Dam abutment slope cave dwelling type excavation supporting scheme optimization method, device and equipment, storage medium and program product

Abstract

The invention relates to a dam abutment side slope cave dwelling type excavation supporting scheme optimization method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a cave deformation data set; according to the cave deformation data set, training through a machine learning algorithm to obtain a cave deformation prediction model; constructing a multi-objective optimization mathematical model, and solving the multi-objective optimization mathematical model by using the cave dwelling deformation prediction model to obtain a target support scheme; the multi-objective optimization mathematical model is used for optimizing cave deformation and support cost during cave excavation in the target dam abutment slope area. The method can effectively improve the obtaining efficiency of the support scheme.

Description

Technical Field

[0001] The present application relates to the technical field of hydropower station engineering, and in particular to a method, device, equipment, storage medium and program product for optimizing a dam abutment slope cave-type excavation support scheme. Background Art

[0002] The cave-style excavation method used for the dam abutment slope can effectively reduce the excavation scope and workload, thereby protecting the slope ecological environment and improving the dam abutment stability. In particular, supporting the cave-style excavation project can effectively ensure the stability and safety of the excavation project.

[0003] However, traditional cave-style excavation support solutions for dam abutment slopes often require technical experts to calculate the corresponding support parameters based on their personal experience and on-site measurement data. This traditional method of obtaining support solutions is computationally inefficient and increases the time and cost of excavation work. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for optimizing the cave-type excavation support scheme of the dam abutment slope, which can effectively improve the calculation efficiency, in order to address the above technical problems.

[0005] In a first aspect, in one example, the present application provides a method for optimizing a cave-type excavation support scheme for a dam abutment slope, the method comprising:

[0006] Obtain cave deformation dataset;

[0007] Based on the cave deformation dataset, a cave deformation prediction model was obtained through machine learning algorithm training;

[0008] A multi-objective optimization mathematical model is constructed, and the cave deformation prediction model is used to solve the multi-objective optimization mathematical model to obtain the target support scheme; the multi-objective optimization mathematical model is used to optimize the cave deformation and support cost when cave-style excavation is carried out in the target dam abutment slope area.

[0009] In one embodiment, the step of obtaining a cave deformation dataset includes:

[0010] The Latin hypercube sampling method is used to obtain the support parameters of a preset number of groups, and the preset number of support parameters are input into the finite element model to obtain the cave deformation data set.

[0011] In one embodiment, the finite element model uses the Mohr-Coulomb criterion as the yield criterion of the finite element model, and adopts an elastic-plastic model for surrounding rock analysis.

[0012] In one embodiment, the machine learning algorithm includes an LSSVR algorithm; and the steps of obtaining a cave deformation prediction model by training the machine learning algorithm based on the cave deformation dataset include:

[0013] The cave deformation dataset is randomly divided into a model training set and a model test set according to a preset ratio;

[0014] According to the LSSVR algorithm, a cave deformation prediction model to be trained based on the LSSVR model is constructed;

[0015] Based on the model training set and the model test set, the cave deformation prediction model to be trained is trained and tested to obtain a trained cave deformation prediction model.

[0016] In one embodiment, the steps of constructing a multi-objective optimization mathematical model and solving the multi-objective optimization mathematical model using a cave deformation prediction model to obtain a target support solution include:

[0017] Based on the support parameters for the target dam abutment slope area, a multi-objective optimization mathematical model is constructed;

[0018] Based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model, and the target support scheme for the target dam abutment slope area is obtained.

[0019] In one embodiment, based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model to obtain the target support scheme for the target dam abutment slope area, including the following steps:

[0020] Based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model and obtain the Pareto frontier solution set.

[0021] The Pareto front solution set is processed by TOPSIS method to obtain the target support scheme for the target dam abutment slope area.

[0022] In a second aspect, in one example, the present application provides a device for optimizing a dam abutment slope cave-type excavation support scheme, the device comprising:

[0023] Dataset acquisition module, used to obtain cave deformation dataset;

[0024] The prediction model training module is used to obtain a cave deformation prediction model through machine learning algorithm training based on the cave deformation dataset;

[0025] The support scheme acquisition module is used to construct a multi-objective optimization mathematical model and use the cave deformation prediction model to solve the multi-objective optimization mathematical model to obtain the target support scheme; the multi-objective optimization mathematical model is used to optimize the cave deformation and support cost when cave-style excavation is carried out in the target dam abutment slope area.

[0026] In a third aspect, in one example, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method of any one of the method embodiments of the first aspect are implemented.

[0027] In a fourth aspect, in one example, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method of any one of the method embodiments of the first aspect above when the computer program is executed by a processor.

[0028] In a fifth aspect, in one example, the present application provides a computer program product, including a computer program, which implements the steps of the method of any one of the method embodiments of the first aspect when the computer program is executed by a processor.

[0029] The aforementioned method, device, equipment, storage medium, and program product for optimizing cave-type excavation support schemes for dam abutment slopes obtain a cave deformation dataset and, based on the cave deformation dataset, utilize a machine learning algorithm to train a cave deformation prediction model. A multi-objective optimization mathematical model is then constructed and rapidly solved using the cave deformation prediction model to obtain a target support scheme. Obtaining a target support scheme for a target dam abutment slope area in this manner can effectively improve the efficiency of obtaining support schemes. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 2. A diagram showing the application environment of a method for optimizing a cave-type excavation support scheme for a dam abutment slope in one embodiment;

[0032] Figure 2 A schematic flow chart of a method for optimizing a dam abutment slope cave-type excavation support scheme in one embodiment;

[0033] Figure 3 A schematic diagram of a flow chart of steps for training a cave deformation prediction model in one embodiment;

[0034] Figure 4 A schematic diagram of a process for obtaining a target support solution in one embodiment;

[0035] Figure 5 A schematic diagram of a process for obtaining a target support scheme in another embodiment;

[0036] Figure 6 A structural block diagram of a device for optimizing a dam abutment slope cave-type excavation support scheme in one embodiment;

[0037] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0039] The optimization method for the cave-type excavation support scheme of the dam abutment slope provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, drones, low-altitude aircraft, Internet of Things devices, and portable wearable devices. Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0040] In an exemplary embodiment, Figure 2 As shown in the figure, a method for optimizing cave-type excavation support scheme for dam abutment slope is provided. Figure 1 The server 104 in the example is used as an example to illustrate the process, including the following steps S202 to S206.

[0041] Step S202: Acquire cave deformation dataset.

[0042] The cave deformation dataset can include multiple cave deformation data corresponding to multiple support schemes. The cave deformation data can be used to characterize the difference between the actual excavation shape and the ideal excavation shape of the target dam abutment slope area when performing cave excavation in the target dam abutment slope area. It is understood that in actual engineering, the cave deformation data should be optimized to be minimized.

[0043] In some examples, a cave cave deformation dataset can be constructed based on historical cave cave excavation data on dam abutment slopes. It is understood that the method for obtaining the cave cave deformation dataset is not limited to the aforementioned implementation methods. As long as the required cave cave deformation dataset can be obtained, this embodiment of the application does not limit this.

[0044] Specifically, the server can obtain cave deformation datasets. For example, the cave deformation dataset includes multiple cave deformation data corresponding to different support schemes. For example, a support scheme with an anchor length of 6m, an anchor spacing of 3.5m, and a shotcrete thickness of 20cm is used. In actual projects, the cave deformation data generated by this support scheme is 26.53mm.

[0045] Step S204: Based on the cave deformation dataset, a cave deformation prediction model is obtained through training using a machine learning algorithm.

[0046] Exemplarily, the machine learning algorithm may include the LSSVR algorithm, etc. It is understood that the cave deformation prediction model obtained by training the machine learning algorithm can output cave deformation data under different support schemes; different support schemes use different support parameters.

[0047] Specifically, the server can train a cave deformation prediction model based on the obtained cave deformation dataset through a machine learning algorithm.

[0048] Step S206: construct a multi-objective optimization mathematical model, and use the cave deformation prediction model to solve the multi-objective optimization mathematical model to obtain a target support solution.

[0049] Among them, the multi-objective optimization mathematical model can be used to optimize the cave deformation and support cost when cave-type excavation is carried out in the target dam abutment slope area.

[0050] For example, the objective function of the multi-objective optimization mathematical model can be constructed based on the cave deformation data and support cost; the design variables of the mathematical model can be optimized with the support parameters as the target; the constraints of the target optimization mathematical model can be determined with the range of support parameter values; based on the above objective function, design variables and constraints, a multi-objective optimization mathematical model for the target dam shoulder slope area is constructed.

[0051] Specifically, the server can construct a multi-objective optimization mathematical model for the target dam shoulder slope area based on cave deformation data, support cost and support parameters, and use the cave deformation prediction model obtained above to solve the multi-objective optimization mathematical model, thereby obtaining the target support plan for the target dam shoulder slope area.

[0052] The above-mentioned method for optimizing the support scheme for cave-type excavation on the dam abutment slope obtains a cave deformation dataset, and based on the cave deformation dataset, uses a machine learning algorithm to train a cave deformation prediction model. Then, a multi-objective optimization mathematical model is constructed, and the cave deformation prediction model is used to quickly solve the multi-objective optimization mathematical model to obtain a target support scheme. Through the above-mentioned method, the present application not only efficiently obtains a support scheme for the target dam abutment slope area, but also optimizes the support cost, so that the support scheme can take into account both safety and economy, effectively improving the engineering efficiency of cave-type excavation on the dam abutment slope.

[0053] In one embodiment, the step of obtaining a cave deformation dataset includes the following steps:

[0054] The Latin hypercube sampling method is used to obtain the support parameters of a preset number of groups, and the preset number of support parameters are input into the finite element model to obtain the cave deformation data set.

[0055] Among them, the Latin hypercube sampling method can be used for efficient stratified sampling. For example, the Latin hypercube sampling method can be used to extract a preset number of support schemes from historical support schemes for cave-type excavation projects, and the support parameters corresponding to these support schemes can be used as input data for the finite element model. Optionally, the preset number of groups can be set to 100 groups. In this way, the sample distribution of the support parameters input to the finite element model can be optimized. Even when the sample size for the target dam abutment slope area is small, the distribution range of the input variables can be evenly covered, thereby effectively improving the simulation accuracy and computational efficiency of the finite element calculation.

[0056] In some examples, support parameters may include anchor rod length, anchor rod spacing, and shotcrete thickness. For example, taking the dam abutment slope area of ​​a hydropower station project as an example, the hydropower station project is mainly composed of a concrete hyperbolic arch dam, a left bank underground water diversion power generation system, etc. The maximum dam height is about 270m, the dam site area is a deep V-shaped deep valley, the banks on both sides are steep, and there is a natural slope of about 800m above the dam top elevation of 3000m. For the dam abutment slope area of ​​the above hydropower station project, the adopted support scheme may include the following support parameters: anchor rod length, anchor rod spacing, and shotcrete thickness. For example, when a support scheme with an anchor rod length of 6m, an anchor rod spacing of 3.5m, and a shotcrete thickness of 20cm is adopted in the dam abutment slope area of ​​the hydropower station project, 26.53mm of cave deformation data will be generated accordingly, and a support cost of 1.95 million yuan will be required.

[0057] Specifically, the server can use the Latin hypercube sampling method to obtain a preset number of support parameters, and input these support parameters as input data into a preset finite element model to obtain the required cave deformation data set through finite element calculation.

[0058] In one embodiment, the finite element model uses the Mohr-Coulomb criterion as the yield criterion of the finite element model, and adopts an elastic-plastic model for surrounding rock analysis.

[0059] Specifically, the server adopts an elastic-plastic model when performing surrounding rock analysis calculations using a finite element model, and uses the Mohr-Coulomb criterion as the yield criterion.

[0060] In some examples, when using a finite element model to simulate support methods, the shotcrete concrete is calculated using the finite element model's solid elements combined with a linear elastic model, while the anchor elements are simulated using pre-set truss elements, with the rod elements and geotechnical elements coupled in an embedded manner. Optionally, the finite element model can include ABAQUS, and the pre-set truss elements can use T3D2 truss elements.

[0061] For example, consider the abutment slope area of ​​a hydropower station project in the aforementioned embodiment. This hydropower station primarily consists of a concrete hyperbolic arch dam and a left-bank underground water diversion and power generation system. The maximum dam height is approximately 270 meters. The dam site is a deep V-shaped, incised river valley with steep bank slopes on both sides. Above the dam crest elevation of 3,000 meters, there is a natural slope of approximately 800 meters. For example, the calculation parameters of the finite element model for this hydropower station project can be set as shown in Table 1 below:

[0062] Table 1

[0063]

[0064] In one embodiment, the machine learning algorithm includes an LSSVR algorithm; Figure 3 As shown, the steps of obtaining a cave deformation prediction model by training a machine learning algorithm based on the cave deformation dataset include the following steps S302 to S306.

[0065] Step S302: randomly divide the cave deformation dataset into a model training set and a model test set in a preset ratio.

[0066] Among them, the model training set is used to train the cave deformation prediction model; the model test set can be used to test and verify the cave deformation prediction model.

[0067] For example, the obtained cave deformation dataset can be randomly divided into a model training set and a model test set in a preset ratio of 8:2.

[0068] Specifically, after the cave deformation dataset is calculated, the server can further divide the obtained cave deformation dataset into a model training set and a model test set according to a preset ratio.

[0069] Step S304: constructing a cave deformation prediction model to be trained based on the LSSVR model according to the LSSVR algorithm.

[0070] For example, according to the following formulas 1 and 2, the cave deformation prediction model to be trained based on the LSSVR model is:

[0071] (Formula 1)

[0072] (Formula 2)

[0073] in, The cave deformation prediction value output by the cave deformation prediction model; is the Lagrange multiplier; is the kernel function of the cave deformation prediction model; and are the dataset to be predicted and the cave deformation dataset obtained by numerical simulation respectively; is the offset; l is the total number of input variables; is the kernel sensitivity coefficient. Optionally, the hyperparameters of the LSSVR model are The value range is generally (0.1, 100) and can be adjusted according to project needs.

[0074] Specifically, the server can construct a cave deformation prediction model to be trained based on the LSSVR model according to the LSSVR algorithm.

[0075] Step S306: Based on the model training set and the model test set, the cave deformation prediction model to be trained is trained and tested to obtain a trained cave deformation prediction model.

[0076] Specifically, the server can use the LSSVR algorithm to train the cave deformation prediction model to be trained based on the model training set, and after training, test and verify the cave deformation prediction model using the model test set to evaluate the model performance of the current cave deformation prediction model. For example, if the cave deformation prediction value output by the cave deformation prediction model to be trained does not meet the preset accuracy requirements, the model parameters of the cave deformation prediction model are adjusted and the next round of training is continued; if the cave deformation prediction value output by the cave deformation prediction model to be trained meets the preset accuracy requirements, it is determined that the cave deformation prediction model training is complete.

[0077] In one embodiment, Figure 4 As shown, the steps of constructing a multi-objective optimization mathematical model and solving the multi-objective optimization mathematical model using the cave deformation prediction model to obtain the target support scheme include the following steps S402 to S404.

[0078] Step S402: construct a multi-objective optimization mathematical model based on the support parameters for the target dam abutment slope area.

[0079] For example, the support parameters for the target abutment slope area may include parameters such as anchor length, anchor spacing, and shotcrete thickness. In some examples, as shown in the following formulas 3 to 7, the multi-objective optimization mathematical model can be expressed as:

[0080] (Formula 3)

[0081] (Formula 4)

[0082] (Formula 5)

[0083] (Formula 6)

[0084] (Formula 7)

[0085] in, The best support solution for the target dam abutment slope area; The cave deformation prediction model mentioned above is input [ ] output cave deformation data; is the anchor rod length, is the spacing between anchor rods (the spacing between rows is the same), is the thickness of the shotcrete; H is the height of the slope to be supported; is the total support cost; and They are the cost of bolt support and the cost of shotcrete support respectively; and They are the total perimeter of the cave dwelling and the perimeter excluding the bottom of the cave dwelling; The support cost per linear meter of anchor hole; is the unit volume cost of shotcrete.

[0086] Furthermore, as shown in the following formula, the constraints of the multi-objective optimization mathematical model can be expressed as follows:

[0087] (Formula 8)

[0088] (Formula 9)

[0089] (Formula 10)

[0090] in, and are the upper and lower limits of the anchor length respectively; and are the upper and lower limits of the spacing between anchor bolts respectively; and are the upper and lower limits of the spray mix thickness respectively. For example, taking the dam shoulder slope area of ​​a hydropower station project in the above embodiment as an example, the hydropower station project is mainly composed of a concrete hyperbolic arch dam, a left bank underground water diversion and power generation system, etc. The maximum dam height is about 270m, the dam site area is a deep V-shaped deep valley, the banks on both sides are steep, and there is a natural slope of about 800m above the dam top elevation of 3000m. At this time, the constraints of the multi-objective optimization mathematical model can be set as: anchor rod length L = 4 ~ 8m, anchor rod spacing S = 2 ~ 4m, spray layer thickness T = 10 ~ 30cm. It can be understood that by reasonably taking the constraints of the multi-objective optimization mathematical model, better modeling accuracy can be obtained while reducing the model calculation workload.

[0091] Specifically, the server can construct a multi-objective optimization mathematical model for the target dam abutment slope area based on support parameters such as anchor length, anchor spacing and shotcrete thickness.

[0092] Step S404: Based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model to obtain a target support scheme for the target dam abutment slope area.

[0093] Exemplarily, the initial population size, number of algorithm iterations, crossover operator, and mutation operator of the NSGA-III algorithm can be determined based on the actual engineering conditions of the target dam abutment slope area and the computational cost. For example, taking the dam abutment slope area of ​​a hydropower station project in the above embodiment as an example, the initial population size of the NSGA-III algorithm can be set to 100, the number of iterations can be set to 800, the crossover operator can be set to 0.9, and the mutation operator can be set to 0.1. It can be understood that the parameter setting of the above NSGA-III algorithm is not limited to the implementation method mentioned in the above embodiment. As long as it can solve the above multi-objective optimization mathematical model, the embodiment of the present application does not limit the specific parameter setting of the NSGA-III algorithm.

[0094] Specifically, the server uses the NSGA-III algorithm to quickly solve the multi-objective optimization mathematical model for the target dam abutment slope area based on the cave deformation prediction model, thereby obtaining the optimal target support scheme for the cave-style excavation in the target dam abutment slope area.

[0095] In one embodiment, Figure 5 As shown, based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model to obtain the target support scheme for the target dam abutment slope area, including the following steps S502 to S504.

[0096] Step S502: Based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model to obtain the Pareto frontier solution set.

[0097] For example, the NSGA-III algorithm continuously generates new individuals and approaches the Pareto optimal front by performing non-dominated sorting, selection, crossover, and mutation operations, ultimately outputting a set of Pareto front solutions located on the Pareto front. It can be understood that the Pareto front solution set output by the NSGA-III algorithm can provide engineering decision makers with a variety of support solutions.

[0098] Specifically, based on the constructed cave deformation prediction model, the server uses the NSGA-III algorithm to quickly solve the multi-objective optimization mathematical model to obtain the Pareto frontier solution set, and provide a variety of feasible support schemes through the Pareto frontier solution set.

[0099] Step S504: Process the Pareto front solution set using the TOPSIS method to obtain a target support scheme for the target dam abutment slope area.

[0100] For example, the TOPSIS method is used to sort all non-inferior solutions in the Pareto front solution set. In the absence of obvious optimization bias, the indicator weights of cave deformation and support cost in the TOPSIS method are both 0.5. The Euclidean distance between each support scheme and the optimal value and the worst value is calculated to obtain the relative proximity of each support scheme. Then, the schemes are sorted according to the relative proximity of each support scheme. Finally, the support scheme ranked first (with the largest relative proximity) is selected as the optimal support scheme for the dam abutment slope area of ​​the hydropower station project.

[0101] Specifically, the server can optimize and sort the Pareto frontier solution set through the TOPSIS method, thereby obtaining the optimal target support scheme for the target dam abutment slope area.

[0102] For example, consider the abutment slope area of ​​a hydropower station project in the aforementioned embodiment. This hydropower station primarily consists of a concrete hyperbolic arch dam and a left-bank underground water diversion and power generation system. The maximum dam height is approximately 270 meters, and the dam site is a deep V-shaped, incised river valley with steep bank slopes on both sides. Above the dam crest elevation of 3,000 meters, there is a natural slope of approximately 800 meters. For this abutment slope area, a comparison of the optimized support scheme ultimately obtained in this application with the original scheme originally planned is shown in Table 2 below:

[0103] Table 2

[0104]

[0105] From the comparison results in Table 2 above, it can be seen that the optimized support scheme finally obtained by this application reduces the cave deformation by 13.8% and the support cost by 5% compared with the original scheme. This shows that the optimization method of the dam abutment slope cave excavation support scheme of this application effectively improves the safety and economy of the support scheme.

[0106] It can be understood that the present application can efficiently predict the deformation of caves under different support schemes, thereby replacing complex numerical simulation calculations and saving a lot of computing costs. Secondly, the present application can intelligently obtain optimized support schemes, which are more comprehensive and economical than support schemes obtained by relying on expert experience. In addition, the multi-objective optimization mathematical model based on machine learning can efficiently obtain appropriate support optimization schemes, thereby providing decision support for the optimal design of support schemes for cave-type excavations on dam abutment slopes.

[0107] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps. It is understandable that the various steps in different embodiments can be freely combined as needed, and the various non-contradictory schemes formed by the combination all fall within the scope of protection of this application.

[0108] Based on the same inventive concept, embodiments of the present application also provide a device for optimizing a dam abutment slope cave-type excavation and support schemes for implementing the aforementioned method for optimizing a dam abutment slope cave-type excavation and support schemes. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the device for optimizing a dam abutment slope cave-type excavation and support schemes provided below can be found in the limitations of the method for optimizing a dam abutment slope cave-type excavation and support schemes described above and will not be further elaborated here.

[0109] In an exemplary embodiment, Figure 6 As shown, the present application provides a device 600 for optimizing a dam abutment slope cave-type excavation support scheme, the device 600 comprising:

[0110] The data set acquisition module 602 is used to acquire the cave deformation data set;

[0111] The prediction model training module 604 is used to obtain a cave deformation prediction model through training of a machine learning algorithm based on the cave deformation dataset;

[0112] The support scheme acquisition module 606 is used to construct a multi-objective optimization mathematical model and use the cave deformation prediction model to solve the multi-objective optimization mathematical model to obtain a target support scheme; the multi-objective optimization mathematical model is used to optimize the cave deformation and support cost when cave-type excavation is carried out in the target dam shoulder slope area.

[0113] In one embodiment, the data set acquisition module 602 is further configured to:

[0114] The Latin hypercube sampling method is used to obtain the support parameters of a preset number of groups, and the preset number of support parameters are input into the finite element model to obtain the cave deformation data set.

[0115] In one embodiment, the finite element model uses the Mohr-Coulomb criterion as the yield criterion of the finite element model, and adopts an elastic-plastic model for surrounding rock analysis.

[0116] In one embodiment, the machine learning algorithm includes an LSSVR algorithm; the prediction model training module 604 is further configured to:

[0117] The cave deformation dataset is randomly divided into a model training set and a model test set according to a preset ratio;

[0118] According to the LSSVR algorithm, a cave deformation prediction model to be trained based on the LSSVR model is constructed;

[0119] Based on the model training set and the model test set, the cave deformation prediction model to be trained is trained and tested to obtain a trained cave deformation prediction model.

[0120] In one embodiment, the support scheme acquisition module 606 is further configured to:

[0121] Based on the support parameters for the target dam abutment slope area, a multi-objective optimization mathematical model is constructed;

[0122] Based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model, and the target support scheme for the target dam abutment slope area is obtained.

[0123] In one embodiment, the support scheme acquisition module 606 is further configured to:

[0124] Based on the cave deformation prediction model, the NSGA-III algorithm is used to solve the multi-objective optimization mathematical model and obtain the Pareto frontier solution set.

[0125] The Pareto front solution set is processed by TOPSIS method to obtain the target support scheme for the target dam abutment slope area.

[0126] Each module in the aforementioned device for optimizing cave-style excavation support schemes for dam abutment slopes can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a computer device's memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0127] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data such as support parameters, support costs and cave deformation data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for optimizing a cave excavation support scheme for a dam abutment slope is implemented.

[0128] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0129] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining a cave deformation data set; obtaining a cave deformation prediction model through training of a machine learning algorithm based on the cave deformation data set; constructing a multi-objective optimization mathematical model, and using the cave deformation prediction model to solve the multi-objective optimization mathematical model to obtain a target support scheme.

[0130] In one embodiment, when the processor executes the computer program, it also implements the following steps: using the Latin hypercube sampling method to obtain a preset number of groups of support parameters, and inputting the preset number of groups of support parameters into the finite element model to obtain a cave deformation data set.

[0131] In one embodiment, when the processor executes the computer program, the following steps are also implemented: randomly dividing the cave deformation data set into a model training set and a model test set in a preset ratio; constructing a cave deformation prediction model to be trained based on the LSSVR model according to the LSSVR algorithm; training and testing the cave deformation prediction model to be trained based on the model training set and the model test set to obtain a trained cave deformation prediction model.

[0132] In one embodiment, when the processor executes the computer program, it also implements the following steps: constructing a multi-objective optimization mathematical model based on the support parameters for the target dam abutment slope area; solving the multi-objective optimization mathematical model using the NSGA-III algorithm based on the cave deformation prediction model to obtain a target support scheme for the target dam abutment slope area.

[0133] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the cave deformation prediction model, the multi-objective optimization mathematical model is solved using the NSGA-III algorithm to obtain a Pareto front solution set; the Pareto front solution set is processed using the TOPSIS method to obtain a target support scheme for the target dam abutment slope area.

[0134] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining a cave deformation data set; obtaining a cave deformation prediction model through training of a machine learning algorithm based on the cave deformation data set; constructing a multi-objective optimization mathematical model, and using the cave deformation prediction model to solve the multi-objective optimization mathematical model to obtain a target support scheme; the multi-objective optimization mathematical model is used to optimize the cave deformation and support cost when cave-type excavation is carried out in the target dam shoulder slope area.

[0135] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: using the Latin hypercube sampling method to obtain a preset number of groups of support parameters, and inputting the preset number of groups of support parameters into the finite element model to obtain a cave deformation data set.

[0136] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: randomly dividing the cave deformation data set into a model training set and a model test set in a preset ratio; constructing a cave deformation prediction model to be trained based on the LSSVR model according to the LSSVR algorithm; training and testing the cave deformation prediction model to be trained based on the model training set and the model test set to obtain a trained cave deformation prediction model.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: a multi-objective optimization mathematical model is constructed based on the support parameters for the target dam abutment slope area; based on the cave deformation prediction model, the multi-objective optimization mathematical model is solved using the NSGA-III algorithm to obtain a target support scheme for the target dam abutment slope area.

[0138] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the cave deformation prediction model, the multi-objective optimization mathematical model is solved using the NSGA-III algorithm to obtain the Pareto front solution set; the Pareto front solution set is processed using the TOPSIS method to obtain a target support scheme for the target dam abutment slope area.

[0139] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0140] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0141] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0142] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for optimizing cave-type excavation support scheme for dam abutment slope, characterized in that: The method comprises: Obtain cave deformation dataset; Based on the cave deformation data set, a cave deformation prediction model is obtained through training of a machine learning algorithm; A multi-objective optimization mathematical model is constructed, and the cave deformation prediction model is used to solve the multi-objective optimization mathematical model to obtain a target support scheme; the multi-objective optimization mathematical model is used to optimize the cave deformation and support cost when cave-type excavation is carried out in the target dam abutment slope area.

2. The method according to claim 1, characterized in that The step of obtaining the cave deformation dataset includes: A preset number of groups of support parameters are obtained using a Latin hypercube sampling method, and the preset number of groups of support parameters are input into a finite element model to obtain the cave deformation data set.

3. The method according to claim 2, characterized in that The finite element model uses the Mohr-Coulomb criterion as the yield criterion of the finite element model and adopts the elastic-plastic model to perform surrounding rock analysis.

4. The method according to claim 1, wherein The machine learning algorithm includes an LSSVR algorithm; and the step of obtaining a cave deformation prediction model through training of the machine learning algorithm based on the cave deformation dataset includes: The cave deformation dataset is randomly divided into a model training set and a model test set according to a preset ratio; According to the LSSVR algorithm, a cave deformation prediction model to be trained based on the LSSVR model is constructed; Based on the model training set and the model test set, the cave deformation prediction model to be trained is trained and tested to obtain a trained cave deformation prediction model.

5. The method according to any one of claims 1 to 4, characterized in that The step of constructing a multi-objective optimization mathematical model and solving the multi-objective optimization mathematical model using the cave deformation prediction model to obtain a target support solution includes: constructing the multi-objective optimization mathematical model according to the support parameters for the target dam abutment slope area; Based on the cave deformation prediction model, the multi-objective optimization mathematical model is solved using the NSGA-III algorithm to obtain the target support scheme for the target dam abutment slope area.

6. The method according to claim 5, characterized in that The step of solving the multi-objective optimization mathematical model based on the cave deformation prediction model using the NSGA-III algorithm to obtain the target support scheme for the target dam abutment slope area includes: Based on the cave deformation prediction model, the multi-objective optimization mathematical model is solved using the NSGA-III algorithm to obtain the Pareto frontier solution set; The Pareto front solution set is processed by the TOPSIS method to obtain the target support scheme for the target dam abutment slope area.

7. A device for optimizing cave-type excavation support scheme for dam abutment slope, characterized in that: The device comprises: Dataset acquisition module, used to obtain cave deformation dataset; A prediction model training module is used to obtain a cave deformation prediction model through training of a machine learning algorithm based on the cave deformation dataset; The support scheme acquisition module is used to construct a multi-objective optimization mathematical model and use the cave deformation prediction model to solve the multi-objective optimization mathematical model to obtain a target support scheme; the multi-objective optimization mathematical model is used to optimize the cave deformation and support cost when cave-type excavation is carried out in the target dam shoulder slope area.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images