Tunnel construction parameter adjustment method, device and equipment based on spatial variability

Abstract

The application provides a tunnel construction parameter adjustment method, device and equipment based on spatial variability, relates to the technical field of data processing, and comprises the following steps: obtaining an analytical mapping function according to a tunnel design scale and a preset stratum correlation length based on quantile theory of probability statistics; constructing a conditional random field of a stratum in an advancing direction through multi-source geological sampling data based on a Kriging interpolation algorithm; obtaining a local variation coefficient in an influence area of an excavation face according to the conditional random field, and obtaining an equivalent elastic modulus through the local variation coefficient by using the analytical mapping function; inputting the equivalent elastic modulus into a preset deterministic numerical model for solving to obtain a tunnel displacement prediction value; and performing self-adaptive compensation decision on a current tunnel construction parameter by using the tunnel displacement prediction value to obtain a target tunnel construction parameter. The application realizes that the tunnel construction parameter is more in line with actual construction conditions.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method, apparatus, and equipment for adjusting tunnel construction parameters based on spatial variability. Background Technology

[0002] Tunnel construction is a complex systems engineering project, requiring the selection of appropriate excavation methods and support technologies based on geological conditions. With the development of engineering technology, modern tunnel construction has formed various mature construction methods and intelligent management systems. Currently, the main approach involves preliminary geological surveys before construction, using empirical parameters or statistical averages for numerical simulation to model changes in geological conditions during construction, and then designing parameters for the tunnel construction process. This requires thousands of repeated calculations to obtain the probability distribution characteristics, resulting in predictions that lag significantly behind the construction schedule. Furthermore, as a naturally occurring heterogeneous material, soil and rock exhibit significant spatial variability in their mechanical parameters. Traditional deterministic models ignore this spatial variability, leading to large deviations between tunnel construction parameters and actual working conditions. Summary of the Invention

[0003] The problem addressed by this invention is to solve at least one of the problems described above.

[0004] To address the aforementioned problems, this invention provides a method, apparatus, and equipment for adjusting tunnel construction parameters based on spatial variability.

[0005] In a first aspect, the present invention provides a method for adjusting tunnel construction parameters based on spatial variability, comprising: Based on the quantile theory of probability statistics, an analytical mapping function is obtained according to the tunnel design scale and the preset relevant length of the strata; Based on the Kriging interpolation algorithm, a conditional random field of strata in the forward direction is constructed using multi-source geological sampling data; The local coefficient of variation within the influence zone of the excavation face is obtained based on the conditional random field, and the equivalent elastic modulus is obtained through the local coefficient of variation using the analytical mapping function. The equivalent elastic modulus is input into a preset deterministic numerical model for solution to obtain the predicted tunnel displacement value. The predicted tunnel displacement values ​​are used to make adaptive compensation decisions for the current tunnel construction parameters to obtain the target tunnel construction parameters.

[0006] Optionally, obtaining the analytical mapping function based on the tunnel design dimensions and the preset geological stratum length includes: Based on Vanmarcke's local averaging theory, a variance reduction function is obtained according to the tunnel design scale and the preset stratum-related length. The variance reduction function includes: , Wherein, γ(L) is the variance reduction function, L is the tunnel design scale, and θ is the preset stratum-related length; The analytical mapping function is obtained based on the variance reduction function; The parsing mapping function includes: , Where λ is the reduction factor, COV is the coefficient of variation, and k is the quantile of the standard normal distribution.

[0007] Optionally, the construction of a conditional random field of strata along the forward direction using multi-source geological sampling data includes: A known data vector is obtained based on the multi-source geological sampling data, wherein the known data vector is used to represent the spatial three-dimensional coordinate set of multiple multi-source geological sampling points and the corresponding measured values ​​of stratigraphic parameters; An unconditional random field is used to simulate the entire spatial computational region to obtain an unconditional simulation vector, wherein the unconditional simulation vector is used to represent the simulated values ​​of stratigraphic parameters of multiple multi-source geological sampling points; The known data vector and the unconditional simulation vector are used as condition points to perform interpolation calculations on the full-space computational region to obtain the corresponding measured estimation field and simulation estimation field. The conditional random field is obtained using the unconditional random field based on the measured estimated field and the simulated estimated field.

[0008] Optionally, the conditional random field includes: , Among them, Z c Let Z be the conditional random field. K * Z represents the measured estimated field. u Let Z be the unconditional random field. uK * The simulated estimated field.

[0009] Optionally, obtaining the local variation coefficient within the excavation face influence zone based on the conditional random field includes: By extracting the elastic modulus values ​​of the center points of all finite element mesh units in the conditional random field, a sample set of elastic modulus values ​​is obtained. The local mean and local standard deviation are obtained from the sample set of elastic modulus values. The local mean includes: , Where, μloc E is the local mean. i Let N be the sample set of elastic modulus values, where N is the total number of samples; The local standard deviation includes: , Where, σ loc The local standard deviation; The local coefficient of variation is obtained based on the local mean and the local standard deviation; The local coefficient of variation includes: , Among them, COV loc is the local coefficient of variation.

[0010] Optionally, obtaining the equivalent elastic modulus using the analytical mapping function through the local coefficient of variation includes: Obtain the current tunnel excavation scale and the relevant length of the current strata; The current variance reduction function is obtained by using the current tunnel excavation scale and the current stratum length. The local coefficient of variation and the current variance reduction function are input into the analytical mapping function to obtain the current reduction coefficient; The low-value characteristic of the parameter is used as the equivalent elastic modulus by utilizing the current reduction factor; The equivalent elastic modulus includes: , Among them, E eq Let λ be the equivalent elastic modulus. loc Let μ be the current reduction factor. loc This refers to the local mean.

[0011] Optionally, the step of using the predicted tunnel displacement value to make adaptive compensation decisions on the current tunnel construction parameters to obtain the target tunnel construction parameters includes: Obtain the support mechanical parameters to be adjusted; Based on the predicted tunnel displacement values, an influence analysis is performed on the support mechanical parameters to obtain a sensitivity matrix; The difference between the predicted tunnel displacement value and the preset safety threshold is calculated to obtain the deviation vector; The mechanical compensation amount is obtained by using the sensitivity matrix and the deviation vector; The mechanical compensation amount includes: , Wherein, △P is the mechanical compensation amount, S is the sensitivity matrix, and △U is the deviation vector; The target tunnel construction parameters are obtained by adjusting the current tunnel construction parameters using the mechanical compensation amount.

[0012] Secondly, the present invention provides a tunnel construction parameter adjustment device based on spatial variability, comprising: an analytical mapping function acquisition module, used to obtain an analytical mapping function based on the quantile theory of probability statistics, according to the tunnel design scale and the preset stratum related length; The Conditional Random Field (CRF) construction module is used to construct a CRF of the stratigraphic direction based on multi-source geological sampling data using the Kriging interpolation algorithm. The equivalent elastic modulus acquisition module is used to obtain the local variation coefficient within the influence zone of the excavation face based on the conditional random field, and to obtain the equivalent elastic modulus through the local variation coefficient using the analytical mapping function. The tunnel displacement prediction value acquisition module is used to input the equivalent elastic modulus into a preset deterministic numerical model for solution to obtain the tunnel displacement prediction value. The target tunnel construction parameter acquisition module is used to make adaptive compensation decisions on the current tunnel construction parameters using the predicted tunnel displacement values ​​to obtain the target tunnel construction parameters.

[0013] Thirdly, the present invention provides an electronic device, including a memory and a processor; The memory is used to store computer programs; The processor is configured to, when executing the computer program, implement the tunnel construction parameter adjustment method based on spatial variability as described in the first aspect.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the tunnel construction parameter adjustment method based on spatial variability as described in the first aspect.

[0015] The beneficial effects of the tunnel construction parameter adjustment method, device, and equipment based on spatial variability of the present invention are as follows: By introducing the quantile theory of probability statistics, an analytical mapping function is constructed from high-dimensional random statistical parameters to deterministic equivalent parameters based on the tunnel design scale and the preset stratum length, taking into account the spatial variability characteristics of stratum parameters. A conditional random field (CRF) of the strata in the forward direction is constructed by fusing multi-source geological sampling data using the Kriging interpolation algorithm, and local weakening characteristics in front of the excavation are captured in real time using CRF technology. The local variation coefficients within the excavation face influence zone are obtained based on the CRF, and the analytical mapping function replaces the thousands of Monte Carlo simulations in traditional stochastic finite element methods, improving parameter simulation efficiency and ensuring real-time data processing. The equivalent elastic modulus is input into a preset deterministic numerical model for solution, obtaining the predicted tunnel displacement value, providing a reliable basis for subsequent construction parameter adjustments. The predicted tunnel displacement value is used to back-calculate the mechanical compensation amount, and adaptive compensation decisions are made on the current tunnel construction parameters to obtain the target tunnel construction parameters, which conform to the actual construction conditions. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a method for adjusting tunnel construction parameters based on spatial variability according to an embodiment of the present invention. Figure 2 This is a schematic diagram of a tunnel construction parameter adjustment device based on spatial variability according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0018] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0019] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to"; the term "based on" means "at least partially based on"; the term "one embodiment" means "at least one embodiment"; and the term "another embodiment" means "at least one additional embodiment". Definitions of other terms will be given in the following description.

[0020] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for adjusting tunnel construction parameters based on spatial variability, comprising: Step 110: Based on the quantile theory of probability statistics, an analytical mapping function is obtained according to the tunnel design scale and the preset stratum length.

[0022] Specifically, firstly, based on the tunnel design dimensions and the pre-set geological length, a variance reduction function is constructed using Vanmarcke's local averaging theory. Then, based on the quantile theory of probability statistics, an analytical mapping function between the loss coefficient and the coefficient of variation (COV) is constructed using the variance reduction function, thereby establishing a theoretical operator for mapping from random statistical parameters to deterministic equivalent parameters.

[0023] Step 120: Based on the Kriging interpolation algorithm, construct a conditional random field of the strata in the forward direction using multi-source geological sampling data.

[0024] Specifically, the Kriging interpolation algorithm, also known as the spatial local estimation method, is an optimized spatial interpolation technique based on geostatistics. The core of the Kriging algorithm lies in the variogram function, which quantifies the spatial correlation between sample points to construct a mathematical model describing the spatial variation of variables. Real-time acquisition of multi-source geological sampling data is crucial. This multi-source geological sampling data includes at least one of the following: monitoring while drilling (MWD) parameters, advanced horizontal borehole core parameters, in-hole imaging joint statistics, and static cone penetration test (CPT) measured data. Using the measured values ​​at the sampling points as hard constraints, the Kriging interpolation algorithm is used to construct a conditional random field for the strata ahead of the tunnel, ensuring that the variance of the random field at the observation points is zero, thereby accurately capturing the local weakening characteristics of the strata ahead.

[0025] Step 130: Obtain the local coefficient of variation within the influence zone of the excavation face based on the conditional random field, and use the analytical mapping function to obtain the equivalent elastic modulus through the local coefficient of variation.

[0026] Specifically, by extracting the elastic modulus values ​​of the center points of all finite element mesh units in the conditional random field, an elastic modulus value sample set is obtained. The local mean and local coefficient of variation of the elastic modulus value sample set in the influence zone of the excavation face are calculated in real time. The equivalent elastic modulus is then calculated instantaneously through the analytical mapping function.

[0027] Step 140: Input the equivalent elastic modulus into a preset deterministic numerical model for solution to obtain the predicted tunnel displacement value.

[0028] In some more specific embodiments, the equivalent elastic modulus is substituted into a preset deterministic numerical model for a single, rapid solution, outputting a tunnel displacement prediction value with a preset confidence level. Since the loss coefficient is constructed using the standard normal quantile k=1.645 corresponding to the confidence level Q (default 95%), the equivalent elastic modulus calculated from the loss coefficient itself represents the characteristic value of the soil parameter at the "low end" of the 95% confidence level. The tunnel displacement prediction value calculated by inputting the equivalent elastic modulus into the preset deterministic numerical model automatically has the same confidence level, i.e., the actual displacement exceeds U... predict The probability is less than 5%. This is safer than traditional mean deterministic analysis (with a risk probability of about 50%), and it can obtain predictive results with clear probabilistic significance without requiring a large amount of random analysis.

[0029] Step 150: Use the predicted tunnel displacement value to make adaptive compensation decisions for the current tunnel construction parameters to obtain the target tunnel construction parameters.

[0030] Specifically, by comparing the deviations between the predicted tunnel displacement values ​​and the safety threshold, a sensitivity matrix of the influence of support parameters on displacement is constructed. The mechanical compensation required to return the displacement to a safe range is obtained through back-calculation and converted into adjustments to the current tunnel construction parameters, thus obtaining the target tunnel construction parameters and enabling control of the construction equipment.

[0031] In some more specific embodiments, the mechanical compensation amount is automatically converted into target tunnel construction parameters for the next excavation cycle, based on the technological characteristics of drill-and-blast construction. Drill-and-blast construction uses a "cycle" as the work unit, with each cycle including drilling, blasting, muck removal, and initial support (anchor bolts + shotcrete + steel arches). Based on the magnitude of the mechanical compensation amount and a preset mechanical-support mapping relationship, the required adjustment of support parameters is automatically calculated to obtain the target tunnel construction parameters, including support pressure, grouting volume, and anchor bolt parameters. Examples include: anchor bolt spacing (or increased quantity), shotcrete thickness increment, and steel arch spacing reduction. If the mechanical compensation amount is negative (surrounding rock is better than expected), it can automatically suggest increasing the cycle advance or reducing the support strength. The target tunnel construction parameters are packaged into a standardized electronic construction instruction sheet, containing information such as the project location, adjusted support parameters, and execution procedures. The instruction sheet is automatically pushed to the mobile terminals of on-site engineers and the control systems of digital construction equipment such as drilling rigs and wet shotcrete machines. After the support is executed according to the instruction sheet in the next cycle, the system reacquires multi-source geological sampling data and constructs a conditional random field of the strata in the forward direction using this data. The adjustment range for a single instance shall not exceed 30% of the original design; if this limit is exceeded, the system switches to manual confirmation mode. Through this process, automatic computer compensation and adaptive support control of the tunnel are achieved.

[0032] In this embodiment, the quantile theory of probability statistics is introduced. Based on the tunnel design scale and the preset stratum length, an analytical mapping function is constructed from high-dimensional random statistical parameters to deterministic equivalent parameters, taking into account the spatial variation characteristics of stratum parameters. The Kriging interpolation algorithm is used to fuse multi-source geological sampling data to construct a conditional random field for the strata in the forward direction. This conditional random field technique is combined to capture local weakening characteristics ahead of excavation in real time. The local variation coefficients within the excavation face influence zone are obtained from the conditional random field. The analytical mapping function replaces the thousands of Monte Carlo simulations in traditional stochastic finite element methods, improving parameter simulation efficiency and ensuring real-time data processing. The equivalent elastic modulus is input into a preset deterministic numerical model for solution, obtaining the predicted tunnel displacement value, providing a reliable basis for subsequent construction parameter adjustments. The predicted tunnel displacement value is used to back-calculate the mechanical compensation amount, and adaptive compensation decisions are made for the current tunnel construction parameters to obtain the target tunnel construction parameters, which conform to the actual construction conditions.

[0033] Optionally, obtaining the analytical mapping function based on the tunnel design dimensions and the preset geological stratum length includes: Based on Vanmarcke's local averaging theory, a variance reduction function is obtained according to the tunnel design scale and the preset stratum-related length. The variance reduction function includes: , Wherein, γ(L) is the variance reduction function, L is the tunnel design scale, and θ is the preset stratum-related length; The analytical mapping function is obtained based on the variance reduction function; The parsing mapping function includes: , Where λ is the reduction factor, COV is the coefficient of variation, and k is the quantile of the standard normal distribution.

[0034] Specifically, Vanmarcke's local mean theory is a classical probabilistic and statistical theory used to handle the spatial variability of geotechnical materials. The mechanical response of geotechnical engineering structures (such as tunnel displacement and slope stability safety factor) does not directly depend on the material properties at a single point, but rather on the spatial local mean of the material properties within the structure's influence range. An exponential autocorrelation function is employed. The relevant structure is described, and the variance reduction function is obtained by performing a double integral over the correlation function within a scale L. According to geotechnical mechanics theory, tunnel deformation is not controlled by parameters at a single point, but rather by the average characteristics of the soil and rock parameters within the excavation-affected zone (scale L). Let the original random field be E(x), with a mean of μ. E The standard deviation is σ E After local averaging at scale L, a new random variable is obtained. According to the theory of local averaging, The mean remains essentially unchanged, but its variance will decrease, that is: , Secondly, to ensure project safety, the average value cannot be used for design; instead, the unfavorable situation with confidence level Q (i.e., the low end of the parameter distribution) must be covered. Therefore, under a normal distribution (or log-normal distribution), the low-value characteristic value E of the parameter with confidence level Q is... Q It can be represented as: , Where k is the quantile of the standard normal distribution, for example, the quantile k = 1.645 when the confidence level Q is 95%. The equivalent elastic modulus E is defined. eq It is exactly equal to this low-value eigenvalue E after considering spatial reduction. Q The reduction factor can be obtained as follows: , Among them, E det The mean parameter used in conventional deterministic numerical analysis, i.e., μ E Extract common factors and use the definition of coefficient of variation: COV = σ E / μ EThe analytical mapping function is obtained. Based on the definition of the reduction coefficient λ, the equivalent elastic modulus can be obtained. E det The mean value of the deterministic elastic modulus of the formation, μ E k is the quantile of the standard normal distribution, for example, the quantile k=1.645 when the confidence level Q is 95%.

[0035] In this optional embodiment, based on Vanmarcke theory, we treat the formation parameters as spatial random fields. By introducing a variance reduction function, a deterministic analytical mapping operator is constructed, eliminating the need for generating multiple random field samples for repeated calculations. Instead, the mapping between input and output is directly established through mathematical analytical expressions. This instantaneous analytical mapping operator from high-dimensional random statistical parameters to deterministic equivalent parameters replaces time-consuming Monte Carlo simulations.

[0036] Optionally, the construction of a conditional random field of strata along the forward direction using multi-source geological sampling data includes: A known data vector is obtained based on the multi-source geological sampling data, wherein the known data vector is used to represent the spatial three-dimensional coordinate set of multiple multi-source geological sampling points and the corresponding measured values ​​of stratigraphic parameters; An unconditional random field is used to simulate the entire spatial computational region to obtain an unconditional simulation vector, wherein the unconditional simulation vector is used to represent the simulated values ​​of stratigraphic parameters of multiple multi-source geological sampling points; The known data vector and the unconditional simulation vector are used as condition points to perform interpolation calculations on the full-space computational region to obtain the corresponding measured estimation field and simulation estimation field. The conditional random field is obtained using the unconditional random field based on the measured estimated field and the simulated estimated field.

[0037] Optionally, the conditional random field includes: , Among them, Z c Let Z be the conditional random field. K * Z represents the measured estimated field. u Let Z be the unconditional random field. uK * The simulated estimated field.

[0038] Specifically, based on multi-source geological sampling data, a spatial three-dimensional coordinate set of n multi-source geological sampling points ahead of tunnel excavation is obtained, along with the corresponding measured values ​​of strata parameters, to construct a known data vector Z. k Based on the prior mean, coefficient of variation, and spatial autocorrelation function of the formation parameters, an unconditional random field Z is generated within the full-space computational domain including the excavation face.u The simulated values ​​of the field at the coordinates of the above n sampling points are extracted to construct the unconditional simulation vector Z. uK Using the spatial autocorrelation function as the theoretical variogram function, and taking the known data vector Z... k and unconditional analog vector Z uK Using the condition point, Kriging interpolation is performed over the entire computational domain to obtain the measured estimated field Z. K * With the simulated estimated field Z uK * The spatial residual features extracted from the measured information are injected into the initial unconditional random field Z. u In the process, a conditional random field Z that has completely passed through the measured sampling points is reconstructed by superposition. c Among them, the variance of the conditional random field at any sampling point in space strictly converges to zero, and the spatial variability of soil and rock parameters is preserved in non-sampling areas.

[0039] In this optional embodiment, the Conditional Random Field (CRF) incorporates sparse, measured sampling data as hard constraints into the model through conditional simulation. Compared to the Unconditional Random Field (URF), the CRF can more accurately reflect the actual situation and effectively reduce the uncertainty of the predicted response.

[0040] Optionally, obtaining the local variation coefficient within the excavation face influence zone based on the conditional random field includes: By extracting the elastic modulus values ​​of the center points of all finite element mesh units in the conditional random field, a sample set of elastic modulus values ​​is obtained. The local mean and local standard deviation are obtained from the sample set of elastic modulus values. The local mean includes: , Where, μ loc E is the local mean. i Let N be the sample set of elastic modulus values, where N is the total number of samples; The local standard deviation includes: , Where, σ loc The local standard deviation; The local coefficient of variation is obtained based on the local mean and the local standard deviation; The local coefficient of variation includes: , Among them, COV loc is the local coefficient of variation.

[0041] Specifically, after constructing the conditional random field, the local coefficient of variation (COV) within the influence zone of the excavation face is obtained. loc First, define the spatial domain of the influence zone. Taking the center of the current excavation face as the origin, extend forward along the tunnel axis by a distance D (D is the tunnel diameter or excavation height). The horizontal width is D, and the vertical height is D', forming a three-dimensional influence zone Ω. zone The conditional random field Z c In Ω zone Elastic modulus E at the center point of all finite element mesh elements i Extracted to form a sample set Where N is the total number of elements within the affected area. The local coefficient of variation directly reflects the relative dispersion of geotechnical mechanical parameters within a certain range ahead of the excavation face, and is a key input for subsequent analytical mapping.

[0042] Optionally, obtaining the equivalent elastic modulus using the analytical mapping function through the local coefficient of variation includes: Obtain the current tunnel excavation scale and the relevant length of the current strata; The current variance reduction function is obtained by using the current tunnel excavation scale and the current stratum length. The local coefficient of variation and the current variance reduction function are input into the analytical mapping function to obtain the current reduction coefficient; The low-value characteristic of the parameter is used as the equivalent elastic modulus by utilizing the current reduction factor; The equivalent elastic modulus includes: , Among them, E eq Let λ be the equivalent elastic modulus. loc Let μ be the current reduction factor. loc This refers to the local mean.

[0043] Specifically, based on the lower quantile principle of the probability distribution, the low-value eigenvalue of the parameter with confidence level Q is defined as the equivalent elastic modulus. The conditional random field, which contains three-dimensional spatial randomness, is reduced in dimension and simplified to a scalar E. eq A deterministic equivalent homogeneous mechanical model is used as input parameters in subsequent numerical analysis models. A two-dimensional or three-dimensional axisymmetric / plane strain model of the structure-strata for tunnel excavation or support is pre-built in commercial finite element software (such as ABAQUS, ANSYS, FLAC3D). The model mesh, boundary conditions, and constitutive relations (such as Mohr-Coulomb and hardened soil models) are all fixed. During each prediction, only the elastic modulus in the material property field is replaced with the equivalent elastic modulus E. eq Perform a static or dynamic explicit solution and extract the displacements of key nodes (such as crown settlement, perimeter convergence, and base heave) as U. predictThe time for a single solution is typically in the minutes range.

[0044] Optionally, the step of using the predicted tunnel displacement value to make adaptive compensation decisions on the current tunnel construction parameters to obtain the target tunnel construction parameters includes: Obtain the support mechanical parameters to be adjusted; Based on the predicted tunnel displacement values, an influence analysis is performed on the support mechanical parameters to obtain a sensitivity matrix; The difference between the predicted tunnel displacement value and the preset safety threshold is calculated to obtain the deviation vector; The mechanical compensation amount is obtained by using the sensitivity matrix and the deviation vector; The mechanical compensation amount includes: , Wherein, △P is the mechanical compensation amount, S is the sensitivity matrix, and △U is the deviation vector; The target tunnel construction parameters are obtained by adjusting the current tunnel construction parameters using the mechanical compensation amount.

[0045] Specifically, with the equivalent elastic modulus E eq In a deterministic numerical model for parameters, displacement characteristic quantities of m key monitoring points are selected. And select n support mechanical parameters to be adjusted. The partial derivatives of the influence of each support parameter on displacement are calculated using the perturbation method, and a sensitivity matrix S of dimension m×n is constructed: , Calculate the predicted displacement value U of the tunnel predict With preset safety threshold U limit The deviation vector △U between them: , Based on the principle of linear perturbation, an incremental equilibrium equation is established. The mechanical compensation amount ΔP required for reinforcement can be solved using the least squares method or the generalized inverse matrix.

[0046] In some more specific embodiments, if it is shield tunneling, the target tunnel construction parameters include: the increase in face support pressure, the increase in backfill grouting pressure, or the increase in grouting volume; if it is drill-and-blast construction, the target tunnel construction parameters include: the increased spacing of anchor bolts, the increase in shotcrete thickness, or the amount of explosives consumed per blast.

[0047] In some more specific embodiments, firstly, an offline analytical mapping function is preset, and the tunnel design dimension L affected by excavation is set to be equal to the height of the excavation layer of the plant, with L=8m being the tunnel design dimension. Based on the results of previous geological surveys and core tests, the prior mean value μ of the elastic modulus of the surrounding rock is determined.E =30 GPa, coefficient of variation COV=0.25, longitudinal correlation length θ=15m. Substituting L=8m and θ=15m into the Vanmarcke analytical formula: , Setting the security confidence level Q to 95% (corresponding to k=1.645), the parsing mapping function includes: .

[0048] Secondly, online sensing and conditional random field (CRF) construction were performed, and multi-source geological sampling data were collected in real time. During the excavation of the tunnel, rock wave velocity data within a 20m range ahead was obtained using advanced horizontal boreholes and converted into measured elastic modulus values. The modulus measured at z=5m and z=10m ahead were 22GPa and 25GPa, respectively. Using these two measured points as hard constraints, the global random field was corrected using the Kriging interpolation algorithm. Specifically, at z=5m, the conditional mean was forcibly updated to 22GPa, and the variance at this point became 0; the system detected a local weakening region 5m ahead. Local feature identification: Scanning the CRF revealed that within the cubic region 5m ahead, influenced by the weakening point, the local coefficient of variation increased to COV. loc =0.32, COV loc Substituting 0.32 into the analytical mapping function yields the current reduction coefficient λ. loc The equivalent elastic modulus E is obtained. eq : , .

[0049] E eq =15.54GPa was used as the surrounding rock mechanical parameter input for the finite element method (FEM) numerical model. Finite element numerical analysis was performed to calculate the predicted settlement value of the crown arch after excavation of this section, i.e., the predicted tunnel displacement value U. predict =42mm. Preset safety threshold U limit =30mm. At this point, the predicted value of 42mm is greater than 30mm, and the system issues a red alert. Using the anchor bolt support parameters as adjustment variables, the control sensitivity of each additional anchor bolt on the crown displacement under the current working conditions is calculated. The back-calculated compensation amount includes: .

[0050] The system automatically generates a construction revision sheet for the next cycle, adding 10 anchor bolts to the existing support area. Assume the support area is 50m². 2 The original support scheme had an anchor bolt density of 0.44 bolts / m. 2(Spacing 1.5m × 1.5m), then the anchor bolt density of the adjusted support scheme is 0.64 bolts / m. 2 (Spacing 1.25m × 1.25m). The above process is repeated during the next face excavation operation to provide feedback loops for the support scheme.

[0051] In this optional embodiment, the local weakening features ahead of the excavation are captured in real time by combining conditional random field technology, and the mechanical compensation amount is calculated inversely by the sensitivity matrix. This establishes a complete closed loop from the perception of geological uncertainty to the automatic control of construction parameters, which significantly improves the safety level and intelligence of tunneling construction in complex strata.

[0052] like Figure 2 As shown in the figure, an embodiment of the present invention provides a tunnel construction parameter adjustment device based on spatial variability, comprising: The analytical mapping function acquisition module 10 is used to obtain the analytical mapping function based on the quantile theory of probability statistics, according to the tunnel design scale and the preset relevant length of the strata. Conditional random field construction module 20 is used to construct a conditional random field of the strata in the forward direction based on the Kriging interpolation algorithm and multi-source geological sampling data; The equivalent elastic modulus acquisition module 30 is used to obtain the local variation coefficient in the influence zone of the excavation face according to the conditional random field, and to obtain the equivalent elastic modulus through the local variation coefficient using the analytical mapping function. The tunnel displacement prediction value acquisition module 40 is used to input the equivalent elastic modulus into a preset deterministic numerical model for solving to obtain the tunnel displacement prediction value. The target tunnel construction parameter acquisition module 50 is used to make adaptive compensation decisions on the current tunnel construction parameters using the predicted tunnel displacement values ​​to obtain the target tunnel construction parameters.

[0053] The tunnel construction parameter adjustment device based on spatial variability in this embodiment is used to implement the tunnel construction parameter adjustment method based on spatial variability as described above. Its advantages over the prior art are the same as those of the tunnel construction parameter adjustment method based on spatial variability compared to the prior art, and will not be repeated here.

[0054] like Figure 3 As shown, an electronic device 300 provided in this embodiment of the invention includes a memory 310 and a processor 320; the memory 310 is used to store a computer program; the processor 320 is used to implement the tunnel construction parameter adjustment method based on spatial variability as described above when the computer program is executed.

[0055] Alternatively, an electronic device 300 includes a memory 310 and a processor 320 coupled to the memory 310; the memory 310 is configured to store a computer program; and the processor 320 is configured to perform the following operations when the computer program is executed: Based on the quantile theory of probability statistics, an analytical mapping function is obtained according to the tunnel design scale and the preset relevant length of the strata; Based on the Kriging interpolation algorithm, a conditional random field of strata in the forward direction is constructed using multi-source geological sampling data; The local coefficient of variation within the influence zone of the excavation face is obtained based on the conditional random field, and the equivalent elastic modulus is obtained through the local coefficient of variation using the analytical mapping function. The equivalent elastic modulus is input into a preset deterministic numerical model for solution to obtain the predicted tunnel displacement value. The predicted tunnel displacement values ​​are used to make adaptive compensation decisions for the current tunnel construction parameters to obtain the target tunnel construction parameters.

[0056] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the tunnel construction parameter adjustment method based on spatial variability as described above.

[0057] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations: Based on the quantile theory of probability statistics, an analytical mapping function is obtained according to the tunnel design scale and the preset relevant length of the strata; Based on the Kriging interpolation algorithm, a conditional random field of strata in the forward direction is constructed using multi-source geological sampling data; The local coefficient of variation within the influence zone of the excavation face is obtained based on the conditional random field, and the equivalent elastic modulus is obtained through the local coefficient of variation using the analytical mapping function. The equivalent elastic modulus is input into a preset deterministic numerical model for solution to obtain the predicted tunnel displacement value. The predicted tunnel displacement values ​​are used to make adaptive compensation decisions for the current tunnel construction parameters to obtain the target tunnel construction parameters.

[0058] The present invention will now be described an electronic device 300 that can serve as a server or client of the present invention, which is an example of a hardware device that can be applied to various aspects of the present invention. Electronic device 300 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0059] Electronic device 300 includes a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or a computer program loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0060] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0061] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for adjusting tunnel construction parameters based on spatial variability, characterized in that, include: Based on the quantile theory of probability statistics, an analytical mapping function is obtained according to the tunnel design scale and the preset geological length, including: Based on Vanmarcke's local averaging theory, a variance reduction function is obtained according to the tunnel design scale and the preset stratum-related length. The variance reduction function includes: ， Wherein, γ(L) is the variance reduction function, L is the tunnel design scale, and θ is the preset stratum-related length; The analytical mapping function is obtained based on the variance reduction function; The parsing mapping function includes: ， Where λ is the reduction factor, COV is the coefficient of variation, and k is the quantile of the standard normal distribution; Based on the Kriging interpolation algorithm, a conditional random field of strata in the forward direction is constructed using multi-source geological sampling data; The local coefficient of variation within the influence zone of the excavation face is obtained based on the conditional random field, and the equivalent elastic modulus is obtained through the local coefficient of variation using the analytical mapping function, including: By extracting the elastic modulus values ​​of the center points of all finite element mesh units in the conditional random field, a sample set of elastic modulus values ​​is obtained. The local mean and local standard deviation are obtained from the sample set of elastic modulus values. The local mean includes: ， Where, μ loc E is the local mean. i Let N be the sample set of elastic modulus values, where N is the total number of samples; The local standard deviation includes: ， Where, σ loc The local standard deviation; The local coefficient of variation is obtained based on the local mean and the local standard deviation; The local coefficient of variation includes: ， Among them, COV loc The local coefficient of variation; The equivalent elastic modulus is input into a preset deterministic numerical model for solution to obtain the predicted tunnel displacement value. The predicted tunnel displacement values ​​are used to perform adaptive compensation decisions on the current tunnel construction parameters to obtain the target tunnel construction parameters, including: Obtain the support mechanical parameters to be adjusted; Based on the predicted tunnel displacement values, an influence analysis is performed on the support mechanical parameters to obtain a sensitivity matrix; The difference between the predicted tunnel displacement value and the preset safety threshold is calculated to obtain the deviation vector; The mechanical compensation amount is obtained by using the sensitivity matrix and the deviation vector; The mechanical compensation amount includes: ， Wherein, △P is the mechanical compensation amount, S is the sensitivity matrix, and △U is the deviation vector; The target tunnel construction parameters are obtained by adjusting the current tunnel construction parameters using the mechanical compensation amount.

2. The method for adjusting tunnel construction parameters based on spatial variability according to claim 1, characterized in that, The construction of a conditional random field for forward-direction strata using multi-source geological sampling data includes: A known data vector is obtained based on the multi-source geological sampling data, wherein the known data vector is used to represent the spatial three-dimensional coordinate set of multiple multi-source geological sampling points and the corresponding measured values ​​of stratigraphic parameters; An unconditional random field is used to simulate the entire spatial computational region to obtain an unconditional simulation vector, wherein the unconditional simulation vector is used to represent the simulated values ​​of stratigraphic parameters of multiple multi-source geological sampling points; The known data vector and the unconditional simulation vector are used as condition points to perform interpolation calculations on the full-space computational region to obtain the corresponding measured estimation field and simulation estimation field. The conditional random field is obtained using the unconditional random field based on the measured estimated field and the simulated estimated field.

3. The method for adjusting tunnel construction parameters based on spatial variability according to claim 2, characterized in that, The conditional random field includes: ， Among them, Z c Let Z be the conditional random field. K Z represents the measured estimated field. u Let Z be the unconditional random field. uK The simulated estimated field.

4. The method for adjusting tunnel construction parameters based on spatial variability according to claim 1, characterized in that, The step of obtaining the equivalent elastic modulus using the analytical mapping function through the local coefficient of variation includes: Obtain the current tunnel excavation scale and the relevant length of the current strata; The current variance reduction function is obtained by using the current tunnel excavation scale and the current stratum length. The local coefficient of variation and the current variance reduction function are input into the analytical mapping function to obtain the current reduction coefficient; The low-value characteristic of the parameter is used as the equivalent elastic modulus by utilizing the current reduction factor; The equivalent elastic modulus includes: ， Among them, E eq Let λ be the equivalent elastic modulus. loc Let μ be the current reduction factor. loc This refers to the local mean.

5. A tunnel construction parameter adjustment device based on spatial variability, characterized in that, The apparatus for implementing the tunnel construction parameter adjustment method based on spatial variability as described in any one of claims 1 to 4 includes: The analytical mapping function acquisition module is used to obtain the analytical mapping function based on the quantile theory of probability statistics, according to the tunnel design scale and the preset relevant length of the strata; The Conditional Random Field (CRF) construction module is used to construct a CRF of the stratigraphic direction based on multi-source geological sampling data using the Kriging interpolation algorithm. The equivalent elastic modulus acquisition module is used to obtain the local variation coefficient within the influence zone of the excavation face based on the conditional random field, and to obtain the equivalent elastic modulus through the local variation coefficient using the analytical mapping function. The tunnel displacement prediction value acquisition module is used to input the equivalent elastic modulus into a preset deterministic numerical model for solution to obtain the tunnel displacement prediction value. The target tunnel construction parameter acquisition module is used to make adaptive compensation decisions on the current tunnel construction parameters using the predicted tunnel displacement values ​​to obtain the target tunnel construction parameters.

6. An electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to, when executing the computer program, implement the tunnel construction parameter adjustment method based on spatial variability as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the tunnel construction parameter adjustment method based on spatial variability as described in any one of claims 1 to 4.

Images