A method and system for generating tunnel construction progress model based on artificial intelligence

Abstract

The present invention provides a method and system for generating a tunnel construction progress model based on artificial intelligence, which relates to the field of artificial intelligence technology. First, the tunnel path of the target tunnel is constructed in three-dimensional geographic information, and the rock structure detection information of the target area is imported into the three-dimensional geographic information; then, the tunnel path is divided into multiple tunnel excavation granularities; then, the rock structure information, excavation depth and burial depth information corresponding to each tunnel excavation granularity are input into the construction period prediction model for prediction, and the predicted construction period corresponding to each tunnel excavation granularity is obtained; finally, a tunnel construction progress model is generated based on the predicted construction period and three-dimensional geographic information. The above method predicts the construction period based on the information of different tunnel excavation granularities, and can finely predict the construction period of different tunnel excavation granularities, thereby improving the progress accuracy of the entire tunnel construction, and facilitating an intuitive understanding of the progress of the entire project.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based tunnel construction progress model generation method and system. Background Art

[0002] my country is a mountainous country. In the process of highway or railway construction, the problem of tunnel construction is inevitable. The construction period of tunnel construction cannot be accurately predicted due to the complex construction environment, which leads to the completion of the entire highway or railway being restricted by tunnel construction. Summary of the invention

[0003] In order to at least overcome the above-mentioned deficiencies in the prior art, in a first aspect, the present invention provides a method for generating a tunnel construction progress model based on artificial intelligence, the method comprising:

[0004] Obtaining three-dimensional geographic information of a target area according to geographic location information of a target tunnel, and constructing a tunnel path of the target tunnel in the three-dimensional geographic information;

[0005] Importing the rock structure detection information of the target area into the three-dimensional geographic information;

[0006] Dividing the tunnel path into a plurality of tunnel excavation granularities, obtaining rock layer structure information at a position corresponding to each tunnel excavation granularity and an excavation depth between each tunnel excavation granularity and a tunnel entrance, and obtaining burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path;

[0007] Input each tunnel excavation granularity, the rock layer structure information at the position corresponding to each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the buried depth information of each tunnel excavation granularity into the construction period prediction model for prediction, and obtain the predicted construction period corresponding to each tunnel excavation granularity;

[0008] A tunnel construction progress model is generated based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information.

[0009] In a possible implementation, the step of obtaining three-dimensional geographic information of a target area according to geographic location information of a target tunnel, and constructing a tunnel path of the target tunnel in the three-dimensional geographic information includes:

[0010] Acquire the geographical location information of the target tunnel, wherein the geographical location information of the target tunnel includes the tunnel direction, the altitude information of the tunnel, the length of the tunnel and the longitude and latitude coordinates of the tunnel entrance;

[0011] Determine a target area where the target tunnel is located based on the geographical location information of the target tunnel, wherein the target area is determined by a plurality of points having longitude and latitude coordinates, and the target tunnel is located in the target area;

[0012] The three-dimensional geographic information corresponding to the target area is acquired from the three-dimensional image of the earth, and the tunnel path of the target tunnel is constructed in the three-dimensional geographic information.

[0013] In a possible implementation, before the step of importing the rock structure detection information of the target area into the three-dimensional geographic information, the method further includes:

[0014] Acquire rock formation structure detection information of the target area, wherein the rock formation structure detection information includes rock formation structure distribution at different locations in the target area at different altitudes;

[0015] The step of dividing the tunnel path into a plurality of tunnel excavation granularities, obtaining rock layer structure information at a position corresponding to each tunnel excavation granularity and an excavation depth between each tunnel excavation granularity and a tunnel entrance, and obtaining burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path comprises:

[0016] Dividing the tunnel path into a plurality of tunnel excavation granularities, and determining an altitude interval of a tunnel portion corresponding to each tunnel excavation granularity;

[0017] Determine the rock structure information at the position corresponding to each tunnel excavation granularity based on the altitude interval corresponding to each tunnel excavation granularity and the rock structure distribution at different positions and altitudes in the target area;

[0018] Calculating the excavation depth between each tunnel excavation granularity and the tunnel entrance;

[0019] Based on the altitude information at each position in the tunnel path and the altitude information of the ground surface corresponding to the position, the burial depth information of each tunnel excavation granularity is calculated.

[0020] In a possible implementation, before the step of inputting the excavation granularity of each tunnel, the rock structure information at the position corresponding to each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the buried depth information of each tunnel excavation granularity into the construction period prediction model for prediction to obtain the predicted construction period corresponding to each tunnel excavation granularity, the method further includes:

[0021] The step of training and obtaining the construction period prediction model comprises:

[0022] Acquire a training sample set, wherein the training sample set is derived from historical tunnel construction data, the training sample set includes training samples and corresponding sample construction periods, the training samples include tunnel excavation granularity samples, rock structure information corresponding to the tunnel excavation granularity samples, excavation depths corresponding to the tunnel excavation granularity samples, and burial depth information corresponding to the tunnel excavation granularity samples;

[0023] The training samples in the training sample set are input into the deep learning model for training to obtain the predicted construction period corresponding to the tunnel excavation granularity sample, and the loss function value of the deep learning model is calculated based on the predicted construction period and the corresponding sample construction period. When the loss function value does not meet the preset conditions, the model parameters in the deep learning model are updated and re-trained until the loss function value meets the preset conditions, and the deep learning model when the loss function value meets the preset conditions is used as the construction period prediction model.

[0024] In a possible implementation, when the tunnel excavation granularity in the target tunnel has been excavated, the method further includes a step of updating the construction period prediction model, the step including:

[0025] Acquire the tunnel excavation granularity that has been excavated in the target tunnel, the rock layer structure information at the position corresponding to the tunnel excavation granularity that has been excavated, the excavation depth of the tunnel excavation granularity that has been excavated, the buried depth information of the tunnel excavation granularity that has been excavated, and the actual construction period of the tunnel excavation granularity that has been excavated;

[0026] If the difference between the predicted construction period of the tunnel excavation granularity that has been excavated in the target tunnel by the construction period prediction model and the actual construction period is greater than the preset time difference, the tunnel excavation granularity that has been excavated in the target tunnel, the rock layer structure information at the position corresponding to the tunnel excavation granularity that has been excavated, the excavation depth of the tunnel excavation granularity that has been excavated, and the buried depth information of the tunnel excavation granularity that has been excavated are added to the training sample set as new training samples;

[0027] The construction cycle prediction model is trained using new training samples, and the model parameters of the construction cycle prediction model are adjusted until the difference between the predicted construction cycle of the tunnel excavation granularity that has been excavated in the target tunnel by the construction cycle prediction model and the actual construction cycle of the tunnel excavation granularity that has been excavated in the target tunnel is less than the preset time difference, and the construction cycle prediction model at this time is used as the updated construction cycle prediction model.

[0028] In a possible implementation, the updated construction period prediction model is used to re-predict the construction period of the unexplored tunnel excavation granularity in the target tunnel, and the predicted construction period of the unexplored tunnel excavation granularity in the target tunnel is updated.

[0029] In a possible implementation, the method further includes:

[0030] Acquire on-site construction image information of the tunnel excavation granularity currently being excavated in the target tunnel;

[0031] Performing image recognition on the rock layer structure of the tunnel excavation granularity currently being excavated based on the on-site construction image information to obtain actual rock layer structure information of the tunnel excavation granularity currently being excavated;

[0032] Determine whether the rock layer structure information of the tunnel excavation granularity currently being excavated is consistent with the actual rock layer structure information. If they are inconsistent, update the rock layer structure information of the tunnel excavation granularity currently being excavated and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity currently being excavated to the corresponding actual rock layer structure information;

[0033] The construction period prediction model is used to re-predict the construction period of the tunnel excavation granularity being excavated in the target tunnel and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity being currently excavated, and the predicted construction period of the tunnel excavation granularity being excavated in the target tunnel and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity being currently excavated is updated.

[0034] In a possible implementation, the step of generating a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information includes:

[0035] The total predicted construction period for completing the target tunnel is calculated based on the predicted construction period corresponding to each tunnel excavation granularity;

[0036] The total construction progress of the target tunnel is calculated based on the total construction time of all tunneling granularities that have been excavated and the total predicted construction period, and the total construction progress of the target tunnel is integrated into the three-dimensional geographic information in the form of a graphical plug-in to obtain the tunnel construction progress model;

[0037] Wherein, the step of generating a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information further includes:

[0038] In the three-dimensional geographic information, a tunnel path corresponding to the tunnel excavation granularity that has been excavated is represented by a first grayscale, a tunnel path corresponding to the tunnel excavation granularity that is being excavated is represented by a second grayscale, and a tunnel path corresponding to the tunnel excavation granularity that has not been excavated is represented by a third grayscale;

[0039] Based on the construction time of the tunnel excavation granularity being excavated and the predicted construction period of the tunnel excavation granularity being excavated, the construction progress of the tunnel excavation granularity being excavated is calculated, and the construction progress of the tunnel excavation granularity being excavated is integrated into the three-dimensional geographic information in the form of a graphical plug-in.

[0040] In a second aspect, the present invention further provides a tunnel construction progress model generation system based on artificial intelligence, the system comprising:

[0041] A construction module, used to obtain three-dimensional geographic information of a target area according to the geographic location information of a target tunnel, and to construct a tunnel path of the target tunnel in the three-dimensional geographic information;

[0042] An import module, used for importing the rock structure detection information of the target area into the three-dimensional geographic information;

[0043] A division module, used to divide the tunnel path into a plurality of tunnel excavation granularities, obtain rock layer structure information at a position corresponding to each tunnel excavation granularity and the excavation depth between each tunnel excavation granularity and the tunnel entrance, and obtain the burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path;

[0044] A prediction module is used to input the excavation granularity of each tunnel, the rock structure information at the position corresponding to each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the burial depth information of each tunnel excavation granularity into the construction period prediction model for prediction, so as to obtain the predicted construction period corresponding to each tunnel excavation granularity;

[0045] A generation module is used to generate a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information.

[0046] In a third aspect, the present invention also provides a computer device, comprising a processor, a computer-readable storage medium and a communication interface, wherein the computer-readable storage medium, the communication interface and the processor are connected via a bus system, the computer-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the computer-readable storage medium to execute the artificial intelligence-based tunnel construction progress model generation method described in any possible implementation method of the first aspect.

[0047] In a fourth aspect, the present invention further provides a computer-readable storage medium, in which instructions are stored, which, when executed, enable a computer to execute the method for generating a tunnel construction progress model based on artificial intelligence in any possible implementation of the first aspect.

[0048] In the above scheme provided by the present invention, first, the three-dimensional geographic information of the target area is obtained according to the geographic location information of the target tunnel, and the tunnel path of the target tunnel is constructed in the three-dimensional geographic information, and the rock structure detection information of the target area is imported into the three-dimensional geographic information; then, the tunnel path is divided into multiple tunnel excavation granularities, and the rock structure information, excavation depth and burial depth information corresponding to each tunnel excavation granularity are obtained; then, the rock structure information, excavation depth and burial depth information corresponding to each tunnel excavation granularity are input into the construction period prediction model for prediction, and the predicted construction period corresponding to each tunnel excavation granularity is obtained; finally, the tunnel construction progress model is generated based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information. The above method divides the tunnel path into multiple tunnel excavation granularities, and predicts the construction period based on the information of different tunnel excavation granularities, so that the construction period of different tunnel excavation granularities can be predicted in a refined manner, thereby improving the progress accuracy of the entire tunnel construction, facilitating an intuitive understanding of the progress of the entire project, and improving the efficiency of tunnel construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A schematic diagram of a process flow of a method for generating a tunnel construction progress model based on artificial intelligence provided in an embodiment of the present application;

[0051] Figure 2 One of the partial flow diagrams of the method for generating a tunnel construction progress model based on artificial intelligence provided in an embodiment of the present application;

[0052] Figure 3 A second partial flow chart of a method for generating a tunnel construction progress model based on artificial intelligence provided in an embodiment of the present application;

[0053] Figure 4 A third partial flow chart of a method for generating a tunnel construction progress model based on artificial intelligence provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of functional modules of a system for generating a tunnel construction progress model based on artificial intelligence provided by an embodiment of the present invention;

[0055] Figure 6 A schematic diagram of the structural framework of a computer device for implementing the above-mentioned artificial intelligence-based tunnel construction progress model generation method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The present invention is described in detail below with reference to the accompanying drawings. The specific operation method in the method embodiment can also be applied to the system embodiment or system embodiment.

[0057] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the embodiment of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0058] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0059] See also Figure 1 The method for generating a tunnel construction progress model based on artificial intelligence provided in the embodiment of the present application can be executed by a computer device. In other embodiments, the order of some steps in the method for generating a tunnel construction progress model based on artificial intelligence in the embodiment of the present application can be exchanged with each other according to actual needs, or some of the steps can be omitted or deleted. The detailed steps of the method for generating a tunnel construction progress model based on artificial intelligence executed by a computer device are introduced as follows.

[0060] Step S110, obtaining three-dimensional geographic information of the target area according to the geographic location information of the target tunnel, and constructing a tunnel path of the target tunnel in the three-dimensional geographic information.

[0061] In this embodiment, the geographic location information of the target tunnel may include the tunnel direction, tunnel altitude information, tunnel length and longitude and latitude coordinates of the tunnel entrance, wherein the target tunnel may be a planned tunnel to be built or a tunnel under construction.

[0062] The target area is determined according to the geographical location information of the target tunnel. The target area covers the extension area of ​​the target tunnel. The three-dimensional geographical information of the target area includes the topography and landforms in the target area, such as mountains, rivers, canyons, etc.

[0063] Step S120, importing the rock structure detection information of the target area into the three-dimensional geographic information.

[0064] Before step S120, the method for generating a tunnel construction progress model based on artificial intelligence provided in this embodiment further includes obtaining rock formation structure detection information of the target area, wherein the rock formation structure detection information of the target area refers to the rock formation structure information of the target area explored on-site by the exploration personnel before planning the tunnel path, and the rock formation structure information includes the distribution of rock formation structures at different altitudes in different areas. The rock formation structure detection information of the target area can be input into the computer device by means of data transmission.

[0065] The rock structure detection information of the target area is imported into the three-dimensional geographic information, and a mapping relationship between the rock structure detection information of the target area and different positions and altitudes in the three-dimensional geographic information is established, that is, the corresponding rock structure information is configured at different positions and altitudes in the three-dimensional geographic information.

[0066] Step S130, divide the tunnel path into multiple tunnel excavation granularities, obtain the rock layer structure information at the corresponding position of each tunnel excavation granularity and the excavation depth between each tunnel excavation granularity and the tunnel entrance, and obtain the burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path.

[0067] In this step, the tunnel path is divided into multiple tunnel excavation granularities, wherein the tunnel excavation granularity corresponds to a tunnel construction section of a certain length, for example, the tunnel excavation granularity corresponds to a tunnel construction section of 20 meters. In this embodiment, the lengths of the tunnel construction sections corresponding to the multiple tunnel excavation granularities formed by the tunnel path division can be the same or different. Exemplarily, the tunnel excavation granularity can be divided based on the rock layer structure through which the tunnel path passes, and the tunnel path parts of the same rock layer structure are divided into tunnel excavation granularities of the same length, and the tunnel path parts of different rock layer structures are divided into tunnel excavation granularities of different lengths. For example, when the rock layer structure is granite, the tunnel path part corresponding to the granite is divided into a tunnel excavation granularity of 20 meters in length; when the rock layer structure is dolomite, the tunnel path part corresponding to the dolomite is divided into a tunnel excavation granularity of 30 meters in length. In addition, the tunnel excavation granularity can also be divided according to the excavation depth between the excavation position and the tunnel entrance. The deeper the excavation depth, the smaller the length of the corresponding tunnel excavation granularity. In addition, other methods can be used to divide the tunnel path into multiple tunnel excavation granularities, which will not be described here.

[0068] Step S140, input each tunnel excavation granularity, the rock structure information at the position corresponding to each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the burial depth information of each tunnel excavation granularity into the construction period prediction model for prediction, and obtain the predicted construction period corresponding to each tunnel excavation granularity.

[0069] In this step, the corresponding predicted construction period can be predicted based on the rock structure information, excavation depth and burial depth information of different tunnel excavation granularity. Compared with the method of predicting the construction period of the entire tunnel path, the prediction accuracy of the construction period can be improved.

[0070] Step S150, generating a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information.

[0071] In the method provided above, since the rock structure information, excavation depth and burial depth information at different positions of the tunnel path may be different, the construction difficulty during construction will also be different, which will affect the construction speed. Compared with the method of predicting the construction period of the entire tunnel path, the above method can improve the prediction accuracy of the construction period, and can improve the progress accuracy of the entire tunnel construction, which is convenient for intuitively understanding the progress of the entire project and improving the efficiency of tunnel construction.

[0072] Further, in this embodiment, step S110 can be implemented in the following manner.

[0073] First, obtain the geographic location information of the target tunnel.

[0074] Next, a target area where the target tunnel is located is determined based on the geographical location information of the target tunnel.

[0075] The target area is determined by a plurality of points with longitude and latitude coordinates. Specifically, the target area may be formed by a plurality of points with longitude and latitude coordinates. For example, the target area may be a rectangular area formed by four points with longitude and latitude coordinates.

[0076] Then, three-dimensional geographic information corresponding to the target area is obtained from the three-dimensional image of the earth, and a tunnel path of the target tunnel is constructed in the three-dimensional geographic information.

[0077] The topography and landforms of the target area are obtained based on the three-dimensional geographic information, the topography and landforms of the target area are processed, and the tunnel path of the target tunnel is constructed in the three-dimensional geographic information, so that the topography and landforms of the target area are in a semi-transparent state and the tunnel path of the target tunnel can be observed.

[0078] Further, in this embodiment, step S130 can be implemented in the following manner.

[0079] Firstly, the tunnel path is divided into a plurality of tunnel excavation granularities, and the altitude interval of the tunnel portion corresponding to each tunnel excavation granularity is determined.

[0080] Next, based on the altitude interval corresponding to each tunnel excavation granularity and the rock structure distribution at different altitudes at different locations in the target area, the rock structure information at the position corresponding to each tunnel excavation granularity is determined, wherein the tunnel construction efficiency corresponding to different rock structure distributions is different.

[0081] Next, the excavation depth between each tunnel excavation granularity and the tunnel entrance is calculated, that is, the distance between the tunnel excavation granularity and the tunnel entrance. The deeper the excavation depth, the greater the impact on the tunnel construction efficiency. Generally speaking, the deeper the excavation depth, the lower the tunnel construction efficiency.

[0082] Then, based on the altitude information at each position in the tunnel path and the altitude information of the ground surface corresponding to the position, the burial depth information of each tunnel excavation granularity is calculated.

[0083] Among them, the construction efficiency of tunnel construction is also related to the burial depth. Generally speaking, the deeper the burial depth, the greater the possibility of rock burst, water gushing and landslide, and the lower the construction efficiency of tunnel construction.

[0084] Furthermore, before step S140, the method provided in this embodiment also includes the step of training and obtaining a construction period prediction model, please refer to Figure 2 , this step can be achieved in the following way.

[0085] Step S161, obtaining a training sample set.

[0086] In this step, the training sample set is derived from historical tunnel construction data, wherein the historical tunnel construction data may be completed or unfinished tunnel construction data of the same domestic construction unit within a preset time period (for example, the last five years), or may be completed tunnel construction data of different domestic construction units within a preset time period.

[0087] The training sample set includes training samples and corresponding sample construction periods, and the training samples include tunnel excavation granularity samples, rock structure information corresponding to the tunnel excavation granularity samples, excavation depths corresponding to the tunnel excavation granularity samples, and burial depth information corresponding to the tunnel excavation granularity samples, wherein the tunnel excavation granularity samples correspond to a tunnel construction section of a certain length.

[0088] Step S162: Input the training samples in the training sample set into the deep learning model for training to obtain the predicted construction period corresponding to the tunnel excavation granularity sample, calculate the loss function value of the deep learning model based on the predicted construction period and the corresponding sample construction period, and when the loss function value does not meet the preset conditions, update the model parameters in the deep learning model and re-train until the loss function value meets the preset conditions, and use the deep learning model when the loss function value meets the preset conditions as the construction period prediction model.

[0089] Furthermore, when the target tunnel has begun construction, that is, when the tunnel excavation granularity in the target tunnel has been excavated, the method provided in this embodiment also includes the step of updating the construction period prediction model, such as Figure 3 As shown, the step of updating the construction period prediction model can also be implemented in the following way.

[0090] Step S171, obtain the tunnel excavation granularity that has been excavated in the target tunnel, the rock layer structure information at the corresponding position of the tunnel excavation granularity that has been excavated, the excavation depth of the tunnel excavation granularity that has been excavated, the burial depth information of the tunnel excavation granularity that has been excavated, and the actual construction period of the tunnel excavation granularity that has been excavated.

[0091] In this step, actual excavation information of the tunnel excavation granularity that has been excavated in the target tunnel is obtained, wherein the actual excavation information includes the actual construction period of the tunnel excavation granularity that has been excavated.

[0092] Step S172, if the difference between the predicted construction period of the tunnel excavation granularity that has been excavated in the target tunnel by the construction period prediction model and the actual construction period is greater than the preset time difference, the tunnel excavation granularity that has been excavated in the target tunnel, the rock structure information at the corresponding position of the tunnel excavation granularity that has been excavated, the excavation depth of the tunnel excavation granularity that has been excavated, and the burial depth information of the tunnel excavation granularity that has been excavated are added to the training sample set as new training samples.

[0093] In this step, if the difference between the predicted construction period of the tunnel excavation granularity that has been excavated in the target tunnel and the actual construction period of the construction period prediction model is greater than the preset time difference, the training sample set is updated and the construction period prediction model is updated; otherwise, the training sample set and the construction period prediction model are not processed.

[0094] Step S173, use new training samples to train the construction cycle prediction model, adjust the model parameters of the construction cycle prediction model, until the difference between the predicted construction cycle of the tunnel excavation granularity that has been excavated in the target tunnel by the construction cycle prediction model and the actual construction cycle of the tunnel excavation granularity that has been excavated in the target tunnel is less than the preset time difference, and use the construction cycle prediction model at this time as the updated construction cycle prediction model.

[0095] Furthermore, the method provided in this embodiment also includes using the updated construction period prediction model to re-predict the construction period of the un-excavated tunnel excavation granularity in the target tunnel, and updating the predicted construction period of the un-excavated tunnel excavation granularity in the target tunnel.

[0096] In the above scheme, by updating the construction period prediction model, the prediction error caused by the difference between the historical tunnel construction environment and the target tunnel construction environment can be resolved, and the prediction accuracy of the construction period of the target tunnel can be improved.

[0097] Furthermore, the method provided in this embodiment also includes the following steps.

[0098] Step S210, obtaining on-site construction image information of the tunnel excavation granularity currently being excavated in the target tunnel.

[0099] Exemplarily, on-site construction image information of the tunnel excavation granularity currently being excavated in the target tunnel can be obtained through an image acquisition device, and the on-site construction image information can be transmitted to a computer device, wherein the on-site construction image information includes tunnel rock formation images of the tunnel excavation granularity being excavated.

[0100] Step S220, performing image recognition on the rock layer structure of the tunnel excavation granularity currently being excavated based on the on-site construction image information, and obtaining actual rock layer structure information of the tunnel excavation granularity currently being excavated.

[0101] In this step, the computer device can obtain the actual rock structure information of the tunnel excavation granularity currently being excavated through image recognition.

[0102] Step S230, determine whether the rock layer structure information of the tunnel excavation granularity currently being excavated is consistent with the actual rock layer structure information. If inconsistent, update the rock layer structure information of the tunnel excavation granularity currently being excavated and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity currently being excavated to the corresponding actual rock layer structure information.

[0103] Since there are detection errors in the rock structure detection conducted before the construction of the target tunnel begins, if it is found in actual excavation that the rock structure information of the tunnel excavation granularity currently being excavated is inconsistent with the actual rock structure information, the rock structure information of the tunnel excavation granularity currently being excavated can be updated in time. At the same time, since the rock distribution has a certain extension length, the rock structure information of the tunnel excavation granularity of at least one adjacent unexcavated tunnel can also be updated.

[0104] Step S240, using the construction period prediction model to re-predict the construction period of the tunnel excavation granularity being excavated in the target tunnel and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity currently being excavated, and update the predicted construction period of the tunnel excavation granularity being excavated in the target tunnel and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity currently being excavated.

[0105] Through the above method, the prediction accuracy of the predicted construction period of each tunnel excavation granularity can be further improved, and the prediction error caused by inaccurate detected rock structure information can be avoided.

[0106] In this embodiment, step S150 can be implemented in the following manner.

[0107] Firstly, the total predicted construction period for completing the target tunnel is calculated based on the predicted construction period corresponding to each tunnel excavation granularity.

[0108] By adding up the predicted construction periods corresponding to all tunnel excavation granularities in the target tunnel, the total predicted construction period for completing the target tunnel can be obtained.

[0109] Next, the total construction progress of the target tunnel is calculated based on the total construction time and total predicted construction period of all tunnel excavation granularities that have been excavated, and the total construction progress of the target tunnel is integrated into the three-dimensional geographic information in the form of a graphical plug-in to obtain the tunnel construction progress model.

[0110] For example, the total construction progress can be the ratio of the total construction time of all tunnel excavation granularities that have been excavated to the total predicted construction period, and the total construction progress can be integrated into the three-dimensional geographic information in the form of a graphical plug-in such as a progress bar. The overall progress of the construction can be intuitively understood at any time in the tunnel construction progress model.

[0111] Furthermore, step S150 may also include the following implementation manner.

[0112] First, in the three-dimensional geographic information, the tunnel path corresponding to the tunnel excavation granularity that has been excavated is represented by the first grayscale, the tunnel path corresponding to the tunnel excavation granularity that is being excavated is represented by the second grayscale, and the tunnel path corresponding to the tunnel excavation granularity that has not been excavated is represented by the third grayscale.

[0113] In this embodiment, the three-dimensional geographic information can be perspective processed so that the distribution of the target track in the target area can be observed. At the same time, different grayscales are used to represent different path segments of the tunnel path, which can facilitate the observation of the overall construction status of the target tunnel.

[0114] Next, based on the construction time of the tunnel excavation granularity being excavated and the predicted construction period of the tunnel excavation granularity being excavated, the construction progress of the tunnel excavation granularity being excavated is calculated, and the construction progress of the tunnel excavation granularity being excavated is integrated into the three-dimensional geographic information in the form of a graphical plug-in.

[0115] Through the above scheme, not only can the overall construction status of the target tunnel be visually observed in the tunnel construction progress model, but also the construction progress of the tunnel excavation granularity currently being excavated can be specifically understood, which facilitates a clearer understanding of the construction status of the target tunnel.

[0116] Please refer to Figure 5 , Figure 5 The functional module diagram of the tunnel construction progress model generation system 100 based on artificial intelligence provided in this embodiment, this embodiment can divide the functional modules of the tunnel construction progress model generation system 100 based on artificial intelligence according to the above method embodiment, that is, the following functional modules corresponding to the tunnel construction progress model generation system 100 based on artificial intelligence can be used to execute the above method embodiments. Among them, the tunnel construction progress model generation system 100 based on artificial intelligence can include a construction module 110, an import module 120, a division module 130, a prediction module 140 and a generation module 150. The functions of each functional module of the tunnel construction progress model generation system 100 based on artificial intelligence are described in detail below.

[0117] The construction module 110 is used to obtain three-dimensional geographic information of the target area according to the geographic location information of the target tunnel, and construct a tunnel path of the target tunnel in the three-dimensional geographic information.

[0118] In this embodiment, the geographic location information of the target tunnel may include the tunnel direction, tunnel altitude information, tunnel length and longitude and latitude coordinates of the tunnel entrance, wherein the target tunnel may be a planned tunnel to be built or a tunnel under construction.

[0119] The construction module 110 determines the target area according to the geographical location information of the target tunnel. The target area covers the extension area of ​​the target tunnel. The three-dimensional geographical information of the target area includes the topography and landforms in the target area, such as mountains, rivers, canyons, etc.

[0120] The construction module 110 may be used to execute the above step S110 . The detailed implementation of the construction module 110 may refer to the above detailed description of step S110 .

[0121] The import module 120 is used to import the rock structure detection information of the target area into the three-dimensional geographic information.

[0122] The import module 120 imports the rock layer structure detection information of the target area into the three-dimensional geographic information, and establishes a mapping relationship between the rock layer structure detection information of the target area and different positions and different altitudes in the three-dimensional geographic information, that is, the corresponding rock layer structure information is configured at different positions and different altitudes in the three-dimensional geographic information.

[0123] The import module 120 may be used to execute the above step S120. The detailed implementation of the import module 120 may refer to the above detailed description of step S120.

[0124] The division module 130 is used to divide the tunnel path into multiple tunnel excavation granularities, obtain the rock layer structure information at the corresponding position of each tunnel excavation granularity and the excavation depth between each tunnel excavation granularity and the tunnel entrance, and obtain the burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path.

[0125] In this embodiment, the division module 130 divides the tunnel path into multiple tunneling granularities, wherein the tunneling granularity corresponds to a tunnel construction section of a certain length, for example, the tunneling granularity corresponds to a tunnel construction section of 20 meters. In this embodiment, the lengths of the tunnel construction sections corresponding to the multiple tunneling granularities formed by the tunnel path division can be the same or different. Exemplarily, the tunneling granularity can be divided based on the rock layer structure through which the tunnel path passes, and the tunnel path parts of the same rock layer structure are divided into tunneling granularities of the same length, and the tunnel path parts of different rock layer structures are divided into tunneling granularities of different lengths. For example, when the rock layer structure is granite, the tunnel path part corresponding to the granite is divided into a tunneling granularity of 20 meters in length; when the rock layer structure is dolomite, the tunnel path part corresponding to the dolomite is divided into a tunneling granularity of 30 meters in length. In addition, the tunneling granularity can also be divided according to the excavation depth between the excavation position and the tunnel entrance. The deeper the excavation depth, the smaller the length of the corresponding tunneling granularity. In addition, other methods can be used to divide the tunnel path into multiple tunnel excavation granularities, which will not be described here.

[0126] The division module 130 executes the above step S130 . The detailed implementation of the division module 130 may refer to the above detailed description of step S130 .

[0127] The prediction module 140 is used to input each tunnel excavation granularity, the rock structure information at the corresponding position of each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the burial depth information of each tunnel excavation granularity into the construction period prediction model for prediction, so as to obtain the predicted construction period corresponding to each tunnel excavation granularity.

[0128] In this embodiment, the prediction module 140 can predict the corresponding predicted construction period based on the rock layer structure information, excavation depth and burial depth information of different tunnel excavation granularity, which can improve the prediction accuracy of the construction period compared with the method of predicting the construction period of the entire tunnel path. Among them, the prediction module 140 can be used to execute the above step S140, and the detailed implementation method of the prediction module 140 can refer to the detailed description of the above step S140.

[0129] The generation module 150 is used to generate a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information.

[0130] The generation module 150 may be used to execute the above step S150. The detailed implementation of the generation module 150 may refer to the above detailed description of step S150.

[0131] It should be noted that it should be understood that the division of the various modules of the above system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or physically separated. And these modules can all be implemented in the form of software (for example, open source software) called by processing elements. It can also be implemented in the form of hardware. Some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the prediction module 140 can be a separately established processing element, or it can be integrated in a chip of the above system for implementation. In addition, it can also be stored in the memory of the above system in the form of program code, and called and executed by a processing element of the above system. The function of the above prediction module 140. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in a processor element or instructions in the form of software.

[0132] Please refer to Figure 6 , Figure 6 The hardware structure diagram of the computer device 10 provided in the embodiment of the present disclosure for implementing the above-mentioned method for generating a tunnel construction progress model based on artificial intelligence is shown. The computer device 10 can be implemented on a cloud server. Figure 6 As shown, the computer device 10 may include a processor 101 , a computer-readable storage medium 102 , a bus 103 , and a communication interface 104 .

[0133] In a specific implementation process, at least one processor 101 executes computer-executable instructions (e.g., Figure 5 ), so that the processor 101 can execute the tunnel construction progress model generation method based on artificial intelligence as described in the above method embodiment, wherein the processor 101, the computer readable storage medium 102 and the communication interface 104 are connected via a bus 103, and the processor 101 can be used to control the sending and receiving actions of the communication interface 104.

[0134] The specific implementation process of the processor 101 can refer to the various method embodiments executed by the above-mentioned computer device 10. The implementation principles and technical effects are similar and will not be repeated in this embodiment.

[0135] The computer-readable storage medium 102 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0136] The bus 103 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, the bus in the drawings of the present invention is not limited to only one bus or one type of bus.

[0137] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the above-mentioned method for generating a tunnel construction progress model based on artificial intelligence is implemented.

[0138] In summary, the technical solution provided by the embodiment of the present invention is, first, to obtain the three-dimensional geographic information of the target area according to the geographic location information of the target tunnel, and to construct the tunnel path of the target tunnel in the three-dimensional geographic information, and to import the rock structure detection information of the target area into the three-dimensional geographic information; then, to divide the tunnel path into multiple tunnel excavation granularities, and obtain the rock structure information, excavation depth and burial depth information corresponding to each tunnel excavation granularity; then, to input the rock structure information, excavation depth and burial depth information corresponding to each tunnel excavation granularity into the construction period prediction model for prediction, and obtain the predicted construction period corresponding to each tunnel excavation granularity; finally, to generate the tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information. The above method divides the tunnel path into multiple tunnel excavation granularities, and predicts the construction period based on the information of different tunnel excavation granularities, so that the construction period of different tunnel excavation granularities can be predicted in a refined manner, thereby improving the progress accuracy of the entire tunnel construction, facilitating an intuitive understanding of the progress of the entire project, and improving the efficiency of tunnel construction.

[0139] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for generating a tunnel construction progress model based on artificial intelligence, characterized in that: The method comprises: Obtaining three-dimensional geographic information of a target area according to geographic location information of a target tunnel, and constructing a tunnel path of the target tunnel in the three-dimensional geographic information; Importing the rock structure detection information of the target area into the three-dimensional geographic information; Dividing the tunnel path into a plurality of tunnel excavation granularities, obtaining rock layer structure information at a position corresponding to each tunnel excavation granularity and an excavation depth between each tunnel excavation granularity and a tunnel entrance, and obtaining burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path; Input each tunnel excavation granularity, the rock layer structure information at the position corresponding to each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the buried depth information of each tunnel excavation granularity into the construction period prediction model for prediction, and obtain the predicted construction period corresponding to each tunnel excavation granularity; Generate a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information; The step of dividing the tunnel path into a plurality of tunnel excavation granularities, obtaining rock structure information at a position corresponding to each tunnel excavation granularity and the excavation depth between each tunnel excavation granularity and the tunnel entrance, and obtaining the burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path includes: Dividing the tunnel path into a plurality of tunnel excavation granularities, and determining an altitude interval of a tunnel portion corresponding to each tunnel excavation granularity; Determine the rock structure information at the position corresponding to each tunnel excavation granularity based on the altitude interval corresponding to each tunnel excavation granularity and the rock structure distribution at different positions and altitudes in the target area; Calculating the excavation depth between each tunnel excavation granularity and the tunnel entrance; Based on the altitude information at each position in the tunnel path and the altitude information of the ground surface corresponding to the position, the burial depth information of each tunnel excavation granularity is calculated.

2. The method for generating a tunnel construction progress model based on artificial intelligence according to claim 1, characterized in that: The step of obtaining three-dimensional geographic information of the target area according to the geographic location information of the target tunnel, and constructing the tunnel path of the target tunnel in the three-dimensional geographic information includes: Acquire the geographical location information of the target tunnel, wherein the geographical location information of the target tunnel includes the tunnel direction, the altitude information of the tunnel, the length of the tunnel and the longitude and latitude coordinates of the tunnel entrance; Determine a target area where the target tunnel is located based on the geographical location information of the target tunnel, wherein the target area is determined by a plurality of points having longitude and latitude coordinates, and the target tunnel is located in the target area; The three-dimensional geographic information corresponding to the target area is acquired from the three-dimensional image of the earth, and the tunnel path of the target tunnel is constructed in the three-dimensional geographic information.

3. The method for generating a tunnel construction progress model based on artificial intelligence according to claim 1, characterized in that: Before the step of importing the rock structure detection information of the target area into the three-dimensional geographic information, the method further includes: The rock formation structure detection information of the target area is obtained, wherein the rock formation structure detection information includes the distribution of rock formation structures at different locations in the target area at different altitudes.

4. The method for generating a tunnel construction progress model based on artificial intelligence according to claim 1, characterized in that: Before the step of inputting each tunnel excavation granularity, the rock layer structure information at the position corresponding to each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the burial depth information of each tunnel excavation granularity into the construction period prediction model for prediction to obtain the predicted construction period corresponding to each tunnel excavation granularity, the method further includes: The step of training and obtaining the construction period prediction model comprises: Acquire a training sample set, wherein the training sample set is derived from historical tunnel construction data, the training sample set includes training samples and corresponding sample construction periods, the training samples include tunnel excavation granularity samples, rock structure information corresponding to the tunnel excavation granularity samples, excavation depths corresponding to the tunnel excavation granularity samples, and burial depth information corresponding to the tunnel excavation granularity samples; The training samples in the training sample set are input into the deep learning model for training to obtain the predicted construction period corresponding to the tunnel excavation granularity sample, and the loss function value of the deep learning model is calculated based on the predicted construction period and the corresponding sample construction period. When the loss function value does not meet the preset conditions, the model parameters in the deep learning model are updated and re-trained until the loss function value meets the preset conditions, and the deep learning model when the loss function value meets the preset conditions is used as the construction period prediction model.

5. The method for generating a tunnel construction progress model based on artificial intelligence according to claim 4, characterized in that: When the tunnel excavation granularity in the target tunnel has been excavated, the method further includes the step of updating the construction period prediction model, the step comprising: Acquire the tunnel excavation granularity that has been excavated in the target tunnel, the rock layer structure information at the position corresponding to the tunnel excavation granularity that has been excavated, the excavation depth of the tunnel excavation granularity that has been excavated, the buried depth information of the tunnel excavation granularity that has been excavated, and the actual construction period of the tunnel excavation granularity that has been excavated; If the difference between the predicted construction period of the tunnel excavation granularity that has been excavated in the target tunnel by the construction period prediction model and the actual construction period is greater than the preset time difference, the tunnel excavation granularity that has been excavated in the target tunnel, the rock layer structure information at the position corresponding to the tunnel excavation granularity that has been excavated, the excavation depth of the tunnel excavation granularity that has been excavated, and the buried depth information of the tunnel excavation granularity that has been excavated are added to the training sample set as new training samples; The construction cycle prediction model is trained using new training samples, and the model parameters of the construction cycle prediction model are adjusted until the difference between the predicted construction cycle of the tunnel excavation granularity that has been excavated in the target tunnel by the construction cycle prediction model and the actual construction cycle of the tunnel excavation granularity that has been excavated in the target tunnel is less than the preset time difference, and the construction cycle prediction model at this time is used as the updated construction cycle prediction model.

6. The method for generating a tunnel construction progress model based on artificial intelligence according to claim 5, characterized in that: The method further comprises: The updated construction period prediction model is used to re-predict the construction period of the unexplored tunnel excavation granularity in the target tunnel, and the predicted construction period of the unexplored tunnel excavation granularity in the target tunnel is updated.

7. The method for generating a tunnel construction progress model based on artificial intelligence according to claim 5, characterized in that: The method further comprises: Acquire on-site construction image information of the tunnel excavation granularity currently being excavated in the target tunnel; Performing image recognition on the rock layer structure of the tunnel excavation granularity currently being excavated based on the on-site construction image information to obtain actual rock layer structure information of the tunnel excavation granularity currently being excavated; Determine whether the rock layer structure information of the tunnel excavation granularity currently being excavated is consistent with the actual rock layer structure information. If they are inconsistent, update the rock layer structure information of the tunnel excavation granularity currently being excavated and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity currently being excavated to the corresponding actual rock layer structure information; The construction period prediction model is used to re-predict the construction period of the tunnel excavation granularity being excavated in the target tunnel and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity being currently excavated, and the predicted construction period of the tunnel excavation granularity being excavated in the target tunnel and at least one unexcavated tunnel excavation granularity adjacent to the tunnel excavation granularity being currently excavated is updated.

8. The method for generating a tunnel construction progress model based on artificial intelligence according to claim 7, characterized in that: The step of generating a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information comprises: The total predicted construction period for completing the target tunnel is calculated based on the predicted construction period corresponding to each tunnel excavation granularity; The total construction progress of the target tunnel is calculated based on the total construction time of all tunneling granularities that have been excavated and the total predicted construction period, and the total construction progress of the target tunnel is integrated into the three-dimensional geographic information in the form of a graphical plug-in to obtain the tunnel construction progress model; Wherein, the step of generating a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information further includes: In the three-dimensional geographic information, a tunnel path corresponding to the tunnel excavation granularity that has been excavated is represented by a first grayscale, a tunnel path corresponding to the tunnel excavation granularity that is being excavated is represented by a second grayscale, and a tunnel path corresponding to the tunnel excavation granularity that has not been excavated is represented by a third grayscale; Based on the construction time of the tunnel excavation granularity being excavated and the predicted construction period of the tunnel excavation granularity being excavated, the construction progress of the tunnel excavation granularity being excavated is calculated, and the construction progress of the tunnel excavation granularity being excavated is integrated into the three-dimensional geographic information in the form of a graphical plug-in.

9. A tunnel construction progress model generation system based on artificial intelligence, characterized in that: The system comprises: A construction module, used to obtain three-dimensional geographic information of a target area according to the geographic location information of a target tunnel, and to construct a tunnel path of the target tunnel in the three-dimensional geographic information; An import module, used for importing the rock structure detection information of the target area into the three-dimensional geographic information; A division module, used to divide the tunnel path into a plurality of tunnel excavation granularities, obtain rock layer structure information at a position corresponding to each tunnel excavation granularity and the excavation depth between each tunnel excavation granularity and the tunnel entrance, and obtain the burial depth information of each tunnel excavation granularity based on the altitude information at each position in the tunnel path; A prediction module is used to input the excavation granularity of each tunnel, the rock structure information at the position corresponding to each tunnel excavation granularity, the excavation depth between each tunnel excavation granularity and the tunnel entrance, and the burial depth information of each tunnel excavation granularity into the construction period prediction model for prediction, so as to obtain the predicted construction period corresponding to each tunnel excavation granularity; A generation module, used for generating a tunnel construction progress model based on the predicted construction period corresponding to each tunnel excavation granularity and the three-dimensional geographic information; Wherein, the division module is specifically used for: Dividing the tunnel path into a plurality of tunnel excavation granularities, and determining an altitude interval of a tunnel portion corresponding to each tunnel excavation granularity; Determine the rock structure information at the position corresponding to each tunnel excavation granularity based on the altitude interval corresponding to each tunnel excavation granularity and the rock structure distribution at different positions and altitudes in the target area; Calculating the excavation depth between each tunnel excavation granularity and the tunnel entrance; Based on the altitude information at each position in the tunnel path and the altitude information of the ground surface corresponding to the position, the burial depth information of each tunnel excavation granularity is calculated.

10. A computer device, characterized in that: The computer device includes a processor, a readable storage medium and a communication interface. The readable storage medium, the communication interface and the processor are connected via a bus system. The readable storage medium is used to store programs, instructions or codes. The processor is used to execute the programs, instructions or codes in the readable storage medium to execute the artificial intelligence-based tunnel construction progress model generation method described in any one of claims 1 to 8.

Images