Information fusion advanced geological prediction system based on multiple detection methods

Abstract

The invention relates to the technical field of advanced geological prediction, in particular to an information fusion advanced geological prediction system based on multiple detection methods, which comprises a comprehensive analysis subsystem, an advanced prediction module and a notification and statistics module. Wherein the comprehensive analysis subsystem comprises a tunnel face analysis module, an advanced drilling analysis module and a geological radar analysis module. Various detection methods such as stress-strain monitoring, geological radar detection and advanced drilling are combined, the adaptability to a complex construction environment is improved, the intelligent level is improved, and rapid transmission and sharing of geological information are achieved; according to the method, data is analyzed in a centralized mode through a logic judgment program, geological abnormal conditions such as rockburst and discontinuous geological structures are found in time in the drilling process, and therefore corresponding early warning signals are output, and a clearer decision basis is provided for constructors.

Description

Technical Field

[0001] The invention relates to the technical field of advanced geological prediction, and in particular to an advanced geological prediction system based on information fusion of multiple detection methods. Background Art

[0002] Advanced geological forecast refers to a geological exploration method that uses geological survey, geophysical exploration and other exploration methods to determine the engineering geology, hydrogeology and adverse geological effects ahead of the tunnel at the tunnel face or corresponding ground position during tunnel construction based on existing geological data.

[0003] Multi-source data fusion originated from multi-source information fusion. It was first proposed in the 1970s and was mainly used in the military field. By fusing data generated from multiple information sources, a better understanding of the observed phenomenon can be achieved. The results of multi-source data fusion fully tap the available value between data. The information of various data sources is cross-verified, which improves the accuracy of decision-making results and reduces information errors and omissions. This is of great value in many engineering fields. At present, many domestic and foreign scholars have proposed some fusion methods for different data sources at the theoretical level. These fusion methods can be divided into probability-based methods and non-probabilistic methods.

[0004] However, there are still many problems with the existing advanced geological prediction technology. First, different advanced geological prediction methods have their specific scope of application and limitations. In some remote areas or areas with extremely complex geological conditions, the application of advanced geological prediction may be limited due to the limitations of equipment and technicians.

[0005] Secondly, the existing advanced geological prediction technology has not established a complete observation system, and the processing and analysis level of observation data needs to be improved. The results of advanced geological prediction depend to a large extent on the experience and level of the interpreters, and different interpreters may come up with different prediction results based on the same observation data.

[0006] In view of the above problems, it is necessary to propose an advanced geological prediction system based on information fusion of multiple detection methods. Summary of the invention

[0007] The purpose of the present invention is to solve the problems existing in the background technology and to propose an advanced geological prediction system based on information fusion of multiple detection methods.

[0008] An advanced geological prediction system based on information fusion of multiple detection methods includes a comprehensive analysis subsystem, an advanced prediction module, and a notification and statistics module. The comprehensive analysis subsystem includes a face analysis module, an advanced drilling analysis module, and a geological radar analysis module.

[0009] The tunnel face analysis module obtains the lithological characteristic data of the tunnel face at each preset time interval, specifically:

[0010] Get the mileage stake number K of the tunnel face. Get the rock types contained in the tunnel face, including slate, limestone, phyllite, sandstone, schist, andesite, shale, marble, granite and basalt, and match the preset lithology parameter C according to the lithology type. Get the rock layer inclination of the tunnel face Rock thickness Number of joint groups Maximum joint gap and water output

[0011] As a preferred method of the present invention, obtaining stress-strain characteristic data of the rock around the tunnel face includes:

[0012] Convergence value of surrounding rock wall Convergence rate of surrounding rock wall Convergence acceleration of surrounding rock wall Vault settlement Vault sinking rate Vault sinking acceleration Maximum principal stress value of surrounding rock Maximum principal stress direction of surrounding rock and the maximum principal stress inclination of surrounding rock

[0013] By formula Calculate the first section characteristic parameter E11(k) and the second section characteristic parameter E12(k) of the tunnel face with mileage stake number K. and These are all preset weight factors.

[0014] The first section characteristic parameter and the second section characteristic parameter are sent to the advanced prediction module.

[0015] The advance drilling analysis module obtains information obtained by the horizontal drilling machine during horizontal geological drilling at the tunnel face with mileage stake number K at preset time intervals t, including the drilling power P, drilling speed V and drilling mileage depth ΔK of the horizontal drilling machine.

[0016] As a preferred method of the present invention, the lithology experimental parameters of the drill core are obtained, including the natural density Dry density Saturation density Moisture content Test longitudinal wave velocity with sound waves

[0017] As a preferred method of the present invention, the mechanical experimental parameters of the drilled core are obtained, including the axial compressive strength of the drilled core. Cohesion Elastic modulus Poisson's ratio and softening coefficient

[0018] With drilling power P as the vertical axis and time t as the horizontal axis, a drilling power-time graph is established and its function expression P=f1(t) is obtained. With drilling speed V as the vertical axis and time t as the horizontal axis, a drilling speed-time graph is established and its function expression V=f2(t) is obtained.

[0019] By formula Calculate the first drilling characteristic parameter E21 (K + △ K) and the second drilling characteristic parameter E22 (K + △ K). Where T is the preset detection period, is a set of preset weight factors, Where μ is the first moment of the function g(t).

[0020] The first drilling characteristic parameter and the second drilling characteristic parameter are sent to the advanced prediction module.

[0021] The geological radar analysis module obtains the electromagnetic intensity transient variable ΔB of the electromagnetic wave detected at the mileage depth ΔK along the tunneling direction of the tunnel face. The electromagnetic intensity transient variable ΔB is used as the vertical axis and the mileage depth ΔK is used as the horizontal axis to establish the electromagnetic intensity transient variable-mileage depth map. The function expression of the electromagnetic intensity transient variable-mileage depth map ΔB=h(ΔK) is obtained.

[0022] As a preferred embodiment of the present invention, the electromagnetic intensity transient variable-mileage depth map is converted into the frequency domain by Fourier transform to obtain the electromagnetic wave frequency spectrum.

[0023] The Fourier transform formula is: Where i is an imaginary unit and i×i=-1, where v is the frequency obtained after decomposition, and S(v) is the electromagnetic wave frequency spectrum function obtained after Fourier transform. Feature extraction is performed in the electromagnetic wave frequency spectrum, and the formula is used. Calculate the high frequency occupancy ρ, where v1 is the preset high and low frequency cutoff frequency. Send the high frequency occupancy ρ to the advance prediction module.

[0024] The advanced prediction module obtains the analysis data sent by the comprehensive analysis subsystem, including the first section characteristic parameter E11(k), the second section characteristic parameter E12(k), the first drilling characteristic parameter E21(K+△K), the second drilling characteristic parameter E22(K+△K) and the high frequency occupancy rate ρ. The analysis data is input into the logic judgment program.

[0025] As a preferred embodiment of the present invention, the logic judgment program is specifically as follows:

[0026] The drilling mileage depth ΔK in the first drilling characteristic parameter E21 (K+ΔK) and the second drilling characteristic parameter E22 (K+ΔK) is extracted to enter the first numerical judgment and the second numerical judgment.

[0027] First numerical judgment: judge whether the high-frequency occupancy rate ρ is less than the threshold ρMin. If so, enter the third numerical judgment; if not, enter the fourth numerical judgment;

[0028] Second numerical judgment: judge whether the second drilling characteristic parameter E22 (K+△K) is greater than the threshold value E22Ma. If so, output a rock burst warning signal and then enter the fourth numerical judgment; if not, directly enter the fourth numerical judgment.

[0029] The third numerical judgment: judge whether the first drilling characteristic parameter E21 (K + △ K) is greater than the threshold value E21Max. If so, output a discontinuous geological warning signal, and then enter the fourth numerical judgment; if not, directly enter the fourth numerical judgment.

[0030] Fourth numerical judgment: judge whether the mileage depth ΔK is less than the threshold value KMax. If so, enter the fifth numerical judgment; if not, end the entire logic judgment program.

[0031] Fifth numerical judgment: judge whether the condition that the first section characteristic parameter E11(k) is greater than the threshold value E11Max or the second section characteristic parameter E12(k) is greater than the threshold value E12Max is met. If so, output a stop inspection signal, and then end the entire logic judgment program; if not, output a first-level alarm signal, and then end the entire logic judgment program.

[0032] After the entire logic judgment program is completed, all output signals are sent to the statistics and notification module.

[0033] The statistics and notification module outputs the signals generated by the advance prediction module through the display screen, including discontinuous geological warning signals, rock burst warning signals, shutdown inspection signals or first-level alarm signals. The alarm information corresponding to the signal is output through the display screen, and the number of times each signal is generated within the preset statistical period is counted.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] (1) The present invention provides a detailed geological information basis for tunnels or underground projects by obtaining key geological parameters such as the mileage pile number, rock type, rock layer inclination, rock layer thickness, number of joint groups, maximum joint gap and water yield of the tunnel face; by obtaining stress-strain characteristic data of the surrounding rock around the tunnel face, including convergence value, convergence rate, convergence acceleration, vault subsidence, subsidence rate, subsidence acceleration, and maximum principal stress value, direction and inclination of the surrounding rock, the deformation and stress state of the surrounding rock can be monitored in real time; this is of great significance for timely discovering signs of surrounding rock instability and preventing geological disasters;

[0036] (2) The present invention combines multiple detection methods such as stress-strain monitoring, geological radar detection, and advance drilling, improves adaptability to complex construction environments, sets up multiple links such as real-time monitoring, data analysis, and early warning, and improves the level of intelligence; it acquires and processes geological information through digital means, and realizes the rapid transmission and sharing of geological information;

[0037] (3) The present invention uses a logical judgment program to conduct centralized data analysis, and timely discovers geological anomalies such as rock bursts and discontinuous geological structures during the drilling process, thereby outputting corresponding warning signals; a multi-level numerical judgment mechanism is adopted, and each level of judgment is based on specific conditions and thresholds; this design makes the output of warning signals more accurate and avoids false alarms and missed alarms; at the same time, according to different judgment results, the program can output warning signals of different levels, providing construction personnel with a clearer decision-making basis, which helps construction personnel to take preventive measures in advance and reduce construction risks; and reduces the dependence of geological forecasts on the experience and level of interpreters. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings:

[0039] Figure 1 is a system block diagram of the present invention;

[0040] Figure 2 It is a logic judgment flow chart of the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Advanced geological forecast (geological forecast).

[0043] During the tunnel construction process, a geological exploration method is used to determine the engineering geology, hydrogeology and adverse geological effects ahead of the tunnel at the tunnel face or corresponding ground position based on existing geological data by using geological survey methods, geophysical exploration and other exploration means.

[0044] See also Figure 1 As shown, an advanced geological prediction system based on information fusion of multiple detection methods includes a comprehensive analysis subsystem, an advanced prediction module and a notification and statistics module. The comprehensive analysis subsystem includes a face analysis module, an advanced drilling analysis module and a geological radar analysis module.

[0045] The tunnel face analysis module obtains the lithological characteristic data of the tunnel face at each preset time interval, specifically:

[0046] Get the mileage stake number K of the tunnel face. Get the rock types contained in the tunnel face, including slate, limestone, phyllite, sandstone, schist, andesite, shale, marble, granite and basalt, and match the preset lithology parameter C according to the lithology type. Get the rock layer inclination of the tunnel face Rock thickness Number of joint groups Maximum joint gap and water output

[0047] Furthermore, the stress-strain characteristic data of the rock around the tunnel face are obtained, including:

[0048] Convergence value of surrounding rock wall Convergence rate of surrounding rock wall Convergence acceleration of surrounding rock wall Vault settlement Vault sinking rate Vault sinking acceleration Maximum principal stress value of surrounding rock Maximum principal stress direction of surrounding rock and the maximum principal stress inclination of surrounding rock

[0049] By formula Calculate the first section characteristic parameter E11(k) and the second section characteristic parameter E12(k) of the tunnel face with mileage stake number K. and These are all preset weight factors.

[0050] The first section characteristic parameter and the second section characteristic parameter are sent to the advanced prediction module.

[0051] It should be noted that the first section characteristic parameters quantify the lithological characteristics of the tunnel face, including rock type, rock formation occurrence, joint opening, and rock permeability. The second section characteristic parameters quantify the stress and strain characteristics of the surrounding rock around the tunnel face.

[0052] The advance drilling analysis module obtains information obtained by the horizontal drilling machine during horizontal geological drilling at the tunnel face with mileage stake number K at preset time intervals t, including the drilling power P, drilling speed V and drilling mileage depth ΔK of the horizontal drilling machine.

[0053] Furthermore, the lithology experimental parameters of the drill core are obtained, including the natural density Dry density Saturation density Moisture content Test longitudinal wave velocity with sound waves

[0054] Furthermore, the mechanical experimental parameters of the drilled core are obtained, including the axial compressive strength of the drilled core. Cohesion Elastic modulus Poisson's ratio and softening coefficient

[0055] With drilling power P as the vertical axis and time t as the horizontal axis, a drilling power-time graph is established and its function expression P=f1(t) is obtained. With drilling speed V as the vertical axis and time t as the horizontal axis, a drilling speed-time graph is established and its function expression V=f2(t) is obtained.

[0056] By formula Calculate the first drilling characteristic parameter E21 (K + △ K) and the second drilling characteristic parameter E22 (K + △ K). Where T is the preset detection period, is a set of preset weight factors, Where μ is the first moment of the function g(t).

[0057] The first drilling characteristic parameter and the second drilling characteristic parameter are sent to the advanced prediction module.

[0058] It should be noted that the first drilling characteristic parameter comprehensively reflects the fluctuation of the ratio of drilling power to drilling speed, and indirectly reflects the continuity of the rock formation encountered during the advance drilling process. If the rock encountered during the advance drilling process is uniform and continuous, the value of the first drilling characteristic parameter will approach 0. Conversely, if discontinuous formations such as faults, boulders, and goafs are encountered during the advance drilling process, the value of the first drilling characteristic parameter will increase.

[0059] It should be further explained that the second drilling characteristic parameter comprehensively reflects the mechanical properties of the rocks encountered during the advance drilling process.

[0060] The geological radar analysis module obtains the electromagnetic intensity transient variable ΔB of the electromagnetic wave detected at the mileage depth ΔK along the tunneling direction of the tunnel face. The electromagnetic intensity transient variable ΔB is used as the vertical axis and the mileage depth ΔK is used as the horizontal axis to establish the electromagnetic intensity transient variable-mileage depth map. The function expression of the electromagnetic intensity transient variable-mileage depth map ΔB=h(ΔK) is obtained.

[0061] Furthermore, the electromagnetic intensity transient variable-mileage depth map is converted into the frequency domain through Fourier transform to obtain the electromagnetic wave frequency spectrum.

[0062] The Fourier transform formula is: Where i is an imaginary unit and i×i=-1, where v is the frequency obtained after decomposition, and S(v) is the electromagnetic wave frequency spectrum function obtained after Fourier transform. Feature extraction is performed in the electromagnetic wave frequency spectrum, and the formula is used. Calculate the high frequency occupancy ρ, where v1 is the preset high and low frequency cutoff frequency. Send the high frequency occupancy ρ to the advance prediction module.

[0063] It should be noted that the dielectric constant of rock mass fluctuates between 4 and 7, the dielectric constant of water is 81, and the dielectric constant of air is 1. There is a large difference between the dielectric constants of the three. Therefore, when electromagnetic waves pass through water-rich areas and goaf areas, the propagation speed of electromagnetic waves in the medium will decrease rapidly, and the reflected waves will show obvious positive peak anomalies, accompanied by strong reflection, diffraction and scattering of electromagnetic waves, resulting in a change from high frequency to low frequency in the electromagnetic wave frequency spectrum. Reflected in the specific numerical value, the value of high frequency occupancy ρ will decrease.

[0064] The advanced prediction module obtains the analysis data sent by the comprehensive analysis subsystem, including the first section characteristic parameter E11(k), the second section characteristic parameter E12(k), the first drilling characteristic parameter E21(K+△K), the second drilling characteristic parameter E22(K+△K) and the high frequency occupancy rate ρ. The analysis data is input into the logic judgment program.

[0065] See also Figure 2 As shown, the logic judgment procedure is specifically as follows:

[0066] The drilling mileage depth ΔK in the first drilling characteristic parameter E21 (K+ΔK) and the second drilling characteristic parameter E22 (K+ΔK) is extracted to enter the first numerical judgment and the second numerical judgment.

[0067] First numerical judgment: judge whether the high-frequency occupancy rate ρ is less than the threshold ρMin. If so, enter the third numerical judgment; if not, enter the fourth numerical judgment;

[0068] Second numerical judgment: judge whether the second drilling characteristic parameter E22 (K+△K) is greater than the threshold value E22Ma. If so, output a rock burst warning signal and then enter the fourth numerical judgment; if not, directly enter the fourth numerical judgment.

[0069] The third numerical judgment: judge whether the first drilling characteristic parameter E21 (K + △ K) is greater than the threshold value E21Max. If so, output a discontinuous geological warning signal, and then enter the fourth numerical judgment; if not, directly enter the fourth numerical judgment.

[0070] Fourth numerical judgment: judge whether the mileage depth ΔK is less than the threshold value KMax. If so, enter the fifth numerical judgment; if not, end the entire logic judgment program.

[0071] Fifth numerical judgment: judge whether the condition that the first section characteristic parameter E11(k) is greater than the threshold value E11Max or the second section characteristic parameter E12(k) is greater than the threshold value E12Max is met. If so, output a stop inspection signal, and then end the entire logic judgment program; if not, output a first-level alarm signal, and then end the entire logic judgment program.

[0072] After the entire logic judgment program is completed, all output signals are sent to the statistics and notification module.

[0073] The statistics and notification module outputs the signals generated by the advance prediction module through the display screen, including discontinuous geological warning signals, rock burst warning signals, shutdown inspection signals or first-level alarm signals. The alarm information corresponding to the signal is output through the display screen, and the number of times each signal is generated within the preset statistical period is counted.

[0074] It should be understood that the terms “include” and “comprising” used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0075] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and the claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and the claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations;

[0076] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An advanced geological prediction system based on information fusion of multiple detection methods, including a comprehensive analysis subsystem and an advanced prediction module, characterized in that: The comprehensive analysis subsystem includes an advance drilling analysis module; the advance drilling analysis module obtains drilling information obtained by the horizontal drilling machine at the tunnel face with a mileage pile number K at a preset time t, and obtains a first drilling characteristic parameter and a second drilling characteristic parameter through numerical calculation; the analysis data sent by the comprehensive analysis subsystem is obtained and input into a logic judgment program to carry out logic judgment, and the logic judgment program is specifically as follows: Extract the drilling mileage depth ΔK from the first drilling characteristic parameter E21 (K+ΔK) and the second drilling characteristic parameter E22 (K+ΔK), and enter the first numerical judgment and the second numerical judgment; First numerical judgment: judge whether the high-frequency occupancy rate ρ is less than the threshold ρMin; if so, enter the third numerical judgment; if not, enter the fourth numerical judgment; Second numerical judgment: judging whether the second drilling characteristic parameter E22(K+△K) is greater than the threshold value E22Ma; If yes, output a rockburst warning signal, and then enter the fourth numerical judgment; if no, directly enter the fourth numerical judgment; The third numerical judgment: judge whether the first drilling characteristic parameter E21 (K + △ K) is greater than the threshold value E21Max; if so, output a discontinuous geological warning signal, and then enter the fourth numerical judgment; if not, directly enter the fourth numerical judgment; Fourth numerical judgment: judge whether the mileage depth ΔK is less than the threshold value KMax; if so, enter the fifth numerical judgment; if not, end the entire logic judgment program; The fifth numerical judgment: judge whether the condition that the first section characteristic parameter E11(k) is greater than the threshold value E11Max or the second section characteristic parameter E12(k) is greater than the threshold value E12Max is met; if so, output a stop inspection signal, and then end the entire logic judgment program; if not, output a first-level alarm signal, and then end the entire logic judgment program.

2. The advanced geological prediction system based on information fusion of multiple detection methods according to claim 1 is characterized in that: It also includes a statistics and notification module, and the comprehensive analysis subsystem also includes a face analysis module and a geological radar analysis module; The statistics and notification module outputs the signals generated by the advance prediction module through the display screen, including discontinuous geological warning signals, rock burst warning signals, shutdown inspection signals, and first-level alarm signals; outputs the alarm information corresponding to the signals through the display screen, and counts the number of times each signal is generated within the preset statistical period; The tunnel face analysis module obtains the lithology characteristic data of the tunnel face at each preset time interval, and obtains the first section characteristic parameters and the second section characteristic parameters of the tunnel face with the mileage pile number K through calculation; The geological radar analysis module obtains the electromagnetic intensity transient variable ΔB of the electromagnetic wave detected at the mileage depth ΔK along the tunneling direction of the tunnel face; establishes an electromagnetic intensity transient variable-mileage depth map with the electromagnetic intensity transient variable ΔB as the vertical axis and the mileage depth ΔK as the horizontal axis; obtains the function expression ΔB=h(ΔK) of the electromagnetic intensity transient variable-mileage depth map; transforms the electromagnetic intensity transient variable-mileage depth map into the frequency domain through Fourier transform to obtain an electromagnetic wave frequency spectrum; performs feature extraction in the electromagnetic wave frequency spectrum; calculates the high-frequency occupancy rate ρ, and sends the high-frequency occupancy rate ρ to the information fusion module.

3. The advanced geological prediction system based on information fusion of multiple detection methods according to claim 1 is characterized in that: The drilling information obtained from horizontal geological drilling includes: Drilling power P, drilling speed V and drilling mileage depth ΔK of the horizontal drilling rig; Lithology test parameters of drill core, including natural density Dry density Saturation density Moisture content Test longitudinal wave velocity with sound waves Mechanical test parameters of drill core, including axial compressive strength of drill core Cohesion Elastic modulus Poisson's ratio and softening coefficient 4. The advanced geological prediction system based on information fusion of multiple detection methods according to claim 1 is characterized in that: The specific process of obtaining the first drilling characteristic parameter and the second drilling characteristic parameter through numerical calculation is as follows: With drilling power P as the vertical axis and time t as the horizontal axis, a drilling power-time graph is established and its function expression P=f1(t) is obtained; with drilling speed V as the vertical axis and time t as the horizontal axis, a drilling speed-time graph is established and its function expression V=f2(t) is obtained; By formula Calculate the first drilling characteristic parameter E21 (K + △ K) and the second drilling characteristic parameter E22 (K + △ K); where T is a preset detection time period, where is a set of preset weight factors, Where μ is the first moment of the function g(t).

5. The advanced geological prediction system based on information fusion of multiple detection methods according to claim 2 is characterized in that: The lithological characteristic data of the tunnel face include: The mileage stake number K of the tunnel face; the rock types contained in the tunnel face include slate, limestone, phyllite, sandstone, schist, andesite, shale, marble, granite and basalt, and the preset lithology parameters C are matched according to the lithology types; Dip angle of the rock formation at the tunnel face Rock thickness Number of joint groups Maximum joint gap and water output Stress-strain characteristic data of the surrounding rock around the tunnel face, including the convergence value of the surrounding rock wall Convergence rate of surrounding rock wall Convergence acceleration of surrounding rock wall Vault settlement Vault sinking rate Vault sinking acceleration Maximum principal stress value of surrounding rock Maximum principal stress direction of surrounding rock and the maximum principal stress inclination of the surrounding rock 6. The advanced geological prediction system based on information fusion of multiple detection methods according to claim 2 is characterized in that: The specific process of obtaining the first section characteristic parameters and the second section characteristic parameters of the tunnel face with mileage pile number K through calculation is as follows: By formula Calculate the first section characteristic parameter E11(k) and the second section characteristic parameter E12(k) of the tunnel face with mileage stake number K; and These are all preset weight factors.

7. The advanced geological prediction system based on information fusion of multiple detection methods according to claim 2 is characterized in that: The specific process of converting the electromagnetic intensity transient variable-mileage depth map into the frequency domain and calculating the high-frequency occupancy rate through Fourier transform is as follows: The Fourier transform formula is: Where i is an imaginary unit and i×i=-1, where v is the frequency obtained after decomposition, and S(v) is the electromagnetic wave frequency spectrum function obtained after Fourier transform; feature extraction is performed in the electromagnetic wave frequency spectrum, and the formula is used Calculate the high-frequency occupancy rate ρ, where v1 is the preset high and low frequency cutoff frequency; send the high-frequency occupancy rate ρ to the information fusion module.

Images