CN117993725A - Stability prediction method, system, terminal and medium for large-section tunnel - Google Patents
Stability prediction method, system, terminal and medium for large-section tunnel Download PDFInfo
- Publication number
- CN117993725A CN117993725A CN202410410037.5A CN202410410037A CN117993725A CN 117993725 A CN117993725 A CN 117993725A CN 202410410037 A CN202410410037 A CN 202410410037A CN 117993725 A CN117993725 A CN 117993725A
- Authority
- CN
- China
- Prior art keywords
- section tunnel
- current
- dimensional model
- analysis
- stability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000004458 analytical method Methods 0.000 claims abstract description 157
- 238000013507 mapping Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 abstract description 9
- 238000004590 computer program Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a stability prediction method, a system, a terminal and a medium for a large-section tunnel, wherein the method comprises the following steps: scanning the large-section tunnel based on preset scanning equipment to obtain current contour data of the large-section tunnel, and updating an initial three-dimensional model of the large-section tunnel based on the current contour data to obtain a current three-dimensional model of the large-section tunnel; dividing the current three-dimensional model into areas, and determining an analysis area, wherein the analysis area comprises two side support areas of the large-section tunnel and a top area of the large-section tunnel; the method comprises the steps of obtaining target deformation data corresponding to an analysis area, inputting the target deformation data into a preset stability analysis model, obtaining target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis area based on the target risk probability. The intelligent analysis method can conduct intelligent analysis aiming at the risks of accidents of the complicated large-section tunnel so as to predict the stability of the tunnel during construction and use.
Description
Technical Field
The invention relates to the technical field of tunnel stability prediction, in particular to a stability prediction method, device, terminal and medium for a large-section tunnel.
Background
In the current stage, a common anchor rod is adopted to anchor surrounding rock in the tunnel construction process, and the mode only temporarily fixes the tunnel, but cannot completely put an end to risks. In the prior art, the judgment and the prediction of the tunnel stability are basically carried out by means of monitored tunnel data and engineering experience, the influence of human intervention is large, and particularly, the tunnel stability cannot be accurately predicted without abundant engineering experience aiming at a complex large-section tunnel.
Accordingly, there is a need for improvement and advancement in the art.
Disclosure of Invention
The invention aims to solve the technical problems that the stability prediction method, device, terminal and medium of the large-section tunnel are provided for overcoming the defects of the prior art, and aims to solve the problems that the judgment and the prediction of the tunnel stability in the prior art are basically carried out by means of monitored tunnel data and engineering experience, the influence of human intervention is large, the tunnel stability cannot be accurately predicted and the like.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
In a first aspect, the present invention provides a method for predicting stability of a large-section tunnel, where the method includes:
Scanning a large-section tunnel based on preset scanning equipment to obtain current profile data of the large-section tunnel, and updating an initial three-dimensional model of the large-section tunnel based on the current profile data to obtain a current three-dimensional model of the large-section tunnel, wherein the current three-dimensional model is used for reflecting the current three-dimensional structure of the large-section tunnel;
dividing the current three-dimensional model into areas, and determining an analysis area, wherein the analysis area comprises two side support areas of the large-section tunnel and a top area of the large-section tunnel;
Obtaining target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model, obtaining target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on mapping relations between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and the sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region.
In one implementation manner, the updating the initial three-dimensional model of the large-section tunnel based on the current profile data to obtain the current three-dimensional model of the large-section tunnel includes:
acquiring initial contour data corresponding to the initial three-dimensional model;
Determining profile variation data based on the initial profile data and the current profile data;
And updating the initial three-dimensional model based on the contour change data to obtain the current three-dimensional model.
In one implementation manner, the updating the initial three-dimensional model of the large-section tunnel based on the current profile data to obtain the current three-dimensional model of the large-section tunnel further includes:
placing the current three-dimensional model and the initial three-dimensional model in a superposition manner, and determining a non-superposition area between the current three-dimensional model and the initial three-dimensional model;
and marking the non-coincident region on the current three-dimensional model.
In one implementation, the performing region division on the current three-dimensional model to determine an analysis region includes:
Carrying out stress analysis on the current three-dimensional model to determine the overall stress distribution of the current three-dimensional model;
And determining a stress concentration area of the current three-dimensional model based on the overall stress distribution, and taking the stress concentration area as the analysis area.
In one implementation manner, the obtaining the target deformation data corresponding to the analysis area includes:
Acquiring initial size data corresponding to the analysis area in the initial three-dimensional model;
acquiring current size data corresponding to the analysis area in the current three-dimensional model;
and determining the target deformation data based on the initial size data and the current size data.
In one implementation, the training mode of the stability analysis model includes:
A plurality of sample areas on the large-section tunnel are collected in advance, wherein the sample areas comprise two side supporting areas of the large-section tunnel and a top area of the large-section tunnel;
Acquiring sample deformation data of a plurality of key points in each sample area, and determining sample risk probability of accidents of each key point in each sample area;
establishing a mapping relation between sample deformation data of key points and sample risk probability for each sample region;
and training a preset neural network model based on the mapping relation to obtain the stability analysis model.
In one implementation, the method further comprises:
Scanning tunnel areas corresponding to the analysis areas on the large-section tunnel at preset time intervals to obtain latest contour data of the analysis areas, and determining latest deformation data of the analysis areas based on the latest contour data;
and analyzing the latest deformation data based on the stability analysis model, outputting the latest risk probability, and outputting the latest stability prediction result according to the latest risk probability.
In a second aspect, an embodiment of the present invention further provides a stability prediction system for a large-section tunnel, where the apparatus includes:
The three-dimensional model updating module is used for scanning the large-section tunnel based on preset scanning equipment to obtain current contour data of the large-section tunnel, updating an initial three-dimensional model of the large-section tunnel based on the current contour data to obtain a current three-dimensional model of the large-section tunnel, and the current three-dimensional model is used for reflecting the current three-dimensional structure of the large-section tunnel;
The analysis area determining module is used for dividing the current three-dimensional model into areas and determining an analysis area, wherein the analysis area comprises two side supporting areas of the large-section tunnel and a top area of the large-section tunnel;
The stability prediction module is used for acquiring target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model, obtaining target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on mapping relations between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region.
In a third aspect, an embodiment of the present invention further provides a terminal, where the terminal includes a memory, a processor, and a stability prediction program of a large-section tunnel stored in the memory and capable of running on the processor, and when the processor executes the stability prediction program of the large-section tunnel, the processor implements the steps of the stability prediction method of the large-section tunnel in any one of the above schemes.
In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium, where a stability prediction program of a large-section tunnel is stored on the computer readable storage medium, and when the stability prediction program of the large-section tunnel is executed by a processor, the steps of the stability prediction method of the large-section tunnel in any one of the above schemes are implemented.
The beneficial effects are that: compared with the prior art, the invention provides a stability prediction method of a large-section tunnel, which comprises the steps of firstly scanning the large-section tunnel based on preset scanning equipment to obtain current profile data of the large-section tunnel, updating an initial three-dimensional model of the large-section tunnel based on the current profile data to obtain a current three-dimensional model of the large-section tunnel, wherein the current three-dimensional model is used for reflecting the current three-dimensional structure of the large-section tunnel. And then, carrying out region division on the current three-dimensional model, and determining an analysis region, wherein the analysis region comprises two side support regions of the large-section tunnel and a top region of the large-section tunnel. And finally, acquiring target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model to obtain target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on a mapping relation between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and the sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region. According to the method, the target deformation data of the large-section tunnel can be intelligently analyzed by utilizing the pre-trained stability analysis model, the corresponding target risk probability is automatically output, and the stability of the large-section tunnel can be predicted based on the target risk probability, so that whether the large-section tunnel is stable or not is predicted, and the safety of tunnel construction is ensured.
Drawings
Fig. 1 is a flowchart of a preferred embodiment of a method for predicting stability of a large-section tunnel according to an embodiment of the present invention.
Fig. 2 is a schematic architecture diagram of a stability prediction system for a large-section tunnel according to an embodiment of the present invention.
Fig. 3 is a schematic block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and more specific, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Based on the problems existing in the prior art, the embodiment provides a stability prediction method for a large-section tunnel, and based on the method of the embodiment, the stability of the large-section tunnel can be predicted. Specifically, when the embodiment is applied specifically, a large-section tunnel is scanned based on preset scanning equipment to obtain current profile data of the large-section tunnel, an initial three-dimensional model of the large-section tunnel is updated based on the current profile data to obtain a current three-dimensional model of the large-section tunnel, and the current three-dimensional model is used for reflecting a current three-dimensional structure of the large-section tunnel. And then, carrying out region division on the current three-dimensional model, and determining an analysis region, wherein the analysis region comprises two side support regions of the large-section tunnel and a top region of the large-section tunnel. And finally, acquiring target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model to obtain target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on a mapping relation between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and the sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region. Therefore, the method and the device can utilize the pre-trained stability analysis model to intelligently analyze the target deformation data of the large-section tunnel, automatically output the corresponding target risk probability, and predict the stability of the large-section tunnel based on the target risk probability so as to predict whether the large-section tunnel is stable or not and ensure the safety of tunnel construction.
The stability prediction method of the large-section tunnel can be applied to a terminal, and the terminal can be an intelligent product terminal such as a computer, a mobile phone and an intelligent television. As shown in fig. 1, the method for predicting the stability of the large-section tunnel comprises the following steps:
Step S100, scanning a large-section tunnel based on preset scanning equipment to obtain current contour data of the large-section tunnel, and updating an initial three-dimensional model of the large-section tunnel based on the current contour data to obtain a current three-dimensional model of the large-section tunnel, wherein the current three-dimensional model is used for reflecting the current three-dimensional structure of the large-section tunnel.
The scanning device of the embodiment includes various sensors, such as an infrared sensor, and the like, and the scanning device can scan the external contour and the internal contour of the large-section tunnel to obtain the current contour data of the large-section tunnel, and the current contour data can reflect the overall shape and the overall size of the large-section tunnel. Then, the embodiment can update the initial three-dimensional model of the large-section tunnel based on the current profile data to obtain the current three-dimensional model of the large-section tunnel. In this embodiment, the current three-dimensional model is used to reflect the current three-dimensional structure of the large-section tunnel. The initial three-dimensional model of this embodiment reflects a three-dimensional model established by scanning the outer contour and the inner contour of the large-section tunnel at the last scanning time. Therefore, after the terminal scans the current contour data obtained by the current scanning, the initial three-dimensional model of the large-section tunnel can be updated based on the current contour data.
In one implementation, when updating the initial three-dimensional model, the embodiment includes the following steps:
step S101, obtaining initial contour data corresponding to the initial three-dimensional model;
Step S102, determining contour change data based on the initial contour data and the current contour data;
And step S103, updating the initial three-dimensional model based on the contour change data to obtain the current three-dimensional model.
In this embodiment, first, initial contour data of an initial three-dimensional model is acquired, where the initial contour data is size data corresponding to an external contour and an internal contour of a large-section tunnel by scanning at a previous scanning time. The initial contour data and the current contour data are compared to determine difference data between the initial contour data and the current contour data, wherein the difference data is contour change data, and the embodiment can locate the position of contour change in an initial three-dimensional model based on the contour change data, and then adjust and update the initial three-dimensional model based on the determined position and the corresponding contour change data to obtain the current three-dimensional model.
In other implementation manners, the embodiment may further place the current three-dimensional model and the initial three-dimensional model in a superposition manner, determine a non-superposition area between the current three-dimensional model and the initial three-dimensional model, and then identify the non-superposition area on the current three-dimensional model, so that deformation conditions of the large-section tunnel can be reflected more intuitively.
And step 200, carrying out region division on the current three-dimensional model to determine an analysis region, wherein the analysis region comprises two side support regions of the large-section tunnel and a top region of the large-section tunnel.
After the current three-dimensional model is obtained, the current three-dimensional model may be subjected to gridding processing to divide the current three-dimensional model into regions to obtain an analysis region, where the analysis region is a region for stability prediction in the large-section tunnel, and in order to ensure accurate analysis on stability of the large-section tunnel, the analysis region in the embodiment may be a region in the large-section tunnel where an accident easily occurs, such as a collapse accident easily occurs in a top region of the large-section tunnel, so that the top region may be used as an analysis region, and further, such as an inclined or over-digging accident easily occurs in two side support regions of the large-section tunnel, so that the two side support regions may also be used as analysis regions.
In one implementation, this embodiment, when determining the analysis area, includes the steps of:
step S201, carrying out stress analysis on the current three-dimensional model to determine overall stress distribution of the current three-dimensional model;
Step S202, determining a stress concentration area of the current three-dimensional model based on the overall stress distribution, and taking the stress concentration area as the analysis area.
Since the analysis area in the present embodiment is an area in which an accident easily occurs in a large-section tunnel, the area in which an accident easily occurs must be an area in which stress is relatively concentrated. Based on the above, the present three-dimensional model of the large-section tunnel is subjected to stress analysis, the load applied to the present three-dimensional model is analyzed, and then the overall stress distribution of the present three-dimensional model is output, from which the stress condition of each position in the present three-dimensional model can be determined. Preferably, in specific application, the embodiment can simulate the load applied to the actual construction site of the large-section tunnel, distribute the simulated load into the current three-dimensional model according to the actual construction site to obtain the overall stress distribution of the current three-dimensional model, and display the overall stress distribution in the form of a stress distribution map so as to intuitively determine a stress concentration area in the current three-dimensional model, and then take the stress concentration area in the current three-dimensional model as an analysis area.
In other implementations, the present embodiment may also determine the analysis area directly based on construction experience. Specifically, the embodiment can analyze the historical accident data, wherein the historical accident data comprises the historical accident position of the accident of the large-section tunnel in the past and specific accident conditions, records the historical accident position, and screens out the accident high-incidence position according to the historical accident position. After the current three-dimensional model is obtained, the embodiment finds the area corresponding to the accident high-incidence position in the current three-dimensional model, and takes the area corresponding to the accident high-incidence position as an analysis area. The analysis areas determined in the embodiment are all areas easy to occur accidents, so that stability prediction can be more accurate for the large-section tunnel according to the analysis areas.
Step S300, obtaining target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model, obtaining target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on mapping relations between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region.
After determining the analysis area, the embodiment can analyze the analysis area to obtain the target deformation data of the analysis area, wherein the target deformation data reflects the outline deformation of the analysis area. Then, the embodiment inputs the target deformation data into a preset stability analysis model to obtain a target risk probability corresponding to the target deformation data. In this embodiment, the stability analysis model is a model trained based on a mapping relationship between sample deformation data and sample risk probabilities corresponding to a plurality of sample regions on the large-section tunnel, so that the stability analysis model can automatically process the target deformation data and output a target risk probability corresponding to the target deformation data, where the target risk probability reflects the probability of an accident occurring in the analysis region. According to the target risk probability, the stability prediction result corresponding to the analysis region can be determined. Therefore, the probability of occurrence of accidents in the analysis area of the large-section tunnel can be automatically analyzed based on the stability analysis model, and the stability of the large-section tunnel can be further predicted.
In one implementation, the method in this embodiment includes the following steps when analyzing the target deformation data:
Step S301, obtaining initial size data corresponding to the analysis area in the initial three-dimensional model;
step S302, current size data corresponding to the analysis area in the current three-dimensional model is obtained;
Step S303, determining the target deformation data based on the initial size data and the current size data.
Specifically, the present embodiment first determines, based on an analysis area, a target position corresponding to the large-section tunnel, and further determines initial size data corresponding to the target position in the initial three-dimensional model, and current size data corresponding to the target position in the current three-dimensional model. When the initial size data and the current size data are compared, target deformation data can be obtained. According to the embodiment, the target deformation data can be input into the stability analysis model, and the target risk probability corresponding to the target deformation data is obtained. After the target risk probability is obtained, the embodiment can compare the target risk probability with a preset probability threshold value, and if the target risk probability is greater than or equal to the probability threshold value, the analysis area corresponding to the moment can be determined to be easy to have accidents, so that the stability prediction result of the large-section tunnel can be obtained to be lower in stability, and the situation that the large-section tunnel is unsafe at the moment is indicated, and safety emergency measures need to be taken. If the target risk probability is smaller than the probability threshold, it can be determined that the corresponding analysis area is not easy to have accidents, so that the stability prediction result of the large-section tunnel can be obtained to be high in stability, and the fact that the large-section tunnel is safe at the moment is indicated.
In one implementation, the present embodiment may collect a number of sample areas on the large-section tunnel in advance, where the sample areas include two side support areas of the large-section tunnel and a top area of the large-section tunnel. And then acquiring sample deformation data of a plurality of key points in each sample area, and determining the sample risk probability of accidents of each key point in each sample area. In a specific application, the embodiment can calculate the sample risk probability of the accident of each key point in each sample area according to the accident situation of each key point in each sample area recorded in the historical accident data. Then, for each sample area, a mapping relation between sample deformation data of the key points and sample risk probability is established. And finally training a preset neural network model based on the mapping relation to obtain the stability analysis model. After training is completed, the stability analysis model may be further verified by using a verification data set, where the verification data set includes first deformation data of a specific area and a corresponding first risk probability, the first deformation data and the first risk probability are known, and the first deformation data of the specific area is input into the stability analysis model, and then the first probability data is output, and the first probability data is compared with the first risk probability, so that whether the stability analysis model meets the requirement can be judged.
In other implementations, the embodiment may further scan a tunnel region corresponding to the analysis region on the large-section tunnel at preset time intervals, obtain the latest profile data of the analysis region, and determine the latest deformation data of the analysis region based on the latest profile data. And then analyzing the latest deformation data based on the stability analysis model, outputting the latest risk probability, and outputting the latest stability prediction result according to the latest risk probability. Therefore, the embodiment can realize real-time monitoring of the large-section tunnel and perform stability analysis in real time, so that early warning is performed in time when an emergency occurs, and the safety of tunnel construction is ensured.
In summary, the present embodiment scans a large-section tunnel based on a preset scanning device to obtain current profile data of the large-section tunnel, and updates an initial three-dimensional model of the large-section tunnel based on the current profile data to obtain a current three-dimensional model of the large-section tunnel, where the current three-dimensional model is used for reflecting a current three-dimensional structure of the large-section tunnel. And then, carrying out region division on the current three-dimensional model, and determining an analysis region, wherein the analysis region comprises two side support regions of the large-section tunnel and a top region of the large-section tunnel. And finally, acquiring target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model to obtain target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on a mapping relation between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and the sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region. According to the method, the device and the system, the target deformation data of the large-section tunnel can be intelligently analyzed by utilizing the pre-trained stability analysis model, the corresponding target risk probability is automatically output, and the stability of the large-section tunnel can be predicted based on the target risk probability, so that whether the large-section tunnel is stable or not is predicted, and the safety of tunnel construction is ensured.
Based on the above embodiment, the present invention further provides a stability prediction system for a large-section tunnel, as shown in fig. 2, where the apparatus includes: a three-dimensional model update module 10, an analysis region determination module 20, and a stability prediction module 30. Specifically, the three-dimensional model updating module 10 is configured to scan a large-section tunnel based on a preset scanning device, obtain current profile data of the large-section tunnel, and update an initial three-dimensional model of the large-section tunnel based on the current profile data, so as to obtain a current three-dimensional model of the large-section tunnel, where the current three-dimensional model is configured to reflect a current three-dimensional structure of the large-section tunnel. The analysis region determining module 20 is configured to perform region division on the current three-dimensional model, and determine an analysis region, where the analysis region includes two side support regions of the large-section tunnel and a top region of the large-section tunnel. The stability prediction module 30 is configured to obtain target deformation data corresponding to the analysis region, input the target deformation data into a preset stability analysis model, obtain a target risk probability corresponding to the target deformation data, and determine a stability prediction result corresponding to the analysis region based on the target risk probability, where the stability analysis model is a model trained based on a mapping relationship between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and sample risk probability, and the target risk probability is used to reflect a probability of an accident occurring in the analysis region.
In one implementation, the three-dimensional model update module 10 includes:
An initial contour obtaining unit, configured to obtain initial contour data corresponding to the initial three-dimensional model;
A contour change analysis unit configured to determine contour change data based on the initial contour data and the current contour data;
And the three-dimensional model updating unit is used for updating the initial three-dimensional model based on the contour change data to obtain the current three-dimensional model.
In one implementation, the three-dimensional model update module 10 includes:
The coincidence placing unit is used for placing the current three-dimensional model and the initial three-dimensional model in a coincidence way and determining a non-coincidence area between the current three-dimensional model and the initial three-dimensional model;
and the region identification unit is used for identifying the non-coincident region on the current three-dimensional model.
In one implementation, the analysis region determination module 20 includes:
the stress analysis unit is used for carrying out stress analysis on the current three-dimensional model and determining overall stress distribution of the current three-dimensional model;
And the region determining unit is used for determining a stress concentration region of the current three-dimensional model based on the whole stress distribution, and taking the stress concentration region as the analysis region.
In one implementation, the stability prediction module 30 includes:
The initial size determining unit is used for acquiring initial size data corresponding to the analysis area in the initial three-dimensional model;
the current size determining unit is used for acquiring current size data corresponding to the analysis area in the current three-dimensional model;
and the target deformation analysis unit is used for determining the target deformation data based on the initial size data and the current size data.
In one implementation, the apparatus further includes a model training module, the model training module comprising:
The sample area acquisition unit is used for acquiring a plurality of sample areas on the large-section tunnel in advance, wherein the sample areas comprise two side support areas of the large-section tunnel and a top area of the large-section tunnel;
the sample data determining unit is used for obtaining sample deformation data of a plurality of key points in each sample area and determining sample risk probability of accidents of each key point in each sample area;
The mapping relation establishing unit is used for establishing a mapping relation between sample deformation data of the key points and sample risk probability for each sample area;
and the model training unit is used for training a preset neural network model based on the mapping relation to obtain the stability analysis model.
In one implementation, the apparatus further comprises:
The latest deformation analysis unit is used for scanning the tunnel region corresponding to the analysis region on the large-section tunnel at preset time intervals to obtain latest contour data of the analysis region, and determining the latest deformation data of the analysis region based on the latest contour data;
And the prediction result updating unit is used for analyzing the latest deformation data based on the stability analysis model, outputting the latest risk probability and outputting the latest stability prediction result according to the latest risk probability.
The working principle of each module in the stability prediction system of the large-section tunnel in this embodiment is the same as the principle of each step in the above method embodiment, and will not be described here again.
Based on the above embodiment, the present invention also provides a terminal, and a schematic block diagram of the terminal may be shown in fig. 3. The terminal may include one or more processors 100 (only one shown in fig. 3), a memory 101, and a computer program 102 stored in the memory 101 and executable on the one or more processors 100, such as a stability prediction program for a large-section tunnel. The one or more processors 100, when executing the computer program 102, may implement the various steps in an embodiment of a method for stability prediction for a large-section tunnel. Or the one or more processors 100, when executing the computer program 102, may implement the functions of the modules/units in the stability prediction method embodiment of the large-section tunnel, which is not limited herein.
In one embodiment, the Processor 100 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application SPECIFIC INTEGRATED Circuits (ASICs), off-the-shelf Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
In one embodiment, the memory 101 may be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The memory 101 may also be an external storage device of the electronic device, such as a plug-in hard disk provided on the electronic device, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like. Further, the memory 101 may also include both an internal storage unit and an external storage device of the electronic device. The memory 101 is used to store computer programs and other programs and data required by the terminal. The memory 101 may also be used to temporarily store data that has been output or is to be output.
It will be appreciated by those skilled in the art that the functional block diagram shown in fig. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the terminal to which the present inventive arrangements may be applied, as a specific terminal may include more or less components than those shown, or may be combined with some components, or may have a different arrangement of components.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium, that when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, operational database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual operation data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for predicting stability of a large-section tunnel, the method comprising:
Scanning a large-section tunnel based on preset scanning equipment to obtain current profile data of the large-section tunnel, and updating an initial three-dimensional model of the large-section tunnel based on the current profile data to obtain a current three-dimensional model of the large-section tunnel, wherein the current three-dimensional model is used for reflecting the current three-dimensional structure of the large-section tunnel;
dividing the current three-dimensional model into areas, and determining an analysis area, wherein the analysis area comprises two side support areas of the large-section tunnel and a top area of the large-section tunnel;
Obtaining target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model, obtaining target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on mapping relations between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and the sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region.
2. The method for predicting the stability of a large-section tunnel according to claim 1, wherein updating the initial three-dimensional model of the large-section tunnel based on the current profile data to obtain the current three-dimensional model of the large-section tunnel comprises:
acquiring initial contour data corresponding to the initial three-dimensional model;
Determining profile variation data based on the initial profile data and the current profile data;
And updating the initial three-dimensional model based on the contour change data to obtain the current three-dimensional model.
3. The method for predicting the stability of a large-section tunnel according to claim 2, wherein updating the initial three-dimensional model of the large-section tunnel based on the current profile data to obtain the current three-dimensional model of the large-section tunnel further comprises:
placing the current three-dimensional model and the initial three-dimensional model in a superposition manner, and determining a non-superposition area between the current three-dimensional model and the initial three-dimensional model;
and marking the non-coincident region on the current three-dimensional model.
4. The method for predicting the stability of a large-section tunnel according to claim 1, wherein the performing region division on the current three-dimensional model to determine an analysis region comprises:
Carrying out stress analysis on the current three-dimensional model to determine the overall stress distribution of the current three-dimensional model;
And determining a stress concentration area of the current three-dimensional model based on the overall stress distribution, and taking the stress concentration area as the analysis area.
5. The method for predicting stability of a large-section tunnel according to claim 1, wherein the obtaining the target deformation data corresponding to the analysis region comprises:
Acquiring initial size data corresponding to the analysis area in the initial three-dimensional model;
acquiring current size data corresponding to the analysis area in the current three-dimensional model;
and determining the target deformation data based on the initial size data and the current size data.
6. The method for predicting the stability of a large-section tunnel according to claim 1, wherein the training mode of the stability analysis model comprises:
A plurality of sample areas on the large-section tunnel are collected in advance, wherein the sample areas comprise two side supporting areas of the large-section tunnel and a top area of the large-section tunnel;
Acquiring sample deformation data of a plurality of key points in each sample area, and determining sample risk probability of accidents of each key point in each sample area;
establishing a mapping relation between sample deformation data of key points and sample risk probability for each sample region;
and training a preset neural network model based on the mapping relation to obtain the stability analysis model.
7. The method for predicting the stability of a large-section tunnel according to claim 1, further comprising:
Scanning tunnel areas corresponding to the analysis areas on the large-section tunnel at preset time intervals to obtain latest contour data of the analysis areas, and determining latest deformation data of the analysis areas based on the latest contour data;
and analyzing the latest deformation data based on the stability analysis model, outputting the latest risk probability, and outputting the latest stability prediction result according to the latest risk probability.
8. A stability prediction system for a large-section tunnel, the system comprising:
The three-dimensional model updating module is used for scanning the large-section tunnel based on preset scanning equipment to obtain current contour data of the large-section tunnel, updating an initial three-dimensional model of the large-section tunnel based on the current contour data to obtain a current three-dimensional model of the large-section tunnel, and the current three-dimensional model is used for reflecting the current three-dimensional structure of the large-section tunnel;
The analysis area determining module is used for dividing the current three-dimensional model into areas and determining an analysis area, wherein the analysis area comprises two side supporting areas of the large-section tunnel and a top area of the large-section tunnel;
The stability prediction module is used for acquiring target deformation data corresponding to the analysis region, inputting the target deformation data into a preset stability analysis model, obtaining target risk probability corresponding to the target deformation data, and determining a stability prediction result corresponding to the analysis region based on the target risk probability, wherein the stability analysis model is a model obtained by training based on mapping relations between sample deformation data corresponding to a plurality of sample regions on the large-section tunnel and sample risk probability, and the target risk probability is used for reflecting the probability of accident occurrence of the analysis region.
9. A terminal comprising a memory, a processor and a stability prediction program for a large-section tunnel stored in the memory and operable on the processor, wherein the processor, when executing the stability prediction program for a large-section tunnel, implements the steps of the stability prediction method for a large-section tunnel according to any one of claims 1-7.
10. A computer-readable storage medium, wherein a stability prediction program for a large-section tunnel is stored on the computer-readable storage medium, and the stability prediction program for the large-section tunnel, when executed by a processor, implements the steps of the stability prediction method for the large-section tunnel according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410410037.5A CN117993725A (en) | 2024-04-07 | 2024-04-07 | Stability prediction method, system, terminal and medium for large-section tunnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410410037.5A CN117993725A (en) | 2024-04-07 | 2024-04-07 | Stability prediction method, system, terminal and medium for large-section tunnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117993725A true CN117993725A (en) | 2024-05-07 |
Family
ID=90889513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410410037.5A Pending CN117993725A (en) | 2024-04-07 | 2024-04-07 | Stability prediction method, system, terminal and medium for large-section tunnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117993725A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110411370A (en) * | 2019-07-26 | 2019-11-05 | 北京住总集团有限责任公司 | A kind of the risk of tunnel construction managing and control system based on space time parameter |
| CN114997003A (en) * | 2022-05-25 | 2022-09-02 | 广东交通职业技术学院 | Multi-model fusion tunnel construction risk prediction method, system, device and medium |
| CN117787684A (en) * | 2023-11-17 | 2024-03-29 | 深圳市特区铁工建设集团有限公司 | Tunnel surrounding rock collapse risk analysis method and system based on visual detection |
-
2024
- 2024-04-07 CN CN202410410037.5A patent/CN117993725A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110411370A (en) * | 2019-07-26 | 2019-11-05 | 北京住总集团有限责任公司 | A kind of the risk of tunnel construction managing and control system based on space time parameter |
| CN112945139A (en) * | 2019-07-26 | 2021-06-11 | 北京住总集团有限责任公司 | Shield engineering auxiliary system combining three-dimensional scanning with BIM technology |
| CN112985304A (en) * | 2019-07-26 | 2021-06-18 | 北京住总集团有限责任公司 | Tunnel construction auxiliary monitoring system |
| CN114997003A (en) * | 2022-05-25 | 2022-09-02 | 广东交通职业技术学院 | Multi-model fusion tunnel construction risk prediction method, system, device and medium |
| CN117787684A (en) * | 2023-11-17 | 2024-03-29 | 深圳市特区铁工建设集团有限公司 | Tunnel surrounding rock collapse risk analysis method and system based on visual detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111667011B (en) | Damage detection model training and vehicle damage detection method, device, equipment and medium | |
| US11004234B2 (en) | Method and apparatus for annotating point cloud data | |
| CN110533925B (en) | Vehicle illegal video processing method and device, computer equipment and storage medium | |
| US20180292328A1 (en) | Information processing device and information processing method | |
| CN110490608B (en) | Risk assessment method and device, computer equipment and storage medium | |
| CN112200493A (en) | Digital twin model construction method and device | |
| CN111199346B (en) | Utility tunnel supervision method, device, computer equipment and storage medium | |
| CN113470374A (en) | Vehicle overspeed monitoring method and device, computer equipment and storage medium | |
| CN111339074A (en) | Threshold generation method, device, equipment and storage medium | |
| EP4145177A1 (en) | Method, apparatus and computer program for generating input feature map of artificial intelligence model to detect object based on lidar | |
| CN110796757A (en) | Automatic detection method, equipment and storage medium for patrol fraud in intelligent community | |
| CN117765708A (en) | Slope instability prediction method and device based on map image analysis technology | |
| CN117194868B (en) | Surrounding rock deformation monitoring method and device, electronic equipment and storage medium | |
| CN110781887A (en) | License plate screw detection method and device and computer equipment | |
| CN117787684A (en) | Tunnel surrounding rock collapse risk analysis method and system based on visual detection | |
| CN117993725A (en) | Stability prediction method, system, terminal and medium for large-section tunnel | |
| CN111967398B (en) | Tunnel detection method and device, electronic equipment and readable storage medium | |
| CN110275896B (en) | Optical cable intrusion construction event identification method, device, equipment and readable storage medium | |
| CN111444833B (en) | Fruit actual measurement production method, device, computer equipment and storage medium | |
| CN117610375A (en) | Bridge suspension casting construction digital twin method, device and equipment based on machine vision | |
| CN114812528B (en) | Automatic monitoring system applied to expressway disease side slope | |
| CN116296233A (en) | Test data validity analysis system and method for transonic continuous wind tunnel | |
| CN116340770A (en) | Intelligent identification method for tunnel lining geological radar data | |
| CN111141981B (en) | Line loss point inspection method and device, computer equipment and storage medium | |
| CN114282834A (en) | Evaluation result traceability analysis method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |