Shield tunnel stratum type identification method, device and program product

Abstract

The application discloses a shield tunnel stratum type identification method, device and program product, and belongs to the technical field of shield tunnels. The method comprises the following steps: acquiring survey parameters and shield parameters of a target stratum slice, wherein the target stratum slice is obtained by performing slicing processing on a target soil column located in a shield tunnel area; performing feature extraction on the shield parameters to obtain shield parameter features of the target stratum slice, which indicate the stratum strength of the target stratum slice; performing type feature extraction on the survey parameters of a survey hole soil column adjacent to the target stratum slice to obtain stratum type features of the target stratum slice, which indicate the distribution of the stratum type of the survey hole soil column adjacent to the target stratum slice, wherein the survey hole soil column is located in the shield tunnel area; and inputting the shield parameter features, the stratum type features, the survey parameters and the shield parameters into a stratum type identification model to obtain the stratum type of the target stratum slice. The application improves the identification precision of the stratum type.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of shield tunneling, and in particular to a shield tunnel stratum type identification method, device and program product. BACKGROUND

[0002] A shield tunnel is a tunnel structure formed by using a shield machine to excavate underground, and its core principle is to cut rock and soil through a cutter head at the front end of the shield machine while forming a tunnel lining by assembling segments to realize excavation and support at the same time. In related technologies, a mapping relationship between tunneling parameters of a shield tunnel and stratum types is constructed to identify the stratum type of an unknown area in the shield tunnel, thereby realizing geological survey of the shield tunnel. However, related technologies only consider tunneling parameters of the shield tunnel, and the considered factors are relatively single, which is difficult to comprehensively reflect the actual geological conditions of the shield tunnel, thereby leading to low identification accuracy of the stratum type. SUMMARY

[0003] The main purpose of the embodiments of the present application is to propose a shield tunnel stratum type identification method, device and program product, which aims to effectively improve the identification accuracy of the stratum type.

[0004] To achieve the above-mentioned purpose, one aspect of the embodiments of the present application proposes a shield tunnel stratum type identification method, which comprises:

[0005] obtaining survey parameters and shield parameters of a target stratum slice; wherein the target stratum slice is obtained by slicing a target soil column located in a shield tunnel area;

[0006] performing feature extraction on the shield parameters to obtain shield parameter features of the target stratum slice; wherein the shield parameter features are used to indicate the stratum strength of the target stratum slice;

[0007] performing type feature extraction according to survey parameters of a survey hole soil column adjacent to the target stratum slice to obtain stratum type features of the target stratum slice; wherein the stratum type features are used to indicate the distribution of the stratum type of the survey hole soil column adjacent to the target stratum slice, and the survey hole soil column is located in the shield tunnel area;

[0008] inputting the shield parameter features, the stratum type features, the survey parameters and the shield parameters into a stratum type identification model to obtain the stratum type of the target stratum slice.

[0009] In some embodiments, the slicing of the target soil column located in the shield tunnel area comprises:

[0010] Within the contour line of the shield tunnel region, a plurality of virtual soil columns perpendicular to the tunneling direction are arranged along the tunneling direction, and any one of the virtual soil columns is determined as the target soil column; wherein the diameter of the virtual soil column is the same as the diameter of the survey hole soil column, and the length of the virtual soil column is the excavation diameter of the shield tunnel region;

[0011] The target soil column is divided into a plurality of target stratum slices along a direction perpendicular to the tunneling direction.

[0012] In some embodiments, the shield parameters include a shield thrust value, a cutter head torque value, a propulsion speed value, and a cutter head rotation speed value; the feature extraction of the shield parameters to obtain the shield parameter feature of the target stratum slice includes:

[0013] The product of the cutter head torque value and the cutter head rotation speed value is obtained as a cutter head operation feature;

[0014] The product of the propulsion speed value and the shield thrust value is obtained as a propulsion operation feature;

[0015] The ratio of the cutter head operation feature to the propulsion operation feature is obtained as the shield parameter feature.

[0016] In some embodiments, the survey parameters include a plane coordinate value and a depth value; the type feature extraction according to the survey parameters of the survey hole soil columns adjacent to the target stratum slice to obtain the stratum type feature of the target stratum slice includes:

[0017] From each of the survey hole soil columns, a stratum slice matching the depth value of the target stratum slice is selected as a candidate stratum slice;

[0018] According to the plane coordinate value of the target stratum slice and the plane coordinate value of each of the candidate stratum slices, a plurality of the candidate stratum slices adjacent to the target stratum slice are selected as adjacent stratum slices;

[0019] The type feature extraction is performed according to the stratum type of each of the adjacent stratum slices to obtain the stratum type feature of the target stratum slice.

[0020] In some embodiments, the selection of the stratum slice matching the depth value of the target stratum slice from each of the survey hole soil columns as a candidate stratum slice includes:

[0021] From each of the survey hole soil columns, a stratum slice located at the same depth value as the target stratum slice is selected as the candidate stratum slice.

[0022] In some embodiments, the selecting, according to the planar coordinate value of the target stratum slice and the planar coordinate value of each of the candidate stratum slices, a plurality of the candidate stratum slices adjacent to the target stratum slice as adjacent stratum slices, comprises:

[0023] obtaining a distance value of each of the candidate stratum slices from the target stratum slice according to the planar coordinate value of the target stratum slice and the planar coordinate value of each of the candidate stratum slices;

[0024] determining the candidate stratum slice with the distance value less than a distance threshold as the adjacent stratum slice.

[0025] In some embodiments, the type feature extraction according to the stratum type of each of the adjacent stratum slices to obtain the stratum type feature of the target stratum slice comprises:

[0026] obtaining the reciprocal of the distance value of each of the adjacent stratum slices from the target stratum slice as a weight value of each of the adjacent stratum slices;

[0027] performing assignment processing on the stratum type of each of the adjacent stratum slices to obtain a stratum type value of each of the adjacent stratum slices;

[0028] obtaining the product of the weight value and the stratum type value of each of the adjacent stratum slices as a stratum type weighted feature of each of the adjacent stratum slices;

[0029] determining the ratio of the sum of the stratum type weighted features of each of the adjacent stratum slices to the sum of the weight values of each of the adjacent stratum slices as the stratum type feature.

[0030] In some embodiments, the method further comprises:

[0031] obtaining stratum slice samples, shield parameter samples and stratum types of a plurality of the investigation hole soil columns; wherein the stratum slice is obtained by slicing processing on the investigation hole soil column;

[0032] performing feature extraction on the shield parameter samples of each of the stratum slices to obtain shield parameter feature samples of each of the stratum slices; wherein the shield parameter feature sample is used to indicate the stratum strength of the stratum slice;

[0033] performing type feature extraction according to the investigation parameters of the investigation hole soil column adjacent to each of the stratum slices to obtain stratum type feature samples of each of the stratum slices; wherein the stratum type feature sample is used to indicate the distribution of the stratum type of the investigation hole soil column adjacent to the stratum slice;

[0034] The survey parameter samples, the shield parameter samples, the shield parameter feature samples and the stratum type feature samples of each stratum slice are taken as input data, and the stratum types of each stratum slice are taken as labels, to construct a shield tunnel data set;

[0035] The shield tunnel data set is subjected to model training by using a machine learning method, to obtain the stratum type identification model.

[0036] To achieve the above object, another aspect of the embodiment of the present application provides a shield tunnel stratum type identification device, which comprises:

[0037] An acquisition module is configured to acquire survey parameters and shield parameters of a target stratum slice, wherein the target stratum slice is obtained by slicing a target soil column located in a shield tunnel region;

[0038] A first processing module is configured to perform feature extraction on the shield parameters, to obtain shield parameter features of the target stratum slice, wherein the shield parameter features are used to indicate stratum strength of the target stratum slice;

[0039] A second processing module is configured to perform type feature extraction according to survey parameters of a survey hole soil column adjacent to the target stratum slice, to obtain stratum type features of the target stratum slice, wherein the stratum type features are used to indicate distribution of stratum types of the survey hole soil column adjacent to the target stratum slice, and the survey hole soil column is located in the shield tunnel region;

[0040] A third processing module is configured to input the shield parameter features, the stratum type features, the survey parameters and the shield parameters into a stratum type identification model, to obtain a stratum type of the target stratum slice.

[0041] To achieve the above object, another aspect of the embodiment of the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above-described shield tunnel stratum type identification method.

[0042] According to the shield tunnel stratum type identification method, device and program product provided in the embodiment of the present application, the survey parameters and the shield parameters of a target stratum slice are obtained, the target stratum slice is obtained by performing slice processing on a target soil column located in a shield tunnel region; feature extraction is performed on the shield parameters to obtain shield parameter features of the target stratum slice, which indicate the stratum strength of the target stratum slice; type feature extraction is performed on the survey parameters of a survey hole soil column adjacent to the target stratum slice to obtain stratum type features of the target stratum slice, which indicate the distribution of the stratum type of the survey hole soil column adjacent to the target stratum slice, the survey hole soil column being located in the shield tunnel region; the shield parameter features, the stratum type features, the survey parameters and the shield parameters are input into a stratum type identification model to obtain the stratum type of the target stratum slice. According to the technical solution of the embodiment of the present application, the cross verification and complementarity between multiple source data are used to realize the identification processing of the stratum type, which can effectively make up for the information limitation when the stratum type is identified by using data such as shield parameters alone, and then effectively improve the identification accuracy of the stratum type, and provide effective data support for the construction decision of the shield tunnel.

[0043] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the structure particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 is a flowchart of a shield tunnel stratum type identification method provided by the present application;

[0045] Figure 2 is an example diagram of performing slice processing on a target soil column provided by the present application;

[0046] Figure 3 is an example diagram of performing slice processing on a survey hole soil column provided by the present application;

[0047] Figure 4 is an example diagram of an adjacent stratum slice provided by the present application;

[0048] Figure 5 is an implementation process diagram of a shield tunnel stratum type identification method provided by the present application;

[0049] Figure 6 is a performance example diagram of a machine learning method provided by the present application;

[0050] Figure 7 is an example diagram of a geological profile provided by the present application;

[0051] Figure 8It is a structural diagram of a shield tunnel stratum type identification device provided by the application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0053] It can be understood that the terms "first", "second", and the like used in the present application can be used herein to describe various concepts, but unless specifically stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "when" or "in response to determining".

[0054] The terms "at least one", "multiple", "each", "any" and the like used in the present application include one, two or more than two, multiple includes two or more than two, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0056] Before the embodiments of the present application are described in detail, first, some nouns and terms involved in the embodiments of the present application are described, and the nouns and terms involved in the embodiments of the present application are applicable to the following explanations.

[0057] 1) Shield tunnel, a kind of tunnel structure formed by using shield machine (i.e. full face tunnel boring machine) to dig underground, its core principle is to cut rock and soil by the cutter head at the front end of shield machine, simultaneously use segmental lining to form tunnel lining, realize side excavation side support, with the advantages of construction safety, little influence on ground traffic, adapt to complex geological conditions, etc.

[0058] 2) Investigation hole, which is a core technical means for obtaining stratum parameters, supporting design and construction in shield tunnel engineering, and can be divided into control hole, general hole and technical hole (such as sampling test hole, hydrological test hole, etc.) according to functions.

[0059] In recent years, shield method is widely applied in tunnel construction with its safe and efficient construction process, and the tunnel constructed by shield method is usually referred to as shield tunnel. The construction process and posture of shield tunnel are usually affected by the rock-soil properties of the shield tunneling section. Specifically, the stratum traversed by the shield machine in the tunneling process is often complex and changeable, such as soft soil stratum, sandy soil stratum, boulder stratum, hard rock stratum and composite stratum with uneven soft and hard strata, etc. These complex and changeable strata are prone to increase the construction risk, such as tunneling difficulty, abnormal wear of cutter, ground subsidence and water inrush, etc., which seriously affects the construction efficiency of shield tunnel and causes the construction project to be delayed. If the continuous geological conditions in the tunnel excavation area can be determined, the construction risk of shield tunnel can be effectively reduced, and the construction process of shield tunnel can be ensured to proceed normally.

[0060] To this end, in the related art, the stratum type of an unknown area in a shield tunnel is identified by constructing a mapping relationship between the tunneling parameters (such as the tunneling parameters at the investigation hole) of the shield tunnel and the stratum type, and then the geological investigation of the shield tunnel is realized. For example, first, the investigation report of the shield tunnel before construction is collected and the stratum conditions are pre-classified, and the tunneling parameters collected in real time are processed by removing blank values and abnormal values, smoothing, twice transforming into field penetration index and torque penetration index, and standardizing, then the processed indexes are plotted into a two-dimensional plane graph, whether a new stratum type is generated is judged and the number of stratum types is updated to K, then the standardized parameters are input into the K-Means algorithm, K cluster centers are selected and the stratum types are divided according to the shortest distance method, the positions of the divided type center points are recalculated, the square error is calculated and minimized, and finally the stratum type corresponding to the determined parameters is output. However, the related art only considers the tunneling parameters of the shield tunnel when implemented, and the considered factors are relatively single, which is difficult to fully reflect the actual geological conditions of the shield tunnel, and thus leads to low identification accuracy of the stratum type.

[0061] Therefore, in the embodiments of the present application, a shield tunnel stratum type identification method, device and program product are provided to effectively improve the identification accuracy of the stratum type.

[0062] First, a shield tunnel stratum type identification method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0063] The shield tunnel stratum type identification method provided by the embodiments of the present application can be applied to a terminal, can be applied to a server, can also be software running in the terminal or the server, and the like. The terminal can be a tablet computer, a notebook computer, a desktop computer, and the like, but is not limited thereto. The server can be a standalone physical server, can also be a server cluster or a distributed system composed of multiple physical servers, can also be a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content delivery network (CDN), and big data and artificial intelligence platform. In addition, the server can also be a node server in a blockchain network, but is not limited thereto. The blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0064] With reference to Figure 1 The shield tunnel stratum type identification method can include the following steps S101-S104.

[0065] S101, obtain survey parameters and shield parameters of a target stratum slice; wherein the target stratum slice is obtained by slicing a target soil column located in a shield tunnel region.

[0066] It should be noted that the shield parameters of the target stratum slice refer to the tunneling parameters required for the shield machine to tunnel into the target stratum slice, which can directly indicate the dynamic construction condition of the target stratum slice, and the dynamic construction condition is indirectly related to the stratum type. In addition, the survey parameters of the target stratum slice indicate the static condition of the target stratum slice before construction, which is directly related to the stratum type of the target stratum slice. The types of the survey parameters and the types of the shield parameters are not specifically limited, for example, the survey parameters can include but are not limited to plane coordinate values and depth values, and the shield parameters can include but are not limited to shield thrust values, cutter head torque values, advancing speed values, and cutter head rotating speed values.

[0067] In this step, the shield tunnel region refers to the construction region of the shield tunnel, and the target soil column refers to a virtual and unknown survey hole soil column in the shield tunnel region. A plurality of target stratum slices can be obtained by slicing the target soil column, and the target stratum slice is a stratum slice whose stratum type is unknown. For any one target stratum slice, the survey parameters and the shield parameters of the target stratum slice are obtained, so as to identify the stratum type of the target stratum slice based on these data in the subsequent steps.

[0068] S102, perform feature extraction on the shield parameters to obtain shield parameter features of the target stratum slice; wherein the shield parameter features are used to indicate the stratum strength of the target stratum slice.

[0069] It should be noted that the shield parameter feature is positively correlated with the stratum strength, which means that the greater the specific value of the shield parameter feature, the higher the stratum strength and the greater the difficulty of excavation; the smaller the specific value of the shield parameter feature, the smaller the stratum strength and the smaller the difficulty of excavation.

[0070] In this step, the same shield parameter may correspond to different geological properties, which means that high thrust may be caused by hard rock layers, or may be caused by tool wear or shield machine posture correction. Affected by the polysemy of the shield parameter, if the shield parameter of the target stratum slice is directly used to identify the stratum type of the target stratum slice, it may appear that mechanical failure is misjudged as stratum hardening, etc., thereby causing low identification accuracy of the stratum type. To this end, the shield parameter of the target stratum slice is feature extracted in this step, aiming to non-dimensionalize the shield parameter of the target stratum slice to obtain the shield parameter feature of the target stratum slice, which can linearly express the stratum hardness of the target stratum slice, i.e., the stratum strength. In this way, not only can the geological body physical law of the target stratum slice be fully captured, which can indirectly indicate the stratum type of the target stratum slice, but also the key features representing the stratum type and the noise features irrelevant to the stratum type can be decoupled, so that the shield parameter feature can accurately indicate the geological properties of the target stratum slice, thereby reducing the negative impact of the polysemy of the shield parameter on identifying the stratum type.

[0071] S103, type feature extraction is performed according to the survey parameters of the survey hole soil column adjacent to the target stratum slice to obtain the stratum type feature of the target stratum slice; wherein the stratum type feature is used to indicate the distribution of the stratum type of the survey hole soil column adjacent to the target stratum slice, and the survey hole soil column is located within the shield tunnel area.

[0072] It should be noted that the stratum type feature is a feature value of the stratum type of the target stratum slice, and its essence is the distribution of the stratum type of the survey hole soil column adjacent to the target stratum slice. The closer the stratum type feature of a survey hole soil column to the stratum type value of the stratum slice of the survey hole soil column, the greater the probability that the stratum type of the target stratum slice is the stratum type of the stratum slice, and vice versa.

[0073] It can be understood that the survey hole soil column refers to a survey hole soil column that is pre-set in the shield tunnel area and is known.

[0074] In this step, the adjacent strata often have similar geological types, and accordingly, the soil column adjacent to the target stratum slice and its survey parameters are first determined, and then the type feature extraction is performed based on the survey parameters of the adjacent soil column, so as to obtain the stratum type feature of the target stratum slice. In this way, the spatial correlation between the stratum type of the target stratum slice and the stratum type of the soil column adjacent to the target stratum slice can be accurately positioned, so that the spatial law of the geological body of the target stratum slice can be fully captured, which can indirectly indicate the stratum type of the target stratum slice.

[0075] S104, inputting the shield parameter feature, the stratum type feature, the survey parameter and the shield parameter into a stratum type identification model to obtain the stratum type of the target stratum slice.

[0076] In this step, the shield parameter of the target stratum slice indicates the dynamic construction condition of the target stratum slice, the shield parameter feature of the target stratum slice indicates the physical law of the geological body of the target stratum slice, the stratum type feature of the target stratum slice indicates the spatial law of the geological body of the target stratum slice, and these parameter features all have indirect correlation with the stratum type of the target stratum slice, while the survey parameter of the target stratum slice indicates the static condition before construction, which has direct correlation with the stratum type of the target stratum slice. Accordingly, this step fully considers the original observation factors such as the dynamic construction condition and the static condition before construction, and the abstract representation factors such as the physical law of the geological body and the spatial law of the geological body, and identifies the stratum type of the target stratum slice based on these multi-dimensional factors and the stratum type identification model. In this way, the cross verification and complementarity between multi-source data are utilized to realize the identification of the stratum type, which can effectively make up for the information limitation when using data such as shield parameters alone to identify the stratum type, and further improve the identification accuracy of the stratum type.

[0077] The above steps will be further described below.

[0078] In some embodiments, the above slicing processing of the target soil column located in the shield tunnel area can include the following steps A01-A02:

[0079] A01, within the contour line of the shield tunnel area, a plurality of virtual soil columns perpendicular to the tunnel excavation direction are arranged along the tunnel excavation direction, and any one of the virtual soil columns is determined as a target soil column; wherein the diameter of the virtual soil column is the same as the diameter of the survey hole soil column, and the length of the virtual soil column is the excavation diameter of the shield tunnel area;

[0080] A02, the target soil column is divided into a plurality of target stratum slices along the direction perpendicular to the tunnel excavation direction.

[0081] It should be noted that the tunneling direction refers to the tunneling direction of the shield tunnel region.

[0082] In this embodiment, a plurality of known survey hole soil columns are provided in the shield tunnel region in advance. Accordingly, first, along the tunneling direction, a virtual survey hole soil column perpendicular to the tunneling direction is selected at a certain interval in the contour line of the shield tunnel region, so that a plurality of virtual survey hole soil columns, i.e., virtual soil columns, can be obtained. The diameter of the virtual soil column is the same as that of the known survey hole soil column, the length of the virtual soil column is the tunnel excavation diameter, and the interval of the adjacent two virtual soil columns can be the same or different. Then, any virtual soil column is determined as a target soil column, and the target soil column is divided into a plurality of target stratum slices at a certain interval along the direction perpendicular to the tunneling direction. The interval of the adjacent two target stratum slices can be the same or different. For example, as shown in FIG. 2, 0.1 meters is taken as the interval of the adjacent two target stratum slices, and the target soil column is sliced to obtain 10 target stratum slices, wherein the plane coordinate value of the first target stratum slice is (0, 0), the plane coordinate value of the second target stratum slice is (0, 0.1), the depth value of the first target stratum slice is 0, and the depth value of the second target stratum slice is 0.1. Figure 2

[0083] Optionally, the specific value of the interval of the adjacent two virtual soil columns can be set according to the actual situation, which is not limited in the present embodiment, for example, the value range of the interval of the adjacent two virtual soil columns can be 0.5 meters to 1 meter, but is not limited thereto. Similarly, the interval of the adjacent two target stratum slices can also be set according to the actual situation, which is not limited in the present embodiment, for example, the value range of the interval of the adjacent two target stratum slices can be 0.1 meters to 0.5 meters, but is not limited thereto. In addition, the tunnel excavation diameter and the diameter of the known survey hole soil column can also be set according to the actual situation, which is not limited in the present embodiment.

[0084] It should be understood that since the virtual soil column is set based on the known survey hole soil column, in the case that the interval of the adjacent two virtual soil columns and the interval of the adjacent two stratum slices in the virtual soil column are known, the survey parameters (such as the plane coordinate value and the depth value) of the virtual soil column can be inferred from the survey parameters of the known survey hole soil column, the interval of the adjacent two virtual soil columns, and the interval of the adjacent two stratum slices in the virtual soil column, and the shield parameters of the virtual soil column can be obtained by data measurement on the position of the virtual soil column.

[0085] ​​​​​​​In some embodiments, the shield parameters can include a shield thrust value, a cutterhead torque value, a propulsion speed value, and a cutterhead rotation speed value; and the feature extraction of the shield parameters in the step S102 to obtain the shield parameter features of the target stratum slice can include the following steps B01-B03:

[0086] B01, obtaining a product of the cutterhead torque value and the cutterhead rotation speed value as a cutterhead operation feature;

[0087] B02, obtaining a product of the propulsion speed value and the shield thrust value as a propulsion operation feature;

[0088] B03, obtaining a ratio of the cutterhead operation feature to the propulsion operation feature as the shield parameter feature.

[0089] In the embodiment, the shield thrust value, the cutterhead torque value, the propulsion speed value, and the cutterhead rotation speed value of the target stratum slice are dimensionless fused to obtain the shield parameter feature for indicating the stratum strength. In specific implementation, first, a product of the cutterhead torque value and the cutterhead rotation speed value is obtained as a cutterhead operation feature. The cutterhead operation feature is directly related to the cutting resistance of the stratum, and the cutting resistance is positively correlated with the stratum strength, i.e., the higher the stratum strength, the greater the cutting resistance, and the lower the stratum strength, the smaller the cutting resistance, and accordingly the cutterhead operation feature can be indirectly related to the stratum strength. Meanwhile, a product of the propulsion speed value and the shield thrust value is obtained as a propulsion operation feature. The propulsion operation feature is related to the propulsion resistance of the stratum, and the propulsion resistance is positively correlated with the stratum strength, i.e., the higher the stratum strength, the greater the propulsion resistance, and the lower the stratum strength, the smaller the propulsion resistance, and accordingly the propulsion operation feature can be indirectly related to the stratum strength. Then, a ratio of the cutterhead operation feature to the propulsion operation feature is obtained as the shield parameter feature. When the cutting resistance and the propulsion resistance increase synchronously, the shield parameter feature increases accordingly, which represents that the stratum strength becomes higher, and when the cutting resistance and the propulsion resistance decrease synchronously, the shield parameter feature decreases accordingly, which represents that the stratum strength becomes lower, thereby enabling the shield parameter feature to directly quantify the stratum strength. For ease of understanding, the shield parameter feature can be represented by the following formula (1):

[0090] (1);

[0091] In the formula (1), represents the shield parameter feature; represents the shield thrust value, and the unit is ; represents the cutterhead torque value, and the unit is ; represents the propulsion speed value, and the unit is ; represents the cutterhead rotation speed value, and the unit is .

[0092] Therefore, in the embodiment, the shield thrust value, the cutterhead torque value, the advancing speed value and the cutterhead rotating speed value of the target stratum slice are dimensionless fused to obtain the cutterhead operation characteristic and the advancing operation characteristic, and they are further converted into the shield parameter characteristic which can directly quantify the stratum strength. In this way, not only the geological body physical law of the target stratum slice can be fully captured, which can indirectly indicate the stratum type of the target stratum slice, but also the key characteristic representing the stratum type and the noise characteristic irrelevant to the stratum type can be decoupled, so that the shield parameter characteristic can accurately indicate the geological attribute of the target stratum slice, and then the negative influence of the polysemy of the shield parameter on the identification of the stratum type is reduced.

[0093] In some embodiments, the survey parameters can include plane coordinate values and depth values; and in the step S103, the type characteristic extraction is performed according to the survey parameters of the soil columns adjacent to the target stratum slice to obtain the stratum type characteristic of the target stratum slice, which can include the following steps C01-C03:

[0094] C01, selecting a stratum slice matching the depth value of the target stratum slice from each soil column as a candidate stratum slice;

[0095] C02, selecting multiple candidate stratum slices adjacent to the target stratum slice as adjacent stratum slices according to the plane coordinate values of the target stratum slice and the plane coordinate values of each candidate stratum slice;

[0096] C03, performing type characteristic extraction according to the stratum types of each adjacent stratum slice to obtain the stratum type characteristic of the target stratum slice.

[0097] It should be noted that each soil column is divided into multiple stratum slices. The division manner of the soil column is the same as the division manner of the target soil column in the foregoing embodiments, and will not be described again. For example, as shown in FIG. 2, the soil column is divided into 10 stratum slices with a spacing of 0.1 meters between adjacent two stratum slices, and the plane coordinate values of the first stratum slice are (0, 0), the depth value of the first stratum slice is 0.1 meters, and the stratum type value of the first stratum slice is clay. Figure 3

[0098] ​​​​​​​​​In this embodiment, the stratum type of the target stratum slice has a spatially continuous physical relationship with the adjacent soil columns of the survey hole due to the geological origin: the stratum often presents a layered distribution in the vertical direction, i.e., the stratum type at different depths can be significantly different; at the same depth, the closer the stratum slice is to the target stratum slice, the more similar the stratum type of the stratum slice is to the stratum type of the target stratum slice. Accordingly, first, for the depth value of the target stratum slice, the stratum slices in each soil column of the survey hole that match the depth value of the target stratum slice are preliminarily selected, and the selected stratum slices are determined as candidate stratum slices, which can effectively reduce the type mixed noise interference caused by the inhomogeneity of the geology in the vertical direction (i.e., the difference in the stratum type in the vertical direction). Then, taking the planar coordinate value of the target stratum slice and the planar coordinate value of each candidate stratum slice as a reference, the candidate stratum slices closer to the target stratum slice are further selected as adjacent stratum slices, and the stratum types of these adjacent stratum slices are highly related to the stratum type of the target stratum slice, which can effectively reduce the type mixed noise interference caused by the inhomogeneity of the geology in the horizontal direction (i.e., the difference in the stratum type in the horizontal direction). Finally, the stratum type of each adjacent stratum slice is taken as a reference to perform type feature extraction, thereby obtaining the stratum type feature of the target stratum slice, which can accurately locate the spatial correlation between the stratum type of the target stratum slice and the stratum type of the adjacent stratum slices, thereby fully capturing the spatial law of the geological body of the target stratum slice, which can indirectly indicate the stratum type of the target stratum slice.

[0099] In some embodiments, the step C01 above can include:

[0100] In some embodiments, the step C01 above can include:

[0101] In this embodiment, the soil column of the survey hole has a plurality of stratum slices, and each stratum slice has a corresponding depth value. Accordingly, from the stratum slices possessed by each soil column of the survey hole, the stratum slice with a depth value equal to the depth value of the target stratum slice is selected as a candidate stratum slice, which makes the stratigraphic position of the candidate stratum slice in the vertical direction strictly match the stratigraphic position of the target stratum slice in the vertical direction, thereby reducing the type mixed noise interference caused by the inhomogeneity of the geology in the vertical direction, and helping to improve the accuracy of subsequent type feature extraction.

[0102] In some embodiments, the step C02 above can include:

[0103] According to the planar coordinate value of the target stratum slice and the planar coordinate value of each candidate stratum slice, a distance value of each candidate stratum slice and the target stratum slice is obtained;

[0104] The candidate stratum slice with a distance value less than the distance threshold is determined as the adjacent stratum slice.

[0105] In the embodiment, the survey hole soil column has a plurality of stratum slices, and each stratum slice has a corresponding planar coordinate value. Accordingly, for each candidate stratum slice, the planar coordinate value of the target stratum slice and the planar coordinate value of the candidate stratum slice are processed based on a preset distance function to obtain a distance value of the target stratum slice and the candidate stratum slice. The distance values of the target stratum slice and each candidate stratum slice can be obtained by traversing the plurality of candidate stratum slices. Then, according to a pre-set distance threshold, a candidate stratum slice with a distance value less than the distance threshold is selected from the plurality of candidate stratum slices, and the selected candidate stratum slice is set as the adjacent stratum slice. For example, as shown in FIG. 5, five candidate stratum slices are selected as the adjacent stratum slices according to the distance threshold. Figure 4 As shown in FIG. 5, the distance values of the target stratum slice and each candidate stratum slice are calculated and the threshold is set, so that the candidate stratum slices adjacent to the target stratum slice in the physical position are further retained as the adjacent stratum slices. In this way, the type mixed noise interference caused by the lateral heterogeneity of the geology can be effectively reduced, and the spatial correlation between the stratum type of the target stratum slice and the stratum type of the adjacent stratum slice is strengthened, which helps to improve the accuracy of subsequent type feature extraction.

[0106] Optionally, the distance threshold can be set according to the actual situation, and the embodiment does not limit this. In addition, the distance function can also be set according to the actual situation, and the embodiment does not limit this. For example, the distance function can be the Euclidean distance, but is not limited thereto.

[0107] In some embodiments, in step C03, the type feature extraction is performed according to the stratum types of the adjacent stratum slices to obtain the stratum type features of the target stratum slice, which can include:

[0108] The reciprocal of the distance value of each adjacent stratum slice and the target stratum slice is obtained as the weight value of each adjacent stratum slice;

[0109] The stratum types of the adjacent stratum slices are processed by assignment to obtain the stratum type values of the adjacent stratum slices;

[0110] The product of the weight value and the stratum type value of each adjacent stratum slice is obtained as the stratum type weighted feature of each adjacent stratum slice;

[0111] The stratigraphic type feature is determined by the ratio of the sum of the stratigraphic type weighted features of each neighboring stratigraphic slice to the sum of the weight values ​​of each neighboring stratigraphic slice.

[0112] In this embodiment, during type feature extraction, firstly, the reciprocal of the distance between each neighboring stratigraphic slice and the target stratigraphic slice is calculated as the weight value of each neighboring stratigraphic slice. This results in a higher weight for neighboring stratigraphic slices closer to the target stratigraphic slice and a lower weight for neighboring stratigraphic slices farther away from the target stratigraphic slice. Then, the stratigraphic type of each neighboring stratigraphic slice is assigned a value to quantify the stratigraphic type into a specific numerical value, resulting in the stratigraphic type value for each neighboring stratigraphic slice. Next, the product of the weight value and the stratigraphic type value of each neighboring stratigraphic slice is obtained as the stratigraphic type weighting feature for each neighboring stratigraphic slice. This strengthens the influence of the stratigraphic type value of physically close neighboring stratigraphic slices on the stratigraphic type of the target stratigraphic slice, while mitigating the influence of the stratigraphic type value of physically distant neighboring stratigraphic slices on the stratigraphic type of the target stratigraphic slice. Finally, the ratio of the sum of the stratigraphic type weighted features of each adjacent stratigraphic slice to the sum of the weight values ​​of each adjacent stratigraphic slice is calculated as the stratigraphic type feature, thereby quantifying the weighted probability distribution of each adjacent stratigraphic slice. When the stratigraphic type feature is closer to the stratigraphic type value of a certain adjacent stratigraphic slice, it indicates that the stratigraphic type of the target stratigraphic slice is the same as that of the adjacent stratigraphic slice, and vice versa. In this way, the spatial correlation between the stratigraphic type of the target stratigraphic slice and the stratigraphic type of the adjacent stratigraphic slice can be effectively characterized, thereby fully capturing the spatial pattern of the geological body of the target stratigraphic slice. This spatial pattern can indirectly indicate the stratigraphic type of the target stratigraphic slice. For ease of understanding, the above stratigraphic type feature can be expressed as the following formula (2):

[0113] , , (2);

[0114] In equation (2), The plane coordinates are represented as The target stratigraphic slice at depth value Stratigraphic characteristics at the location; Indicates the first Stratigraphic type values ​​of adjacent stratigraphic slices; Indicates the first The weight values ​​of adjacent stratigraphic slices; Indicates the first Distance values ​​between neighboring stratigraphic slices and the target stratigraphic slice; This indicates the number of adjacent stratigraphic slices.

[0115] In some embodiments, the above method can further comprise the following steps D01-D05.

[0116] D01, obtaining investigation parameter samples, shield parameter samples and stratum types of a plurality of stratum slices of the plurality of investigation hole soil columns; wherein the stratum slices are obtained by slicing the investigation hole soil columns.

[0117] In this step, the stratum slices corresponding to the investigation hole soil columns can be obtained by slicing the investigation hole soil columns, and the slicing manner of the investigation hole soil columns is the same as that of the target soil column in the foregoing embodiments, which will not be described herein. Based on this, the planar coordinate values, depth values and corresponding stratum types of the stratum slices corresponding to the investigation holes in the shield tunnel region are obtained through the investigation report, wherein the planar coordinate values and the depth values jointly constitute the investigation parameter samples. At the same time, the shield parameter samples of the stratum slices corresponding to the investigation holes in the shield tunnel region are obtained through the sensors arranged on the shield machine.

[0118] It should be understood that the definition of the shield parameter samples herein is the same as that of the shield parameters in the foregoing embodiments, and the definition of the investigation parameter samples herein is the same as that of the investigation parameters in the foregoing embodiments, which will not be described herein.

[0119] D02, performing feature extraction on the shield parameter samples of each stratum slice to obtain shield parameter feature samples of each stratum slice; wherein the shield parameter feature samples are used to indicate the stratum strength of the stratum slice.

[0120] It should be understood that the description of the feature extraction on the shield parameter samples of the stratum slice herein can follow the description of the feature extraction on the shield parameters in the foregoing embodiments, and the only difference is that the data object herein is the stratum slice; in addition, the definition of the shield parameter feature samples herein is the same as that of the shield parameter features in the foregoing embodiments, which will not be described herein.

[0121] D03, performing type feature extraction on the investigation parameters of the investigation hole soil columns adjacent to each stratum slice to obtain stratum type feature samples of each stratum slice; wherein the stratum type feature samples are used to indicate the distribution of the stratum types of the investigation hole soil columns adjacent to the stratum slice.

[0122] It should be understood that the description of the type feature extraction on the investigation parameters of the investigation hole soil columns adjacent to each stratum slice herein can follow the description of the type feature extraction on the investigation parameters of the investigation hole soil columns adjacent to the target stratum slice in the foregoing embodiments, and the only difference is that the data object herein is the stratum slice; in addition, the definition of the stratum type feature samples herein is the same as that of the stratum type features in the foregoing embodiments, which will not be described herein.

[0123] D04, taking the survey parameter sample, the shield parameter sample, the shield parameter feature sample and the stratum type feature sample of each stratum slice as input data, and taking the stratum type of each stratum slice as a label, to construct a shield tunnel data set.

[0124] In this step, for each stratum slice, the survey parameter sample, the shield parameter sample, the shield parameter feature sample and the stratum type feature sample of the stratum slice are combined into input data of the stratum slice, and the corresponding stratum type is assigned to the input data as a label; by traversing each type of sample and stratum type of each stratum slice, the input data and its label of each stratum slice can be obtained, thereby constructing a shield tunnel data set. For ease of understanding, the shield tunnel data set can be represented as formula (3) as follows:

[0125] (3);

[0126] In formula (3), represents the shield tunnel data set; the first row of the shield tunnel data set represents the data index, and the other rows represent the specific data; is a data serial number, is a planar coordinate value in the survey parameter sample, is a depth value in the survey parameter sample, is a stratum type feature sample, is a shield thrust value in the shield parameter sample, is a cutterhead torque value in the shield parameter sample, is a cutterhead rotation speed value in the shield parameter sample, is a propulsion speed value in the shield parameter sample, is a shield parameter feature sample, is a stratum type; is the number of input data in the shield tunnel data set, i.e. the sum of the number of stratum slices of all soil columns of the survey hole.

[0127] D05, using a machine learning method to train the shield tunnel data set to obtain a stratum type recognition model.

[0128] In this step, the shield tunnel data set is input into a plurality of pre-constructed machine learning models, and each machine learning model is trained and tested. Finally, the machine learning model with the best performance is selected as the stratum type recognition model, so that the stratum type recognition model can learn the correlation between the survey parameter sample, the shield parameter sample, the shield parameter feature sample and the stratum type feature sample and the stratum type, and identify the stratum type of the target stratum slice according to the correlation.

[0129] Optionally, the machine learning method can be set according to actual conditions, and the embodiment does not limit this. For example, the machine learning method can be a support vector machine, logistic regression, random forest, K-nearest neighbor algorithm, gradient boosting decision tree, etc., but is not limited thereto. In addition, the number of machine learning methods is not specifically limited.

[0130] Illustratively, each machine learning model is trained using a rotating cross-validation method. In a specific implementation, starting from the excavation starting point of the shield tunnel, the input data of the stratum slices from the first survey hole soil column to the last survey hole soil column are selected as the prediction set, and the input data of the stratum slices of other survey hole soil columns adjacent to each survey hole soil column are selected as the training set according to a distance function such as the Euclidean distance, and the machine learning model is trained and tested. During model testing, performance indicators such as average accuracy can be calculated. By traversing multiple machine learning models, the performance indicators of multiple machine learning models can be obtained, and finally the machine learning model with the optimal performance indicator (e.g., the highest average accuracy) is selected as the stratum type identification model. Here, the rotating cross-validation method is introduced to perform model training and testing, which uses the data of multiple survey hole soil columns as test input and selects the data of other survey hole soil columns adjacent to each survey hole soil column as training input. This makes each survey hole soil column and its adjacent other survey hole soil columns have a strong geological origin physical connection, strengthens the correlation between the training set and the test set, and thus promotes the machine learning model to better learn the correlation between the four of the survey parameter sample, the shield parameter sample, the shield parameter feature sample, and the stratum type feature sample and the stratum type, effectively improving the training effect of the machine learning model.

[0131] To facilitate understanding of the above-mentioned shield tunnel stratum type identification method of the present application, the actual application scenario of the above-mentioned shield tunnel stratum type identification method of the present application is exemplified.

[0132] The shield tunnel project of the present example is located in a southern region, and before construction, drilling sampling is performed on the area through which the shield tunnel passes, i.e., multiple survey hole soil columns are constructed, and the depth of each survey hole soil column exceeds the burial depth of the shield tunnel, thereby covering the entire depth of the shield tunnel, so that discontinuous stratum information along the shield tunnel can be obtained. The survey report shows that the construction area of the shield tunnel contains four stratum types: miscellaneous fill, fully weathered, strongly weathered, and moderately weathered granite. Since the stratum strength of the moderately weathered granite type is relatively high, it is easy to cause problems such as damage to the cutter of the shield machine, thereby causing a delay in the construction period. Therefore, the above-mentioned shield tunnel stratum type identification method is used to predict the stratum type of the unknown tunneling area within the shield tunnel, thereby providing a basis for the construction decision of the shield tunnel.

[0133] According to the excavation starting point coordinates of the shield tunnel, a virtual survey hole soil column perpendicular to the tunnel excavation direction is selected every 1 meter along the tunnel excavation direction within the contour line of the shield tunnel area, so that a plurality of virtual survey hole soil columns, i.e. virtual soil columns, can be obtained. The planar coordinate values of each virtual soil column are known, the diameter of each virtual soil column is the same as that of the survey hole soil column, and the length of each virtual soil column is the excavation diameter of the shield tunnel area, which is 9.1 meters. Then, an arbitrary virtual soil column is selected as a target soil column, and the target soil column is sliced along a direction perpendicular to the tunnel excavation direction at an interval of 0.1 meters to obtain 91 target stratum slices.

[0134] Referring to Figure 5 For each target stratum slice, the following stratum type identification operation is performed:

[0135] S201, shield parameters and survey parameters of the target stratum slice are obtained. The shield parameters include shield thrust value, cutterhead torque value, advancing speed value and cutterhead rotating speed value, which can be obtained by sensors of the shield machine; the survey parameters include planar coordinate value and depth value, which can be inferred from the survey parameters of the known survey hole soil column, the interval between two adjacent virtual soil columns, and the interval between two adjacent stratum slices in the virtual soil column.

[0136] S202, shield parameter features of the target stratum slice are calculated according to the shield thrust value, cutterhead torque value, advancing speed value and cutterhead rotating speed value, combined with the above formula (1).

[0137] S203, first, from the stratum slices of each survey hole soil column, a stratum slice with a depth value equal to that of the target stratum slice is selected as a candidate stratum slice. Then, for each candidate stratum slice, the Euclidean distance value between the target stratum slice and the candidate stratum slice is calculated according to the planar coordinate value of the target stratum slice and the planar coordinate value of the candidate stratum slice, and four candidate stratum slices with a distance value less than a distance threshold value are selected as adjacent stratum slices. Then, each stratum type is assigned a value. In this example, the value of the miscellaneous fill type is 1, the value of the fully weathered granite type is 2, the value of the strongly weathered granite type is 3, and the value of the moderately weathered granite type is 4. Finally, the stratum type features of the target stratum slice are calculated using the above formula (2).

[0138] S204, the shield parameter features, the stratum type features, the survey parameters and the shield parameters are input into the stratum type identification model to obtain the stratum type of the target stratum slice. In this example, the model identification can determine that the target stratum slice is of the strongly weathered granite type.

[0139] The construction process of the stratum type identification model is specifically as follows: first, a plurality of survey parameter samples, shield parameter samples and stratum types of a plurality of stratum slices of the soil column of the survey hole are obtained, and the stratum slices are obtained by slicing the soil column of the survey hole. Then, the shield parameter samples of each stratum slice are subjected to feature extraction to obtain shield parameter feature samples of each stratum slice, the shield parameter feature samples being used to indicate the stratum strength of the stratum slice, and type feature extraction is performed according to the survey parameters of the soil column of the survey hole adjacent to each stratum slice to obtain stratum type feature samples of each stratum slice, the stratum type feature samples being used to indicate the distribution of the stratum type of the soil column of the survey hole adjacent to the stratum slice. Subsequently, the survey parameter samples, the shield parameter samples, the shield parameter feature samples and the stratum type feature samples of each stratum slice are taken as input data, and the stratum type of each stratum slice is taken as a label to construct a shield tunnel data set. Finally, a plurality of machine learning models are constructed, for each machine learning model, the input data of the stratum slices of the first soil column to the last soil column of the survey hole from the excavation starting point of the shield tunnel are selected as a prediction set, and other input data of the stratum slices of the soil columns of the survey holes adjacent to each survey hole are selected as a training set according to a distance function such as the Euclidean distance, the machine learning model is trained and tested, and performance indicators such as average accuracy can be calculated during the model testing. The performance indicators of the plurality of machine learning models can be obtained by traversing the plurality of machine learning models, and finally the machine learning model with the optimal performance indicator (for example, the highest average accuracy) is selected as the stratum type identification model. For example, Figure 6 as shown in the figure, Figure 6 the abscissa represents the number of adjacent survey hole soil columns (i.e. adjacent stratum slices), and the ordinate represents the average accuracy, the random forest, support vector machine, XGBoost and K nearest neighbor algorithm are selected as the machine learning model, the support vector machine model with the highest average accuracy is determined as the final stratum type identification model in this example, and it is verified that the number of adjacent stratum slices is 4, which is the optimal effect.

[0140] Through the above process, the stratum types of each target stratum slice in the target soil column can be obtained; and by traversing a plurality of virtual soil columns, the stratum types of the stratum slices corresponding to the plurality of virtual soil columns can be obtained, and accordingly a geological profile of the soil layer class in the tunnel construction area can be drawn, as shown in Figure 7 , which further supports the shield construction decision.

[0141] Please refer to Figure 8 , the present application embodiment also provides a shield tunnel stratum type identification device, which comprises:

[0142] The acquisition module 301 is configured to acquire survey parameters and shield parameters of a target stratum slice; wherein the target stratum slice is obtained by slicing a target soil column located in a shield tunnel region.

[0143] The first processing module 302 is configured to perform feature extraction on the shield parameters to obtain shield parameter features of the target stratum slice; the shield parameter features are used to indicate the stratum strength of the target stratum slice;

[0144] The second processing module 303 is configured to perform type feature extraction on the survey parameters of the survey hole soil column adjacent to the target stratum slice to obtain stratum type features of the target stratum slice; the stratum type features are used to indicate the distribution of the stratum type of the survey hole soil column adjacent to the target stratum slice, and the survey hole soil column is located in the shield tunnel area;

[0145] The third processing module 304 is configured to input the shield parameter features, the stratum type features, the survey parameters, and the shield parameters into a stratum type identification model to obtain the stratum type of the target stratum slice.

[0146] The content in the above method embodiments is applicable to the device embodiments, the device embodiments specifically implement the same functions as the above method embodiments, and achieve the same beneficial effects as the above method embodiments.

[0147] Finally, the embodiment of the present application further provides a computer program product, including a computer program, which is executed by a processor to implement the above shield tunnel stratum type identification method.

[0148] The content in the above method embodiments is applicable to the program product embodiments, the program product embodiments specifically implement the same functions as the above method embodiments, and achieve the same beneficial effects as the above method embodiments.

[0149] The shield tunnel stratum type identification method, device, and program product provided by the embodiment of the present application fully consider original observation factors such as dynamic construction conditions and static conditions before construction and abstract representation factors such as physical laws of geologic bodies and spatial laws of geologic bodies, and identify the stratum type of the target stratum slice based on these multi-dimensional factors in combination with a stratum type identification model. In this way, the cross verification and complementarity between multi-source data are used to implement the identification processing of the stratum type, which can effectively make up for the information limitation when the stratum type is identified by using data such as shield parameters alone, and further effectively improve the identification accuracy of the stratum type, thereby providing effective data support for the construction decision of the shield tunnel.

[0150] The embodiments described in the specification are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0151] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than shown in the figures, or combine certain steps, or different steps.

[0152] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0153] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the functional modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0154] The terms "first", "second", "third", "fourth" and the like (if any) in the specification of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0155] It should be understood that, in the application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases of only A, only B, and A and B existing at the same time, wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, and c can be single or multiple.

[0156] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed mutual ones can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0157] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0158] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0159] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0160] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method for identifying a ground type in a shield tunneling, characterized by, The method comprises: obtaining survey parameters and shield parameters of a target stratum slice; wherein the target stratum slice is obtained by slicing a target soil column located in a shield tunnel region; performing feature extraction on the shield parameters to obtain shield parameter features of the target stratum slice; wherein the shield parameter features are used to indicate the stratum strength of the target stratum slice; performing type feature extraction on survey parameters of a survey hole soil column adjacent to the target stratum slice to obtain stratum type features of the target stratum slice; wherein the stratum type features are used to indicate the distribution of the stratum type of the survey hole soil column adjacent to the target stratum slice, and the survey hole soil column is located in the shield tunnel region; inputting the shield parameter features, the stratum type features, the survey parameters and the shield parameters into a stratum type identification model to obtain the stratum type of the target stratum slice; wherein the survey parameters comprise planar coordinate values and depth values; the stratum type features of the target stratum slice are obtained by performing type feature extraction on the survey parameters of the survey hole soil column adjacent to the target stratum slice, comprising: selecting, from each of the survey hole soil columns, a stratum slice matching the depth value of the target stratum slice as a candidate stratum slice; selecting, according to the planar coordinate values of the target stratum slice and the planar coordinate values of each of the candidate stratum slices, a plurality of the candidate stratum slices adjacent to the target stratum slice as adjacent stratum slices; performing type feature extraction on the stratum types of each of the adjacent stratum slices to obtain the stratum type features of the target stratum slice; wherein the stratum type features of the target stratum slice are obtained by performing type feature extraction on the stratum types of each of the adjacent stratum slices, comprising: obtaining the reciprocal of the distance value of each of the adjacent stratum slices from the target stratum slice as the weight value of each of the adjacent stratum slices; performing assignment processing on the stratum types of each of the adjacent stratum slices to obtain the stratum type value of each of the adjacent stratum slices; obtaining the product of the weight value and the stratum type value of each of the adjacent stratum slices as the stratum type weighting feature of each of the adjacent stratum slices; determining the ratio of the sum of the stratum type weighting features of each of the adjacent stratum slices to the sum of the weight values of each of the adjacent stratum slices as the stratum type features.

2. The method of claim 1, wherein, The slicing processing of the target soil column located in the shield tunnel region comprises: within the contour line of the shield tunnel region, a plurality of virtual soil columns perpendicular to the tunnel excavation direction are arranged along the tunnel excavation direction, and any one of the virtual soil columns is determined as the target soil column; wherein the diameter of the virtual soil column is the same as the diameter of the survey hole soil column, and the length of the virtual soil column is the excavation diameter of the shield tunnel region; the target soil column is divided into a plurality of target stratum slices along a direction perpendicular to the tunnel excavation direction.

3. The method of claim 1, wherein, The shield parameters include a shield thrust value, a cutterhead torque value, a propulsion speed value, and a cutterhead rotation speed value; the feature extraction on the shield parameters obtains shield parameter features of the target stratum slice, and the feature extraction includes: obtaining a product of the cutterhead torque value and the cutterhead rotation speed value as a cutterhead operation feature; obtaining a product of the propulsion speed value and the shield thrust value as a propulsion operation feature; obtaining a ratio of the cutterhead operation feature to the propulsion operation feature as the shield parameter feature.

4. The method of claim 1, wherein, The selection of the stratum slices from the survey hole soil columns and matching the depth value of the target stratum slice as the candidate stratum slices includes: from each of the survey hole soil columns, selecting a stratum slice at the same depth value as the target stratum slice as the candidate stratum slice.

5. The method of claim 1, wherein, The selection of the multiple candidate stratum slices adjacent to the target stratum slice according to the planar coordinate value of the target stratum slice and the planar coordinate value of each of the candidate stratum slices as the adjacent stratum slices includes: obtaining a distance value of each of the candidate stratum slices from the target stratum slice according to the planar coordinate value of the target stratum slice and the planar coordinate value of each of the candidate stratum slices; determining the candidate stratum slice with the distance value less than a distance threshold as the adjacent stratum slice.

6. The method of claim 1, wherein, The method further includes: obtaining survey parameter samples, shield parameter samples, and stratum types of a plurality of stratum slices of the survey hole soil columns; wherein the stratum slices are obtained by slicing processing on the survey hole soil columns; performing feature extraction on the shield parameter samples of each of the stratum slices to obtain shield parameter feature samples of each of the stratum slices; wherein the shield parameter feature samples are used to indicate stratum strength of the stratum slices; performing type feature extraction on survey parameters of the survey hole soil columns adjacent to each of the stratum slices to obtain stratum type feature samples of each of the stratum slices; wherein the stratum type feature samples are used to indicate distribution of stratum types of the survey hole soil columns adjacent to the stratum slices; constructing a shield tunnel data set by taking the survey parameter samples, the shield parameter samples, the shield parameter feature samples, and the stratum type feature samples of each of the stratum slices as input data and taking stratum types of each of the stratum slices as labels; performing model training on the shield tunnel data set by using a machine learning method to obtain the stratum type recognition model.

7. A shield tunnel ground type recognition apparatus, characterized by, The device includes: an obtaining module configured to obtain survey parameters and shield parameters of a target stratum slice; wherein the target stratum slice is obtained by slicing processing on a target soil column located in a shield tunnel region; a first processing module configured to perform feature extraction on the shield parameters to obtain shield parameter features of the target stratum slice; wherein the shield parameter features are used to indicate stratum strength of the target stratum slice; The second processing module is configured to perform type feature extraction according to the survey parameters of the borehole soil columns adjacent to the target formation slice to obtain a formation type feature of the target formation slice; wherein the formation type feature is used to indicate a distribution of formation types of the borehole soil columns adjacent to the target formation slice, and the borehole soil columns are located within the shield tunnel region; The third processing module is configured to input the shield parameter feature, the formation type feature, the survey parameters, and the shield parameters into a formation type identification model to obtain a formation type of the target formation slice. The survey parameters include plane coordinate values and depth values; the type feature extraction according to the survey parameters of the borehole soil columns adjacent to the target formation slice to obtain the formation type feature of the target formation slice includes: selecting formation slices matching the depth value of the target formation slice from the borehole soil columns as candidate formation slices; selecting multiple candidate formation slices adjacent to the target formation slice as adjacent formation slices according to the plane coordinate values of the target formation slice and the plane coordinate values of the candidate formation slices; performing type feature extraction according to the formation types of the adjacent formation slices to obtain the formation type feature of the target formation slice; The type feature extraction according to the formation types of the adjacent formation slices to obtain the formation type feature of the target formation slice includes: obtaining the reciprocal of the distance value of each adjacent formation slice and the target formation slice as a weight value of each adjacent formation slice; performing value assignment processing on the formation types of the adjacent formation slices to obtain a formation type value of each adjacent formation slice; obtaining the product of the weight value and the formation type value of each adjacent formation slice as a formation type weighted feature of each adjacent formation slice; determining the ratio of the sum of the formation type weighted features of each adjacent formation slice to the sum of the weight values of each adjacent formation slice as the formation type feature.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement a shield tunnel formation type identification method according to any one of claims 1 to 6.

Images