Method for identifying geological conditions of deep-buried long tunnel based on multi-source geological exploration data

Abstract

The application discloses a deep-buried long tunnel geological condition identification method based on multi-source geological exploration data, which comprises the following steps: preprocessing and standardizing geological parameters; converting the parameter values after standardization into abnormal indexes in the interval [0, 1] to obtain abnormal indexes of each geological parameter; calculating the weight of the abnormal indexes of each geological parameter; calculating a comprehensive abnormal index Si based on the abnormal indexes of each geological parameter and the weight of the abnormal indexes of each geological parameter; and when the comprehensive abnormal index Si is greater than a preset identification threshold S0, it is judged that the geological condition is poor. The method fuses multi-element data such as wave velocity, well diameter, nuclear logging, resistivity and drilling fluid leakage, comprehensively reflects the geological condition from multiple dimensions such as rock mass integrity, hole wall stability, lithological composition, water content characteristics and permeability, avoids misjudgment caused by the influence of single parameters on geological environment interference factors, can more accurately present the real condition of the geological body, provides reliable geological basis for engineering construction, and guarantees the safety of the engineering.

Description

Technical Field

[0001] This invention belongs to the field of underground engineering, specifically relating to a method for accurately identifying the geological conditions of deep-buried long tunnels based on multi-source geological exploration data. Background Technology

[0002] With the rapid development of national infrastructure construction, the importance of deep-buried long tunnel projects in fields such as hydropower development is becoming increasingly prominent. These projects often traverse complex geological zones, encountering adverse geological conditions such as fault fracture zones, karst caves, and water-rich fissures, which can easily lead to significant construction risks such as sudden water inrushes, mudslides, and surrounding rock instability. Therefore, accurate identification of geological conditions is a core prerequisite for ensuring project safety and controlling investment costs.

[0003] Currently, geological exploration of deep-buried long tunnels mainly relies on borehole geophysical exploration technology, which obtains multi-dimensional data such as wave velocity (e.g., sonic logging), well diameter, nuclear logging (natural gamma / density), resistivity, and drilling fluid loss through boreholes. These parameters reflect geological conditions from dimensions such as rock mass integrity, borehole wall stability, lithological composition, water-bearing characteristics, and permeability. However, existing technologies face the following key bottlenecks:

[0004] 1. Geological features are presented in a one-sided manner.

[0005] Most methods rely on a single parameter, but geological characteristics are the result of multi-parameter coupling. A single parameter is highly susceptible to interference factors in the geological environment, such as changes in lithology around the borehole and localized groundwater flow, which can lead to parameter anomalies. This, in turn, results in biased judgments of geological conditions, a high misjudgment rate, and an inability to comprehensively and accurately reflect the true condition of the geological body.

[0006] 2. Multi-parameter fusion methods lack objectivity.

[0007] While some methods attempt to fuse multi-source data, their weight allocation relies on expert experience and fails to consider the differences in information content of the parameters themselves. This results in fusion results that are insufficiently targeted and lack adaptability. For example, in the identification of fault fracture zones, wave velocity parameters may be more sensitive to the degree of rock mass fracture and contain more information, while natural gamma parameters contain relatively less information. However, if the weights are allocated equally according to expert experience, the importance of wave velocity parameters will be weakened, causing the fusion results to fail to highlight key geological features. This weight allocation method, lacking objective basis, makes the fusion results insufficiently targeted and difficult to adapt flexibly to tunnel engineering projects with different geological conditions. It also results in poor adaptability and an inability to accurately capture the unique characteristics of different geological conditions.

[0008] Therefore, there is an urgent need for a precise identification method for the geological conditions of deep-buried long tunnels based on multi-source geological exploration data, so as to improve the identification accuracy and engineering adaptability of the geological conditions of deep-buried long tunnels. Summary of the Invention

[0009] The purpose of this invention is to provide a method for accurately identifying the geological conditions of deep-buried long tunnels based on multi-source geological exploration data, in order to solve the following key problems existing in the current technology for identifying the geological conditions of deep-buried long tunnels:

[0010] This addresses the problem that a single data source leads to a one-sided reflection of geological characteristics, making it susceptible to interference from factors in the geological environment (such as changes in lithology around the borehole, localized groundwater flow, etc.), resulting in biased judgments of geological conditions, a high rate of misjudgment, and an inability to comprehensively and accurately reflect the true condition of the geological body.

[0011] It also addresses the problems of existing scoring methods lacking objectivity, relying on expert experience for weight allocation, failing to consider the differences in information content of the parameters themselves, resulting in insufficient targeting and poor adaptability of the fusion results, inability to highlight key geological features, difficulty in flexibly adapting to tunnel projects with different geological conditions, and inability to accurately capture the unique characteristics of different geological conditions.

[0012] To achieve the above objectives, the technical solution of this invention is as follows:

[0013] A method for identifying geological conditions of deep-buried long tunnels based on multi-source geological exploration data, the method comprising:

[0014] S1: Perform preprocessing and standardization of geological parameters;

[0015] S2: Convert the standardized parameter values ​​in step S1 into anomaly indices in the [0,1] interval to obtain the anomaly indices of various geological parameters;

[0016] S3: Calculate the weights of the anomaly indices of various geological parameters;

[0017] S4: Calculate the comprehensive anomaly index Si based on the anomaly indices of the various geological parameters and the weights of the anomaly indices of the various geological parameters.

[0018] S5: When the comprehensive anomaly index Si is greater than the preset identification threshold S0, it is judged as unfavorable geology.

[0019] Furthermore, the preprocessing of the geological parameters includes noise reduction processing of the geological parameters, using equation (1) to perform smooth noise reduction processing on the geological data.

[0020] , (1)

[0021] in, x j For the first j The original parameter values ​​of each measurement point; For the first i The smoothed parameter values ​​of each point; k Let be the window radius.

[0022] Furthermore, the standardization of the geological parameters involves converting the smoothed and denoised geological data into dimensionless data using formula (2).

[0023] , (2)

[0024] in, This is the mean of the smoothed parameters; The standard deviation of the smoothed parameters; These are the standardized parameter values.

[0025] Furthermore, the calculation of the anomaly index of the geological parameters includes the wave velocity anomaly index. I v Calculate the wave velocity anomaly index. I v The calculation formula is:

[0026] , (3)

[0027] Among them, take , This represents the mean of the standardized wave velocity in the normal segment. The standard deviation of the normalized wave velocity; This is the normalized value of the wave velocity. The value is calculated according to formula (2).

[0028] Furthermore, the calculation of the anomaly index of the geological parameters includes the wellbore anomaly index. I d Calculate the wellbore anomaly index. I d The calculation formula is:

[0029] , (4)

[0030] Among them, take , This represents the average standardized wellbore diameter for the normal section. The standard deviation of the standardized well diameter in the normal section is taken as... , This is the standardized value for well diameter. The value is calculated according to formula (2).

[0031] Furthermore, the calculation of the anomaly index of the geological parameters includes the natural gamma anomaly index. I GR Calculate the natural gamma anomaly index. I GR The calculation formula is:

[0032] , (5)

[0033] Among them, take , The mean of the standardized gamma values ​​for the normal segment. The standard deviation of the standardized gamma values ​​in the normal range. This is the standardized value of the natural gamma. The value is calculated according to formula (2).

[0034] Furthermore, the calculation of the anomaly index of the geological parameters includes the resistivity anomaly index. I ρ Calculate the resistivity anomaly index. I ρ The calculation formula is:

[0035] , (6)

[0036] Among them, take , This represents the mean of the standardized resistivity for the normal range. The standard deviation of the normalized resistivity is given by the standard deviation of the resistivity. This is the resistivity standardized value. The value is calculated according to formula (2).

[0037] Furthermore, the calculation of the anomaly index of the geological parameters includes the leakage anomaly index. I L Calculate the leakage anomaly index. I L The calculation formula is:

[0038] , (7)

[0039] Among them, take , This represents the mean of the standardized leakage rate during the normal segment. The standard deviation of the normal segment's standardized leakage rate. This is the standardized value of the leakage. The value is calculated according to formula (2).

[0040] Furthermore, the weighting calculation of the geological parameter anomaly index in step S3 includes:

[0041] S31: Construct an anomaly index matrix by dividing the tunnel into n unit segments along the axis, with each unit segment corresponding to an anomaly index of five parameters, forming a matrix:

[0042] , (8)

[0043] in, The anomaly index of the j-th parameter in the k-th unit segment;

[0044] S32: Normalization process, converting the matrix into probabilities and normalizing them to [0,1];

[0045] , (9)

[0046] like ,but ;

[0047] in, Let the percentage of the abnormal index of the j-th parameter in the k-th unit segment satisfy the following condition: ;

[0048] S33: Calculate the degree of parameter dispersion, and use equation (10) to measure the degree of parameter dispersion.

[0049] , (10)

[0050] in, These are the normalization coefficients;

[0051] S34: Calculate the weights, if the information content of a certain parameter is 1- The proportion of the information content of the weighted parameters to the total information content is:

[0052] , (11)

[0053] Where, in the formula The weight of the j-th parameter satisfies .

[0054] Furthermore, the comprehensive anomaly index S i The calculation method is as follows:

[0055] No. i The comprehensive anomaly index of a unit segment is the weighted sum of the anomaly indices of each parameter:

[0056] , (12)

[0057] in For wave speed weighting, For well diameter weight, For natural gamma weight, For resistivity weighting, Leakage weight, , , , , Calculate according to formula (11); For the first iWave velocity anomaly index of unit segment, For the first i Anomaly index of well diameter in unit section, For the first i The natural gamma anomaly index of the unit segment, For the first i The resistivity anomaly index of the unit segment, For the first i The leakage anomaly index of the unit segment.

[0058] The technical solution of this invention has the following technical effects:

[0059] 1. This invention improves the comprehensiveness and accuracy of geological condition identification: This method integrates multi-dimensional data such as wave velocity, well diameter, nuclear logging, resistivity, and drilling fluid loss, and comprehensively reflects geological conditions from multiple dimensions such as rock mass integrity, borehole wall stability, lithological composition, water-bearing characteristics, and permeability. It avoids misjudgment caused by the influence of geological environmental interference factors on a single parameter, and can present the true condition of the geological body more comprehensively and accurately, significantly reducing the misjudgment rate.

[0060] 2. This invention enhances the relevance and adaptability of results through objective multi-parameter fusion: By objectively allocating the fusion weights of multiple parameters, it fully considers the differences in information content of each parameter, avoiding the weakening of key features caused by relying on expert experience to average out weights. This enables the fusion results to accurately capture the unique characteristics of different geological conditions, providing stronger adaptability to tunnel engineering projects with varying geological conditions and improving the ability to adapt to complex geological environments.

[0061] 3. This invention can ensure project safety and control investment costs: With higher identification accuracy, it can accurately identify geological conditions, provide reliable geological basis for project construction, effectively prevent major construction risks such as water inrush and mudslide, and surrounding rock instability, and ensure project safety; at the same time, it reduces unnecessary engineering measures or rework caused by misjudgment, thereby reasonably controlling investment costs and providing strong support for the efficient advancement of deep-buried long tunnel projects. Attached Figure Description

[0062] Figure 1 This is a flowchart of the method for accurately identifying geological conditions of deep-buried long tunnels based on multi-source geological exploration data, as per the present invention. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only some, not all, of the embodiments of this invention, and are not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0064] This invention proposes a method for accurately identifying the geological conditions of deep-buried long tunnels based on multi-source geological exploration data. The method mainly includes five steps: data preprocessing and standardization, single-parameter anomaly index quantification, multi-parameter weight calculation, comprehensive anomaly index and threshold judgment, and verification and optimization, as detailed below:

[0065] I. Data Preprocessing and Standardization

[0066] Raw geological exploration data are affected by instrument accuracy, environmental interference, and the heterogeneity of geological bodies, resulting in random noise (such as instantaneous measurement errors) and systematic bias (such as differences in the dimensions of different instruments). Preprocessing is required to eliminate interference and lay the data foundation for subsequent analysis.

[0067] 1. Noise Reduction Processing

[0068] Geological parameters are continuous in spatial distribution (geological conditions of adjacent tunnel sections change gradually), and random noise is characterized by high-frequency jump fluctuations. Equation (1) is used to smooth the data.

[0069] , (1)

[0070] in, x j For the first j The original parameter values ​​of each measurement point (such as wave velocity, well diameter, etc.); For the first i The smoothed parameter values ​​of each point; k The window radius determines the smoothness.

[0071] 2. Standardized processing

[0072] The dimensions and orders of magnitude of different geological parameters differ significantly. They are standardized using Equation (2) and converted into dimensionless data.

[0073] , (2)

[0074] in, This is the mean of the smoothed parameters. ;

[0075] The standard deviation of the smoothed parameters. ;

[0076] The standardized parameter value reflects the degree to which the data at that point deviates from the mean (in standard deviation).

[0077] II. Quantification of Single-Parameter Anomaly Index

[0078] Single-parameter anomalies in geological conditions have clear physical orientations. The standardized parameter values ​​need to be converted into anomaly indices in the range of [0,1] to quantify the degree to which the parameters of geological conditions deviate from the normal range.

[0079] (1) Wave speed anomaly index ( I v )

[0080] The higher the integrity of the rock mass, the faster the elastic wave propagation speed. In fault fracture zones, weak interlayers, and other unfavorable sections, due to the destruction of the rock mass structure, the wave velocity (especially the longitudinal wave velocity) increases. v p () significantly reduced.

[0081] First, based on the wave velocity statistics of the known normal segment, we take... = 2 This threshold covers 95% of the normal data segment; values ​​below this are considered abnormal. The abnormality index formula is:

[0082] (3)

[0083] in, This represents the mean of the standardized wave velocity in the normal segment. The standard deviation of the normalized wave velocity; This is the normalized value of the wave velocity. The value is calculated according to formula (2).

[0084] (2) Wellbore anomaly index ( I d )

[0085] During drilling, the wellbore is stable in intact rock masses and the well diameter is close to the design value; in unfavorable sections (such as loose and fractured zones), the well diameter is significantly enlarged due to wellbore collapse or drilling fluid erosion (diameter enlargement phenomenon).

[0086] Pick If the value exceeds this, it is considered an abnormal expansion of the diameter.

[0087] in, This represents the average standardized wellbore diameter for the normal section. The standard deviation of the normal wellbore diameter. This is the standardized value for well diameter. The value is calculated according to formula (2).

[0088] (3) Natural Gamma Anomaly Index ( I GR )

[0089] Natural gamma values ​​are positively correlated with the content of radioactive elements in the rock mass. Soft rock masses such as claystone and argillaceous interlayers have significantly higher gamma values ​​than hard rock masses due to the adsorption of radioactive elements.

[0090] Pick Values ​​exceeding this value are considered abnormal natural gamma values.

[0091] in, The mean of the standardized gamma values ​​for the normal segment. The standard deviation of the standardized gamma values ​​in the normal range. This is the standardized value of the natural gamma. The value is calculated according to formula (2).

[0092] (4) Resistivity anomaly index ( I ρ )

[0093] Rock resistivity is negatively correlated with water content and degree of fragmentation: intact and dry rock mass has high resistivity, while fragmented and water-bearing sections have low resistivity.

[0094] Pick If the value exceeds this value, it is considered an abnormal resistivity.

[0095] , (6)

[0096] in, This represents the mean of the standardized resistivity for the normal range. The standard deviation of the normalized resistivity is given by the standard deviation of the resistivity. This is the resistivity standardized value. The value is calculated according to formula (2).

[0097] (5) Leakage anomaly index ( I L )

[0098] Drilling fluid loss reflects the permeability of the rock mass: intact rock masses with poorly developed fissures have low loss; karst areas or areas with dense fissures have high permeability and significantly higher loss.

[0099] Pick If the value exceeds this, it is considered an abnormal leakage.

[0100] , (7)

[0101] in, This represents the mean of the standardized leakage rate during the normal segment. The standard deviation of the normal segment's standardized leakage rate. This is the standardized value of the leakage. The value is calculated according to formula (2).

[0102] III. Multi-parameter weight calculation

[0103] Since different parameters have varying sensitivities to indicating defective segments, the weights of each parameter are objectively quantified to avoid subjective assignment bias.

[0104] 1. Construct an anomaly index matrix

[0105] The tunnel is divided into n unit segments along the axis (each 1m is one unit), and each unit segment corresponds to anomaly indices of 5 parameters, forming a matrix:

[0106] , (8)

[0107] in, This is the anomaly index of the j-th parameter in the k-th unit segment (j=1 corresponds to wave velocity, j=2 corresponds to well diameter, j=3 corresponds to natural gamma value, j=4 corresponds to resistivity, j=5 corresponds to leakage).

[0108] 2. Normalization process: Convert the matrix into probabilities and normalize it to [0,1].

[0109] , (9)

[0110] like ,but ;

[0111] in, Let the percentage of the abnormal index of the j-th parameter in the k-th unit segment satisfy the following condition: ;

[0112] 3. Calculate the degree of parameter dispersion, and use equation (10) to measure the degree of parameter dispersion.

[0113] , (10)

[0114] in, For normalization coefficients, ensure When the anomaly index of a certain parameter is equal across all unit segments ( =1 / n), =1 (no distinguishing ability); when only one unit segment of a certain parameter has an anomaly ( =1), =0 (extremely strong distinguishing ability).

[0115] 4. Calculate the weights. If the information content of a certain parameter is 1- The proportion of the information content of the weighted parameters to the total information content is:

[0116] , (11)

[0117] Where, in the formula The weight of the j-th parameter satisfies .

[0118] IV. Comprehensive Anomaly Index and Threshold Judgment

[0119] This step involves weighted summation of single-parameter anomaly indices to obtain a comprehensive anomaly index, which is then integrated with multi-source data to ultimately determine the tunnel's geological conditions.

[0120] 1. Comprehensive Abnormality Index (S i )

[0121] No. i The comprehensive anomaly index of a unit segment is the weighted sum of the anomaly indices of each parameter:

[0122] , (12)

[0123] in For wave speed weighting, For well diameter weight, For natural gamma weight, For resistivity weighting, Leakage weight, , , , , Calculate according to formula (11); For the first i Wave velocity anomaly index of unit segment, For the first i Anomaly index of well diameter in unit section, For the first i The natural gamma anomaly index of the unit segment, For the first i The resistivity anomaly index of the unit segment, For the first i The leakage anomaly index of the unit segment. For the first i The comprehensive anomaly index of the segment ranges from [0,1]. The larger the value, the higher the probability that the segment has unfavorable geological conditions.

[0124] 2. Identification threshold (S0)

[0125] The threshold was determined using a combination of statistical methods and engineering verification.

[0126] (1) Select normal sections (at least 50 units) that have passed drilling verification and calculate the mean of their comprehensive anomaly index. and ;

[0127] (2) Take This value corresponds to a 95% confidence level, meaning the probability of a normal segment being misclassified as a bad segment is less than 5% when a certain unit segment... > At that time, it was determined to be unfavorable geological conditions.

[0128] (3) For complex geological areas (such as normal sections and unfavorable sections) (For overlapping distributions), dynamic threshold adjustment can be used: through ROC curve analysis, select segments with a correct identification rate of ≥90% for defective segments and a false positive rate of 10% for normal segments. As the optimal threshold.

[0129] V. Verification and Optimization

[0130] Based on the actual field measurement results, the method was validated and optimized.

[0131] 1. Accuracy Verification: Compare with actual drilling results to calculate the identification accuracy (P = number of correctly identified segments / total number of identified segments) and recall (R = number of correctly identified defective segments / actual number of defective segments).

[0132] 2. Dynamic Optimization: If the abnormal direction of parameters in a certain area does not conform to the norm (such as a high-resistance faulty section), the judgment direction of the single-parameter abnormality index can be adjusted (e.g., (Calculation time).

[0133] The above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for identifying geological conditions of a deep-buried long tunnel based on multi-source geological exploration data, characterized in that The method comprises: S1: preprocessing and standardizing the geological parameters; S2: converting the parameter values standardized in the S1 step into an anomaly index in the interval [0, 1] to obtain the anomaly index of each geological parameter; S3: calculating the weight of the anomaly index of each geological parameter; S4: calculating a comprehensive anomaly index S based on the anomaly indexes of the geological parameters and the weights of the anomaly indexes of the geological parameters i ; S5: When the comprehensive anomaly index S i is greater than a preset identification threshold S0, it is determined that the geological condition is poor. The weight calculation of the anomaly index of the geological parameter in the S3 step comprises: S31: constructing an anomaly index matrix, dividing the tunnel along the axis into n unit segments, and each unit segment corresponding to the anomaly index of five parameters to form a matrix: ， （8） wherein, is the anomaly index for the jth parameter of the kth cell segment; S32: normalization processing, converting the matrix into a probability, and normalizing to [0, 1]; , （9） If , then ; wherein, is the abnormal index proportion of the jth parameter in the kth unit segment, satisfying ; S33: calculating the parameter dispersion degree, using formula (10) to measure the parameter dispersion degree, , （10） wherein is a normalization coefficient; S34: Calculate the weight, if the information quantity of a parameter is 1 , the proportion of the information quantity of the parameter in the total information quantity is: ， （11） wherein in the formula is the weight of the jth parameter, satisfying .

2. The method for identifying geological conditions of a long deep-buried tunnel based on multi-source geological exploration data according to claim 1, characterized in that: The preprocessing of the geological parameters comprises denoising processing of the geological parameters, and the smoothed denoising processing of the geological data is performed by using formula (1), ， （1） wherein, x j is the original parameter value for the j th measurement point; is the smoothed parameter value for the i th point; k is the window radius.

3. The method for identifying geological conditions of a long deep-buried tunnel based on multi-source geological exploration data according to claim 1, characterized in that: The standardization processing of the geological parameters is to convert the smoothed denoised geological data into dimensionless data by formula (2), ， （2） wherein, is the mean of the smoothed parameter; is the standard deviation of the smoothed parameter; is the normalized parameter value.

4. The method for identifying geological conditions of a long deep-buried tunnel based on multi-source geological exploration data according to claim 1, characterized in that: The abnormal index calculation of the geological parameter includes a wave velocity abnormal index I v The wave velocity abnormal index is calculated I v The calculation formula is: ， （3） wherein, take , is the mean of the normalized wave velocity of normal segments, is the standard deviation of the normalized wave velocity of normal segments; is the normalized value of the wave velocity, the value is calculated according to formula (2).

5. The method for identifying geological conditions of a long deep-buried tunnel based on multi-source geological exploration data according to claim 1, characterized in that: The abnormal index calculation of the geological parameter includes a caliper abnormal index I d The abnormal index calculation of the geological parameter includes a caliper abnormal index I d The calculation formula is: ， （4） Wherein, take , is the mean value of the normalized hole diameter of the normal section, is the standard deviation of the normalized hole diameter of the normal section, take , is the normalized value of the hole diameter, The value is calculated according to formula (2).

6. The method for identifying geological conditions of a long deep-buried tunnel based on multi-source geological exploration data according to claim 1, characterized in that: The anomaly index calculation of the geological parameter includes a natural gamma anomaly index I GR The anomaly index calculation of the geological parameter includes a natural gamma anomaly index I GR The calculation formula is: ， （5） wherein, take , is the mean value of the normalized gamma value of the normal section, is the standard deviation of the normalized gamma value of the normal section, is the normalized value of the natural gamma value, the value is calculated according to formula (2).

7. The method for identifying geological conditions of a long deep-buried tunnel based on multi-source geological exploration data according to claim 1, characterized in that: The abnormal index calculation of the geological parameter includes a resistivity abnormal index I ρ , calculate, resistivity abnormal index I ρ The calculation formula is: ， （6） wherein, take , is the mean of the normalized resistivity of the normal section, is the standard deviation of the normalized resistivity of the normal section, is the normalized value of the resistivity, The value is calculated according to formula (2).

8. The method for identifying geological conditions of a long deep-buried tunnel based on multi-source geological exploration data according to claim 1, characterized in that: The abnormal index calculation of the geological parameter includes a leakage abnormal index I L The leakage abnormal index is calculated I L The calculation formula is: ， （7） wherein, take , is the mean of the normalized leakage amount of the normal section, is the standard deviation of the normalized leakage amount of the normal section, is the normalized value of the leakage amount, the value is calculated according to formula (2).

9. The method for identifying geological conditions of a deep long tunnel based on multi-source geological exploration data according to claim 1, characterized in that, The comprehensive abnormality index S i The calculation method is: No. i The comprehensive anomaly index of a unit segment is the weighted sum of the anomaly indices of each parameter: ， （12） wherein is a wave velocity weight, is a caliper weight, is a natural gamma weight, is a resistivity weight, is a loss quantity weight, , , , , is calculated according to formula (11); is a wave velocity anomaly index of the i unit section, is a caliper anomaly index of the i unit section, is a natural gamma anomaly index of the i unit section, is a resistivity anomaly index of the i unit section, is a loss quantity anomaly index of the i unit section.

Images