A real-time detection method for geotechnical mechanical parameters of a slope of an engineering site to be detected

Abstract

The present invention provides a real-time detection method for geotechnical mechanical parameters of a slope of an engineering site to be detected. The method includes: conducting a field survey at the engineering site to be detected to obtain the actual geotechnical mechanical parameters of the slope of the engineering site to be detected; the detection device obtains the monitoring data of the slope of the engineering site to be detected and transmits the monitoring data to the processor, and the processor continuously tries to calculate and invert the geotechnical mechanical parameters by using a numerical analysis model until the deviation between the inverted geotechnical mechanical parameters and the actual geotechnical mechanical parameters meets the accuracy requirements; taking the inverted geotechnical mechanical parameters as training samples and inputting them into the BP-GA model for training until the accuracy requirements are met to obtain a trained BP-GA model; the processor inputs the monitoring data of the slope of the engineering site to be detected received in real time into the trained BP-GA model, and the BP-GA model outputs the real-time geotechnical mechanical parameters of the slope of the engineering site to be detected. The embodiment of the present invention can obtain dynamic geotechnical parameters based on real-time monitoring data.

Description

Technical Field

[0001] The invention relates to the technical field of rock and soil parameter analysis, and in particular to a real-time detection method for rock and soil mechanical parameters of a slope of an engineering site to be detected. Background Art

[0002] The rapid construction of railways and highways is accompanied by the emergence of a large number of high slopes. The stability of high slopes directly affects the operational safety of railways and highways, so it is particularly important to adopt appropriate reinforcement and management plans for high slopes. The selection of management measures and the specific design of management measures are based on geotechnical mechanics parameters.

[0003] Due to the complexity of geotechnical materials, the methods for obtaining geotechnical parameters have certain limitations to a greater or lesser extent. One method is based on indoor tests. This method is based on field survey sampling, and various mechanical tests are carried out in the laboratory to obtain geotechnical parameter data. However, this method cannot fully consider the size effect of rocks and joints and fissures. For soil, there are problems such as disturbance of soil samples. In addition, survey sampling is limited by cost, and the survey area may be much smaller than the study area, which cannot fully reflect the variability of geotechnical materials. Another method is based on field tests. The biggest problem with field tests is that they are limited by cost and cannot be tested in the entire study area. In addition, field tests may have a certain impact on the mechanical properties of rock and soil.

[0004] With the continuous development of monitoring and communication technologies, many projects have carried out a large number of monitoring on potentially dangerous slopes. The monitoring data can reflect the stability of the slope in real time. The most direct way is to obtain monitoring data such as surface displacement and deep displacement. The displacement of the slope is the most direct manifestation of slope deformation.

[0005] The stability analysis of slopes and the design of treatment plans are basically based on numerical simulation. In numerical simulation, the mechanical parameters of rock and soil are important input parameters. The accuracy of the values ​​of rock and soil mechanical parameters is directly related to the stability analysis results and the design of treatment plans.

[0006] At present, the existing methods for obtaining rock mass mechanical parameters include indoor and outdoor tests, engineering analogy, rock mass classification method, inversion analysis and numerical simulation. In recent years, with the rapid development of fuzzy mathematics and neural networks, some people have gradually begun to use neural network methods to invert rock and soil mechanical parameters, that is, based on test data or numerical simulation analysis data, sufficient c (cohesion) is obtained. (internal friction angle), E (elastic modulus), μ (Poisson's ratio), k (slope safety factor), ω (water content) and other rock and soil parameter data. Waiting for inversion data As the output layer, with other data as the input layer, the non-linear relationship between them is obtained using neural network algorithms, and then the trained neural network is used to analyze the values of similar projects.

[0007] The disadvantages of the method for obtaining rock mass mechanical parameters through indoor and outdoor tests in the above-mentioned prior art are as follows: Although the indoor test method can obtain relatively accurate geotechnical mechanical parameters, it cannot accurately consider the influence of rock size effect on rock mass mechanical parameters. For soil, it may cause disturbance to soil samples and cannot accurately represent the mechanical properties of soil in the actual site; In-situ tests can relatively well reflect the natural characteristics of geotechnical bodies and can reduce the influence of rock mass size effect to a certain extent. However, in-situ tests generally take a long time, cost a lot, and the test results have great discreteness, and are usually only applied in important or large-scale projects.

[0008] Engineering geology can obtain geotechnical mechanical parameters relatively quickly, but limited by the differences in the understanding of geological personnel themselves, different people may have different results for the same site, which is greatly affected by subjective factors, and the data is basically relatively conservative. Although the rock mass classification method considers many influencing factors, the acquisition of these influencing factors themselves is limited not only by on-site exploration conditions but also by the subjective cognition of geological personnel in aspects such as the degree of joint surface combination and the self-stability of slopes.

[0009] The basis of the back-analysis method based on measured data is to be able to understand or reasonably estimate rock mass parameters in advance for trial calculations, and it is also necessary to reasonably list the functional relationship between known data and the data to be obtained, which is relatively difficult in itself; When using neural network algorithms for back-analysis, the accuracy of basic data has a great influence on the analysis results, but the acquisition of basic data itself is also a difficult problem. Summary of the Invention

[0010] An embodiment of the present invention provides a real-time detection method for geotechnical mechanical parameters of a slope of a to-be-detected engineering site to overcome the problems of the prior art.

[0011] To achieve the above object, the present invention adopts the following technical solutions.

[0012] A real-time detection method for geotechnical mechanical parameters of a slope of a to-be-detected engineering site includes:

[0013] Conduct on-site reconnaissance at the to-be-detected engineering site to obtain the actual geotechnical mechanical parameters of the slope of the to-be-detected engineering site;

[0014] The detection device obtains the monitoring data of the slope of the engineering site to be detected, and transmits the monitoring data to the processor. The processor continuously tries to calculate and invert the geotechnical mechanical parameters by using a numerical analysis model until the deviation between the inverted geotechnical mechanical parameters and the actual geotechnical mechanical parameters meets the accuracy requirements;

[0015] Taking the inverted geotechnical mechanical parameters as training samples, input them into the BP-GA model for training until the accuracy requirements are met, and obtain the trained BP-GA model;

[0016] The processor inputs the monitoring data of the slope of the engineering site to be detected received in real time into the trained BP-GA model, and the BP-GA model outputs the real-time geotechnical mechanical parameters of the slope of the engineering site to be detected.

[0017] Preferably, on-site investigation is carried out at the engineering site to be detected to obtain the actual geotechnical mechanical parameters of the slope of the engineering site to be detected, including:

[0018] Carry out on-site investigation for the engineering site to be detected, obtain rock cores and soil samples, and conduct triaxial compression tests on the rock cores and soil samples indoors to obtain the corresponding actual geotechnical mechanical parameters. The actual geotechnical mechanical parameters include cohesion, internal friction angle, elastic modulus and compressive strength.

[0019] Preferably, the detection device obtains the monitoring data of the slope of the engineering site to be detected, and transmits the monitoring data to the processor. The processor continuously tries to calculate and invert the geotechnical mechanical parameters by using a numerical analysis model until the deviation between the inverted geotechnical mechanical parameters and the actual geotechnical mechanical parameters meets the accuracy requirements, including:

[0020] Arrange detection devices on the slope of the engineering site to be detected to obtain the monitoring data of the slope of the engineering site to be detected. The monitoring data includes surface displacement and rainfall, and the detection device transmits the monitoring data to the processor in real time through the network;

[0021] The processor uses the finite element analysis software Flac3d to establish a numerical analysis model, and uses the numerical analysis model to continuously try to calculate and invert the geotechnical mechanical parameters based on the monitoring data and the test data determined by indoor and outdoor tests, with displacement as the known quantity;

[0022] The processor calculates the deviation according to the following formula:

[0023] Deviation = (inverted geotechnical mechanical parameters - actual geotechnical mechanical parameters) / actual geotechnical mechanical parameters

[0024] Judge whether the deviation is less than the set judgment threshold. If so, determine that the inverted geotechnical mechanical parameters meet the accuracy requirements; otherwise, return to recalculate until the deviation is less than the set judgment threshold, and obtain the trial-calculated and inverted geotechnical mechanical parameters that meet the accuracy requirements.

[0025] Preferably, the inverse geotechnical mechanical parameters are used as training samples and input into the BP-GA model for training until the accuracy requirement is met, and a trained BP-GA model is obtained, including:

[0026] The processor uses the monitoring data that meets the accuracy requirement and the corresponding geotechnical mechanical parameters as training samples. The displacement value, rainfall, type of rock and soil mass, compression modulus, Poisson's ratio, and elastic modulus are used as the input layer neurons, and the cohesion and internal friction angle are used as the output layer neurons. The number of neurons in the middle hidden layer is determined by (the number of input layers + the number of output layers) / 2 to (2 times the number of input layer neurons + 1), and the BP-GA model is trained until the accuracy requirement is met;

[0027] During the training process, the output data of the BP-GA model are the cohesion and internal friction angle of each layer of rock and soil mass corresponding to the input layer data. The training of the BP-GA model takes the root mean square error less than 0.01 as the judgment criterion. If the judgment criterion is met, the model training is completed; if not, the number of hidden neurons in the middle layer is readjusted until the accuracy requirement is met, and a trained BP-GA model is obtained.

[0028] It can be seen from the technical solutions provided by the embodiments of the present invention above that the embodiments of the present invention can obtain dynamic geotechnical parameters based on real-time monitoring data through the BP (error backpropagation neural network)-GA (genetic algorithm) model. It overcomes the problems of high cost, low efficiency, and discrete results in outdoor tests, and can also avoid the influence of subjective factors in the engineering analogy method.

[0029] Additional aspects and advantages of the present invention will be given in part in the following description, which will become apparent from the following description, or can be understood through the practice of the present invention. Brief Description of the Drawings

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a schematic diagram of the implementation principle of a real-time detection method for geotechnical mechanical parameters of a slope of a to-be-detected engineering site provided by an embodiment of the present invention. Detailed Embodiments

[0032] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0033] Those skilled in the art of the present technology can understand that unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or coupling. The phrase "and / or" used herein includes any and all combinations of any one of the one or more related listed items.

[0034] Those skilled in the art of the present technology can understand that unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the art to which the present invention belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted with an idealized or overly formal meaning unless defined as here.

[0035] For the convenience of understanding the embodiments of the present invention, the following will further explain with several specific embodiments as examples in conjunction with the accompanying drawings, and each embodiment does not constitute a limitation to the embodiments of the present invention.

[0036] In order to overcome the various deficiencies of the previous methods for obtaining mechanical parameters along the way, especially for obtaining dynamic geotechnical parameters, the embodiments of the present invention provide a real-time detection method for geotechnical mechanical parameters of the slopes of the engineering sites to be detected. Based on the on-site monitoring data, this method first uses the displacement inversion method to obtain the mechanical parameters of the slope rock and soil mass, and then, based on this, uses the BP-GA algorithm to obtain the direct relationship between the displacement and the mechanical parameters of the rock and soil mass, so as to possibly obtain more realistic mechanical parameters of the rock and soil mass very well.

[0037] The implementation principle diagram of a real-time detection method for geotechnical mechanical parameters of the slopes of the engineering sites to be detected provided by the embodiments of the present invention is as Figure 1 shown, and includes the following processing steps:

[0038] Step S1: Conduct on-site investigation for the engineering site to be detected, obtain core samples and soil samples, etc., and conduct triaxial compression tests on the core samples and soil samples indoors to obtain actual geotechnical mechanical parameters such as cohesion, internal friction angle, elastic modulus, and compressive strength.

[0039] To make up for the size effect problem of indoor tests, appropriate load tests, in-situ direct shear tests, etc. can also be added to obtain geotechnical mechanical parameters for mutual correction with indoor tests.

[0040] Step S2: According to the on-site investigation situation, determine the main picture of the slope of the engineering site to be detected, deploy reasonable detection equipment at the slope site, and obtain monitoring data such as surface displacement and rainfall of the slope through the detection equipment. The detection equipment transmits the monitoring data to the processor in real time through the GNSS (Global Navigation Satellite System) network.

[0041] Step S3: The processor uses the finite element analysis software Flac3d to establish a numerical analysis model, and based on the monitoring data and the test data determined by indoor and outdoor tests using the numerical analysis model, gives a reasonable parameter trial calculation range. Taking displacement as the known quantity, continuously trial calculate and invert the geotechnical mechanical parameters.

[0042] Calculate the deviation according to the following formula:

[0043] Deviation = (inverted geotechnical mechanical parameter - actual geotechnical mechanical parameter) / actual geotechnical mechanical parameter

[0044] When the deviation < 5%, it is judged that the above inverted geotechnical mechanical parameters meet the accuracy requirements, otherwise return to recalculate until the accuracy requirements are met. In this way, the geotechnical mechanical parameters corresponding to different displacements are determined.

[0045] Step S4: The processor uses the inverted geotechnical mechanical parameters obtained in Step S3 as training samples, takes the displacement value, rainfall, type of rock and soil mass, compression modulus, Poisson's ratio, and elastic modulus as input layer neurons, and cohesion and internal friction angle as output layer neurons. The number of intermediate hidden neurons is determined by (number of input layer neurons + number of output layer neurons) / 2 to (2 times the number of input layer neurons + 1), and is input into the BP - GA model for training. The above displacement value and rainfall are monitoring data, the type of rock and soil mass is the initial exploration conclusion, and the compression modulus, Poisson's ratio, and elastic modulus are empirical data (reference data are generally provided in the exploration report).

[0046] The output data of the BP - GA model during the training process are the cohesion and internal friction angle of each layer of rock and soil mass corresponding to the input layer data, and are stored in the output layer neurons.

[0047] The BP-GA model is a neural network model improved by the genetic algorithm. The genetic algorithm is designed based on the evolution law of organisms in nature. It is a computational model that simulates the natural selection of Darwin's theory of biological evolution and the biological evolution process of genetic mechanism. It is a method for searching the optimal solution by simulating the natural evolution process. By optimizing the neural network algorithm with the genetic algorithm, the weights of each input factor can be optimized to better conform to the actual situation. Finally, the training model takes the root mean square error less than 0.01 as the judgment standard. If it meets the requirement, the model training is completed. If it does not meet the requirement, the number of hidden neurons in the middle layer is readjusted until the accuracy requirement is reached, and the trained BP-GA model is obtained.

[0048] The mean square error (MSE) is a conventional mathematical definition, which is the average of the sum of the squares of the differences between each data and the true value.

[0049]

[0050] X i represents the sample value of the i-th sample, and Y i represents the true value of the i-th sample.

[0051] Step S5: Based on the BP-GA model trained in step S4, the processor inputs the real-time monitored data into the trained BP-GA model, and the BP-GA model outputs the real-time geotechnical mechanics parameters.

[0052] The trained BP-GA model is a mature and predictable neural network model. When the values of each neuron in the input layer are input, the corresponding geotechnical mechanics parameters can be obtained by using the trained neural network. The monitored data refers to the displacement value and rainfall, and only needs to be input together with other parameter values. There will be a data normalization function in the algorithm.

[0053] In summary, the embodiment of the present invention overcomes the problems of size effect, disturbance, etc. in obtaining geotechnical parameters by indoor tests, overcomes the problems of high cost, low efficiency, and discrete results in outdoor tests, and can also avoid the subjective factor influence of the engineering analogy method. This method can obtain relatively accurate geotechnical mechanics parameters even for people without a strong geological background.

[0054] In the past, geotechnical mechanics parameters were mainly static. Based on real-time monitored data, the present invention can obtain dynamic geotechnical parameters through the BP-GA model.

[0055] Those of ordinary skill in the art can understand that the drawings are only schematic diagrams of an embodiment, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0056] As can be seen from the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0057] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments. The device and system embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0058] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A real-time detection method for geotechnical mechanical parameters of a slope of an engineering site to be detected, characterized in that, it includes: conducting on-site reconnaissance at the engineering site to be detected to obtain the actual geotechnical mechanical parameters of the slope of the engineering site to be detected; the detection device obtains the monitoring data of the slope of the engineering site to be detected, transmits the monitoring data to the processor, and the processor continuously calculates and inversely analyzes the geotechnical mechanical parameters using a numerical analysis model until the deviation between the inversely analyzed geotechnical mechanical parameters and the actual geotechnical mechanical parameters meets the accuracy requirements; using the inversely analyzed geotechnical mechanical parameters as training samples, inputting them into the BP-GA model for training until the accuracy requirements are met, and obtaining a trained BP-GA model; the processor inputs the monitoring data of the slope of the engineering site to be detected received in real time into the trained BP-GA model, and the BP-GA model outputs the real-time geotechnical mechanical parameters of the slope of the engineering site to be detected; the detection device obtains the monitoring data of the slope of the engineering site to be detected, transmits the monitoring data to the processor, and the processor continuously calculates and inversely analyzes the geotechnical mechanical parameters using a numerical analysis model until the deviation between the inversely analyzed geotechnical mechanical parameters and the actual geotechnical mechanical parameters meets the accuracy requirements, including: deploying detection devices on the slope of the engineering site to be detected to obtain the monitoring data of the slope of the engineering site to be detected, where the monitoring data includes surface displacement and rainfall, and the detection device transmits the monitoring data to the processor in real time through a network; the processor uses the finite element analysis software Flac3d to establish a numerical analysis model, and based on the monitoring data and the test data determined by indoor and outdoor tests using the numerical analysis model, with displacement as the known quantity, continuously calculates and inversely analyzes the geotechnical mechanical parameters; the processor calculates the deviation according to the following formula: Deviation = (Inversely analyzed geotechnical mechanical parameters - Actual geotechnical mechanical parameters) / Actual geotechnical mechanical parameters; judging whether the deviation is less than the set judgment threshold. If so, it is determined that the inversely analyzed geotechnical mechanical parameters meet the accuracy requirements; otherwise, return to recalculate until the deviation is less than the set judgment threshold to obtain the inversely analyzed geotechnical mechanical parameters that meet the accuracy requirements; using the inversely analyzed geotechnical mechanical parameters as training samples, inputting them into the BP-GA model for training until the accuracy requirements are met, and obtaining a trained BP-GA model, including: the processor uses the monitoring data that meets the accuracy requirements and the corresponding geotechnical mechanical parameters as training samples, takes the displacement value, rainfall, soil mass type, compression modulus, Poisson's ratio, and elastic modulus as input layer neurons, and cohesion and internal friction angle as output layer neurons. The number of neurons in the middle hidden layer is determined by (Number of input layer + Number of output layer) / 2 to (2 times the number of input layer neurons + 1), and conducts training on the BP-GA model until the accuracy requirements are met; the displacement value and rainfall are monitoring data, the soil mass type is the initial exploration conclusion, and the compression modulus, Poisson's ratio, and elastic modulus are empirical data; During the training process, the output data of the BP-GA model are the cohesion and internal friction angle of each layer of rock and soil corresponding to the input layer data. The training of the BP-GA model is judged by the root mean square error being less than 0.

01. If the judgment criterion is met, the model training is completed; if not, the number of hidden neurons in the middle layer is readjusted until the accuracy requirement is reached, and a trained BP-GA model is obtained; The mean square error MSE is the average of the sum of the squares of the differences between each data and the true value; X i represents the sample value of the i-th sample, Y i represents the true value of the i-th sample.

2. The method according to claim 1, characterized in that conducting on-site reconnaissance at the engineering site to be detected to obtain the actual rock and soil mechanical parameters of the slope of the engineering site to be detected, including: conducting on-site reconnaissance at the engineering site to be detected to obtain rock cores and soil samples, and conducting triaxial compression tests on the rock cores and soil samples indoors to obtain the corresponding actual rock and soil mechanical parameters, which include cohesion, internal friction angle, elastic modulus, and compressive strength.

Images