Decision tree determination method, subsea tunnel surrounding rock impermeability grading method and product

Abstract

The invention discloses a decision tree determination method, a subsea tunnel surrounding rock impermeability grading method and a product, and relates to the technical field of subsea tunnel surrounding rock impermeability grading, the determination method comprises the following steps: obtaining training data of a tunnel section; the training data comprises surrounding rock parameter data and corresponding impermeability level data; the surrounding rock parameters comprise the rock covering layer thickness, the water head height, the rock uniaxial saturated compressive strength and the surrounding rock volume joint number; classifying the training data by adopting a dichotomy to obtain a plurality of division points and corresponding division results; calculating the information gain of each division point in combination with an information gain criterion; and selecting the division point with the maximum information gain and the corresponding division result, respectively taking two data sets in the division result as training data, and repeatedly executing the steps to obtain the decision tree for impermeability grading. According to the method, surrounding rock impermeability grading can be accurately carried out, surrounding rock impermeability grading is simple and visual, and rock mass impermeability can be objectively reflected.

Description

Technical Field

[0001] The present application relates to the technical field of classification of the impermeability of surrounding rocks of submarine tunnels, and in particular to a decision tree determination method, a method for classifying the impermeability of surrounding rocks of submarine tunnels, and a product thereof. Background Art

[0002] The V-shaped longitudinal slope of the submarine tunnel makes it impossible for the seepage water to be discharged naturally, so the drainage problem is the key difficulty in its construction and operation safety. Looking at the underwater tunnels at home and abroad, the drainage methods used can be divided into two types: full blocking and drainage, and both use the secondary lining as the main bearing structure. The water pressure borne by the full blocking tunnel lining is equivalent to the groundwater head, so it is not suitable for tunnel projects with high overlying water layers and deep burial depths. The drainage system can reduce the external water pressure acting on the lining structure to a certain extent, and greatly reduce the probability of its deterioration and leakage, making the lining structure economical and reasonable. At present, the "water blocking and drainage limiting" waterproofing system is mostly used for submarine tunnels, which controls the drainage volume while considering the stability of the surrounding rock reinforcement ring. However, the surrounding rock reinforcement ring and the primary support structure also bear the corresponding water load while blocking water, so it is necessary to comprehensively consider the safety and economy of the drainage system. In order to achieve the overall safety of the "water blocking and drainage limiting" drainage system of the submarine tunnel, it is necessary to construct an active control drainage system, the core feature of which is to allow the active determination of the drainage volume and the coordinated design of the water blocking system.

[0003] The drainage system is affected by factors such as surrounding rock conditions and hydrogeological conditions, and the main difference in its design scheme lies in the understanding of the surrounding rock's water blocking capacity and the determination of the allowable drainage volume. Although domestic and foreign scholars have conducted a lot of research on the theory and technology of submarine tunnel drainage design, the allowable drainage volume of submarine tunnels mainly relies on engineering experience analogy, and no unified standard for reference has been formed. The fundamental reason is that the understanding of the surrounding rock's water blocking capacity is insufficient, which makes the drainage design lack of theoretical basis. For submarine tunnels, zoning waterproofing design is often required, and this design in current projects often depends on the results of surrounding rock classification. The existing surrounding rock classification is an evaluation of the surrounding rock strength, which is mainly determined by the hardness of the rock and the integrity of the rock mass. The surrounding rock permeability classification is an evaluation of the water seepage of the surrounding rock, which needs to be determined by the hydrogeological conditions and the permeability of the rock mass where the tunnel is located. If the surrounding rock level is low, but the tunnel is located in a high head, its permeability level may be high; if the surrounding rock level is low and the integrity is good, but the water passage conditions formed by its joints are good and the permeability is strong, its permeability level is high. Existing research has not yet provided a reliable classification method to directly and objectively evaluate the impermeability of surrounding rocks. Summary of the invention

[0004] The purpose of this application is to provide a decision tree determination method, a method and product for grading the permeability of the surrounding rock of an undersea tunnel, which can accurately grade the permeability of the surrounding rock of an undersea tunnel, make the grading of the permeability of the surrounding rock simple and intuitive, and objectively reflect the permeability of the rock mass.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a decision tree determination method, the decision tree determination method comprising:

[0007] Acquire training data of the tunnel section; the training data includes: surrounding rock parameter data and corresponding impermeability grade data; the surrounding rock parameter data includes: surrounding rock parameters and corresponding engineering data; the surrounding rock parameters include: rock cover thickness, water head height, rock uniaxial saturated compressive strength and number of surrounding rock volume joints;

[0008] The training data is classified by using a binary method to obtain a plurality of division points and corresponding division results; the division results include: a large training data set and a small training data set; the large training data set is a set of training data in the training data that is larger than the division point; the small training data set is a set of training data in the training data that is smaller than the division point;

[0009] Calculate the information gain of each of the division points in combination with the information gain criterion;

[0010] Selecting a partition point with the largest information gain and a corresponding partition result to obtain a first partition point and a corresponding first partition result; the first partition result includes: a first large training data set and a first small training data set; the first large training data set is a set of training data greater than the first partition point; the first small training data set is a set of training data less than the first partition point;

[0011] The first large training data set and the first small training data set are respectively combined as "training data", and the step of "using binary search to classify the training data to obtain a plurality of division points and corresponding division results" is returned until the step of "selecting the division point with the largest information gain and the corresponding division result to obtain the first division point and the corresponding first division result" is completed. There is only one data in the first large training data set and the first small training data set, and a decision tree for grading the permeability resistance of surrounding rock of submarine tunnels is obtained.

[0012] Optionally, the information gain criterion is used to calculate the information gain of each of the partition points as follows:

[0013]

[0014] Among them, Gain(D,a) represents the information gain of the partition point t, Ent(D) represents the information entropy of the entire training data set D, Represents the set of partition results corresponding to the partition point t The information entropy of represents the large training data set corresponding to the partition point t, Represents the small training data set corresponding to the partition point t.

[0015] Optionally, the information entropy is calculated as:

[0016]

[0017] Among them, p k is the proportion of samples of the kth category in set D, k = 1, 2, ..., n.

[0018] Optionally, the adopting of a binary method to classify the training data to obtain a number of division points and corresponding division results specifically includes:

[0019] Inputting the training data into a decision tree model;

[0020] The training data is classified by using a decision tree model and a binary method to obtain a number of division points and corresponding division results.

[0021] Optionally, inputting the training data into a decision tree model specifically includes:

[0022] The training data is organized into a decision tree model matrix; the decision tree model matrix includes: a training data set and an attribute set; the training data set D = {(x1, y1), (x2, y2), ..., (x 42 ,y 42 )}, where x i (i=1,2,…,42) is a 4-dimensional vector, which is the engineering data of the four evaluation indicators: rock cover thickness, water head height, volume joint number and rock uniaxial saturated compressive strength. i (i=1,2,…,42) is the corresponding level of impermeability; the attribute set A={a1,a2,a3,a4}, where a1,a2,a3,a4 are the thickness of rock cover, water head height, number of volume joints and uniaxial saturated compressive strength of rock respectively.

[0023] The decision tree model matrix is ​​input into the decision tree model.

[0024] Optionally, the training data of the tunnel section is training data of 52 typical tunnel sections.

[0025] In a second aspect, the present application provides a method for grading the impermeability of surrounding rocks of a submarine tunnel, characterized in that the method for grading the impermeability of surrounding rocks of a submarine tunnel comprises:

[0026] Obtain surrounding rock parameters and corresponding engineering data of surrounding rock to be classified;

[0027] The surrounding rock parameters and corresponding engineering data are input into a decision tree to obtain the classification of the surrounding rock to be classified; the decision tree is determined by any of the decision tree determination methods described above.

[0028] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described decision tree determination methods or subsea tunnel surrounding rock impermeability grading methods.

[0029] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described decision tree determination methods or subsea tunnel surrounding rock impermeability grading methods.

[0030] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned decision tree determination methods or subsea tunnel surrounding rock impermeability grading methods.

[0031] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0032] The present application provides a decision tree determination method, a method for grading the permeability of surrounding rocks of submarine tunnels and a product. The decision tree determination method comprises: obtaining training data of a tunnel section; the training data comprises: surrounding rock parameter data and corresponding permeability grade data; the surrounding rock parameters comprise: rock cover thickness, water head height, rock uniaxial saturated compressive strength and number of surrounding rock volume joints; classifying the training data using a binary method to obtain a number of division points and corresponding division results; the division results comprise: a large training data set and a small training data set; the large training data set is a set of training data in the training data that is greater than the division point; the small training data set is a set of training data in the training data that is less than the division point; calculating the information gain of each of the division points in combination with the information gain criterion; selecting the division point with the largest information gain and the corresponding division result. The first partition result is obtained by dividing the first partition point and the corresponding first partition result; the first partition result includes: a first large training data set and a first small training data set; the first large training data set is a set of training data larger than the first partition point; the first small training data set is a set of training data smaller than the first partition point; the first large training data set and the first small training data set are respectively combined as "training data", and the step of "using binary search to classify the training data to obtain several partition points and corresponding partition results" is returned until the step of "selecting the partition point with the largest information gain and the corresponding partition result to obtain the first partition point and the corresponding first partition result" is completed, there is only one data in the first large training data set and the first small training data set, and a decision tree for impermeability classification is obtained. The purpose of this application is to provide a decision tree determination method, a method and product for grading the permeability of surrounding rocks of submarine tunnels, and proposes that the permeability grading indicators are the thickness of the rock cover, the head height, the uniaxial saturated compressive strength of the rock, and the number of volume joints, thereby ensuring the accuracy of the grading of the permeability of the surrounding rocks. At the same time, through machine learning of a large amount of data, a decision tree prediction model is established in combination with the dichotomy, information gain criterion and information gain rate criterion, and the hierarchical prediction of continuous attribute data is realized, and finally a surrounding rock decision tree is formed, which makes the grading of the permeability of the surrounding rocks simple and intuitive, and can objectively reflect the permeability of the rock mass. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1An application environment diagram of a decision tree determination method or a method for grading the impermeability of surrounding rock of a submarine tunnel in an embodiment of the present application;

[0035] Figure 2 A flowchart of a decision tree determination method provided in one embodiment of the present application;

[0036] Figure 3 A schematic diagram of a decision tree for grading the impermeability of surrounding rocks of a submarine tunnel provided in one embodiment of the present application;

[0037] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] In fact, due to the complex hydrogeological conditions of the submarine tunnel and the differences in connectivity with water, in order to actively determine the allowable drainage volume of the tunnel and provide a design method for the drainage system, it is necessary to objectively evaluate the water blocking capacity of the submarine tunnel surrounding rock, that is, the impermeability of the surrounding rock, and formulate different drainage control standards accordingly. This provides a theoretical basis for the coordinated design of the submarine tunnel drainage system, and also has certain reference significance for the drainage design of water-rich tunnels.

[0040] This application uses rock cover thickness, water head height, rock uniaxial saturated compressive strength and volume joint number as impermeability classification evaluation indicators, and establishes a decision tree model that can analyze continuous value attributes through machine learning of a large number of tunnel seepage case data, which can realize the impermeability classification of tunnel surrounding rock. It mainly includes the following steps:

[0041] (1) Based on the prediction formula for the original water seepage of a fractured rock submarine tunnel under high-speed flow conditions during the construction period, a statistical analysis was conducted on the water seepage case data of a large number of typical underwater tunnels and water-rich tunnel sections. The thickness of the rock cover, the water head height, the uniaxial saturated compressive strength of the rock, and the number of volume joints were determined as the impermeability classification indicators. The tunnel water inflow was classified using the four-point method as a reference for the surrounding rock impermeability classification.

[0042] (2) The tunnel surrounding rock sample data is divided using the dichotomy method, information gain and information gain rate criteria, the sample data division points are determined, and a decision tree prediction model is established based on the sample data division points to achieve hierarchical prediction of continuous attribute data. Using this decision tree model, the tunnel surrounding rock parameters can be searched and classified to obtain the surrounding rock impermeability classification.

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0044] The decision tree determination method or the subsea tunnel surrounding rock impermeability classification method provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers.

[0045] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0046] In an exemplary embodiment, Figure 2 As shown, a decision tree determination method is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S1 to S5. Among them:

[0047] S1. Obtain training data of a tunnel section; the training data includes: surrounding rock parameter data and corresponding impermeability grade data; the surrounding rock parameter data includes: surrounding rock parameters and corresponding engineering data; the surrounding rock parameters include: rock cover thickness, water head height, rock uniaxial saturated compressive strength and number of surrounding rock volume joints.

[0048] In this embodiment, the evaluation indexes of tunnel surrounding rock impermeability are selected as follows: rock cover thickness, water head height, rock uniaxial saturated compressive strength, and surrounding rock volume joint number. The classification standards for surrounding rock impermeability are shown in Table 1:

[0049] Table 1 Standard table for classification of impermeability grades

[0050] <![CDATA[Seepage volume (m 3 ·d -1 ·m -1 )]]> grade 0～3.32 Ⅰ(Wet) 3.32～8.47 Ⅱ(Dripping water) 8.47～22.28 Ⅲ(Linear flow) >22.28 IV (Water)

[0051] This example collects surrounding rock parameter data and corresponding impermeability grade data of 52 typical tunnel sections, and some statistical data are shown in Table 2 below:

[0052] Table 2 Statistical data of some typical tunnel sections

[0053]

[0054]

[0055] The four evaluation index attributes of rock cover thickness, head height, volume joint number and rock uniaxial saturated compressive strength are expressed as A = {a1, a2, a3, a4}, and they are all continuous attributes. At the same time, the surrounding rock impermeability level is divided into four levels according to the seepage amount, namely y i ∈{Ⅰ,Ⅱ,Ⅲ,Ⅳ},(i=1,2,...,n). The statistical data of some typical tunnel sections above are split into training set and test set in a ratio of 4:1, that is, the first 42 groups of data are training sets, and the last 10 groups of data are test sets.

[0056] S2. Classify the training data using a binary search method to obtain a number of partition points and corresponding partition results; the partition results include: a large training data set and a small training data set; the large training data set is a set of training data in the training data that is larger than the partition point; the small training data set is a set of training data in the training data that is smaller than the partition point.

[0057] Specifically:

[0058] S21, inputting the training data into a decision tree model.

[0059] The training data is organized into a decision tree model matrix; the decision tree model matrix includes: a training data set and an attribute set; the training data set D = {(x1, y1), (x2, y2), ..., (x 42 ,y 42 )}, where x i (i=1,2,…,42) is a 4-dimensional vector, which is the engineering data of the four evaluation indicators: rock cover thickness, water head height, volume joint number and rock uniaxial saturated compressive strength. i (i=1,2,…,42) is the corresponding impermeability level; attribute set A={a1,a2,a3,a4}, a1,a2,a3,a4 are respectively the thickness of rock cover layer, water head height, volume joint number and uniaxial saturated compressive strength of rock. The decision tree model matrix is ​​input into the decision tree model.

[0060] Next, feature selection is performed on each evaluation index to generate the root node of the decision tree.

[0061] S22. Using a decision tree model, the training data is classified by using a binary method to obtain a plurality of division points and corresponding division results.

[0062] S3. Calculate the information gain of each of the division points in combination with the information gain criterion. The calculation formula is:

[0063]

[0064] Among them, Gain(D,a) represents the information gain of the partition point t, and Ent(D) represents the information entropy of the entire training data set D. Represents the set of partition results corresponding to the partition point t The information entropy of represents the large training data set corresponding to the partition point t, Represents the small training data set corresponding to the partition point t.

[0065] The key point of feature selection is to select the best features that have the ability to classify the training data, so as to improve the classification efficiency of the decision tree. For each data classification within an internal node, it is hoped that the data contained in the next node belongs to the same category as much as possible, that is, the "purity" is higher. Information entropy can measure the uncertainty of random variables and is one of the most commonly used indicators for measuring the purity of a sample set. The smaller its value, the higher the purity of the sample set. Let the proportion of the kth class of samples in the sample set D be p k (k=1,2,...,n), then the information entropy Ent(D) of set D is defined as:

[0066]

[0067] For continuous attributes, the number of possible values ​​is infinite, and the sample data in the node cannot be directly divided according to the possible values ​​of the continuous attribute. Therefore, the binary method is considered to discretize the continuous attribute. Suppose the continuous attribute a in the sample set D has k different values ​​{m1,m2,m3,...,m k}, sort the k values ​​from small to large, denoted as {m 1 ,m 2 ,m 3 ,...,m k}. Define the set of k-1 partition points t as

[0068]

[0069] Among them, T a is a set containing k-1 partition points t, m iThe value of the continuous attribute a is sorted from small to large and ranked at the i-th position. The partition point t divides D into subsets and in Contains samples with values ​​greater than t on the continuous attribute a, Contains samples whose values ​​of the continuous attribute a are less than or equal to t.

[0070] At this point, t can be regarded as a discrete attribute value, and the information entropy Ent(D) can be calculated according to the above information entropy calculation formula. and The information entropy of and Different number of samples included, weights assigned to subsets where λ∈{-,+}, The set of samples D that are greater than the partition point and less than the partition point after being partitioned by the partition point t and |D| is the number of samples in set D.

[0071] From this, the information gain Gain(D,a) of each partition point t can be calculated, that is:

[0072]

[0073] Among them, Gain represents information gain and Ent represents information entropy.

[0074] Taking the root node rock cover thickness attribute as an example, we first use the set partitioning formula The values ​​of the overburden thickness are discretized, and then the information entropy calculation formula and information gain calculation formula are used to calculate the information gain of each candidate division point of the attribute. The information gain of the rock overburden thickness (in descending order of information gain) is shown in Table 3:

[0075] Table 3 Information gain table of some rock cover thickness division points

[0076] Divide point Information Gain 220.00 0.302895712 215.50 0.236562694 412.00 0.215919612 235.00 0.211351419 260.00 0.202191118 329.00 0.200234818 …… …… 18.722 0.027855219 25.3315 0.027847104 19.15 0.024835007

[0077] S4. Select the division point with the largest information gain and the corresponding division result to obtain the first division point and the corresponding first division result; the first division result includes: a first large training data set and a first small training data set; the first large training data set is a set of training data larger than the first division point; the first small training data set is a set of training data smaller than the first division point.

[0078] The information gain of all evaluation index attributes is calculated according to the above method, and there are 204 candidate partition points in total. Some calculation results are shown in Table 4 (in descending order of information gain rate). The partition point with the largest information gain is selected as the optimal partition point. It can be obtained that the partition point of the root node sample data is the cover layer thickness>220m.

[0079] Table 4 Information gain table of some candidate partition points

[0080] property Divide point Information Gain Cover thickness 220.00 0.302895712 Head height 156.63 0.299002614 Head height 146.43 0.292477282 Head height 134.39 0.280747145 Head height 124.19 0.279537018 Uniaxial saturated compressive strength 107.75 0.265164245 Uniaxial saturated compressive strength 70.00 0.264305872 Head height 118.73 0.272936082 Number of joints 35 0.261076105 Uniaxial saturated compressive strength 100.40 0.253066785 …… …… …… Head height 19.9 0.008583831 Uniaxial saturated compressive strength 30.75 0.007550855 Uniaxial saturated compressive strength 33.85 0.005698035 Uniaxial saturated compressive strength 28.5 0.003184926

[0081] S5. Combine the first large training data set and the first small training data set as "training data" respectively, and return to the step of "using binary search to classify the training data to obtain a number of division points and corresponding division results", until the step of "selecting the division point with the largest information gain and the corresponding division result to obtain the first division point and the corresponding first division result" is completed, there is only one data in the first large training data set and the first small training data set, and a decision tree for grading the permeability resistance of the surrounding rock of the submarine tunnel is obtained.

[0082] The 42 training set data are recursively generated into a decision tree according to the above method. Figure 3 As shown, 10 groups of test set data were used to evaluate the decision tree model. The impermeability grade predicted by the decision tree was compared with the actual impermeability grade. The number of correct predictions accounted for 90% of the number of test set groups, and the accuracy rate was 90%, indicating that the model prediction effect was good.

[0083] In short, the technical solution of this application mainly includes the following three steps:

[0084] (1) The evaluation indicators of tunnel surrounding rock impermeability are determined as rock cover thickness, water head height, rock uniaxial saturated compressive strength and number of surrounding rock volume joints. At the same time, the water seepage of the surrounding rock is classified as the classification standard of surrounding rock impermeability.

[0085] (2) The original sample data set, i.e., water seepage case data of typical submarine and water-rich tunnel sections, was split into a training set and a test set in a ratio of 4:1. The training set data was analyzed and processed according to the binary method, information gain criterion, and information gain rate criterion to form the optimal division point, and a decision tree was recursively generated. The test set data was used to evaluate the generated decision tree model.

[0086] (3) Input the evaluation index parameters of the surrounding rock impermeability of the specified tunnel section into the decision tree. By classifying the nodes of the decision tree, the surrounding rock impermeability level of the tunnel section can be obtained.

[0087] This embodiment proposes that the permeability classification index is the thickness of the rock cover layer, the water head height, the uniaxial saturated compressive strength of the rock, and the number of volume joints, and the tunnel seepage is classified as a reference for the classification of the surrounding rock permeability. In addition, this embodiment uses machine learning on a large amount of data, combines the dichotomy method, the information gain criterion, and the information gain rate criterion to establish a decision tree prediction model, realizes the hierarchical prediction of continuous attribute data, and finally forms a decision tree for the classification of the surrounding rock permeability of submarine tunnels, making the classification of the surrounding rock permeability simple and intuitive, and can objectively reflect the rock mass permeability.

[0088] In an exemplary embodiment, Figure 2 As shown, a method for grading the impermeability of surrounding rocks of a submarine tunnel is provided, and the method for grading the impermeability of surrounding rocks of a submarine tunnel comprises:

[0089] Step A1: Obtain surrounding rock parameters and corresponding engineering data of the surrounding rock to be classified.

[0090] Step A2: input the surrounding rock parameters and corresponding engineering data into a decision tree to obtain the classification of the surrounding rock to be classified; the decision tree is determined by the decision tree determination method described above.

[0091] Specifically, the surrounding rock parameters of a tunnel section and the corresponding engineering data obtained in this embodiment are shown in Table 5:

[0092] Table 5 Surrounding rock parameters of a tunnel and corresponding engineering data

[0093]

[0094] Input these data into the decision tree obtained above, refer to Figure 3 From the decision tree shown, it can be seen that the permeability grade of the surrounding rock of the tunnel section is Grade II.

[0095] Thus, a method for grading the impermeability of surrounding rock of submarine tunnels has been formed, which has good engineering practical value.

[0096] Compared with the existing surrounding rock classification method, this embodiment comprehensively considers the hydrogeological conditions of the tunnel and the permeability of the rock mass, and proposes the thickness of the rock cover, the head height, the uniaxial saturated compressive strength of the rock and the number of volume joints as evaluation indicators for the surrounding rock impermeability classification. The selected indicators are easy to collect during the on-site investigation stage and have certain practicality for the subsequent design and construction stages. The machine learning method is combined with the dichotomy, the information gain criterion and the information gain rate criterion to form a decision tree. The decision tree is simple and intuitive, and can directly and objectively classify the input surrounding rock parameters and then predict the surrounding rock impermeability grade.

[0097] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a decision tree determination method or a subsea tunnel surrounding rock impermeability grading method is implemented.

[0098] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0099] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0100] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0101] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0102] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0103] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0104] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0105] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A decision tree determination method, characterized in that: The decision tree determination method comprises: Acquire training data of the tunnel section; the training data includes: surrounding rock parameter data and corresponding impermeability grade data; the surrounding rock parameter data includes: surrounding rock parameters and corresponding engineering data; the surrounding rock parameters include: rock cover thickness, water head height, rock uniaxial saturated compressive strength and number of surrounding rock volume joints; The training data is classified by using a binary method to obtain a plurality of division points and corresponding division results; the division results include: a large training data set and a small training data set; the large training data set is a set of training data in the training data that is larger than the division point; the small training data set is a set of training data in the training data that is smaller than the division point; Calculate the information gain of each of the division points in combination with the information gain criterion; Selecting a partition point with the largest information gain and a corresponding partition result to obtain a first partition point and a corresponding first partition result; the first partition result includes: a first large training data set and a first small training data set; the first large training data set is a set of training data greater than the first partition point; the first small training data set is a set of training data less than the first partition point; The first large training data set and the first small training data set are respectively combined as "training data", and the step of "using binary search to classify the training data to obtain a plurality of division points and corresponding division results" is returned until the step of "selecting the division point with the largest information gain and the corresponding division result to obtain the first division point and the corresponding first division result" is completed, and there is only one data in the first large training data set and the first small training data set, and a decision tree for classification of the permeability resistance of surrounding rock of submarine tunnels is obtained.

2. The decision tree determination method according to claim 1, characterized in that: The calculation formula for calculating the information gain of each partition point in combination with the information gain criterion is: Among them, Gain(D,a) represents the information gain of the partition point t, and Ent(D) represents the information entropy of the entire training data set D. Represents the set of partition results corresponding to the partition point t The information entropy of represents the large training data set corresponding to the partition point t, Represents the small training data set corresponding to the partition point t.

3. The decision tree determination method according to claim 2, characterized in that: The calculation formula of information entropy is: Among them, p k is the proportion of samples of the kth category in set D, k = 1, 2, ..., n.

4. The decision tree determination method according to claim 1, characterized in that: The binary method is used to classify the training data to obtain a number of division points and corresponding division results, specifically including: Inputting the training data into a decision tree model; The training data is classified by using a decision tree model and a binary method to obtain a number of division points and corresponding division results.

5. The decision tree determination method according to claim 4, characterized in that: Inputting the training data into a decision tree model specifically includes: The training data is organized into a decision tree model matrix; the decision tree model matrix includes: a training data set and an attribute set; the training data set D = {(x1, y1), (x2, y2), ..., (x 42 ,y 42 )}, where x i (i=1,2,…,42) is a 4-dimensional vector, which is the engineering data of the four evaluation indicators: rock cover thickness, water head height, volume joint number and rock uniaxial saturated compressive strength. i (i=1,2,…,42) is the corresponding impermeability level; attribute set A={a1,a2,a3,a4}, a1,a2,a3,a4 are the thickness of rock cover, water head height, number of volume joints and uniaxial saturated compressive strength of rock respectively; The decision tree model matrix is ​​input into the decision tree model.

6. The decision tree determination method according to claim 1, characterized in that: The training data of the tunnel section is training data of 52 typical tunnel sections.

7. A method for grading the impermeability of surrounding rock of a submarine tunnel, characterized in that: The method for grading the impermeability of surrounding rock of a submarine tunnel comprises: Obtain surrounding rock parameters and corresponding engineering data of surrounding rock to be classified; The surrounding rock parameters and corresponding engineering data are input into a decision tree to obtain the classification of the surrounding rock to be classified; the decision tree is determined by the decision tree determination method described in any one of claims 1-6.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the decision tree determination method described in any one of claims 1 to 6 or the method for grading the impermeability of surrounding rocks of an undersea tunnel described in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the decision tree determination method described in any one of claims 1 to 6 or the method for grading the impermeability of surrounding rocks of a submarine tunnel described in claim 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the decision tree determination method described in any one of claims 1 to 6 or the method for grading the impermeability of surrounding rocks of a submarine tunnel described in claim 7 is implemented.

Images