Method and system for determining the grade of surrounding rock in tunneling based on shield construction parameters

Abstract

The application provides a kind of based on the determination method and system of shield construction parameter evaluation in tunneling surrounding rock grade, comprising: obtaining engineering data;According to the engineering data, the specific thrust and specific torque are obtained by calculation;According to the specific thrust and specific torque, a model database is built, and precalculation is carried out;Based on the engineering data and the precalculation result, a fuzzy discrimination model for surrounding rock classification of tunneling stratum is established by using fuzzy mathematics method;The surrounding rock classification discrimination model is used for surrounding rock classification discrimination, and abnormal conditions are identified and judged.The present application fully considers the randomness of complex geology, effectively solves the problem that the engineering geological conditions in front of the working face are difficult to identify, and significantly improves the accuracy of surrounding rock identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of shield tunnel construction, in particular, to a method and system for determining the grade of surrounding rock during tunneling based on shield construction parameters. BACKGROUND

[0002] With the continuous development of urban rail transit construction in China, shield tunnel construction technology has been increasingly widely used due to its economic efficiency. Shield tunneling construction process has the characteristics of complex geological environment, high construction safety risk, and multiple risk sources, and the surrounding rock conditions and tunneling operation parameters play a crucial role. After determining the surrounding rock conditions, reasonable tunneling construction parameters can be set to control the environmental effects and construction risks to ensure the safety and efficiency of tunneling. Therefore, it is necessary to reasonably analyze the shield tunneling parameters and conduct research on the discrimination of surrounding rock types, which has a crucial impact on the safety and cost of tunnel projects. Sun Zhenchuan et al. emphasized in the paper "Analysis method of correlation between shield tunneling and geology based on big data" published in Tunnel Construction (English and Chinese) in 2020 that the correlation analysis research between shield tunneling parameters and geological parameters has great engineering significance for ensuring the smooth tunneling of tunnels. Therefore, it is necessary to propose a method for determining the grade of surrounding rock during tunneling based on shield construction parameters to ensure the safety and economy of shield tunneling.

[0003] Currently, the discrimination of shield surrounding rock is mainly based on the pre-geological survey, which is usually determined according to the test results of the pre-geological drilling, and it is often difficult to determine the engineering geological conditions in front of the tunnel face. Through the search of existing technical documents, it is found that the patent with the patent publication number CN113762360A discloses a "surrounding rock grade prediction method in TBM tunneling process based on SMOTE+ADACOST algorithm", which predicts the surrounding rock grade by training a machine learning model and warns about soft surrounding rock. However, this method is relatively complex and requires a large amount of data, and does not consider the variability of mechanical properties and actual engineering geology. SUMMARY

[0004] In view of the defects in the prior art, the purpose of the present application is to provide a method, system, medium and terminal for determining the grade of surrounding rock during tunneling based on shield construction parameters.

[0005] According to one aspect of the present application, a method for determining the grade of surrounding rock during tunneling based on shield construction parameters is provided, comprising:

[0006] obtaining engineering data;

[0007] calculating the specific thrust and specific torque based on the engineering data;

[0008] building a model database based on the specific thrust and specific torque, and performing pre-computation;

[0009] Based on the engineering data and the pre-computed results, a fuzzy discrimination model for surrounding rock classification of the tunneling stratum is established by using a fuzzy mathematics method;

[0010] Surrounding rock classification is performed by using the fuzzy discrimination model for surrounding rock classification of the tunneling stratum, and abnormal conditions are identified and judged.

[0011] Preferably, the engineering data includes shield tunneling parameters and cutter head size parameters of the shield tunneling project.

[0012] The shield tunneling parameters include total shield thrust, cutter head torque and penetration.

[0013] The cutter head size parameter data includes cutter head roller cutter radius.

[0014] Preferably, the specific thrust is , and the specific torque is . α F and β T is a uniformity coefficient considering stratum variability, and the value range is 0-1. F is total shield thrust, and the unit is kN. M is cutter head torque, and the unit is kN·m. P v is penetration, and the unit is mm. r m is the average installation radius of the roller cutter.

[0015] Preferably, the model database is composed of the specific thrust and the specific torque; and the pre-computation includes data set division and center point calculation.

[0016] The data set division process includes:

[0017] The average value of all specific thrusts and specific torques in the model database is calculated.

[0018] Data smaller than the average value is taken as a soft rock data set TS s and FS s = {( TS s1 , FS s1 ), ( TS s2 , FS s2 ),……, ( TS sm , FS sm )}m The number of data points in the soft rock dataset;

[0019] Data above the average value are used as the hard rock dataset. TS h and FS h = {( TS h1 , FS h1 ), ( TS h2 , FS h2 ),……, ( TS hn , FS hn )},in n = N – m ;

[0020] The center point calculation process includes:

[0021] Calculate the mean of the soft rock dataset and use this mean as the center point of the soft rock. p 1( TS sc , FS sc );

[0022] Calculate the mean of the hard rock dataset and use this mean as the center point of the hard rock. p 2( TS hc , FS hc ).

[0023] Preferably, the step of establishing a fuzzy discrimination model for classifying the surrounding rock of the tunneling strata using fuzzy mathematics methods based on the engineering data and the pre-calculation results includes:

[0024] The surrounding rock is classified into grades;

[0025] With specific torque TS As x Shaft, specific thrust FS As y The axis plots the parameters of each ring of the tunnel boring machine operation on a plane to obtain the tunneling characteristic space;

[0026] The characteristic space is divided into intervals;

[0027] The fuzzy set is determined based on the interval classification;

[0028] Calculate the distance between the tunneling parameter points and the fuzzy set, and then normalize the distance.

[0029] Based on the normalized distance, the membership degree of the tunneling parameter point is calculated;

[0030] Based on the membership degree, the membership degree determination surrounding rock classification evaluation standard is established.

[0031] Preferably, the tunneling parameter data point x i , y i ) is subjected to linear regression analysis to obtain the control line y = k x The lower boundary y 1 and the upper boundary y 2 of the classification interval are obtained by controlling the linear regression accuracy;

[0032] The line p 3 passing through the soft rock center point y 1 and the line p 4 passing through the hard rock center point y 2 are perpendicular to the control line;

[0033] The entire space is divided into five regions by the four lines y 1, y 2, y 3 and y 4, which correspond to five classification intervals respectively;

[0034] The fuzzy set is determined by the regression analysis of the specific torque TS and the specific thrust FS ;

[0035] ;

[0036] In the formula, μ 1-α / 2 It can be obtained by looking up the table; is the standard deviation of the regression analysis residual; k 3= -1 / k , b3= FS sc + 1 / kTS sc , b4= FS hc + 1 / kTS hc ; The four fuzzy sets A , B , G , E belong to the space;

[0037] The Euclidean distance is used to calculate the tunneling parameter point TSi , FS i ) and the distance between the tunneling parameter point and the set A 、 B 、 G and E is respectively D Α 、 D Β 、 D Γ and D Ε ;

[0038] and the distance D Α 、 D Β 、 D Γ and D Ε is respectively normalized:

[0039] ;

[0040] wherein, u = A , B , G , E ; d u is the distance between the normalized tunneling parameter point and the set D u is the distance between each tunneling parameter point and the set u , D umax is the maximum distance between the point and the set u , D umin is the minimum distance between the point and the set u ;

[0041] The membership degree of the tunneling parameter point TS i , FS i to the set A , B , G , E is respectively calculated by using the normalized distance: u Α , u Β , u Γ , u Ε ;

[0042] The surrounding rock segmentation discriminant function is established by using the membership, so that the surrounding rock grade of the tunneling stratum can be discriminated based on the membership.

[0043] Preferably, the parameter point membership is substituted into the tunneling stratum surrounding rock fuzzy discrimination model to obtain the surrounding rock classification discrimination result, and the abnormal condition is identified and judged.

[0044] According to a second aspect of the present application, a system for determining the surrounding rock grade in tunneling based on shield construction parameters is provided, comprising:

[0045] A data acquisition module is configured to acquire engineering data.

[0046] A data calculation module is configured to calculate the specific thrust and specific torque based on the engineering data.

[0047] A model building module is configured to build a model database based on the specific thrust and specific torque, and to perform pre-calculation.

[0048] A fuzzy discrimination module is configured to establish a tunneling stratum surrounding rock classification fuzzy discrimination model by using a fuzzy mathematical method based on the engineering data and the pre-calculation result.

[0049] A discrimination application module is configured to perform surrounding rock classification discrimination by using the tunneling stratum surrounding rock classification fuzzy discrimination model, and to identify and judge the abnormal condition.

[0050] According to a third aspect of the present application, an electronic device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the light field image compression method or the light field image compression system.

[0051] According to a fourth aspect of the present application, a terminal is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor is configured to execute the program to implement any one of the methods or to run the system.

[0052] Compared with the prior art, the present application has the following beneficial effects:

[0053] The method and system for determining the grade of surrounding rock in tunneling based on shield construction parameters in the embodiment of the present application determine the grade of surrounding rock of shield tunnel by using shield construction parameters, establish a fuzzy discrimination model for classifying surrounding rock of stratum being tunneled by using fuzzy mathematics, and obtain stratum classification results by using membership degrees to discriminate the surrounding rock in front of the working face. The method fully considers the randomness of complex geology and effectively solves the problem that the engineering geological conditions in front of the working face are difficult to discriminate, significantly improves the accuracy of surrounding rock discrimination, and provides a new method that is more simple, reasonable and efficient for determining the grade of surrounding rock in shield tunneling.

[0054] In addition, the method and system for determining the grade of surrounding rock in tunneling based on shield construction parameters in the embodiment of the present application can identify abnormal conditions and dangerous geology by analyzing and researching shield tunneling parameters. BRIEF DESCRIPTION OF DRAWINGS

[0055] Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments with reference to the attached drawings:

[0056] A The flow chart of the method for determining the grade of surrounding rock in shield tunneling in an embodiment of the present application;

[0057] B The flow chart of the method for determining the grade of surrounding rock in shield tunneling in a preferred embodiment of the present application;

[0058] G The schematic diagram of fuzzy sets determined by regression analysis in a preferred embodiment of the present application;

[0059] E The membership degree function value in a preferred embodiment of the present application;

[0060] TS The schematic diagram of membership degree segmented function discrimination in a preferred embodiment of the present application;

[0061] FS The structure diagram of the system for determining the grade of surrounding rock in shield tunneling in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0062] The present application will be described in detail below with reference to specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application. These all belong to the protection scope of the present application.

[0063] The application provides an embodiment of a method for determining the grade of surrounding rock in tunneling based on shield construction parameters, referring to A The process is as follows:

[0064] S100, collecting engineering data;

[0065] S200, calculating the specific thrust and specific torque based on the data collected in S100 B G ;

[0066] S300, based on the specific thrust and specific torque calculated in S200 E Figure 1 , building a model database and precomputing the data;

[0067] S400, based on the data in S100 and the precomputing results in S300, using a fuzzy mathematical method to establish a fuzzy discrimination model for classifying the surrounding rock in tunneling strata;

[0068] S500, using the fuzzy discrimination model for classifying the surrounding rock in tunneling strata to classify the surrounding rock and identify and judge abnormal conditions.

[0069] This embodiment uses a fuzzy mathematical method to build a fuzzy discrimination model for classifying the surrounding rock, which can effectively consider the complexity and randomness and solve the problem of difficult discrimination of the engineering geological conditions in front of the working face, thereby improving the accuracy of the discrimination of the surrounding rock.

[0070] In a preferred embodiment of the application, the engineering data in S100 refers to the shield tunneling parameters and cutter head size parameter data of the shield tunneling project.

[0071] The shield tunneling parameters are the specific parameters of the shield machine during construction, including the total thrust of the shield, the torque of the cutter head, and the penetration depth. The cutter head size parameter refers to the radius of the cutter head roller cutter.

[0072] In a preferred embodiment, the specific values of the shield tunneling parameters can be obtained from the shield machine's own acquisition system. Of course, other methods can also be used to directly or indirectly calculate the values.

[0073] In a preferred embodiment of the application, based on the shield tunneling parameters collected in S100, the specific thrust and specific torque can be calculated by the following formulas (1) and (2), respectively:

[0074] (1)

[0075] (2)

[0076] In the formulas, α F and β ​​T The uniformity coefficient, which takes into account the variability of the formation, is taken in the range of 0 to 1. F The total thrust of the tunnel boring machine is expressed in kN. M The torque of the cutter head is expressed in kN·m. P v Penetration depth, in mm; r m The average installation radius of the hob is typically 0.55 to 0.60 times the radius of the cutter head.

[0077] Specific thrust Figure 2 The thrust (kN / mm) generated by the hydraulic system per 1mm of shield advance is related to the soil's ability to resist the shield's advance. Specific torque. Figure 3 The torque (kN / mm) required by the main drive to penetrate 1mm of soil is related to the soil's resistance to breakage. The specific thrust in this example... Figure 4 and specific torque Figure 5 It can intuitively show the relationship between the shield cutterhead torque and total thrust, as well as the relationship between shield parameters and geological conditions, thereby improving the accuracy of surrounding rock grade determination.

[0078] In a preferred embodiment of the present invention, step S300 is implemented to build a model database and pre-calculate the data.

[0079] The database consists of specific thrust Figure 6 and specific torque Figure 1 The composition and pre-computation include dataset partitioning and centroid calculation.

[0080] The dataset is divided into two parts: hard rock and soft rock datasets, which are determined by the overall mean.

[0081] The overall average refers to the value calculated in the database. FS and TS The average of all the data.

[0082] Data with values ​​less than the mean will be used as the soft rock dataset. FS s and TS s = {( FS s1 , TS s1 ), ( FS s2 , TS s2 ), ……,( FS sm , TS sm )},in m The number of data points in the soft rock dataset is greater than the mean; those in the hard rock dataset are used as the hard rock dataset.FS h and TS h = ( TS h1 , FS h1 ), ( TS h2 , FS h2 ), ……, ( TS hn , FS hn ), wherein n = N - m .

[0083] The center point calculation refers to calculating the mean center of the soft rock data set p 1( TS sc , FS sc ) is the soft rock center point, and the mean center of the hard rock data set p 2( TS hc , FS hc ) is the hard rock center point.

[0084] In the embodiment, the soft rock center point and the hard rock center point respectively represent the mean values of the soft rock data set and the hard rock data set, and can represent the average level of the numerical size of the data set. In the subsequent classification of the surrounding rock grade, the center point can provide a reference for the division of the classification interval and the judgment of the tunneling geological characteristics, and facilitate the judgment of the parameter setting and the tunneling state of the shield machine through the numerical size of the specific thrust and the specific torque.

[0085] In one preferred embodiment of the present application, S400 is implemented, and a tunneling stratum surrounding rock classification fuzzy discrimination model is established by using a fuzzy mathematics method, and the specific process includes:

[0086] S401, determining the surrounding rock evaluation classification.

[0087] The surrounding rock evaluation classification should be divided according to the actual engineering geological conditions of the surrounding rock grade. Generally, the classification is performed according to the soft and hard degree, weathering condition and the like of the surrounding rock, and the surrounding rock can be classified into homogeneous soft rock, medium-soft stratum, relatively homogeneous hard rock, medium-weathered soft and hard uneven stratum, medium-hard stratum, super-soft weak or super-hard stratum, soft and hard uneven hard stratum and the like.

[0088] S402, drawing a tunneling characteristic space schematic diagram.

[0089] The specific torque TS is taken as the x axis, and the specific thrust FSAs y the shaft, the parameters of each ring of the shield machine can be plotted in a plane, i.e., a tunneling characteristic space. The tunneling parameter data points in the space are TS i , FS i , i.e., x i , y i .

[0090] S403, the classification intervals of the tunneling characteristic space are preliminarily divided.

[0091] Linear regression analysis is performed on the tunneling parameter data points x i , y i to obtain a control line y = k x The lower boundary y 1 and the upper boundary y 2 of the classification intervals are obtained by the control linear regression accuracy.

[0092] A line y 3 passing through the soft rock center point p 1 and a line y 4 passing through the hard rock center point p 2 are perpendicular to the control line.

[0093] The entire space is divided into five regions by the above four lines y 1, y 2, y 3 and y 4, which correspond to five types of classification intervals, respectively.

[0094] The classification intervals divided can provide a judgment reference for the parameter setting and the tunneling state of the shield machine. In the space, two of the five classification intervals are outside the lower boundary y 1 and the upper boundary y 2 corresponding to the control linear regression accuracy. At this time, for the tunneling parameter points x i , y i located in the two intervals, it can be considered that the parameter setting of the shield machine is unreasonable, the shield machine is in a low-efficiency tunneling working condition or the geology is in an abnormal condition. The specific situation can be analyzed in combination with the numerical size of the specific thrust and the specific torque. Meanwhile, for the other three intervals in the space, it can be considered that the shield machine is in a normal working condition. The specific situation can be analyzed in combination with the numerical size of the specific thrust and the specific torque, and the tunneling parameter points xi , y i ) and two mean centers.

[0095] S404, by specific torque TS and specific thrust FS Test principle in regression analysis, determine fuzzy set:

[0096] ;

[0097] In the formula, TS 1-α / 2 Can be obtained by looking up table; The standard deviation of the regression analysis residual; k 3= -1 / k , b 3= FS sc + 1 / TS sc , b 4= FS hc + 1 / TS hc The above four fuzzy sets ( FS , TS , FS , TS ) belong to space.

[0098] S405, using the Euclidean distance to calculate the distance between the tunneling parameter point ( FS i , μ i ) and four sets, and carry on the normalization processing to get the normalized distance. Specifically,

[0099] The distance of tunneling parameter point to set FS , kTS , FS and kTS is respectively D Α , D Β , D Γ and D Ε .

[0100] The normalization method is as follows formula (4):

[0101] (4)

[0102] In the formula, u = A , B ,G , E ; d u is the distance of the normalized tunneling parameter point to each set, D u is the distance of each tunneling parameter point to set u, D umax is the maximum value of the distance of the point to set u . D umin is the minimum value of the distance of the point to set u .

[0103] S406, the normalized distance is used to calculate the membership of the tunneling parameter point (x, y, z) to the set (u, v, w), TS i , FS i ) to the set (u, v, w), A , B , G , E .

[0104] , wherein: u Α , u Β , u Γ , u Ε are the membership of the tunneling parameter point to the fuzzy set A , B , G , E respectively.

[0105] S407, the surrounding rock evaluation standard is determined.

[0106] The surrounding rock evaluation standard needs to be determined according to the actual situation of the construction site. The surrounding rock segmentation discriminant function is established by using the membership, and the surrounding rock grade of the tunneling stratum of the shield machine can be discriminated based on the membership. Generally, the process of establishing the surrounding rock segmentation discriminant function is as follows: first, for the three normal tunneling classification intervals of the space, the fuzzy discriminant segmentation function is drawn by taking u Γ as the horizontal axis and u Ε as the vertical axis; then, for the two abnormal tunneling classification intervals of the space, the u A and u B are directly determined.

[0107] The embodiment analyzes and researches the tunneling parameters of a shield tunneling machine, adopts a fuzzy mathematics method, constructs a surrounding rock classification fuzzy discrimination model, obtains stratum classification results by using membership degrees, discriminates the surrounding rock in front of a working face, and can identify abnormal conditions and dangerous geology, thereby significantly improving the accuracy of surrounding rock discrimination.

[0108] In a preferred embodiment of the present application, S500 is implemented, i.e., the parameter point membership degree is substituted into the tunneling stratum surrounding rock fuzzy discrimination model, i.e., the surrounding rock evaluation standard or rock section discrimination function; the surrounding rock classification discrimination result is obtained, and abnormal conditions are identified and judged.

[0109] Based on the same inventive concept, another embodiment of the present application provides a determination system for evaluating surrounding rock grades in tunneling based on shield construction parameters, as shown in TS , comprising a data acquisition module, a data calculation module, a model building module, a fuzzy discrimination module, and a discrimination application module; the data acquisition module acquires engineering data; the data calculation module calculates the specific thrust and specific torque based on the engineering data; the model building module builds a model database based on the specific thrust and specific torque, and performs pre-calculation; the fuzzy discrimination module establishes a tunneling stratum surrounding rock classification fuzzy discrimination model based on the engineering data and the pre-calculation result by using a fuzzy mathematics method; and the discrimination application module uses the tunneling stratum surrounding rock classification fuzzy discrimination model to perform surrounding rock classification discrimination, and identifies and judges abnormal conditions.

[0110] Based on the same inventive concept, another embodiment of the present application provides an electronic device, which comprises a processor and a memory, the memory stores at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the light field image compression method or the light field image compression system.

[0111] Based on the same inventive concept, another embodiment of the present application provides a terminal, which comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executes the program to implement any of the methods or runs the system.

[0112] In order to further understand the application and verify its effect, the application provides a specific application example. Taking the construction of a newly-built railway shield tunnel in a city as an example, the earth pressure balance shield construction is adopted, the buried depth is 11-22 m, the excavation diameter is 9.15 m, the inner diameter and the outer diameter of the tunnel are 8 m and 8.8 m respectively, and the groundwater depth is 0.1-5.7 m underground. The geological conditions along the large-diameter shield tunnel of the project are complex, the strata mainly include silt layer, silty clay, sand layer, full, strong and medium weathered mixed granite, and the surrounding environment is complex and needs to pass through existing high-speed, high-voltage towers and rivers and ponds, etc., so the parameter optimization of the shield construction is difficult. In the construction of the project, it is necessary to ensure that the construction parameter setting matches the surrounding rock conditions, so as to ensure the stability of the excavation face and reduce the environmental effect of the shield construction. Therefore, in the project, the method for determining the surrounding rock grade of the tunnel 250-400 rings based on the shield construction parameter evaluation is adopted to evaluate the surrounding rock grade of the tunnel 250-400 rings, FS The flow chart of the method for determining the surrounding rock grade in the shield tunneling process of the embodiment is shown in the figure, and the method has five steps, and the specific steps are as follows:

[0113] Step 1: Collect engineering data.

[0114] In the embodiment, the cutter head of the shield machine is provided with 6 17-inch double-blade center cutters and 48 19-inch single-blade face cutters, and the diameters thereof are 432 mm and 483 mm respectively. The data of the research section 250-400 rings are exported from the self-collecting system of the shield machine, including the total thrust F , the cutter head torque M and the penetration P v .

[0115] Step 2: Calculate the specific thrust A and the specific torque B .

[0116] The specific thrust G and the specific torque E can intuitively reflect the relationship between the cutter head torque and the total thrust of the shield and the relationship between the shield parameters and the geological conditions, and can be calculated by the following formula:

[0117] ;

[0118] ;

[0119] In the formula, α F and β T is the uniformity coefficient considering the variability of the stratum, and in the embodiment, 1 is taken; F the unit is kN, M the unit is kN·m, P vThe unit is mm; r m The average installation radius of the hob is taken as 0.65 times the radius of the cutter head in this embodiment.

[0120] Step 3: Build a model database and perform pre-calculation on the data.

[0121] The database consists of specific thrust. A and specific torque B The composition and pre-calculation include dataset partitioning and centroid calculation. In this embodiment, the overall average value, i.e., the value in the database, is used. G and E The data is divided into two parts: hard rock and soft rock datasets, based on the average of all data. Data with values ​​less than the average is classified as the soft rock dataset. TS s and FS s = {( A s1 , B s1 ), ( G s2 , E s2 ),……, ( Figure 6 sm , Figure 2 sm )},in m = 79 represents the number of data points in the soft rock dataset; those greater than the mean are used in the hard rock dataset. FS h and TS h = {( FS h1 , TS h1 ), ( FS h2 , TS h2 ),……, ( FS hn , TS hn )},in n = 71.

[0122] In this embodiment, the mean center of the soft rock dataset ( TS sc , FS sc () represents the center point of the soft rock. p 1 (29.79, 660.50), the mean center of the hard rock dataset ( TS hc , FS hchard rock center point p 2 (29.79, 660.50).

[0123] Fourth step: using fuzzy mathematics method to establish the tunneling stratum surrounding rock classification fuzzy discrimination model, specifically:

[0124] 1) Determine the surrounding rock evaluation classification.

[0125] The surrounding rock evaluation classification should be divided according to the actual engineering geological conditions of the surrounding rock grade, which can be generally classified according to the softness and hardness, weathering conditions, etc. In this embodiment, mainly full weathering mixed granite is taken as the main part, and there is soft stratum on the upper part, and silty clay is often mixed with granite, and the main geological characteristics of this embodiment are soft on the upper part and hard on the lower part. In this embodiment, the surrounding rock is divided into 9 categories, relatively homogeneous soft rock A1, full weathering soft and hard uneven stratum A2, medium soft stratum A3, relatively homogeneous hard rock A4, strong weathering and medium weathering soft and hard uneven stratum A5, medium hard stratum A6, super soft weak or super hard stratum A7, soft and hard uneven hard stratum A8, soft and hard uneven soft stratum A9.

[0126] 2) Draw a tunneling characteristic space diagram.

[0127] In this embodiment, the shield machine operation 250~400 ring parameters are drawn in a plane as the tunneling characteristic space. TS as the axis, x as the axis, FS y

[0128] 3) Preliminary division of the classification interval of the tunneling characteristic space.

[0129] In this embodiment, linear regression analysis is performed on the 250~400 ring tunneling parameter data points x i , y i The regression equation y = 19.438 x is obtained, which is the control line of this embodiment, and the lower boundary y 1 and the upper boundary y 2 of the classification interval are obtained by controlling the linear regression accuracy. p 1(29.79, 660.50) is a line y 3 and a line p 2(91.76, 1760.56) is a line y 4, which is perpendicular to the control line. Therefore, the above four lines y 1, y 2, y 3 and y ​​4, the whole space is divided into 5 regions, corresponding to five classification intervals respectively.

[0130] 4) by specific torque TS and specific thrust FS Test principle in regression analysis, determine fuzzy set:

[0131] ;

[0132] The confidence level of this embodiment is 0.95, and the table can be obtained by looking up TS 1-0.05 / 2 = 1.96; The standard deviation of the regression analysis residual is 146.53, so the set FS , TS is respectively:

[0133] ;

[0134] The soft rock center point p 1(29.79, 660.50) of this embodiment makes a line y 3 and the hard rock center point p 2(91.76, 1760.56) makes a line y 4 and the control line y = 19.438 x Perpendicular intersection, so the set FS and TS :

[0135] ;

[0136] The above four fuzzy sets in this embodiment FS , TS , FS , TS All belong to space, and the excavation characteristic space divided by the set is shown in FS .

[0137] 5) The Euclidean distance is used to calculate the distance between the excavation parameter point TS i , FS i and the four sets, and the normalized distance is obtained after normalization.

[0138] In this embodiment, the distances of the excavation parameter point to the sets TS , FS , TS and FS are respectively D Α , D Β、 D Γ and D Ε , the distance can be calculated as:

[0139] ;

[0140] In this embodiment, the calculated distance is normalized, and the normalization formula is as follows:

[0141] ;

[0142] In the formula, u = μ , A , B , G ; d u is the distance from the normalized tunneling parameter point to each set; D u is the distance from each tunneling parameter point to set u; D umax is the maximum distance from the point to set u ; D umin is the minimum distance from the point to set u .

[0143] 6) Calculate the membership of all tunneling parameter points ( E i , A i ) to set ( B , G , E , Figure 3 ), which are u Α , u Β , u Γ , u Ε respectively. In this embodiment, the calculated membership is shown in TS .

[0144] 7) Determine the surrounding rock evaluation standard.

[0145] In this embodiment, according to the actual situation of the construction site, the membership is used to establish a surrounding rock segmentation discriminant function, that is, the membership can be used to make fuzzy discrimination of the surrounding rock grade of the tunneling stratum of the shield machine. Specifically, take u Γ as the horizontal axis, u Ε as the vertical axis, and draw a segmented function for fuzzy discrimination, as shown in FSAs shown.

[0146] Specifically:

[0147] For the three normal tunneling classification intervals in the space, the following is adopted: u Γ As the horizontal axis, u Ε Used as the vertical axis to plot the piecewise function for fuzzy discrimination;

[0148] For the two abnormal excavation classification intervals in the space, directly based on... u A and u B judge.

[0149] The evaluation criteria for each example are described in detail here:

[0150] ①. For those outside the confidence level threshold (the threshold in this embodiment is 0.95), i.e., within... y 1( x i )and y 2( x i In addition, it was identified as an abnormal tunneling state;

[0151] ②. In space y 1( x i ) ≤ y i ≤ y 2( x i This is a normal tunneling classification section, using... A The evaluation criteria classify the surrounding rock, specifically:

[0152] a. Regarding u Ε <0.5 and u Γ ≤ 0.5: corresponds to A7, if u Ε > u Γ This corresponds to extremely hard strata, at which point the tunnel boring machine may be facing hard strata such as moderately weathered mixed granite; if u Ε < u Γ This corresponds to an extremely soft stratum, which may be located in a sandy soil layer or an artificial fill layer, etc.

[0153] b. For u Ε >0.5 and u Γ ≥ 0.5: Ifu Ε u Γ Corresponding to A8, that is, corresponding to the uneven hard and soft stratum (partial hard); if u Ε u Γ Corresponding to A9, that is, corresponding to the uneven hard and soft stratum (partial soft), at this time the shield may face the similar proportion of silty clay layer and fully weathered mixed granite layer;

[0154] c. For u Γ ≥ 0.5 and u Ε <0.5: if u Ε <0.22 (the specific value is determined in combination with engineering experience and actual data), corresponding to A1, which corresponds to soft normal, at this time the shield is excavated in the relatively homogeneous silty clay or silt layer; if 0.5> u Ε >0.22 and u Γ <0.85, corresponding to A2, that is, corresponding to the uneven hard and soft stratum (partial soft), at this time the shield is excavated in the mixed granite layer with a proportion not more than 15% in the stratum section (the specific value is determined in combination with engineering experience and actual data to correspond to 15% granite content); if 0.5> u Ε >0.22 and u Γ ≥ 0.85, corresponding to A3, that is, corresponding to the medium soft normal, at this time the shield may be excavated in the fully weathered mixed granite containing silty clay;

[0155] d. For u Ε ≥ 0.5 and u Γ <0.5: if u Γ <0.19, corresponding to A4, which corresponds to the hard normal, at this time the shield is excavated in the relatively homogeneous strong weathered mixed granite; if 0.5> u Γ >0.19 and u Ε <0.80, corresponding to A5, that is, corresponding to the uneven hard and soft stratum (partial hard), at this time the shield is excavated in the fully weathered granite containing silty clay, and the thrust is slightly high; if 0.5> u Γ >0.19 and u Γ ​​≥ 0.80, corresponding to A6, namely corresponding to medium-hard normal, at this time the shield may be in full, strong mixed granite stratum tunneling.

[0156] Fifth step: the 250~400 ring tunneling parameter points are substituted into the tunneling stratum surrounding rock fuzzy discrimination model, the membership degree thereof can be calculated (see B ), and according to the surrounding rock evaluation standard ( G E A B G E TS FS A B G E Figure 4 Figure 5 Figure 5 Figure 4 Figure 5 ), the surrounding rock classification discrimination result can be obtained, and the abnormal condition can be identified and judged. In this embodiment, part of the representative surrounding rock classification fuzzy discrimination result is shown in Table 1.

[0157] Table 1 Part of the representative surrounding rock classification fuzzy discrimination result

[0158]

[0159] The specific embodiments of the present application are described above. It should be understood that the present application is not limited to the above specific embodiments, and various modifications or changes can be made by those skilled in the art within the scope of the claims, which does not affect the essential content of the present application. The above preferred features can be used in combination in the case of not conflicting with each other.

Claims

1. A method for determining the grade of surrounding rock in tunneling based on shield construction parameters, characterized in that, The method comprises the following steps: acquiring engineering data; calculating specific thrust and specific torque according to the engineering data; building a model database according to the specific thrust and specific torque, and precomputing; establishing a tunneling stratum surrounding rock classification fuzzy discrimination model by using fuzzy mathematics method based on the engineering data and the precomputing result; classifying and discriminating surrounding rock by using the tunneling stratum surrounding rock classification fuzzy discrimination model, and identifying and judging abnormal conditions; wherein, the step of establishing a tunneling stratum surrounding rock classification fuzzy discrimination model by using fuzzy mathematics method based on the engineering data and the precomputing result comprises: dividing surrounding rock grades; in terms of torque TS as x axis, specific thrust FS as y axis, the parameters of operating each ring of the shield machine are plotted in a plane, and the tunneling characteristic space is obtained; classifying the characteristic space by intervals; determining a fuzzy set based on the interval classification; calculating the distance between the tunneling parameter point and the fuzzy set, and normalizing the distance; calculating the membership degree of the tunneling parameter point based on the normalized distance; determining the surrounding rock classification evaluation standard based on the membership degree.

2. The method according to claim 1, characterized in that, The engineering data comprises shield tunneling parameters and cutter head size parameters of shield tunnel engineering; wherein, the shield tunneling parameters comprise total thrust of the shield, cutter head torque and penetration degree; wherein, the cutter head size parameter data comprises cutter head roller radius.

3. The method of claim 1, wherein the method is characterized by, The model database is composed of the specific thrust and the specific torque; the precomputing comprises data set division and center point calculation; wherein, the data set division process comprises: calculating the average value of all specific thrusts and specific torques in the model database; Data less than the average value is taken as the soft rock data set TS s and FS s = {( TS s1 , FS s1 ), ( TS s2 , FS s2 ), ……,( TS sm , FS sm )} wherein m is the number of data points of the soft rock data set; Data greater than the average value as hard rock data set TS h and FS h = {( TS h1 , FS h1 ), ( TS h2 , FS h2 ), ……,( TS hn , FS hn )}, wherein n = N – m ; The center point calculation process comprises: calculating a mean of the soft rock data set, the mean being a soft rock center point p 1 ( TS sc , FS sc ) calculating a mean of the hard rock data set, the mean being a hard rock center point p 2 ( TS hc , FS hc ) 4. The method according to claim 3, characterized in that, Linear regression analysis is performed on the tunneling parameter data points x i , y i ) to obtain a control line y = k x , and the lower boundary y 1 and the upper boundary y 2 of the classification interval are obtained by controlling the linear regression accuracy. through the soft rock center point p 1 draw a line y 3 and through the hard rock center point p 2 draw a line y 4 intersecting the control line perpendicularly; By four lines y 1、 y 2、 y 3 and y 4, the entire space is divided into 5 regions, corresponding to five types of classification intervals respectively; By torque TS And thrust FS Test principle in regression analysis, determine fuzzy sets: ； wherein may be obtained by looking up a table; is the standard deviation of the regression analysis residuals; k 3 = -1 / k , b 3 = FS sc + 1 / kTS sc , b 4 = FS hc + 1 / kTS hc ; the four fuzzy sets ( Α , Β , Γ , Ε ) belong to the space; Euclidean distance is used to calculate tunneling parameter points ( TS i , FS i The distance between the tunneling parameter point and the four fuzzy sets, and the distance from the tunneling parameter point to the set. Α , Β , Γ and Ε The distances are respectively D Α , D Β , D Γ and D Ε ; normalizing the distances D Α , D Β , D Γ and D Ε respectively. ； wherein u = 0.5 Α , Β , Γ , Ε ; d u is the distance of the normalized tunneling parameter point to the respective set, D u is the distance of each tunneling parameter point to the set u , D umax is the maximum value of the distance of the point to the set u , D umin is the minimum value of the distance of the point to the set u . The normalized distance is used to calculate the tunneling parameter point TS i , FS i The membership degree of the set Α , Β , Γ , Ε is respectively , , , ; The tunneling stratum surrounding rock classification fuzzy discrimination model is established by using the membership degree, and the membership degree is used to fuzzy discriminate the surrounding rock grade of the tunneling stratum of the shield machine.

5. The method of claim 4, wherein the method is characterized by, The parameter point membership degree is substituted into the tunneling stratum surrounding rock classification fuzzy discrimination model to obtain the surrounding rock classification discrimination result, and abnormal conditions are identified and judged.

6. A determination system for determining a method for evaluating a surrounding rock grade in tunneling based on the shield tunneling parameter evaluation method according to claim 1, characterized in that, The method comprises the following steps: a data acquisition module for acquiring engineering data; a data calculation module for calculating specific thrust and specific torque according to the engineering data; a model building module for building a model database according to the specific thrust and specific torque, and precomputing; a fuzzy discrimination module for establishing a tunneling stratum surrounding rock classification fuzzy discrimination model by using fuzzy mathematics method based on the engineering data and the precomputing result; a discrimination application module for classifying and discriminating surrounding rock by using the tunneling stratum surrounding rock classification fuzzy discrimination model, and identifying and judging abnormal conditions.

7. An electronic device, comprising: The electronic device comprises a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set, which are loaded and executed by the processor to implement any one of the following methods or systems: - The method for determining the grade of surrounding rock in tunneling based on the parameters of shield construction according to any one of claims 1-5, or - The determination system according to claim 6.

Images