Intelligent design method for overall scheme of tunnel portal
Through intelligent design methods, the light and dark boundary mileage and hole mileage of tunnel entrances are automatically predicted, which solves the problems of low efficiency and relying on experience in traditional design, and realizes efficient and stable tunnel entrance design.
Patent Information
- Application Number
- CN202411013523.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-07-26
AI Technical Summary
Traditional tunnel entrance design relies on manual iterative attempts, which is time-consuming and labor-intensive and highly dependent on the experience of designers, resulting in low design efficiency and unstable results.
By adopting intelligent design method, by obtaining terrain point cloud data, tunnel line data and structural dimensions, inputting the light and dark boundary mileage prediction model and the hole mileage prediction model, automatically predicting the light and dark boundary mileage and hole mileage, and determining the hole length and the hole gate length according to the model results. Subdivided types to reduce the subjective intervention of designers.
It realizes efficient automation of tunnel opening design, reduces design time and artificial errors, and improves the stability and reliability of design results.
Smart Images

Figure CN119066738A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of tunnel construction design, and in particular to an intelligent design method for an overall tunnel portal solution. Background Art
[0002] At present, the design of tunnel openings relies on manual design in two-dimensional transverse and longitudinal sections. The main process is: 1. Select a certain mileage within the design mileage range as the potential light-dark boundary mileage and select a certain mileage as the potential opening mileage; 2. Draw transverse and longitudinal section diagrams and observe the relative position of the terrain and the tunnel to determine whether the above potential light-dark boundary mileage and opening mileage are appropriate; 3. Repeat steps 1 and 2 until the appropriate light-dark boundary mileage and opening mileage are found; 4. Select the potential portal length and portal type, and determine whether it is appropriate based on the transverse and longitudinal section diagrams; 5. Repeat step 4 until the appropriate portal length and portal type are found. It can be seen that the traditional method of designing tunnel openings requires continuous iterative attempts. The entire design process is not only time-consuming and labor-intensive, but also highly dependent on the experience of designers.
[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention
[0004] The main purpose of this application is to provide an intelligent design method for the overall solution of a tunnel portal, aiming to solve the technical problem that the traditional method of designing a tunnel portal is not only time-consuming and labor-intensive, but also highly dependent on the experience of designers.
[0005] To achieve the above objectives, the present application proposes an intelligent design method for an overall solution of a tunnel entrance, and the intelligent design method for an overall solution of a tunnel entrance comprises:
[0006] Acquire target tunnel data of the tunnel entrance to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data, and tunnel structure dimensions;
[0007] Inputting the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value;
[0008] Input the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the target tunnel entrance mileage design value;
[0009] Determine the target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determine the target portal type of the target portal length based on the potential portal length table;
[0010] The target portal subdivision type is determined according to the target portal mileage design value, the target portal type and the target tunnel data.
[0011] In one embodiment, the step of determining the target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determining the target portal type of the target portal length based on the potential portal length table includes:
[0012] Determine the preferred order of portal types and determine the range of potential portal lengths for each portal type;
[0013] Based on the preferred order and the potential tunnel length range, construct a potential tunnel length table;
[0014] The potential portal length table contains the screening portal types whose potential portal length range includes the target portal length, and the target portal type of the target portal length is determined from the screening portal types according to the preferred order.
[0015] In one embodiment, the step of determining the potential portal length range for each portal type comprises:
[0016] Count the length range of the tunnel and the length range of the open hole corresponding to each tunnel type;
[0017] The portal length range and the open hole length range are fused and deduplicated to obtain the potential portal length range of each portal type.
[0018] In one embodiment, the step of determining the portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data comprises:
[0019] When the portal type is a cut-type portal, determining the tunnel length of the tunnel to be designed according to the target tunnel data;
[0020] Determining the number of openings based on a comparison result of the tunnel length and a critical portal length parameter;
[0021] The subdivision type of the portal is determined according to the target portal type and the number of openings.
[0022] In one embodiment, the step of determining the portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data comprises:
[0023] When the portal type is a wall-type portal, a first feature, a second feature, a third feature and a fourth feature are determined according to the target portal mileage design value and the target tunnel data, wherein the first feature is a first height difference between a terrain point on the left side of the tunnel on the cross section at the target portal mileage design value and a first reference line, the second feature is a second height difference between a terrain point on the right side of the tunnel on the cross section at the target portal mileage design value and the first reference line, the third feature is a third height difference between a terrain point on the left side of the tunnel on the cross section at the target portal mileage design value and the second reference line, the fourth feature is a fourth height difference between a terrain point on the right side of the tunnel on the cross section at the target portal mileage design value and the second reference line, the first reference line is a straight line on the cross section at the target portal mileage design value passing through the top of the tunnel and parallel to the bottom of the tunnel, the second reference line is a straight line on the cross section at the target portal mileage design value having a preset distance difference in height from the center point of the tunnel and parallel to the first reference line, and the second reference line is higher than the top of the tunnel;
[0024] Based on the wall-type portal subdivision category discrimination table, the target portal subdivision type is determined according to the first feature, the second feature, the third feature and the fourth feature.
[0025] In one embodiment, before the step of obtaining target tunnel data of the tunnel entrance to be designed, the step further includes:
[0026] Acquire tunnel data of constructed tunnel openings, wherein the tunnel data includes terrain point cloud data, line data, tunnel structure dimensions, and design parameters;
[0027] The light-dark boundary mileage prediction model is established based on the tunnel data, and the tunnel entrance mileage prediction model is established based on the tunnel data.
[0028] In one embodiment, the step of establishing the light-dark boundary mileage prediction model based on the tunnel data includes:
[0029] Determine the design starting mileage, design ending mileage, bright and dark boundary mileage and design axis according to the tunnel data;
[0030] Uniformly select multiple mileages along the design axis within the range of the design start mileage and the design end mileage, calculate the first boundary mileage feature and the second boundary mileage feature of each mileage on the cross section in turn, and determine the first sequence feature according to the first boundary mileage feature and the second boundary mileage feature, wherein the first boundary mileage feature is the distance between the topographic line and the tunnel top on the cross section, and the second boundary mileage feature is the terrain slope on the cross section;
[0031] Determine the relative position of the light-dark boundary mileage of the constructed tunnel entrance according to the designed starting mileage, the designed ending mileage and the light-dark boundary mileage;
[0032] A first data set is constructed based on the first sequence features and the relative positions of the light-dark boundary mileages, and a light-dark boundary mileage prediction model is established based on the first data set.
[0033] In one embodiment, the step of establishing a tunnel entrance mileage prediction model based on the tunnel data includes:
[0034] Determine the tunnel boundary design mileage, light-dark boundary mileage and design axis according to the tunnel data;
[0035] Uniformly select multiple mileages along the design axis within the range of the tunnel boundary design mileage and the light-dark boundary mileage, calculate the first hole opening mileage feature and the second hole opening mileage feature of each mileage on the cross section in turn, and determine the second sequence feature according to the first hole opening mileage feature and the second hole opening mileage feature, wherein the first hole opening mileage feature is the distance between the left terrain line and the retaining wall on the cross section, and the second hole opening mileage feature is the distance between the right terrain line and the retaining wall on the cross section;
[0036] Performing feature masking processing on the second sequence feature to obtain a second target sequence feature;
[0037] Determine the tunnel entrance mileage according to the tunnel data, and determine the relative position of the tunnel entrance mileage of the constructed tunnel entrance according to the tunnel entrance mileage;
[0038] Based on the second target sequence features and the relative position of the tunnel entrance mileage, a second data set is constructed, and based on the second data set, the tunnel entrance mileage prediction model is established.
[0039] In one embodiment, the step of inputting the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value comprises:
[0040] Inputting the target tunnel data into a tunnel entrance light-dark boundary mileage prediction model to obtain the relative position of the target light-dark boundary mileage;
[0041] Based on the light-dark boundary mileage conversion formula, the relative position of the target light-dark boundary mileage is converted into the target light-dark boundary mileage design value.
[0042] In one embodiment, the step of inputting the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the target tunnel entrance mileage design value includes:
[0043] Input the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the relative position of the tunnel entrance mileage;
[0044] Based on the tunnel opening mileage conversion formula, the relative position of the tunnel opening mileage is converted into the tunnel opening mileage design value.
[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent design device for an overall solution of a tunnel entrance, and the intelligent design device for an overall solution of a tunnel entrance comprises:
[0046] An acquisition module is used to acquire target tunnel data of a tunnel entrance to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data and tunnel structure dimensions;
[0047] An input module, used for inputting the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value;
[0048] The input module is further used to input the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the target tunnel entrance mileage design value;
[0049] A determination module, used to determine a target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determine a target portal type of the target portal length based on a potential portal length table;
[0050] The determination module is further used to determine the target portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data.
[0051] In addition, to achieve the above-mentioned objectives, the present application also proposes an intelligent design device for the overall solution of a tunnel portal, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the intelligent design method for the overall solution of a tunnel portal as described above.
[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the intelligent design method of the overall tunnel portal solution as described above are implemented.
[0053] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the intelligent design method of the overall tunnel portal solution as described above.
[0054] One or more technical solutions proposed in this application have at least the following technical effects:
[0055] The intelligent design method of the overall tunnel portal scheme proposed in the present application obtains the target tunnel data of the tunnel portal to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data and tunnel structure dimensions; inputs the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value; inputs the target tunnel data and the target light-dark boundary mileage design value into a portal mileage prediction model to obtain a target portal mileage design value; determines a target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determines a target portal type of the target portal length based on a potential portal length table; determines a target portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data. The present invention solves the technical problem that the traditional method of designing tunnel entrances is not only time-consuming and labor-intensive, but also highly dependent on the experience of designers. Compared with the existing technology, the present application can predict the light-dark boundary mileage and entrance mileage of the tunnel entrance to be designed through the established light-dark boundary mileage prediction model and the entrance mileage prediction model, so that the design of the tunnel entrance to be designed can be realized without repeated attempts by designers, thereby achieving efficient design. The present application also provides a unified method for determining the portal type and the portal subdivision type, and the design result is not affected by the subjectivity of the designer, so that the design result of the tunnel entrance to be designed is more stable and reliable. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0058] Figure 1 A flow chart of the first embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application;
[0059] Figure 2 A sequence feature extraction diagram of light-dark boundary mileage provided in the first embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application;
[0060] Figure 3LSTM network model diagram provided for the first embodiment of the intelligent design method for the overall solution of the tunnel entrance of this application;
[0061] Figure 4 A sequence feature extraction diagram of tunnel portal mileage provided in the first embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application;
[0062] Figure 5 A technical roadmap provided for the first embodiment of the intelligent design method for the overall solution of the tunnel portal of this application;
[0063] Figure 6 A characteristic meaning diagram of a wall-type portal provided in the first embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application;
[0064] Figure 7 A flow chart of the second embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application;
[0065] Figure 8 A potential portal length process diagram provided for the second embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application;
[0066] Fig. 9 A topographic point cloud data map of a designed tunnel opening provided in Embodiment 2 of the intelligent design method for the overall solution of the tunnel opening of this application;
[0067] Fig.10 A topographic point cloud data map of the tunnel opening to be designed provided in the second embodiment of the intelligent design method for the overall solution of the tunnel opening of the present application;
[0068] Fig.11 A trend chart of the loss value change of the light-dark boundary mileage prediction model provided in the second embodiment of the intelligent design method for the overall solution of the tunnel portal of this application;
[0069] Fig.12 A trend chart of the loss value change of the portal mileage prediction model provided in the second embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application;
[0070] Fig.13 A schematic diagram of the module structure of an intelligent design device for the overall solution of a tunnel portal according to an embodiment of the present application;
[0071] Fig.14 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the intelligent design method of the overall tunnel portal solution in the embodiment of the present application.
[0072] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0073] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0074] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0075] The main solution of the embodiment of the present application is: obtaining target tunnel data of the tunnel entrance to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data and tunnel structure size; inputting the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value; inputting the target tunnel data and the target light-dark boundary mileage design value into a portal mileage prediction model to obtain a target portal mileage design value; determining a target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determining a target portal type of the target portal length based on a potential portal length table; determining a target portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data.
[0076] In this embodiment, for ease of description, the following description is made by taking the intelligent design device for identifying the overall solution of the tunnel entrance as the execution subject.
[0077] Since the traditional method of designing tunnel entrances requires continuous iterative attempts, the entire design process is not only time-consuming and labor-intensive, but also highly dependent on the experience of designers.
[0078] The present application provides a solution, which can predict the light-dark boundary mileage and entrance mileage of the tunnel entrance to be designed through the established light-dark boundary mileage prediction model and entrance mileage prediction model, so that the design of the tunnel entrance to be designed can be realized without repeated attempts by designers, thereby achieving efficient design. The present application also provides a unified method for determining the portal type and the portal subdivision type, and the design result is not affected by the subjectivity of the designer, making the design result of the tunnel entrance to be designed more stable and reliable.
[0079] It can be seen from the above embodiments that the present application obtains the target tunnel data of the tunnel entrance to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data and tunnel structure dimensions; the target tunnel data is input into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value; the target tunnel data and the target light-dark boundary mileage design value are input into a portal mileage prediction model to obtain a target portal mileage design value; the target portal length is determined according to the target light-dark boundary mileage design value and the target portal mileage design value, and the target portal type of the target portal length is determined based on a potential portal length table; the target portal subdivision type is determined according to the target portal mileage design value, the target portal type and the target tunnel data. The present invention solves the technical problem that the traditional method of designing tunnel entrances is not only time-consuming and labor-intensive, but also highly dependent on the experience of designers. Compared with the existing technology, the present application can predict the light-dark boundary mileage and entrance mileage of the tunnel entrance to be designed through the established light-dark boundary mileage prediction model and the entrance mileage prediction model, so that the design of the tunnel entrance to be designed can be realized without repeated attempts by designers, thereby achieving efficient design. The present application also provides a unified method for determining the portal type and the portal subdivision type, and the design result is not affected by the subjectivity of the designer, so that the design result of the tunnel entrance to be designed is more stable and reliable.
[0080] It should be noted that the execution subject of this 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, an intelligent design device for the overall solution of the tunnel portal, etc. The following takes the intelligent design device for the overall solution of the tunnel portal as an example to illustrate this embodiment and the following embodiments.
[0081] Based on this, the embodiment of the present application provides an intelligent design method for the overall solution of a tunnel entrance, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the intelligent design method for the overall solution of the tunnel portal of the present application.
[0082] In this embodiment, the intelligent design method of the overall tunnel portal solution includes steps S10 to S40:
[0083] Step S10, obtaining target tunnel data of the tunnel entrance to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data and tunnel structure dimensions;
[0084] In a feasible implementation manner, before the step of obtaining the target tunnel data of the tunnel entrance to be designed, the step also includes: obtaining tunnel data of the constructed tunnel entrance, wherein the tunnel data includes terrain point cloud data, line data, tunnel structure dimensions, and design parameters; establishing the light-dark boundary mileage prediction model based on the tunnel data, and establishing a portal mileage prediction model based on the tunnel data.
[0085] It should be noted that when establishing a light-dark boundary mileage prediction model, the sequence characteristics reflecting the relative position of the terrain and the tunnel, and the terrain slope can be extracted within the design starting mileage and ending mileage based on the tunnel data of the constructed tunnel entrance, and then the relative position of the light-dark boundary mileage is calculated based on the design parameters. Finally, a deep learning algorithm is used to establish a light-dark boundary mileage prediction model.
[0086] It should be noted that when establishing a portal mileage prediction model, the sequence features reflecting the relative position of the terrain and the tunnel can be extracted within the range of the light-dark boundary mileage and the design boundary mileage based on the tunnel data of the constructed tunnel portal, and the sequence features can be masked using the non-potential portal mileage. The relative position of the portal mileage is calculated based on the design parameters, and finally a deep learning algorithm is used to establish a portal mileage prediction model.
[0087] In this embodiment, the prediction model of light-dark boundary mileage and entrance mileage is established by constructing the features of tunnel data of constructed tunnel entrances and using deep learning technology, thereby realizing the automatic calculation of light-dark boundary mileage and entrance mileage, thereby improving the design efficiency.
[0088] In a feasible implementation manner, the step of establishing the light-dark boundary mileage prediction model based on the tunnel data includes: determining the design start mileage, the design end mileage, the light-dark boundary mileage and the design axis according to the tunnel data; uniformly selecting multiple mileages along the design axis within the range of the design start mileage and the design end mileage, calculating the first boundary mileage feature and the second boundary mileage feature of each mileage on the cross section in turn, and determining a first sequence feature according to the first boundary mileage feature and the second boundary mileage feature, wherein the first boundary mileage feature is the distance between the topographic line and the tunnel top on the cross section, and the second boundary mileage feature is the terrain slope on the cross section; determining the relative position of the light-dark boundary mileage of the constructed tunnel entrance according to the design start mileage, the design end mileage and the light-dark boundary mileage; constructing a first data set based on the first sequence feature and the relative position of the light-dark boundary mileage, and establishing the light-dark boundary mileage prediction model based on the first data set.
[0089] In the specific implementation, N mileages are uniformly selected along the design axis within the design start mileage and the design end mileage, and the first boundary mileage features and the second boundary mileage features on the cross section corresponding to the N mileages are calculated in turn, and the first sequence features are formed based on the two boundary mileage features. The extraction process of the first sequence features is as follows: Figure 2 As shown, feature 1 (i.e., the first boundary mileage feature) is the distance between the topography line and the tunnel top on the cross section, feature 2 (i.e., the second boundary mileage feature) is the slope of the topography line on the cross section, and the first sequence feature represents the overall relative position of the topography line and the tunnel within the design starting mileage and ending mileage, as well as the terrain slope.
[0090] In a specific implementation, the relative position of the light-dark boundary mileage can be calculated according to the light-dark boundary mileage, the designed starting mileage, and the designed ending mileage in the tunnel data (the relative position of the light-dark boundary mileage includes the relative position of the import light-dark boundary mileage and the relative position of the export light-dark boundary mileage). The specific calculation formula is as follows:
[0091]
[0092] In the formula, S b Indicates the light-dark boundary mileage, S s Indicates the design starting mileage, S e Indicates the design termination mileage, y jb Indicates the relative position of the light-dark boundary mileage of the inlet, y cb Indicates the relative position of the light-dark boundary mileage of the exit.
[0093] In a specific implementation, when establishing a light-dark boundary mileage prediction model, the extracted first sequence features are standardized and combined with the relative positions of the light-dark boundary mileages to form a first data set, and the first data set is further divided into a training set and a test set, wherein the training set is used to establish the model, and the test set is used to evaluate the model, such as Figure 3 As shown, a prediction model for the light-dark boundary mileage can be established based on the existing LSTM algorithm, wherein the input feature shape of the model is N×2 and the output is 1 neuron (representing the relative position of the light-dark boundary mileage).
[0094] In a feasible implementation manner, the step of establishing a portal mileage prediction model based on the tunnel data includes: determining the tunnel boundary design mileage, the light-dark boundary mileage and the design axis according to the tunnel data; uniformly selecting multiple mileages along the design axis within the range of the tunnel boundary design mileage and the light-dark boundary mileage, sequentially calculating the first portal mileage feature and the second portal mileage feature of each mileage on the cross section, and determining a second sequence feature according to the first portal mileage feature and the second portal mileage feature, wherein the first portal mileage feature is the distance between the left topographic line and the retaining wall on the cross section, and the second portal mileage feature is the distance between the right topographic line and the retaining wall on the cross section; performing feature masking processing on the second sequence feature to obtain a second target sequence feature; determining the portal mileage according to the tunnel data, and determining the relative position of the portal mileage of the constructed tunnel portal according to the portal mileage; constructing a second data set based on the second target sequence feature and the relative position of the portal mileage, and establishing the portal mileage prediction model based on the second data set.
[0095] In the specific implementation, M mileages are uniformly selected along the design axis within the range of the light-dark boundary mileage and the design boundary mileage, and the first opening mileage features and the second opening mileage features on the cross section corresponding to the M mileages are calculated in sequence to form the second sequence features. The second sequence feature extraction process is as follows: Figure 4 As shown, the first tunnel entrance mileage feature (feature 1) is the distance between the left terrain line and the retaining wall on the cross section, and the second tunnel entrance mileage feature (feature 2) is the distance between the right terrain line and the retaining wall on the cross section. The second sequence feature can well reflect the overall relative position of the terrain line and the tunnel within the light and dark boundary mileage and the design boundary mileage.
[0096] In the specific implementation, the feature masking processing is to set the features corresponding to the non-potential opening mileage in the second sequence features to 0. Specifically, the corresponding potential portal lengths of all portal types are counted according to the tunnel data of the designed tunnel openings. For the entrance, the potential opening mileage is the difference between the light-dark boundary mileage and the potential portal length. For the exit, the potential opening mileage is the sum of the light-dark boundary mileage and the potential portal length. The potential opening mileage and non-potential opening mileage are further mapped to the second sequence features, and the features corresponding to the non-potential opening mileage are set to 0 to obtain the second target sequence features.
[0097] In the specific implementation, the relative position of the tunnel entrance mileage can be calculated according to the light-dark boundary mileage, the design start mileage, the design end mileage and the tunnel entrance mileage in the tunnel data (the relative position of the tunnel entrance mileage includes the relative position of the entrance entrance mileage and the relative position of the exit entrance mileage). The specific calculation formula is as follows:
[0098]
[0099] In the formula, S b Indicates the light-dark boundary mileage, S s Indicates the design starting mileage, S e Indicates the design termination mileage, S p Indicates the tunnel entrance mileage, y jp Indicates the relative position of the entrance mileage, y cp Indicates the relative position of the exit tunnel mileage.
[0100] In a specific implementation, when establishing a tunnel entrance mileage prediction model, the extracted second target sequence features are standardized and combined with the relative position of the tunnel entrance mileage to form a second data set, and the second data set is further divided into a training set and a test set, wherein the training set is used to establish the model, and the test set is used to evaluate the model, such as Figure 3 As shown, a prediction model for the cave entrance mileage can be established based on the existing LSTM algorithm, where the input feature shape of the model is N×2 and the output is 1 neuron (representing the relative position of the cave entrance mileage).
[0101] Step S20, inputting the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value;
[0102] In a feasible implementation manner, the step of inputting the target tunnel data into the light-dark boundary mileage prediction model to obtain the target light-dark boundary mileage design value includes: inputting the target tunnel data into the light-dark boundary mileage prediction model of the tunnel entrance to obtain the relative position of the target light-dark boundary mileage; based on the light-dark boundary mileage conversion formula, converting the relative position of the target light-dark boundary mileage into the target light-dark boundary mileage design value.
[0103] It should be noted that by inputting the basic data (i.e., target tunnel data) of the terrain point cloud data, tunnel line data, and tunnel structure dimensions of the tunnel to be designed into the light-dark boundary mileage prediction model, the relative position of the target light-dark boundary mileage can be obtained, and then the relative position of the target light-dark boundary mileage is converted into the target light-dark boundary mileage design value (the target light-dark boundary mileage design value includes the target inlet light-dark boundary mileage design value and the target outlet light-dark boundary mileage design value). The specific conversion formula is as follows:
[0104]
[0105] In the formula, S b Indicates the light-dark boundary mileage, S s Indicates the design starting mileage, S e Indicates the design termination mileage, y jb Indicates the relative position of the light-dark boundary mileage of the inlet, ycb Indicates the relative position of the light-dark boundary mileage of the exit. Indicates the target inlet light-dark boundary mileage design value, Indicates the design value of the light-dark boundary mileage of the target exit.
[0106] Step S30, inputting the target tunnel data and the target light-dark boundary mileage design value into a tunnel entrance mileage prediction model to obtain a target tunnel entrance mileage design value;
[0107] In a feasible implementation manner, the step of inputting the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the target tunnel entrance mileage design value includes: inputting the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the relative position of the tunnel entrance mileage; based on the tunnel entrance mileage conversion formula, converting the relative position of the tunnel entrance mileage into the tunnel entrance mileage design value.
[0108] It should be noted that the terrain point cloud data, tunnel line data, tunnel structure dimensions and other basic data (i.e., target tunnel data) of the tunnel to be designed and the target light-dark boundary mileage design value can be input into the light-dark boundary mileage prediction model to obtain the relative position of the target tunnel entrance mileage, and then the relative position of the target tunnel entrance mileage is converted into the target tunnel entrance mileage design value (the target tunnel entrance mileage design value includes the target entrance mileage design value and the target exit mileage design value). The specific conversion formula is as follows:
[0109]
[0110] In the formula, S b Indicates the light-dark boundary mileage, S s Indicates the design starting mileage, S e Indicates the design termination mileage, y jp Indicates the relative position of the entrance mileage, y cp Indicates the relative position of the exit tunnel mileage, Indicates the target inlet light-dark boundary mileage design value, Indicates the design value of the light-dark boundary mileage of the target exit.
[0111] Step S40, determining a target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determining a target portal type of the target portal length based on a potential portal length table;
[0112] It should be noted that the potential portal length table is designed in advance and can be used to represent the mapping relationship between potential portal length and portal type. The potential portal length table mainly includes two types of portals: wall-type portals and cut-type portals.
[0113] It can be understood that the target tunnel length is the difference between the target light-dark boundary mileage design value and the target tunnel entrance mileage design value.
[0114] In a specific implementation, a gate type matching the target gate length may be determined from a potential gate length table according to the target gate length as the target gate type.
[0115] Step S50, determining the target portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data.
[0116] In the specific implementation, Figure 5 The technical roadmap for intelligent design of tunnel portals shown in the figure can first establish a tunnel portal light-dark boundary mileage prediction model and a portal mileage prediction model based on the tunnel data of the designed tunnel portal, and set the method for determining the portal type, portal length and portal subdivision type. Finally, the tunnel data of the tunnel portal to be designed can be used to obtain the light-dark boundary mileage and portal mileage of the tunnel portal to be designed according to the light-dark boundary mileage prediction model and the portal mileage prediction model. Finally, the portal type, portal length and portal subdivision type of the tunnel portal to be designed can be determined according to the method for determining the portal type, portal length and portal subdivision type.
[0117] In a feasible implementation manner, the step of determining the portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data includes: when the portal type is a cut-type portal, determining the tunnel length of the tunnel to be designed according to the target tunnel data; determining the number of openings based on the comparison result of the tunnel length and the critical portal length parameter; determining the portal subdivision type according to the target portal type and the number of openings.
[0118] It should be noted that the critical portal length parameter is pre-set.
[0119] In the specific implementation, the inverted cut portal, the oblique cut portal, the straight cut portal, etc. are all cut portals. The cut portal further determines the number of openings according to the tunnel length, thereby forming a subdivision type of portals with the number of openings. Specifically, the calculation formula for calculating the number of openings based on the tunnel length is as follows:
[0120]
[0121] Where T is the tunnel length, n k is the number of openings, and a, b, c, d are the critical portal length parameters.
[0122] In a feasible implementation manner, the step of determining the portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data includes: when the portal type is a wall-type portal, determining a first feature, a second feature, a third feature and a fourth feature according to the target portal mileage design value and the target tunnel data, wherein the first feature is a first height difference between a terrain point on the left side of the tunnel on the cross section at the target portal mileage design value and a first reference line, the second feature is a second height difference between a terrain point on the right side of the tunnel on the cross section at the target portal mileage design value and the first reference line, and the third feature is a first height difference between a terrain point on the right side of the tunnel on the cross section at the target portal mileage design value and the first reference line. The third height difference between the terrain point on the left side of the tunnel on the section and the second reference line, the fourth feature is the fourth height difference between the terrain point on the right side of the tunnel on the cross section at the design value of the target tunnel entrance mileage and the second reference line, the first reference line is a straight line passing through the top of the tunnel and parallel to the bottom of the tunnel on the cross section at the design value of the target tunnel entrance mileage, the second reference line is a straight line on the cross section at the design value of the target tunnel entrance mileage, the height difference with the center point of the tunnel is a preset distance and is parallel to the first reference line, and the second reference line is higher than the top of the tunnel; based on the wall-type portal subdivision category discrimination table, the target portal subdivision type is determined according to the first feature, the second feature, the third feature and the fourth feature.
[0123] In the specific implementation, generally wall-type portals, open-hole wall-type portals, etc. are all wall-type portals. When the target portal type corresponding to the tunnel to be designed is a wall-type portal, it is also necessary to calculate the tunnel slope support type at the tunnel entrance mileage to form a wall-type portal with a slope support type.
[0124] It can be understood that the left-side terrain point and the right-side terrain point can be set in advance, the left-side terrain point refers to the point on the left side of the cross-sectional terrain line, and the right-side terrain point refers to the point on the right side of the cross-sectional terrain line.
[0125] It should be noted that the subdivision types of the wall-type portal formed by the slope support types on the left and right sides of the tunnel opening can be jointly determined based on the first feature, the second feature, the third feature and the fourth feature.
[0126] In the specific implementation, Figure 6 As shown, feature 1 (i.e., the first feature) and feature 2 (i.e., the second feature) are the height differences between the terrain point A on the left side of the tunnel and the terrain point B on the right side and reference line 1 (i.e., the first reference line) on the cross section, respectively. Feature 3 (i.e., the third feature) and feature 4 (i.e., the fourth feature) are the height differences between the terrain point A on the left side of the tunnel and the terrain point B on the right side and reference line 2 (i.e., the second reference line) on the cross section, respectively. The specific calculation method of each feature is as follows:
[0127] f 1 =z A -zo -R
[0128] f 2 =z B -z o -R
[0129] f 3 =z A -z o -h 1
[0130] f 4 =z A -z o -h 1
[0131] In the formula, f 1 represents the first feature, f 2 represents the second feature, f 3 represents the third feature, f 4 represents the third feature, z o is the z coordinate value of the tunnel center point on the cross section, R is the tunnel radius, h 1 is the height difference between reference line 2 (i.e., the second reference line) and the center point of the tunnel, z A Indicates the z coordinate value of terrain point A (i.e., the terrain point on the left), z B Indicates the z coordinate value of terrain point B (that is, the terrain point on the right).
[0132] It should be noted that the wall-type opening subdivision category discrimination table is pre-constructed, and the wall-type opening subdivision type can be determined from the wall-type opening subdivision category discrimination table according to the first feature, the second feature, the third feature and the fourth feature.
[0133] In the specific implementation, the wall-type door subdivision classification discrimination table is shown in Table 1:
[0134] Table 1 Specific classification of wall-type openings
[0135]
[0136]
[0137] This embodiment obtains target tunnel data of a tunnel entrance to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data, and tunnel structure dimensions; inputs the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value; inputs the target tunnel data and the target light-dark boundary mileage design value into a portal mileage prediction model to obtain a target portal mileage design value; determines a target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determines a target portal type of the target portal length based on a potential portal length table; determines a target portal subdivision type according to the target portal mileage design value, the target portal type, and the target tunnel data. The present invention solves the technical problem that the traditional method of designing tunnel entrances is not only time-consuming and labor-intensive, but also highly dependent on the experience of designers. Compared with the existing technology, the present application can predict the light-dark boundary mileage and entrance mileage of the tunnel entrance to be designed through the established light-dark boundary mileage prediction model and the entrance mileage prediction model, so that the design of the tunnel entrance to be designed can be realized without repeated attempts by designers, thereby achieving efficient design. The present application also provides a unified method for determining the portal type and the portal subdivision type, and the design result is not affected by the subjectivity of the designer, so that the design result of the tunnel entrance to be designed is more stable and reliable.
[0138] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 7 , step S40 includes steps S401 to S403:
[0139] Step S401, determining the preferred order of portal types and determining the potential portal length range of each portal type;
[0140] It should be noted that the preferred order of portal types can be determined based on different tunnel working conditions, and the preferred order is tunnel inverted-cut portal, oblique-cut portal, wall-type portal and other portal types.
[0141] In a feasible implementation, the step of determining the potential portal length range of each portal type includes: counting the portal length range and open hole length range corresponding to each portal type; and fusing and deduplicating the portal length range and the open hole length range to obtain the potential portal length range of each portal type.
[0142] In the specific implementation, Figure 8As shown, the potential portal length of each portal type is determined based on the portal length range and the open hole length range. Specifically, the portal length ranges and open hole length ranges under different portal types can be counted, and the potential portal length range of the portal type can be obtained after fusion and deduplication based on the portal length range and the open hole length range.
[0143] Step S402, constructing a potential tunnel length table based on the preferred sequence and the potential tunnel length range;
[0144] It should be noted that the potential portal length table is designed according to the preferred order of portal types. For example, the portal types in the potential portal length table are sorted from top to bottom according to the preferred order.
[0145] Step S403, screening out screening gate types whose potential gate length range includes the target gate length in the potential gate length table, and determining the target gate type of the target gate length from the screening gate types according to the preferred order.
[0146] It should be noted that the screening portal type refers to all portal types whose potential portal length range in the potential portal length table includes the target portal length. After the screening portal type is determined, the portal type with the highest order is determined from the screening portal types in the preferred order, and this portal type is determined as the target portal type.
[0147] In a specific implementation, it can be determined in sequence according to the preferred order whether the potential portal length range of the portal type in the potential portal length table includes the target portal length. If it includes the target portal length, the portal type can be determined as the target portal type of the target portal length.
[0148] The first embodiment and the second embodiment are described in detail below in conjunction with a specific tunnel portal design data set:
[0149] 1. Collect the designed and constructed tunnel opening data sets and the undesigned tunnel opening data sets. The topographic point cloud data of a tunnel opening that has been designed and constructed is as follows: Fig. 9 As shown in Figure 1, the topographic point cloud data of a tunnel entrance to be designed is as follows: Fig.10 The other relevant parameters are shown in Table 2.
[0150] Table 2 Tunnel portal related parameters
[0151]
[0152]
[0153] 2. Based on the collected designed and constructed tunnel opening data sets, extract features and calculate the relative position of the light-dark boundary mileage, and establish a prediction model for the light-dark boundary mileage. The following uses the designed and constructed tunnel data sets in the case as an example to illustrate the specific process:
[0154] (2.1) Extracting sequence features. The feature values of the light-dark boundary mileage sequence extracted from the designed and constructed tunnels in this case are shown in Table 3. Here, the sequence length is set to 100.
[0155] Table 3 Characteristic value table of light-dark boundary mileage sequence
[0156]
[0157]
[0158] (2.2) Calculate the relative position of the light-dark boundary mileage. The relative position of the light-dark boundary mileage of the designed and constructed tunnel entrance in this case is 0.592.
[0159] (2.3) Establish a prediction model for the light-dark boundary mileage. The collected data set is divided into training set: test set = 80%: 20%. The loss value change trend of the light-dark boundary mileage prediction model established based on the LSTM network model is as follows: Fig.11 As shown in the figure, the loss value of the model on the training set and the test set is quickly reduced to a smaller value, and the difference between the two is not large, which shows that the established model is good.
[0160] 3. Based on the collected designed and constructed tunnel opening data sets, extract features and calculate the relative position of the opening mileage, and establish a prediction model for the opening mileage. The following uses the designed and constructed tunnel data sets in the case as an example to illustrate the specific process:
[0161] (3.1) Extracting sequence features of tunnel entrance mileage. The sequence feature values of tunnel entrance mileage extracted from the designed and constructed tunnels in this case are shown in Table 4, where the sequence length is set to 50.
[0162] Table 4. Table of characteristic values of tunnel mileage sequence
[0163]
[0164]
[0165] (3.2) Feature masking. The potential tunnel entrance mileage of this tunnel is 236627~236675m, and the non-potential tunnel entrance mileage is 236675~236685m. The potential tunnel entrance mileage and non-potential tunnel entrance mileage are mapped to the sequence features in (3.1). The features after masking are shown in Table 5.
[0166] Table 5. Table of characteristic values of tunnel mileage masking sequence
[0167]
[0168] (3.3) Calculate the relative position of the tunnel entrance mileage. In this case, the relative position of the tunnel entrance mileage is 0.414.
[0169] (3.4) Establish a prediction model for tunnel mileage. The collected data set is divided into training set: test set = 80%: 20%. The loss value change trend of the tunnel mileage prediction model established based on the LSTM network model is as follows: Fig.12 As shown in the figure, the loss value of the model on the training set and the test set is quickly reduced to a smaller value, and the difference between the two is not large, which shows that the established model is good.
[0170] 4. The specific process for determining the portal type and portal length for the tunnel in the case is as follows.
[0171] (4.1) Determine the potential portal length. The priority of portal types is beveled portal, beveled + open-cut portal, inverted portal, inverted + open-cut portal, open-cut portal. Their respective potential portal lengths are shown in Table 6.
[0172] Table 6 Potential tunnel length
[0173] Door Type Potential portal length Bevel 24m Bevel cut + bright hole 29~58m Reverse Cut 15m Inverted cut + bright hole 20~58m Myeongdong 10~58m
[0174] (4.2) Determine the type and length of the tunnel. The difference between the light-dark boundary mileage in step 3 and the tunnel entrance mileage in step 2 is 24m. It can be known that the oblique-cut tunnel includes this distance, so the main type of the tunnel is oblique-cut and the length of the tunnel is 24m.
[0175] 5. Since the tunnel portal is mainly a cut-type portal, the subdivision type of the portal type can be determined based on the tunnel length. Given the parameters a=2000m, b=4000m, c=6000m, d=8000m, the subdivision type of the portal is a two-hole oblique-cut portal.
[0176] 6. Repeat steps 2 to 5 above to obtain the design value of the tunnel to be designed. The specific process is as follows.
[0177] (6.1) Determine the light-dark boundary mileage. Input the basic data of the tunnel to be designed into the light-dark boundary mileage prediction model in step 2, and the light-dark boundary mileage prediction value can be obtained as 0.720, which is further converted into an absolute distance, that is, the light-dark boundary mileage design value is 385471m.
[0178] (6.2) Determine the tunnel entrance mileage. Input the basic data of the tunnel to be designed and the design value of the light-dark boundary mileage in step 2 into the tunnel entrance mileage prediction model in step 3, and the predicted value of the tunnel entrance mileage can be obtained as 0.428, which is further converted into an absolute distance, that is, the design value of the tunnel entrance mileage is 385450m.
[0179] (6.3) Determine the type and length of the tunnel. According to the rule in step 4, the design value of the light-dark boundary mileage in step (6.1) and the design value of the tunnel entrance mileage in step (6.2) can be obtained as the main type of the tunnel door is the oblique cut type + open tunnel door, and the length of the tunnel door is 14m.
[0180] (6.4) Determine the portal subdivision type. Input the basic data, the portal mileage design value in step (6.2), and the portal category in step (6.3) into the rules in step 5, and the portal subdivision type is the oblique-cut portal without opening.
[0181] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the intelligent design method of the overall tunnel portal solution of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0182] This application also provides an intelligent design device for the overall solution of the tunnel entrance, please refer to Fig.13 , the intelligent design device of the overall solution of the tunnel portal includes:
[0183] An acquisition module 10 is used to acquire target tunnel data of a tunnel portal to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data and tunnel structure dimensions;
[0184] An input module 20 is used to input the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value;
[0185] The input module 20 is further used to input the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the target tunnel entrance mileage design value;
[0186] A determination module 30 is used to determine a target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determine a target portal type of the target portal length based on a potential portal length table;
[0187] The determination module 30 is further used to determine the target portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data.
[0188] The intelligent design device for the overall solution of the tunnel portal provided by the present application adopts the intelligent design method for the overall solution of the tunnel portal in the above-mentioned embodiment, which can solve the technical problem that the traditional method of designing the tunnel portal is not only time-consuming and labor-intensive, but also highly dependent on the experience of the designer. Compared with the prior art, the beneficial effects of the intelligent design device for the overall solution of the tunnel portal provided by the present application are the same as the beneficial effects of the intelligent design method for the overall solution of the tunnel portal provided by the above-mentioned embodiment, and the other technical features of the intelligent design device for the overall solution of the tunnel portal are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.
[0189] The present application provides an intelligent design device for an overall solution of a tunnel portal, the intelligent design device for an overall solution of a tunnel portal comprising: at least one processor; and a memory communicatively connected to 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 so that the at least one processor can execute the intelligent design method for the overall solution of a tunnel portal in the above-mentioned embodiment one.
[0190] Reference below Fig.14 , which shows a schematic diagram of the structure of an intelligent design device for the overall solution of the tunnel portal suitable for implementing the embodiment of the present application. The intelligent design device for the overall solution of the tunnel portal in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.14 The intelligent design device for the overall solution of the tunnel portal shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0191] like Fig.14As shown, the intelligent design device for the overall solution of the tunnel portal may include a processing device 1001 (such as 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 to a random access memory (RAM) 1004. Various programs and data required for the operation of the intelligent design device for the overall solution of the tunnel portal are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the intelligent design device for the overall solution of the tunnel portal to communicate wirelessly or wired with other devices to exchange data. Although the figure shows the intelligent design device for the overall solution of the tunnel portal with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.
[0192] 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, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0193] The intelligent design device for the overall solution of the tunnel portal provided by the present application adopts the intelligent design method for the overall solution of the tunnel portal in the above-mentioned embodiment, which can solve the technical problem that the traditional method of designing the tunnel portal is not only time-consuming and labor-intensive, but also highly dependent on the experience of the designer. Compared with the prior art, the beneficial effects of the intelligent design device for the overall solution of the tunnel portal provided by the present application are the same as the beneficial effects of the intelligent design method for the overall solution of the tunnel portal provided by the above-mentioned embodiment, and the other technical features of the intelligent design device for the overall solution of the tunnel portal are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0194] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0195] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0196] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the intelligent design method for the overall solution of the tunnel portal in the above-mentioned embodiment.
[0197] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more 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 this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0198] The computer-readable storage medium may be included in the intelligent design device for the overall solution of the tunnel portal; or may exist independently without being assembled into the intelligent design device for the overall solution of the tunnel portal.
[0199] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the intelligent design device for the overall solution of the tunnel portal, the intelligent design device for the overall solution of the tunnel portal: obtains the target tunnel data of the tunnel portal to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data and tunnel structure dimensions; inputs the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value; inputs the target tunnel data and the target light-dark boundary mileage design value into a portal mileage prediction model to obtain a target portal mileage design value; determines a target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determines the target portal type of the target portal length based on a potential portal length table; determines the target portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data.
[0200] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0201] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0202] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0203] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned intelligent design method for the overall solution of the tunnel portal, and can solve the technical problem that the traditional method of designing the tunnel portal is not only time-consuming and labor-intensive, but also highly dependent on the experience of the designer. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the intelligent design method for the overall solution of the tunnel portal provided by the above-mentioned embodiment, and will not be repeated here.
[0204] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the intelligent design method for the overall solution of the tunnel portal as described above.
[0205] The computer program product provided by the present application can solve the technical problem that the traditional method of designing a tunnel portal is not only time-consuming and labor-intensive, but also highly dependent on the experience of the designer. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the intelligent design method for the overall solution of the tunnel portal provided by the above embodiment, and will not be repeated here.
[0206] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. An intelligent design method for the overall scheme of a tunnel portal, characterized in that: The method comprises: Acquire target tunnel data of the tunnel entrance to be designed, wherein the target tunnel data includes terrain point cloud data, tunnel line data, and tunnel structure dimensions; Inputting the target tunnel data into a light-dark boundary mileage prediction model to obtain a target light-dark boundary mileage design value; Input the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the target tunnel entrance mileage design value; Determine the target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determine the target portal type of the target portal length based on the potential portal length table; The target portal subdivision type is determined according to the target portal mileage design value, the target portal type and the target tunnel data.
2. The method according to claim 1, characterized in that The step of determining the target portal length according to the target light-dark boundary mileage design value and the target portal mileage design value, and determining the target portal type of the target portal length based on the potential portal length table comprises: Determine the preferred order of portal types and determine the range of potential portal lengths for each portal type; Based on the preferred order and the potential tunnel length range, construct a potential tunnel length table; The potential portal length table contains the screening portal types whose potential portal length range includes the target portal length, and the target portal type of the target portal length is determined from the screening portal types according to the preferred order.
3. The method according to claim 2, characterized in that The steps to determine the range of potential portal lengths for each portal type include: Count the length range of the tunnel and the length range of the open hole corresponding to each tunnel type; The portal length range and the open hole length range are fused and deduplicated to obtain the potential portal length range of each portal type.
4. The method according to claim 1, characterized in that The step of determining the portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data comprises: When the portal type is a cut-type portal, determining the tunnel length of the tunnel to be designed according to the target tunnel data; Determining the number of openings based on a comparison result of the tunnel length and a critical portal length parameter; The subdivision type of the portal is determined according to the target portal type and the number of openings.
5. The method according to claim 1, characterized in that The step of determining the portal subdivision type according to the target portal mileage design value, the target portal type and the target tunnel data comprises: When the portal type is a wall-type portal, a first feature, a second feature, a third feature and a fourth feature are determined according to the target portal mileage design value and the target tunnel data, wherein the first feature is a first height difference between a terrain point on the left side of the tunnel on the cross section at the target portal mileage design value and a first reference line, the second feature is a second height difference between a terrain point on the right side of the tunnel on the cross section at the target portal mileage design value and the first reference line, the third feature is a third height difference between a terrain point on the left side of the tunnel on the cross section at the target portal mileage design value and the second reference line, the fourth feature is a fourth height difference between a terrain point on the right side of the tunnel on the cross section at the target portal mileage design value and the second reference line, the first reference line is a straight line on the cross section at the target portal mileage design value passing through the top of the tunnel and parallel to the bottom of the tunnel, the second reference line is a straight line on the cross section at the target portal mileage design value having a preset distance difference in height from the center point of the tunnel and parallel to the first reference line, and the second reference line is higher than the top of the tunnel; Based on the wall-type portal subdivision category discrimination table, the target portal subdivision type is determined according to the first feature, the second feature, the third feature and the fourth feature.
6. The method according to claim 1, characterized in that The step of obtaining the target tunnel data of the tunnel opening to be designed also includes: Acquire tunnel data of constructed tunnel openings, wherein the tunnel data includes terrain point cloud data, line data, tunnel structure dimensions, and design parameters; The light-dark boundary mileage prediction model is established based on the tunnel data, and the tunnel entrance mileage prediction model is established based on the tunnel data.
7. The method according to claim 6, characterized in that The step of establishing the light-dark boundary mileage prediction model based on the tunnel data comprises: Determine the design starting mileage, design ending mileage, bright and dark boundary mileage and design axis according to the tunnel data; Uniformly select multiple mileages along the design axis within the range of the design start mileage and the design end mileage, calculate the first boundary mileage feature and the second boundary mileage feature of each mileage on the cross section in turn, and determine the first sequence feature according to the first boundary mileage feature and the second boundary mileage feature, wherein the first boundary mileage feature is the distance between the topographic line and the tunnel top on the cross section, and the second boundary mileage feature is the terrain slope on the cross section; Determine the relative position of the light-dark boundary mileage of the constructed tunnel entrance according to the designed starting mileage, the designed ending mileage and the light-dark boundary mileage; A first data set is constructed based on the first sequence features and the relative positions of the light-dark boundary mileages, and a light-dark boundary mileage prediction model is established based on the first data set.
8. The method according to claim 7, characterized in that The step of establishing a tunnel entrance mileage prediction model based on the tunnel data comprises: Determine the tunnel boundary design mileage, light-dark boundary mileage and design axis according to the tunnel data; Uniformly select multiple mileages along the design axis within the range of the tunnel boundary design mileage and the light-dark boundary mileage, calculate the first hole opening mileage feature and the second hole opening mileage feature of each mileage on the cross section in turn, and determine the second sequence feature according to the first hole opening mileage feature and the second hole opening mileage feature, wherein the first hole opening mileage feature is the distance between the left terrain line and the retaining wall on the cross section, and the second hole opening mileage feature is the distance between the right terrain line and the retaining wall on the cross section; Performing feature masking processing on the second sequence feature to obtain a second target sequence feature; Determine the tunnel entrance mileage according to the tunnel data, and determine the relative position of the tunnel entrance mileage of the constructed tunnel entrance according to the tunnel entrance mileage; Based on the second target sequence features and the relative position of the tunnel entrance mileage, a second data set is constructed, and based on the second data set, the tunnel entrance mileage prediction model is established.
9. The method according to claim 1, characterized in that The step of inputting the target tunnel data into the light-dark boundary mileage prediction model to obtain the target light-dark boundary mileage design value comprises: Inputting the target tunnel data into a tunnel entrance light-dark boundary mileage prediction model to obtain the relative position of the target light-dark boundary mileage; Based on the light-dark boundary mileage conversion formula, the relative position of the target light-dark boundary mileage is converted into the target light-dark boundary mileage design value.
10. The method according to claim 1, characterized in that The step of inputting the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the target tunnel entrance mileage design value comprises: Input the target tunnel data and the target light-dark boundary mileage design value into the tunnel entrance mileage prediction model to obtain the relative position of the tunnel entrance mileage; Based on the tunnel opening mileage conversion formula, the relative position of the tunnel opening mileage is converted into the tunnel opening mileage design value.
Citation Information
Patent Citations
Tunnel hole opening position automatic comparison and selection BIM (building information modeling) design method
CN106202648A
Tunnel parameter prediction model training method and device and electronic equipment
CN115600285A
Digital design method for tunnel portal
CN116305430A
Knowledge graph driven tunnel portal structure scheme design method
CN117610128A
Intelligent design method for tunnel portal length
CN118296692A
Cited By
Prediction method of rule engine and deep learning combined high-speed railway tunnel shaft construction method
CN120387224A
A prediction method for high-speed railway tunnel construction methods based on a combination of rule engine and deep learning
CN120387224B
