A method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters or rock strata

Abstract

The present invention discloses a method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters or rock strata. According to the method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters of the present application, the following steps are included: S100. Divide the river valley into several sub-regions, assign a first number, and obtain a first coordinate result; S200. Conduct multiple rock mass samplings to obtain rock mass samples, and the rock mass mechanical parameter of each rock mass sample is the first parameter; S300. Compose each group of first parameters into a first parameter set; S400. Select several sub-regions at the position of any valley width observation section in the river valley; S500A. Read and establish a first vector set for the several sub-regions selected in S400; S600. Obtain the total head distribution field in the river valley; S700A. Input the first vector set and the local head value into a pre-trained first prediction model to output a second coordinate result. By using multiple models to predict the valley width deformation of the dam and obtaining the prediction result based on factors such as rock mass mechanical parameters and coordinate positions, the result is more reliable.

Description

Technical Field

[0001] The present invention belongs to the field of predicting valley width deformation based on computer technology, and particularly relates to a method for predicting valley width deformation of a water storage dam based on rock mass mechanical parameters or rock strata. Background Art

[0002] Valley width deformation refers to the horizontal deformation (i.e., horizontal displacement) phenomenon of the reservoir bank (here, the reservoir bank refers to the river valley slope) in a large area upstream and downstream of the dam caused by reservoir impoundment under specific geological conditions. It is the manifestation of regional deformation in the horizontal direction and is equal to the change in the shortest horizontal distance between the same elevation points on the valley slopes on the left and right banks of the reservoir (river valley). Usually, an observer will select a valley width observation section to measure the valley width deformation.

[0003] Valley width deformation is different from the common valley slope erosion and other phenomena that cause slope collapse, resulting in sediment or rock and soil deposition at the bottom of the valley, causing valley deformation. It is mainly determined by geological conditions and reservoir impoundment, and the internal valley width structure is changed due to stress.

[0004] Currently, for valley width deformation, direct measurement is usually adopted to measure the valley width at the measurement moment, and then it is judged whether more severe deformation will occur based on experience or calculation. The prediction results obtained by this method are not accurate enough and have insufficient reference value. If the estimation of valley width deformation is misjudged, a series of serious consequences such as dam cracking may occur.

[0005] Therefore, a method that can assist observers in predicting valley width deformation at future moments is needed. Summary of the Invention

[0006] Aiming at the above problems, the purpose of the present invention is to disclose a method for predicting valley width deformation of a water storage dam based on rock mass mechanical parameters.

[0007] Another purpose of the present invention is to disclose a method for predicting valley width deformation of a water storage dam based on rock strata.

[0008] A method for predicting the valley width deformation of a water storage dam based on the rock mass mechanical parameters of the present invention. The water storage dam is built on any cross-section of the river valley, and includes the following steps: S100: Divide the river valley into several sub-regions, assign a first number to each sub-region, and obtain the coordinates of each sub-region at the initial moment as the first coordinate result; S200: Conduct multiple rock mass samplings on each sub-region to obtain a set of rock mass samples, obtain the rock mass mechanical parameters of each rock mass sample as the first parameter, and obtain the coordinates of each rock mass sample as the sub-coordinates; S300: Each set of rock mass samples collected from each sub-region corresponds to a set of the first parameters, and form a first parameter set with each set of the first parameters; S400: Select several sub-regions at the position of any valley width observation section in the river valley, and read several first parameters corresponding to the selected sub-regions; S500A: Read the first coordinate results corresponding to the several sub-regions selected in S400, and establish a first vector set according to the first number, where the first vector set includes several first sub-vectors, and each first sub-vector includes: the first number corresponding to the sub-region; the first parameter and sub-coordinates corresponding to a rock mass sample; S600: Obtain the total head distribution field in the river valley, and retrieve the total head at the coordinates of each sub-region as the local head value according to the total head distribution field; S700A: Input the first vector set and the local head value into a pre-trained first prediction model; the first prediction model outputs the coordinates of each sub-region at the prediction moment as the second coordinate result, and the second coordinate result includes multiple new sub-coordinates corresponding to the coordinates of each rock mass sample at the prediction moment.

[0009] Optionally, S200 includes: S210: Conduct multiple rock mass samplings on each sub-region in sequence along the depth direction of the valley slope of the river valley, and assign a second number to each rock mass sample in sequence according to the depth where each rock mass sample is located; S220: Obtain the rock mass mechanical parameters of each rock mass sample as the first parameter.

[0010] Further, store the first vector set obtained in S500A, and read the first vector set in the stored data when executing S600 - S700.

[0011] Further, it also includes S710 performed after S700A: S710: Obtain the second coordinate result, and select the second coordinate result corresponding to the valley width observation section; obtain the valley width deformation result by comparing the vector difference between the first coordinate result and the second coordinate result.

[0012] Further, the S710 includes: S711, matching the first coordinate result and the second coordinate result according to the first number, and matching the sub-coordinates with the new sub-coordinates; S712, obtaining the vector difference between each pair of the sub-coordinates and the new sub-coordinates as a single vector; S713, reading the rock formation division in each of the sub-regions and its position in the total head distribution field, and assigning a first weight coefficient to each of the sub-regions corresponding to several of the single vectors; S714, performing vector summation on each of the single vectors to obtain a first change amount; S715, assigning the first weight coefficient to each of the first change amounts, and performing mathematical synthesis on each of the first change amounts after weighting to obtain the overall displacement result of the valley amplitude observation section; S716, obtaining the valley amplitude deformation result at each valley amplitude observation section according to the overall displacement result.

[0013] Optionally, it further includes S800 performed after S710: S800, updating the first coordinate result, and completing the update after overwriting the first coordinate result with the second coordinate result; and re-performing S100 after the update is completed.

[0014] Optionally, it further includes S610 performed after S600; S610, inputting the first vector set and the local head value into a pre-trained third prediction model; the third prediction model outputs a corrected value of the permeability coefficient, and re-performing S310 according to the corrected permeability coefficient.

[0015] Optionally, it further includes S310 performed after S300:

[0016] S310, reading the second number, and assigning a permeability coefficient value to each of the rock mass samples according to the arrangement order of the second number; dividing the sub-regions according to the permeability coefficient; the rock formation division includes permeable rock formations and general rock formations divided along the depth direction of the valley slope of the river valley.

[0017] Further, in S310: the permeable rock formation is a rock mass with a high permeability coefficient value, and the permeable rock formation includes: fractured rock formations and broken rock formations; the general rock formation is a rock mass with a low permeability coefficient value, and the general rock formation includes: granite and mudstone.

[0018] A method for predicting the valley width deformation of a water storage dam based on rock strata according to an embodiment of the present invention. For the method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters described in the embodiment of the present invention, replace S500A with S500B; S500B, read the first coordinate results corresponding to several selected sub-regions in S400, and establish a second vector set according to the first numbers, where the second vector set includes several second sub-vectors, and each second sub-vector includes: the first number corresponding to the sub-region; the first parameter, sub-coordinates, and the result of rock stratum division corresponding to a rock mass sample; replace S700 with S700B; S700B, input the second vector set and the local water head value into a pre-trained second prediction model; the second prediction model outputs the coordinates of each sub-region at the prediction time as the second coordinate results, and the second coordinate results include new sub-coordinates corresponding to the coordinates of each rock mass sample at the prediction time.

[0019] The beneficial effects of the present invention are as follows:

[0020] By comprehensively using multiple models to predict the valley width deformation of the dam and obtaining the prediction results based on factors such as rock mass mechanical parameters and coordinate positions, the final prediction results are more reliable. The model parameters involve multiple core parameters, enabling the present invention to cover different types of data and various factors that may affect the valley width deformation, so as to be applicable to the prediction of the valley width deformation of dams under different conditions and having strong generality.

[0021] Other features and advantages of the present invention will be described in the following description of the specification, and in part, will be obvious from the description of the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures pointed out in the specification, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 Shows an exemplary valley width observation section structure according to an embodiment of the present invention;

[0024] Figure 2 Shows a schematic diagram for assisting in understanding the first vector set according to an embodiment of the present invention;

[0025] Figure 3Shows a flowchart of a method for predicting the valley width deformation of a water storage dam based on rock mass mechanics according to an embodiment of the present invention;

[0026] Figure 4 Shows a flowchart of a method for predicting the valley width deformation of a water storage dam based on rock strata according to an embodiment of the present invention.

[0027] In the accompanying drawings:

[0028] 1 - Sub - region, 2 - River valley, 3 - Valley slope, 4 - Water level, 5 - Reservoir bottom, 6 - Reservoir edge; Detailed implementation manners

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0030] Professional terms such as "river valley", "rock mass sampling", "valley width observation section", and "total head distribution field" described in the embodiments of the present application are known to those of ordinary skill in the art, so they will not be elaborated in the embodiments of the present application.

[0031] Next, combine Figures 1-4 Understand the first - aspect embodiment and the second - aspect embodiment disclosed in this embodiment.

[0032] First - aspect embodiment;

[0033] A method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters, where the water storage dam is built on any cross - section of the river valley 2, and includes the following steps:

[0034] S100. Divide the river valley 2 into several sub - regions 1, assign a first number to each sub - region 1, obtain the coordinates of each sub - region 1 at the initial moment as the first coordinate result, and combine Figure 1 In a certain valley width observation section as shown, the area between the left and right reservoir edges 6 of the river valley 2 and a certain distance extended to both sides is the reservoir bottom 5. The river valley 2 can be divided into several sub - regions 1 along the direction of the valley slope 3. Of course, several sub - regions 1 are also divided in other observation sections; the purpose is to predict the deformation of different river valley 2 regions, and correspondingly, obtaining the first coordinate result and the first number can be used to locate different sub - regions 1.

[0035] S200. Conduct multiple rock mass samplings for each of the sub-regions 1 to obtain a set of rock mass samples, acquire the rock mass mechanical parameters of each rock mass sample as the first parameters, and acquire the coordinates of each rock mass sample as sub-coordinates. It can be understood that since the valley width deformation mainly depends on the mechanical parameters of the rock mass samples and the water head distribution at their locations, multiple rock mass samplings need to be conducted for each of the sub-regions 1 to obtain the corresponding rock mass mechanical parameters.

[0036] S300. Each set of the rock mass samples collected from each sub-region 1 corresponds to a set of the first parameters. Combine each set of the first parameters to form a first parameter set. In this embodiment, the first parameters include, but are not limited to, elastic modulus and compressive strength. Those skilled in the art can select the specific parameters in combination with the existing common knowledge.

[0037] S400. Select several of the sub-regions 1 at the location of any valley width observation section in the river valley 2. For example, Figure 1 as shown in the valley width observation section, read the several first parameters corresponding to the selected several sub-regions 1.

[0038] It can be understood that the valley width deformation is affected by various factors. The main influencing factors include rock mass mechanical parameters and water head distribution. By measuring these parameters at the actual section location, the direct data of the rock mass at a specific location can be obtained. In this example, the river valley 2 is divided into several sub-regions 1, and the rock mass mechanical parameters are obtained for each sub-region 1 in order to capture the changes in the valley width at different positions. In the foregoing example, in step S400, any valley width observation section is selected and the first parameter set of the relevant sub-regions 1 is read. Then each observation section can be regarded as a representative region to obtain the rock mass response at this specific section.

[0039] And when there is valley width deformation in the water storage dam, the deformation phenomenon that the mountain near the dam shows towards the riverbed direction is called valley width deformation. Therefore, by selecting one or several specific valley width observation sections for analysis of the valley width deformation, the dam body changes at one or more valley width observation sections can be obtained to accurately obtain the result of the valley width deformation.

[0040] S500A. Read the first coordinate results corresponding to the several sub-regions 1 selected in S400. Among them, the first sub-coordinate results include several sub-coordinates corresponding to each rock mass sample. Establish a first vector set for each sub-region 1 according to the first number. The first vector set can be understood in combination with Figure 2 Herein, the first vector set includes several first sub-vectors, and each first sub-vector includes:

[0041] the first number corresponding to the sub-region 1; the first parameter and sub-coordinates corresponding to a rock mass sample.

[0042] In a specific example, the first sub-vector V i is:.

[0043] V ia = (i, P ia1 , P ia2 , …, P ian , X ia1 , Y ia1 , Y ia1 );

[0044] wherein, i is the first number corresponding to the first sub-region 1, and a is the a-th rock mass sample corresponding to the first sub-region 1; (P ia1 , P ia2 , …, P ian ) are the respective mechanical parameters in the first parameter set corresponding to the a-th rock mass sample in the first sub-region 1, with a total of n rock mass mechanical parameters; (X ia1 , Y ia1 , Y ia1 ) are the sub-coordinates corresponding to the a-th rock mass sample in the first sub-region 1.

[0045] Similarly, the first vector set corresponding to the same first sub-region 1 further includes:

[0046] V ib = (i, P ib1 , P ib2 , …, P ibn , X ib1 , Y ib1 , Y ib1 );

[0047] wherein, b represents the b-th rock mass sample corresponding to the first sub-region 1, and so on.

[0048] The first vector set is:

[0049] V i = (V ia， V ib，… );

[0050] In an optional example, the first vector set obtained in S500A is stored, and the first vector set in the stored data is read when executing S600 - S700. It is worth mentioning that in the conventional means of obtaining rock mass mechanical parameters, sampling and analysis of the rock mass are required, and this method is generally carried out only once or regularly. Therefore, in this example, when performing a rock mass sampling task, the parameters obtained from the rock mass sampling are stored, that is, the first vector obtained in S500A is stored after being obtained, and is retrieved during subsequent multiple prediction processes. And each time a prediction is made, the total head distribution field continuously changes and needs to be measured in real time.

[0051] S600. Obtain the total head distribution field in the river valley 2, and retrieve the total head at the coordinates of each sub-region 1 as the local head value according to the total head distribution field.

[0052] In this example, to obtain the local head value of the sub-region 1, the first coordinate result and the first number obtained in steps S100 - S500A can be used to locate the corresponding coordinates of different sub-regions 1.

[0053] When making a prediction, a data set obtained by measuring inside the river valley 2 is used. Specifically, hydrogeological methods and tools can be used to measure the water pressure at each point in the river valley 2, usually by installing water pressure sensors or using other hydrographic measurement techniques. The specific process of obtaining the total head distribution field is well-known to those skilled in the art and will not be elaborated here.

[0054] Then the local head value is extracted. Specifically, the head value located at the coordinates of a specific sub-region 1 is extracted and calculated. In this example, the coordinates of each sub-region 1 can be corresponded to the total head distribution field, so as to obtain the local head value of each specific sub-region 1. By simulating the total head distribution field data in the form of a graph or a table, the local head value can be obtained by reading the total head value corresponding to the coordinates where the sub-region 1 is located, or directly collecting the local head value of the corresponding sub-region 1.

[0055] S700A. Input the first vector set and the local head value into a pre-trained first prediction model; the first prediction model outputs the coordinates of each sub-region 1 at the prediction moment as the second coordinate result, and the second coordinate result includes multiple new sub-coordinates corresponding to the coordinates of each rock mass sample at the prediction moment.

[0056] The new sub - coordinates are the coordinates after valley amplitude deformation predicted by the first prediction model. In this example, since valley amplitude deformation is affected by multiple factors and deals with scenarios with rich and complex geological data, the first model selects the gradient boosting machine model. The gradient boosting model is a supervised learning model and has a regression function. Then the first model can well map the relationship between input parameters and coordinate changes, is not easily affected by outliers, and does not require as much data as neural networks to avoid overfitting.

[0057] Specifically, various data corresponding to other past water storage dams that have generated valley amplitude deformation are selected, and historical data is sorted according to the obtained historical data: the mechanical parameters and corresponding coordinates of each rock mass sample, as well as the water head distribution data. Then historical data is used to train the model to learn the mapping relationship between input parameters and coordinate changes.

[0058] In one example, before inputting into the model, feature processing is performed on the first vector set and local water head values, specifically including scaling, normalization, or encoding. Specifically, the mechanical parameters of the rock mass need to be normalized to have the same scale.

[0059] When training the model, the gradient boosting model used is G(x), where x is the feature vector containing the mechanical parameters of the rock mass and the local water head value. The model training process can be expressed as:

[0060]

[0061] where, J min (G) is the total loss function to be minimized, L is the loss function that calculates the difference between the model prediction and the actual observation, y i is the true coordinate corresponding to the i - th rock mass sample in the training parameters. It can be understood that the aforementioned true coordinate is the selected true coordinate in the parameters for training the model, rather than the sub - coordinates in the previous or subsequent examples; N is the number of training samples, and Ω is the regularization term, which is used to penalize model complexity to prevent overfitting.

[0062] To evaluate the generalization ability of the model, a cross - validation method is adopted. The data is divided into K parts, and K - 1 parts are used for training in turn, and the remaining part is used for validation. The model evaluation can select the best - performing model parameters as the final model according to the results of cross - validation. The evaluation indicators include the coefficient of determination R2, mean square error (MSE), or root mean square error (RMSE). The specific process is not elaborated here.

[0063] The finally trained model G is used to predict valley amplitude deformation under future or new conditions. That is, new mechanical parameters of the rock mass and local water head values are input to predict new coordinate points:

[0064]

[0065] Among them, is the new sub-coordinate output by the prediction, V new is the first vector set at the current moment (the moment when the prediction is made). It can be understood that V new As the first vector set at the prediction moment, it can be input into the subsequent model update continuously as an unobservable parameter without being observed. The user only needs to observe that is, the new sub-coordinate to obtain the corresponding prediction result of the valley amplitude change. For specific content, refer to the subsequent examples.

[0066] Finally, evaluate the performance of the model on an independent validation set and make necessary adjustments to obtain the trained first prediction model.

[0067] According to the foregoing embodiments, in an optional example, the S200 includes:

[0068] S210. Perform multiple rock mass sample collections on each of the sub-regions 1 along the depth direction of the slope body of the valley slope 3 of the river valley 2. In one example, reference can be made to Figure 1 for understanding. The direction of the valley slope 3 of the rock river valley 2 is Figure 1 the arrow direction shown in. Assign a second number to each of the rock mass samples in sequence according to the depth where each rock mass sample is located; it can be understood that another factor affecting the valley amplitude deformation lies in the rock stratum of the river valley 2.

[0069] S220. Obtain the rock mass mechanical parameters of each of the rock mass samples as the first parameter.

[0070] It should be understood that the rock stratum division also has an impact on the valley amplitude deformation. Therefore, in order to improve the accuracy of the valley amplitude deformation prediction, the rock stratum division should be considered. The multiple rock mass sample collections performed on the depth direction of the slope body of the valley slope 3 of the river valley 2 in step S210 can be understood by referring to Figure 1 for understanding. In the embodiments of the present application, according to the first parameter, the pre-stored permeability coefficient values are read. The specific values corresponding to the specific values can be known to those skilled in the relevant art according to the existing public content and will not be elaborated here.

[0071] In a further example, the rock stratum is divided in S310, and S310 is performed after S300.

[0072] S310. Read the second number and assign a permeability coefficient value to each of the rock mass samples according to the arrangement order of the second number. It is not difficult to understand that according to the arrangement order of the second number, the rock masses of the sub-region 1 are actually assigned permeability coefficients in sequence according to the sampling depth of the corresponding sub-region 1.

[0073] Divide the rock formations in the sub-region 1 according to the permeability coefficient. As described above, after assigning the permeability coefficient according to the depth order indicated by the second numbering, the rock formations can be divided according to the permeability coefficients at different depths.

[0074] In a further example, the rock formation division includes permeable rock formations and general rock formations divided along the depth direction of the slope body of the valley slope 3 of the valley 2.

[0075] According to the foregoing embodiment, after obtaining a number of new sub-coordinates, in a further embodiment, after S700A, perform S710:

[0076] S710. Obtain the second coordinate result, and select the second coordinate result corresponding to the valley width observation cross-section; obtain the valley width deformation result by comparing the vector difference between the first coordinate result and the second coordinate result.

[0077] Specifically, the S710 includes:

[0078] S711. Match the first coordinate result and the second coordinate result according to the first numbering, and match the sub-coordinates with the new sub-coordinates; it can be understood that each sub-region 1 corresponds to a set of sub-coordinates and new sub-coordinates, and the position change of the sub-region 1 can be obtained by comparing the new sub-coordinates with the sub-coordinates.

[0079] Continue to refer to Figure 1 Understand S712.

[0080] S712. Obtain the vector difference between each pair of sub-coordinates and new sub-coordinates as a single vector;

[0081] S713. Read the rock formation division in each sub-region 1 and its position in the total head distribution field, and assign a first weight coefficient to several of the single vectors corresponding to each sub-region 1;

[0082] S714. Perform vector summation on each of the single vectors to obtain a first change amount;

[0083] S715. Assign the first weight coefficient to each of the first change amounts, and perform mathematical synthesis on each of the first change amounts after weighting to obtain the overall displacement result of the valley width observation cross-section;

[0084] S716. Obtain the valley width deformation result at each valley width observation cross-section according to the overall displacement result.

[0085] Exemplarily, in a specific scenario, take a sub-region 1 as an example:

[0086] First, perform the coordinate matching for sub-region 1 of S711 to obtain two corresponding sub-coordinates:

[0087] The sub-coordinates at the initial moment are:

[0088] (X1, Y1, Z1);

[0089] The sub-coordinates at the predicted moment are:

[0090] (X 1new , Y new , Z 1new );

[0091] Then, perform the vector difference calculation of S712. For each rock mass sample i in sub-region 1j, calculate the difference as:

[0092] Δr i，j =(X 1new，ij - X 1,ij , Y 1new，ij - Y 1，ij , Z 1new，ij - Z 1，ij );

[0093] Then, perform the weight coefficient assignment of S713. Each individual vector r ij is assigned a weight coefficient w ij according to its rock layer type and position. Subsequently, perform S-714, and sum up all the individual vectors to obtain the first change amount ΔR j :

[0094]

[0095] Subsequently, perform S715 to weight and synthesize the change amounts of all regions to obtain the overall displacement ΔR of the valley amplitude observation section:

[0096]

[0097] Finally, perform S716 to analyze the obtained overall displacement ΔR to obtain the final valley amplitude deformation result.

[0098] In a further example, the method further includes S800 performed after S710:

[0099] S800. Update the first coordinate result, and complete the update after covering the first coordinate result with the second coordinate result; after the update is completed, re-perform S100.

[0100] It is not difficult to understand that with the passage of time, valley amplitude deformation will continue to occur. The mechanical parameters of the rock mass basically do not change, but valley amplitude deformation is constantly occurring. Therefore, in order to improve the accuracy of the prediction results, it is necessary to continuously update the coordinates of each of the sub-regions 1. Specifically, in S800, the prediction result at the current moment is used as the input value for the next prediction, that is, the second coordinate result overwrites the first coordinate result to complete the update.

[0101] Second aspect embodiment;

[0102] This embodiment discloses a method for predicting the valley amplitude deformation of a water storage dam based on rock strata, which is different from the method disclosed in the first aspect embodiment in that: S500A is replaced with S500B, and S700A is replaced with S700B.

[0103] In this embodiment, the prediction of the new sub-coordinates also takes into account the rock stratum division. Therefore, the input content for predicting the valley amplitude deformation is the second vector including the rock stratum division.

[0104] In a specific example, S500B includes: reading the first coordinate results corresponding to several of the sub-regions 1 selected in S400, and establishing a second vector set for each of the sub-regions | according to the first number, where the second vector set includes several second sub-vectors, and each second sub-vector includes:

[0105] The first number corresponding to the sub-region |; the first parameters, sub-coordinates, and the result of the rock stratum division corresponding to a rock mass sample.

[0106] Exemplarily, in a specific example, the second sub-vector Vi′ is:

[0107] V′ ia =(i, P′ ia1 , P′ ia2 ,..., P′ ian , X′ ia , Y′ ia , Z′ ia , K′ i )

[0108] Wherein, i is the first number corresponding to the i-th sub-region 1, and a is the a-th rock mass sample corresponding to the i-th sub-region 1; (P’ ia1 , P’ ia2 , …, P’ ian ) are the respective mechanical parameters in the first parameter set corresponding to the a-th rock mass sample in the i-th sub-region 1, with a total of n rock mass mechanical parameters; (X’ ia , Y’ ia , Z’ ia′) is the sub-coordinate corresponding to the a-th rock sample in the i-th sub-region 1; K i ′ represents the corresponding rock stratum division results.

[0109] As described in the aforementioned embodiment of the first aspect, it is also necessary to perform S600 to obtain the total water head distribution field in the valley 2, and the specific details will not be repeated here.

[0110] As previously mentioned, the training parameters of the prediction model in this embodiment are changed compared to those in the first embodiment, resulting in a fundamental change in the training model. It is worth noting that although the same model and training steps can be used, the first prediction model in this example is different from the second prediction model, and the specific training process will not be repeated here.

[0111] Specifically, S700B includes: inputting the second vector set and the local head value into a pre-trained second prediction model; the second prediction model outputs the coordinates of each of the sub-areas 1 at the prediction moment as a second coordinate result, and the second coordinate result includes multiple new sub-coordinates corresponding to the coordinates of each of the rock samples at the prediction moment.

[0112] In this example, the gradient enhancement model is also used, but now the second input vector contains not only rock mass mechanical parameters and head values, but also information related to rock strata division.

[0113] According to the method described in the first or second embodiment, in an optional example, the method further includes S610 (not shown in the flowchart) performed after S600. In practice, while valley deformation does not affect rock mass mechanical parameters, it does change the permeability of the rock formation in Valley 2. Therefore, the permeability coefficient also needs to be updated, as described in detail in S610.

[0114] S610: Input the first vector set and the local hydraulic head value into a pre-trained third prediction model. The third prediction model is used to calculate or predict the new permeability coefficient after valley deformation or its impact on valley deformation prediction. Specifically, the third prediction model uses machine learning methods to capture and predict the complex relationship between the mechanical parameters, sub-coordinates, and hydraulic head values of the rock sample. The third prediction model can account for the impact of valley deformation on the permeability coefficient, and the output of the third prediction model includes the updated permeability coefficient of each sub-region 1 at the prediction time.

[0115] In S310 , the permeable rock layer is a rock mass with a high permeability coefficient, including a fractured rock layer and a broken rock layer; the general rock layer is a rock mass with a low permeability coefficient, including granite and mudstone.

[0116] Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters, wherein the water storage dam is constructed on any cross-section of a river valley, and is characterized in that, It includes the following steps: S100. Divide the river valley into several sub-regions, assign a first number to each sub-region, and obtain the coordinates of each sub-region at the initial moment as the first coordinate result; S200. Conduct multiple rock mass samplings on each sub-region to obtain a set of rock mass samples, obtain the rock mass mechanical parameters of each rock mass sample as the first parameter, and obtain the coordinates of each rock mass sample as the sub-coordinates; S300. Each set of rock mass samples collected from each sub-region corresponds to a set of the first parameters, and each set of the first parameters forms a first parameter set; S400. Select several sub-regions at the position of any valley cross-section observation section in the river valley, and read several first parameters corresponding to the selected sub-regions; S500A. Read the first coordinate results corresponding to several sub-regions selected in S400, and establish a first vector set according to the first number, where the first vector set includes several first sub-vectors, and each first sub-vector includes: The first number corresponding to the sub-region; The first parameter and sub-coordinates corresponding to a rock mass sample; Several first sub-vectors with the same first number constitute the first vector set; S600. Obtain the total head distribution field in the river valley, and retrieve the total head at the coordinates of each sub-region as the local head value according to the total head distribution field; S700A. Input the first vector set and the local head value into a pre-trained first prediction model; The first prediction model outputs the coordinates of each sub-region at the prediction moment as the second coordinate result, and the second coordinate result includes multiple new sub-coordinates corresponding to the coordinates of each rock mass sample at the prediction moment.

2. The method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters according to claim 1, wherein The S200 includes: S210. Conduct multiple rock mass samplings on each sub-region in sequence along the depth direction of the valley slope of the river valley, and assign a second number to each rock mass sample in sequence according to the depth where each rock mass sample is located; S220. Obtain the rock mass mechanical parameters of each rock mass sample as the first parameter.

3. The method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters according to claim 2, wherein Store the first vector set obtained in S500A, and read the first vector set in the stored data when executing S600 - S700A.

4. The method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters according to claim 3, characterized in that It also includes S710 performed after S700A: S710. Obtain the second coordinate result, and select the second coordinate result corresponding to the valley cross-section observation section; Obtain the valley cross-section deformation result by comparing the vector difference between the first coordinate result and the second coordinate result.

5. The method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters according to claim 4, characterized in that, The S710 includes: S711. Match the first coordinate result and the second coordinate result according to the first number, and match the sub-coordinates and the new sub-coordinates; S712. Obtain the vector difference between each pair of sub-coordinates and new sub-coordinates as a single vector; S713. Read the rock layer division in each sub-region and its position in the total head distribution field, and assign a first weight coefficient to several single vectors corresponding to each sub-region; S714. Perform vector summation on each single vector to obtain the first change amount; S715. Assign the first weight coefficient to each of the first change amounts, perform mathematical synthesis after weighting each of the first change amounts, and obtain the overall displacement result of the valley amplitude observation section. S716. Obtain the valley amplitude deformation results at each valley amplitude observation section according to the overall displacement result.

6. The method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters according to claim 4, characterized in that It further includes S800 performed after S710: S800. Update the first coordinate result, complete the update after covering the first coordinate result with the second coordinate result; after the update is completed, perform S100 again.

7. The method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters according to claim 4, characterized in that It further includes S610 performed after S600; S610. Input the first vector set and the local water head value into a pre-trained third prediction model; The third prediction model outputs the corrected permeability coefficient value, and re-perform S310 according to the corrected permeability coefficient.

8. The method for predicting the valley width deformation of a water storage dam based on rock mass mechanical parameters according to claim 4, characterized in that, It further includes S310 performed after S300: S310. Read the second number, and assign a permeability coefficient value to each of the rock mass samples according to the arrangement order of the second number; Perform rock layer division on the sub-region according to the permeability coefficient; The rock layer division includes permeable rock layers and general rock layers divided along the depth direction of the valley slope of the river valley.

9. A method for predicting valley amplitude deformation of a water storage dam based on rock layers. According to the method for predicting valley amplitude deformation of a water storage dam based on rock mass mechanical parameters described in any one of claims 5-8, characterized in that: Replace S500A with S500B; S500B. Read the first coordinate results corresponding to several of the sub-regions selected in S400, and establish a second vector set according to the first number, where the second vector set includes several second sub-vectors, and each second sub-vector includes: The first number corresponding to this sub-region; The first parameter, sub-coordinates and the result of rock layer division corresponding to a rock mass sample; Several first sub-vectors with the same first number constitute the first vector set; Replace S700A with S700B; S700B. Input the second vector set and the local water head value into a pre-trained second prediction model; 10. The method for predicting the valley width deformation of a water storage dam based on rock strata according to claim 9, characterized in that, The second prediction model outputs the coordinates of each sub-region at the prediction moment as the second coordinate result, and the second coordinate result includes multiple new sub-coordinates corresponding to the coordinates of each rock mass sample at the prediction moment. In S310: The permeable rock layer is a rock mass with a high permeability coefficient value, and the permeable rock layer includes: fractured rock layer and broken rock layer; The general rock layer is a rock mass with a low permeability coefficient value, and the general rock layer includes: granite and mudstone.

Images