Tunnel surrounding rock level refined advanced prediction method based on drilling parameters

Abstract

The invention relates to the technical field of tunnel surrounding rocks, in particular to a tunnel surrounding rock level refined advanced prediction method based on drilling parameters, which comprises the following steps of: 1, acquiring continuous circulating drilling parameters by using a drill jumbo; 2, drilling parameter statistical characteristics are extracted; 3, training a tunnel surrounding rock level advanced prediction model based on the drilling parameters by adopting a long-short term memory network model; and step 4, dividing the whole cycle into a plurality of blocks in the transverse direction through a surrounding rock three-dimensional space unit body division method, and performing surrounding rock level refined advanced prediction. According to the method, the drilling parameters of excavation circulation can be continuously collected, and the continuity of advanced prediction is ensured.

Description

Technical Field

[0001] The invention relates to the technical field of tunnel surrounding rock, and in particular to a method for advanced prediction of tunnel surrounding rock level based on drilling parameters. Background Art

[0002] Advanced geological prediction during the tunnel construction phase is a key technology to effectively grasp the geological conditions ahead of the tunnel face during the tunnel construction phase. Since the 1970s, people have begun to focus on the theory, technical research and engineering practice of advanced geological prediction during the tunnel construction phase, and have developed many types of advanced geological prediction technologies. In the advanced geological prediction of railway tunnels, according to the prediction type, it can be divided into geological survey method, advanced drilling method (advanced horizontal drilling method, deepening blasthole method), geophysical method (seismic wave reflection method, electromagnetic wave reflection method, transient electromagnetic method, induced polarization method) and advanced pilot pit prediction method. According to the prediction distance, it can be divided into long-distance prediction (forecast length of more than 100m), medium-long distance prediction (forecast length of 30 to 100m) and short-distance prediction (forecast length within 30m).

[0003] Different types of advanced geological prediction technologies have different physical bases. A single advanced geological prediction technology can only obtain a certain physical property of the geological body and then infer its geological attributes. However, the accuracy of geological prediction by a single advanced geological prediction technology is not very reliable. At the same time, different methods have different prediction effects on different geological defects. This has prompted the development of comprehensive advanced geological prediction technology, and many scholars have done a lot of research on comprehensive advanced geological prediction technology. Some scholars have proposed a comprehensive advanced geological prediction method for double shield TBM construction based on multi-source information such as ground geological analysis, face surrounding rock observation, tunneling parameters and slag analysis, hammer shock three-dimensional seismic method, three-dimensional resistivity method and advanced drilling. Some scholars have proposed a comprehensive advanced geological prediction method that uses geological radar as the main means of advance prediction, combined with TGP206 seismic reflection wave method and engineering geological survey method, and successfully applied this method to the prediction of fault fracture zones and water-rich zones in actual engineering. Some scholars have proposed a comprehensive advance prediction technology based on face cataloging and geological radar, which has been successfully implemented in a deep and long tunnel project. In general, advance geological prediction has a good effect in exploring the geological conditions in front of the face during the tunnel construction stage, but due to cost and time constraints, it cannot be fully implemented during the tunnel construction stage.

[0004] Compared with the surrounding rock classification in the design stage, the surrounding rock classification in the tunnel construction stage pays more attention to re-evaluating the surrounding rock level in combination with the situation of the excavation working face, which is very important and objective. At the same time, the surrounding rock classification in the tunnel construction stage will directly guide the construction and feedback the design, and is an important link in tunnel construction. In order to improve the accuracy and reliability of the surrounding rock classification in the tunnel construction stage, many scholars have conducted a lot of research on the surrounding rock classification in the tunnel construction stage.

[0005] With the continuous improvement of the mechanized construction level of tunnels, drilling rigs are gradually used for excavation and drilling operations of drill-and-blast tunnels, and the drilling parameters collected by the drilling rigs are gradually used for surrounding rock classification. On this basis, the three-dimensional spatial characteristics of the drilling parameters are used to achieve the three-dimensional fine classification of the surrounding rock within the cycle footage range of the drilling parameters of the drilling rig blastholes. However, whether it is the overall classification of the surrounding rock using drilling parameters or the three-dimensional fine classification of the surrounding rock, it is only for the cycle where the current excavation face is located, and no research has been conducted on the identification of the surrounding rock level of the unexcavated cycle, resulting in a short length of the geological conditions in front of the face that can be judged.

[0006] In summary, how to continuously predict the geological conditions of a certain length in front of the tunnel face during the tunnel construction phase has become the key to preparing for complex geological conditions in advance, which needs further research. Summary of the invention

[0007] The present invention provides a method for fine-grained advance prediction of tunnel surrounding rock level based on drilling parameters, which can continuously collect drilling parameters of excavation cycles to ensure the continuity of advance prediction.

[0008] The method for advanced prediction of tunnel surrounding rock level based on drilling parameters of the present invention comprises the following steps:

[0009] Step 1: Collect drilling parameters of continuous cycle using a rock drilling rig;

[0010] Step 2, extracting statistical characteristics of drilling parameters;

[0011] Step 3: Using the long short-term memory network model, a tunnel surrounding rock grade advance prediction model based on drilling parameters is trained;

[0012] Step 4: Divide the entire cycle into multiple blocks horizontally through the surrounding rock three-dimensional space unit division method to perform refined advanced prediction of the surrounding rock level.

[0013] Preferably, in step 1, the drilling trolley uses an impact-rotation coupling method to drill holes, and the drilling process includes four actions: advancement, impact, rotation, and flushing. During this process, a total of six drilling parameters, namely, feed speed, advancement pressure, impact pressure, rotation pressure, water pressure, and water flow, as well as the corresponding drilling depth, interval time, and drilling coordinates, are collected. The feed speed and advancement pressure correspond to the advancement drilling action, the impact pressure corresponds to the impact drilling action, the rotation pressure corresponds to the rotation drilling action, and the water pressure and water flow correspond to the flushing drilling action.

[0014] Preferably, in step 1, during the drilling process, tunnel excavation is carried out in a cyclic manner, and 20,000 to 70,000 sets of drilling parameters are collected in each cycle. After each cycle of drilling is completed, the drilling rig combines all sets of drilling parameters of each cycle in units of cycles to form a drilling parameter file as the drilling parameters of the cycle.

[0015] Preferably, in step 2, specifically:

[0016] The mean, standard deviation, three quartiles, and coefficient of variation were selected as statistical features of drilling parameters for extraction;

[0017] The mean is the sum of all the data in the data set divided by the number of data. The calculation formula is shown in formula (1):

[0018]

[0019] Where μ represents the mean value of the drilling parameters of the current cycle, x i represents the drilling parameters of each blasthole point in the current cycle, and n represents the number of all blasthole points in the current cycle;

[0020] The standard deviation is the square root of the average of the sum of the squares of the differences between each data point and the mean in the data set. The standard deviation reflects the degree of dispersion of the data set. The larger the standard deviation, the more dispersed the data distribution is, and the smaller the standard deviation, the more concentrated the data distribution is. The calculation formula is shown in formula (2):

[0021]

[0022] In the formula, σ represents the standard deviation of the drilling parameters of the current cycle, μ represents the mean of the drilling parameters of the current cycle, and x i represents the drilling parameters of each blasthole point in the current cycle, and n represents the number of all blasthole points in the current cycle;

[0023] Quartiles are the values ​​at the three dividing points after all the data in the data set are arranged from small to large and divided into four equal parts; the three quartiles are the first quartile Q1, the second quartile Q2 and the third quartile Q3, where the first quartile Q1 is equal to the 25th percentile number after all the data in the data set are arranged from small to large; the second quartile Q2 is equal to the 50th percentile number after all the data in the data set are arranged from small to large; the third quartile Q3 is equal to the 75th percentile number after all the data in the data set are arranged from small to large;

[0024] The coefficient of variation is the ratio of the standard deviation to the mean. The coefficient of variation can eliminate the influence of the mean of the data set and only reflects the degree of dispersion of the data set relative to its mean. It is a relative indicator used to measure the degree of dispersion of a data set and is suitable for comparing the degree of dispersion of different data sets. The calculation formula is shown in formula (3):

[0025]

[0026] In the formula, c v represents the coefficient of variation of the drilling parameters of the current cycle, σ represents the standard deviation of the drilling parameters of the current cycle, and μ represents the mean of the drilling parameters of the current cycle;

[0027] Preferably, in the tunnel surrounding rock grade advance prediction model based on drilling parameters in step 3, the statistical characteristics of the drilling parameters of four excavated cycles are added to the statistical characteristics of the drilling parameters of a drilled but not yet blasted cycle to form a set of cyclic sequence data with a step length of 5 to advance predict the surrounding rock grade of the next unexcavated cycle.

[0028] As a preferred method, the training process of the tunnel surrounding rock level advance prediction model based on drilling parameters is specifically as follows:

[0029] 3.1) Dataset division;

[0030] The data set is divided into a training set and a test set in a ratio of 4:1. The training set is used to train the model, and the test set is used to evaluate the model. The data set is composed of samples, and a sample consists of two parts, namely sample features and sample labels. The sample features are passed to the model as model input to obtain the model output, and then the model output is compared with the sample label to achieve the purpose of training or testing the model.

[0031] A sample consists of six consecutive cycles arranged in the order of excavation. The statistical characteristics of drilling parameters in the first five cycles constitute the sample characteristics, and the surrounding rock level of the last cycle constitutes the sample label.

[0032] 3.2) SMOTE oversampling of training set;

[0033] SMOTE oversampling creates new samples by interpolating between minority class samples;

[0034] 3.3) Training set standardization;

[0035] Select Z-score standardization to standardize the training set. Subtract the mean of each feature value and divide it by its standard deviation, so that the mean of the processed data is 0 and the standard deviation is 1, and the distribution form of the original data is maintained, thereby eliminating the influence of different dimensions on model training. At the same time, in order to maintain the consistency of data processing and the fairness of model evaluation, the same Z-score standardization parameters as the training set are used to perform the same standardization on the test set.

[0036] 3.4) K-fold cross validation training model;

[0037] K is taken as 5. First, the 5-fold cross validation divides the training set into 5 subsets, selects 1 subset as the cross validation set, and the other 4 subsets as the cross validation training set. Then, the model is trained, and the model evaluation index of the model trained this time on the cross validation set is obtained. Finally, the above steps are repeated until each subset has served as a cross validation set, and the model evaluation index of the model trained 5 times on the cross validation set is obtained, and the optimal model is selected as the surrounding rock grade advance prediction model.

[0038] Preferably, in step 4, the surrounding rock three-dimensional space unit volume division method is:

[0039] According to the non-uniformity characteristics of the loop, the entire loop is divided into multiple blocks in the horizontal direction in the form of horizontal blocks; in the process of horizontal block division, the tunnel centerline is used as a vertical reference line and is offset to the left or right until the left and right boundaries of the tunnel contour, and the vicinity of the rail bottom surface is used as a horizontal reference line and is offset upward or downward until the upper and lower boundaries of the tunnel contour, and finally the entire loop is divided into multiple blocks in the horizontal direction;

[0040] According to the above-mentioned horizontal block division rule, the drilling parameters of each cycle collected by the drilling rig are synchronously divided, and finally each cycle obtains multiple blocks and drilling parameters within the range of each block.

[0041] Preferably, in step 4, the four most recently excavated cycles and one drilled but not yet blasted cycle are selected and arranged in order of excavation, and the statistical features of the drilling parameters of the same position blocks in these five cycles are selected to form sequence data at the cycle block level, which are input into the above-trained advanced prediction model for surrounding rock level to obtain the surrounding rock levels of multiple blocks of the next unexcavated cycle, thereby realizing refined advanced prediction of surrounding rock level.

[0042] The present invention can provide a reference for judging the geological conditions farther away from the tunnel face. At the same time, since the rock drilling rig is used as a fixed excavation and drilling operation equipment, it can continuously collect the drilling parameters of the excavation cycle without adding any process, thereby ensuring the continuity of the advanced prediction.

[0043] The refined advance prediction result of surrounding rock grade obtained by the method for refined advance prediction of tunnel surrounding rock grade based on drilling parameters in the present invention has good effect. It can grasp some surrounding rock grade conditions in front of the heading face in advance, pre-evaluate potential construction risks, adjust excavation footage and blasting parameters, ensure construction safety and efficiency, and provide suggestions for timely adjustment of on-site construction plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a method for advanced prediction of tunnel surrounding rock level based on drilling parameters in an embodiment;

[0045] Figure 2 Schematic diagram of blasthole arrangement on the tunnel face in the embodiment;

[0046] Figure 3 A schematic diagram of single blasthole drilling parameter collection in the embodiment;

[0047] Figure 4 Schematic diagram of the corresponding relationship between hardness, integrity and basic classification of surrounding rock in the embodiment;

[0048] Figure 5 A schematic diagram showing sample types and quantity details in the embodiment;

[0049] Figure 6 Schematic diagram of drilling parameter statistics characteristics in the embodiment;

[0050] Figure 7 This is a schematic diagram of the advanced prediction of surrounding rock level in the embodiment;

[0051] Figure 8 This is a schematic diagram of the data set structure in the embodiment;

[0052] Fig. 9 A schematic diagram of a sample structure in an embodiment;

[0053] Fig.10 This is a schematic diagram of the confusion matrix of the test set results in the embodiment;

[0054] Fig.11 It is a schematic diagram of horizontal block division in the embodiment;

[0055] Fig.12 This is a schematic diagram of cyclic block advance prediction in the embodiment;

[0056] Fig.13It is a schematic diagram of the refined advance prediction results of the surrounding rock level of the cycle DK3+431.4~DK3+434.4 in the embodiment;

[0057] Fig.14 It is a schematic diagram of the face of the cycle DK3+431.4~DK3+434.4 in the embodiment. DETAILED DESCRIPTION

[0058] In order to further understand the content of the present invention, the present invention is described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0059] Example

[0060] like Figure 1 As shown, this embodiment provides a method for advanced prediction of tunnel surrounding rock level based on drilling parameters, which includes the following steps:

[0061] Step 1: Collect drilling parameters of continuous cycle using a rock drilling rig;

[0062] Step 2, extracting statistical characteristics of drilling parameters;

[0063] Step 3: Using the long short-term memory network model, a tunnel surrounding rock grade advance prediction model based on drilling parameters is trained;

[0064] Step 4: Divide the entire cycle into multiple blocks horizontally through the surrounding rock three-dimensional space unit division method to perform refined advanced prediction of the surrounding rock level.

[0065] Drilling parameter collection

[0066] In step 1, the drilling rig uses an impact-rotation coupling method to drill holes. The drilling process includes four actions: advancement, impact, rotation, and flushing. During this process, a total of six drilling parameters, including feed speed, thrust pressure, impact pressure, rotation pressure, water pressure, and water flow, as well as the corresponding drilling depth, interval time, and drilling coordinates, are collected. Among them, the feed speed and thrust pressure correspond to the thrust drilling action, the impact pressure corresponds to the impact drilling action, the rotary pressure corresponds to the rotary drilling action, and the water pressure and water flow correspond to the flushing drilling action.

[0067] The definitions and acquisition methods of various drilling parameters are shown in Table 1.

[0068] Table 1 Drilling parameter definitions and acquisition methods

[0069]

[0070]

[0071] In step 1, during the drilling and blasting tunnel drilling process, the tunnel excavation is carried out in a cyclic manner. The excavation footage of each cycle is about 2 to 5 m (related to the excavation method, surrounding rock grade, etc.). Each cycle of excavation is carried out in a drilling and blasting manner. In each cycle, 200 to 300 blast holes are arranged at a blast hole spacing of 50 to 70 cm. The blast hole arrangement on the tunnel face is as follows: Figure 2 shown.

[0072] The acquisition method of each drilling parameter of each blasthole is to record at equal depth intervals, and the acquisition depth interval is 0.02m, that is, in each blasthole, one blasthole point is set every 2cm of drilling, and one set of drilling parameters is collected, such as Figure 3 As shown in the figure, about 100 to 250 sets of drilling parameters are collected for each blasthole, and about 20,000 to 70,000 sets of drilling parameters are collected for each cycle. After each cycle of drilling is completed, the drilling rig combines all the sets of drilling parameters for each cycle in units of cycles to form a drilling parameter file as the drilling parameters for that cycle.

[0073] Since the water pressure and water flow record the water outlet pressure and water outlet flow of the drilling rig water pump and have nothing to do with the quality of the surrounding rock, the drilling parameters used in this embodiment mainly refer to the four drilling parameters of feed speed, thrust pressure, impact pressure, and rotary pressure.

[0074] Surrounding rock level collection

[0075] In actual production, the surrounding rock grade is used for design in cycles. The entire rock mass of each cycle is regarded as a whole, and the quality of the rock mass is comprehensively judged based on the whole to determine the surrounding rock grade.

[0076] The corresponding surrounding rock level of the drilling parameter cycle collected in this embodiment is mainly determined by the surrounding rock classification method in the Railway Tunnel Design Code (TB 10003-2016) through the geological sketch of the tunnel face carried out by the geological engineer. After the blasting and slag removal in the previous cycle, the lithology, weathering degree, hardness and integrity of the surrounding rock are determined by observing the exposed tunnel face in the current cycle, and then the basic classification of the surrounding rock is determined. The basic classification of the surrounding rock is based on the following: Figure 4 As shown, the groundwater discharge status, initial ground stress status and the occurrence status of the main structural surface are determined through on-site measurement and other means, and then the surrounding rock classification is corrected.

[0077] Number of samples collected

[0078] According to statistics, a total of 2670 cycles of drilling parameters and their corresponding surrounding rock levels were collected, including four surrounding rock levels: II, III, IV and V. The sample types and quantity details are as follows: Figure 5 shown.

[0079] Drilling parameter statistical feature extraction

[0080] As mentioned above, about 20,000 to 70,000 sets of drilling parameters are collected in each cycle, and the surrounding rock level is used in actual production in cycles. Therefore, it is necessary to perform mathematical statistics on the drilling parameters of a large number of blasthole points in each cycle and extract the drilling parameters at the cycle level. Specifically:

[0081] The mean, standard deviation, three quartiles, and coefficient of variation are selected as the statistical features of drilling parameters for extraction, such as Figure 6 As shown in the figure, six statistical features can be extracted from each original feature of the drilling parameter, and finally 24 statistical features are obtained in each cycle.

[0082] The mean is the sum of all the data in the data set divided by the number of data. The calculation formula is shown in formula (1):

[0083]

[0084] Where μ represents the mean value of the drilling parameters of the current cycle, x i It represents the drilling parameters of each blasthole point in the current cycle, and n represents the number of all blasthole points in the current cycle.

[0085] The standard deviation is the square root of the average of the sum of the squares of the differences between each data point and the mean in the data set. The standard deviation reflects the degree of dispersion of the data set. The larger the standard deviation, the more dispersed the data distribution is, and the smaller the standard deviation, the more concentrated the data distribution is. The calculation formula is shown in formula (2):

[0086]

[0087] In the formula, σ represents the standard deviation of the drilling parameters of the current cycle, μ represents the mean of the drilling parameters of the current cycle, and x i It represents the drilling parameters of each blasthole point in the current cycle, and n represents the number of all blasthole points in the current cycle.

[0088] Quartiles are the values ​​at the three dividing points after all the data in the data set are arranged from small to large and divided into four equal parts; the three quartiles are the first quartile Q1, the second quartile Q2 and the third quartile Q3, among which the first quartile Q1 is also called the "lower quartile" or "smaller quartile", which is equal to the 25% number after all the data in the data set are arranged from small to large; the second quartile Q2 is also called the "median", which is equal to the 50% number after all the data in the data set are arranged from small to large; the third quartile Q3 is also called the "upper quartile" or "larger quartile", which is equal to the 75% number after all the data in the data set are arranged from small to large.

[0089] The coefficient of variation is the ratio of the standard deviation to the mean, also known as the coefficient of dispersion or standard deviation rate. The coefficient of variation can eliminate the influence of the mean of the data set and only reflects the degree of dispersion of the data set relative to its mean. It is a relative indicator used to measure the degree of dispersion of the data set, so it is suitable for comparing the degree of dispersion of different data sets; the calculation formula is shown in formula (3):

[0090]

[0091] In the formula, c v represents the coefficient of variation of the drilling parameters of the current cycle, σ represents the standard deviation of the drilling parameters of the current cycle, and μ represents the mean of the drilling parameters of the current cycle;

[0092] Advanced prediction model of tunnel surrounding rock grade based on drilling parameters

[0093] Long Short Term Memory (LSTM) is a special recurrent neural network (RNN) architecture that solves the gradient vanishing or gradient exploding problems encountered by traditional recurrent neural networks (RNN) when processing long sequence data. Since the LSTM can capture and understand the complex long-term dependencies in sequence data, it can predict the future trend of sequence data and is often used for time series prediction. Therefore, this embodiment uses the LSTM to train a surrounding rock level advance prediction model, and uses the drilling parameter statistical features of four excavated cycles plus the drilling parameter statistical features of a drilled but not yet blasted cycle to form a set of cyclic sequence data with a step size of 5 to advance predict the surrounding rock level of the next unexcavated cycle, such as Figure 7 As shown in the figure, it is used for refined advance prediction of surrounding rock level.

[0094] 3.1) Dataset Division

[0095] The data set is divided into a training set and a test set in a ratio of 4:1. The training set is used to train the model, and the test set is used to evaluate the model. The data set is composed of samples, and a sample consists of two parts, namely sample features and sample labels. The sample features are passed to the model as model input to obtain the model output, and then the model output is compared with the sample label to achieve the purpose of training or testing the model. The data set structure is as follows: Figure 8 shown.

[0096] Since the model input of the surrounding rock grade advance prediction model of this embodiment is a cyclic sequence data composed of the statistical characteristics of drilling parameters of four excavated cycles and one drilled but not yet blasted cycle, and the model output is the surrounding rock grade of the next unexcavated cycle, a sample in the data set of this embodiment includes six consecutive cycles arranged in the order of excavation, and the statistical characteristics of drilling parameters of the first five cycles are taken to constitute the sample characteristics, and the surrounding rock grade of the last cycle is taken to constitute the sample label; the sample structure is shown in Figure 9.

[0097] According to the above method, the extracted drilling parameter statistical features are converted into standard training and testing samples to form the final data set, and finally the data set division is completed. The details of the data set division are shown in Table 2.

[0098] Table 2 Dataset division details

[0099]

[0100] 3.2) SMOTE oversampling of training set

[0101] Since the number of samples of different surrounding rock levels is inconsistent during the sample collection process, the samples of the divided training set and data set are unbalanced. When the number of samples of some categories is much larger than that of other categories, the model will pay too much attention to the categories with large data volumes during training, while ignoring the categories with small data volumes, causing the model to be more inclined to classify samples into the categories with large data volumes, thereby reducing the accuracy and reliability of the model. Therefore, the problem of sample imbalance needs to be solved.

[0102] Oversampling and undersampling are two common methods for dealing with sample imbalance. Oversampling is to balance samples of different categories by increasing the number of minority class samples. Undersampling is to balance samples of different categories by reducing the number of majority class samples. Since the total number of samples collected in this embodiment is small, oversampling is selected for processing.

[0103] General oversampling is to randomly select some samples from the minority class samples, and then generate new samples by copying these samples, thereby increasing the number of minority class samples and making the number of samples in each class relatively balanced. However, directly copying samples may cause model overfitting because the model will pay too much attention to these repeated samples. SMOTE oversampling creates new samples by interpolating between minority class samples; therefore, SMOTE oversampling generates synthetic samples of minority class samples, not direct copies. Therefore, SMOTE oversampling is finally selected for processing. At the same time, in order to maintain the independence of the test set and conform to the actual application scenario, SMOTE oversampling is only performed on the training set. The details of the data set division after SMOTE oversampling are shown in Table 3.

[0104] Table 3 Details of the data set division after SMOTE oversampling

[0105]

[0106] 3.3) Training set standardization

[0107] Since the 24 drilling parameter statistical features that make up the sample features are of different magnitudes, their orders of magnitude are different. If features of different dimensions are directly used to train the model, features with larger values ​​may dominate the model, while features with smaller values ​​have little influence, thus affecting the accuracy and reliability of the results. Therefore, the problem of different feature dimensions needs to be solved.

[0108] This embodiment selects Z-score standardization to standardize the training set, subtracting the mean of each feature value and dividing it by its standard deviation, so that the mean of the processed data is 0 and the standard deviation is 1, and the distribution form of the original data is maintained, thereby eliminating the influence of different dimensions on model training. At the same time, in order to maintain the consistency of data processing and the fairness of model evaluation, the same Z-score standardization parameters (i.e., the same mean and standard deviation) as the training set are used to perform the same standardization on the test set.

[0109] 3.4) K-fold cross validation training model

[0110] K-fold cross validation further divides the training set into a cross-validation training set and a cross-validation verification set to train the model. In this embodiment, K is taken as 5. First, the 5-fold cross validation divides the training set into 5 subsets, selects 1 subset as the cross-validation verification set, and the other 4 subsets as the cross-validation training set. Then, the model is trained, and the model evaluation index of the model trained this time on the cross-validation verification set is obtained. Finally, the above steps are repeated until each subset has served as a cross-validation verification set once, and the model evaluation index of the model trained 5 times on the cross-validation verification set is obtained, as shown in Table 4.

[0111] Table 4 5-fold cross validation set model evaluation index table

[0112] 50% off round Accuracy Average precision Average recall Average F1 score 1st Fold 93.6％ 94.1％ 94.1％ 93.7％ 2nd Fold 93.3％ 93.4％ 93.4％ 93.3％ 3rd Fold 95.5％ 95.5％ 95.4％ 95.4％ 4th Discount 94.6％ 95.1％ 94.7％ 94.6％ 5th Discount 94.3％ 94.4％ 94.0％ 94.0％

[0113] As can be seen from the above table, the five models obtained through 5-fold cross validation all have good model evaluation indicators. In this embodiment, the optimal model obtained by the third fold training is selected as the surrounding rock level advance prediction model.

[0114] 3.5) Model Evaluation

[0115] The trained rock mass level advance prediction model was applied to the test set, and the accuracy was 93.5%, the average precision was 84.9%, the average recall was 92.1%, and the average F1 score was 87.3%. The confusion matrix of the test set results is as follows: Fig.10 The results show that the surrounding rock grade advance prediction model has a good effect in the advance prediction of surrounding rock grade, and based on this, it can be further used for refined advance prediction of surrounding rock grade.

[0116] Method for dividing surrounding rock into three-dimensional space units

[0117] According to the non-uniform characteristics of the cycle, the entire cycle is divided into multiple blocks in the horizontal direction in the form of horizontal blocks. In the process of horizontal block division, considering the differences in the tunnel excavation design contours and the uniformity of the number of blocks, it is proposed to use the tunnel centerline as the vertical reference line, shift 2 to 4 meters to the left or right, until the left and right boundaries of the tunnel contour, and use the track bottom surface (pit bottom surface) as the horizontal reference line, shift 2 to 4 meters up or down, until the upper and lower boundaries of the tunnel contour. Finally, the entire cycle is divided into 18 blocks in the horizontal direction, numbered A-1 to A-18, among which the maximum size of a single block is 2 to 4 meters, and the longitudinal area of ​​a single block is 3 to 8 meters. 2 The number of blastholes in a single block is 10 to 20. Fig.11 shown.

[0118] According to the above-mentioned horizontal block division rules, the drilling parameters of each cycle collected by the drilling rig are synchronously divided, and finally 18 blocks and drilling parameters within each block are obtained for each cycle. After horizontal block division, each block can be regarded as a "micro cycle", and the statistical characteristics of drilling parameters of each "micro cycle" can be directly calculated according to the above-mentioned method of extracting the statistical characteristics of drilling parameters of the entire cycle.

[0119] Refined and advanced prediction of surrounding rock level

[0120] According to the above-mentioned surrounding rock three-dimensional space unit body division method, each excavation cycle can be divided into 18 blocks, and 24 drilling parameter statistical characteristics of each block can be obtained.

[0121] In the actual tunnel excavation process, the four most recently excavated cycles and one drilled but not yet blasted cycle are selected and arranged in order of excavation. The drilling parameter statistical features of the same position blocks in these five cycles are selected to form the sequence data of the cycle block level, which is input into the above-trained rock mass level advance prediction model to obtain the surrounding rock level of the next unexcavated cycle of 18 blocks, so as to achieve refined advance prediction of surrounding rock level and provide suggestions for the adjustment of on-site construction plans. Fig.12 shown.

[0122] Case analysis of refined advanced prediction of surrounding rock level

[0123] In order to verify the effect of the refined advance prediction method of tunnel surrounding rock grade based on drilling parameters, the excavation cycle of a double-track railway tunnel was taken as an example for analysis.

[0124] The excavation method of this tunnel is the full-face method. A fully computerized three-arm rock drilling rig is used to drill and blast the face, and manual + handheld pneumatic drills are used to drill and blast the invert. The current cycle excavation footage is 3m, the mileage range is DK3+428.4~DK3+431.4, and the holes have been drilled but not blasted yet. The drilling parameters of the current excavation cycle and the latest four excavation cycles are used to perform a refined advance prediction of the surrounding rock level according to the surrounding rock three-dimensional space unit division method and the surrounding rock level refined advance prediction strategy, and the refined advance prediction results of the surrounding rock level of the next unexcavated cycle are obtained, such as Fig.13 As shown, the mileage range of the next trenchless cycle is DK3+431.4 to DK3+434.4.

[0125] According to the on-site geological data after the excavation of cycle DK3+431.4~DK3+434.4, the tunnel face area contains two types of rock: conglomerate and slate. The conglomerate part is located on the right side of the tunnel face area, accounting for a large part of the area. The rock is hard and belongs to hard rock, and is relatively complete, which can be judged as Class III. The slate part is located on the left side of the tunnel face area, accounting for a small part of the area. The rock is weak and belongs to relatively soft rock, and is relatively complete, which can be judged as Class IV. Fig.14 shown.

[0126] After excavation at DK3+431.4~DK3+434.4, the excavation showed obvious heterogeneity characteristics. Fig.13 and Fig.14 By comparison, the conglomerate part is basically consistent with the Grade III area, and the slate part is basically consistent with the Grade IV area, which proves that the refined advance prediction method of tunnel surrounding rock grade based on drilling parameters is reliable.

[0127] This embodiment obtains the following conclusions through the study of the refined advance prediction method of tunnel surrounding rock grade based on drilling parameters.

[0128] (1) Based on a large number of collected drilling parameters and combined with the long short-term memory network (LSTM), a tunnel surrounding rock grade advance prediction model based on drilling parameters was constructed. The model accuracy was 93.5%, the average precision was 84.9%, the average recall was 92.1%, and the average F1 score was 87.3%, indicating that the model has a good effect in advance prediction of surrounding rock grade.

[0129] (2) Based on the three-dimensional spatial characteristics of drilling parameters, a three-dimensional spatial unit division method for surrounding rock and a refined advance prediction strategy for surrounding rock grade were proposed. The tunnel surrounding rock grade advance prediction model based on drilling parameters was constructed to achieve refined advance prediction of surrounding rock grade. The surrounding rock grade of the next unexcavated cycle was successfully predicted in advance, which can judge the geological conditions farther away from the tunnel face to a certain extent.

[0130] (3) Taking actual engineering as an example, through the analysis of classic cases, the reliability of the refined advance prediction method of tunnel surrounding rock level based on drilling parameters is proved.

[0131] The refined advance prediction result of surrounding rock grade obtained by the refined advance prediction method of tunnel surrounding rock grade based on drilling parameters in this embodiment can grasp some surrounding rock grade conditions in front of the heading face in advance, pre-evaluate potential construction risks, adjust excavation footage and blasting parameters, ensure construction safety and efficiency, and provide suggestions for timely adjustment of on-site construction plans.

[0132] The present invention and its embodiments are described schematically above, and the description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. Therefore, if a person skilled in the art is inspired by it and designs a structural method and an embodiment similar to the technical solution without creativity without departing from the purpose of the invention, they shall all fall within the protection scope of the present invention.

Claims

1. A refined advance prediction method for tunnel surrounding rock grade based on drilling parameters, characterized by: The following steps are involved: Step 1: Collect drilling parameters of continuous cycle using a rock drilling rig; Step 2, extracting statistical characteristics of drilling parameters; Step 3: Using the long short-term memory network model, a tunnel surrounding rock grade advance prediction model based on drilling parameters is trained; Step 4: Divide the entire cycle into multiple blocks horizontally through the surrounding rock three-dimensional space unit division method to perform refined advanced prediction of the surrounding rock level.

2. The method for advanced prediction of tunnel surrounding rock level based on drilling parameters according to claim 1 is characterized in that: In step 1, the drilling rig uses an impact-rotation coupling method to drill holes. The drilling process includes four actions: advancement, impact, rotation, and flushing. During this process, a total of six drilling parameters, including feed speed, thrust pressure, impact pressure, rotation pressure, water pressure, and water flow, as well as the corresponding drilling depth, interval time, and drilling coordinates, are collected. Among them, the feed speed and thrust pressure correspond to the thrust drilling action, the impact pressure corresponds to the impact drilling action, the rotary pressure corresponds to the rotary drilling action, and the water pressure and water flow correspond to the flushing drilling action.

3. The method for advanced prediction of tunnel surrounding rock grade based on drilling parameters according to claim 2 is characterized in that: In step 1, during the drilling process, tunnel excavation is carried out in a cyclic manner, and 20,000 to 70,000 sets of drilling parameters are collected in each cycle. After each cycle of drilling is completed, the drilling rig combines all sets of drilling parameters of each cycle in units of cycles to form a drilling parameter file as the drilling parameters of the cycle.

4. The method for advanced prediction of tunnel surrounding rock grade based on drilling parameters according to claim 3 is characterized in that: In step 2, specifically: The mean, standard deviation, three quartiles, and coefficient of variation were selected as statistical features of drilling parameters for extraction; The mean is the sum of all the data in the data set divided by the number of data. The calculation formula is shown in formula (1): Where μ represents the mean value of the drilling parameters of the current cycle, x i represents the drilling parameters of each blasthole point in the current cycle, and n represents the number of all blasthole points in the current cycle; The standard deviation is the square root of the average of the sum of the squares of the differences between each data point and the mean in the data set. The standard deviation reflects the degree of dispersion of the data set. The larger the standard deviation, the more dispersed the data distribution is, and the smaller the standard deviation, the more concentrated the data distribution is. The calculation formula is shown in formula (2): In the formula, σ represents the standard deviation of the drilling parameters of the current cycle, μ represents the mean of the drilling parameters of the current cycle, and x i represents the drilling parameters of each blasthole point in the current cycle, and n represents the number of all blasthole points in the current cycle; Quartiles are the values ​​at the three dividing points after all the data in the data set are arranged from small to large and divided into four equal parts; the three quartiles are the first quartile Q1, the second quartile Q2 and the third quartile Q3, where the first quartile Q1 is equal to the 25th percentile number after all the data in the data set are arranged from small to large; the second quartile Q2 is equal to the 50th percentile number after all the data in the data set are arranged from small to large; the third quartile Q3 is equal to the 75th percentile number after all the data in the data set are arranged from small to large; The coefficient of variation is the ratio of the standard deviation to the mean. The coefficient of variation can eliminate the influence of the mean of the data set and only reflects the degree of dispersion of the data set relative to its mean. It is a relative indicator used to measure the degree of dispersion of a data set and is suitable for comparing the degree of dispersion of different data sets. The calculation formula is shown in formula (3): In the formula, c v represents the coefficient of variation of the drilling parameters of the current cycle, σ represents the standard deviation of the drilling parameters of the current cycle, and μ represents the mean of the drilling parameters of the current cycle.

5. The method for advanced prediction of tunnel surrounding rock grade based on drilling parameters according to claim 4 is characterized in that: In the advanced prediction model of tunnel surrounding rock grade based on drilling parameters in step 3, the statistical characteristics of drilling parameters of four excavated cycles and the statistical characteristics of drilling parameters of a drilled but not yet blasted cycle are used to form a set of cyclic sequence data with a step length of 5 to advance the prediction of the surrounding rock grade of the next unexcavated cycle.

6. The method for advanced prediction of tunnel surrounding rock grade based on drilling parameters according to claim 5 is characterized by: The training process of the tunnel surrounding rock grade advance prediction model based on drilling parameters is as follows: 3.1) Dataset division; The data set is divided into a training set and a test set in a ratio of 4:

1. The training set is used to train the model, and the test set is used to evaluate the model. The data set is composed of samples, and a sample consists of two parts, namely sample features and sample labels. The sample features are passed to the model as model input to obtain the model output, and then the model output is compared with the sample label to achieve the purpose of training or testing the model. A sample consists of six consecutive cycles arranged in the order of excavation. The statistical characteristics of drilling parameters in the first five cycles constitute the sample characteristics, and the surrounding rock level of the last cycle constitutes the sample label. 3.2) SMOTE oversampling of training set; SMOTE oversampling creates new samples by interpolating between minority class samples; 3.3) Training set standardization; Select Z-score standardization to standardize the training set. Subtract the mean of each feature value and divide it by its standard deviation, so that the mean of the processed data is 0 and the standard deviation is 1, and the distribution form of the original data is maintained, thereby eliminating the influence of different dimensions on model training. At the same time, in order to maintain the consistency of data processing and the fairness of model evaluation, the same Z-score standardization parameters as the training set are used to perform the same standardization on the test set. 3.4) K-fold cross validation training model; K is taken as 5. First, the 5-fold cross validation divides the training set into 5 subsets, selects 1 subset as the cross validation set, and the other 4 subsets as the cross validation training set. Then, the model is trained, and the model evaluation index of the model trained this time on the cross validation set is obtained. Finally, the above steps are repeated until each subset has served as a cross validation set, and the model evaluation index of the model trained 5 times on the cross validation set is obtained, and the optimal model is selected as the surrounding rock grade advance prediction model.

7. The method for advanced prediction of tunnel surrounding rock grade based on drilling parameters according to claim 6 is characterized by: In step 4, the surrounding rock three-dimensional space unit volume division method is: According to the non-uniformity characteristics of the loop, the entire loop is divided into multiple blocks in the horizontal direction in the form of horizontal blocks; in the process of horizontal block division, the tunnel centerline is used as a vertical reference line and is offset to the left or right until the left and right boundaries of the tunnel contour, and the vicinity of the rail bottom surface is used as a horizontal reference line and is offset upward or downward until the upper and lower boundaries of the tunnel contour, and finally the entire loop is divided into multiple blocks in the horizontal direction; According to the above-mentioned horizontal block division rule, the drilling parameters of each cycle collected by the drilling rig are synchronously divided, and finally each cycle obtains multiple blocks and drilling parameters within the range of each block.

8. The method for advanced prediction of tunnel surrounding rock grade based on drilling parameters according to claim 7 is characterized in that: In step 4, the four most recently excavated cycles and one drilled but not yet blasted cycle are selected and arranged in order of excavation, and the statistical characteristics of the drilling parameters of the blocks at the same position in these five cycles are selected to form sequence data at the cycle block level, which are input into the above-trained rock mass level advance prediction model to obtain the rock mass levels of multiple blocks of the next unexcavated cycle, thereby realizing refined advance prediction of the rock mass level.

Images