A parameter inversion method and system for slope rock-soil

Abstract

The application provides a parameter inversion method and system for slope rock-soil, and relates to the technical field of slope treatment, which comprises the following steps: obtaining the surface topography and soil layer boundary of a slope, establishing a three-dimensional model of the slope in simulation software according to the surface topography and soil layer decomposition of the slope; randomly assigning shear strength parameters to a to-be-inverted section, and simulating the three-dimensional model of the slope by using the simulation software; arranging a plurality of monitoring points in the to-be-inverted section of the three-dimensional model of the slope, collecting the displacement and stress of the monitoring points in the simulation process, and calculating the local safety factor of the to-be-inverted section by using the stress of the monitoring points; constructing a data set by taking the displacement of the monitoring points as an input layer and taking the shear strength parameters and the local safety factor of the to-be-inverted section as an output layer; constructing a radial basis neural network, training the radial basis neural network by using the data set, and obtaining a trained parameter inversion model; and the application can determine the shear strength parameters of multilayer rock-soil bodies at different positions along a sliding surface.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of slope treatment, in particular to a parameter inversion method and system for slope rock-soil. BACKGROUND

[0002] The geotechnical test method is disturbed to different degrees in the process of sampling, transportation and testing of the rock-soil sample, especially the broken weathered rock layer, so the parameters obtained by the test method cannot reflect the true state of the rock-soil in many cases. The empirical rule is limited by the personal ability and experience accumulation of the engineer, has certain limitations and ignores the influence of the actual engineering geological condition on the parameters, so the reliability of the research result is not high in the actual engineering application. The traditional rock-soil shear strength parameter inversion method is only applicable to the case that the landslide model and boundary conditions are known, and the rock-soil is homogeneous and single sliding surface, and the traditional inversion method cannot simultaneously invert the shear strength parameters of the multi-layer rock-soil to ensure the reliability of the selected rock-soil shear strength parameters when analyzing the stability of some composite slopes. SUMMARY

[0003] The present application aims to provide a parameter inversion method and system for slope rock-soil to improve the above problems. In order to achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0004] In a first aspect, the present application provides a parameter inversion method for slope rock-soil, comprising:

[0005] obtaining the surface topography and soil layer boundary of the slope, and establishing a three-dimensional model of the slope in a simulation software according to the surface topography and soil layer of the slope;

[0006] determining a to-be-inverted section of the three-dimensional model of the slope, randomly assigning shear strength parameters to the to-be-inverted section, and simulating the three-dimensional model of the slope by using the simulation software;

[0007] arranging a plurality of monitoring points in the to-be-inverted section of the three-dimensional model of the slope, collecting the displacement and stress of the monitoring points in the simulation process, and calculating the local safety factor of the to-be-inverted section by using the stress of the monitoring points;

[0008] constructing a data set by taking the displacement of the monitoring points as the input layer and the shear strength parameters and the local safety factor of the to-be-inverted section as the output layer;

[0009] constructing a radial basis neural network, training the radial basis neural network by using the data set, and obtaining a trained parameter inversion model.

[0010] In a second aspect, the present application further provides a parameter inversion system for slope rock-soil, comprising:

[0011] The model establishing module obtains the surface topography and soil layer demarcation of the slope, and establishes a three-dimensional model of the slope in a simulation software according to the surface topography and soil layer demarcation of the slope;

[0012] The simulation module determines a section to be inverted of the three-dimensional model of the slope, randomly assigns a shear strength parameter to the section to be inverted, and simulates the three-dimensional model of the slope by using the simulation software;

[0013] The calculation module arranges a plurality of monitoring points in the section to be inverted of the three-dimensional model of the slope, collects the displacement and stress of the monitoring points in the simulation process, and calculates the local safety factor of the section to be inverted by using the stress of the monitoring points;

[0014] The data set constructing module constructs a data set by taking the displacement of the monitoring points as an input layer and taking the shear strength parameter and the local safety factor of the section to be inverted as an output layer;

[0015] The training module constructs a radial basis neural network, trains the radial basis neural network by using the data set, and obtains a trained parameter inversion model.

[0016] In a third aspect, the present application further provides a parameter inversion device for slope rock-soil, comprising:

[0017] A memory for storing a computer program;

[0018] A processor for executing the computer program to realize the steps of the parameter inversion method for slope rock-soil.

[0019] In a fourth aspect, the present application further provides a readable storage medium, wherein the readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the parameter inversion method for slope rock-soil.

[0020] The present application has the following beneficial effects:

[0021] The present application calculates the displacement and the slope safety factor under different parameter combinations by establishing a three-dimensional slope model, takes the sample data for inversion analysis, trains the RBF neural network model, and obtains the trained parameter inversion model. The in-situ monitoring displacement data is input into the parameter inversion model to invert the shear strength parameter and the local safety factor of different sections of the slope, and the quantitative function relationship between the in-situ monitoring displacement and the safety factor of the weighted point of the slope is fitted, so that the shear parameter inversion of the rock-soil body and the rapid evaluation and analysis of the dynamic stability of the slope based on the displacement back analysis method are realized.

[0022] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the application. The objects and other advantages of the application can be realized and attained by means of the instrumentalities and combinations particularly pointed out in the written description and claims hereof. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0024] Figure 1 The figure is a flow chart of the parameter inversion method of the slope rock-soil described in the embodiments of the present application.

[0025] Figure 2 The figure is a three-dimensional model of the slope described in the embodiments of the present application.

[0026] Figure 3 The figure is a displacement curve of the monitoring point described in the embodiments of the present application.

[0027] Figure 4 The figure is a schematic diagram of the local safety factor of the inversion section described in the embodiments of the present application.

[0028] Figure 5 The figure is a flow chart of the radial basis neural network training described in the embodiments of the present application.

[0029] Figure 6 The figure is a schematic diagram of the parameter inversion system structure of the slope rock-soil described in the embodiments of the present application.

[0030] Figure 7 The figure is a schematic diagram of the parameter inversion equipment structure of the slope rock-soil described in the embodiments of the present application.

[0031] Markings in the figure:

[0032] 800, parameter inversion equipment of slope rock-soil; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0033] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings of the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0034] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used for distinguishing description, and cannot be understood as indicating or implying relative importance.

[0035] Embodiment 1

[0036] The embodiment provides a parameter inversion method for slope rock-soil.

[0037] Referring to Figure 1 , the method includes:

[0038] S1. Obtain the surface topography and soil layer boundary of the slope, and establish a three-dimensional model of the slope in a simulation software according to the surface topography and soil layer decomposition of the slope;

[0039] Specifically, the step S1 includes:

[0040] S11. Measure the surface topography of the slope by using contour lines, and determine the soil layer boundary by soil layer drilling;

[0041] S12. Establish an initial three-dimensional model of the slope in a simulation software FLAC3D according to the surface topography and soil layer decomposition of the slope;

[0042] S13. Calculate the plastic zone of the initial three-dimensional model of the slope based on the strength reduction method, form a sliding surface penetrating the slope body of the initial three-dimensional model of the slope from the plastic zone, and divide the initial three-dimensional model of the slope into a sliding bed and a sliding body by the sliding surface; in the embodiment, the sliding bed is a mudstone layer, and the sliding body is a clay intercalated layer.

[0043] S14. Divide the sliding body into a traction segment, a main sliding segment and an anti-sliding segment, and generate a three-dimensional model of the slope, as shown in Figure 2 .

[0044] Based on the above embodiments, the method further comprises:

[0045] S2. Determine the inversion section of the slope three-dimensional model, randomly assign the shear strength parameters of the inversion section, and simulate the slope three-dimensional model using simulation software;

[0046] Specifically, the step S2 comprises:

[0047] S21. The slide bed, traction section, main slide section and anti-slide section are taken as the inversion section, and the cohesion and internal friction angle are taken as the shear strength parameters to be inverted;

[0048] S22. Randomly select the cohesion value and internal friction angle for the slide bed, traction section, main slide section and anti-slide section in turn to generate several groups of tests;

[0049] Specifically, according to the test results of the physical and mechanical parameters of the rock and soil layer and the recommended value range of the specification, the physical and mechanical parameter value table of the rock and soil body for FLAC3D numerical calculation is obtained, as shown in Table 1.

[0050] Table 1

[0051]

[0052] In Table 1, the specific gravity, elastic modulus and Poisson's ratio are fixed values, and the cohesion and internal friction angle are value ranges.

[0053] The DPS data processing system is used for uniform test design of the inversion section and shear strength parameters to obtain factor groups [(c1, φ1), (c2, φ2), (c3, φ3), (c4, φ4)], wherein [c1, φ1], [c2, φ2] and [c3, φ3] are the traction section, main slide section and anti-slide section of the clay and crushed stone, and [c4, φ4] is the mudstone layer, that is, the uniform test design contains 8 factors.

[0054] This embodiment designs 10 groups of tests, that is, each group of tests contains a factor group, and the cohesion and internal friction angle in each factor group are randomly selected from the range given in Table 1 to obtain the uniform test results as shown in Table 2.

[0055] Table 2

[0056]

[0057] S23. Simulate each test using simulation software, and in the FLAC3D numerical simulation software, set the model around and the ground as normal constraint, generate initial stress field and displacement field under the action of gravity;

[0058] S24. Clear the displacement field, and regenerate the slope displacement field in the strength reduction process, and the slope displacement changes.

[0059] Based on the above embodiment, the method further comprises:

[0060] S3. Arranging a plurality of monitoring points in the to-be-inverted section of the three-dimensional model of the slope, collecting the displacement and stress of the monitoring points in the simulation process, and calculating the local safety factor of the to-be-inverted section by using the stress of the monitoring points;

[0061] In this embodiment, 12 monitoring points are arranged, four monitoring points are arranged in the vertical direction at the center positions of the traction section, the main sliding section and the anti-sliding section, two monitoring points are arranged in the sliding body layer, one monitoring point is arranged in the sliding zone layer, and one monitoring point is arranged in the sliding body layer. The displacement curves of the 12 monitoring points are as shown in Figure 3 ;

[0062] The point safety factor of the monitoring point is calculated by using the stress of the monitoring point:

[0063]

[0064] In the formula, τ u is the shear strength of the sliding zone unit in the sliding direction; τ is the shear stress of the sliding zone unit in the sliding direction; c、 are the cohesion and internal friction angle of the monitoring point respectively; σ n is the normal stress perpendicular to the sliding zone unit;

[0065] The point safety factors of all the monitoring points are calculated in sequence by using the above formula, the point safety factors in the same section are weighted and summed to calculate the local safety factor of the section. Please refer to Figure 4 . Specifically, the point safety factors in the sliding bed are weighted and summed to calculate the local safety factor of the sliding bed.

[0066] Based on the above embodiment, the method further comprises:

[0067] S4. Constructing a data set by taking the displacement of the monitoring point as the input layer and the shear strength parameter and the local safety factor of the to-be-inverted section as the output layer;

[0068] Specifically, the step S4 comprises:

[0069] S41. Normalizing the displacement of the monitoring point and the local safety factor;

[0070]

[0071] In the formula, l represents the to-be-processed data, which is the displacement or the local safety factor, l min represents the minimum value of the to-be-processed data, l max represents the maximum value of the to-be-processed data, and l' represents the processed data.

[0072] S42. The normalized monitoring point displacement is converted into a one-dimensional vector as an input layer, the shear strength parameter of the section to be inverted is taken as a first output layer, and the normalized local safety factor is taken as a second output layer to construct a data set;

[0073] S43. The data set is divided into a training set and a test set according to a ratio of 7:3, the training set is used to train the neural network model, and the test set is used to evaluate the generalization ability of the model.

[0074] Based on the above embodiments, the method further comprises:

[0075] S5. A radial basis neural network is constructed, and the radial basis neural network is trained using the data set to obtain a trained parameter inversion model.

[0076] Specifically, please refer to Figure 5 , the step S5 comprises:

[0077] S51. Initialize the particle swarm, and generate a position vector and a speed for each particle;

[0078] X={x1,x2,…,x i ,...,x n}; (3)

[0079] In the formula, x i is a D-dimensional vector representing the position of the i-th particle;

[0080] V={v1,v2…,v i ,...,v n}; (4)

[0081] where v i is a D-dimensional vector representing the speed of the i-th particle.

[0082] S52. A radial basis neural network is constructed, and each particle position vector is mapped to the radial basis neural network to generate a set of radial basis network parameters, i.e., RBF network parameters, each particle representing a set of solutions of the RBF network parameters. A set of RBF network parameters includes RBF network weights, RBF network centers and RBF network radii, which are respectively:

[0083] W={w1,w2,...,w k}; (5)

[0084] where w k represents the weight of the k-th RBF neuron;

[0085] C={c1,c2,...,c k}; (6)

[0086] where ck is a D-dimensional vector, representing the center of the k-th RBF neuron;

[0087] R={r1,r2,...,r k}; (7)

[0088] where r k is a scalar representing the radius of the kth RBF neuron.

[0089] S53. The data set is sequentially input into each set of radial basis network parameters, and after the radial basis network parameters learn the monitoring point displacement, the output value of the radial basis network parameters is obtained;

[0090]

[0091] Where q represents displacement, represents the RBF function; ||xc k || represents q and c k The Euclidean distance between them, y represents the output value, namely the predicted shear strength parameter and the predicted local safety factor.

[0092] S54. Calculate the particle fitness using the output value of the radial basis network parameters, and update the particle position vector and velocity according to the particle fitness to obtain the updated radial basis network parameters;

[0093] In this embodiment, the fitness can be a mean square error (MSE) or a root mean square error (RMSE). The fitness between the output shear strength parameter and the actual shear strength parameter, and the fitness between the output local safety factor and the actual local safety factor are calculated respectively. The smaller the error value, the smaller the fitness.

[0094] Compare the fitness of all particles to determine the global optimal position of the particle swarm and the individual optimal position of each particle;

[0095] Update the particle's position vector and velocity:

[0096]

[0097] Where, v i ′ represents the updated speed, x′ i Represents the updated position vector, pbest i Represents particle x i The individual optimal position of the particle swarm; gbest represents the global optimal position of the particle swarm; p1 and p2 are calculation parameters; rand() is a random number generation function;

[0098] Get the optimal weight corresponding to the individual's optimal position and the optimal radius i.e. the weight and radius found by the particle in the search space that minimizes the fitness function value, according to the optimal weight and the optimal radius updating the radial basis network parameters:

[0099]

[0100] where a, b are calculation parameters, w' and r' represent the updated weight and radius, respectively. k k

[0101] S55. Repeating the calculation of the particle fitness with the updated radial basis network parameters until the calculation number reaches a preset iteration number or the minimum fitness of the particle reaches a preset threshold;

[0102] S56. The parameter inversion model is composed of the radial basis network parameters corresponding to the particle with the minimum fitness.

[0103] In the particle swarm optimization (PSO) algorithm, each particle updates its own speed and position according to its current position, speed, and its historical optimal position (pbest) and the optimal position of all particles in the particle swarm (gbest, i.e. global optimum) to guide the particle to move to the region in the search space that may have a better solution. The fitness of the particle directly reflects the performance of the RBF network parameters it represents, and the PSO algorithm optimizes the RBF network parameters through an iterative process to improve the prediction or regression performance of the RBF network.

[0104] Based on the above embodiment, the method further comprises:

[0105] S6. Determining the actual positions of the monitoring points on the slope and obtaining the actual displacements of the monitoring points, which can be obtained by using a total station, GPS, inclinometer, etc.

[0106] S7. After normalizing the actual displacements of the monitoring points, converting them into a one-dimensional vector input parameter inversion model for inversion analysis to generate the shear strength parameters and local safety factors of the to-be-inverted section.

[0107] S8. Taking the actual displacements of the monitoring points as the independent variables and the local safety factors as the dependent variables, performing fitting analysis through Matlab software to determine the quantitative functional relationship between the displacements and the local safety factors.

[0108] S9. Constructing a displacement-local safety factor analysis model according to the quantitative functional relationship to realize rapid evaluation and analysis of the dynamic stability of the slope.

[0109] Embodiment 2:

[0110] As​​Figure 6 The embodiment shown provides a parameter inversion system for slope rock-soil, which comprises:

[0111] The model establishing module obtains the surface topography and soil layer demarcation of the slope, and establishes a three-dimensional model of the slope in simulation software according to the surface topography and soil layer demarcation of the slope;

[0112] The simulation module determines a section to be inverted of the three-dimensional model of the slope, randomly assigns shear strength parameters to the section to be inverted, and simulates the three-dimensional model of the slope by using the simulation software;

[0113] The calculation module arranges a plurality of monitoring points in the section to be inverted of the three-dimensional model of the slope, collects the displacement and stress of the monitoring points in the simulation process, and calculates the local safety factor of the section to be inverted by using the stress of the monitoring points;

[0114] The data set construction module constructs a data set by taking the displacement of the monitoring points as an input layer and taking the shear strength parameters and the local safety factor of the section to be inverted as an output layer;

[0115] The training module constructs a radial basis neural network, trains the radial basis neural network by using the data set, and obtains a parameter inversion model after training.

[0116] Based on the above embodiment, the model establishing module comprises:

[0117] The measurement unit measures the surface topography of the slope by using contour lines and determines the soil layer demarcation by soil layer drilling;

[0118] The three-dimensional model establishing unit establishes an initial three-dimensional model of the slope in simulation software according to the surface topography and soil layer demarcation of the slope;

[0119] The first division unit calculates a plastic zone of the initial three-dimensional model of the slope based on the strength reduction method, forms a sliding surface penetrating the slope body of the initial three-dimensional model of the slope from the plastic zone, and divides the initial three-dimensional model of the slope into a slide bed and a slide body by using the sliding surface;

[0120] The second division unit divides the slide body into a traction segment, a main slide segment and an anti-slide segment, and generates the three-dimensional model of the slope.

[0121] Based on the above embodiment, the simulation module comprises:

[0122] The determination unit determines the slide bed, the traction segment, the main slide segment and the anti-slide segment as the section to be inverted, and determines the cohesion and the internal friction angle as the shear strength parameters to be inverted;

[0123] The selection unit randomly selects the cohesion value and the internal friction angle for the slide bed, the traction segment, the main slide segment and the anti-slide segment in sequence, and generates a plurality of groups of tests;

[0124] Simulation unit: simulate each group of tests by using simulation software, generate initial stress field and displacement field under the action of gravity;

[0125] Clear the displacement field, and re-generate the slope displacement field in the strength reduction process.

[0126] Based on the above embodiment, the data set construction module comprises:

[0127] Normalization unit: normalize the displacement of the monitoring point and the local safety factor;

[0128] Data set construction unit: construct a data set by taking the normalized displacement of the monitoring point as the input layer, the shear strength parameter of the to-be-inverted section as the first output layer, and the normalized local safety factor as the second output layer;

[0129] Data set division unit: divide the data set into a training set and a test set according to a ratio of 7:3.

[0130] Based on the above embodiment, the training module comprises:

[0131] Initialization unit: initialize the particle swarm, and generate a position vector and a speed for each particle;

[0132] Model construction unit: construct a radial basis neural network, and generate a set of radial basis network parameters from the position vector of each particle;

[0133] Learning unit: input the data set into each set of radial basis network parameters in turn, and obtain the output value of the radial basis network parameter after learning the displacement of the monitoring point by the radial basis neural network parameter;

[0134] First calculation unit: calculate the particle fitness by using the output value of the radial basis network parameter, update the position vector and the speed of the particle according to the particle fitness, and thus obtain the updated radial basis network parameter;

[0135] Second calculation unit: repeatedly calculate the particle fitness by using the updated radial basis network parameter until the calculation number reaches a preset iteration number or the minimum fitness of the particle reaches a preset threshold;

[0136] Generation unit: the parameter inversion model is composed of the radial basis network parameter corresponding to the particle with the minimum fitness.

[0137] Based on the above embodiment, the method further comprises:

[0138] Actual displacement acquisition unit: determine the actual positions of the monitoring points on the slope, and acquire the actual displacements of the monitoring points, wherein the actual displacements of the monitoring points can be acquired by using a total station, a GPS, an inclinometer or the like;

[0139] The inversion analysis unit: the actual displacement of each monitoring point is normalized and input into the parameter inversion model for inversion analysis, to generate the shear strength parameters and local safety factors of the section to be inverted;

[0140] The fitting analysis unit: the actual displacement of the monitoring point is taken as the independent variable, and the local safety factor is taken as the dependent variable for fitting analysis to determine the quantitative functional relationship between the displacement and the local safety factor;

[0141] The analysis model construction unit: an analysis model of displacement-local safety factor is constructed according to the quantitative functional relationship.

[0142] It should be noted that, as for the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment related to the method, and will not be described in detail here.

[0143] Embodiment 3:

[0144] Corresponding to the above method embodiment, the present embodiment also provides a parameter inversion device for slope rock-soil. The parameter inversion device for slope rock-soil described below can be mutually corresponding to the parameter inversion method for slope rock-soil described above.

[0145] Figure 7 is a block diagram of a parameter inversion device 800 for slope rock-soil according to an example embodiment. As shown, the parameter inversion device 800 for slope rock-soil can include a processor 801, a memory 802. The parameter inversion device 800 for slope rock-soil can also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805. Figure 7

[0146] ​The processor 801 is configured to control overall operations of the parameter inversion device 800 for the slope rock-soil, so as to complete all or part of steps in the parameter inversion method for the slope rock-soil. The memory 802 is configured to store various types of data to support operations of the parameter inversion device 800 for the slope rock-soil. For example, the data can include instructions for any application or method operating on the parameter inversion device 800 for the slope rock-soil, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 can include a screen and an audio component. The screen can be a touch screen, for example. The audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 802 or transmitted through the communication component 805. The audio component further includes at least one speaker configured to output audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the parameter inversion device 800 for the slope rock-soil and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include a Wi-Fi module, a Bluetooth module, an NFC module.

[0147] In an example embodiment, the parameter inversion device 800 for slope rock-soil can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the parameter inversion method for slope rock-soil as described above.

[0148] In another example embodiment, a computer readable storage medium including program instructions is also provided, which when executed by a processor, implement the steps of the parameter inversion method for slope rock-soil as described above. For example, the computer readable storage medium can be the memory 802 as described above including program instructions executable by the processor 801 of the parameter inversion device 800 for slope rock-soil to complete the parameter inversion method for slope rock-soil as described above.

[0149] Embodiment 4:

[0150] Corresponding to the method embodiments above, in this embodiment, a readable storage medium is also provided, which can be referred to each other below and above in the description of the parameter inversion method for slope rock-soil.

[0151] A readable storage medium, on which a computer program is stored, when executed by a processor, implements the steps of the parameter inversion method for slope rock-soil of the method embodiments as described above.

[0152] The readable storage medium can be specifically a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various readable storage media that can store program codes.

[0153] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

[0154] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A parameter inversion method for slope rock and soil, characterized in that: include: Obtain the surface topography and soil layer boundaries of the slope, and build a three-dimensional slope model in the simulation software based on the surface topography and soil layer decomposition of the slope; Determine the section to be inverted of the three-dimensional slope model, randomly assign values ​​to the shear strength parameters of the section to be inverted, and simulate the three-dimensional slope model using simulation software; Arrange multiple monitoring points in the section to be inverted of the 3D slope model, collect the displacement and stress of the monitoring points during the simulation, and use the stress of the monitoring points to calculate the local safety factor of the section to be inverted; The dataset is constructed by taking the displacement of the monitoring point as the input layer and the shear strength parameters and local safety factor of the section to be inverted as the output layer; Constructing a radial basis function neural network, and using the data set to train the radial basis function neural network to obtain a trained parameter inversion model, including: Initialize the particle swarm and generate the position vector and velocity for each particle; Construct a radial basis neural network and generate a set of radial basis network parameters from the position vector of each particle; The data set is input into each set of radial basis network parameters in turn, and the output value of the radial basis network parameters is obtained after the displacement of the monitoring point is learned by the radial basis network parameters; The particle fitness is calculated using the output value of the radial basis network parameters, and the particle position vector and velocity are updated according to the particle fitness, thereby obtaining the updated radial basis network parameters; The particle fitness is repeatedly calculated using the updated radial basis network parameters until the number of calculations reaches a preset number of iterations or the minimum fitness of the particle reaches a preset threshold; The parameter inversion model is composed of the radial basis network parameters corresponding to the particles with the minimum fitness; The method of constructing a data set by using the displacement of the monitoring point as the input layer and the shear strength parameter and local safety factor of the section to be inverted as the output layer includes: Normalize the displacement of monitoring points and local safety factors; The normalized monitoring point displacement is used as the input layer, the shear strength parameters of the section to be inverted are used as the first output layer, and the normalized local safety factor is used as the second output layer to construct the data set.

2. The parameter inversion method of slope rock and soil according to claim 1 is characterized in that , obtain the surface topography and soil layer boundary of the slope, and build a three-dimensional slope model in the simulation software according to the surface topography and soil layer decomposition of the slope, including: Use contour lines to measure the surface topography of the slope and use soil drilling to determine the boundaries of the soil layers; Establish an initial three-dimensional slope model in the simulation software based on the slope's surface topography and soil layer decomposition; The plastic zone of the initial three-dimensional slope model is calculated based on the strength reduction method, and a sliding surface is formed by the plastic zone that penetrates the slope body of the initial three-dimensional slope model. The sliding surface divides the initial three-dimensional slope model into a sliding bed and a sliding body. The sliding body is divided into traction section, main sliding section and anti-sliding section, and a three-dimensional slope model is generated.

3. The parameter inversion method of slope rock and soil according to claim 2 is characterized in that ,determine the section to be inverted and the shear strength parameters of the slope 3D model, randomly assign values ​​to the shear strength parameters of the section to be inverted, and simulate the slope 3D model using simulation software, including: The sliding bed, traction section, main sliding section and anti-sliding section are taken as sections to be inverted, and the cohesion and internal friction angle are taken as shear strength parameters to be inverted. The cohesion values ​​and internal friction angles are randomly selected for the slider bed, traction section, main sliding section, and anti-sliding section in turn to generate several groups of tests; Each set of tests was simulated using simulation software to generate initial stress and displacement fields under the action of gravity; The displacement field is cleared and the slope displacement field is regenerated during the strength reduction process.

4. The parameter inversion method of slope rock and soil according to claim 1 is characterized in that ,The displacement of the monitoring point is used as the input layer, and the shear strength parameters and local safety factors of the ,section to be inverted are used as the output layer to construct a dataset, including: The dataset is divided into training set and test set in a ratio of 7:

3.

5. A parameter inversion system for slope rock and soil, used in the parameter inversion method for slope rock and soil according to any one of claims 1 to 4, characterized in that: include: Model building module: obtain the surface topography and soil layer boundaries of the slope, and build a three-dimensional slope model in the simulation software based on the surface topography and soil layer decomposition of the slope; Simulation module: determines the section to be inverted of the slope 3D model, randomly assigns values ​​to the shear strength parameters of the section to be inverted, and simulates the slope 3D model using simulation software; Calculation module: Arrange multiple monitoring points in the section to be inverted of the 3D slope model, collect the displacement and stress of the monitoring points during the simulation process, and use the stress of the monitoring points to calculate the local safety factor of the section to be inverted; Dataset construction module: The displacement of the monitoring point is used as the input layer, and the shear strength parameters and local safety factors of the section to be inverted are used as the output layer to construct the dataset; Training module: constructing a radial basis function neural network, and using the data set to train the radial basis function neural network to obtain a trained parameter inversion model; The data set construction module includes: Normalization unit: normalizes the displacement of monitoring points and local safety factors; Dataset construction unit: The normalized monitoring point displacement is used as the input layer, the shear strength parameters of the section to be inverted are used as the first output layer, and the normalized local safety factor is used as the second output layer to construct the dataset.

6. The slope rock and soil parameter inversion system according to claim 5, characterized in that: The model building module includes: Measurement unit: Use contour lines to measure the surface topography of the slope and use soil drilling to determine the boundaries of the soil layers; 3D model building unit: build an initial 3D slope model in simulation software based on the surface topography and soil layer decomposition of the slope; The first division unit calculates the plastic zone of the initial three-dimensional slope model based on the strength reduction method, and forms a sliding surface that penetrates the slope of the initial three-dimensional slope model from the plastic zone. The sliding surface divides the initial three-dimensional slope model into a sliding bed and a sliding body. The second division unit: divide the sliding body into traction segment, main sliding segment and anti-sliding segment to generate a three-dimensional slope model.

7. The slope rock and soil parameter inversion system according to claim 6, characterized in that: The simulation module includes: Determine the unit: the sliding bed, traction section, main sliding section and anti-sliding section are taken as the sections to be inverted, and the cohesion and internal friction angle are taken as the shear strength parameters to be inverted; Select units: randomly select cohesion values ​​and internal friction angles for the slider bed, traction section, main sliding section, and anti-sliding section in turn to generate several groups of tests; Simulation unit: Use simulation software to simulate each set of tests and generate initial stress and displacement fields under the action of gravity; The displacement field is cleared and the slope displacement field is regenerated during the strength reduction process.

8. The slope rock and soil parameter inversion system according to claim 5, characterized in that: The data set construction module also includes: Dataset division unit: The dataset is divided into training set and test set in a ratio of 7:3.

Images