CN115688251A - Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning - Google Patents
Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning Download PDFInfo
- Publication number
- CN115688251A CN115688251A CN202211629044.1A CN202211629044A CN115688251A CN 115688251 A CN115688251 A CN 115688251A CN 202211629044 A CN202211629044 A CN 202211629044A CN 115688251 A CN115688251 A CN 115688251A
- Authority
- CN
- China
- Prior art keywords
- tunnel
- neural network
- data set
- module
- network model
- 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
Images
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a deep learning-based earthquake multi-occurrence zone tunnel risk decision method and a system, wherein the method comprises the following steps: establishing a sample data set of a tunnel in an earthquake multi-occurrence area; constructing and training a neural network model to obtain a trained neural network model; inputting the sample data set into a trained neural network model, and outputting a prediction result, wherein the prediction result comprises: the circumferential peak stress and the deformation of surrounding rocks of the tunnel; and obtaining a tunnel surrounding rock supporting form according to the risk grade of the tunnel based on the prediction result. The system comprises: the system comprises a data acquisition module, a model training module, a prediction output module and a risk decision module; the data acquisition module, the model training module, the prediction output module and the risk decision module are sequentially connected. The method can provide exclusive intelligent decision aiming at different risk levels, effectively guide the support of the surrounding rock and ensure the safety of construction.
Description
Technical Field
The invention belongs to the field of tunnel support design, and particularly relates to a deep learning-based earthquake multi-occurrence-zone tunnel risk decision method and system.
Background
With the rapid development of economy and the progress of tunnel technology in China, railway tunnels and road tunnels are continuously built deep into former 'geological restricted areas', complicated long tunnels are more and more, and geological problems are more and more complicated. For example, areas such as Xinjiang and Chuanzang are located in active earthquake zones, earthquake disasters occur frequently, stratum disturbance and even fault dislocation are caused, and therefore the stability control of surrounding rocks faces a great test. A reliable surrounding rock supporting system is an important premise for guaranteeing safe construction of the tunnel, and if the supporting design is unreasonable, the tunnel is easy to deform greatly and even collapse accidents are easy to happen, so that great economic and personnel losses are caused.
The current tunnel support design method comprises an engineering experience method, a field measurement method, a theory, a numerical analysis method and the like, and because underground tunnel engineering is complex and changeable, a limited number of field analysis cases mainly aim at specific engineering, so that the support design theory depending on experience and field monitoring information cannot meet the requirements of all the engineering under construction, and the design is often over conservative. Meanwhile, in the aspects of theory and numerical research, surrounding rock and other conditions are mostly simplified and processed, the considered factors are limited, and the tunnel construction condition cannot be completely simulated.
Disclosure of Invention
The invention aims to provide a deep learning-based earthquake multi-occurrence-area tunnel risk decision method, which scientifically predicts and evaluates the damage conditions of different earthquake intensities to surrounding rocks in different geological environments by excavating the internal relation among geological information, earthquake intensity information and the surrounding rock damage conditions through deep learning, and guides tunnel support design through risk analysis and intelligent decision so as to solve the problems that the requirements of all under-construction projects cannot be met and the tunnel construction conditions cannot be completely simulated in the prior art.
In order to achieve the purpose, the invention provides a deep learning-based earthquake multi-occurrence zone tunnel risk decision method, which comprises the following steps:
establishing a sample data set of a tunnel in an earthquake multi-occurrence area;
constructing and training a neural network model to obtain a trained neural network model;
inputting the sample data set into a trained neural network model, and outputting a prediction result, wherein the prediction result comprises: the circumferential peak stress and the surrounding rock deformation of the tunnel;
and obtaining a tunnel surrounding rock supporting form according to the risk grade of the tunnel based on the prediction result.
Preferably, the process of establishing the sample data set of the tunnel of the seismic multi-occurrence zone comprises:
acquiring tunnel geological information subjected to earthquake disasters, wherein the tunnel geological information comprises: geological information, seismic intensity information and surrounding rock damage conditions;
and establishing a three-dimensional digital tunnel model through a numerical simulation test based on the tunnel geological information, and establishing a sample data set of the tunnel in the earthquake multi-occurrence area based on the three-dimensional digital tunnel model.
Preferably, the process of constructing and training the neural network model comprises:
carrying out normalization pretreatment on the sample data set to obtain a pretreated sample data set; and dividing the preprocessed sample data set into a training set and a testing set, and training the neural network model through the training set until the output error is reduced to an expected value to obtain the trained neural network model.
Preferably, the process of outputting the prediction result comprises:
inputting the test set into a trained neural network model to obtain a mapping relation between the tunnel geological information and the prediction result, and outputting the prediction result based on the mapping relation.
Preferably, the process of obtaining the tunnel surrounding rock supporting form comprises the following steps:
analyzing the tunnel hoop peak stress and the surrounding rock deformation to obtain an analysis result; and obtaining a tunnel surrounding rock supporting form corresponding to the analysis result according to the risk grade of the tunnel.
In order to achieve the technical purpose, the invention also provides a deep learning-based earthquake multi-occurrence zone tunnel risk decision system, which comprises: the system comprises a data acquisition module, a model training module, a prediction output module and a risk decision module; the data acquisition module, the model training module, the prediction output module and the risk decision module are connected in sequence;
the data acquisition module is used for establishing a sample data set of the tunnel in the earthquake multi-occurrence area;
the model training module is used for constructing and training a neural network model to obtain a trained neural network model;
the prediction output module is configured to input the sample data set to a trained neural network model, and output a prediction result, where the prediction result includes: the circumferential peak stress and the surrounding rock deformation of the tunnel;
and the risk decision module is used for obtaining a tunnel surrounding rock supporting form according to the risk grade of the tunnel based on the prediction result.
Preferably, the data acquisition module comprises: the device comprises an information acquisition unit and a data set construction unit;
the information acquisition unit is used for acquiring tunnel geological information subjected to earthquake disasters, wherein the tunnel geological information comprises: geological information, seismic intensity information and surrounding rock damage conditions;
the data set construction unit establishes a three-dimensional digital tunnel model through a numerical simulation test based on the tunnel geological information, and establishes a sample data set of the tunnel in the earthquake multi-occurrence area based on the three-dimensional digital tunnel model.
Preferably, the model training module comprises: the system comprises a data preprocessing unit and a model training unit;
the data preprocessing unit is used for carrying out normalization preprocessing on the sample data set to obtain a preprocessed sample data set;
and the model training unit is used for dividing the preprocessed sample data set into a training set and a testing set, training the neural network model through the training set until the output error is reduced to an expected value, and obtaining the trained neural network model.
Preferably, the prediction output module includes: a mapping relation obtaining unit and a prediction output unit;
the mapping relation obtaining unit is used for inputting the test set into a trained neural network model to obtain a mapping relation between the tunnel geological information and the prediction result;
and the prediction output unit outputs a prediction result based on the mapping relation.
Preferably, in the risk decision module, the tunnel hoop peak stress and the surrounding rock deformation are analyzed to obtain an analysis result; and obtaining a tunnel surrounding rock supporting form corresponding to the analysis result according to the tunnel risk level.
The invention has the technical effects that:
according to the invention, the sample data set of the tunnel in the earthquake multi-occurrence area is established, so that the support method is not limited in limited field engineering cases, and the large cost of the entity model is saved;
according to the method, a sample data set is input into a trained neural network model, a prediction result is output, and a tunnel surrounding rock support form is obtained according to the prediction result and the risk level of the tunnel. The invention introduces the neural network model, can acquire and manage corresponding data for the tunnel established in the earthquake-prone area, analyzes the influence of the earthquake occurrence on the tunnel, and more accurately predicts the stress change and the change of the surrounding rock of the tunnel, further provides a decision scheme and guides the support of the surrounding rock, avoids the situations of 'over-support due to small earthquake, less support due to large earthquake', and simultaneously ensures the safety of constructors and the safety of tunnel-passing personnel in the later operation process.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, are included to provide a further understanding of the application, and the description of the exemplary embodiments of the application are intended to be illustrative of the application and are not intended to limit the application. In the drawings:
FIG. 1 is a flow chart of a method in an embodiment of the invention;
FIG. 2 is a schematic diagram of a system in an embodiment of the invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
In the prior art, the tunnel anti-seismic design is weak, so that once an accident occurs, loss which is difficult to recover is caused. The invention provides an intelligent analysis decision-making method and system for building a tunnel in an earthquake multi-occurrence area, which utilize some factors which are most sensitive to the influence of an earthquake: the tunnel buried depth, the surrounding rock grade, the number of fault fracture zones and the earthquake intensity grade are trained, the output prediction result is evaluated, the risk grade is determined, an exclusive intelligent decision is provided for different risk grades, the surrounding rock support is effectively guided, and the construction safety is guaranteed.
Example one
The embodiment provides a deep learning-based tunnel risk decision method for a seismic multi-occurrence area, which comprises the following steps:
establishing a sample data set of a tunnel in an earthquake multi-occurrence area;
constructing and training a neural network model to obtain a trained neural network model;
inputting the sample data set into a trained neural network model, and outputting a prediction result, wherein the prediction result comprises: the circumferential peak stress and the deformation of surrounding rocks of the tunnel;
and obtaining a tunnel surrounding rock supporting form according to the risk grade of the tunnel based on the prediction result.
In some embodiments, the process of establishing a sample data set for a seismic multi-launch zone tunnel comprises: acquiring tunnel geological information subjected to earthquake disasters, wherein the tunnel geological information comprises: geological information, seismic intensity information and surrounding rock damage conditions; and establishing a three-dimensional digital tunnel model through a numerical simulation test based on the tunnel geological information, and establishing a sample data set of the tunnel in the earthquake multi-occurrence area based on the three-dimensional digital tunnel model.
In some embodiments, the process of building and training the neural network model comprises: carrying out normalization pretreatment on the sample data set to obtain a pretreated sample data set; and dividing the preprocessed sample data set into a training set and a testing set, and training the neural network model through the training set until the output error is reduced to an expected value, so as to obtain the trained neural network model.
In some embodiments, the process of outputting the prediction results comprises: and inputting the test set into the trained neural network model to obtain a mapping relation between the tunnel geological information and the prediction result, and outputting the prediction result based on the mapping relation.
In some embodiments, the process of obtaining a tunnel surrounding rock support form comprises: analyzing the tunnel hoop peak stress and the surrounding rock deformation to obtain an analysis result; and obtaining a tunnel surrounding rock supporting form corresponding to the analysis result according to the tunnel risk level.
As shown in fig. 1, the specific implementation manner in this embodiment:
(1) Collecting historical earthquake damage data, and collecting earthquake intensity, intensity information and various geological information of a tunnel, such as tunnel burial depth, surrounding rock characteristics, fault fracture zone conditions and the like, and the ground stress change conditions, surrounding rock deformation, tunnel damage conditions and the like after an earthquake occurs; through a numerical simulation test, tunnel damage conditions when an earthquake occurs are simulated, a large amount of data are collected, and a database is established based on the data. Specifically, the method comprises the following steps:
the method for retrieving the literature data and collecting the geological information of the existing tunnel suffered from the earthquake disaster comprises the following steps: the method comprises the following steps of tunnel burial depth, surrounding rock grade, fault fracture zone quantity, seismic intensity grade, and post-earthquake ground tunnel annular peak stress and surrounding rock deformation quantity. Due to the limited engineering case, a three-dimensional digital tunnel model is established, the model is positioned in the external environment of frequent earthquakes, the earthquakes with different intensity levels are repeatedly simulated, a large amount of tunnel annular peak stress and surrounding rock deformation data are stored through the calculated stress change and displacement change in the tunnel, and a database is established.
(2) And (4) preprocessing data, and deeply excavating the internal relation among seismic information, surrounding rock geological information, tunnel damage information such as ground stress and surrounding rock displacement change and the like by using a BP neural network model. Specifically, the method comprises the following steps:
and I, normalizing wrong values, values with different types, abnormal values and values which are not suitable for the algorithm model in the data set to enable the data to meet the analysis requirement. Data normalization refers to a process of subtracting the minimum value of data from the data and dividing the data by the range of 0-1.
The formula is as follows:
wherein x represents the data value in the tunnel annular peak stress or the surrounding rock deformation quantity, min (x) represents the minimum value in the data, max (x) represents the maximum value in the data,
representing the normalized data values.
And II, taking 80% of the preprocessed data as a training data set, and taking 20% of the preprocessed data as a test data set. The seismic information, tunnel buried depth, surrounding rock grade and fault fracture zone number are set as input parameters, and the annular peak stress and surrounding rock deformation of the earthquake tunnel are set as input parameters.
Provide input examples to input layer neurons and then forward signals layer by layer until a result for the output layer is produced.
And IV, calculating the error of the output layer, reversely transmitting the error to the hidden layer neuron, and updating the connection weight and the threshold according to the error of the hidden layer neuron.
And V, estimating errors by using the verification set, stopping training if the errors of the training set are reduced but the errors of the verification set are increased, and returning the connection weight and the threshold value with the minimum errors of the verification set, otherwise, performing iteration and circulation. And finally, acquiring the mapping relation among the seismic intensity level, the surrounding rock stratum information, the surrounding rock displacement and the stress change.
(3) Establishing an intelligent decision module, investigating data, analyzing the seismic intensity possibly or ever occurring along the tunnel, the geological condition along the tunnel and the like, using a neural network model, proposing a tunnel risk classification mechanism by analyzing the relation between input parameters and output parameters, and guiding a tunnel support mode based on risk grades. Specifically, the method comprises the following steps:
the method comprises the steps of I, consulting data, and obtaining historical highest earthquake grade of an earthquake-prone area and some geological information of a construction tunnel, including tunnel burial depth, surrounding rock grade and fault fracture zone number;
and II, acquiring predicted tunnel annular peak stress and surrounding rock deformation quantity of the tunnel by using the mapping relation of the input parameters and the output parameters obtained by the neural network model.
And III, determining a risk level by analyzing the annular peak stress and the deformation quantity of the surrounding rock of the tunnel according to an index selection principle or consulting experts, and determining a supporting form of the surrounding rock according to the risk level.
The invention has the beneficial effects that:
the invention establishes a database containing various seismic information, geological information and tunnel damage information. And the data volume is increased by utilizing numerical simulation, so that the supporting method is not confined to limited field engineering cases, and the large cost of the entity model is saved.
The method introduces a neural network model, and deeply excavates the mapping relation between the seismic information, the geological information and the tunnel damage information based on the database. For the tunnel established in the earthquake-prone area, the method can acquire and manage corresponding data, analyze the influence of the earthquake on the tunnel, and accurately predict the stress change and the change of the surrounding rock of the tunnel, so as to put forward a decision scheme and guide the support of the surrounding rock, avoid the situations of over-support due to small earthquake, over-support due to large earthquake and less support due to large earthquake, and ensure the safety of constructors and the safety of the personnel passing through the tunnel in the later operation process.
Example two
In order to achieve the technical purpose, the invention also provides a deep learning-based earthquake multi-occurrence zone tunnel risk decision system, which comprises: the system comprises a data acquisition module, a model training module, a prediction output module and a risk decision module; the data acquisition module, the model training module, the prediction output module and the risk decision module are sequentially connected;
the data acquisition module is used for establishing a sample data set of the tunnel in the earthquake multi-occurrence area;
the model training module is used for constructing and training a neural network model to obtain a trained neural network model;
the prediction output module is used for inputting the sample data set into the trained neural network model and outputting a prediction result, wherein the prediction result comprises: the circumferential peak stress and the deformation of surrounding rocks of the tunnel;
and the risk decision module is used for obtaining a tunnel surrounding rock supporting form according to the risk grade of the tunnel based on the prediction result.
In some embodiments, the data acquisition module comprises: the device comprises an information acquisition unit and a data set construction unit; the information acquisition unit is used for acquiring tunnel geological information subjected to earthquake disasters, wherein the tunnel geological information comprises: geological information, seismic intensity information and surrounding rock damage conditions; and the data set construction unit is used for establishing a three-dimensional digital tunnel model through a numerical simulation test based on the tunnel geological information and establishing a sample data set of the tunnel in the earthquake multi-occurrence area based on the three-dimensional digital tunnel model.
In some embodiments, the model training module comprises: the system comprises a data preprocessing unit and a model training unit; the data preprocessing unit is used for carrying out normalization preprocessing on the sample data set to obtain a preprocessed sample data set; and the model training unit is used for dividing the preprocessed sample data set into a training set and a testing set, training the neural network model through the training set until the output error is reduced to an expected value, and obtaining the trained neural network model.
In some embodiments, the prediction output module comprises: a mapping relation obtaining unit and a prediction output unit; the mapping relation obtaining unit is used for inputting the test set into the trained neural network model to obtain the mapping relation between the tunnel geological information and the prediction result; and a prediction output unit which outputs a prediction result based on the mapping relation.
In some embodiments, in the risk decision module, the tunnel hoop peak stress and the surrounding rock deformation are analyzed to obtain an analysis result; and obtaining a tunnel surrounding rock supporting form corresponding to the analysis result according to the tunnel risk level.
As shown in fig. 2, the specific implementation manner in this embodiment:
(1) And the data acquisition module comprises a database unit and a field data unit. In the database unit, a large number of data samples are established, including various seismic information, geological information and tunnel destruction information. In the field data unit, collecting earthquake sensitivity influence information of the construction tunnel: tunnel buried depth, surrounding rock grade, fault fracture zone quantity and seismic intensity grade. And inputting the collected data into a data processing module, and obtaining a predicted output parameter based on the preprocessing unit and the actual combat unit.
(2) The data processing module comprises a preprocessing unit, a training unit and an actual combat unit. In the preprocessing unit, the data are normalized in the training unit, the preprocessed data are led into a neural network algorithm model based on BP (back propagation) for training, and the mapping relation between various input parameters (tunnel burial depth, surrounding rock grade, fault fracture zone quantity and seismic intensity grade) and output parameters (tunnel annular peak stress and surrounding rock deformation) is analyzed. In the actual combat unit, the predicted output parameters are output by using the obtained mapping relation.
(3) And the intelligent decision module is used for determining the risk level according to the index selection principle or consulting experts on the tunnel annular peak stress and the surrounding rock deformation amount, and determining the surrounding rock supporting form according to the risk level.
In a data acquisition module, storing a plurality of data samples, comprising: the method comprises the steps of inputting geological information of a construction tunnel, such as tunnel burial depth, surrounding rock grade, fault broken zone quantity and historical highest seismic grade of a tunnel along a line, and obtaining surrounding rock ground stress change and surrounding rock deformation quantity through a data processing module, wherein the geological information, the surrounding rock geological information, the ground stress, the surrounding rock displacement change and other tunnel damage information are input.
In the data processing module, by some factors sensitive to the influence of the earthquake: the tunnel buried depth, the surrounding rock grade, the number of fault fracture zones, the seismic intensity grade and the seismic intensity grade are trained by utilizing a neural network model, and the intrinsic relation between seismic information, surrounding rock geological information, ground stress, surrounding rock displacement change and other tunnel damage information is mined.
In the intelligent decision module, by establishing the risk level, a special intelligent decision is provided for different risk levels, and the support of the surrounding rock is effectively guided.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A deep learning-based earthquake multi-occurrence zone tunnel risk decision method is characterized by comprising the following steps:
establishing a sample data set of a tunnel in an earthquake multi-occurrence area;
constructing and training a neural network model to obtain a trained neural network model;
inputting the sample data set into a trained neural network model, and outputting a prediction result, wherein the prediction result comprises: the circumferential peak stress and the deformation of surrounding rocks of the tunnel;
and obtaining a tunnel surrounding rock supporting form according to the risk grade of the tunnel based on the prediction result.
2. The deep learning-based seismic multi-occurrence zone tunnel risk decision method according to claim 1, wherein the process of establishing the sample data set of the seismic multi-occurrence zone tunnel comprises:
acquiring tunnel geological information subjected to earthquake disasters, wherein the tunnel geological information comprises: geological information, seismic intensity information and surrounding rock damage conditions;
and establishing a three-dimensional digital tunnel model through a numerical simulation test based on the tunnel geological information, and establishing a sample data set of the tunnel in the earthquake multi-occurrence area based on the three-dimensional digital tunnel model.
3. The deep learning-based seismic multi-occurrence zone tunnel risk decision method according to claim 2, wherein the process of constructing and training the neural network model comprises:
carrying out normalization pretreatment on the sample data set to obtain a pretreated sample data set; and dividing the preprocessed sample data set into a training set and a testing set, and training the neural network model through the training set until the output error is reduced to an expected value to obtain the trained neural network model.
4. The deep learning-based seismic multi-occurrence zone tunnel risk decision method according to claim 3, wherein the process of outputting the prediction result comprises:
and inputting the test set into a trained neural network model to obtain a mapping relation between the tunnel geological information and the prediction result, and outputting the prediction result based on the mapping relation.
5. The deep learning-based earthquake multi-occurrence zone tunnel risk decision method as claimed in claim 1, wherein the process of obtaining the tunnel surrounding rock support form comprises:
analyzing the tunnel annular peak stress and the surrounding rock deformation to obtain an analysis result; and obtaining a tunnel surrounding rock supporting form corresponding to the analysis result according to the tunnel risk level.
6. A deep learning-based earthquake multi-occurrence zone tunnel risk decision making system is characterized by comprising: the system comprises a data acquisition module, a model training module, a prediction output module and a risk decision module; the data acquisition module, the model training module, the prediction output module and the risk decision module are connected in sequence;
the data acquisition module is used for establishing a sample data set of the tunnel in the earthquake multi-occurrence area;
the model training module is used for constructing and training a neural network model to obtain a trained neural network model;
the prediction output module is configured to input the sample data set to a trained neural network model, and output a prediction result, where the prediction result includes: the circumferential peak stress and the surrounding rock deformation of the tunnel;
and the risk decision module is used for obtaining a tunnel surrounding rock supporting form according to the risk grade of the tunnel based on the prediction result.
7. The deep learning based seismic multi-issue zone tunnel risk decision system of claim 6, wherein the data acquisition module comprises: the device comprises an information acquisition unit and a data set construction unit;
the information acquisition unit is used for acquiring tunnel geological information subjected to earthquake disasters, wherein the tunnel geological information comprises: geological information, seismic intensity information and surrounding rock damage conditions;
the data set construction unit establishes a three-dimensional digital tunnel model through a numerical simulation test based on the tunnel geological information, and establishes a sample data set of the tunnel in the earthquake multi-occurrence area based on the three-dimensional digital tunnel model.
8. The deep learning based seismic multi-issue zone tunnel risk decision system of claim 7, wherein the model training module comprises: the system comprises a data preprocessing unit and a model training unit;
the data preprocessing unit is used for carrying out normalization preprocessing on the sample data set to obtain a preprocessed sample data set;
and the model training unit is used for dividing the preprocessed sample data set into a training set and a testing set, training the neural network model through the training set until the output error is reduced to an expected value, and obtaining the trained neural network model.
9. The deep learning based seismic multi-zone tunnel risk decision system of claim 8, wherein the prediction output module comprises: a mapping relation obtaining unit and a prediction output unit;
the mapping relation obtaining unit is used for inputting the test set into a trained neural network model to obtain a mapping relation between the tunnel geological information and the prediction result;
and the prediction output unit outputs a prediction result based on the mapping relation.
10. The deep learning-based earthquake multi-occurrence-zone tunnel risk decision system as claimed in claim 6, wherein in the risk decision module, the tunnel hoop peak stress and the surrounding rock deformation are analyzed to obtain an analysis result; and obtaining a tunnel surrounding rock supporting form corresponding to the analysis result according to the tunnel risk level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211629044.1A CN115688251A (en) | 2022-12-19 | 2022-12-19 | Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211629044.1A CN115688251A (en) | 2022-12-19 | 2022-12-19 | Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115688251A true CN115688251A (en) | 2023-02-03 |
Family
ID=85055035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211629044.1A Pending CN115688251A (en) | 2022-12-19 | 2022-12-19 | Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115688251A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115788591A (en) * | 2023-02-08 | 2023-03-14 | 山东大学 | Monitoring and intelligent regulation and control system for dust and harmful gas in deep-buried long tunnel |
| CN116975623A (en) * | 2023-05-04 | 2023-10-31 | 西南交通大学 | Method, device and medium for predicting large deformation grade in tunnel construction stage by drilling and blasting method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344389A (en) * | 2008-08-20 | 2009-01-14 | 中国建筑第八工程局有限公司 | Method for estimating tunnel surrounding rock displacement by neural network |
| CN104182622A (en) * | 2014-08-12 | 2014-12-03 | 大连海事大学 | Feedback analytical method and feedback analytical device during tunnel construction and based on extreme learning machine |
| CN106570563A (en) * | 2015-10-13 | 2017-04-19 | 中国石油天然气股份有限公司 | Deformation prediction method and apparatus based on Kalman filtering and BP neural network |
| CN110688689A (en) * | 2019-07-16 | 2020-01-14 | 中铁隧道局集团有限公司 | Tunnel deformation prediction method based on multi-source monitoring data fusion |
| CN112084553A (en) * | 2020-08-06 | 2020-12-15 | 重庆市市政设计研究院有限公司 | Surveying method for tunnel planning |
| CN112614021A (en) * | 2020-12-24 | 2021-04-06 | 东南大学 | Tunnel surrounding rock geological information prediction method based on built tunnel information intelligent identification |
| CN113112446A (en) * | 2020-03-05 | 2021-07-13 | 成都理工大学 | Tunnel surrounding rock level intelligent judgment method based on residual convolutional neural network |
| CN114611193A (en) * | 2022-03-15 | 2022-06-10 | 浙江省交通运输科学研究院 | Tunnel mechanical property rapid inversion method based on deep learning |
| CN114722482A (en) * | 2022-06-08 | 2022-07-08 | 北京邦业智能科技有限公司 | Method for predicting deformation of plateau tunnel and plateau tunnel health detection system |
| CN115062375A (en) * | 2022-05-24 | 2022-09-16 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Grading method and system for tunnel surrounding rock |
| CN115221793A (en) * | 2022-07-29 | 2022-10-21 | 招商局重庆交通科研设计院有限公司 | Tunnel surrounding rock deformation prediction method and device |
-
2022
- 2022-12-19 CN CN202211629044.1A patent/CN115688251A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344389A (en) * | 2008-08-20 | 2009-01-14 | 中国建筑第八工程局有限公司 | Method for estimating tunnel surrounding rock displacement by neural network |
| CN104182622A (en) * | 2014-08-12 | 2014-12-03 | 大连海事大学 | Feedback analytical method and feedback analytical device during tunnel construction and based on extreme learning machine |
| CN106570563A (en) * | 2015-10-13 | 2017-04-19 | 中国石油天然气股份有限公司 | Deformation prediction method and apparatus based on Kalman filtering and BP neural network |
| CN110688689A (en) * | 2019-07-16 | 2020-01-14 | 中铁隧道局集团有限公司 | Tunnel deformation prediction method based on multi-source monitoring data fusion |
| CN113112446A (en) * | 2020-03-05 | 2021-07-13 | 成都理工大学 | Tunnel surrounding rock level intelligent judgment method based on residual convolutional neural network |
| CN112084553A (en) * | 2020-08-06 | 2020-12-15 | 重庆市市政设计研究院有限公司 | Surveying method for tunnel planning |
| CN112614021A (en) * | 2020-12-24 | 2021-04-06 | 东南大学 | Tunnel surrounding rock geological information prediction method based on built tunnel information intelligent identification |
| CN114611193A (en) * | 2022-03-15 | 2022-06-10 | 浙江省交通运输科学研究院 | Tunnel mechanical property rapid inversion method based on deep learning |
| CN115062375A (en) * | 2022-05-24 | 2022-09-16 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Grading method and system for tunnel surrounding rock |
| CN114722482A (en) * | 2022-06-08 | 2022-07-08 | 北京邦业智能科技有限公司 | Method for predicting deformation of plateau tunnel and plateau tunnel health detection system |
| CN115221793A (en) * | 2022-07-29 | 2022-10-21 | 招商局重庆交通科研设计院有限公司 | Tunnel surrounding rock deformation prediction method and device |
Non-Patent Citations (1)
| Title |
|---|
| 崔涛: ""岩溶隧道风险预报及支护技术研究"" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115788591A (en) * | 2023-02-08 | 2023-03-14 | 山东大学 | Monitoring and intelligent regulation and control system for dust and harmful gas in deep-buried long tunnel |
| CN116975623A (en) * | 2023-05-04 | 2023-10-31 | 西南交通大学 | Method, device and medium for predicting large deformation grade in tunnel construction stage by drilling and blasting method |
| CN116975623B (en) * | 2023-05-04 | 2024-01-30 | 西南交通大学 | Method, device and medium for predicting large deformation grade in tunnel construction stage by drilling and blasting method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Dynamic prediction for attitude and position in shield tunneling: A deep learning method | |
| CN115688251A (en) | Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning | |
| CN108510112B (en) | Mine disaster prediction and early warning method combining field monitoring and numerical simulation | |
| Liu et al. | Tunnel boring machine vibration-based deep learning for the ground identification of working faces | |
| CN110109895A (en) | Fender graded unified prediction and application suitable for TBM driving tunnel | |
| Niu et al. | Types and occurrence time of rockbursts in tunnel affected by geological conditions and drilling & blasting procedures | |
| CN116562656B (en) | Tunnel construction geological disaster early warning and prevention and control intelligent decision method and auxiliary platform | |
| CN112308306A (en) | Multi-mode input coal and gas outburst risk prediction method | |
| CN113821977B (en) | Rock burst risk assessment system and method for TBM tunnel construction | |
| CN116591777B (en) | Multi-field multi-source information fusion rock burst intelligent monitoring and early warning device and method | |
| Wang et al. | An auto-detection network to provide an automated real-time early warning of rock engineering hazards using microseismic monitoring | |
| Wang et al. | Rock burst monitoring and early warning under uncertainty based on multi-information fusion approach | |
| CN107798189A (en) | One kind is based on the geophysical precisely dynamic anti-burst method of Transparent space | |
| CN116384112A (en) | Method and system for mine disaster simulation and early warning | |
| CN116044501A (en) | Advanced geological forecast dynamic monitoring and early warning system and method | |
| CN113326661B (en) | RS-XGboost-based tunnel advanced drilling quantitative interpretation method and device | |
| CN114810213A (en) | Multi-source information fusion intelligent early warning method and device for coal and gas outburst | |
| Zhang et al. | Risk identification for coal and gas outburst in underground coal mines: A critical review and future directions | |
| CN117152918A (en) | Dangerous dynamic early warning method applied to regional landslide disaster | |
| CN114066271A (en) | Tunnel water inrush disaster monitoring and management system | |
| Zhang et al. | Risk Assessment of Rockburst with a LS‐FAHP‐CRITIC Method: A Case in Gaojiapu Coal Mine, North of China | |
| Su et al. | A Review of Deep Learning Applications in Tunneling and Underground Engineering in China | |
| Zhang et al. | Performance and Applicability of Recognizing Microseismic Waveforms Using Neural Networks in Tunnels | |
| Wu et al. | A rapid detection method of earthquake infrasonic wave based on decision-making tree and the BP neural network | |
| Jiang | Adaptive GA-BP Model Prediction of Subway Shield Tunneling Settlement in Smart City Construction |
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 |