CN110909402B - Advanced small catheter design method based on neural network technology - Google Patents
Advanced small catheter design method based on neural network technology Download PDFInfo
- Publication number
- CN110909402B CN110909402B CN201911042531.6A CN201911042531A CN110909402B CN 110909402 B CN110909402 B CN 110909402B CN 201911042531 A CN201911042531 A CN 201911042531A CN 110909402 B CN110909402 B CN 110909402B
- Authority
- CN
- China
- Prior art keywords
- neural network
- data
- advanced
- small
- monitoring
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention discloses a design method of a small advanced catheter based on a neural network technology, which comprises the following steps: firstly, counting a large amount of tunnel construction monitoring measurement data, analyzing the monitoring measurement data by adopting a multivariate correlation analysis method, and determining a monitoring measurement item for advanced small conduit parameter analysis; secondly, taking the design parameters of the advanced small catheter as input data, taking the monitoring data of the monitoring measurement items as output data to construct a neural network model, and carrying out reliability test on the prediction result of the neural network to obtain the nonlinear relation between the parameters of the small catheter and the monitoring data; and finally, optimizing the parameters of the small catheter by adopting a multi-objective genetic algorithm to determine the optimal design parameters. The method can quantize the design parameters of the advanced small guide pipe on the basis of ensuring the accuracy and reliability of the monitoring and measuring project result, improve the design efficiency and the operability and greatly reduce the potential safety hazard in the construction process.
Description
Technical Field
The invention belongs to the field of tunnel protection, and particularly relates to a design method of a small advanced catheter based on a neural network technology.
Background
In recent years, with the pace of infrastructure in China accelerating, and the broad breadth and complex landform of the country, various tunnels including traffic tunnels, hydraulic tunnels, municipal tunnels, mine tunnels and the like appear. For some unfavorable geological rock strata such as weak broken zones and shallow buried sections, the advance support of the tunnel face before excavation becomes a common mode for solving the problem of large excavation difficulty. The current forepoling form mainly comprises: advance stock, advance pipe canopy and advance slip casting, advance little pipe in advance specifically as follows:
(1) The advanced anchor rod is installed with a large external inserting angle along the tunnel face to the front of the excavation face to form pre-anchoring to front surrounding rock, and construction operation is carried out under the protection of the formed surrounding rock anchoring ring. The anchor rod is 3-5 m long and is matched with a steel frame for construction. The advanced anchor rod is mainly suitable for tunnels with small surrounding rock stress, less underground water and small weak and broken degree of rock masses;
(2) The advanced pipe shed is characterized in that a steel pipe shed protector is annularly arranged along a part or all of the tunnel face at a certain interval. The forepoling is mainly used in the weak broken surrounding rock tunnel engineering which has more strict restriction requirements for surrounding rock deformation and ground surface subsidence;
(3) The advanced pre-grouting is to utilize grout to fill and re-bond the surrounding rock around the tunnel face and improve the physical and mechanical properties of the surrounding rock, thereby improving the overall stability and impermeability of the surrounding rock. The advanced pre-grouting is mainly used for faults, weak broken surrounding rocks and rock stratums rich in a large amount of tectonic fracture water;
(4) The advanced small conduit is an effective auxiliary construction method for stabilizing the rock stratum. In the construction of weak and broken rock strata, the leading small guide pipe is annularly driven into the rock strata according to a certain distance, then the leading small guide pipe is grouted, and the stability of the weak and broken surrounding rock is effectively enhanced. When the hole is easy to collapse after the hole is dug in a weak and broken stratum and the construction of an advanced anchor rod is difficult or the structural section is large, an advanced small conduit is adopted for supporting.
Because the geological condition of the rock stratum is complex and the mechanical parameters are difficult to determine, the parameters such as the length, the pipe diameter, the annular arrangement distance, the arrangement extrapolation angle and the like of the small pipe are often determined by adopting design experience and engineering experience when the parameters of the small pipe are designed. The uncertainty of the design parameters directly creates certain potential safety hazards for tunnel construction. Therefore, a method of combining the neural network technology and the field measured data is introduced to ensure that the test result is accurate and reliable and reduce the potential safety hazard.
The neural network is a network formed by parallel interconnection of adaptive neurons, can simulate the nervous system of a living being and can interactively react with the real world. The neural network is provided with an input layer, a hidden layer and an output layer, can be regarded as a nonlinear complex function, the input layer and the output layer respectively represent independent variables and dependent variables, only existing input and output are used as samples, the neural network is repeatedly trained through the samples, the functional relation between the independent variables and the dependent variables is established, an ideal network model is finally obtained, training of the network is completed, and corresponding predicted values are obtained. The neural network has strong learning ability, so that the neural network is suitable for analyzing the characteristics of complex geological rock strata and solving the problem that the mechanical parameters of the neural network are difficult to determine.
The purpose of the credibility inspection is to control the reliability of the required result, inspect the unreliable condition and process in time, so that the final result can meet the safety evaluation requirement. The mean square error (mse) may reflect the degree of difference between the estimator and the estimated quantity. The mean square error between the predicted value and the measured value of the neural network training can well reflect the performance of the neural network training. Reliability alpha test is introduced to further evaluate the performance of the neural network, and the accuracy and reliability of the test result are ensured.
Multiobjective optimization mainly studies the problem of simultaneous optimization of multiple numerical targets under certain conditions. The multi-target Genetic Algorithm GA (Genetic Algorithm) is a self-organizing and self-adapting artificial intelligence technology for simulating the natural biological evolution process and mechanism to solve problems, and the Algorithm is used for the reference of natural selection and natural Genetic mechanism in the biology world. The essence of the optimization problem is: in many cases, the sub-targets may conflict with each other, and the improvement of one sub-target may cause the performance of another sub-target to be reduced, that is, it is difficult to simultaneously optimize a plurality of sub-targets, and coordination and compromise processing can only be performed among the sub-targets, so that the sub-target function is optimized as much as possible, that is, the monitoring and measuring item is used as an optimization target, the optimal advanced small conduit parameter is selected, the risk in the construction process is reduced to the maximum extent, and the safety of personnel and the smooth operation of construction are ensured.
Disclosure of Invention
In order to solve the problems, the invention discloses a method for designing an advanced small duct based on a neural network technology, which can well solve the problems of difficult determination of mechanical parameters of a complex rock stratum, difficult design of advanced small duct parameter design quantization, potential safety hazards in the construction process and the like, and has an instructive effect on the design of a future small duct.
In order to achieve the purpose, the technical scheme of the invention is as follows:
the design method of the advanced small catheter based on the neural network technology comprises the following steps:
the first step is as follows: according to the existing advanced small conduit design parameters and tunnel construction monitoring measurement data, the influence of different design parameters on the monitoring measurement data is statistically analyzed, and small conduit design parameters influencing the monitoring measurement data are determined, wherein the small conduit design parameters comprise the length, the pipe diameter, the extrapolation angle and the circumferential arrangement distance of a small conduit;
the second step: the tunnel monitoring and measuring items comprise multiple items such as vault settlement, surface settlement, tunnel horizontal convergence, surrounding rock pressure, arch springing deformation and inverted arch uplift, the monitoring and measuring item data are analyzed by adopting multivariate correlation analysis, the measuring items with high correlation degree are removed, and the monitoring and measuring items influencing the parameters of the small advanced guide pipe are determined;
the third step: taking the design parameters of the advanced small catheter as input data of a neural network, monitoring and measuring the data as output data, and training a neural network model;
the fourth step: dividing the existing statistical data into a training set (60%), a verification set (20%) and a test set (20%), training a neural network by adopting the training set and the verification set, establishing a nonlinear relation between the advanced ductule parameters and monitoring measurement data, and taking the mean square error (mse) and the reliability (alpha) between the test set data and the neural network prediction result as the basis for testing the reliability of the neural network;
the fifth step: if the test result in the fourth step does not meet the requirement, repeating the steps 1-4 until the test result meets the requirement so as to ensure the reliability of the prediction result;
and a sixth step: optimizing the parameters of the advanced small catheter by adopting a multi-objective genetic algorithm, taking the monitoring and measuring data as an optimization target, taking the design parameter range of the small catheter as a constraint condition, and determining the optimal design parameters of the small catheter;
the seventh step: and constructing a neural network model based on the existing statistical data, and performing multi-objective optimization on the advanced ductus efferens parameters to obtain an advanced ductus efferens parameter analysis and multi-objective optimization model based on the neural network technology, wherein the advanced ductus efferens parameter analysis and multi-objective optimization model is used for selecting reasonable ductus efferens design parameters.
In the second step, tunnel monitoring measurement project data are analyzed by adopting a multivariate correlation analysis method, monitoring projects with the correlation degree higher than 85% are removed, and the reserved monitoring projects reflect original information as much as possible.
In the third step, the parameters of the leading small catheter are used as the input data of the neural network, the monitoring measurement data determined by multivariate correlation analysis is used as the output data, and the neural network model is trained, wherein x i (i = 1.... N) is input information, the hidden layer has d neurons, y j (j = 1.... M) is output information, and the weights and thresholds of the neurons i to j are ω respectively ij And T j Then the state of neuron j can be expressed as:
In the fourth step, to verify the concentrated measured data y i And neural network prediction result f (x) i ) Mean square error (mse) and confidence a of the neural network model, wherein the mean square error
Confidence level
If alpha is epsilon [0,5%]If the test result does not meet the requirement, the first step to the fourth step are repeated until the test result meets the requirement so as to ensure the reliability of the predicted result.
In the sixth step, the result of the neural network prediction is optimized by adopting a multi-objective genetic algorithm, the design parameter range of the small catheter is taken as a constraint condition, and the monitored measurement item data y of the neural network prediction is used j (j = 1.. Eta., m) as an optimization target, determining an optimal small catheter design parameter x i (i = 1.. Times, n). Each design parameter range of the small catheter is x il ≤x i ≤x ir (i = 1.... N), where x is il 、x ir Monitoring the metrology item data y for the left and right boundaries of the design parameter range, respectively j ≤y j max (j = 1.. Multidot.m), wherein, y j max To monitor the limits of the measured items, a multi-objective genetic algorithm model of the advanced ductus arteriosus design parameters is built, as shown below.
The invention has the beneficial effects that:
the invention discloses a method for designing an advanced small catheter based on a neural network technology, aiming at the defects of the advanced small catheter in parameter quantitative design. And then, predicting the monitored measurement items by adopting a neural network technology, comparing the predicted measurement items with the actually measured data, and introducing a reliability index to evaluate the model until a neural network model conforming to the evaluation is obtained. And finally, optimally designing the parameters of the advanced small catheter by adopting a multi-objective genetic algorithm. The method can quantize the design parameters of the advanced small guide pipe on the basis of ensuring the accurate and reliable result of the derived measurement project, improve the design efficiency and the operability and greatly reduce the potential safety hazard in the construction process. In view of the acceleration of the pace of infrastructure construction in China, tunnel construction under complex geological conditions is an urgent problem in China, and a scientific, accurate, reliable and convenient advanced small conduit parameter design technology is urgently needed to be developed. Therefore, the invention has wide application prospect in the future advanced small catheter optimization design and generates remarkable social and economic benefits.
Drawings
FIG. 1 is a technical flow chart of a leading small catheter design method based on a neural network technology.
FIG. 2 is a schematic diagram of a neural network model.
FIG. 3 is a flow chart of a multi-objective genetic algorithm.
Detailed Description
The present invention will be further illustrated with reference to the accompanying drawings and specific embodiments, which are to be understood as merely illustrative of the invention and not as limiting the scope of the invention.
The main flow of the implementation scheme of the invention is specifically as follows (see fig. 1):
the first step is as follows: according to the existing advanced small conduit design parameters and tunnel construction monitoring measurement data, the influence of different design parameters on the monitoring measurement data is counted and analyzed, and the small conduit design parameter x influencing the monitoring measurement data is determined i (i = 1.., 4), including a small catheter length x 1 Diameter x of pipe 2 And a circumferential arrangement distance x 3 And arranging the extrapolation angle x 4 。
The second step is that: according to the provisions of technical rules for monitoring and measuring railway tunnels (QCR 9218-2015), tunnel monitoring and measuring items comprise multiple items such as vault settlement, surface subsidence, tunnel horizontal convergence, surrounding rock pressure, arch springing deformation and inverted arch uplift, data of the monitoring and measuring items are analyzed by adopting a multivariate correlation analysis method, a correlation coefficient matrix (as follows) between any two monitoring and measuring items is established, variables with the correlation degree higher than 85% are eliminated, and the monitoring and measuring item y influencing the parameters of the advanced ductus j (j＝1,..,m)。
Wherein r is ij The correlation coefficient between any two monitored metrology items is determined.
Wherein, cov (y) i ,y j ) Is y i And y j Covariance of D (y) i )D(y j ) Are each y i And y j The variance of (c).
The third step: training a neural network model (see fig. 2) by using the design parameters of the small advanced catheter as input data of the neural network and the monitoring measurement item data determined by multivariate correlation analysis as output data, wherein x is i (i = 1.... N) is input information, the hidden layer has d neurons, y j (j = 1.. Multidot., m) is output information, and the weights and thresholds of the neurons i to j are ω, respectively ij And T j Then the state of neuron j can be expressed as:
The fourth step: dividing the existing statistical data into a training set (60%), a verification set (20%) and a test set (20%), training a neural network by adopting the training set and the verification set, and establishing a nonlinear relation between the advanced ductule parameters and the monitoring measurement data.
The fifth step: and (3) testing the reliability of the neural network by using the mean square error (mse) and the credibility (alpha) between the test set data and the prediction result of the neural network. With measured data y in the test set j And neural network prediction result f (x) j ) Mean square error (mse) and confidence a of the neural network, wherein the mean square error
Confidence level
If alpha belongs to [0,5%]Indicating that the predicted value meets the reliability requirement; if the test result does not meet the requirement, repeating the steps of 1-5 until the test result meets the requirement so as to ensure the reliability of the prediction result.
And a sixth step: since different design small catheter parameters have different influences on monitoring measurement items, a multi-objective genetic algorithm is adopted to optimize advanced small catheter parameters (see fig. 3). The design range of the advanced small conduit parameters is determined according to related data such as high-speed railway tunnel engineering construction technical regulations (Q/CR 9604-2015). Monitoring measurement project data y predicted by neural network j (j = 1.. Eta., m) as an optimization target, a small catheter parameter design range as a constraint condition, and determining an optimal small catheter design parameter x i (i = 1.. Ang., n), monitoring the measurement item data y j ≤y j max (j = 1.. Multidot., m), wherein, y j max For monitoring the limit values of the measurement items, the range of the individual design parameters of the small catheter is x il ≤x i ≤x ir (i = 1.... N), where x is il 、x ir The left boundary and the right boundary of the design parameter range are respectively set, so that a multi-target genetic algorithm model of the advanced small catheter design parameters is established, and the following steps are shown.
The seventh step: a neural network model is established based on the existing statistical data, and multi-objective optimization is carried out on the advanced small catheter parameters to obtain the advanced small catheter design method based on the neural network technology, which is used for selecting reasonable small catheter design parameters.
The technical means disclosed in the invention scheme are not limited to the technical means disclosed in the above embodiments, but also include the technical scheme formed by any combination of the above technical features.
Claims (4)
1. A design method of a leading small catheter based on a neural network technology is characterized by comprising the following steps:
the first step is as follows: according to the existing advanced small conduit design parameters and tunnel construction monitoring measurement project data, the influence of different design parameters on the monitoring measurement project data is counted and analyzed, and the small conduit design parameters influencing the monitoring measurement project data are determined, wherein the small conduit design parameters comprise the small conduit length, the pipe diameter, the extrapolation angle and the annular arrangement distance;
the second step: the tunnel monitoring and measuring items comprise vault settlement, surface settlement, tunnel horizontal convergence, surrounding rock pressure, arch springing deformation and inverted arch uplift, the monitoring and measuring item data are analyzed by adopting multivariate correlation analysis, measuring items with the correlation degree higher than 85% are removed, and monitoring and measuring items influencing the parameters of the small advanced guide pipe are determined;
the third step: taking the design parameters of the advanced small catheter as input data of a neural network, monitoring measurement project data as output data, and training a neural network model;
the fourth step: dividing the existing statistical data into a training set, a verification set and a test set according to the proportion of 60%, 20% and 20%, training a neural network by adopting the training set and the verification set, establishing a nonlinear relation between the advanced ductus efferens parameters and the monitoring measurement project data, and taking the mean square error mse and the reliability alpha between the test set data and the neural network prediction result as the basis for testing the reliability of the neural network;
the fifth step: if the test result in the fourth step does not meet the requirement, repeating the first step to the fourth step until the test result meets the requirement so as to ensure the reliability of the prediction result;
and a sixth step: optimizing the parameters of the advanced small catheter by adopting a multi-objective genetic algorithm, taking the data of the monitored measurement project as an optimization target, taking the design parameter range of the small catheter as a constraint condition, and determining the optimal design parameters of the small catheter;
the seventh step: and constructing a neural network model based on the existing statistical data, and performing multi-objective optimization on the advanced ductule parameters to obtain an advanced ductule parameter analysis and multi-objective optimization model based on the neural network technology, wherein the advanced ductule parameter analysis and multi-objective optimization model is used for selecting ductule design parameters.
2. The method for designing the small advanced catheter based on the neural network technology as claimed in claim 1, wherein: in the third step, the parameters of the advanced small catheter are used as input data of the neural network, the monitoring measurement item data determined by multivariate correlation analysis is used as output data, and a neural network model is trained, wherein x i For input information, i = 1.., n, hidden layer has d neurons, y j For the output information, j = 1.. M, the weights and thresholds of the neurons i to j are ω, respectively ij And T j Then the state of neuron j can be expressed as:
3. The method for designing the small advanced catheter based on the neural network technology as claimed in claim 1, wherein: in the fourth step, the measured data y in the test set is adopted i And neural network prediction result f (x) i ) The mean square error mse and the confidence degree alpha of (MSE) check the reliability of the neural network model, wherein the MSE
Confidence level->
If alpha belongs to [0,5%]If the test result does not meet the requirement, repeating the steps one to four until the test result meets the requirement so as to ensure the reliability of the predicted result.
4. The method for designing a leading small catheter based on the neural network technology as claimed in claim 1, wherein: in the sixth step, the prediction result of the neural network is optimized by adopting a multi-objective genetic algorithm, and the monitoring measurement item data y predicted by the neural network is used j As optimization targetDetermining the optimum small catheter design parameter x by using the small catheter design parameter range as the constraint condition i I =1,.., n; the constraint condition of each monitored measurement item data is y j ≤y jmax J = 1.. Am, wherein y jmax For monitoring the limit value of the measurement project data, each design parameter range of the small conduit is x il ≤x i ≤x ir I = 1.., n, where x il 、x ir Establishing a multi-target genetic algorithm model of the design parameters of the advanced small catheter by respectively setting the left boundary and the right boundary of the design parameter range as shown in the following;
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911042531.6A CN110909402B (en) | 2019-10-30 | 2019-10-30 | Advanced small catheter design method based on neural network technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911042531.6A CN110909402B (en) | 2019-10-30 | 2019-10-30 | Advanced small catheter design method based on neural network technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110909402A CN110909402A (en) | 2020-03-24 |
| CN110909402B true CN110909402B (en) | 2023-04-18 |
Family
ID=69814673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911042531.6A Active CN110909402B (en) | 2019-10-30 | 2019-10-30 | Advanced small catheter design method based on neural network technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909402B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104179514A (en) * | 2014-08-18 | 2014-12-03 | 同济大学 | Method for water inrush prediction and seepage control for underwater-tunnel broken surrounding rocks |
| 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 |
| CN105260575A (en) * | 2015-11-17 | 2016-01-20 | 中国矿业大学 | Roadway surrounding rock deformation predicting method based on neural network |
-
2019
- 2019-10-30 CN CN201911042531.6A patent/CN110909402B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN104179514A (en) * | 2014-08-18 | 2014-12-03 | 同济大学 | Method for water inrush prediction and seepage control for underwater-tunnel broken surrounding rocks |
| CN105260575A (en) * | 2015-11-17 | 2016-01-20 | 中国矿业大学 | Roadway surrounding rock deformation predicting method based on neural network |
Non-Patent Citations (2)
| Title |
|---|
| 周桥等.样条权函数神经网络算法在超前锚杆加固方式中的应用研究.金属矿山.2009,(第11期),全文. * |
| 王志斌等.长春地铁暗挖隧道围岩参数智能位移反分析.水利与建筑工程学报.2015,(第5期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110909402A (en) | 2020-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407493B (en) | A kind of rock burst grade evaluation method based on multidimensional Gauss cloud model | |
| US20230144184A1 (en) | Advanced geological prediction method and system based on perception while drilling | |
| CN109034641A (en) | Defect of pipeline prediction technique and device | |
| CN103810524A (en) | Method for predicting ground subsidence in underground metro construction process | |
| CN106198870B (en) | A kind of anchor rod body damage location identification method based on neural network | |
| CN106952003A (en) | High Ground Stress Areas beded rock mass underground rock cavern Failure type Forecasting Methodology | |
| Wang et al. | Risk Assessment of Water Inrush in Karst Tunnels Based on the Efficacy Coefficient Method. | |
| CN106326624A (en) | Method for predicating stratum fracture pressure | |
| CN103205972A (en) | Method for analyzing relationship between deformation of foundation pit and ground subsidence outside of foundation pit | |
| CN107016205A (en) | A kind of multi-model construction method of groundwater Numerical Simulation | |
| Wu et al. | A dynamic decision approach for risk analysis in complex projects | |
| CN115828374A (en) | Method and system for predicting non-uniform deformation of composite stratum tunnel in construction period | |
| CN115640996A (en) | Evaluation method for water inrush disaster of tunnel in water-rich complex stratum | |
| CN115293316A (en) | Prediction method for deep-buried thick coal seam water flowing fractured zone based on SSA-ELMAN | |
| CN112926267B (en) | TBM tunnel rock burst grade prediction method and system based on tunneling parameter inversion | |
| CN110909402B (en) | Advanced small catheter design method based on neural network technology | |
| CN104615908A (en) | Method for determining displacement release coefficient of surrounding rock by considering spatial effect | |
| CN116882023A (en) | Method for predicting transverse settlement of upper earth covering layer in underground excavation construction of subway tunnel | |
| CN104268785A (en) | Analysis method for deep well floor water inrush risk | |
| CN112257154B (en) | Transparent construction monitoring method and system for urban tunnel | |
| CN115130724A (en) | Dynamic adjustment method and system for urban underground water mining planning | |
| CN106021717A (en) | Neural network-based method for analyzing surface subsidence caused by metro excavation | |
| CN111663935A (en) | Method and system for evaluating shaft annulus air tightness | |
| CN117574781B (en) | Intelligent prediction method and system for security risk of surrounding rock of underground factory building of pumped storage power station | |
| CN117236429A (en) | Diversion tunnel surrounding rock deformation prediction method and system based on extreme random forest |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |