A tunnel advanced geological prediction method and related device under a severe environment

Abstract

The application discloses a tunnel advanced geological prediction method and related equipment under a severe environment. The method comprises the following steps: collecting core influence parameters of the severe environment, weighting and summing after dimensionless to obtain an environment comprehensive influence coefficient; performing multi-field coupling nonlinear correction on a detection signal according to the coefficient; calculating the adaptation degree of each detection technology under the current environment, and dynamically calculating a fusion weight; using the corrected detection signal, the fusion weight and the environment comprehensive influence coefficient, calculating the vertical distance and the lateral scale of the adverse geological body and the tunnel face through a quantitative positioning formula; performing multidimensional reliability evaluation on the prediction result, and dynamically correcting and updating the formula coefficient to the formula system according to the prediction error after construction exposure. The application can adapt to the multi-factor coupling influence of the severe environment, realize the quantitative positioning of the adverse geological body, has a closed-loop self-optimization capability, and effectively improves the precision of the tunnel advanced geological prediction.

Description

Technical Field

[0001] This invention belongs to the field of tunnel engineering geological exploration and advanced prediction technology, specifically involving a method and related equipment for advanced geological prediction of tunnels under harsh environments. Background Technology

[0002] Advanced geological prediction for tunnels is a crucial aspect of ensuring tunnel construction safety. Commonly used detection methods include TSP elastic wave detection, ground-penetrating radar detection, advanced drilling, and geological surveys. Under normal geological conditions, these technologies are relatively mature and can accurately identify the location and scale of adverse geological bodies ahead of the tunnel face. However, when tunnels traverse harsh environments such as high water pressure, high ground stress, dense fault zones, acidic water erosion areas, or high geothermal areas, the coupling of multiple factors causes nonlinear attenuation and propagation path distortion of the detection signals, resulting in a significant decrease in prediction accuracy.

[0003] Current practices typically involve linearly correcting the detection signal for a single environmental factor, then weighting and fusing the results from multiple detection techniques according to fixed weights, and finally relying on engineering experience to determine the boundary and scale of the adverse geological body.

[0004] The aforementioned existing technologies have the following shortcomings: First, in harsh environments, multiple environmental factors often coexist and are coupled with each other. Linear correction of a single factor cannot reflect the nonlinear distortion effect of multi-field coupling on the detected signal, resulting in significant deviations between the corrected wave velocity and attenuation and the actual values. Second, the effectiveness of different detection technologies varies significantly under various harsh environments. Fixed-weight fusion methods cannot adapt to environmental changes. When the data quality of a certain technology is low due to environmental interference, its fixed weights will still introduce significant errors, reducing the reliability of the fusion results. Third, the location of adverse geological bodies mainly relies on empirical interpretation and lacks quantitative calculation formulas based on environmental quantitative indicators. This leads to large location errors and a high risk of underreporting or false alarms of major risks such as water inrush, mudslides, and rock bursts. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention provides a method and related equipment for advanced geological prediction of tunnels under harsh environments. Its purpose is to solve the problems of nonlinear distortion of detection signals caused by multi-factor coupling in harsh environments, insufficient accuracy of linear correction by single factors, inability of fixed-weight fusion to adapt to environmental changes, and reliance on empirical interpretation for locating adverse geological bodies. This invention provides a method for advanced geological prediction of tunnels that can quantitatively characterize the comprehensive environmental impact, dynamically adapt the weights of detection technologies, accurately calculate the location and scale of adverse geological bodies through quantitative positioning formulas, and possess multi-dimensional reliability evaluation and closed-loop correction capabilities. This reduces signal interpretation errors, improves the reliability and positioning accuracy of prediction results, and reduces missed or false alarms of major risks such as water inrush, mudslides, and rock bursts.

[0006] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution: According to a first aspect of the present invention, a method for advanced geological prediction of tunnels under harsh environments is provided, comprising: The core impact parameters of the current severe environment are collected, and after the core impact parameters are processed to be dimensionless, they are weighted and summed to calculate the comprehensive environmental impact coefficient. The detection signal is collected, and multi-field coupling nonlinear correction is performed on the detection signal according to the comprehensive environmental influence coefficient to obtain the corrected detection signal; The adaptability of each detection technology in the current harsh environment is calculated separately, and the fusion weight of each detection technology is dynamically calculated based on the adaptability of each detection technology. Using the corrected detection signal, the fusion weight, and the comprehensive environmental impact coefficient, the prediction result is calculated through a pre-constructed quantitative positioning formula. The prediction result is the vertical distance between the adverse geological body and the tunnel face, as well as the lateral scale of the adverse geological body. The forecast results are evaluated for reliability in multiple dimensions. After construction and exposure, the forecast error between the actual exposure parameters and the forecast results is used to dynamically correct the multi-field coupling nonlinear correction, the quantitative positioning formula, and the formula coefficients used in the multi-dimensional reliability evaluation. The corrected coefficients are then updated to the formula system.

[0007] In one possible implementation of the first aspect, the comprehensive environmental impact coefficient is calculated using the following formula:

[0008] In the formula, This is the comprehensive environmental impact coefficient; The number of core influencing parameters; For the first Dimensionless values ​​of the core influencing parameters; For the first The weights of the core influencing parameters.

[0009] In one possible implementation of the first aspect, the step of performing multi-field coupled nonlinear correction on the detection signal based on the comprehensive environmental influence coefficient includes: The elastic longitudinal wave velocity is corrected using the following formula:

[0010] In the formula, This is the corrected elastic longitudinal wave velocity; The elastic longitudinal wave velocity under normal conditions; For the dynamic elastic modulus of rock mass under harsh conditions; This refers to the static elastic modulus of rock mass under normal conditions. This represents the comprehensive environmental impact coefficient.

[0011] In one possible implementation of the first aspect, the step of performing multi-field coupled nonlinear correction on the detection signal based on the comprehensive environmental influence coefficient includes: The electromagnetic wave attenuation is corrected using the following formula:

[0012] In the formula, This is the corrected electromagnetic wave attenuation. This represents the attenuation of electromagnetic waves under normal conditions. This is the dielectric constant-water content-corrosion coupling correction factor; This represents the comprehensive environmental impact coefficient.

[0013] In one possible implementation of the first aspect, the calculation of the adaptability of each detection technology to the current harsh environment specifically involves:

[0014] In the formula, For the first The adaptability of various detection technologies to the current harsh environment; For the first time under harsh conditions The measured accuracy of this detection technology; For the first time under normal conditions The benchmark accuracy of this detection technology; Environmental adaptability coefficient; This is the data quality coefficient; The dynamic calculation of the fusion weight of each detection technology based on the adaptability of each detection technology is specifically as follows:

[0015] In the formula, The total number of detection technologies; For the first The fusion weight of various detection technologies; For the first The adaptability of this detection technology to the current harsh environment.

[0016] In one possible implementation of the first aspect, the pre-constructed quantitative positioning formula includes a vertical distance positioning formula and a lateral scale positioning formula; the detection technology includes geological survey method, TSP detection method, ground-penetrating radar detection method, and advanced drilling method; The vertical distance positioning formula is as follows:

[0017] In the formula, This refers to the vertical distance between the unfavorable geological formation and the tunnel face. To determine the reliability coefficient of the detection signal; This is the path correction factor; This is the corrected elastic longitudinal wave velocity; The round-trip propagation time of the elastic longitudinal wave; The fusion weights for the TSP detection method; The speed of electromagnetic waves in a vacuum; This refers to the propagation time of the electromagnetic wave. The fusion weights for ground-penetrating radar detection methods; The formula for horizontal scale positioning is:

[0018] In the formula, The lateral scale of the unfavorable geological body; To detect the angle of signal transmission; This is the longitudinal extension coefficient; The fusion weight for geological survey methods; The fusion weight for advanced drilling methods; This represents the comprehensive environmental impact coefficient.

[0019] In one possible implementation of the first aspect, the multi-dimensional reliability evaluation includes: calculating the reliability coefficient based on the comprehensive environmental impact coefficient using the following formula:

[0020] In the formula, Reliability coefficient; The total number of detection technologies; To ensure consistency in multi-source data fusion; This is the average data quality coefficient; For the first The adaptability of various detection technologies to the current harsh environment; according to Values ​​are used to classify reliability levels: A value ≥0.8 indicates Level 1 reliability, and 0.5≤ A value less than 0.8 indicates a level 2 reliability requirement, which needs further verification. A value less than 0.5 indicates a Level 3 reliability threshold, requiring a new forecast.

[0021] In one possible implementation of the first aspect, the prediction error is calculated using the following formula:

[0022] In the formula, This is the forecast error; The actual vertical distance and / or actual lateral scale revealed during construction. The vertical distance between the adverse geological body and the tunnel face and / or the lateral scale of the adverse geological body in the forecast results; The dynamic correction is performed according to the following formula:

[0023] In the formula, These are the coefficients used in the multi-field coupling nonlinear correction, the quantitative positioning formula, and the multi-dimensional reliability evaluation. These are the corrected coefficients; This represents the forecast error.

[0024] According to a second aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the aforementioned method for advanced geological prediction of tunnels under harsh environments.

[0025] According to a third aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned method for advanced geological prediction of tunnels under harsh environments.

[0026] According to a fourth aspect of the present invention, a computer program product is provided that, when executed by a processor, implements the aforementioned method for advanced geological prediction of tunnels under harsh environments.

[0027] Compared with the prior art, the present invention has at least the following beneficial effects: The tunnel advanced geological prediction method provided by this invention collects the core influencing parameters of the harsh environment, performs dimensionless processing, and then weights and sums them to obtain an environmental comprehensive influence coefficient that comprehensively reflects the coupling strength of multiple factors. This environmental comprehensive influence coefficient provides a unified quantitative benchmark for signal correction, weight allocation, and positioning calculation, changing the traditional approach of ignoring multi-field coupling or only performing single-factor correction. Based on this, the collected detection signals are subjected to multi-field coupling nonlinear correction according to this environmental comprehensive influence coefficient, making the corrected elastic wave velocity and electromagnetic wave attenuation closer to the real physical field under harsh conditions, thereby reducing interpretation errors caused by signal distortion. Furthermore, by calculating the adaptability of each detection technology in the current harsh environment and dynamically calculating the fusion weight of each detection technology accordingly, detection technologies with strong adaptability to different harsh environments receive higher weights, while the weights of technologies with poor adaptability are automatically reduced, avoiding the problems of insufficient complementarity and decreased accuracy caused by fixed-weight fusion. By utilizing corrected detection signals, dynamic fusion weights, and environmental comprehensive influence coefficients, the vertical distance and lateral scale between adverse geological bodies and the tunnel face are directly calculated through a pre-constructed quantitative positioning formula. This transforms the traditional qualitative or semi-quantitative work, which relies on experience-based interpretation, into quantifiable parameter outputs, effectively eliminating subjective human error and improving positioning accuracy. A multi-dimensional reliability evaluation is performed on the calculated forecast results to avoid safety risks arising from blind construction due to inaccurate forecasts. Finally, after construction exposure, based on the forecast error between the actual exposed parameters and the forecast results, the coefficients of the formulas used in the aforementioned multi-field coupled nonlinear correction, quantitative positioning formula, and multi-dimensional reliability evaluation are dynamically corrected. The corrected coefficients are then updated into the formula system, enabling the entire forecasting method to continuously self-optimize with the accumulation of engineering practice, gradually improving forecast accuracy under similar harsh environments. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the specific embodiments of the present invention, the drawings used in the description of the specific embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0029] Figure 1 This is a flowchart of a method for advanced geological prediction of tunnels under harsh environments, as described in this invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] This invention addresses the problems of signal distortion caused by multi-factor coupling in harsh environments, insufficient accuracy of single-factor linear correction, inadequacy of fixed-weight fusion to adapt to environmental changes, and reliance on empirical interpretation for locating adverse geological bodies. It provides a tunnel advanced geological prediction method based on a comprehensive environmental influence coefficient. This method quantifies environmental parameters, nonlinearly corrects the detection signal, dynamically allocates the weights of detection technologies, quantitatively calculates the location and scale of adverse geological bodies, and utilizes closed-loop correction formula coefficients based on construction data to achieve adaptive and accurate prediction. The following section, in conjunction with the appendix... Figure 1 The flowchart shown illustrates the technical solution of the present invention in detail, taking a tunnel in a harsh environment as an example.

[0032] This invention provides a method for advanced geological prediction of tunnels under harsh environments, specifically including the following steps: S1. Collect the core impact parameters of the current severe environment, perform dimensionless processing on the core impact parameters, and then perform weighted summation to calculate the comprehensive environmental impact coefficient.

[0033] It should be understood that harsh environmental types include karst areas with high water pressure, rockburst areas with high ground stress, fault-prone zones, acidic water erosion areas, and high geothermal areas. Specifically, the corresponding core influencing parameters should be selected based on the actual environmental type in which the project is located.

[0034] For example, in high-pressure karst areas, core parameters include pore water pressure, karst fissure ratio, rock mass dielectric constant, groundwater water-bearing capacity, and groundwater seepage velocity. In high-stress rockburst areas, core parameters include maximum principal stress, rock mass compressive strength, joint development, rock mass integrity coefficient, and stress release coefficient. In densely faulted zones, core parameters include fault fracture zone width, fault hydraulic conductivity, fault attitude, rock mass fracturing degree, and fault infill water content. In acidic water erosion areas, core parameters include groundwater pH, rock mass corrosion coefficient, rock mass water content, erosion environment level, and rock mass electrical conductivity. In high-temperature areas, core parameters include ambient temperature, rock mass thermal conductivity, thermal expansion coefficient, geothermal gradient, and rock mass thermal stability coefficient.

[0035] For example, a matrix-style optimized sampling method is used, setting up multiple sampling points within a 20m radius of the tunnel face to ensure comprehensive parameter coverage while avoiding redundant sampling. Parameters are dynamically collected continuously for 12 hours using dedicated equipment, and the average value is used as the baseline parameter.

[0036] Preferably, since the parameters have different dimensions, directly involving them in the calculation would lead to distorted results. Therefore, the extreme value method is used to uniformly map all basic parameters to the interval between 0 and 1, eliminating the influence of dimensions. Let the first... The measured average value of each parameter is The measured minimum value under similar harsh engineering conditions is Maximum value Then the dimensionless value Calculate according to the following formula:

[0037] Different influencing parameters have varying degrees of impact on the detected signal. After dimensionless transformation, the weights of each parameter are determined using the analytic hierarchy process (AHP) combined with the entropy weight method. Then, the comprehensive environmental impact coefficient is obtained by weighted summation. This characterizes the overall interference level of the environment on the detection signal.

[0038] It should be noted that, ∈[0,1], A higher value indicates stronger environmental interference.

[0039] S2. Collect the detection signal, and perform multi-field coupling nonlinear correction on the detection signal according to the comprehensive environmental influence coefficient to obtain the corrected detection signal.

[0040] Specifically, under harsh environments, the propagation patterns of TSP elastic waves and ground-penetrating radar electromagnetic waves are affected by the coupling of multiple environmental factors, leading to distortions in core parameters such as wave velocity and attenuation. By analyzing the multi-field coupling influence mechanism of the environment on signal propagation, two sets of core correction formulas are derived to eliminate signal distortion and restore accurate geological information. The formula derivation is based on fitting measured data from complex geological tunnels, avoiding complex theoretical derivations, and is simple in form, suitable for engineering field applications.

[0041] In one feasible approach, for TSP elastic wave detection, a multi-field coupling correction factor is introduced into the conventional elastic wave velocity formula, and the elastic longitudinal wave velocity is corrected according to the following formula:

[0042] In the formula, The corrected elastic longitudinal wave velocity (km / s); The elastic longitudinal wave velocity (km / s) under normal conditions; The dynamic elastic modulus of rock mass under harsh conditions (GPa); The static elastic modulus of rock mass under normal conditions (GPa); This represents the comprehensive environmental impact coefficient.

[0043] In one feasible approach, for ground-penetrating radar electromagnetic wave detection, the electromagnetic wave attenuation is corrected by combining ground-penetrating radar measured data from complex geological tunnels using the following formula:

[0044] In the formula, This is the corrected electromagnetic wave attenuation (dB). This represents the electromagnetic wave attenuation (dB) under normal conditions. This is the dielectric constant-water content-corrosion coupling correction factor; This represents the comprehensive environmental impact coefficient.

[0045] S3. Calculate the adaptability of each detection technology in the current harsh environment, and dynamically calculate the fusion weight of each detection technology based on the adaptability of each detection technology.

[0046] In one feasible approach, the detection technologies employed include geological surveys, TSP (Through-Slip Perimeter) detection, ground-penetrating radar (GPR) detection, and advanced drilling. Adaptability Characterizing the first The forecast adaptability of this detection technology in the current harsh environment, with values ​​ranging from 0 to 1. A higher value indicates a higher degree of compatibility between the detection technology and the environment, and stronger data reliability. The compatibility is calculated using the following formula:

[0047] In the formula, For the first time under harsh conditions Measured accuracy (%) of the detection technology; For the first time under normal conditions The baseline accuracy (%) of the detection technology; This is the environmental adaptability coefficient, with a value ranging from 0 to 1; This is the data quality coefficient, with a value ranging from 0 to 1.

[0048] In one feasible approach, the fusion weights of each detection technology are dynamically calculated using a weighted normalization method based on the compatibility of each technology, as shown in the following formula:

[0049] In the formula, The total number of detection technologies; For the first The fusion weight of various detection technologies; For the first The adaptability of various detection technologies to the current harsh environment, summation subscript Iterate through all detection technologies.

[0050] Optionally, after obtaining the fusion weights of each detection technology, a weighted average method is further used to fuse the adverse geological body parameters interpreted by each detection technology using multi-source data. The fusion formula is as follows:

[0051] In the formula, The parameters of the fused unfavorable geological body, For the first The parameters of the adverse geological body obtained by interpreting the detection technology For the first The fusion weight of various detection technologies and These represent the maximum and minimum values ​​for the adaptability of each detection technology. This fusion result can be used to assist in interpreting other attributes of adverse geological bodies, such as water-bearing capacity and morphological characteristics, providing more reference information for construction decisions.

[0052] S4. Using the corrected detection signal, the fusion weight, and the environmental comprehensive influence coefficient, the prediction result is calculated through a pre-constructed quantitative positioning formula. The prediction result is the vertical distance between the adverse geological body and the tunnel face, and the lateral scale of the adverse geological body.

[0053] In one feasible approach, the vertical distance positioning formula is:

[0054] In the formula, The vertical distance (m) between the adverse geological body and the tunnel face; To determine the reliability coefficient of the detection signal; This is the path correction factor; This is the corrected elastic longitudinal wave velocity; The round-trip propagation time of the elastic longitudinal wave (s); The fusion weights for the TSP detection method; The velocity of electromagnetic waves in a vacuum (3 × 10⁻⁶) 8 m / s); The electromagnetic wave propagation time (s); The fusion weights are used for the ground-penetrating radar detection method.

[0055] In one feasible approach, the formula for horizontal scaling is:

[0056] In the formula, The lateral scale (m) of the unfavorable geological body; To detect the signal transmission angle (°); This is the longitudinal extension coefficient; The fusion weight for geological survey methods; The fusion weight for advanced drilling methods; This represents the comprehensive environmental impact coefficient.

[0057] S5. Perform a multi-dimensional reliability evaluation on the forecast results, and after construction and exposure, dynamically correct the multi-field coupling nonlinear correction, the quantitative positioning formula, and the formula coefficients used in the multi-dimensional reliability evaluation based on the forecast error between the actual exposure parameters and the forecast results, and update the corrected coefficients to the formula system.

[0058] In one feasible approach, to quantify the reliability of forecast results and avoid construction risks caused by misjudgments, a multi-dimensional reliability evaluation formula is derived, a three-level evaluation system is established, and the application scenarios are clearly defined, distinguishing it from existing single-dimensional evaluation methods. Details are as follows: Multi-dimensional reliability evaluation calculates the reliability coefficient using the following formula. :

[0059] In the formula, The reliability coefficient ranges from 0 to 1. To ensure consistency (0~1) in multi-source data fusion, cosine similarity is used for calculation. ,in The total number of detection technologies; The average data quality coefficient (0~1). .

[0060] according to The forecast results are divided into three levels: when A value ≥0.8 indicates Level 1 reliability, with high consistency of multi-source data, good data quality, minimal environmental interference, and strong adaptability and synergy. The forecast results can be directly used as the basis for construction decisions without the need for supplementary detection. When 0.5≤ When the value is less than 0.8, it is considered Level 2 reliability. However, there may be some environmental interference or data discrepancies. It is necessary to use methods such as deepening the boreholes and short-distance advanced drilling to further verify the data before use. For example, deepen three boreholes to a depth of ≥5m and perform one short-distance advanced drilling to a depth of ≥15m. when When the value is less than 0.5, it is considered Level 3 reliable, indicating strong environmental interference, poor data consistency, weak adaptability and coordination, rendering the forecast invalid and requiring a new forecast.

[0061] During tunnel construction, the actual parameters of adverse geological bodies are recorded in real time. , and forecast parameters Compare and calculate the forecast error:

[0062] The forecast error is fed back to the preceding formula, and the engineering fitting coefficients in the formula are dynamically corrected. The correction formula is as follows:

[0063] In the formula, These are the formula coefficients used in the multi-field coupling nonlinear correction, the quantitative positioning formula, and the multi-dimensional reliability evaluation, i.e., the original engineering fitting coefficients in the formulas. For example, 1.08, 0.47, and 0.12 in the elastic longitudinal wave velocity correction formula; 0.88 and 0.22 in the electromagnetic wave attenuation correction formula; 0.92, 0.08, 0.22, 0.06, and 0.07 in the vertical distance positioning formula; 0.16 and 0.04 in the lateral scale positioning formula; and 0.42, 0.95, and 0.05 in the reliability coefficient formula. These are the corrected coefficients; This represents the forecast error.

[0064] The revised engineering fitting coefficients are incorporated into the formula system, and the formula parameter library is updated. Simultaneously, actual construction verification data (environmental parameters, fit, weights, and prediction errors) are included in the engineering case library. A correspondence between environment type, formula parameters, and prediction accuracy is established, forming an industry-shared database that provides a reference for advanced geological prediction in similar harsh environment tunnel projects. Through a closed-loop mechanism, the prediction accuracy of the method continuously improves with the increase of engineering cases, demonstrating strong self-optimization capabilities and adapting to the personalized needs of different harsh environments.

[0065] This invention departs from the past practice of linearly correcting only a single environmental factor. By collecting core influencing parameters of harsh environments and weighted summing them to obtain a comprehensive influence coefficient, this coefficient is introduced into the elastic wave velocity correction formula and electromagnetic wave attenuation correction formula in the form of a high-order polynomial. This allows the corrected detection signal to accurately reflect the actual propagation characteristics under multi-field coupling, directly reducing signal interpretation errors. Simultaneously, addressing the significant differences in sensitivity of different detection technologies to various harsh environments, this method dynamically calculates the fit degree based on the measured accuracy, environmental adaptability coefficient, and data quality coefficient of each detection technology in the current environment. The fusion weight is then normalized according to the fit degree, allowing the weight allocation to automatically adjust with environmental type. Technologies with strong environmental adaptability receive higher weights, avoiding the failure of fixed weights in harsh environments and effectively improving the reliability of multi-source data fusion results. Building upon this foundation, this method introduces a path correction factor and a signal reliability coefficient based on the corrected elastic wave velocity and electromagnetic wave propagation time. It establishes a vertical distance positioning formula and, combined with the detection signal emission angle, longitudinal extension coefficient, and the fusion weights of various detection technologies, establishes a lateral scale positioning formula. By substituting the signal parameters corrected through multi-field coupling and the comprehensive environmental influence coefficient, the vertical distance and lateral scale between the adverse geological body and the working face are directly calculated. This transforms traditional empirical interpretation into quantifiable parameter calculations, reducing positioning errors and subjective uncertainties. Furthermore, this method comprehensively considers the consistency of multi-source data fusion, the average data quality coefficient, the comprehensive environmental influence coefficient, and the adaptability distribution of various detection technologies to construct a reliability coefficient calculation formula. The calculation results are divided into three reliability levels, enabling construction teams to take differentiated countermeasures based on the reliability level, effectively reducing construction risks caused by inaccurate forecasts. Finally, after construction and exposure, the method compares the actual exposed parameters with the predicted parameters to calculate the error, and uses this error to correct the engineering fitting coefficients used in the previous steps. At the same time, the corrected coefficients and engineering case data are stored in a shared database, so that the formula coefficients are continuously optimized with the accumulation of engineering cases, realizing the leap from open-loop forecasting to closed-loop self-optimization, and continuously improving the forecast accuracy.

[0066] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used in the operation of a tunnel advanced geological prediction method under harsh environments.

[0067] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be Random Access Memory (RAM) or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the tunnel advanced geological prediction method under harsh environments described in the above embodiments.

[0068] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0069] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] This invention also provides a computer program product for executing any of the aforementioned methods for advanced geological prediction of tunnels under harsh environments. Since the computer program product provided by this invention belongs to the same inventive concept as the aforementioned method for advanced geological prediction of tunnels under harsh environments, it possesses all the advantages of the aforementioned method. Therefore, the beneficial effects of the computer program product provided by this invention will not be elaborated upon here.

[0073] In this invention, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0074] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the scope of the technology disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention.

Claims

1. A method for advanced geological prediction of tunnels under harsh environments, characterized in that, include: The core impact parameters of the current severe environment are collected, and after the core impact parameters are processed to be dimensionless, they are weighted and summed to calculate the comprehensive environmental impact coefficient. The detection signal is collected, and multi-field coupling nonlinear correction is performed on the detection signal according to the comprehensive environmental influence coefficient to obtain the corrected detection signal; The adaptability of each detection technology in the current harsh environment is calculated separately, and the fusion weight of each detection technology is dynamically calculated based on the adaptability of each detection technology. Using the corrected detection signal, the fusion weight, and the comprehensive environmental impact coefficient, the prediction result is calculated through a pre-constructed quantitative positioning formula. The prediction result is the vertical distance between the adverse geological body and the tunnel face, as well as the lateral scale of the adverse geological body. The forecast results are evaluated for reliability in multiple dimensions. After construction and exposure, the forecast error between the actual exposure parameters and the forecast results is used to dynamically correct the multi-field coupling nonlinear correction, the quantitative positioning formula, and the formula coefficients used in the multi-dimensional reliability evaluation. The corrected coefficients are then updated to the formula system.

2. The method for advanced geological prediction of tunnels under harsh environments according to claim 1, characterized in that, The comprehensive environmental impact coefficient is calculated using the following formula: In the formula, This represents the comprehensive environmental impact coefficient. The number of core influencing parameters; For the first Dimensionless values ​​of the core influencing parameters; For the first The weights of the core influencing parameters.

3. The method for advanced geological prediction of tunnels under harsh environments according to claim 1, characterized in that, The step of performing multi-field coupling nonlinear correction on the detection signal based on the comprehensive environmental influence coefficient includes: The elastic longitudinal wave velocity is corrected using the following formula: In the formula, This is the corrected elastic longitudinal wave velocity; The elastic longitudinal wave velocity under normal conditions; For the dynamic elastic modulus of rock mass under harsh conditions; This refers to the static elastic modulus of rock mass under normal conditions. This represents the comprehensive environmental impact coefficient.

4. The method for advanced geological prediction of tunnels under harsh environments according to claim 1, characterized in that, The step of performing multi-field coupling nonlinear correction on the detection signal based on the comprehensive environmental influence coefficient includes: The electromagnetic wave attenuation is corrected using the following formula: In the formula, This is the corrected electromagnetic wave attenuation. This represents the attenuation of electromagnetic waves under normal conditions. This is the dielectric constant-water content-corrosion coupling correction factor; This represents the comprehensive environmental impact coefficient.

5. The method for advanced geological prediction of tunnels under harsh environments according to claim 1, characterized in that, The calculation of the adaptability of each detection technology to the current harsh environment is specifically as follows: In the formula, For the first The adaptability of various detection technologies to the current harsh environment; For the first time under harsh conditions The measured accuracy of this detection technology; For the first time under normal conditions The benchmark accuracy of this detection technology; Environmental adaptability coefficient; This is the data quality coefficient; The dynamic calculation of the fusion weight of each detection technology based on the adaptability of each detection technology is specifically as follows: In the formula, The total number of detection technologies; For the first The fusion weight of various detection technologies; For the first The adaptability of this detection technology to the current harsh environment.

6. The method for advanced geological prediction of tunnels under harsh environments according to claim 5, characterized in that, The pre-constructed quantitative positioning formulas include vertical distance positioning formulas and horizontal scale positioning formulas; the detection technologies include geological survey methods, TSP detection methods, ground-penetrating radar detection methods, and advanced drilling methods; The vertical distance positioning formula is as follows: In the formula, This refers to the vertical distance between the unfavorable geological formation and the tunnel face. To determine the reliability coefficient of the detection signal; This is the path correction factor; This is the corrected elastic longitudinal wave velocity; The round-trip propagation time of the elastic longitudinal wave; The fusion weights for the TSP detection method; The speed of electromagnetic waves in a vacuum; This refers to the propagation time of the electromagnetic wave. The fusion weights for ground-penetrating radar detection methods; The formula for determining the horizontal scale is: In the formula, The lateral scale of the unfavorable geological body; To detect the angle of signal transmission; This is the longitudinal extension coefficient; The fusion weight for geological survey methods; The fusion weight for advanced drilling methods; This represents the comprehensive environmental impact coefficient.

7. The method for advanced geological prediction of tunnels under harsh environments according to claim 1, characterized in that, The multi-dimensional reliability evaluation includes: calculating the reliability coefficient based on the comprehensive environmental impact coefficient using the following formula: In the formula, Reliability coefficient; The total number of detection technologies; To ensure consistency in multi-source data fusion; This is the average data quality coefficient; For the first The adaptability of various detection technologies to the current harsh environment; according to Values ​​are used to classify reliability levels: A value ≥0.8 indicates Level 1 reliability, and 0.5≤ A value less than 0.8 indicates a level 2 reliability requirement, which needs further verification. A value less than 0.5 indicates a Level 3 reliability threshold, requiring a new forecast.

8. The method for advanced geological prediction of tunnels under harsh environments according to claim 1, characterized in that, The forecast error is calculated using the following formula: In the formula, This is the forecast error; The actual vertical distance and / or actual lateral scale revealed during construction. The vertical distance between the adverse geological body and the tunnel face and / or the lateral scale of the adverse geological body in the forecast results; The dynamic correction is performed according to the following formula: In the formula, These are the coefficients used in the multi-field coupling nonlinear correction, the quantitative positioning formula, and the multi-dimensional reliability evaluation. These are the corrected coefficients; This represents the forecast error.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements a method for advanced geological prediction of tunnels under harsh environments as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements a method for advanced geological prediction of tunnels under harsh environments as described in any one of claims 1 to 8.

Images