TBM tunneling section feature extraction and cutterhead thrust prediction method based on kernel density estimation

Abstract

The invention discloses a TBM tunneling section feature extraction and cutterhead thrust prediction method based on kernel density estimation. The method comprises the following steps: step 1, classifying surrounding rocks; step 2, constructing a cutterhead thrust prediction model; step 3, constructing a model training sample library, which specifically comprises the steps of collecting effective tunneling section data, segmenting the internal stage of the tunneling section, extracting operation parameters of a loading section and calculating the average thrust of a cutterhead of a stable section; 4, training a cutterhead thrust prediction model; 5, selecting a cutterhead thrust prediction model; 6, tunneling is conducted; 7, extracting operation parameters of the first loading section; and 8, predicting the average thrust of the cutterhead in the stable section. According to the method, the rock mass quality index is extracted from the data of the loading section, the operation parameters of the stable excavation section are used for establishing the cutterhead thrust prediction model and engineering application, the cutterhead thrust in the TBM construction process is predicted in time, and the prediction result can provide guidance for setting the operation parameters of a field machine driver; and the excavation efficiency of the tunnel boring machine is further improved.

Description

Technical Field

[0001] The invention relates to the field of automatic processing of monitoring data of tunnel engineering tunnel boring machine excavation process, in particular to a TBM excavation section feature extraction and cutterhead thrust prediction method based on kernel density estimation. Background Art

[0002] As a mechanized equipment integrating multiple functions such as rock breaking, slag discharge and support, tunnel boring machine (TBM) is widely used in the construction of major deep buried tunnel projects. During the excavation process, the TBM driver needs to adjust the machine operating parameters in time according to the changes in geological conditions to achieve the best excavation efficiency under different rock mass qualities. Therefore, the prediction of TBM response parameters can effectively guide the adjustment of operating parameters during the construction process. On the contrary, if the machine operating parameters are not adjusted in time, such as using a large thrust in weak rock formations, it will easily cause engineering accidents such as landslides and machine jams, seriously threatening the lives of construction workers and causing serious economic losses.

[0003] TBM effective rock breaking An effective excavation section is a process in which the TBM driver adjusts the operating parameters to gradually increase the excavation speed from zero within the maximum travel range, and then excavates stably until the final unloading and shutdown. The stable excavation stage is the main stage for TBM to cut the rock mass to form a tunnel. At present, the adjustment of operating parameters during TBM construction is mainly based on the driver's experience of the machine parameters in the rock breaking and loading stage, but there is no relevant reference for the selection and setting of operating parameters in the stable excavation stage. Therefore, how to predict the machine response cutter thrust in the stable excavation stage based on the rock breaking data of the machine loading stage during TBM construction is of great engineering significance for guiding the adjustment of operating parameters, improving the adaptability of parameters and rock mass, and improving the excavation efficiency of the machine. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for extracting the features of the TBM excavation section and predicting the cutterhead thrust based on kernel density estimation in view of the deficiencies of the above-mentioned prior art. To predict the cutterhead thrust in the excavation and stable excavation section during the TBM construction process, it is necessary to collect the excavation section data under different rock mass conditions on site, accurately segment the loading section and stable excavation section data, and establish a thrust prediction model that reflects the interaction between rock and machine based on the loading section data. The present invention establishes a feature extraction method for the excavation section and its internal loading section and stable excavation section based on the characteristics of the TBM on-site excavation process, providing an accurate data basis for the training of the prediction model. The prediction model established on this basis is applied to the prediction of the cutterhead thrust during the TBM excavation process, which can provide parameter guidance for on-site machine operators and improve the efficiency of machine excavation.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for extracting features of a TBM excavation section and predicting cutterhead thrust based on kernel density estimation comprises the following steps.

[0007] Step 1: Surrounding rock classification: Based on the relevant national or industry surrounding rock classification standards, the surrounding rock is divided into N types according to rock strength, integrity, structural surface state, occurrence and groundwater conditions.

[0008] Step 2: Construct a cutterhead thrust prediction model: A neural network-based cutterhead thrust prediction model is constructed for each surrounding rock type; the input layer of the cutterhead thrust prediction model is the loading section operation and rock mass index parameter vector [n, v, a, b, TPI], and the output layer is the average cutterhead thrust prediction value in the stable section. Where n is the cutter head speed in the loading section; v is the TBM advancement speed in the loading section; a is the slope of the fitting curve of single cutter thrust and penetration in the loading section; b is the initial penetration thrust of the roller cutter in the loading section; TPI is the linear fitting slope of single cutter torque and penetration in the loading section.

[0009] Step 3: Build a model training sample library, which includes the following steps:

[0010] Step 3-1, collect effective excavation section data: collect effective excavation section data of all types of surrounding rock in step 1; wherein, the number of effective excavation sections of each type of surrounding rock is not less than M; M≥100.

[0011] Step 3-2, segmentation of internal stages of the excavation section: Based on the two-way sliding window method of kernel density estimation, each effective excavation section of each type of surrounding rock is segmented into loading section, stable section and unloading section.

[0012] Step 3-3, extracting operating parameters of loading section and rock mass: extracting operating parameters for each loading section of each type of surrounding rock.

[0013] Step 3-4, calculate the average thrust of the cutterhead in the stable section: For each stable section of each type of surrounding rock, calculate the average thrust of the cutterhead in the stable section.

[0014] Step 4: training the cutterhead thrust prediction model: using the model training sample library constructed in step 3, the cutterhead thrust prediction model of the corresponding surrounding rock type constructed in step 2 is trained to obtain N trained cutterhead thrust prediction models.

[0015] Step 5: Select a cutterhead thrust prediction model: Determine the surrounding rock type at the tunneling site, and select a trained cutterhead thrust prediction model with the same surrounding rock type as determined in step 4.

[0016] Step 6: Tunnel excavation: The TBM performs construction of loading section 1 of the tunnel to be excavated.

[0017] Step 7, extracting the operating parameters of loading section 1: extracting the operating parameters of loading section 1 in step 6, and obtaining the operating parameters of loading section 1 and the rock mass index vector [n′, v′, a′, b′, TPI′].

[0018] Step 8: Predict the average thrust of the cutterhead in the stable section: Substitute the loading section parameter vector [n′, v′, a′, b′, TPI′] obtained in step 7 into the trained cutterhead thrust prediction model selected in step 5 to predict the average thrust of the cutterhead in the stable section of the tunnel to be excavated.

[0019] In step 1, the surrounding rock classification standards of relevant countries or industries are relied upon. For example, according to the national standard "Specifications for Geological Investigation of Water Conservancy and Hydropower Engineering GB50487-2008", the surrounding rock is divided into N=5 types, namely, Class I, II, III, IV and V surrounding rock.

[0020] In step 3-1, the effective excavation section refers to the process in which the TBM driver turns on the cutterhead motor current switch to make the cutterhead run at the specified rotation speed n, and adjusts the control speed parameters so that the cutterhead thrust and cutterhead torque cut the rock mass while overcoming its own friction and idling resistance to form the designed excavation surface; therefore, the method for determining the effective excavation section includes the following steps:

[0021] Step 3-1A, TBM excavation: The TBM conducts tunnel excavation and monitors the excavation operation data according to the set data sampling interval, thereby obtaining several excavation sections. The excavation operation data of each excavation section includes the cutter head speed n, the cutter head propulsion speed v, the cutter head thrust F and the cutter head torque T.

[0022] Step 3-1B, calculate the mean of the excavation section operation parameters: calculate the mean of each excavation operation data of each excavation section; then the mean of the excavation operation data of any excavation section is: the mean of the cutter head speed Mean cutting head advancement speed Mean thrust of cutter head and the mean torque of the cutter head

[0023] Step 3-1C, determine the effective excavation section: when the excavation operation data mean of a certain excavation section meets the following four basic conditions at the same time, the excavation section is considered to be an effective excavation section; otherwise, it is judged to be an ineffective excavation section and no effective cutting and rock breaking is formed; the four basic conditions are:

[0024]

[0025] In the formula, F f is the friction thrust of the cutter disc.

[0026] T fis the friction torque value of the cutter disc.

[0027] In step 3-1C, the friction thrust F f , measured through an on-site TBM friction propulsion test. The test method is: measuring the maximum static friction force of the machine hydraulic system in the process of pushing the cutter disc from static to a speed greater than zero.

[0028] In step 3-1C, the friction torque value of the cutter head is T f , measured through the on-site TBM torque idling test. The test method is: when the cutter head speed is set to the maximum rated speed, the maximum torque value during the cutter head rotation process.

[0029] In step 3-2, the method for segmenting the internal stages of the effective excavation section based on the bidirectional sliding window of kernel density estimation includes the following steps:

[0030] Step 3-2A, identify the loading section starting point index value Index1: traverse the excavation operation data of the effective excavation section A in the order of excavation time; record the first time index value of the excavation operation data that satisfies the following Index1 calculation formula as the loading section starting point index value Index1; then the Index1 calculation formula is:

[0031]

[0032] Step 3-2B, probability density estimation of the cutterhead advancement speed: perform kernel density estimation on the cutterhead advancement speed of the effective excavation section A to obtain the probability density curve of the cutterhead advancement speed.

[0033] Step 3-2C, obtain the maximum probability density of the cutterhead advancement speed: find out the maximum probability density v of the cutterhead advancement speed in the stable section of the effective excavation section A from the probability density curve of the cutterhead advancement speed. max .

[0034] Step 3-2D, identify the index value of the starting point of the stable segment Index2: Use the forward sliding window method to traverse from the starting point of the effective excavation segment A to the end point, and determine the cutter head advancement speed and v in turn. max When the cutter head advance speed equals or exceeds v for the first time max The time index value corresponding to the time is the index value Index2 of the starting point of the stable segment.

[0035] Step 3-2E, identify the index value of the unloading section starting point Index3: Use the reverse sliding window method to traverse from the end point of the effective excavation section A to the starting point, and determine the cutter head advancement speed and v in turn. max When the cutter head advance speed equals or exceeds v for the first time max The time index value corresponding to the time is the starting index value Index3 of the unloading segment.

[0036] Step 3-2F, stage division: the effective excavation section A between the starting index value Index1 of the loading section and the starting index value Index2 of the stable section is recorded as the loading section; the effective excavation section A between the starting index value Index2 of the stable section and the starting index value Index3 of the unloading section is recorded as the stable section; the effective excavation section A between the starting index value Index3 of the unloading section and the end point is recorded as the unloading section.

[0037] In step 3-2B, assume that the effective excavation section A has t cutterhead advancement speeds, which are: x1, x2, ..., x t , the probability density of the cutterhead advancement speed is estimated to be The calculation formula is:

[0038]

[0039] Where K(x) represents the Gaussian kernel function; h is the bandwidth, and the cutter head propulsion speed is used as the index of density estimation, and its bandwidth size is h = 2 mm / min.

[0040] In step 2, the loss function of the cutterhead thrust prediction model is the root mean square error.

[0041] In step 2, the cutterhead thrust prediction model adopts a 5-fully-connected hidden layer structure; 80% of the model training sample library constructed in step 3 is used as a training set, and 20% is used as a test set.

[0042] The present invention has the following beneficial effects:

[0043] (1) The present invention establishes a criterion for identifying the effective rock breaking stage based on the construction characteristics during TBM excavation, and can obtain more accurate excavation section data according to the physical characteristics of the excavation parameters during the cutterhead cutting of the rock mass.

[0044] (2) The method of the present invention can quickly and accurately realize the internal segmentation of the excavation section data, and the identification of the starting index value of different stages can achieve high accuracy; the kernel density estimation method can be applied to various data change processes of the excavation section data, and the maximum probability density value is used to accurately identify the stable section data in the excavation section; the bidirectional traversal method based on the excavation section data can minimize the number of data queries and improve the efficiency of index value identification. At the same time, the proposed method is also applicable to shield monitoring data with obvious loading, stability and unloading trends or other field monitoring big data with similar laws, and has a wide range of applications.

[0045] (3) The cutterhead thrust prediction model is trained based on the rock mass index and operation parameter index extracted from the TBM loading section data reflecting the rock machine action law, which can realize the thrust prediction in the stable excavation stage. This method can effectively reduce the limitation of relying solely on experience when setting the operation parameters of the on-site construction personnel, and guide the setting of the machine control parameters in the stable excavation section based on the thrust prediction results, which can effectively improve the excavation efficiency and ensure the safe and efficient construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 The overall flow chart of the segmentation of the excavation section, extraction of operating parameters, establishment of the thrust model and application of the present invention is shown.

[0047] Figure 2 The curves showing the changes of cutterhead thrust, cutterhead torque, propulsion speed and cutterhead speed over time in the effective excavation section that meets the effective excavation section judgment conditions are shown.

[0048] Figure 3 The curves of cutterhead thrust, cutterhead torque and propulsion speed changing with time in the effective excavation section that does not meet the effective excavation section judgment conditions are shown.

[0049] Figure 4 The schematic diagram shows the principle of data segmentation process of typical effective rock breaking tunneling section data using forward and reverse sliding methods based on kernel density estimation.

[0050] Figure 5 A schematic diagram showing the results of internal segmentation of the cutterhead thrust, cutterhead torque and propulsion speed parameters in a representative effective excavation section using the kernel density forward and reverse sliding segmentation method.

[0051] Figure 6 The curve showing the root mean square error between the predicted thrust and the actual thrust of the cutterhead at location 51735.28 of the fourth section of the Yinsong Project is shown.

[0052] Figure 7 The figure shows the fitting curve of the predicted thrust and the actual thrust of the cutterhead at the location 51735.28 of the fourth section of the Yinsong Project. DETAILED DESCRIPTION

[0053] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific preferred embodiments.

[0054] The invention is elaborated in detail with the collected on-site monitoring data of the tunnel boring machine construction process of the fourth section of the Yinsong Project in Jilin Province.

[0055] A method for extracting features of a TBM excavation section and predicting cutterhead thrust based on kernel density estimation comprises the following steps.

[0056] Step 1: Classification of surrounding rock

[0057] The rock breaking mechanism under different rock mass quality conditions during tunnel excavation is not exactly the same. When the rock mass is intact and there are fewer joints and fissures, the main method is to form slag pieces by machine cutter intrusion and cutting. When there are more joints and fissures in the rock mass, weak fissures are the main way to form rock blocks. Therefore, it is necessary to collect rock breaking data under different surrounding rock quality conditions so that the established prediction model has better generalization and robustness. The working conditions of rock mass quality are divided according to the national or industry technical classification standards of the industry in which the specific tunnel project is located. At the same time, the data collection frequency during the construction of the on-site tunnel boring machine must meet the minimum requirements of the corresponding standards.

[0058] The surrounding rock is divided into N types according to rock strength, integrity, structural surface state, occurrence and groundwater conditions. In this embodiment, according to the national standard "Specifications for Geological Survey of Water Conservancy and Hydropower Engineering GB50487-2008", the surrounding rock is divided into N = 5 types, namely, Class I, II, III, IV and V surrounding rock. The higher the surrounding rock category, the worse the rock mass quality. For the scope of Section 4 of the Yinsong Project, it includes four types of surrounding rock: II, III, IV, and V.

[0059] Step 2: Build a cutterhead thrust prediction model

[0060] A neural network-based cutterhead thrust prediction model is constructed for each surrounding rock type. The input layer of the cutterhead thrust prediction model is the loading section operation parameter vector [n, v, a, b, TPI], and the output layer is the predicted value of the average cutterhead thrust in the stable section. Where n is the cutter head speed in the loading section; v is the TBM advancement speed in the loading section; a is the slope of the fitting curve of single cutter thrust and penetration in the loading section; b is the initial thrust of the roller cutter in the loading section; TPI is the linear fitting slope of single cutter torque and penetration in the loading section.

[0061] The above-mentioned cutter thrust prediction model preferably adopts a 5-fully connected hidden layer structure, in which the number of neurons in each layer is [5, 16, 32, 64, 32, 16, 1], and the loss function selects the root mean square error. When the learning rate is 1e-1, the optimal prediction performance is obtained in the test set through the hyperparameter selection method.

[0062] Step 3: Build a model training sample library, which includes the following steps:

[0063] Step 3-1: Collect effective excavation section data

[0064] Collect the effective excavation section data of all surrounding rock types in step 1; wherein the number of effective excavation sections of each type of surrounding rock is not less than M; M ≥ 100.

[0065] During TBM construction, due to factors such as machine idle switching steps and trial excavation, the cutterhead runs idle without effective rock cutting. Therefore, it is necessary to determine whether the collected field monitoring data under different surrounding rock quality conditions are effective rock breaking sections. The determination of whether the excavation section is an effective rock breaking and cutting section is based on the parameter characteristic law of the effective excavation process of the tunnel boring machine.

[0066] An effective rock-breaking excavation section, also called an effective excavation section, is the process in which the TBM driver turns on the cutterhead motor current switch to make the cutter head run at a specified rotation speed, and adjusts the control parameters on this basis to make the cutterhead thrust and torque overcome its own friction and idling resistance to cut the rock mass to form a designed excavation surface. However, the main difference between the effective rock-breaking stage and the process of machine step change or idling is that, in addition to the values ​​of the cutterhead rotation speed and propulsion speed being greater than zero, the thrust value required for the disc cutter to effectively cut the rock mass needs to be greater than the machine's own friction resistance, and the cutterhead torque needs to be greater than the machine's own idling resistance.

[0067] Therefore, the above-mentioned method for determining the effective excavation section includes the following steps.

[0068] Step 3-1A, TBM excavation: The TBM conducts tunnel excavation and monitors the excavation operation data at set intervals to obtain several excavation sections. The excavation operation data of each excavation section includes the cutter head speed n, the cutter head propulsion speed v, the cutter head thrust F and the cutter head torque T.

[0069] Step 3-1B, calculate the mean of the excavation section operation parameters: calculate the mean of each excavation operation data of each excavation section; then the mean of the excavation operation data of any excavation section is: the mean of the cutter head speed Mean cutting head advancement speed Mean thrust of cutter head and the mean torque of the cutter head

[0070] Step 3-1C: Determine the effective excavation section

[0071] For a field monitoring data of a tunneling section with a length of t, the tunneling section contains a sequence of cutter head speed n {n1,n2,n3,...,n t}, cutter head thrust F sequence {F1, F2, F3, ..., F t}, the cutter head torque T sequence {T1,T2,T3,...,T t}, the cutter head propulsion speed v sequence {v1,v2,v3,...,v tWhen the mean value of the excavation operation data of the excavation section with a length of t satisfies the following four basic conditions at the same time, the excavation section is considered to be an effective excavation section; otherwise, it is judged to be an ineffective excavation section and no effective cutting and rock breaking is formed; the four basic conditions are:

[0072]

[0073] In the formula, F f The friction thrust of the cutter disc is measured through an on-site TBM friction propulsion test. The test method is to measure the maximum static friction force when the machine hydraulic system pushes the cutter disc from a stationary state to a speed greater than zero.

[0074] T f is the friction torque value of the cutter disc, which is measured through the on-site TBM torque idling test. The test method is: when the cutter disc speed is set to the maximum rated speed, the maximum torque value during the rotation of the cutter disc is obtained.

[0075] Based on the above formula, the data of each excavation section in the TBM construction process is judged whether it is an effective rock breaking section. The excavation section sequence of the cutter head speed, cutter head thrust, cutter head torque and propulsion speed of the excavation section that does not meet the above conditions is deleted. The TBM construction machinery of the Yinsong Project is an open tunnel boring machine produced by China Railway Equipment Engineering Co., Ltd. Based on the field test data, the maximum friction thrust of the tunnel boring machine is 4000kN, that is, F f =4000kN; the maximum idling torque of the cutter head at the rated maximum speed of 7.6r / min is 200kN·m, that is, T f =200kN·m.

[0076] Preparation of effective on-site excavation section data under different rock mass qualities. The excavation section data of the on-site tunnel boring machine is prepared according to the rock mass quality classification standards to form a database of excavation sections under different rock mass qualities. The effective excavation section data is judged as a criterion, and the effective excavation section sequence that meets the conditions constitutes a database. Based on the above criteria, the effective excavation section of Section 4 of the Yinsong Project is judged, and the change curves of the cutterhead thrust, cutterhead torque, propulsion speed and cutterhead speed in a typical effective excavation section are obtained as follows: Figure 2 As shown in the figure, the relevant parameter variation curves in the typical invalid excavation section are as follows: Figure 3 shown.

[0077] Step 3-2: Internal segmentation of the tunneling section

[0078] The complete excavation process of the tunneling section is a process in which the thrust, torque and penetration of the TBM cutter head gradually increase from zero to stable rock breaking and cutting under the action of the propulsion system, and then decrease to zero after reaching the maximum stroke. The internal parameters of the tunneling section are composed of four parts: idling section, loading section, stable section and unloading section.

[0079] Based on the bidirectional sliding window method of kernel density estimation, each effective excavation section of each type of surrounding rock is divided into loading section, stable section and unloading section.

[0080] like Figure 3 As shown in the figure, a method for segmenting the internal stages of the effective excavation section based on a bidirectional sliding window of kernel density estimation is shown in the figure. The principle of bidirectional sliding segmentation is shown in the figure. Figure 4 As shown, it preferably includes the following steps.

[0081] Step 3-2A, identify the loading segment starting index value Index1

[0082] The starting point of the loading section refers to the node where the cutter disc initially penetrates the rock mass and then effectively cuts the rock mass. When the cutter disc reaches the starting point of the loading section, the propulsion system must overcome its own gravity and rock breaking resistance, the cutter disc torque must exceed the idling torque, and the penetration rate must be greater than zero. Therefore, the first data index value that meets the above three conditions at the same time corresponds to the starting point index value of the loading section.

[0083] The excavation operation data of the effective excavation section A is traversed in the order of excavation time, and the first time index value of the excavation operation data that satisfies the following Index1 calculation formula is recorded as the loading section starting point index value Index1; then the Index1 calculation formula is:

[0084] Index1 = argfirst(And(F > F f ,T>F f ,v>0))

[0085] An investigation was conducted on the cutterhead propulsion resistance in the Yinsong and Yinchojiliao projects, and the value was 4000kN. Therefore, the value corresponding to the first data in the excavation section that meets the following conditions at the same time is the starting point of the loading section.

[0086] Index1=argfirst(And(F>4000,T>200,v>0))

[0087] The above formula is used to identify the starting point of the loading phase in a typical effective excavation section in Section 4 of the Yinsong Project. Figure 3 As shown, the excavation section is judged according to the above conditions to obtain the starting point of the excavation section at the position of Index1=180s.

[0088] Step 3-2B, probability density estimation of the cutterhead advancement speed: perform kernel density estimation on the cutterhead advancement speed of the effective excavation section A to obtain the probability density curve of the cutterhead advancement speed.

[0089] The curve is obtained by kernel density estimation of the advancement speed of the representative excavation section of the Yinsong Project, such as Figure 3 As shown in the figure on the right.

[0090] Assume that the effective excavation section A has t cutterhead advancement speeds, which are: x1, x2, ..., x t , the probability density of the cutterhead advancement speed is estimated to be The calculation formula is:

[0091]

[0092] Where K(x) represents the Gaussian kernel function; h is the bandwidth, which is a parameter that determines the smoothness of the overall probability density function of f(x). The smaller the bandwidth, the weaker the smoothness of the probability density curve. The Gaussian kernel function is used in the present invention, and the cutter head propulsion speed is used as the index of density estimation to estimate the probability density, and its bandwidth size h = 2mm / min.

[0093] Step 3-2C, obtain the maximum probability density of the cutterhead advancement speed: find out the maximum probability density v of the cutterhead advancement speed in the stable section of the effective excavation section A from the probability density curve of the cutterhead advancement speed. max .

[0094] For the Yinsong Project, the advancement speed value corresponding to the peak position of the probability density is 70mm / min.

[0095] Step 3-2D, identify the stable segment starting point index value Index2

[0096] The forward sliding window method is used to traverse from the starting point of the effective excavation section A to the end point, and the cutter head advancement speed and v are determined in turn. max For comparison, that is:

[0097] Index2=argfirst(v≥v max )

[0098] When the cutter head advance speed equals or exceeds v for the first time max The time index value corresponding to the time is the index value Index2 of the starting point of the stable segment.

[0099] For the Yinsong Project, the first time index value that meets the following conditions is the starting point of the stable excavation section:

[0100] Index2 = argfirst(v≥70)

[0101] The result shows that when the current excavation section is excavated to the 580s position, the advancement speed value of the excavation section exceeds 70mm / min for the first time, so the time index value position of the starting point of the stable section of the excavation section is Index2=580s.

[0102] Step 3-2E, identify the index value of the unloading section starting point Index3: The unloading section starting point is also the end point of the stable section. The reverse sliding window method is used to traverse from the end point of the effective excavation section A to the starting point, and the cutter head advancement speed and v are determined in turn. max When the cutter head advance speed equals or exceeds v for the first time max The time index value corresponding to the time is the starting index value Index3 of the unloading segment.

[0103] For the Yinsong project, the time when the propulsion speed value first exceeds 70mm / min is at 1950s. Figure 3 As shown, the time index value position of the unloading section starting point of the excavation section is obtained as Index3 = 1950s.

[0104] Step 3-2F, stage division: the effective excavation section A between the starting index value Index1 of the loading section and the starting index value Index2 of the stable section is recorded as the loading section; the effective excavation section A between the starting index value Index2 of the stable section and the starting index value Index3 of the unloading section is recorded as the stable section; the effective excavation section A between the starting index value Index3 of the unloading section and the end point is recorded as the unloading section.

[0105] The excavation segment data are segmented and stored independently according to the identified index values ​​of the loading segment start point, the stable excavation segment start point and the unloading segment start point. The above steps are repeated to segment the collected effective excavation segment data under different surrounding rock conditions into loading segment, stable excavation segment and unloading segment data sets.

[0106] For the Yinsong Project, the time index values ​​of the starting point of the loading section, the starting point of the stable section, and the starting point of the unloading section in this tunneling section are 180s, 580s, and 1950s, respectively. The data of different tunneling parameters in this tunneling section between 181s and 580s, 581s and 1950s, and 1951 and 2200s are retrieved according to the above index values. The data after internal segmentation is as follows Figure 5 As shown, the segmented data are stored in three separate CSV files. Repeat the above steps to segment the effective rock breaking excavation section data under different surrounding rock conditions of Yinsong Project into loading section, stable excavation section and unloading section data.

[0107] Step 3-3, extracting the operating parameters of the loading section: extracting the operating parameters of each loading section of each surrounding rock type.

[0108] Step 3-4, calculate the average thrust of the cutterhead in the stable section: for each stable section under each surrounding rock type, calculate the average thrust of the cutterhead in the stable section.

[0109] The rock mass index adopts the empirical index that can reflect the difficulty of rock mass excavation, which includes the field penetration index and the torque penetration index. The thrust penetration index is the linear fitting slope a and thrust intercept b between the single-knife thrust and penetration in the loading stage; the torque penetration index is the linear fitting slope TPI of the single-knife torque and penetration in the loading stage. The rock mass index under different working conditions is obtained by linearly fitting the single-knife thrust and penetration, single-knife torque and penetration in the loading section under different working conditions.

[0110] The operating parameters extract the cutterhead speed and thrust speed in the loading section of the tunneling section. On this basis, the rock mass index, operating parameters and thrust value of each effective tunneling section loading section are assembled to form a thrust prediction model database, and its matrix form is [n, v, a, b, TPI, F]. Similarly, the extracted parameters and prediction parameters of the loading section under different working conditions are assembled to obtain the following initial model training database for a total of m tunneling sections.

[0111]

[0112] Step 4: training the cutterhead thrust prediction model: using the model training sample library constructed in step 3, the cutterhead thrust prediction model of the corresponding surrounding rock type constructed in step 2 is trained, thereby obtaining N cutterhead thrust prediction models trained for different surrounding rock types.

[0113] 80% of the data under each working condition is randomly selected as the training set, and the remaining 20% ​​is used as the test set. Then, the training set data is input into the neural network for training.

[0114] Step 5: Select a cutterhead thrust prediction model: Determine the surrounding rock type at the tunneling site, and select a trained cutterhead thrust prediction model with the same surrounding rock type as determined in step 4.

[0115] Step 6: Tunnel excavation: The thrust prediction model is deployed to the intelligent excavation platform in the main control room of the on-site tunnel boring machine, and the TBM performs the construction of the loading section 1 of the tunnel to be excavated.

[0116] Step 7, extracting the operating parameters of loading section 1: operate the loading section 1 of step 6 and extract the rock mass index parameters to obtain the operating parameter vector of loading section 1 [n′, v′, a′, b′, TPI′].

[0117] Taking the prediction of the on-site cutterhead thrust at the pile number 51735.28 of the fourth section of the Yinsong Project as an example, the rock mass parameters were extracted from the loading section data. The single-cutter thrust and penetration slope a'=5.44, the intercept initial penetration thrust b'=88.89, and the torque penetration coefficient TPI'=1.32.

[0118] Step 8: Predict the average thrust of the cutterhead in the stable section: Substitute the loading section operation parameter vector [n′, v′, a′, b′, TPI′] obtained in step 7 into the trained cutterhead thrust prediction model selected in step 5 to predict the average thrust of the cutterhead in the stable section of the tunnel to be excavated.

[0119] For the pile number 51735.28 of the fourth section of the Yinsong Project, the operating parameter vector of the loading section 1 is input into the thrust prediction model to obtain the predicted thrust and actual thrust values ​​as shown in the figure below: Figure 6 and Figure 7 As shown in the figure, the average percentage error between the actual value and the predicted value of the thrust of the excavation section is 5.34%, and the root mean square error is 8.94; the prediction results show that the established prediction model can accurately predict the cutterhead thrust during the construction process.

[0120] The bidirectional sliding traversal method based on kernel density estimation can significantly improve the efficiency of data segmentation, and proposes a feature extraction method for the corresponding section based on the data characteristics of different stages. It can also achieve high accuracy for data with similar change trends, and has a wide range of applications. By extracting the rock mass quality indicators of the loading section data and the operating parameters of the stable excavation section, a cutterhead thrust prediction model is established and applied in engineering, realizing real-time and high-precision prediction of the cutterhead thrust during TBM construction. The prediction results can provide guidance for the setting of operating parameters for on-site machine drivers, thereby improving the excavation efficiency of tunnel boring machines.

[0121] The preferred embodiments of the present invention are described in detail above; however, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. A method for extracting features of TBM excavation section and predicting cutterhead thrust based on kernel density estimation, characterized by: The steps include: Step 1: Classification of surrounding rocks: Classify surrounding rocks into N types according to rock strength, integrity, structural surface state, occurrence and groundwater conditions; Step 2, construct a cutterhead thrust prediction model: A cutterhead thrust prediction model based on a neural network is constructed for each surrounding rock type; the input layer of the cutterhead thrust prediction model is the loading section operation and rock mass index parameter vector [n, v, a, b, TPI] of the TBM construction process, and the output layer is the average cutterhead thrust prediction value F of the stable section; n is the cutterhead speed in the loading section; v is the TBM advancement speed in the loading section; a is the slope of the fitting curve of the single cutter thrust and penetration in the loading section; b is the initial penetration thrust of the roller cutter in the loading section; TPI is the linear fitting slope of the single cutter torque and penetration in the loading section; Step 3: Build a model training sample library, which includes the following steps: Step 3-1, collect effective excavation section data: collect effective excavation section data of all types of surrounding rock in step 1; wherein the number of effective excavation sections of each type of surrounding rock is not less than M; M ≥ 100; Step 3-2, segmentation of internal stages of the excavation section: Based on the two-way sliding window method of kernel density estimation, each effective excavation section of each type of surrounding rock is segmented into a loading section, a stable section, and an unloading section; Step 3-3, extracting loading section operation and rock mass index parameters: extracting operation parameters for each loading section of each type of surrounding rock; Step 3-4, calculate the average thrust of the cutterhead in the stable section: for each stable section of each type of surrounding rock, calculate the average thrust of the cutterhead in the stable section; Step 4, training the cutterhead thrust prediction model: using the model training sample library constructed in step 3, training the cutterhead thrust prediction model of the corresponding surrounding rock type constructed in step 2, thereby obtaining N trained cutterhead thrust prediction models; Step 5: Select a cutterhead thrust prediction model: determine the surrounding rock type at the tunneling site, and select a trained cutterhead thrust prediction model with the same surrounding rock type as determined in step 4; Step 6: Tunnel excavation: The TBM performs the construction of the loading section 1 of the tunnel to be excavated; Step 7, extracting the operation parameters of the loading section 1: extracting the operation parameters of the loading section 1 in step 6, and obtaining the operation and rock mass index parameter vector [n′, v′, a′, b′, TPI′] of the loading section 1; Step 8, predict the average thrust of the cutterhead in the stable section: substitute the loading section operation parameter vector [n′, v′, a′, b′, TPI′] obtained in step 7 into the trained cutterhead thrust prediction model selected in step 5 to perform prediction and obtain the average thrust F′ of the cutterhead in the stable section of the tunnel to be excavated.

2. The method for extracting features of TBM excavation sections and predicting cutterhead thrust based on kernel density estimation according to claim 1 is characterized in that: In step 1, according to the national standard "Specification for Geological Investigation of Water Conservancy and Hydropower Engineering GB50487-2008", the surrounding rock is divided into N=5 types, namely, Class I, II, III, IV and V surrounding rock.

3. The method for extracting features of TBM excavation section and predicting cutterhead thrust based on kernel density estimation according to claim 1 is characterized in that: In step 3-1, the effective excavation section refers to the process in which the TBM driver turns on the cutterhead motor current switch to make the cutterhead run at the specified rotation speed n, and adjusts the control parameters so that the cutterhead thrust and cutterhead torque cut the rock mass while overcoming its own friction and idling resistance to form the designed excavation surface; therefore, the method for determining the effective excavation section includes the following steps: Step 3-1A, TBM excavation: The TBM excavates the tunnel and monitors the excavation operation data according to the set data sampling interval, thereby obtaining a number of excavation sections. The excavation operation data of each excavation section includes the cutterhead speed n, the cutterhead propulsion speed v, the cutterhead thrust F and the cutterhead torque T; Step 3-1B, calculate the mean of the excavation section operation parameters: calculate the mean of each excavation operation data of each excavation section; then the mean of the excavation operation data of any excavation section is: the mean of the cutter head speed Mean cutting head advancement speed Mean thrust of cutter head and the mean torque of the cutter head Step 3-1C, determine the effective excavation section: when the excavation operation data mean of a certain excavation section meets the following four basic conditions at the same time, the excavation section is considered to be an effective excavation section; otherwise, it is judged to be an ineffective excavation section and no effective cutting and rock breaking is formed; the four basic conditions are: In the formula, F f is the friction thrust of the cutter disc; T f is the friction torque value of the cutter disc.

4. The method for extracting features of TBM excavation sections and predicting cutterhead thrust based on kernel density estimation according to claim 3 is characterized in that: In step 3-1C, the friction thrust F f , measured through an on-site TBM friction propulsion test. The test method is: measuring the maximum static friction force when the machine hydraulic system pushes the cutter head from a standstill to a speed greater than zero.

5. The method for extracting features of TBM excavation section and predicting cutterhead thrust based on kernel density estimation according to claim 3 is characterized in that: In step 3-1C, the friction torque value of the cutter head is T f , measured through the on-site TBM torque idling test. The test method is: when the cutter head speed is set to the maximum rated speed, the maximum torque value during the cutter head rotation process.

6. The method for extracting features of TBM excavation sections and predicting cutterhead thrust based on kernel density estimation according to claim 3 is characterized in that: In step 3-2, the method for segmenting the internal stages of the effective excavation section based on the bidirectional sliding window of kernel density estimation includes the following steps: Step 3-2A, identify the loading section starting point index value Index1: traverse the excavation operation data of the effective excavation section A in the order of excavation time; record the first time index value of the excavation operation data that satisfies the following Index1 calculation formula as the loading section starting point index value Index1; then the Index1 calculation formula is: Step 3-2B, probability density estimation of the cutterhead advancement speed: perform kernel density estimation on the cutterhead advancement speed of the effective excavation section A to obtain a probability density curve of the cutterhead advancement speed; Step 3-2C, obtain the maximum probability density of the cutterhead advancement speed: find out the maximum probability density v of the cutterhead advancement speed in the stable section of the effective excavation section A from the probability density curve of the cutterhead advancement speed. max ; Step 3-2D, identify the index value of the starting point of the stable segment Index2: Use the forward sliding window method to traverse from the starting point of the effective excavation segment A to the end point, and determine the cutter head advancement speed and v in turn. max When the cutter head advance speed equals or exceeds v for the first time max The time index value corresponding to the time is the index value Index2 of the starting point of the stable segment; Step 3-2E, identify the index value of the unloading section starting point Index3: Use the reverse sliding window method to traverse from the end point of the effective excavation section A to the starting point, and determine the cutter head advancement speed and v in turn. max When the cutter head advance speed equals or exceeds v for the first time max The time index value corresponding to the time is the index value Index3 of the starting point of the unloading segment; Step 3-2F, stage division: the effective excavation section A between the starting index value Index1 of the loading section and the starting index value Index2 of the stable section is recorded as the loading section; The effective excavation section A between the starting index value Index2 of the stable section and the starting index value Index3 of the unloading section is recorded as the stable section; the effective excavation section A between the starting index value Index3 of the unloading section and the end point is recorded as the unloading section.

7. The method for extracting features of TBM excavation section and predicting cutterhead thrust based on kernel density estimation according to claim 6 is characterized in that: In step 3-2B, assume that the effective excavation section A has t cutterhead advancement speeds, which are: x1, x2, ..., x t , the probability density of the cutterhead advancement speed is estimated to be The calculation formula is: Where K(x) represents the Gaussian kernel function and h is the bandwidth.

8. The method for extracting features of TBM excavation sections and predicting cutterhead thrust based on kernel density estimation according to claim 7 is characterized in that: The cutter head advancing speed is used as the index of density estimation, and its bandwidth size is h=2mm / min.

9. The method for extracting features of TBM excavation section and predicting cutterhead thrust based on kernel density estimation according to claim 1 is characterized in that: In step 2, the loss function of the cutterhead thrust prediction model is the root mean square error.

10. The method for extracting features of TBM excavation section and predicting cutterhead thrust based on kernel density estimation according to claim 1 is characterized in that: In step 2, the cutterhead thrust prediction model adopts a 5-fully-connected hidden layer structure; 80% of the model training sample library constructed in step 3 is used as a training set, and 20% is used as a test set.

Images