Multi-source data fusion tunnel unfavorable geological problem analysis method and device

Abstract

The invention relates to the technical field of geological analysis, discloses a multi-source data fusion tunnel unfavorable geological problem analysis method and device, and aims at solving the problem that an existing tunnel unfavorable geological problem analysis scheme is poor in accuracy. The scheme mainly comprises the following steps: establishing a whole-process information database and an unfavorable geological problem index system of a tunnel; determining a detection index and corresponding detection data corresponding to the unfavorable geological problem to be analyzed; converting the detection data into a risk value, dividing a detection interval into a plurality of sections according to the coverage range of different detection data, and determining the weight of each detection index; according to the risk value and the weight corresponding to each detection index and based on a weighted average method, a fuzzy fusion theory, a Laplacian fusion theory, a Bayesian average method and a robust statistical method, calculating an average risk index of each section, and according to the average risk index, determining whether each section may have a to-be-analyzed unfavorable geological problem. According to the invention, the accuracy of tunnel unfavorable geological problem analysis is improved.

Description

Technical Field

[0001] The present application relates to the field of geological analysis technology, and in particular to a method and device for analyzing adverse geological problems in tunnels by fusing multi-source data. Background Art

[0002] Tunnel advanced geological prediction is a method of multi-scale and multi-parameter prediction of the geological conditions ahead of the working face based on site conditions, using one or more means such as geological analysis, advanced geological drilling, geophysical detection, and advanced pilot tunnels. Through advanced geological prediction, we can grasp the unfavorable geology and major geological problems ahead of the tunnel, analyze possible unfavorable geological problems such as rock bursts and landslides, provide early warning for construction, ensure construction safety, and provide a reliable basis for information-based design and construction.

[0003] The existing schemes for analyzing adverse geological problems using tunnel advance geological prediction have at least the following problems. First, the existing tunnel advance geological prediction is mainly based on geophysical information and supplemented by geological information during comprehensive exploration. In actual engineering, although geophysical exploration, sensor detection, and simulation test methods have the advantages of non-destructive exploration and high efficiency, their results compared with geological sketches and advance drilling are not intuitive enough. In addition, when the cavern environmental factors have great interference, the regional geological conditions are complex, and adverse geological problems occur frequently, the analysis accuracy of adverse geological conditions is prone to large deviations. Second, the existing multi-source data fusion method considers fewer sources of information and does not fully consider the input of information during the entire tunnel excavation process, which reduces the accuracy of the analysis. Third, due to the unclear geological logic of the interpretation, the existing intelligent machine interpretation of advanced geological prediction is still mainly based on manual interpretation, and its accuracy and universality are poor. Summary of the invention

[0004] The present application aims to solve the problem of poor accuracy of existing analysis schemes for poor geological problems in tunnels, and proposes a method and device for analyzing poor geological problems in tunnels by fusion of multi-source data.

[0005] The technical solution adopted by this application to solve the above technical problems is:

[0006] In a first aspect, the present application provides a method for analyzing adverse geological problems in tunnels by fusion of multi-source data, the method comprising:

[0007] Establish a full-process information database for tunnels and an indicator system for adverse geological problems;

[0008] Determine the current unfavorable geological problems to be analyzed in the tunnel, determine the detection indicators corresponding to the unfavorable geological problems to be analyzed in the unfavorable geological problem indicator system, and determine the detection data of each detection indicator in the detection interval in the whole process information database;

[0009] The test data of each test indicator is converted into a risk value, the test interval is divided into multiple sections according to the coverage of different test data in each test indicator, and the weight of each test indicator is determined;

[0010] According to the risk value and weight corresponding to each detection indicator, the average risk index of each section is calculated based on the weighted average method, fuzzy fusion theory, Laplace fusion theory, Bayesian averaging method and robust statistics method. According to the average risk index, it is judged whether each section will have the unfavorable geological problems to be analyzed.

[0011] Furthermore, the whole process information database includes basic design information of the tunnel, basic geological condition information, advanced exploration information, advanced geophysical prospecting information, excavation and construction parameter information, experiment and test information, and monitoring and detection information;

[0012] The basic design information includes tunnel shape, span, height, excavation form and surrounding rock grade; the basic geological condition information includes geomorphic features, vertical burial depth, formation code, lithology, saturation coefficient, rock integrity, groundwater pressure and shear strength; the advanced exploration information includes the corresponding return water volume, return water color and karst cave conditions of advance drilling, advance exploration cave and advance exploration well; the advanced geophysical information includes the corresponding information of seismic wave method, geological radar method, transient electromagnetic method and induced polarization method; the excavation construction parameter information includes the corresponding information of drilling and blasting construction records, TBM construction records and slag records; the experiment and test information includes the corresponding information of rock experiment and test, soil experiment and test and water experiment and test, and the monitoring and detection information includes the corresponding information of microseismic monitoring, deformation monitoring and radioactive detection.

[0013] Furthermore, the adverse geological problems to be analyzed include high-altitude stress rock bursts, large deformations due to high-altitude stress, karst caves, karst water and mud gushing, fault fracture zone collapse, fault fracture zone water and mud gushing, large deformations due to weak rock zones, collapses due to weak rock zones, high geothermal heat hazards, toxic gas hazards, and radioactive hazards.

[0014] Furthermore, the test data of each test indicator is converted into a risk value, including:

[0015] A detection indicator having upper and lower limit values ​​and continuous intermediate values ​​is used as a first detection indicator, a value range of the first detection indicator is divided into a plurality of intervals, and a first mapping relationship between each interval and a risk value is established respectively;

[0016] A first mapping function between the first detection indicator and the risk value is established according to the first mapping relationship, and a corresponding risk value is determined according to a numerical value corresponding to the detection data of the first detection indicator and based on the first mapping function.

[0017] Furthermore, the test data of each test indicator is converted into a risk value, including:

[0018] Taking the detection index with interval description but no specific value as the second detection index, establishing the second mapping relationship between each interval description of the second detection index and the risk value, and adding the interval description in the second mapping relationship and performing corresponding interpolation on the risk value;

[0019] A corresponding risk value is determined according to the description corresponding to the detection data of the second detection indicator and based on the second mapping relationship.

[0020] Furthermore, the test data of each test indicator is converted into a risk value, including:

[0021] The detection indicator with only qualitative description is used as the third detection indicator, and a third mapping relationship between each qualitative description of the third detection indicator and the risk value is established respectively. The corresponding risk value is determined according to the qualitative description corresponding to the detection data of the third detection indicator and based on the third mapping relationship.

[0022] Furthermore, the detection interval is divided into multiple sections according to the coverage of different detection data in each detection indicator, including:

[0023] Determine the coverage of different detection data of each detection indicator in the tunnel. There are endpoints between the coverage of different detection data. The position of each endpoint of each detection indicator is used as a segmentation point, and the detection interval is divided into multiple segments according to the segmentation point.

[0024] Furthermore, the weight of each detection indicator is determined, specifically by using a hierarchical analysis method to calculate the first weight of each detection indicator, calculating the second weight of each detection indicator according to the Huber weighting method, and taking the average of the first weight and the second weight as the weight of each detection indicator.

[0025] Furthermore, the calculation method of the average risk index includes:

[0026] The first risk index of each section is calculated based on the weighted average method, the second risk index of each section is calculated based on the fuzzy fusion theory, the third risk index of each section is calculated based on the Laplace fusion theory, the fourth risk index of each section is calculated based on the Bayesian average method, and the fifth risk index of each section is calculated based on the robust statistical method;

[0027] An average of the first risk index, the second risk index, the third risk index, the fourth risk index and the fifth risk index is calculated to obtain an average risk index.

[0028] In a second aspect, the present application provides a device for analyzing adverse geological problems in tunnels by fusion of multi-source data, and the device is used to implement the steps of the method for analyzing adverse geological problems in tunnels by fusion of multi-source data as described in the first aspect.

[0029] The beneficial effects of the present application are as follows: the tunnel adverse geological problem analysis method and device with multi-source data fusion provided by the present application takes geological information as the core, constructs a tunnel excavation whole process information database and establishes a set of indicator systems for tunnel engineering adverse geological problems; when adverse geological problems need to be analyzed, the detection indicators related to them are determined from the indicator system, and the detection data corresponding to each detection indicator is obtained from the whole process information database, and the risk value conversion and alignment processing are performed on the obtained detection data, and then information technology is introduced, mathematical geological theory is applied, matrix fusion calculation of multi-source data is carried out, comprehensive analysis of multi-source data fusion is realized, analysis results of adverse geological problems in each section are obtained, and optimization of complementary and redundant information in space and time within the indicator system is realized, a consistent interpretation of the forecast object is obtained, and the accuracy of adverse geological problem analysis is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of a flow chart of a method for analyzing adverse geological problems in tunnels by fusion of multi-source data provided in an embodiment of the present application;

[0031] Figure 2 A schematic diagram of dividing a detection interval into multiple sections provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0033] In some of the processes described in the specification of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or in parallel. The sequence number of the operation is only used to distinguish between different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to different types.

[0034] The technical solution of the embodiment of the present application is applicable to application scenarios where it is necessary to analyze whether a tunnel will have adverse geological problems, such as analyzing whether a tunnel will have geological disasters such as water gushing, gas outburst, rock burst, large deformation, etc.

[0035] At present, the analysis scheme for adverse geological problems in tunnels usually uses tunnel advanced geological prediction for detection. However, the existing tunnel advanced geological prediction scheme considers fewer sources of information and does not fully consider the input of information during the entire tunnel excavation process, which reduces the accuracy of the analysis. In addition, the accuracy of the analysis is affected by the cavern environmental factors, the complexity of regional geological conditions and the frequency of adverse geological problems. At the same time, the presentation of the analysis results is usually based on manual interpretation, which further reduces the accuracy of the analysis results.

[0036] Based on this, the technical solution of the present application is proposed. In an embodiment of the present application, a full-process information database of the tunnel and an adverse geological problem indicator system are established; the current adverse geological problems to be analyzed in the tunnel are determined, and the detection indicators corresponding to the adverse geological problems to be analyzed are determined in the adverse geological problem indicator system, and the detection data of each detection indicator in the detection interval is determined in the full-process information database; the detection data of each detection indicator is converted into a risk value, the detection interval is divided into multiple sections according to the coverage of different detection data in each detection indicator, and the weight of each detection indicator is determined; according to the risk value and weight corresponding to each detection indicator and based on the weighted average method, fuzzy fusion theory, Laplace fusion theory, Bayesian averaging method and robust statistics method, the average risk index of each section is calculated, and according to the average risk index, it is judged whether the adverse geological problems to be analyzed will occur in each section.

[0037] Specifically, the embodiment of the present application takes geological information as the core, uses information data of the entire process of tunnel excavation to establish a full-process information database, and establishes an adverse geological problem indicator system based on various types of adverse geological problems and their related detection indicators. When it is necessary to analyze adverse geological problems, first determine the detection indicators related to them based on the adverse geological problem indicator system, and determine the detection data of each detection indicator based on the full-process information data, and then perform risk value conversion, segment division and weight calculation on each detection indicator. Finally, matrix fusion calculation of multi-source data is carried out based on the risk value and weight of each detection indicator corresponding to each segment, and the average risk index of the adverse geological problem to be analyzed in each segment is obtained, and comprehensive analysis of multi-source data fusion is realized, thereby improving the accuracy of analysis of adverse geological problems.

[0038] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0039] Figure 1 For a flow chart of a method for analyzing adverse geological problems in tunnels by fusion of multi-source data provided in an embodiment of the present application, please refer to Figure 1 , the method comprises the following steps:

[0040] S101. Establish a full-process information database for tunnels and an indicator system for adverse geological problems.

[0041] In the embodiment of the present application, the full-process information database includes basic design information of the tunnel, basic geological conditions information, advanced exploration (holes, caves, wells) information, advanced geophysical information, excavation and construction parameter information, experiment and test information, and monitoring and detection information.

[0042] The embodiments of the present application have extracted a number of key detection indicators for analyzing adverse geological problems, and realized the transformation from scattered information to full-process information, and from fuzzy factors to clear indicators. Specifically, in the basic geological condition information, five sub-categories of information including topography, stratum lithology, geological structure, groundwater and face evaluation are selected, including indicators such as geomorphic characteristics, vertical burial depth, stratum code, lithology, saturation coefficient, rock integrity, groundwater pressure, and shear strength; in the advanced exploration (holes, caves, wells) information, three sub-categories of information including advanced drilling, advanced caverns, and advanced wells are selected, including indicators such as return water volume, return water color, and karst cave conditions; in the advanced geophysical prospecting information, sub-categories of information including seismic wave method, geological radar method, transient electromagnetic method, and induced polarization method are selected, including Indicators such as longitudinal wave velocity, Poisson's ratio, resistivity, and polarizability are selected; in the excavation construction parameter information, three types of information are selected, including drilling and blasting construction records, TBM (tunnel boring machine) construction records, and rock slag records, including excavation footage, cutterhead thrust, rock slag size and other indicators; in the experiment and test information, three types of information are selected, including rock experiments and tests, soil experiments and tests, and water experiments and tests, including indicators such as the main components of rock minerals and rock grinding descriptions; in the monitoring and detection information, information such as microseismic monitoring, deformation monitoring, and radioactivity detection are selected, including indicators such as moment magnitude, settlement, and radon concentration.

[0043] In the embodiment of the present application, the adverse geological problems include high ground stress rock burst, high ground stress large deformation, karst cave, karst water and mud gushing, fault fracture zone collapse, fault fracture zone water and mud gushing, weak rock zone large deformation, weak rock zone collapse, high geothermal heat damage, toxic gas hazards and radioactive hazards. In the process of establishing the adverse geological problem indicator system, by analyzing various types of adverse geological problems, corresponding detection indicators are selected from the whole process information database, so as to determine the detection indicators related to various types of adverse geological problems.

[0044] For example, in response to the adverse geological problems of fault fracture zone collapse, the fault fracture zone collapse is analyzed, screened from the full process information database, and multiple detection indicators related to fault fracture zone collapse are determined. Specifically, collapse refers to destructive geological disasters such as sudden collapse, pile collapse, and collapse caused by the instability of the surrounding rock. Before tunnel excavation, the rock mass is in a certain stress balance state, and engineering excavation will cause stress redistribution in the rock mass around the tunnel. When the tunnel passes through areas with low surrounding rock strength and poor stability such as fault fracture zones and weak rock zones, the surrounding rock after excavation cannot adapt to the changes in redistributed stress, and will deform and become unstable inside the cave, eventually causing collapse. This embodiment targets the collapse of the fault fracture zone, and mainly selects information such as topography, stratum lithology, geological structure, groundwater, face evaluation, advance drilling, seismic wave method, induced polarization method, TBM construction records, water field experiments and tests, deformation monitoring, stress monitoring, seepage detection, etc., including tunnel morphology, rotation speed, longitudinal wave velocity, resistivity, settlement, support internal force, flow rate and other detection indicators.

[0045] S102, determining the current unfavorable geological problems to be analyzed in the tunnel, and determining the detection indicators corresponding to the unfavorable geological problems to be analyzed in the unfavorable geological problem indicator system, and determining the detection data of each detection indicator in the detection interval in the full-process information database.

[0046] In practical applications, the unfavorable geological problems to be analyzed are determined according to the specific working conditions, the detection indicators related to them are determined in the unfavorable geological problem indicator system, and the detection data of each detection indicator in the detection interval is determined in the whole process information database. For example, if the unfavorable geological problem to be detected is the collapse of the fault fracture zone, the detection indicators related to the collapse of the fault fracture zone are determined in the unfavorable geological problem indicator system, and the detection data of each detection indicator in the detection interval is determined in the whole process information database.

[0047] S103, converting the detection data of each detection indicator into a risk value, dividing the detection interval into multiple sections according to the coverage of different detection data in each detection indicator, and determining the weight of each detection indicator.

[0048] In an embodiment of the present application, a mapping conversion method is used to convert the detection data into a normalized dimensionless risk value ranging from 0 to 1, which characterizes the probability of occurrence of adverse geological problems from low to high under the influence of a single indicator, and achieves consistency in the quantitative form and data range of each detection indicator. The mapping conversion method includes a quantitative indicator piecewise function mapping conversion method, a semi-qualitative indicator node interpolation mapping conversion method, and a qualitative indicator threshold graded mapping conversion method.

[0049] In an embodiment of the present application, the quantitative indicator piecewise function mapping conversion method includes: taking a detection indicator with upper and lower limit values ​​and continuous intermediate values ​​as a first detection indicator, dividing the numerical range of the first detection indicator into multiple intervals, and establishing a first mapping relationship between each interval and the risk value respectively; establishing a first mapping function between the first detection indicator and the risk value according to the first mapping relationship, and determining the corresponding risk value according to the numerical value corresponding to the detection data of the first detection indicator and based on the first mapping function.

[0050] Specifically, for the first detection indicators such as Poisson's ratio and longitudinal wave velocity, which have clear upper and lower limits and continuous intermediate values, the risk value of the corresponding detection data is determined by mapping segments, establishing mapping functions, and determining the values ​​of constant parameters. The specific steps are as follows:

[0051] (1) Establish the upper and lower limits of the first detection index and their correlation with the risk value. Taking the Poisson's ratio as an example, its upper and lower limits range from 0 to 0.5, which is positively correlated with the risk value (0 to 1). Therefore, when the Poisson's ratio is 0, the corresponding risk value is 0, and when the Poisson's ratio is 0.5, the corresponding risk value is 1.

[0052] (2) Mapping and segmenting the first detection index. Specific and segmented descriptions are performed according to different formation conditions. For example, the Poisson's ratio of shale is generally 0.10-0.20. When the Poisson's ratio is 0.10, the corresponding risk value is 0.2. When the Poisson's ratio is 0.20, the corresponding risk value is 0.7. The Poisson's ratio is divided into three intervals: 0-0.10, 0.10-0.20, and 0.20-0.50. The first mapping relationship with the risk value is established respectively.

[0053] (3) Establishing a first mapping function between the first detection index and the risk value. Generally, three common relationship models are selected, namely, linear, exponential and S-type, but not limited thereto, and the first mapping function can also be other model functions.

[0054] Linear type: y = ax + b;

[0055] Exponential type: y = ae bx +c;

[0056] S-type:

[0057] Among them, y represents the risk value, x represents the test data corresponding to the first test indicator, and a, b, and c represent parameters, which need to be determined through data fitting. The linear relationship is usually applicable to simple linear relationships, that is, as the first test indicator increases, the risk value increases or decreases linearly; the exponential relationship is applicable to the relationship between the first test indicator and the risk value that shows exponential growth or decay, and is usually used to describe the phenomenon of nonlinear growth or decay; the S-type relationship is usually used to describe the relationship of asymptotic growth, that is, as the first test indicator increases, the risk value first increases rapidly and then tends to be stable.

[0058] (4) Determine the parameter values ​​in the first mapping function. The parameters determine the specific form of the first mapping function and its ability to describe the data. When the amount of data is small, analyze and judge the situation of the tunnel face, refer to the numerical value and geological conditions corresponding to the first detection indicator at the tunnel face, determine the risk value corresponding to the detection data of the first detection indicator at the tunnel face, and calculate the parameter value in combination with the upper and lower limit constraints of the interval.

[0059] For a more complex first mapping function, the least squares method can be used to fit the data when the amount of data is large, thereby establishing a more realistic first mapping function. The least squares method is the most commonly used basic algorithm. Its core idea is to find a curve that minimizes the sum of the squares of the vertical distances from all data points to the curve. Specifically, for n sets of data points (x i ,y i ) and a first mapping function f(x) to be fitted, the least squares method finds the optimal parameters by minimizing the following objective function:

[0060]

[0061] In the formula, S represents the sum of square errors, f(x i ) represents the analytical value of the first mapping function, y i By taking the derivative of the parameter and setting the derivative to zero, we can get the parameter value corresponding to the minimum sum of square errors, which minimizes the error between the fitting curve and the data points.

[0062] (5) After determining the optimal parameters, a first mapping function can be obtained. Substituting the numerical value corresponding to the detection data of the first detection indicator into the first mapping function, the corresponding risk value can be obtained.

[0063] In an embodiment of the present application, the semi-qualitative indicator node interpolation mapping conversion method includes: taking a detection indicator with an interval description but no specific numerical value as a second detection indicator, establishing a second mapping relationship between each interval description of the second detection indicator and the risk value, and in the second mapping relationship, adding an interval description and performing corresponding interpolation on the risk value; determining the corresponding risk value according to the description corresponding to the detection data of the second detection indicator and based on the second mapping relationship.

[0064] Specifically, for semi-qualitative second detection indicators such as groundwater and integrity, which have both clear data interval descriptions and fuzzy segmented qualitative descriptions, it is often impossible to obtain accurate data values ​​in actual projects. We can first establish partition nodes for the detection indicators based on the qualitative descriptions between partitions, and then use the interpolation method between nodes to determine the risk value. For example, for groundwater indicators, according to the specification "Specifications for Geological Survey of Hydropower Engineering GB50287-2016", water volume <25L / (min·10m) is dry to seepage and dripping, water volume 25~125L / (min·10m) is linear flow, and water volume >125L / (min·10m) is gushing water. The specific steps are as follows:

[0065] (1) Establish the upper and lower limits of the second detection index and their correlation with the risk value. Taking the groundwater index as an example, its upper and lower limits range from dry to gushing water, which is positively correlated with the risk value (0 to 1). Therefore, when the groundwater index is dry, the corresponding risk value is 0, and when the groundwater index is gushing water, the corresponding risk value is 1.

[0066] (2) Mapping the second detection index in segments. According to the segmented qualitative description, the node interval of the second detection index is directly divided, which can be evenly divided or unevenly divided, and the second mapping relationship between each interval description and the risk value is established. Taking the groundwater index as an example, the corresponding risk value can be 0-0.3 when the groundwater index is dry to seepage and dripping, the corresponding risk value can be 0.3-0.7 when the groundwater index is linear flow, and the corresponding risk value can be 0.7-1.0 when the groundwater index is gushing water, thereby establishing the second mapping relationship.

[0067] (3) According to the actual geological conditions, the detection data corresponding to the second detection indicator of a certain mileage and its corresponding risk value are selected within the interval in the second mapping relationship for interpolation.

[0068] (4) According to the results of mathematical statistics, when enough sample data under certain geological conditions are accumulated, these data can be used for data analysis or fitting, so as to establish a risk value mapping value that is more in line with reality. When fitting data, optimization algorithms such as the least squares method can be used for fitting.

[0069] (5) After the second mapping relationship is determined, the corresponding risk value can be obtained according to the numerical value corresponding to the detection data of the first detection indicator and based on the second mapping relationship.

[0070] In an embodiment of the present application, the qualitative indicator threshold hierarchical mapping conversion method includes: taking the detection indicator with only qualitative description as the third detection indicator, establishing a third mapping relationship between each qualitative description of the third detection indicator and the risk value, and determining the corresponding risk value according to the qualitative description corresponding to the detection data of the third detection indicator and based on the third mapping relationship.

[0071] Specifically, for the third qualitative detection indicators of geological radar, such as frequency change and phase consistency, which usually only have pictures or text explanations but no specific quantitative data, a given risk value can be directly proposed based on its qualitative properties. The specific steps are as follows:

[0072] (1) Map and segment the third detection index. According to the qualitative description, the risk value is divided into corresponding segments. For example, if the phase consistency description of the geological radar includes three segments: obvious misalignment of the event axis, slight misalignment of the event axis, and basically continuous event axis, the risk value is divided into three segments.

[0073] (2) According to the actual geological conditions, the specific risk values ​​of the risk value section are judged and selected, and the third mapping relationship between each qualitative description of the third detection index and the risk value is established. For example, the amplitude intensity description of the geological radar includes obvious enhancement, slight enhancement, and no change, and the risk values ​​are 0.6, 0.4, and 0.1 respectively; the frequency change description of the geological radar includes obvious change and chaotic waveform, slight change, and no change, and the risk values ​​are 0.6, 0.4, and 0.1 respectively; the phase consistency description of the geological radar includes obvious phase axis misalignment, slight phase axis misalignment, and basically continuous phase axis, and the risk values ​​are 0.5, 0.3, and 0.1 respectively.

[0074] (3) Statistically adjust the risk values ​​in the above steps. The risk values ​​in the above steps are subjective. According to the results of mathematical statistics, when enough sample data under certain geological conditions are accumulated, these data can be used for data analysis to establish a mapping value of risk values ​​that is more in line with reality.

[0075] (4) After the third mapping relationship is determined, the corresponding risk value can be obtained according to the qualitative description corresponding to the detection data of the third detection indicator and based on the third mapping relationship.

[0076] In the embodiment of the present application, the detection interval is divided into multiple sections according to the coverage of different detection data in each detection indicator, specifically including:

[0077] Determine the coverage of different detection data of each detection indicator in the tunnel. There are endpoints between the coverage of different detection data. The position of each endpoint of each detection indicator is used as a segmentation point, and the detection interval is divided into multiple segments according to the segmentation point.

[0078] Specifically, the embodiment of the present application divides all detection indicators corresponding to the unfavorable geological problems to be analyzed into sections based on different data and coverage of different detection indicators, and obtains multiple multi-source data indicator fusion calculation sections. Figure 2 , Assume that the detection indicators corresponding to a certain adverse geological problem include indicator A and indicator B. Indicator A has three different detection data, namely A1, A2 and A3. The three detection data cover different positions of the tunnel respectively, and there are endpoints between the coverage ranges. Indicator B has four different detection data, namely B1, B2, B3 and B4. The four detection data cover different positions of the tunnel respectively, and there are endpoints between the coverage ranges. Indicator A and indicator B are aligned according to the face, and then traversed along the tunnel excavation direction. When traversing to the endpoint corresponding to any detection indicator, the position of the endpoint is used as the segmentation point. After the traversal is completed, the detection interval is divided into 6 sections according to all segmentation points.

[0079] In practical applications, due to the differences in the detection intervals of different detection indicators, the detection data and risk values ​​of different positions of the same detection indicator are also different. Therefore, the embodiment of the present application divides the sections, so that the consistency of the values ​​of each indicator in the same section can be ensured during data fusion, laying the foundation for multi-source data fusion.

[0080] In an embodiment of the present application, the weight of each detection indicator is determined, specifically by using a hierarchical analysis method to calculate the first weight of each detection indicator, calculating the second weight of each detection indicator according to the Huber weighting method, and taking the average of the first weight and the second weight as the weight of each detection indicator.

[0081] Specifically, when determining the weight of each detection index, we follow the principle of taking direct information such as geological information and drilling results as the basis and indirect information such as geophysical exploration and test results as the supplement, and use the combination of the analytic hierarchy process and the Huber weighting method to calculate the index weight. Among them, the analytic hierarchy process takes into account the subjective attribution of the importance of the index, and the Huber weighting method focuses on the properties of the data set itself, such as the degree of discreteness. The combination of the two methods achieves complementary effects and further improves the accuracy and scientificity of the final detection index weight.

[0082] In practical applications, the AHP includes: establishing a hierarchical structure model of detection indicators and determining the quantitative judgment scale, comparing and scoring detection indicators pairwise according to the quantitative judgment scale, constructing a judgment matrix according to the scoring results, and calculating the first weight of each detection indicator according to the judgment matrix. Considering that the AHP has a certain degree of subjectivity, the indicator weights obtained by the four commonly used weight calculation methods of AHP (geometric mean method, arithmetic mean method, eigenvector method and least squares method) can be averaged to reduce the result deviation caused by the subjectivity of scale assignment and obtain the first weight of each detection indicator.

[0083] The Huber weighting method defines a threshold (usually estimated by the standard deviation), within which the least squares method is used, and above the threshold, the linear relationship of the absolute residual is used. This can retain a certain degree of sensitivity to outliers, but not be overly affected by them. In practical applications, by constructing a data set containing detection indicators and adverse geological problems, the second weight of each detection indicator in the data set is determined.

[0084] The weight of each detection index can be obtained by calculating the average of the first weight and the second weight. The two weight calculation methods are used for fusion calculation, taking into account the differences in sensitivity and accuracy of different forecasting methods for various types of adverse geological problems, and solving the problems of significant differences in the physical meanings of different detection indicators, different sensitivities of different detection indicators for the same adverse geological problem, and different sensitivities of the same detection indicator for different adverse geological problems.

[0085] S104. Calculate the average risk index of each section according to the risk value and weight corresponding to each detection indicator based on the weighted average method, fuzzy fusion theory, Laplace fusion theory, Bayesian averaging method and robust statistics method, and judge whether each section will have the unfavorable geological problems to be analyzed according to the average risk index.

[0086] In the embodiment of the present application, the method for calculating the average risk index includes:

[0087] The first risk index of each segment is calculated based on the weighted average method, the second risk index of each segment is calculated based on the fuzzy fusion theory, the third risk index of each segment is calculated based on the Laplace fusion theory, the fourth risk index of each segment is calculated based on the Bayesian averaging method, and the fifth risk index of each segment is calculated based on the robust statistics method; the average values ​​of the first risk index, the second risk index, the third risk index, the fourth risk index and the fifth risk index are calculated to obtain the average risk index.

[0088] Among them, the weighted average method, as one of the foundations of multi-source data fusion technology, integrates the data of various geological indicators by assigning appropriate weights to different data sources, including information from different data sources such as geological surveys, advance drilling, geological radar and seismic exploration, to establish a comprehensive geological condition model. The corresponding first risk index can be obtained by substituting the risk value and weight of the corresponding detection indicator into the geological condition model.

[0089] The application of fuzzy fusion theory makes it possible to deal with uncertainty and ambiguity in geological data. In tunnel engineering, changes in geological conditions are often accompanied by uncertainty. Fuzzy fusion theory can effectively integrate and reason these fuzzy information to more accurately predict the geological problems that may be encountered in tunnel construction. Fuzzy operations are performed using the risk values ​​and weights of the corresponding detection indicators to summarize and link the relevant information together, thereby obtaining the corresponding second risk index.

[0090] The Laplace fusion theory further optimizes the fusion process of multiple geological indicators, considers the correlation and weight between each indicator, and improves the accuracy and credibility of the prediction model. The corresponding third risk index is obtained by using the risk value and weight of the corresponding detection indicator and constructing the Laplace matrix and using the summation operation.

[0091] The Bayesian average rule is integrated on the basis of considering prior information and dynamically adjusts the prediction model to adapt to the changing geological conditions. The corresponding fourth risk index can be obtained by substituting the risk value and weight of the corresponding detection indicator into the prediction model.

[0092] The application of robust statistics ensures the robustness and reliability of the fusion results. When faced with possible anomalies in geological data, the robust statistics method can effectively identify and process outliers to ensure that the final geological prediction results are not affected by abnormal data. The corresponding fifth risk index is obtained by using the risk value and weight of the corresponding detection indicator and the Huber weight function and weighted average.

[0093] Finally, the above five risk indices are averaged to obtain the average risk index of the section. The average risk index of each section is a value between 0 and 1. When the value is close to 0, it means that the probability of the occurrence of unfavorable geological problems to be analyzed in the section is lower, and when the value is close to 1, it means that the probability of the occurrence of unfavorable geological problems to be analyzed in the section is higher.

[0094] Based on the above technical solution, this embodiment also proposes a tunnel adverse geological problem analysis device with multi-source data fusion, which is used to implement the steps of the tunnel adverse geological problem analysis method with multi-source data fusion as described in the embodiment of the present application.

[0095] It can be understood that since the tunnel adverse geological problem analysis device with multi-source data fusion described in the embodiment of the present application is a device for implementing the tunnel adverse geological problem analysis method with multi-source data fusion described in the embodiment, for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method, which will not be repeated here.

[0096] In summary, the tunnel adverse geological problem analysis method and device with multi-source data fusion provided in the embodiment of the present application takes geological information as the core, constructs a tunnel excavation full-process information database and establishes a set of indicator systems for adverse geological problems in tunnel engineering; when adverse geological problems need to be analyzed, the detection indicators related to them are determined from the indicator system, and the detection data corresponding to each detection indicator is obtained from the full-process information database, and the risk value conversion and alignment processing are performed on the obtained detection data, and then information technology is introduced, and mathematical geological theory is used to carry out matrix fusion calculation of multi-source data, so as to realize comprehensive analysis of multi-source data fusion, obtain the analysis results of adverse geological problems in each section, realize the optimization of complementary and redundant information in space and time within the indicator system, obtain a consistent interpretation of the forecast object, and improve the accuracy of adverse geological problem analysis.

Claims

1. A method for analyzing adverse geological problems in tunnels based on multi-source data fusion, characterized in that: The method comprises: Establish a full-process information database for tunnels and an indicator system for adverse geological problems; Determine the current unfavorable geological problems to be analyzed in the tunnel, determine the detection indicators corresponding to the unfavorable geological problems to be analyzed in the unfavorable geological problem indicator system, and determine the detection data of each detection indicator in the detection interval in the whole process information database; The test data of each test indicator is converted into a risk value, the test interval is divided into multiple sections according to the coverage of different test data in each test indicator, and the weight of each test indicator is determined; According to the risk value and weight corresponding to each detection indicator, the average risk index of each section is calculated based on the weighted average method, fuzzy fusion theory, Laplace fusion theory, Bayesian averaging method and robust statistics method. According to the average risk index, it is judged whether each section will have the unfavorable geological problems to be analyzed.

2. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1 is characterized in that: The whole process information database includes basic tunnel design information, basic geological condition information, advanced exploration information, advanced geophysical exploration information, excavation and construction parameter information, experiment and test information, and monitoring and detection information; The basic design information includes tunnel shape, span, height, excavation form and surrounding rock grade; the basic geological condition information includes geomorphic features, vertical burial depth, formation code, lithology, saturation coefficient, rock integrity, groundwater pressure and shear strength; the advanced exploration information includes the corresponding return water volume, return water color and karst cave conditions of advance drilling, advance exploration cave and advance exploration well; the advanced geophysical information includes the corresponding information of seismic wave method, geological radar method, transient electromagnetic method and induced polarization method; the excavation construction parameter information includes the corresponding information of drilling and blasting construction records, TBM construction records and slag records; the experiment and test information includes the corresponding information of rock experiment and test, soil experiment and test and water experiment and test, and the monitoring and detection information includes the corresponding information of microseismic monitoring, deformation monitoring and radioactive detection.

3. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1, characterized in that: The adverse geological problems to be analyzed include high-altitude stress rock bursts, large deformations due to high-altitude stress, karst caves, karst water and mud gushing, fault fracture zone collapse, fault fracture zone water and mud gushing, large deformations in weak rock zones, collapses in weak rock zones, high geothermal heat hazards, toxic gas hazards, and radioactive hazards.

4. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1, characterized in that: The test data of each test indicator is converted into a risk value, including: A detection indicator having upper and lower limit values ​​and continuous intermediate values ​​is used as a first detection indicator, a value range of the first detection indicator is divided into a plurality of intervals, and a first mapping relationship between each interval and a risk value is established respectively; A first mapping function between the first detection indicator and the risk value is established according to the first mapping relationship, and a corresponding risk value is determined according to a numerical value corresponding to the detection data of the first detection indicator and based on the first mapping function.

5. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1, characterized in that: The test data of each test indicator is converted into a risk value, including: Taking the detection index with interval description but no specific value as the second detection index, establishing the second mapping relationship between each interval description of the second detection index and the risk value, and adding the interval description in the second mapping relationship and performing corresponding interpolation on the risk value; A corresponding risk value is determined according to the description corresponding to the detection data of the second detection indicator and based on the second mapping relationship.

6. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1, characterized in that: The test data of each test indicator is converted into a risk value, including: The detection indicator with only qualitative description is used as the third detection indicator, and a third mapping relationship between each qualitative description of the third detection indicator and the risk value is established respectively. The corresponding risk value is determined according to the qualitative description corresponding to the detection data of the third detection indicator and based on the third mapping relationship.

7. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1, characterized in that: The detection interval is divided into multiple sections according to the coverage of different detection data in each detection indicator, including: Determine the coverage of different detection data of each detection indicator in the tunnel. There are endpoints between the coverage of different detection data. The position of each endpoint of each detection indicator is used as a segmentation point, and the detection interval is divided into multiple segments according to the segmentation point.

8. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1, characterized in that: The weight of each detection indicator is determined, specifically by using a hierarchical analysis method to calculate the first weight of each detection indicator, calculating the second weight of each detection indicator according to the Huber weighting method, and taking the average of the first weight and the second weight as the weight of each detection indicator.

9. The method for analyzing adverse geological problems of tunnels by multi-source data fusion according to claim 1, characterized in that: The calculation method of the average risk index includes: The first risk index of each section is calculated based on the weighted average method, the second risk index of each section is calculated based on the fuzzy fusion theory, the third risk index of each section is calculated based on the Laplace fusion theory, the fourth risk index of each section is calculated based on the Bayesian average method, and the fifth risk index of each section is calculated based on the robust statistical method; An average of the first risk index, the second risk index, the third risk index, the fourth risk index and the fifth risk index is calculated to obtain an average risk index.

10. A tunnel adverse geological problem analysis device based on multi-source data fusion, characterized in that: The device is used to implement the steps of the tunnel adverse geological problem analysis method based on multi-source data fusion as described in any one of claims 1 to 9.

Images