Design method of tunnel portal mileage

Abstract

The application discloses a tunnel portal mileage design method, relates to the technical field of tunnel design, and discloses a tunnel portal mileage design method, which comprises the following steps: determining cross section characteristic information of each mileage according to tunnel design information of a to-be-predicted tunnel; classifying each mileage according to a potential portal mileage range of the to-be-predicted tunnel, and determining a plurality of potential mileages; performing feature masking on the cross section characteristic information of each mileage according to each potential mileage, and determining a feature sequence; inputting the feature sequence into a portal mileage prediction model to determine a portal mileage relative position; and determining the portal mileage according to the portal mileage relative position. Through the above method, the design efficiency, design accuracy and automation degree of the portal mileage are improved, the portal mileage is designed by using a unified and explicit standard, and the influence of the subjectivity of technical personnel on the design result is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tunnel design, in particular to a design method of a tunnel portal mileage. BACKGROUND

[0002] In the design of a tunnel portal, the selection of a portal mileage has an important influence on the construction efficiency and safety of the tunnel portal. At present, the selection of a tunnel portal mileage depends on manual design in two-dimensional horizontal and vertical sections. The main process is as follows: (1) selecting a specific mileage within the design mileage range as a potential portal mileage; (2) drawing the horizontal and vertical section diagrams corresponding to the mileage; (3) observing the relative position of the tunnel and the ground on the horizontal and vertical section diagrams and judging whether the mileage is suitable as a portal mileage; and (4) repeating the above steps until a suitable portal mileage is found. The existing design of a tunnel portal mileage is a process of repeated selection, and the design method highly depends on the experience of the designer, without a unified standard, and the design precision based on two-dimensional dimensions is low, so an automatic calculation method is needed to improve the efficiency and precision of the design of a tunnel portal mileage.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a design method of a tunnel portal mileage, aiming to solve the technical problem that the prior art lacks an automatic calculation method to improve the efficiency and precision of the design of a tunnel portal mileage.

[0005] To achieve the above purpose, the present application provides a design method of a tunnel portal mileage, which comprises:

[0006] determining the horizontal section feature information of each mileage within the portal design range according to the tunnel design information of a to-be-predicted tunnel;

[0007] classifying each mileage according to the potential portal mileage range of the to-be-predicted tunnel, and determining a plurality of potential mileages;

[0008] performing feature masking on the horizontal section feature information of each mileage according to each potential mileage, and determining a feature sequence of the to-be-predicted tunnel according to the masking result;

[0009] performing position prediction according to the feature sequence and a portal mileage prediction model, and determining a portal mileage relative position;

[0010] determining the portal mileage of the to-be-predicted tunnel according to the portal mileage relative position.

[0011] In an embodiment, before the determination of the horizontal section feature information of each mileage within the portal design range according to the tunnel design information of the to-be-predicted tunnel, the method further comprises:

[0012] determine a light-dark demarcation mileage and a design boundary mileage of the tunnel to be predicted according to tunnel design information of the tunnel to be predicted;

[0013] determine an entrance design range of the tunnel to be predicted according to the light-dark demarcation mileage and the design boundary mileage;

[0014] divide the entrance design range by mileage according to a preset division interval to obtain a plurality of mileages in the entrance design range.

[0015] In an embodiment, the determination of the cross-section feature information of each mileage in the entrance design range according to the tunnel design information of the tunnel to be predicted comprises:

[0016] determine a light-dark demarcation mileage, a design boundary mileage and a design boundary mileage coordinate of the tunnel to be predicted according to tunnel design information of the tunnel to be predicted;

[0017] determine a cross-section interval of each mileage according to the light-dark demarcation mileage, the design boundary mileage and the number of mileages in the entrance design range;

[0018] determine a cross-section mileage value of each mileage according to the cross-section interval of each mileage and the light-dark demarcation mileage;

[0019] determine a center point height of each mileage by height calculation according to the cross-section mileage value of each mileage, an axis direction vector, the design boundary mileage and the design boundary mileage coordinate;

[0020] determine a cross-section feature information of each mileage by feature value calculation according to the center point height of each mileage and terrain point cloud data.

[0021] In an embodiment, before the classification of each mileage according to the potential entrance mileage range of the tunnel to be predicted and the determination of a plurality of potential mileages, the method further comprises:

[0022] determine an opening number, a tunnel entrance type, a light-dark demarcation mileage and a mileage selection direction of the tunnel to be predicted according to tunnel design information of the tunnel to be predicted;

[0023] determine a potential entrance length of the tunnel to be predicted according to an entrance design criterion, the opening number and the tunnel entrance type;

[0024] determine a potential entrance mileage range of the tunnel to be predicted by range calculation according to the potential entrance length, the light-dark demarcation mileage and the mileage selection direction.

[0025] In an embodiment, the feature masking of the cross-section feature information of each mileage according to each potential mileage, and the determination of the feature sequence of the tunnel to be predicted according to the masking result, comprises:

[0026] determining the masking mileage in the plurality of mileages according to each potential mileage;

[0027] masking the cross-section feature information of each masking mileage according to the preset feature value, to obtain the masking feature information of each masking mileage;

[0028] constructing the feature sequence of the tunnel to be predicted according to the masking feature information of each masking mileage and the cross-section feature information of each potential mileage.

[0029] In an embodiment, before the position prediction and the determination of the relative position of the portal mileage according to the feature sequence and the portal mileage prediction model, the method further comprises:

[0030] determining the cross-section feature information of each sample mileage within the portal design range of each sample construction tunnel according to the sample design information of each sample construction tunnel in the sample tunnel portal data set;

[0031] classifying each sample mileage within the portal design range of each sample construction tunnel according to the potential portal mileage range of each sample construction tunnel, to determine a plurality of sample potential mileages of each sample construction tunnel;

[0032] masking the cross-section feature information of each sample mileage corresponding to each sample construction tunnel according to each sample potential mileage corresponding to each sample construction tunnel, and determining the sample feature sequence of each sample construction tunnel according to the masking result;

[0033] model training according to the sample feature sequence of each sample construction tunnel and the actual portal mileage of each sample construction tunnel, to obtain the portal mileage prediction model.

[0034] In an embodiment, the model training according to the sample feature sequence of each sample construction tunnel and the actual portal mileage of each sample construction tunnel, to obtain the portal mileage prediction model, comprises:

[0035] distance conversion according to the bright-dark boundary mileage, the design boundary mileage and the actual portal mileage of each sample construction tunnel, to obtain the relative position of the portal mileage of each sample construction tunnel;

[0036] standardization processing of the sample feature sequence of each sample construction tunnel, to obtain the standard feature sequence of each sample construction tunnel;

[0037] model training according to the standard feature sequence of each sample construction tunnel and the relative position of the portal mileage, to obtain the portal mileage prediction model.

[0038] Further, in order to achieve the above object, the present application also provides a tunnel portal mileage design device, which comprises a processing module, configured to determine cross-section characteristic information of each mileage within a portal design range according to tunnel design information of a to-be-predicted tunnel;

[0039] a classification module, configured to classify each mileage according to a potential portal mileage range of the to-be-predicted tunnel, and determine a plurality of potential mileages;

[0040] The processing module is further configured to perform feature masking on the cross-section characteristic information of each mileage according to each potential mileage, and determine a feature sequence of the to-be-predicted tunnel according to a masking result.

[0041] an input module, configured to perform position prediction according to the feature sequence and a portal mileage prediction model, and determine a portal mileage relative position.

[0042] The processing module is further configured to determine the portal mileage of the to-be-predicted tunnel according to the portal mileage relative position.

[0043] Further, in order to achieve the above object, the present application also provides a tunnel portal mileage design device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the tunnel portal mileage design method as described above.

[0044] Further, in order to achieve the above object, the present application also provides a storage medium, which is a computer readable storage medium, and a computer program is stored on the storage medium, and the computer program is executed by a processor to implement the steps of the tunnel portal mileage design method as described above.

[0045] The application provides a tunnel portal mileage design method. The application determines cross-section characteristic information of each mileage in a portal design range according to tunnel design information of a to-be-predicted tunnel; classifies each mileage according to a potential portal mileage range of the to-be-predicted tunnel, and determines a plurality of potential mileages; performs feature masking on the cross-section characteristic information of each mileage according to each potential mileage, and determines a feature sequence of the to-be-predicted tunnel according to a masking result; performs position prediction according to the feature sequence and a portal mileage prediction model, and determines a portal mileage relative position; and determines the portal mileage of the to-be-predicted tunnel according to the portal mileage relative position. In the foregoing manner, the cross-section characteristic information of each mileage is determined in combination with the tunnel design information of the to-be-predicted tunnel, the cross-section characteristic information of each mileage is masked through the potential mileages in the plurality of mileages, the feature sequence of the to-be-predicted tunnel is obtained, the position prediction is performed according to the feature sequence through the portal mileage prediction model, the portal mileage of the to-be-predicted tunnel is obtained, the design efficiency, design precision, and design automation degree of the portal mileage are improved, and the portal mileage design is performed through a unified and explicit standard, thereby reducing the influence of the subjectivity of technical personnel on the design result. BRIEF DESCRIPTION OF DRAWINGS

[0046] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0048] Figure 1 A flowchart is provided for the tunnel portal mileage design method embodiment one of the present application;

[0049] Figure 2 A feature masking diagram is provided for the tunnel portal mileage design method of the embodiment one of the present application;

[0050] Figure 3 A model structure diagram is provided for the tunnel portal mileage design method of the embodiment one of the present application;

[0051] Figure 4 A flowchart is provided for the tunnel portal mileage design method embodiment two of the present application;

[0052] Figure 5 A feature significance diagram is provided for the tunnel portal mileage design method of the embodiment two of the present application;

[0053] Figure 6 A feature extraction process schematic diagram of the tunnel portal mileage design method provided for Embodiment Two of the present application;

[0054] Figure 7 A process schematic diagram provided for Embodiment Three of the tunnel portal mileage design method of the present application;

[0055] Figure 8 A brief process schematic diagram of the tunnel portal mileage design method provided for Embodiment Three of the present application;

[0056] Figure 9 A topographic contour line schematic diagram of the tunnel portal mileage design method provided for Embodiment Three of the present application;

[0057] Figure 10 A tunnel contour line schematic diagram of the tunnel portal mileage design method provided for Embodiment Three of the present application;

[0058] Figure 11 A loss value change trend schematic diagram of the tunnel portal mileage design method provided for Embodiment Three of the present application;

[0059] Figure 12 A module structure schematic diagram of the tunnel portal mileage design device of the present application;

[0060] Figure 13 A device structure schematic diagram of the hardware running environment involved in the tunnel portal mileage design method in the embodiment of the present application.

[0061] The object implementation, functional features and advantages of the present application will be further explained with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0062] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0063] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the drawings and specific embodiments of the specification.

[0064] The main solution of the embodiment of the present application is: determining the cross-sectional feature information of each mileage within the portal design range according to the tunnel design information of the to-be-predicted tunnel; classifying each mileage according to the potential portal mileage range of the to-be-predicted tunnel, and determining a plurality of potential mileages; performing feature masking on the cross-sectional feature information of each mileage according to each potential mileage, and determining a feature sequence of the to-be-predicted tunnel according to the masking result; performing position prediction according to the feature sequence and a portal mileage prediction model, and determining a portal mileage relative position; and determining the portal mileage of the to-be-predicted tunnel according to the portal mileage relative position.

[0065] At present, the selection of the tunnel portal mileage depends on the manual design in the two-dimensional horizontal and vertical sections. The main process is: (1) selecting a certain mileage in the design mileage range as a potential portal mileage; (2) drawing the horizontal and vertical section maps corresponding to the mileage; (3) observing the relative position of the tunnel and the ground on the horizontal and vertical section maps, and judging whether the mileage is suitable as the portal mileage; (4) repeating the above steps until a suitable portal mileage is found. The above design method has the following defects: 1. The design efficiency is too low. In the prior art, the designer needs to repeatedly observe and compare the relative position of the terrain and the tunnel and the change trend of the terrain of multiple mileages, which is time-consuming and labor-intensive, has low automation degree, and has low design efficiency. 2. The subjectivity is too strong. In the prior art, there is no unified and clear criterion for determining the tunnel portal mileage, which mainly depends on the experience of the designer, and the design result is greatly affected by the subjectivity of the technician. 3. Lack of three-dimensional overall analysis. In the prior art, the tunnel portal mileage is determined by manually observing the two-dimensional information of the relative position of the tunnel and the terrain on the horizontal and vertical sections, which lacks overall three-dimensional information analysis and is difficult to obtain the optimal solution.

[0066] The present application determines the horizontal section feature information of each mileage by combining the tunnel design information of the tunnel to be predicted, and masks the horizontal section feature information of each mileage by the potential mileage in multiple mileages to obtain the feature sequence of the tunnel to be predicted. The portal mileage is predicted by the portal mileage prediction model according to the feature sequence to obtain the portal mileage of the tunnel to be predicted, which improves the design efficiency, design accuracy and automation degree of the portal mileage, and realizes the portal mileage design by a unified and clear standard, and reduces the influence of the subjectivity of the technician on the design result.

[0067] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a tunnel portal mileage design device, etc. The tunnel portal mileage design device is taken as an example to illustrate the present embodiment and the following embodiments.

[0068] Based on this, the present application provides a tunnel portal mileage design method, which is described with reference to Figure 1 , Figure 1 The flowchart of the first embodiment of the tunnel portal mileage design method of the present application is shown.

[0069] In the present embodiment, the method comprises steps S10-S50:

[0070] Step S10, determining the horizontal section feature information of each mileage in the portal design range according to the tunnel design information of the tunnel to be predicted;

[0071] It should be noted that the tunnel to be predicted refers to the tunnel that needs to be designed for the opening mileage, and the tunnel design information includes but is not limited to the bright-dark boundary mileage, the size and axis position of the tunnel, the design boundary mileage of the tunnel opening, the number of openings, and the type of portal, and the like. The cross-section characteristic information refers to the characteristic information of the cross-section corresponding to each mileage. The cross-section characteristic information includes a plurality of characteristic values, which are calculated based on the opening design range and the terrain point cloud data of the tunnel, and the cross-section characteristic information of each mileage can be obtained.

[0072] It can be understood that in the embodiment, the cross-section characteristic information of each mileage includes two characteristic values, which are the relative height difference between the terrain and the left and right retaining walls on the cross-section corresponding to each mileage, which reflects the relative position of the terrain and the tunnel.

[0073] In a possible implementation, before step S10, steps A11-A13 can also be included:

[0074] Step A11, determining the bright-dark boundary mileage and the design boundary mileage of the tunnel to be predicted according to the tunnel design information of the tunnel to be predicted;

[0075] Step A12, determining the opening design range of the tunnel to be predicted according to the bright-dark boundary mileage and the design boundary mileage;

[0076] Step A13, dividing the mileage of the opening design range according to a preset division interval to obtain a plurality of mileages in the opening design range.

[0077] It should be noted that the design boundary mileage refers to the design boundary mileage of the tunnel opening. For the entrance design boundary mileage, it refers to the design starting mileage; and for the exit design boundary mileage, it refers to the design termination mileage. In the embodiment, the range from the bright-dark boundary mileage to the design boundary mileage of the tunnel opening is the opening design range. In order to represent the relative position characteristics of the terrain and the tunnel in the opening range subsequently, N equally spaced mileages are reselected as representatives in the opening design range according to a preset division interval. The N equally spaced mileages reselected are the plurality of mileages in the opening design range.

[0078] In the embodiment, the bright-dark boundary mileage and the design boundary mileage of the tunnel to be predicted are determined according to the tunnel design information of the tunnel to be predicted; the opening design range of the tunnel to be predicted is determined according to the bright-dark boundary mileage and the design boundary mileage; and the mileage of the opening design range is divided according to a preset division interval to obtain a plurality of mileages in the opening design range. Through the above manner, a foundation is laid for subsequent feature extraction.

[0079] Step S20, classifying each mileage according to the potential portal mileage range of the tunnel to be predicted, and determining a plurality of potential mileages;

[0080] It should be noted that different tunnel portal types have different requirements for portal length, and in the embodiment, the portal type is used as an intermediate variable to establish the association criterion, the potential portal length of the tunnel to be predicted is determined through the association criterion, and the potential tunnel portal mileage selection range is determined based on the potential portal mileage and the light-dark boundary mileage. In the embodiment, the potential portal mileage range refers to the potential tunnel portal mileage selection range.

[0081] It can be understood that each mileage is compared with the potential portal mileage range respectively to determine whether each mileage is within the potential portal mileage range. If yes, the mileage is taken as a potential mileage, and if not, the mileage is taken as a masking mileage that needs to be masked.

[0082] In a feasible implementation, before step S20, steps B11-B13 can also be included:

[0083] Step B11, determining the number of openings, the tunnel portal type, the light-dark boundary mileage, and the mileage selection direction of the tunnel to be predicted according to the tunnel design information of the tunnel to be predicted;

[0084] Step B12, determining the potential portal length of the tunnel to be predicted according to the portal design criterion, the number of openings, and the tunnel portal type;

[0085] It should be noted that under different tunnel working conditions, the relationship between the tunnel length and the number of openings is different, but the general rule can be determined by the following formula That is, as long as the critical value under the corresponding working condition is given, the deterministic relationship between the tunnel length and the number of openings can be determined. Wherein, T is the tunnel length, n k is the number of openings, a, b, c, d are critical length parameters.

[0086] It can be understood that since different tunnel portal types have different requirements for portal length, the portal type is used as an intermediate variable to establish the association criterion. The potential portal length selection range rules for different numbers of openings proposed in the embodiment are shown in Table 1. For different numbers of openings, considering all portal types, all available portal lengths under each portal type are given, and all available lengths of all portal types are de-duplicated, that is, the potential portal length under the opening is obtained. In the embodiment, the available lengths a, b,..., n of different portal types under each opening number shown in the table are only simple examples for easy understanding and have no other meanings. The available lengths of each opening number and each portal type can be determined according to the actual situation of tunnel design.

[0087] Table 1

[0088]

[0089] In a specific implementation, the tunnel portal design criterion refers to a potential tunnel portal length selection range rule of different opening numbers. After the opening number of the to-be-predicted tunnel and the tunnel portal type are determined, the potential tunnel portal length corresponding to the to-be-predicted tunnel can be determined by searching and deduplicating according to the tunnel portal design criterion.

[0090] In step B13, the potential tunnel portal mileage range of the to-be-predicted tunnel is determined by range calculation according to the potential tunnel portal length, the light-dark boundary mileage, and the mileage selection direction.

[0091] It should be noted that for an entrance, the direction of mileage selection is the direction from the light-dark boundary mileage to the design boundary mileage, and at this time, the direction of mileage selection is a decreasing mileage direction; for an exit, the direction of mileage selection is the direction from the light-dark boundary mileage to the design boundary mileage, and at this time, the direction of mileage selection is an increasing mileage direction. The range from the light-dark boundary mileage to the design boundary mileage is the potential tunnel portal mileage range.

[0092] In this embodiment, the opening number, the tunnel portal type, the light-dark boundary mileage, and the mileage selection direction of the to-be-predicted tunnel are determined according to the tunnel design information of the to-be-predicted tunnel; the potential tunnel portal length of the to-be-predicted tunnel is determined according to the tunnel portal design criterion, the opening number, and the tunnel portal type; and the potential tunnel portal mileage range of the to-be-predicted tunnel is determined by range calculation according to the potential tunnel portal length, the light-dark boundary mileage, and the mileage selection direction. Through the above manner, the potential tunnel portal mileage range of the to-be-predicted tunnel can be determined, which lays a foundation for subsequent design of the tunnel portal mileage.

[0093] In step S30, the cross-section feature information of each mileage is feature-masked according to each potential mileage, and the feature sequence of the to-be-predicted tunnel is determined according to the masking result.

[0094] It should be noted that since the cross-section feature information of each mileage contains feature values f1 and f2 corresponding to two features, the cross-section feature values of each mileage are sequentially sorted along the mileage selection direction to form a feature value sequence {(f 11 ,f 12 ),...,(f 1N ,f 2N )}, and the shape is N x 2.

[0095] It can be understood that for the feature value sequence, the cross-section feature values corresponding to the mileages other than the potential mileages are masked, and the feature sequence is the feature value sequence after masking.

[0096] In a possible implementation, step S30 can further include steps C11-C13.

[0097] Step C11: determining a cover mileage in the plurality of mileages according to each potential mileage;

[0098] It should be noted that the mileage other than the potential mileage in the plurality of mileages is the cover mileage.

[0099] Step C12: performing feature covering on the cross-section feature information of each cover mileage according to a preset feature value to obtain cover feature information of each cover mileage;

[0100] It should be noted that in the cross-section feature information of each cover mileage, the corresponding cross-section feature value is replaced by the preset feature value, so as to obtain the cover feature information of each cover mileage. In this embodiment, the preset feature value is set to 0, and can also be set to other values according to requirements, which is not limited in this embodiment.

[0101] Step C13: constructing the feature sequence of the tunnel to be predicted according to the cover feature information of each cover mileage and the cross-section feature information of each potential mileage.

[0102] It should be noted that the cross-section feature information of each potential mileage and the cover feature information of each cover mileage both include two cross-section feature values, and the cross-section feature values of each potential mileage and the cover feature information of each cover mileage are sequentially sorted along the mileage selection direction, so as to obtain the feature sequence of the tunnel to be predicted.

[0103] It can be understood that the cross-section feature values of each mileage can also be sequentially sorted along the mileage selection direction to form a feature value sequence {(f 11 ,f 12 ),...,(f 1N ,f 2N )}, and then the cross-section feature values corresponding to the cover mileage in the feature value sequence are covered, so as to obtain the feature sequence. The principle diagram of feature covering is shown in FIG. 4. Figure 2 Figure 2 The non-potential hole mileage in FIG. 3 is the cover mileage, and the data corresponding to the non-potential hole mileage is regarded as invalid. In order to maintain the consistency of the feature length of each tunnel, the feature corresponding to the non-potential hole mileage is set to 0.

[0104] ​The embodiment determines a plurality of hidden mileages according to each potential mileage; performs feature hiding on cross-section feature information of each hidden mileage according to a preset feature value, to obtain hidden feature information of each hidden mileage; and constructs a feature sequence of the tunnel to be predicted according to the hidden feature information of each hidden mileage and the cross-section feature information of each potential mileage. In this way, the cross-section feature information corresponding to the non-potential portal mileage is hidden, and the feature sequence is constructed based on the hidden cross-section feature information, so that the accuracy and efficiency of subsequent portal mileage prediction are ensured.

[0105] Step S40: performing position prediction according to the feature sequence and a portal mileage prediction model, to determine a portal mileage relative position;

[0106] It should be noted that the portal mileage prediction model is a deep learning model mainly based on LSTM (Long Short Term Memory), and all training parameters in the network are optimized based on a classic Adam algorithm. A structure diagram of the portal mileage prediction model is shown in FIG. 2, in which an LSTM layer, a Dropout layer, an LSTM layer, a Dropout layer, an LSTM layer, a Dropout layer, a full connection layer, and an output layer are sequentially connected. The portal mileage prediction model is obtained by training a deep learning model based on a large number of feature sequences of designed and constructed tunnels and actual portal mileage relative positions. Figure 3

[0107] It can be understood that the feature sequence is standardized according to a formula x' = (x-u) / σ. The standardized feature value is beneficial to improving the convergence speed of the model.

[0108] In a specific implementation, after the feature sequence of the tunnel to be predicted after the standardization is input into the portal mileage prediction model, the portal mileage prediction model outputs a portal mileage relative position of the tunnel to be predicted.

[0109] Step S50: determining the portal mileage of the tunnel to be predicted according to the portal mileage relative position.

[0110] It should be noted that when the portal mileage of the tunnel to be predicted is selected for a tunnel entrance, the portal mileage relative position is converted according to a formula m' = m-m. y b y (m b -m s ) to obtain an absolute distance of the tunnel portal mileage; and when the portal mileage of the tunnel to be predicted is selected for a tunnel exit, the portal mileage relative position is converted according to a formula m' = m+m. y b ​​​​​y (m e -m b ) is converted to obtain the absolute distance of the tunnel portal mileage, wherein m y , m' y are the relative position and the absolute distance of the tunnel portal mileage respectively; m b is the light-dark boundary mileage; m s , m e are the design start mileage and the design end mileage respectively. In the embodiment, after obtaining the absolute distance of the tunnel portal mileage, the portal mileage of the tunnel to be predicted can be obtained.

[0111] The embodiment provides a design method of a tunnel portal mileage. The method of the embodiment determines cross-section characteristic information of each mileage in a portal design range according to tunnel design information of a tunnel to be predicted; classifies each mileage according to a potential portal mileage range of the tunnel to be predicted, and determines a plurality of potential mileages; performs feature masking on the cross-section characteristic information of each mileage according to each potential mileage, and determines a feature sequence of the tunnel to be predicted according to a masking result; performs position prediction according to the feature sequence and a portal mileage prediction model, and determines a portal mileage relative position; and determines the portal mileage of the tunnel to be predicted according to the portal mileage relative position. In the above manner, the cross-section characteristic information of each mileage is determined in combination with the tunnel design information of the tunnel to be predicted, the cross-section characteristic information of each mileage is masked through the potential mileages in the plurality of mileages, the feature sequence of the tunnel to be predicted is obtained, the position prediction is performed according to the feature sequence through the portal mileage prediction model, the portal mileage of the tunnel to be predicted is obtained, the design efficiency, the design precision and the automation degree of design of the portal mileage are improved, the portal mileage design is implemented through a unified and explicit standard, and the influence of the subjectivity of a technical personnel on the design result is reduced.

[0112] Based on the first embodiment of the application, in the second embodiment of the application, the same or similar contents as the above-mentioned first embodiment can be referred to the above introduction, and will not be described in detail. On this basis, please refer to Figure 4 , step S10, the design method of the tunnel portal mileage further includes steps S11-S15:

[0113] Step S11, determining the light-dark boundary mileage, the design boundary mileage and the design boundary mileage coordinate of the tunnel to be predicted according to the tunnel design information of the tunnel to be predicted;

[0114] Step S12, determining the cross-section spacing of each mileage according to the light-dark boundary mileage, the design boundary mileage and the number of mileages in the portal design range;

[0115] It should be noted that the distance interval between the cross section corresponding to each mileage and the adjacent cross section is determined according to the light-dark boundary mileage, the design boundary mileage and the number of mileages in the tunnel portal design range, and the distance interval between the cross section corresponding to each mileage and the adjacent cross section is the cross section interval s = (m b -m a |) / (N-1), wherein m a , m b are the design boundary mileage of the tunnel portal and the light-dark boundary mileage of the tunnel portal respectively, and N is the number of mileages, that is, N mileages selected in the tunnel portal design range.

[0116] Step S13, determining the cross section mileage value of each mileage according to the cross section interval of each mileage and the light-dark boundary mileage;

[0117] It should be noted that the mileage value of the cross section corresponding to each mileage is determined according to the cross section interval of each mileage, the light-dark boundary mileage and the mileage selection direction m i = m b ±s×(i-1), wherein when the tunnel portal mileage is for the tunnel entrance, the ± values are respectively “-”; when the tunnel portal mileage is for the tunnel exit, the ± values are respectively “+”. In this embodiment, the mileage value of the cross section corresponding to each mileage is the cross section mileage value of each mileage.

[0118] Step S14, performing height calculation according to the cross section mileage value of each mileage, the axis direction vector, the design boundary mileage and the design boundary mileage coordinate to determine the center point height of each mileage;

[0119] It should be noted that the tunnel center point coordinate on the cross section corresponding to each mileage is determined by performing height calculation according to the cross section mileage value of each mileage, the axis direction vector, the design boundary mileage and the design boundary mileage coordinate , wherein m o is the tunnel design boundary mileage, is the tunnel axis direction vector on the longitudinal section, is the coordinate corresponding to the tunnel design boundary mileage. In this embodiment, the tunnel axis direction vector on the longitudinal section of the tunnel to be predicted is the axis direction vector.

[0120] It can be understood that the z value of the tunnel center point coordinate on the cross section corresponding to each mileage is the tunnel center point height on the current cross section, and the tunnel center point height on the cross section corresponding to each mileage is the center point height of each mileage.

[0121] Step S15, performing feature value calculation according to the center point height of each mileage and the terrain point cloud data, and determining the cross section feature information of each mileage according to the feature value calculation result.

[0122] It should be noted that the feature values are calculated according to the center point height of each mileage and the terrain point cloud data, the relative height difference between the terrain and the left and right retaining walls of the to-be-predicted tunnel on the cross section corresponding to each mileage is determined, and the two relative height differences are taken as feature values, and the meanings of the two features are as shown in Figure 5 , which reflects the relative position of the terrain and the to-be-predicted tunnel. In the embodiment, the calculation method of the two feature values of the cross section corresponding to each mileage is: f1=z A -(m iz -d); f2=z B -(m iz -d), where f1 and f2 are the values of feature 1 and feature 2 respectively, z A and z B are the z coordinate values of points A and B, d is the height difference between the tunnel center and the top end of the retaining wall on the cross section, and m iz is the center point height of each mileage. In the embodiment, the two feature values of the cross section corresponding to each mileage constitute the cross section feature information of each mileage.

[0123] As shown in Figure 6 , in the embodiment, for the tunnel entrance, the feature values of N cross sections are extracted in turn along the direction from the light-dark boundary mileage to the design starting mileage; for the tunnel exit, the feature values of N cross sections are extracted in turn along the direction from the light-dark boundary mileage to the design termination mileage. The finally constituted feature value sequence can be represented as {(f 11 ,f 12 ),...,(f 1N ,f 2N )}, which is in the shape of N*2.

[0124] The embodiment provides a tunnel portal mileage design method. The embodiment determines the light-dark boundary mileage, the design boundary mileage and the design boundary mileage coordinate of a to-be-predicted tunnel according to tunnel design information of the to-be-predicted tunnel; determines the cross section spacing of each mileage according to the light-dark boundary mileage, the design boundary mileage and the number of mileages in the portal design range; determines the cross section mileage value of each mileage according to the cross section spacing of each mileage and the light-dark boundary mileage; determines the center point height of each mileage according to the cross section mileage value of each mileage, the axis direction vector, the design boundary mileage and the design boundary mileage coordinate; and performs feature value calculation according to the center point height of each mileage and terrain point cloud data, and determines the cross section feature information of each mileage according to the feature value calculation result. In the above manner, the features that have an influence on the tunnel portal mileage design are calculated based on the terrain point cloud data, the obtained cross section feature information well reflects the relative position information of the tunnel and the terrain, and lays a foundation for realizing accurate portal mileage automatic calculation.

[0125] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as the above embodiments one and two can be referred to the above description, and the subsequent will not be described in detail. On this basis, please refer to Figure 7 , before step S40, the design method of the tunnel portal mileage further includes steps S41-S44:

[0126] Step S41, according to the sample design information of each sample construction tunnel in the sample tunnel portal data set, the cross-sectional characteristic information of each sample mileage in the portal design range of each sample construction tunnel is determined;

[0127] It should be noted that the sample tunnel portal data set is a collection of designed and constructed tunnel portal data sets, each sample construction tunnel refers to a designed and constructed tunnel, the sample design information refers to the tunnel design information, and the sample tunnel portal data set includes sample design information, actual portal mileage, size and axis position of the tunnel, and survey topographic point cloud data and other information of each sample construction tunnel.

[0128] It can be understood that, due to the different distances of the bright-dark division mileage to the tunnel design boundary mileage range and the different number of point clouds of each sample construction tunnel, in order to uniformly represent the relative position characteristics of the terrain and the tunnel in the entire range, N equally spaced mileages are selected as representatives, and the selected mileages are the sample mileages of each sample construction tunnel in the portal design range.

[0129] In a specific implementation, the equally spaced mileages are selected in the bright-dark division mileage to the tunnel design boundary mileage range along the tunnel design axis to continuously extract the characteristics, and the cross-sectional characteristic information of each sample mileage in the portal design range of each sample construction tunnel is obtained. The cross-sectional characteristic information of each sample mileage contains two characteristic values, which are the relative height difference between the terrain and the left and right retaining wall of each sample construction tunnel on the corresponding cross section of each sample mileage, which reflects the relative position of the terrain and each sample construction tunnel.

[0130] Step S42, according to the potential portal mileage range of each sample construction tunnel, each sample mileage in the portal design range of each sample construction tunnel is classified, and multiple sample potential mileages of each sample construction tunnel are determined;

[0131] It should be noted that the potential tunnel portal mileage selection range is determined based on the tunnel length. Since there is a certain correlation between the tunnel length, the number of openings, and the portal length, the selectable range of the portal mileage is not in the entire design range. Each sample mileage is compared with the potential portal mileage range of each sample construction tunnel to determine whether each sample mileage is within the potential portal mileage range of each sample construction tunnel. If so, the sample mileage is regarded as a sample potential mileage.

[0132] Step S43: According to the respective sample potential mileage of each sample construction tunnel, the cross-section feature information of the respective sample mileage of each sample construction tunnel is masked, and the sample feature sequence of each sample construction tunnel is determined according to the masking result;

[0133] It should be noted that the features corresponding to the respective sample potential mileage of each sample construction tunnel are retained, and the features corresponding to other mileages are masked. The sample feature sequence of each sample construction tunnel obtained after the masking processing well reflects the overall features in the range from the light-dark boundary mileage to the tunnel design boundary mileage, and the overall features include the potential portal mileage and the non-potential portal mileage.

[0134] Step S44: A model is trained according to the sample feature sequence of each sample construction tunnel and the actual portal mileage of each sample construction tunnel, and a portal mileage prediction model is obtained.

[0135] It should be noted that a data set is constructed by using the sample feature sequence of each sample construction tunnel and combining the relative positions of the actual portal mileages of each sample construction tunnel. A regression prediction model of the portal mileage is established on the data set by using the powerful nonlinear expression capability of deep learning, so as to obtain the trained portal mileage prediction model.

[0136] In a feasible implementation, step S44 can further include steps D11-D13:

[0137] Step D11: The distance conversion is performed according to the light-dark boundary mileage, the design boundary mileage and the actual portal mileage of each sample construction tunnel, and the relative position of the portal mileage of each sample construction tunnel is obtained.

[0138] It should be noted that since the expression of the tunnel portal mileage is a kind of absolute distance measurement, in order to unify the value range of different tunnel portal mileages, it is converted into the expression of the relative position. For the tunnel entrance, the absolute distance of the actual portal mileage of each sample construction tunnel can be converted into the relative position according to the formula For the tunnel exit, the absolute distance of the actual portal mileage of each sample construction tunnel can be converted into the relative position according to the formula . Wherein, m p , are the absolute distance and the relative position of the actual portal mileage of each sample construction tunnel, m b is the light-dark boundary mileage of each sample construction tunnel, m s and m eThe design starting mileage and the design ending mileage of each sample construction tunnel are respectively. In this embodiment, the design boundary mileage of the import is the starting mileage, and the design boundary mileage of the export is the ending mileage. In this embodiment, the relative position of the actual portal mileage of each sample construction tunnel is the portal mileage relative position of each sample construction tunnel.

[0139] In step D12, the sample feature sequence of each sample construction tunnel is standardized to obtain the standard feature sequence of each sample construction tunnel.

[0140] It should be noted that the sample feature sequence of each sample construction tunnel is standardized according to the formula , where x and x' are the feature value sequences before and after standardization, and u and σ are the mean and standard deviation of the feature. The feature value after standardization is conducive to improving the convergence speed of the model. The sample feature sequence of each sample construction tunnel after standardization is the standard feature sequence of each sample construction tunnel.

[0141] In step D13, the standard feature sequence of each sample construction tunnel and the portal mileage relative position are used for model training to obtain a portal mileage prediction model.

[0142] It should be noted that the standard feature sequence of each sample construction tunnel and the portal mileage relative position of each sample construction tunnel are combined to form a data set, the order of the data set is shuffled, and the training set is divided: test set = 70%:30%. The deep learning model based on LSTM (Long Short Term Memory) is trained through the data set, all training parameters in the network are optimized based on the classic Adam algorithm, and a trained deep learning model is obtained, which is the portal mileage prediction model.

[0143] In this embodiment, the portal mileage relative position of each sample construction tunnel is obtained by distance conversion according to the bright-dark boundary mileage, the design boundary mileage and the actual portal mileage of each sample construction tunnel. The sample feature sequence of each sample construction tunnel is standardized to obtain the standard feature sequence of each sample construction tunnel. The standard feature sequence of each sample construction tunnel and the portal mileage relative position are used for model training to obtain a portal mileage prediction model. Through the above manner, the performance of the model is ensured.

[0144] The embodiment provides a design method of a tunnel portal mileage, and the embodiment determines cross section characteristic information of each sample mileage in a portal design range of each sample construction tunnel according to sample design information of each sample construction tunnel in a sample tunnel portal data set; classifies each sample mileage in the portal design range of each sample construction tunnel according to a potential portal mileage range of each sample construction tunnel, and determines a plurality of sample potential mileages of each sample construction tunnel; performs feature masking on the cross section characteristic information of each sample mileage corresponding to each sample construction tunnel according to each sample potential mileage corresponding to each sample construction tunnel, and determines a sample feature sequence of each sample construction tunnel according to a masking result; and performs model training according to the sample feature sequence of each sample construction tunnel and an actual portal mileage of each sample construction tunnel, to obtain a portal mileage prediction model. Through the above manner, the prediction model of the portal mileage is established based on a deep learning algorithm, and the model has a faster convergence speed and a higher accuracy.

[0145] Exemplarily, in order to help understand the implementation process of the design method of the tunnel portal mileage obtained after the above-mentioned embodiments one / two are combined, please refer to Figure 8 , Figure 8 A brief flowchart of the design method of the tunnel portal mileage is provided, and specifically:

[0146] The design method of the tunnel portal mileage of the embodiment mainly includes the following steps: step one, collecting the designed and constructed tunnel portal data set. The designed and constructed tunnel portal data set collected should include the tunnel portal mileage, the light-dark boundary mileage, the design boundary mileage, the axis direction vector, the size of the tunnel, and the surveyed terrain point cloud data. Step two, extracting the relative position features of the tunnel and the ground within the light-dark boundary mileage to the tunnel design boundary mileage range. Along the tunnel design axis, the features are continuously extracted at equidistant mileages within the light-dark boundary mileage to the tunnel design boundary mileage range to form a feature sequence reflecting the relative position information of the entire three-dimensional terrain and the tunnel. Step three, determining the potential tunnel portal mileage selection range based on the tunnel length. Since there is a certain correlation between the tunnel length, the number of openings, and the portal length, the selectable range of the portal mileage is not within the entire design range, and the correlation needs to be used to determine the potential portal mileage selection range. Step four, retaining the features in step two corresponding to the potential portal mileage in step three and masking the features corresponding to other mileages. The sequence features in step two well reflect the overall features within the light-dark boundary mileage to the tunnel design boundary mileage range, and the overall features include the potential portal mileage and the non-potential portal mileage. This embodiment proposes to mask the regional features of the non-potential portal mileage. Step five, constructing a deep learning regression prediction model of the tunnel portal mileage. The sequence features constructed in steps two to four are combined with the relative position of the tunnel portal mileage to construct a data set, and the powerful nonlinear expression capability of deep learning is used to establish a regression prediction model of the portal mileage on the data set. Step six, obtaining the feature values according to steps two to four for the tunnel to be predicted. For the tunnel to be predicted, the feature value sequence reflecting the relative position of the tunnel terrain and the tunnel, and the potential portal mileage is obtained according to steps two to four. Step seven, inputting the feature values in step six into the model in step five to obtain the predicted value of the tunnel portal mileage. The feature values in step six are standardized and input into the trained model in step five to obtain the predicted value of the relative position of the portal mileage, and the relative position is further converted into an absolute distance expressed as a mileage, which is the final portal mileage.

[0147] In this embodiment, the method of the embodiment is further described in detail in combination with the data set of the tunnel portal: the collected designed and constructed tunnel portal data set includes the terrain point cloud data and the design related parameter information. The terrain contour map of part of the tunnel is as shown in Figure 9 The design related parameters of the corresponding tunnel portal are as shown in Table 1.

[0148] Table 1

[0149]

[0150] The terrain contour map near the tunnel portal to be predicted is as shown in Figure 10The relevant design parameters are shown in Table 2.

[0151] Table 2

[0152]

[0153] 1. Collect the designed and constructed tunnel portal dataset, including the terrain point cloud data near the tunnel portal and the corresponding terrain contour map as shown in Figure 9 The relevant design parameters of the tunnel portal include the design boundary mileage, the axis direction vector, the portal mileage, the light-dark boundary mileage, the tunnel length, and the tunnel radius, as shown in Table 1. The terrain contour map near the tunnel portal to be predicted is shown in Figure 10 The relevant design parameters include the design boundary mileage, the axis direction vector, the light-dark boundary mileage, the tunnel length, and the tunnel radius, as shown in Table 2. 2. For the designed and constructed tunnel, extract the relative position features of the tunnel and the ground within the range from the light-dark boundary mileage to the tunnel design boundary mileage, where N is 50. 3. For the designed and constructed tunnel, determine the potential portal mileage range based on the correlation criteria of the number of openings and the tunnel length, and the optional portal length under different opening numbers, as shown in Table 3.

[0154] Table 3

[0155] Tunnel name In / Out Potential portal mile Tunnel 1 In DK154+914, DK154+856 ~ DK154+909 Tunnel 1 Out DK155+884, DK155+889 ~ DK155+979 Tunnel 2 In DK156+435, DK156+356 ~ DK156+430 Tunnel 2 Out DK157+626, DK157+631 ~ DK157+708

[0156] 4. Map the potential portal mileage in step 3 to the feature position in step 1, and perform feature masking for non-potential portal mileage. 5. Convert the absolute distance of the designed and constructed tunnel portal mileage to relative position representation, and the results are shown in Table 4. The collected dataset is shuffled, and 70% of the samples are randomly selected as the training set and 30% of the samples are randomly selected as the test set. The loss value change of the model is shown in Figure 11 The loss value of the model on the training set and the test set decreases continuously and tends to be stable with the increase of the training rounds, and the loss values on the training set and the test set are not much different when stable, which indicates that the established model is good.

[0157] Table 4

[0158] Tunnel name In / Out Portal mile absolute position Portal mile relative position Tunnel 1 In DK154+890 0.414 Tunnel 1 Out DK155+939 0.579 Tunnel 2 In DK156+411 0.304 Tunnel 2 Out DK157+654 0.341

[0159] 5. For the designed tunnel, perform feature value calculation according to steps 2-4. 7. Input the feature values in step 6 into the model in step 5 to obtain the predicted value of the portal mileage, and further convert it to absolute distance as shown in Table 5. The result is the automatically calculated tunnel portal mileage.

[0160] Table 5

[0161] Tunnel name In / Out Portal mile predicted value (relative position) Portal mile predicted value (absolute position) Tunnel 1 to be predicted In 0.326 DK379+296 Tunnel 1 to be predicted Out 0.395 DK382+091

[0162] The method of the embodiment has the following advantages: tunnel portal mileage design is automatically and efficiently completed; two feature calculation methods that have an impact on tunnel portal mileage design are proposed based on terrain point cloud data, the two features well reflect the relative position information of the tunnel and the terrain, laying a foundation for realizing accurate and automatic calculation of the portal mileage; a feature continuous calculation method is proposed to form a feature sequence from the light-dark boundary mileage to the mileage within the design boundary range, which not only reflects the relative position of the terrain and the tunnel on a single horizontal and vertical section, the change trend feature of the terrain, but also reflects the three-dimensional feature of the entire tunnel portal range, which is more conducive to obtaining the optimal solution of the tunnel portal mileage than the existing method of observing only the two-dimensional feature of the horizontal and vertical sections; a prediction model of the portal mileage is established based on the proposed sequence feature and a deep learning algorithm, which has the advantages of fast convergence speed and high accuracy compared with directly establishing a prediction model using a deep learning algorithm.

[0163] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the design method of the tunnel portal mileage of the present application. More forms of simple changes based on this technical concept are within the protection scope of the present application.

[0164] The present application also provides a tunnel portal mileage design device, please refer to Figure 12 The tunnel portal mileage design device comprises:

[0165] The processing module 10 is configured to determine the horizontal section feature information of each mileage within the portal design range according to the tunnel design information of the tunnel to be predicted;

[0166] The classification module 20 is configured to classify each mileage according to the potential portal mileage range of the tunnel to be predicted, and determine a plurality of potential mileages;

[0167] The processing module 10 is further configured to perform feature masking on the horizontal section feature information of each mileage according to each potential mileage, and determine the feature sequence of the tunnel to be predicted according to the masking result;

[0168] The input module 30 is configured to perform position prediction according to the feature sequence and the portal mileage prediction model, and determine the relative position of the portal mileage;

[0169] The processing module 10 is further configured to determine the portal mileage of the tunnel to be predicted according to the relative position of the portal mileage.

[0170] Optionally, the processing module 10 is further configured to:

[0171] The light-dark boundary mileage and the design boundary mileage of the tunnel to be predicted are determined according to the tunnel design information of the tunnel to be predicted; the portal design range of the tunnel to be predicted is determined according to the light-dark boundary mileage and the design boundary mileage; and the portal design range is divided into mileages according to a preset division interval, so as to obtain a plurality of mileages in the portal design range.

[0172] Optionally, the processing module 10 is further configured to:

[0173] The light-dark boundary mileage, the design boundary mileage and the design boundary mileage coordinate of the tunnel to be predicted are determined according to the tunnel design information of the tunnel to be predicted; the cross-section interval of each mileage is determined according to the light-dark boundary mileage, the design boundary mileage and the number of mileages in the portal design range; the cross-section mileage value of each mileage is determined according to the cross-section interval of each mileage and the light-dark boundary mileage; the center point height of each mileage is determined by height calculation according to the cross-section mileage value of each mileage, the axis direction vector, the design boundary mileage and the design boundary mileage coordinate; and the cross-section feature information of each mileage is determined by feature value calculation according to the center point height of each mileage and the terrain point cloud data.

[0174] Optionally, the classification module 20 is further configured to:

[0175] The number of openings, the tunnel portal type, the light-dark boundary mileage and the mileage selection direction of the tunnel to be predicted are determined according to the tunnel design information of the tunnel to be predicted; the potential portal length of the tunnel to be predicted is determined according to the tunnel portal design criterion, the number of openings and the tunnel portal type; and the potential portal mileage range of the tunnel to be predicted is determined by range calculation according to the potential portal length, the light-dark boundary mileage and the mileage selection direction.

[0176] Optionally, the processing module 10 is further configured to:

[0177] The cover mileage in the plurality of mileages is determined according to each potential mileage; the cover feature information of each cover mileage is obtained by feature covering of the cross-section feature information of each cover mileage according to a preset feature value; and the feature sequence of the tunnel to be predicted is constructed according to the cover feature information of each cover mileage and the cross-section feature information of each potential mileage.

[0178] Optionally, the input module 30 is further configured to:

[0179] According to sample design information of each sample construction tunnel in the sample tunnel portal data set, cross section characteristic information of each sample construction tunnel at each sample mileage in the portal design range is determined; according to a potential portal mileage range of each sample construction tunnel, each sample mileage of each sample construction tunnel in the portal design range is classified, and a plurality of sample potential mileages of each sample construction tunnel are determined; according to each sample potential mileage corresponding to each sample construction tunnel, characteristic masking is performed on the cross section characteristic information of each sample mileage corresponding to each sample construction tunnel, and a sample characteristic sequence of each sample construction tunnel is determined according to a masking result; and model training is performed according to the sample characteristic sequence of each sample construction tunnel and an actual portal mileage of each sample construction tunnel, so as to obtain a portal mileage prediction model.

[0180] Optionally, the input module 30 is further configured to:

[0181] According to the bright-dark division mileage, the design boundary mileage and the actual portal mileage of each sample construction tunnel, distance conversion is performed to obtain a portal mileage relative position of each sample construction tunnel; standardization processing is performed on the sample characteristic sequence of each sample construction tunnel respectively to obtain a standard characteristic sequence of each sample construction tunnel; and model training is performed according to the standard characteristic sequence of each sample construction tunnel and the portal mileage relative position to obtain a portal mileage prediction model.

[0182] The tunnel portal mileage design device provided in the present application adopts the tunnel portal mileage design method in the above embodiments, and can solve the technical problem of tunnel portal mileage design. Compared with the prior art, the tunnel portal mileage design device provided in the present application has the same beneficial effects as the tunnel portal mileage design method provided in the above embodiments, and other technical features in the tunnel portal mileage design device are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0183] The present application provides a tunnel portal mileage design device, which comprises at least one processor and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the tunnel portal mileage design method in the above embodiment one.

[0184] The following will be described with reference to the drawings Figure 13The diagram illustrates a structural schematic of a device suitable for designing tunnel portal mileage in accordance with embodiments of this application. The device for designing tunnel portal mileage in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 13 The design equipment for the tunnel entrance mileage shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0185] like Figure 13 As shown, the tunnel portal mileage design device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the tunnel portal mileage design device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the tunnel portal mileage design equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a tunnel portal mileage design equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0186] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0187] The tunnel portal mileage design device provided by the present application adopts the tunnel portal mileage design method in the above-mentioned embodiments, and can solve the technical problem of tunnel portal mileage design. Compared with the prior art, the tunnel portal mileage design device provided by the present application has the same beneficial effects as the tunnel portal mileage design method provided by the above-mentioned embodiments, and other technical features in the tunnel portal mileage design device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0188] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0189] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0190] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the tunnel portal mileage design method in the above-mentioned embodiments.

[0191] The computer readable storage medium provided in the present application may, for example, be a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted in any suitable medium, including but not limited to electrical wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0192] The above computer readable storage medium can be included in the tunnel portal mileage design device, or can exist separately without being assembled into the tunnel portal mileage design device.

[0193] The above computer readable storage medium carries one or more programs, which, when executed by the tunnel portal mileage design device, cause the tunnel portal mileage design device to: design the tunnel portal mileage.

[0194] Computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including object oriented programming languages such as Java, Smalltalk, C++ or conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0195] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0196] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0197] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer program) for executing the tunnel portal mileage design method described above, and can solve the technical problem of tunnel portal mileage design. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the tunnel portal mileage design method provided by the above-mentioned embodiments, which will not be repeated here.

[0198] The present application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the tunnel portal mileage design method as described above.

[0199] The computer program product provided by the present application can solve the technical problem of tunnel portal mileage design. Compared with the prior art, the computer program product provided by the present application has the same beneficial effects as the tunnel portal mileage design method provided by the above-mentioned embodiments, which will not be repeated here.

[0200] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation made by using the content of the present application specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the present application.

Claims

1. A method of designing a tunnel portal mileage, characterized by, The tunnel portal mileage design method comprises: determining cross-section characteristic information of each mileage within a portal design range according to tunnel design information of a to-be-predicted tunnel; classifying each mileage according to a potential portal mileage range of the to-be-predicted tunnel, and determining a plurality of potential mileages; performing characteristic masking on the cross-section characteristic information of each mileage according to each potential mileage, and determining a characteristic sequence of the to-be-predicted tunnel according to a masking result; performing position prediction according to the characteristic sequence and a portal mileage prediction model, and determining a portal mileage relative position; determining a portal mileage of the to-be-predicted tunnel according to the portal mileage relative position; the method comprises: determining a light-dark boundary mileage, a design boundary mileage, and a design boundary mileage coordinate of the to-be-predicted tunnel according to tunnel design information of the to-be-predicted tunnel; determining a cross-section spacing of each mileage according to the light-dark boundary mileage, the design boundary mileage, and a mileage number within the portal design range; determining a cross-section mileage value of each mileage according to the cross-section spacing of each mileage and the light-dark boundary mileage; performing height calculation according to the cross-section mileage value of each mileage, an axis direction vector, the design boundary mileage, and the design boundary mileage coordinate, and determining a center point height of each mileage; performing characteristic value calculation according to the center point height of each mileage and terrain point cloud data, and determining cross-section characteristic information of each mileage according to a characteristic value calculation result; the method comprises: determining a plurality of masking mileages in the plurality of mileages according to each potential mileage; performing characteristic masking on the cross-section characteristic information of each masking mileage according to a preset characteristic numerical value, to obtain masking characteristic information of each masking mileage; constructing the characteristic sequence of the to-be-predicted tunnel according to the masking characteristic information of each masking mileage and the cross-section characteristic information of each potential mileage.

2. The method of claim 1, wherein, before the method of determining the cross-section characteristic information of each mileage within the portal design range according to the tunnel design information of the to-be-predicted tunnel, the method further comprises: determining a light-dark boundary mileage and a design boundary mileage of the to-be-predicted tunnel according to tunnel design information of the to-be-predicted tunnel; determining a portal design range of the to-be-predicted tunnel according to the light-dark boundary mileage and the design boundary mileage; dividing the portal design range into mileages according to a preset division spacing, to obtain a plurality of mileages within the portal design range.

3. The method of claim 1, wherein, before the method of classifying each mileage according to the potential portal mileage range of the to-be-predicted tunnel, and determining a plurality of potential mileages, the method further comprises: determining a number of openings, a tunnel portal type, a light-dark boundary mileage, and a mileage selection direction of the to-be-predicted tunnel according to tunnel design information of the to-be-predicted tunnel; determining a potential portal length of the to-be-predicted tunnel according to a portal design criterion, the number of openings, and the tunnel portal type; determining a potential portal mileage range of the to-be-predicted tunnel according to the potential portal length, the light-dark boundary mileage, and the mileage selection direction.

4. The method of claim 1, wherein, The position prediction according to the feature sequence and the portal mileage prediction model further comprises the following steps before determining the portal mileage relative position: According to the sample design information of each sample construction tunnel in the sample tunnel portal data set, the cross-section feature information of each sample mileage within the portal design range of each sample construction tunnel is determined. According to the potential portal mileage range of each sample construction tunnel, each sample mileage within the portal design range of each sample construction tunnel is classified to determine multiple sample potential mileages of each sample construction tunnel. According to the respective sample potential mileages of each sample construction tunnel, the cross-section feature information of the respective sample mileages of each sample construction tunnel is feature masked, and the sample feature sequence of each sample construction tunnel is determined according to the masking result. According to the sample feature sequence of each sample construction tunnel and the actual portal mileage of each sample construction tunnel, model training is performed to obtain a portal mileage prediction model.

5. The method of claim 4, wherein, The model training according to the sample feature sequence of each sample construction tunnel and the actual portal mileage of each sample construction tunnel to obtain the portal mileage prediction model comprises the following steps: According to the bright-dark boundary mileage, the design boundary mileage, and the actual portal mileage of each sample construction tunnel, distance conversion is performed to obtain the portal mileage relative position of each sample construction tunnel. The sample feature sequence of each sample construction tunnel is respectively standardized to obtain the standard feature sequence of each sample construction tunnel. According to the standard feature sequence of each sample construction tunnel and the portal mileage relative position, model training is performed to obtain the portal mileage prediction model.

6. A device for designing tunnel portal mileage, characterized in that, The tunnel portal mileage design device comprises: A processing module configured to determine the cross-section feature information of each mileage within the portal design range according to the tunnel design information of the tunnel to be predicted; A classification module configured to classify each mileage according to the potential portal mileage range of the tunnel to be predicted to determine multiple potential mileages; The processing module is further configured to mask the cross-section feature information of each mileage according to each potential mileage, and to determine the feature sequence of the tunnel to be predicted according to the masking result; An input module configured to perform position prediction according to the feature sequence and the portal mileage prediction model to determine the portal mileage relative position; The processing module is further configured to determine the portal mileage of the tunnel to be predicted according to the portal mileage relative position; The processing module is further configured to determine the bright-dark boundary mileage, the design boundary mileage, and the design boundary mileage coordinates of the tunnel to be predicted according to the tunnel design information of the tunnel to be predicted, to determine the cross-section spacing of each mileage according to the bright-dark boundary mileage, the design boundary mileage, and the number of mileages within the portal design range, to determine the cross-section mileage value of each mileage according to the cross-section spacing of each mileage and the bright-dark boundary mileage, to determine the center point height of each mileage according to the cross-section mileage value of each mileage, the axis direction vector, the design boundary mileage, and the design boundary mileage coordinates, and to determine the cross-section feature information of each mileage according to the center point height of each mileage and the terrain point cloud data. The processing module is further configured to determine covered mileages from the plurality of mileages according to the respective potential mileages; perform feature covering on cross-section feature information of each covered mileage according to a preset feature value to obtain covered feature information of each covered mileage; and construct a feature sequence of the tunnel to be predicted according to the covered feature information of each covered mileage and the cross-section feature information of each potential mileage.

7. A device for designing a tunnel portal mileage, characterized by The tunnel portal mileage design device comprises a memory, a processor, and a tunnel portal mileage design program stored in the memory and executable on the processor, and the tunnel portal mileage design program is configured to implement the tunnel portal mileage design method according to any one of claims 1 to 5.

8. A storage medium, characterized by The storage medium has a tunnel portal mileage design program stored thereon, and the tunnel portal mileage design program, when executed by a processor, implements the tunnel portal mileage design method according to any one of claims 1 to 5.

Images