index C and the rock mass permeability coefficient K s :

[0022]

[0023] Where: k = 1, 2, ..., M;

[0024] Step S2.3, determine the correlation coefficient r s Is it greater than the threshold ε? If so, select the rock permeability analysis index C.

[0025] Preferably, in step S2, the method for obtaining the core structure surface density feature FSD is:

[0026] Step S2-1, the drilling footage depth is L; the core structural surface inclination trend density is divided into three inclination sections according to the inclination degree interval, namely: (0, 30], (30, 60], (60, 90];

[0027] Step S2-2, counting the number of structural surfaces in each inclination section, respectively: N 0～30 、N 30～60 and N 60～90 ;

[0028] Step S2-3, according to the rock mass lithology factors currently analyzed, the weights corresponding to the inclination sections are set respectively, namely: W1, W2 and W3;

[0029] Step S2-4, using the following formula to obtain the core structure surface density feature FSD:

[0030]

[0031] Thus, the value of the core structure surface density characteristic FSD is obtained.

[0032] Preferably, for metamorphic rocks, the weights are: W1=0.1, W2=0.3, W3=0.6.

[0033] Preferably, step S4 is specifically:

[0034] Step S4.1, the constructed permeability prediction and analysis model is a DELM permeability prediction and analysis model, including 1 input layer, N layers of hidden layers cascaded forward and backward, and 1 output layer; wherein the input layer has 4 neurons, each hidden layer has 4 neurons, and the output layer has 4 neurons;

[0035] Step S4.2, randomly generate the weight of each neuron in the input layer through an orthogonal matrix;

[0036] Step S4.3, for any training sample s = (X, Y), X = (x1, x2, x3, x4), Y represents the corresponding value of the rock mass permeability coefficient K, firstly input x1, x2, x3, x4 into the 4 neurons of the input layer respectively, and each neuron of the input layer outputs x through weight calculation respectively. 11 ,x 21 ,x 31 ,x 41 , forming a matrix X1=(x 11 ,x 21 ,x 31 ,x 41 );

[0037] Step S4.4, transform the matrix X1=(x 11 ,x 21 ,x 31 ,x 41 ) is input to the hidden layer of the first layer, and the output matrix of the hidden layer of the first layer is set to X2 = (x 12 ,x 22 ,x 32 ,x 42 ) is equal to the input matrix X1, so the weight vector β2 of the hidden layer of the second layer is obtained by the following formula:

[0038]

[0039] β2β2 T =I

[0040] Where: C is the regularization parameter; I is the identity matrix;

[0041] Step S4.5, transform the matrix X2=(x 12 ,x 22 ,x 32 ,x 42 ) is input to the hidden layer of the second layer, and the output matrix X3 of the hidden layer of the second layer is obtained using the following formula:

[0042]

[0043] β2β2 T =I

[0044] At the same time, determine the weight vector β3 of the hidden layer of the third layer:

[0045] β3=X3Y

[0046] Step S4.6, input the matrix X3 and the weight vector β3 to the hidden layer of the third layer, and use the same method as step S4.5 to obtain the output matrix X4 of the hidden layer of the third layer and the weight vector β4 of the hidden layer of the fourth layer; and so on, until the output matrix X of the hidden layer of the Nth layer is obtained. N+1 and the weight vector β N+1 ;

[0047] Step S4.7, transform the matrix X N+1 and the weight vector β N+1 Input to the output layer, the output layer outputs the final output vector Y′;

[0048] Step S4.8, by comparing the output vector Y′ and the sign value of the rock permeability coefficient K, that is, Y; if both are less than the threshold, then the weight vectors of each layer at this time form the final trained permeability prediction and analysis model; if it is not less than the threshold, then with Y′ and Y being equal as the goal, the least squares method is used to solve, and the weight vectors of each layer after the solution are obtained to form the final trained permeability prediction and analysis model.

[0049] The method for predicting and analyzing the permeability of rock mass in hydropower engineering provided by the present invention has the following advantages:

[0050] The present invention provides a method for predicting and analyzing the permeability of rock masses in hydropower projects, and in particular relates to a method for predicting and analyzing the permeability of underlying rock masses drilled in pumped storage power stations, conventional hydropower stations, etc. The method can accurately and completely predict and analyze the permeability of various rock masses, and effectively improve the reference value of hydropower project design. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic flow chart of a method for predicting and analyzing rock mass permeability in a hydropower project provided by the present invention.

[0052] Figure 2 A flowchart for training a pre-built permeability prediction analysis model provided by the present invention;

[0053] Figure 3 A relationship diagram between the number of iterations and the convergence curve provided by the present invention;

[0054] Figure 4 A relationship diagram between the true value and the predicted value when training with the training set at different iteration times provided by the present invention;

[0055] Figure 5A relationship diagram between the true value and the predicted value when the test set is used for training at different iteration times provided by the present invention. DETAILED DESCRIPTION

[0056] In order to make the technical problems, technical solutions and beneficial effects solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] The present invention provides a method for predicting and analyzing the permeability of rock masses in hydropower projects, and in particular relates to a method for predicting and analyzing the permeability of underlying rock masses drilled in pumped storage power stations, conventional hydropower stations, etc. The method can accurately and completely predict and analyze the permeability of various rock masses, and effectively improve the reference value of hydropower project design.

[0058] See also Figure 1 The present invention provides a method for predicting and analyzing the permeability of rock mass in a hydropower project, comprising the following steps:

[0059] Step S1, preliminarily determining a plurality of rock mass permeability analysis indices related to the rock mass permeability coefficient K;

[0060] Step S2, performing correlation analysis on various rock mass permeability analysis indicators and rock mass permeability coefficient K determined initially, and obtaining four rock mass permeability analysis indicators having correlation with rock mass permeability coefficient K exceeding a threshold, namely: rock mass burial depth RD, core quality index RQD, core structural surface density feature FSD and rock mass integrity index RID;

[0061] In step S2, correlation analysis is performed on various rock mass permeability analysis indicators and rock mass permeability coefficient K that are initially determined, specifically:

[0062] Step S2.1, denote any rock mass permeability analysis index as C, obtain the measured values ​​of M rock mass permeability analysis indexes C, expressed as: C1, C2, ..., C M ; Obtain the rock mass permeability coefficient K corresponding to the measured value of each rock mass permeability analysis index C, which is expressed as: K1, K2, …, K M ;

[0063] For the measured value sequence of rock permeability analysis index C, C1, C2, ..., C M The measured values ​​of each rock mass permeability analysis index C are expressed in descending order in the measured value sequence of the rock mass permeability analysis index C: Q1, Q2, …, Q M ;

[0064] For the rock mass permeability coefficient K sequence K1, K2, ..., K MThe value of the permeability coefficient K of each rock mass is in the sequence of the permeability coefficient K of the rock mass K1, K2, …, K M The descending numbers in are represented as: P1, P2, ..., P M ;

[0065] Calculate the difference between sequence number Q1 and sequence number P1 to obtain d1;

[0066] Calculate the difference between sequence number Q2 and sequence number P2 to obtain d2;

[0067] And so on

[0068] Calculate the sequence number Q M and serial number P M The difference between M ;

[0069] Step S2.2, using the following formula, obtain the correlation coefficient r between the rock mass permeability analysis index C and the rock mass permeability coefficient K s :

[0070]

[0071] Where: k = 1, 2, ..., M;

[0072] Step S2.3, determine the correlation coefficient r s Is it greater than the threshold ε? If so, select the rock permeability analysis index C.

[0073] In step S2, the method for obtaining the core structure surface density feature FSD is:

[0074] Step S2-1, the drilling footage depth is L; the core structural surface inclination trend density is divided into three inclination sections according to the inclination degree interval, namely: (0, 30], (30, 60], (60, 90];

[0075] Step S2-2, counting the number of structural surfaces in each inclination section, respectively: N 0～30 、N 30～60 and N 60～90 ;

[0076] Step S2-3, according to the rock mass lithology factors currently analyzed, the weights corresponding to the inclination sections are set respectively, namely: W1, W2 and W3;

[0077] Step S2-4, using the following formula to obtain the core structure surface density feature FSD:

[0078]

[0079] Thus, the value of the core structure surface density characteristic FSD is obtained.

[0080] As an example, for metamorphic rocks, the weights are preferably: W1 = 0.1, W2 = 0.3, W3 = 0.6.

[0081] Step S3, constructing multiple training samples, and normalizing each training sample to obtain multiple normalized training samples to form a training sample set;

[0082] Each training sample in the training sample set is represented by s = (X, Y); where X is the rock mass permeability analysis index vector, X = (x1, x2, x3, x4), x1, x2, x3, x4, respectively represent the sample values ​​of rock mass burial depth RD, core quality index RQD, core structure surface density feature FSD and rock mass integrity index RID; Y represents the corresponding value of rock mass permeability coefficient K;

[0083] Step S4, using the training sample set to train the pre-built permeability prediction and analysis model to obtain a trained permeability prediction and analysis model;

[0084] Step S4 is specifically as follows:

[0085] Step S4.1, the constructed permeability prediction and analysis model is a DELM permeability prediction and analysis model, including 1 input layer, N layers of hidden layers cascaded forward and backward, and 1 output layer; wherein the input layer has 4 neurons, each hidden layer has 4 neurons, and the output layer has 4 neurons;

[0086] Step S4.2, randomly generate the weight of each neuron in the input layer through an orthogonal matrix;

[0087] Step S4.3, for any training sample s = (X, Y), X = (x1, x2, x3, x4), Y represents the corresponding value of the rock mass permeability coefficient K, firstly input x1, x2, x3, x4 into the 4 neurons of the input layer respectively, and each neuron of the input layer outputs x through weight calculation respectively. 11 ,x 21 ,x 31 ,x 41 , forming a matrix X1=(x 11 ,x 21 ,x 31 ,x 41 );

[0088] Step S4.4, transform the matrix X1=(x 11 ,x 21 ,x 31 ,x 41 ) is input to the hidden layer of the first layer, and the output matrix of the hidden layer of the first layer is set to X2 = (x 12 ,x22 ,x 32 ,x 42 ) is equal to the input matrix X1, so the weight vector β2 of the hidden layer of the second layer is obtained by the following formula:

[0089]

[0090] β2β2 2 =I

[0091] Where: C is the regularization parameter; I is the identity matrix;

[0092] Step S4.5, transform the matrix X2=(x 12 ,x 22 ,x 32 ,x 42 ) is input to the hidden layer of the second layer, and the output matrix X3 of the hidden layer of the second layer is obtained using the following formula:

[0093]

[0094] β2β2 T =I

[0095] At the same time, determine the weight vector β3 of the hidden layer of the third layer:

[0096] β3=X3Y

[0097] Step S4.6, input the matrix X3 and the weight vector β3 to the hidden layer of the third layer, and use the same method as step S4.5 to obtain the output matrix X4 of the hidden layer of the third layer and the weight vector β4 of the hidden layer of the fourth layer; and so on, until the output matrix X of the hidden layer of the Nth layer is obtained. N+1 and the weight vector β N+1 ;

[0098] Step S4.7, transform the matrix X N+1 and the weight vector β N+1 Input to the output layer, the output layer outputs the final output vector Y′;

[0099] Step S4.8, by comparing the output vector Y′ and the sign value of the rock permeability coefficient K, that is, Y; if both are less than the threshold, then the weight vectors of each layer at this time form the final trained permeability prediction and analysis model; if it is not less than the threshold, then with Y′ and Y being equal as the goal, the least squares method is used to solve, and the weight vectors of each layer after the solution are obtained to form the final trained permeability prediction and analysis model.

[0100] Step S5, for the rock mass that currently needs to be predicted and analyzed for permeability, obtain the measured values ​​of the rock mass burial depth RD, the core quality index RQD, the core structure surface density characteristic FSD and the rock mass integrity index RID that need to be interpolated and calculated, and input them into the trained permeability prediction and analysis model, and the trained permeability prediction and analysis model outputs the corresponding predicted value of the rock mass permeability coefficient K.

[0101] An embodiment is described below:

[0102] In this embodiment, prediction and analysis are performed based on the drilling, water pressure and geophysical exploration test results data completed in the pre-feasibility study and feasibility study stages of a pumped storage project area.

[0103] Step S1, preliminarily determining a plurality of rock mass permeability analysis indices related to the rock mass permeability coefficient K;

[0104] Specifically, according to the drilling test results of the hydropower project and the factors affecting the permeability index, multiple rock permeability analysis indicators are initially set and selected. More specifically, according to the exploration results arranged in the design stage of the hydropower project, combined with professional specifications and industry experience, and based on the lithology factors of the hydropower project, multiple rock permeability analysis indicators are selected.

[0105] Step S2, performing correlation analysis on various rock mass permeability analysis indicators and rock mass permeability coefficient K determined initially, and obtaining four rock mass permeability analysis indicators having correlation with rock mass permeability coefficient K exceeding a threshold, namely: rock mass burial depth RD, core quality index RQD, core structural surface density feature FSD and rock mass integrity index RID;

[0106] In this process, the rock mass burial depth RD of each borehole, the core quality index RQD, the core structure surface density characteristic FSD and the rock mass integrity index RID are selected as the optional parameters for permeability prediction and analysis, and the rock mass permeability coefficient K obtained by the water pressure test is used as the prediction and analysis index.

[0107] Among them, the lithology of the project area in this example is gneiss. The core structural surface dip trend density is divided into three dip sections according to the dip angle: (0, 30], (30, 60], and (60, 90]. Combined with the metamorphic rock lithology factors, the weight of the 0-30° section is 0.1, the weight of the 30-60° section is 0.3, and the weight of the 60-90° section is 0.6. The core structural surface density characteristic statistical formula is as follows:

[0108]

[0109] Where N 0～30 represents the number of structural surfaces in the (0, 30] inclination section, W1 = 0.1; N 30～60 represents the number of structural surfaces in the (30, 60] inclination section, W2 = 0.3; N60～90 Represents the number of structural surfaces in the (60, 90] inclination section, W3=0.6; L is the footage depth.

[0110] The process indicators are as follows:

[0111]

[0112] Step S2, performing correlation analysis on various rock mass permeability analysis indicators and rock mass permeability coefficient K determined initially, and obtaining four rock mass permeability analysis indicators having correlation with rock mass permeability coefficient K exceeding a threshold, namely: rock mass burial depth RD, core quality index RQD, core structural surface density feature FSD and rock mass integrity index RID;

[0113] First, according to the influencing factors of permeability prediction and analysis, the linear normalization method is used to preprocess the rock depth RD, core quality index RQD, core structure surface density feature FSD and rock integrity index RID parameter values. In this example, the exploration results of the pre-feasibility study to feasibility study stage have permeability prediction and analysis indicators of 51 boreholes and 531 groups of prediction and analysis indicators.

[0114] According to the correlation analysis between the permeability prediction and analysis indicators, the industry experience can be further improved based on the predicted value of the rock mass permeability coefficient K and the correlation degree of the superimposed permeability indicators, and the recommended values ​​of various rock mass permeability can be improved. This example uses the Spearman correlation coefficient method to evaluate the non-parametric statistical indicators of the dependence between the rock mass permeability coefficient K and the four rock mass permeability analysis indicator variables. Its value has nothing to do with the specific value of the variable, but is related to the size and order of the variables. Moreover, this method does not need to assume that the variables follow a specific distribution law, and has strong robustness to outliers in the data, so its application range is wider.

[0115] The correlation analysis method of the above step S2 is used, and the results are shown in the following table:

[0116]

[0117] It can be seen that the correlation coefficients of rock mass burial depth RD, core quality index RQD, rock mass integrity index RID and rock mass permeability coefficient K parameter are all greater than 0.6, showing a strong negative correlation, indicating that with the increase of burial depth RD and RQD integrity in the project area, the rock mass permeability coefficient K decreases accordingly, while there is a certain moderate positive correlation between the core structural surface density characteristics, indicating that the steep inclination has a certain influence on the permeability of the rock mass in the project area. For the parts that have not been subjected to water pressure test, it is necessary to make appropriate permeability recommendation values ​​based on the integrity of the core.

[0118] Of course, in practical applications, other correlation coefficient analysis methods can also be used, including Pearson method, Spearman method and Kendall rank correlation method.

[0119] Step S3, constructing multiple training samples, and normalizing each training sample to obtain multiple normalized training samples to form a training sample set;

[0120] Step S4, using the training sample set to train the pre-built permeability prediction and analysis model to obtain a trained permeability prediction and analysis model;

[0121] This process selects, defines and organizes the rock permeability analysis indicators and rock permeability coefficient K of the existing exploration results. In order to solve the problem of scarce and scattered exploration data, this example uses the ISSA-optimized DELM deep learning algorithm to construct a permeability prediction and analysis model.

[0122] DELM is composed of multiple ELM-AE basic units, performs layered unsupervised training and does not require reverse fine-tuning, which can minimize reconstruction errors. The input layer weights of the DELM algorithm used in this example are randomly generated by an orthogonal matrix. This orthogonal design can remove noise outside the features, make the features uniform, and more linearly independent, thereby enhancing the generalization ability of the system. In order to further reduce the volatility of the prediction results, optimize and improve the accuracy of the prediction results.

[0123] The ISSA algorithm is further used to optimize the convergence accuracy and speed of the DELM algorithm, and a rock permeability prediction and analysis model based on the deep learning algorithm is constructed to perform rock permeability prediction and analysis. The specific process of the ISSA-DELM optimization algorithm is shown in Figure 2 shown.

[0124] Specifically, this example is a validation test model, using 430 sets of prediction analysis indicators as training data, and the remaining 101 sets of data as prediction verification data. Using the constructed ISSA-DELM rock permeability prediction and analysis model, it was basically converged after 30 iterations, and the fitting degree between the predicted value and the actual value of the ISSA-DELM model was R 2 The predicted value reaches 0.83, and the permeability index of the standard conditions is basically achieved. It has a certain predictive effect on the permeability of the rock mass. Figure 3 , Figure 4 and Figure 5 As shown, respectively, are: the relationship between the number of iterations and the convergence curve; the relationship between the true value and the predicted value when the training set is used for training at different numbers of iterations; and the relationship between the true value and the predicted value when the test set is used for training at different numbers of iterations. It can be seen from the results that this example model can predict the permeability of rock mass without water pressure test.

[0125] Step S5, for the rock mass that currently needs to be predicted and analyzed for permeability, obtain the measured values ​​of the rock mass burial depth RD, the core quality index RQD, the core structure surface density characteristic FSD and the rock mass integrity index RID that need to be interpolated and calculated, and input them into the trained permeability prediction and analysis model, and the trained permeability prediction and analysis model outputs the corresponding predicted value of the rock mass permeability coefficient K.

[0126] Specifically, according to the constructed deep learning algorithm permeability index prediction model, the data that have not been subjected to water pressure test and need permeability analysis are used as permeability prediction parameter values ​​to predict the corresponding rock permeability index, and the sensitivity of the rock permeability analysis index and the rock permeability coefficient K is analyzed, so as to make reasonable recommended parameters based on parameter values, predicted values ​​and industry experience, and improve the reference value of hydropower project design.

[0127] The second embodiment is described below:

[0128] This embodiment discloses a method for predicting and analyzing the permeability coefficient of a hydropower project rock mass, including the following steps:

[0129] A. Define permeability prediction analysis indicators to set and select permeability prediction analysis indicators based on the results of hydropower engineering drilling tests and permeability index influencing factors.

[0130] The permeability prediction analysis index A is defined as the exploration results arranged in the design stage of the hydropower project, combined with professional specifications and industry experience, and based on the lithological factors of the hydropower project, the rock mass burial depth, core RQD, core structural surface density characteristics and rock mass integrity index RID are selected as permeability prediction analysis parameters, and the permeability coefficient value obtained by the water pressure test is used as the prediction analysis index.

[0131] The core structural surface density characteristics described in process A are based on the core drilling results, and the core structural surface data of the existing water pressure test section and the planned prediction analysis section are recorded. The structural surface data is combined with the inclination trend density to divide the sections autonomously according to the inclination. Then, according to the core lithology factors and the rock mass integrity factors, the inclination weight ratio of each section of the structural surface is customized, and the density value of the number of development lines of each fracture structural surface within the corresponding footage depth is delineated and counted. The formula is as follows:

[0132]

[0133] Where FSD represents the characteristic value of core structure surface density; N i represents the number of structural surfaces in the i-th inclination section; W i is the weight ratio of the i-th inclination segment, ∑W i =1; L is the penetration depth.

[0134] Generally speaking, the permeability of rock mass is correlated with factors such as lithology and fracture connectivity. For example, sedimentary rocks are mostly affected by bedding fractures, and gently dipping fractures have a greater impact on permeability. Metamorphic rocks are mostly affected by structural fractures, and steeply dipping fractures have a greater impact on permeability.

[0135] B. Arrange the permeability prediction analysis parameters to normalize and sort out the permeability prediction analysis parameter values ​​according to the set parameter indicators.

[0136] The permeability prediction analysis parameter B is organized as the influencing factors of the permeability prediction analysis defined according to process A. The data is processed by normalization to ensure that each factor is equivalent in the subsequent prediction analysis model and eliminate the deviation caused by different dimensions and orders of magnitude.

[0137] The data normalization processing methods described in process B include linear normalization, standard deviation normalization, nonlinear normalization and decimal scaling normalization. Each method helps to convert data to a unified dimension and is a key step in subsequent deep learning data preprocessing.

[0138] C. Establish a permeability index prediction model to construct a predictive permeability index model based on the deep learning algorithm and the permeability prediction analysis parameter values.

[0139] Permeability prediction and analysis model C is established. According to processes A and B, the parameters and index values ​​of permeability prediction and analysis influencing factors of existing exploration results are selected, defined and sorted. The normalized data of influencing factors are used as sample parameters, and the permeability index is used as the sample target. The deep learning algorithm is independently selected, and the sample parameters and sample target data are gradually trained to construct a rock permeability index prediction model based on the deep learning algorithm, so as to carry out rock permeability prediction and analysis.

[0140] The deep learning algorithms described in process C mainly include multi-layer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM), deep extreme learning machine (DELM) and other algorithms, as well as further improved and optimized versions based on these basic algorithms.

[0141] D. Predict and analyze rock permeability indexes, which is used to predict and analyze rock permeability by inputting the permeability prediction parameter values ​​before water pressure test based on the established predictive permeability index model.

[0142] Prediction and analysis of rock permeability index D Based on the deep learning algorithm permeability index prediction model constructed by process C, the data that has not been subjected to water pressure test and needs permeability analysis is used as the permeability prediction parameter value to predict the corresponding rock permeability index. The sensitivity of the permeability prediction parameters to the rock permeability is analyzed to combine the parameter values, prediction values, and industry experience to make reasonable parameter recommendations and improve the reference value of hydropower engineering design.

[0143] The prediction corresponding to the rock permeability index described in process D is a rock permeability index model constructed based on existing results. It trains the distribution characteristics and laws of the permeability performance of various underground rock masses, and predicts the underlying rock permeability index for the parts with incomplete results of subsequent water pressure test.

[0144] The present invention provides a method for predicting and analyzing the rock permeability of hydropower projects. For pumped storage and water conservancy and hydropower projects with a large engineering area, the method can select influencing factor parameters suitable for rock permeability prediction and analysis based on completed drilling and test results data in combination with lithological conditions, and construct a rock permeability prediction and analysis model based on a deep learning algorithm in combination with the permeability index of the water pressure test of the corresponding factor parameters. The method can predict the permeability of the rock mass in areas where the water pressure test results are incomplete, and can also analyze the interactive relationship between the various factors of the rock mass in the engineering area and the permeability, which can provide experience to improve judgment and improve design quality and efficiency.

[0145] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be considered as the scope of protection of the present invention.

Claims

1. A method for predicting and analyzing rock mass permeability in hydropower engineering, characterized in that: The following steps are involved: Step S1, preliminarily determining a plurality of rock mass permeability analysis indices related to the rock mass permeability coefficient K; Step S2, performing correlation analysis on various rock mass permeability analysis indicators and rock mass permeability coefficient K determined initially, and obtaining four rock mass permeability analysis indicators having correlation with rock mass permeability coefficient K exceeding a threshold, namely: rock mass burial depth RD, core quality index RQD, core structural surface density feature FSD and rock mass integrity index RID; Step S3, constructing multiple training samples, and normalizing each training sample to obtain multiple normalized training samples to form a training sample set; Each training sample in the training sample set is represented by s = (X, Y); where X is the rock mass permeability analysis index vector, X = (x1, x2, x3, x4), x1, x2, x3, x4, respectively represent the sample values ​​of rock mass burial depth RD, core quality index RQD, core structure surface density feature FSD and rock mass integrity index RID; Y represents the corresponding value of rock mass permeability coefficient K; Step S4, using the training sample set to train the pre-built permeability prediction and analysis model to obtain a trained permeability prediction and analysis model; Step S5, for the rock mass that currently needs to be predicted and analyzed for permeability, obtain the measured values ​​of the rock mass burial depth RD, the core quality index RQD, the core structure surface density characteristic FSD and the rock mass integrity index RID that need to be interpolated and calculated, and input them into the trained permeability prediction and analysis model, and the trained permeability prediction and analysis model outputs the corresponding predicted value of the rock mass permeability coefficient K.

2. A method for predicting and analyzing rock mass permeability of a hydropower project according to claim 1, characterized in that: In step S2, correlation analysis is performed on various rock mass permeability analysis indicators and rock mass permeability coefficient K that are initially determined, specifically: Step S2.1, denote any rock mass permeability analysis index as C, obtain the measured values ​​of M rock mass permeability analysis indexes C, expressed as: C1, C2, ..., C M ; Obtain the rock mass permeability coefficient K corresponding to the measured value of each rock mass permeability analysis index C, which is expressed as: K1, K2, …, K M ; For the measured value sequence of rock permeability analysis index C, C1, C2, ..., C M The measured values ​​of each rock mass permeability analysis index C are expressed in descending order in the measured value sequence of the rock mass permeability analysis index C: Q1, Q2, …, Q M ; For the rock mass permeability coefficient K sequence K1, K2, ..., K M The value of the permeability coefficient K of each rock mass is in the sequence of the permeability coefficient K of the rock mass K1, K2, …, K M The descending numbers in are represented as: P1, P2, ..., P M ; Calculate the difference between sequence number Q1 and sequence number P1 to obtain d1; Calculate the difference between sequence number Q2 and sequence number P2 to obtain d2; And so on Calculate the sequence number Q M and serial number P M The difference between M ; Step S2.2, using the following formula, obtain the correlation coefficient r between the rock mass permeability analysis index C and the rock mass permeability coefficient K s : Where: k = 1, 2, ..., M; Step S2.3, determine the correlation coefficient r s Is it greater than the threshold ε? If so, select the rock permeability analysis index C.

3. A method for predicting and analyzing rock mass permeability of a hydropower project according to claim 1, characterized in that: In step S2, the method for obtaining the core structure surface density feature FSD is: Step S2-1, the drilling footage depth is L; the core structural surface inclination trend density is divided into three inclination sections according to the inclination degree interval, namely: (0, 30], (30, 60], (60, 90]; Step S2-2, counting the number of structural surfaces in each inclination section, respectively: N 0～30 、N 30～60 and N 60～90 ; Step S2-3, according to the rock mass lithology factors currently analyzed, the weights corresponding to the inclination sections are set respectively, namely: W1, W2 and W3; Step S2-4, using the following formula, obtain the core structure surface density feature FSD: Thus, the value of the core structure surface density characteristic FSD is obtained.

4. A method for predicting and analyzing rock mass permeability of a hydropower project according to claim 3, characterized in that: For metamorphic rocks, the weights are: W1=0.1, W2=0.3, W3=0.

6.

5. A method for predicting and analyzing rock mass permeability of a hydropower project according to claim 1, characterized in that: Step S4 is specifically as follows: Step S4.1, the constructed permeability prediction and analysis model is a DELM permeability prediction and analysis model, including 1 input layer, N layers of hidden layers cascaded forward and backward, and 1 output layer; wherein the input layer has 4 neurons, each hidden layer has 4 neurons, and the output layer has 4 neurons; Step S4.2, randomly generate the weight of each neuron in the input layer through an orthogonal matrix; Step S4.3, for any training sample s = (X, Y), X = (x1, x2, x3, x4), Y represents the corresponding value of the rock mass permeability coefficient K, firstly input x1, x2, x3, x4 into the 4 neurons of the input layer respectively, and each neuron of the input layer outputs x through weight calculation respectively. 11 ,x 21 ,x 31 ,x 41 , forming a matrix X1=(x 11 ,x 21 ,x 31 ,x 41 ); Step S4.4, transform the matrix X1=(x 11 ,x 21 ,x 31 ,x 41 ) is input to the hidden layer of the first layer, and the output matrix of the hidden layer of the first layer is set to X2 = (x 12 ,x 22 ,x 32 ,x 42 ) is equal to the input matrix X1, so the weight vector β2 of the hidden layer of the second layer is obtained by the following formula: β2β2 t ＝I Where: C is the regularization parameter; I is the identity matrix; Step S4.5, transform the matrix X2=(x 12 ,x 22 ,x 32 ,x 42 ) is input to the hidden layer of the second layer, and the output matrix X3 of the hidden layer of the second layer is obtained using the following formula: β2β2 T ＝I At the same time, determine the weight vector β3 of the hidden layer of the third layer: β3=X3Y Step S4.6, input the matrix X3 and the weight vector β3 to the hidden layer of the third layer, and use the same method as step S4.5 to obtain the output matrix X4 of the hidden layer of the third layer and the weight vector β4 of the hidden layer of the fourth layer; and so on, until the output matrix X of the hidden layer of the Nth layer is obtained. N+1 and the weight vector β N+1 ; Step S4.7, transform the matrix X N+1 and the weight vector β N+1 Input to the output layer, the output layer outputs the final output vector Y′; Step S4.8, by comparing the output vector Y′ and the sign value of the rock permeability coefficient K, that is, Y; if both are less than the threshold, then the weight vectors of each layer at this time form the final trained permeability prediction and analysis model; if it is not less than the threshold, then with Y′ and Y being equal as the goal, the least squares method is used to solve, and the weight vectors of each layer after the solution are obtained to form the final trained permeability prediction and analysis model.

Images