A tunnel unfavorable geological identification method and system for drilling seismic fusion

Abstract

The present application belongs to the field of tunnel advanced geological risk quantification, and provides a tunnel unfavorable geological identification method and system based on drilling and seismic fusion, which is characterized in that, in the process of tunnel advanced drilling, passive source seismic signals are continuously collected, and drilling parameters are synchronously collected; based on the drilling parameters, an engineering prior probability distribution reflecting the geological risk in front of the tunnel face is established by using a lithology identification model; the passive source seismic signals are processed and reconstructed, seismic response characteristics are extracted, and the seismic response characteristics are converted into a seismic observation likelihood function for Bayesian inference; the seismic observation likelihood function and the current prior probability distribution are sequentially fused by using Bayesian inference, and a posterior probability distribution representing the unfavorable geological risk is obtained by updating; and the advanced geological risk information is quantified and output according to the posterior probability distribution. The reliability of unfavorable geological identification is improved, and more objective data support is provided for advanced support, grouting reinforcement, blasting parameter adjustment and construction risk warning.

Description

Technical Field

[0001] This invention belongs to the field of advanced geological risk quantification for tunnels, and particularly relates to a method and system for identifying adverse geological conditions in tunnels by integrating drilling seismic data. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] During drill-and-blast tunnel construction, the geological conditions ahead of the tunnel face are highly uncertain. Common adverse geological features include fault fracture zones, karst cavities, water-rich zones, weak interlayers, mudslide and water inrush channels, and abrupt transitions between soft and hard rock. If these adverse geological features are not identified in time before excavation, they may lead to engineering risks such as collapses, water inrushes, mudslides, exacerbated over- and under-excavation, instability of the support structure, and delays in construction progress. Therefore, conducting advanced geological condition detection and risk identification before excavation is a crucial technical step in ensuring safe tunnel construction and optimizing construction organization.

[0004] Currently, commonly used advanced geological prediction methods for drill-and-blast tunnels mainly include geological sketching, advanced horizontal drilling, TSP seismic prediction, transient electromagnetic methods, ground-penetrating radar, infrared water detection, and drilling parameter analysis. Among these, seismic wave methods have become an important technical means in advanced geological prediction for tunnels due to their advantages such as long detection range, sensitivity to wave impedance interfaces, and suitability for identifying fault fracture zones and soft-hard rock interfaces. In particular, passive source seismic methods can utilize naturally generated drilling vibrations during construction as excitation sources, eliminating the need for frequent deployment of active seismic sources and possessing the potential for continuous observation without shutdown and synchronization with the construction process.

[0005] However, tunnel seismic advance prediction results typically involve significant uncertainties. On one hand, the complex tunnel construction environment limits the space for geophone deployment, restricts observation aperture, and introduces strong mechanical noise and unstable signal-to-noise ratios, impacting the quality of seismic records. On the other hand, the subsurface medium ahead of the tunnel face often exhibits strong heterogeneity and complex structural characteristics, while conventional interpretations frequently employ simplified velocity models or homogeneous medium assumptions, easily introducing errors during time-to-distance conversion and anomaly localization. Furthermore, seismic resolution is limited by wavelength, bandwidth, and signal-to-noise ratio, making it difficult to reliably identify small-scale anomalies at long distances. The mapping relationship between observational data and geological properties is also not unique; the same reflection event may correspond to different geological origins such as soft-hard rock interfaces, fracture zones, water-rich zones, or lithological abrupt changes. Therefore, even when seismic anomaly responses are obtained, their spatial location, anomaly type, and risk level remain subject to substantial uncertainty. Summary of the Invention

[0006] To address at least one of the technical problems mentioned above, this invention provides a method and system for identifying adverse geological conditions in tunnels using drilling seismic fusion. This method can fully utilize the existing advanced drilling operations and passive source vibration information during drill-and-blast construction to achieve continuous, quantitative, and interpretable identification of adverse geological risks ahead of the tunnel face without significantly increasing construction interference.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a method for identifying adverse geological conditions in tunnels using drilling seismic fusion, comprising the following steps: Acquire passive source seismic data and drilling parameters. While continuously acquiring passive source seismic data, simultaneously acquire drilling parameters during the advanced geological drilling process. The acquired passive source seismic signals are preprocessed, and empirical Green's function or virtual shot record is constructed to obtain the reconstructed passive source seismic record. The reconstructed passive source seismic record was decomposed according to different frequency bands, and candidate reflection locations, candidate propagation velocities, and reference travel time corrections were scanned. The seismic coherence response was calculated using a coherence function. By performing background subtraction, nonnegation, and area normalization on the seismic coherence response, the likelihood function of each passive source earthquake observation with respect to location x is obtained. A lithology identification model is established using drilling parameters, and an engineering prior probability distribution is constructed by combining the output probabilities of unfavorable lithology and lithology mutation. The likelihood function of the current passive source earthquake observation is updated using Bayesian method with the prior probability after the previous update, and the risk posterior probability distribution after fusing the current observation is obtained. Based on the final posterior probability distribution of the risk, calculate the integral probability of the risk interval and the comprehensive risk function, and output the risk peak location, risk width, risk level and construction treatment suggestions accordingly.

[0008] Furthermore, the coherent seismic response is expressed as: , in, This represents the correction of the k-th passive source earthquake observation at candidate location x, frequency band f, candidate propagation velocity v, and reference travel time. The coherent seismic response calculated under the given conditions; This represents the i-th passive source record corresponding to the k-th observation obtained by cross-correlation or deconvolution; is the channel weight of the i-th channel record; N is the number of detector channels participating in the coherent calculation; m is the sampling point number within the time window; This represents the local time offset of the m-th sampling point within the time window relative to the predicted travel time. This represents the predicted travel time of the i-th record corresponding to candidate position x. To prevent stable terms with a denominator of zero.

[0009] Furthermore, the first Secondary passive source earthquake observations for location The likelihood function is expressed as: , in, Indicates the candidate position ,frequency band Candidate propagation speed and reference time correction Under the condition, the observation data of the kth passive source earthquake The degree of support for the existence of adverse geological anomalies at this location; This represents the correction of the k-th passive source earthquake observation at candidate location x, frequency band f, candidate propagation velocity v, and reference travel time. The coherent seismic response calculated under the given conditions; ξ represents the passive source earthquake observation data of the kth time; ξ is a spatial integral variable used for normalization within the advance detection interval; For background coherence level; This refers to the advanced detection range currently covered by observations; This is a stabilizing term used to avoid the normalization denominator being zero.

[0010] Furthermore, the prior probability distribution of the project is as follows: , , , in, Indicates position Prior probability distribution of the project at the location, This represents the unnormalized a priori engineering risk value after amplitude limiting. This represents the lower bound of the prior probability. This represents the upper limit of the prior probability. This refers to supplementary prior knowledge formed from geological sketches, borehole logging, or empirical geological information. , , These represent the weighting coefficients for the probability of unfavorable lithology, the probability of abrupt lithological changes, and supplementary geological priors, respectively. Indicates position The probability of being located in an unfavorable geological or high-risk lithology category. This represents the probability of a lithological abrupt change, contact between soft and hard rocks, a fault contact zone, or a structural interface occurring at location x. Let Ω be the spatial integral variable, and let Ω be the advance detection interval.

[0011] Furthermore, location The probability of being classified as an unfavorable geological or high-risk lithology category The calculation formula is: , Location The probability of lithological abrupt changes, contact between soft and hard rocks, fault contact zones, or structural interfaces occurring at the location. The calculation formula is: , Where B represents the set of indexes for unfavorable geological conditions or high-risk lithology. This represents the drilling parameters at a given position x. Under these conditions, this location belongs to lithology type c. The probability, This represents the probability that the location x, at a distance δ to the left, belongs to lithology type c, where δ is the half-width of the spatial window and C is the total number of lithology types. This represents the probability that the lithology at a distance δ to the left of position x belongs to type c. This represents the probability that the location x, at a distance δ to the right, belongs to lithology type c.

[0012] Furthermore, the Bayesian update formula is: , in, To integrate the posterior probability distribution of risk after the observation of the k-th passive source earthquake, Represents the observation data of the k-th passive source earthquake. The likelihood function at candidate position x Indicates the fusion of the kth digit The risk posterior probability distribution obtained after one observation is used as the prior for the k-th update, where Ω represents the advance detection interval and ξ represents the spatial integral variable. Represents the k-th observation data In spatial location The likelihood function at the location; This represents the value of the posterior probability of the previous risk at spatial location ξ.

[0013] A second aspect of the present invention provides a tunnel adverse geological condition identification system based on drilling seismic fusion, comprising: The parameter acquisition module is used to acquire passive source seismic data and drilling parameters. While continuously acquiring passive source seismic data, it simultaneously acquires drilling parameters during the advanced geological drilling process. The data reconstruction module is used to preprocess the acquired passive source seismic signals and construct empirical Green's function or virtual shot record to obtain the reconstructed passive source seismic record. The seismic coherence response calculation module is used to decompose the reconstructed passive source seismic record according to different frequency bands, scan candidate reflection locations, candidate propagation velocities and reference travel time corrections, and calculate the seismic coherence response using a coherence function. The risk posterior probability distribution determination module is used to perform background subtraction, nonnegation, and area normalization on the seismic coherence response to obtain the likelihood function of each passive source seismic observation relative to the location; a lithology identification model is established using drilling parameters, and the engineering prior probability distribution is constructed by combining the output probabilities of unfavorable lithology and lithology mutation; the likelihood function of the current passive source seismic observation is updated with the previously updated prior probability using Bayesian method to obtain the risk posterior probability distribution after incorporating the current observation. The risk quantification module is used to calculate the risk interval integral probability and comprehensive risk function based on the final risk posterior probability distribution, and output the risk peak location, risk width, risk level and construction treatment suggestions accordingly.

[0014] A third aspect of the present invention provides a computer-readable storage medium.

[0015] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a tunnel adverse geology identification method based on drilling seismic fusion as described above.

[0016] A fourth aspect of the present invention provides a computer device.

[0017] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the tunnel adverse geology identification method based on drilling seismic fusion as described above.

[0018] A fifth aspect of the present invention provides a program product, which is a computer program product comprising a computer program that, when executed by a processor, implements the steps in the above-described method for identifying adverse geological conditions in tunnels using drilling seismic fusion.

[0019] Compared with the prior art, the beneficial effects of the present invention are: This invention uses the output of the drilling parameter lithology identification model as the engineering prior, transforms continuous passive source seismic observation results into a seismic likelihood function, and performs sequential updates through Bayesian inference to obtain the posterior probability distribution of adverse geological risks ahead of the tunnel face. It can fully utilize existing advance drilling operations and passive source vibration information during drill-and-blast construction, achieving continuous, quantitative, and interpretable identification of adverse geological risks ahead of the tunnel face without significantly increasing construction interference. Compared with traditional single-seismic interpretation or experience-based comprehensive judgment methods, this method can integrate the lithology prior reflected by drilling parameters, the forward wavefield response reflected by passive source seismic events, and observation uncertainties into the probability update process, thereby improving the reliability of adverse geological risk identification and providing more objective data support for advance support, grouting reinforcement, blasting parameter adjustment, and construction risk early warning.

[0020] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0021] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0022] Figure 1 This is a flowchart of a tunnel adverse geological condition identification method based on drilling seismic fusion provided in an embodiment of the present invention. Detailed Implementation

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0025] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0026] Example 1 like Figure 1 As shown in the figure, this embodiment provides a method for identifying adverse geological conditions in tunnels using drilling seismic fusion, including the following steps: Step 1: While continuously acquiring passive source seismic data, simultaneously acquire drilling parameters during the advanced geological drilling process; Let the tunnel axis direction or the direction of the advance drilling be the spatial coordinates. The current working face or borehole starting point position is The advanced detection range is: , in, For advanced detection range.

[0027] When conducting advanced geological drilling in drill-and-blast tunnels, the continuous drilling noise generated by the drill bit breaking rock, drill rod vibration, impact rotation, drilling rig propulsion, and the coupling effect between the drill bit and the surrounding rock is used as a passive source; a geophone array is deployed along the tunnel sidewall to continuously collect passive source seismic data. Specifically, no. One enters the time window, the first The passive source seismic signals acquired by each detector are denoted as: , in, For the number of detectors, For continuous observation sequence numbers, For time, each observation window can correspond to a fixed time period or a drilling depth segment.

[0028] While acquiring passive source seismic data, drilling parameters during advanced geological drilling are simultaneously acquired and registered to spatial coordinates x according to drilling depth, borehole trajectory or tunnel mileage. Specifically, the drilling parameter vector is defined as: , in, For drilling speed, To propel pressure or axial pressure, For torque, For rotational speed, To impact pressure, For flushing fluid pressure, This refers to the flushing fluid flow rate. For inflow, return water characteristics, or slag discharge characteristics, the ellipsis indicates other scalable drilling parameters.

[0029] Step 2: Preprocess the acquired passive source seismic signals and construct an empirical Green's function or virtual shot record; In this embodiment, the preprocessing of the acquired passive source seismic signals includes detrending, mean removal, outlier pulse removal, time normalization, spectral whitening, bandpass filtering, and segmented superposition. The empirical Green's function or virtual shot record can be constructed using cross-correlation or deconvolution, specifically as follows: For the two records within the k-th time window and Empirical Green's functions or virtual shot records can be constructed using cross-correlation: , in, This represents the empirical Green's function or virtual shot record obtained by cross-correlation of the i-th and j-th records within the k-th time window. This represents the passive source seismic signal acquired by the i-th detector at time t within the k-th time window. This represents the passive source seismic signal acquired by the j-th geophone at time t+τ within the k-th time window. For related delays, This is a time window function used to limit the time range of cross-correlation calculations or to weight samples at different times.

[0030] From this, we obtain This serves as the passive source seismic input record for subsequent coherent scanning and seismic likelihood construction.

[0031] Step 3: Decompose the reconstructed passive source seismic record according to different frequency bands, scan the candidate reflection locations, candidate propagation velocities and reference travel time corrections, and calculate the seismic coherence response using the coherence function; In this embodiment, passive source seismic records are divided into different frequency bands. f Decompose and analyze candidate reflection locations. Candidate propagation speed and reference time correction Perform a scan to obtain ; In this embodiment, for the one-dimensional approximation case, the predicted travel time function is... It can be represented as: , in, Indicates candidate reflection position In candidate propagation speed and reference time correction Under the given conditions, the travel time predicted for the i-th passive source record is... Indicates the candidate reflection location or candidate anomaly location; Indicates the candidate propagation speed; Represents the set of reference time correction terms; Indicates the equivalent passive source location or virtual source location; Indicates the position of the i-th detector; This represents the reference timing correction term corresponding to the i-th record.

[0032] It should be noted that for complex geological conditions, ray tracing, finite difference travel time calculation, or velocity model interpolation can also be used to obtain the results. .

[0033] As a further implementation, at candidate location x, the seismic coherence response is calculated using a lookup or equivalent coherence function: , in, This represents the correction of the k-th passive source earthquake observation at candidate location x, frequency band f, candidate propagation velocity v, and reference travel time. The coherent seismic response calculated under the given conditions; This represents the i-th passive source record corresponding to the k-th observation obtained by cross-correlation or deconvolution; is the channel weight of the i-th channel record; N is the number of detector channels participating in the coherent calculation; m is the sampling point number within the time window; This represents the local time offset of the m-th sampling point within the time window relative to the predicted travel time. This represents the predicted travel time of the i-th record corresponding to candidate position x; To prevent stable terms with a denominator of zero. The larger the value, the more the k-th passive source earthquake observation supports the existence of a reflection interface, velocity abrupt change, fracture zone, or other adverse geological anomalies at location x.

[0034] Step 4: Perform background subtraction, nonnegation, and area normalization on the seismic coherence response to obtain the likelihood function of each passive source earthquake observation with respect to location x; In this embodiment, the likelihood function of the k-th passive source seismic observation with respect to location x is expressed as: , in, This indicates the corrections at candidate position x, frequency band f, candidate propagation speed v, and reference travel time. Under the condition, the observation data of the kth passive source earthquake The degree of support for the existence of adverse geological anomalies at this location, i.e., the seismic observation likelihood function; ξ represents the passive source earthquake observation data of the kth time; ξ is a spatial integral variable used for normalization within the advance detection interval; For background coherence level; This refers to the advanced detection range currently covered by observations; This is a stabilizing term used to avoid the normalization denominator being zero.

[0035] Since the frequency band, propagation speed, and reference travel time curve all have uncertainties, the above parameters can be marginalized: , in, , , These represent the weights or probability distributions of the frequency band, propagation velocity, and reference travel time curve, respectively. In engineering implementation, this integral can be approximated by weighted summation of multi-band and multi-velocity scan results.

[0036] Step 5: Build a lithology identification model using drilling parameters, and construct the engineering prior probability distribution by combining the output probabilities of unfavorable lithology and lithology mutation. In this embodiment, a lithology identification model is established using drilling parameters as a real-time source of engineering prior knowledge. Let the set of lithology categories be: , in, Represents a set of lithological categories. These represent different lithological categories or different geological risk categories. This indicates the Cth lithology category. Lithology categories can be set as complete rock mass, fracture zone, weak interlayer, water-rich fracture zone, karst cavity, etc., according to engineering needs.

[0037] The lithology identification model is trained in advance using known geological logging, borehole core sampling, tunnel face sketching, laboratory tests, or historical engineering data. For any position x The model outputs a lithology probability vector: , in, This represents the lithology probability vector output by the lithology identification model at location x; This represents a pre-trained lithology identification model, where θ represents the model parameters. This represents the drilling parameter vector at position x; This represents the drilling parameters at a given position x. Under these conditions, this location belongs to lithology type i. The probability of.

[0038] If Bad represents a set of unfavorable geological or high-risk lithology categories, then the probability of unfavorable lithology at location x can be defined as: , in, B represents the probability that location x belongs to an unfavorable geological or high-risk lithology category; B represents the set of indices for unfavorable geological or high-risk lithology categories, such as indices corresponding to categories like fractured zones, water-rich zones, weak interlayers, and karst cavities. This represents the drilling parameters at a given position x. Under these conditions, this location belongs to lithology type c. The probability of.

[0039] To characterize abrupt changes in soft and hard rocks, fault contact zones, or lithological interfaces, the probability of lithological abrupt changes between adjacent spatial windows is defined: , in, This represents the probability of a lithological abrupt change, contact between soft and hard rocks, a fault contact zone, or a structural interface occurring at location x. This represents the probability that the lithology at a distance δ to the left of position x belongs to type c. This represents the probability that the lithology at a distance δ to the right of position x belongs to lithology type c, where δ is the half-width of the spatial window and C is the total number of lithology types. The greater the difference in lithology probability distributions between the left and right sides of x, the smaller the similarity term in the above formula. The larger the value, the more likely there is a lithological abrupt interface or structural contact zone at that location.

[0040] when x The greater the difference in lithological probability distribution between the left and right sides, the better. The larger the value, the more likely there is a lithological abrupt interface or structural contact zone at that location.

[0041] Furthermore, construct the prior probability distribution of the project: , , , in, This represents the unnormalized prior risk value of the project after amplitude limiting. This represents the prior probability distribution of the project at location x; This represents the lower bound of the prior probability; This represents the upper limit of the prior probability; It refers to supplementary priors formed from geological sketches, borehole logging, or empirical geological information; , , Let represent the weighting coefficients of the probability of unfavorable lithology, the probability of lithological abrupt change, and the supplementary geological prior, respectively, and satisfy . ; This indicates that the value within the parentheses is restricted to a certain range. Within the range; λ is the spatial integration variable; Ω is the advance detection interval. If supplementary geological information is not used, λ3 can be set to 0, and λ1+λ2=1 can be reset.

[0042] The engineering prior is not solely dependent on regional geological data or expert experience, but is generated in real time by inputting drilling parameters such as drilling speed, propulsion pressure, torque, rotational speed, impact pressure, flushing fluid pressure, and water inflow into the lithology identification model. By inputting these drilling parameters into the lithology identification model, lithology probabilities, unfavorable lithology probabilities, and lithological mutation probabilities are obtained, and these are transformed into engineering prior probability distributions, rather than merely serving as qualitative auxiliary judgments.

[0043] Step 6: Perform a Bayesian update on the likelihood function of the current passive source earthquake observation and the prior probability after the previous update to obtain the risk posterior probability distribution after fusing the current observation; For the k Secondary passive source earthquake observation Its likelihood function is The prior after the last update was The Bayesian update formula is: , in, To integrate the risk posterior probability distribution after the observation of the k-th passive source earthquake; Represents the observation data of the k-th passive source earthquake. The likelihood function at candidate position x; Indicates the fusion of the kth digit The posterior probability distribution of risk obtained after one observation is used as the prior for the k-th update; Ω represents the advance detection interval; ξ represents the spatial integral variable; Represents the k-th observation data In spatial location The likelihood function at the location; This represents the value of the posterior probability of the previous risk at spatial location ξ; initially, It is given by the prior probability distribution of the project.

[0044] If multiple relatively independent observational evidences exist within the same observation phase, such as different frequency bands, different detector combinations, different drilling depth windows, or different processing methods, then the joint posterior probability can be expressed as: , in, This represents the joint posterior probability distribution of adverse geological risk at location x after fusing n relatively independent observational evidences. The i-th observation evidence can be an observation result obtained from different frequency bands, different detector combinations, different drilling depth windows, or different processing methods. This represents the prior probability distribution of the initial project at position x; Let ξ represent the initial prior probability distribution of the project at spatial location ξ; Let x represent the likelihood function of the i-th observation evidence at candidate position x; Let ξ represent the likelihood function of the i-th observation evidence at spatial location ξ; Ω represents the advance detection interval; and ξ represents the spatial integral variable.

[0045] If a location has a high risk in the drilling parameter lithology prior and shows a stable coherent peak in multiple passive source seismic observations, then the posterior probability of that location is continuously enhanced; if a seismic peak appears only in a single observation and is inconsistent with the drilling parameter lithology prior, then its posterior probability is weakened during continuous updates.

[0046] Passive source seismic observations across multiple time windows, frequency bands, detector combinations, and drilling depths can be continuously updated using a Bayesian process. This gradually strengthens stable and consistent true anomalies while weakening random noise peaks and single false anomalies. By continuously updating the posterior probability through observations, the stable true anomalies supported by multiple observations are enhanced, while random noise peaks and single false anomalies are weakened. Assuming that after n consecutive Bayesian sequential updates of passive source seismic observations and drilling parameter engineering priors, the final risk posterior probability distribution is obtained... , represented as: .

[0047] Step 7: Based on the final posterior probability distribution of the risk, calculate the integral probability of the risk interval and the comprehensive risk function, and output the risk peak location, risk width, risk level and construction treatment suggestions accordingly.

[0048] Step 7 Using this as input, we further calculate the risk interval integral probability, risk peak location, risk width, and comprehensive risk function.

[0049] For a given lead distance interval [a, b], define the integral probability of the presence of adverse geological risks within this interval. for: , in, Let be the final posterior risk probability distribution obtained after n passive source earthquake observations and engineering prior Bayesian updates, representing the position in front of the tunnel face. x The posterior probability density or posterior probability distribution value of a location with adverse geological risks; Indicates the number of observations that participated in the update; x It indicates the spatial position in the direction of the tunnel axis or the direction of the advance drilling. Indicates the leading distance interval The integral probability of the presence of adverse geological risks within the region; and These represent the start and end points of the risk statistics interval, respectively.

[0050] If the consequence severity of different unfavorable geology on construction safety is considered , a comprehensive risk function is defined as: , According to the peak position, peak magnitude, and integral probability of the risk interval and the comprehensive risk function , the risk peak position, risk width, risk level and construction disposal suggestions are output. The details include: Let the final risk posterior probability distribution be , then the risk peak position , risk peak magnitude and risk width can be respectively defined as: , , , , where η is the risk width determination coefficient, which can be 0.5 or set according to engineering experience; denotes the risk concentration interval; denotes the risk width. If the consequence severity is considered , the comprehensive risk function and the comprehensive risk peak are: , , To comprehensively consider the peak probability, interval risk and consequence severity, a comprehensive risk score can be defined: , , where, denotes the comprehensive risk score; denotes the maximum value or normalization reference value of the consequence severity; , , are weight coefficients. The risk level can be determined according to preset thresholds: when <T1, it is determined as low risk; when T1≤ <T2, it is determined as yellow warning; when T2≤ <T3, it is determined as orange warning; when A risk level ≥T3 is classified as a red alert. Construction recommendations can be provided based on risk level and type: For a yellow alert, it is recommended to increase drilling density, enhance geological profiling, and shorten cycle depth; for an orange alert, it is recommended to implement advanced small-diameter pipe drilling, advanced grouting, adjust blasting parameters, strengthen initial support, and implement drainage and pressure reduction measures; for a red alert, it is recommended to suspend or restrict excavation, implement advanced curtain grouting, strengthen support, implement specialized drainage and pressure reduction, and conduct a specialized safety review before resuming construction. T1, T2, and T3 can be determined through historical project samples, expert experience, or engineering safety standards.

[0051] Example 2 This embodiment provides a tunnel adverse geological condition identification system based on drilling seismic fusion, including: The parameter acquisition module is used to acquire passive source seismic data and drilling parameters. While continuously acquiring passive source seismic data, it simultaneously acquires drilling parameters during the advanced geological drilling process. The data reconstruction module is used to preprocess the acquired passive source seismic signals and construct empirical Green's function or virtual shot record to obtain the reconstructed passive source seismic record. The seismic coherence response calculation module is used to decompose the reconstructed passive source seismic record according to different frequency bands, scan candidate reflection locations, candidate propagation velocities and reference travel time corrections, and calculate the seismic coherence response using a coherence function. The risk posterior probability distribution determination module is used to perform background subtraction, nonnegation, and area normalization on the seismic coherence response to obtain the likelihood function of each passive source seismic observation relative to the location; a lithology identification model is established using drilling parameters, and the engineering prior probability distribution is constructed by combining the output probabilities of unfavorable lithology and lithology mutation; the likelihood function of the current passive source seismic observation is updated with the previously updated prior probability using Bayesian method to obtain the risk posterior probability distribution after incorporating the current observation. The risk quantification module is used to calculate the risk interval integral probability and comprehensive risk function based on the final risk posterior probability distribution, and output the risk peak location, risk width, risk level and construction treatment suggestions accordingly.

[0052] It should be noted that the specific implementation of the tunnel adverse geology identification system based on drilling seismic fusion in this embodiment of the invention is similar to the specific implementation of the tunnel adverse geology identification method based on drilling seismic fusion in this embodiment of the invention. Please refer to the description in the method section for details. To reduce redundancy, it will not be repeated here.

[0053] Example 3 This embodiment provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps in the tunnel adverse geology identification method of drilling seismic fusion as described above.

[0054] Example 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the tunnel adverse geological condition identification method based on drilling seismic fusion as described above.

[0055] Example 5 This embodiment provides a program product, which is a computer program product, including a computer program. When the computer program is executed by a processor, it implements the steps in the tunnel adverse geological condition identification method of drilling seismic fusion as described above.

[0056] 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 hardware embodiments, software embodiments, or embodiments 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 and optical storage) containing computer-usable program code.

[0057] 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.

[0058] 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.

[0059] 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.

[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] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying adverse geological conditions in tunnels using seismic fusion during drilling, characterized in that, Includes the following steps: Acquire passive source seismic data and drilling parameters. While continuously acquiring passive source seismic data, simultaneously acquire drilling parameters during the advanced geological drilling process. The acquired passive source seismic signals are preprocessed, and empirical Green's function or virtual shot record is constructed to obtain the reconstructed passive source seismic record. The reconstructed passive source seismic record was decomposed according to different frequency bands, and candidate reflection locations, candidate propagation velocities, and reference travel time corrections were scanned. The seismic coherence response was calculated using a coherence function. By performing background subtraction, nonnegation, and area normalization on the seismic coherence response, the likelihood function of each passive source earthquake observation for the candidate location is obtained. A lithology identification model is established using drilling parameters, and an engineering prior probability distribution is constructed by combining the output probabilities of unfavorable lithology and lithology mutation. The likelihood function of the current passive source earthquake observation is updated using Bayesian method with the prior probability after the previous update, and the risk posterior probability distribution after fusing the current observation is obtained. Based on the final posterior probability distribution of the risk, calculate the integral probability of the risk interval and the comprehensive risk function, and output the risk peak location, risk width, risk level and construction treatment suggestions accordingly.

2. The method for identifying adverse geological conditions in tunnels using drilling seismic fusion as described in claim 1, characterized in that, The coherent response of an earthquake is expressed as: ， in, This represents the correction of the k-th passive source earthquake observation at candidate location x, frequency band f, candidate propagation velocity v, and reference travel time. The coherent seismic response calculated under the given conditions; This represents the i-th passive source record corresponding to the k-th observation obtained by cross-correlation or deconvolution; is the channel weight of the i-th channel record; N is the number of detector channels participating in the coherent calculation; m is the sampling point number within the time window; This represents the local time offset of the m-th sampling point within the time window relative to the predicted travel time. This represents the predicted travel time of the i-th record corresponding to candidate position x. To prevent stable terms with a denominator of zero.

3. The method for identifying adverse geological conditions in tunnels using drilling seismic fusion as described in claim 1, characterized in that, No. Secondary passive source earthquake observations for location The likelihood function is expressed as: ， in, Indicates the candidate position ,frequency band Candidate propagation speed and reference time correction Under the condition, the observation data of the kth passive source earthquake The degree of support for the existence of adverse geological anomalies at this location; This represents the correction of the k-th passive source earthquake observation at candidate location x, frequency band f, candidate propagation velocity v, and reference travel time. The coherent seismic response calculated under the given conditions; ξ represents the passive source earthquake observation data of the kth time; ξ is a spatial integral variable used for normalization within the advance detection interval; For background coherence level; This refers to the advanced detection range currently covered by observations; This is a stabilizing term used to avoid the normalization denominator being zero.

4. The method for identifying adverse geological conditions in tunnels using drilling seismic fusion as described in claim 1, characterized in that, The prior probability distribution of the project is: , , , in, Indicates position Prior probability distribution of the project at the location, This represents the unnormalized a priori engineering risk value after amplitude limiting. This represents the lower bound of the prior probability. This represents the upper limit of the prior probability. This refers to supplementary prior knowledge formed from geological sketches, borehole logging, or empirical geological information. , , These represent the weighting coefficients for the probability of unfavorable lithology, the probability of abrupt lithological changes, and supplementary geological priors, respectively. Indicates position The probability of being located in an unfavorable geological or high-risk lithology category. This represents the probability of a lithological abrupt change, contact between soft and hard rocks, a fault contact zone, or a structural interface occurring at location x. Let Ω be the spatial integral variable, and let Ω be the advance detection interval.

5. The method for identifying adverse geological conditions in tunnels using drilling seismic fusion as described in claim 4, characterized in that, Location The probability of being classified as an unfavorable geological or high-risk lithology category The calculation formula is: ， Location The probability of lithological abrupt changes, contact between soft and hard rocks, fault contact zones, or structural interfaces occurring at the location. The calculation formula is: ， Where B represents the set of indexes for unfavorable geological conditions or high-risk lithology. This represents the drilling parameters at a given position x. Under these conditions, this location belongs to lithology type c. The probability, This represents the probability that the location x, at a distance δ to the left, belongs to lithology type c, where δ is the half-width of the spatial window and C is the total number of lithology types. This represents the probability that the lithology at a distance δ to the left of position x belongs to type c. This represents the probability that the location x, at a distance δ to the right, belongs to lithology type c.

6. The method for identifying adverse geological conditions in tunnels using drilling seismic fusion as described in claim 1, characterized in that, The Bayesian update formula is: ， in, To integrate the posterior probability distribution of risk after the observation of the k-th passive source earthquake, Represents the observation data of the k-th passive source earthquake. The likelihood function at candidate position x Indicates the fusion of the kth digit The risk posterior probability distribution obtained after one observation is used as the prior for the k-th update, where Ω represents the advance detection interval and ξ represents the spatial integral variable. Represents the k-th observation data In spatial location The likelihood function at the location; This represents the value of the posterior probability of the previous risk at spatial location ξ.

7. A tunnel adverse geological condition identification system based on drilling seismic fusion, characterized in that, include: The parameter acquisition module is used to acquire passive source seismic data and drilling parameters. While continuously acquiring passive source seismic data, it simultaneously acquires drilling parameters during the advanced geological drilling process. The data reconstruction module is used to preprocess the acquired passive source seismic signals and construct empirical Green's function or virtual shot record to obtain the reconstructed passive source seismic record. The seismic coherence response calculation module is used to decompose the reconstructed passive source seismic record according to different frequency bands, scan candidate reflection locations, candidate propagation velocities and reference travel time corrections, and calculate the seismic coherence response using a coherence function. The risk posterior probability distribution determination module is used to perform background subtraction, nonnegation, and area normalization on the seismic coherence response to obtain the likelihood function of each passive source seismic observation relative to the location; a lithology identification model is established using drilling parameters, and the engineering prior probability distribution is constructed by combining the output probabilities of unfavorable lithology and lithology mutation; the likelihood function of the current passive source seismic observation is updated with the previously updated prior probability using Bayesian method to obtain the risk posterior probability distribution after incorporating the current observation. The risk quantification module is used to calculate the risk interval integral probability and comprehensive risk function based on the final risk posterior probability distribution, and output the risk peak location, risk width, risk level and construction treatment suggestions accordingly.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the tunnel adverse geology identification method of drilling seismic fusion as described in any one of claims 1-6.

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 program, it implements the steps in the tunnel adverse geology identification method based on drilling seismic fusion as described in any one of claims 1-6.

10. A program product, said program product being a computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps in the tunnel adverse geology identification method of drilling seismic fusion as described in any one of claims 1-6.

Images