CN113408190B - Surrounding rock deformation prediction method for highway tunnel construction period based on Bayes-LSTM model - Google Patents
Surrounding rock deformation prediction method for highway tunnel construction period based on Bayes-LSTM model Download PDFInfo
- Publication number
- CN113408190B CN113408190B CN202110593891.6A CN202110593891A CN113408190B CN 113408190 B CN113408190 B CN 113408190B CN 202110593891 A CN202110593891 A CN 202110593891A CN 113408190 B CN113408190 B CN 113408190B
- Authority
- CN
- China
- Prior art keywords
- data
- lstm
- model
- bayes
- surrounding rock
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for predicting surrounding rock deformation in a highway tunnel construction period based on a Bayes-LSTM model, which comprises the following steps: acquiring vault settlement and peripheral convergence data; performing mechanism knowledge analysis; preprocessing data; dividing the data set; constructing an LSTM vault settlement and peripheral convergence prediction model by using a Keras frame built in Python; setting up a parameter optimization model by utilizing a Hyperopt Bayesian parameter adjustment module built in Python, and setting Bayes optimization parameters and a search space; optimizing an LSTM model; loading a trained LSTM vault settlement and peripheral convergence prediction model, predicting test set data, and outputting a predicted value; and (5) performing inverse normalization on the predicted data by using an invertase_transform function built in Python. The method has the advantages of high analysis speed, high prediction precision and high data processing efficiency on surrounding rock deformation monitoring data in the construction period of the highway tunnel.
Description
Technical Field
The invention belongs to the technical field of tunnel engineering, and particularly relates to a surrounding rock deformation prediction method in a highway tunnel construction period based on a Bayes-LSTM model.
Background
In recent years, along with the development of traffic construction, the number of highway tunnels is also rapidly increased, the balance state of stress strain of a rock-soil body is destroyed in the tunnel excavation process, the problems of stress redistribution, surrounding rock deformation and the like are also caused, the surrounding rock large deformation is one of common construction disasters in tunnel construction, the supporting structure is destroyed, the section limit is invaded, and the normal construction of the tunnel is greatly influenced. However, the characteristics of discontinuity, non-uniformity and the like of the surrounding rock of the tunnel make theoretical calculation of the deformation of the surrounding rock difficult, so that the arch crown settlement and the peripheral convergence can be accurately predicted in construction, and the method has very important significance for analysis of the deformation of the surrounding rock and the stability of the surrounding rock. Through investigation of a large number of research results of surrounding rock deformation prediction of tunnels by students at home and abroad, a common prediction method is statistical regression and numerical simulation, a new solution is provided for solving the problem of tunnel surrounding rock deformation along with development of artificial intelligence technology, and the students put forward a model which uses a support vector machine as a theoretical basis and utilizes a particle swarm algorithm and chaos theory to optimize model parameters, a chaos optimization PSO-SVM model is constructed to predict tunnel surrounding rock deformation, and the students adopt gray theory analysis and a model of a time sequence analysis and BP neural network.
Although domestic and foreign students have conducted many researches on tunnel surrounding rock deformation prediction methods, the prediction models have certain limitations, for example, BP neural networks are greatly affected by initial values, and meanwhile, problems such as network gradient disappearance and gradient explosion are easy to occur.
Disclosure of Invention
The invention aims to provide a surrounding rock deformation prediction method based on a Bayes-LSTM model in the construction period of a highway tunnel, which can improve the accuracy of surrounding rock deformation prediction and reduce the training time of samples, thereby ensuring the construction safety and the construction progress of the highway tunnel.
The technical scheme adopted by the invention is as follows:
the method for predicting surrounding rock deformation in the construction period of the highway tunnel based on the Bayes-LSTM model is characterized by comprising the following steps of:
the method comprises the following steps:
a. vault subsidence and peripheral convergence data were acquired: the data are continuous sedimentation data actually measured at a certain observation point in a period of time;
b. mechanism knowledge analysis: drawing a curve graph of vault settlement and peripheral convergence change, and performing preliminary analysis and judgment on a curve change rule and a tunnel surrounding rock deformation rule to eliminate the situation that actual measurement data in a construction period is obviously abnormal due to special bad geological reasons;
c. preprocessing data: normalizing the data by using a Python built-in function MinMaxScale, and converting the time sequence data into supervised data by using a series_to_supervised function;
d. dividing the data set: the method comprises the steps that a train_test_split function is utilized, the first 67% of data is used as a training set, the last 33% of data is used as a test sample, and 20% of the training set is used as a verification set to verify the generalization capability of a model;
e. constructing an LSTM vault settlement and peripheral convergence prediction model by using a Keras frame built in Python;
f. setting up a parameter optimization model by utilizing a Hyperopt Bayesian parameter adjustment module built in Python, and setting Bayes optimization parameters and a search space;
g. optimizing the LSTM model: setting initial parameters, training a vault subsidence and peripheral convergence prediction model of the LSTM, using MSE as a loss function, adopting a parameter optimization model in f to repeatedly train the LSTM, judging a model fitting effect according to the loss of a training set verification set, and selecting a group of super-parameter combinations with minimum loss to construct the LSTM model;
h. loading a trained LSTM vault settlement and peripheral convergence prediction model, predicting test set data, and outputting a predicted value y;
i. and (3) performing inverse normalization on the obtained prediction data in h by using an invertase_transform function built in Python.
In the step f, bayes optimization parameters comprise the size of a hidden layer in an LSTM unit, the selection of an optimizer, the learning rate and the iteration times; the search space of the size of the hidden layer in the LSTM unit is 2-64, the selection of the optimizer is 'adam', 'rmsporop', 'adamax', the search space of the learning rate is 0.001-0.01, and the search space of the iteration times is 100-300.
In step g, training the dome subsidence and peripheral convergence prediction model of the LSTM includes:
construction of forgetting gate (forget gate) f t ：f t ＝σ(W f h t-1 +W f x t +b f )；
Building an input gate (i) t ：i t ＝σ(W i h t-1 +W i x t +b i )；
New unit information C at present moment t ：C t ＝f t ×C t-1 +i t ×tanh(W c h t-1 +W c x t +b c )；
Output gate (output gate) o is calculated t ：o t ＝σ(W o h t-1 +W o x t +b o )；
Calculate the final output h t ：h t ＝o t ×tanh(C t )；
Wherein W and b respectively represent a weight matrix and a bias parameter, sigma is a sigmoid function, i t Determining the required information to update into the cellular state, C t For new unit information at time t, o t An output section for determining the cell state, h t Indicated at time x t The output of the corresponding cell.
In step g, the preferred mean square error MSE is the loss function,wherein y is i As a result of the actual measurement of the value,is a predicted value.
In the step g, when the gate output is 0, all information is forbidden to pass through; when the gate output is 1, this indicates that all information is allowed to pass.
In the step g, the LSTM surrounding rock deformation prediction model is a double-layer LSTM model, and the Bayes parameter optimization method is adopted for optimizing, so that the optimal parameters are found.
The invention has the following advantages:
1. the invention utilizes Bayes optimized LSTM model, and the Bayes optimized parameters comprise: the size (units) of the hidden layer in the LSTM unit, the selection of an optimizer (optimizer), the learning rate (learn_rate) and the iteration number (epochs); the search space of the size of the hidden layer in the LSTM unit is 2-64, the selection of the optimizer is 'adam', 'rmsporop', 'adamax', the search space of the learning rate is 0.001-0.01, and the search space of the iteration times is 100-300. And the optimal parameters are trained according to different surrounding rock change curves, so that the accuracy of prediction of surrounding rock deformation is improved.
2. The LSTM network based on the invention is derived from RNN, and is an improved cyclic neural network (Recurrent Neural Networks, RNN), which can solve the problem that RNN cannot handle long-distance dependence and can avoid gradient explosion and gradient disappearance in RNN. All RNNs have a chained form of repeating neural network modules. In a standard RNN, this repeated module has only a very simple structure, such as a tanh layer. LSTM also has this chain structure, but its repeating unit differs from that in a standard RNN network by only one network layer, and by four network layers inside. Meanwhile, LSTM has three "gates," respectively "forget gate", "input gate", "output gate". LSTM relies on a number of "gate" structures to allow information to selectively affect the state of the recurrent neural network at each instant, and can selectively determine which information to allow. Therefore, LSTM reduces the time for model training and further improves the accuracy of model prediction, so that the construction safety and construction progress of the highway tunnel are ensured.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a graph of an example data dome sedimentation change law in the present invention;
FIG. 3 is a graph of an example data perimeter convergence change in accordance with the present invention.
Detailed Description
The present invention will be described in detail with reference to the following embodiments.
The invention relates to a method for predicting surrounding rock deformation in a highway tunnel construction period based on a Bayes-LSTM model, which comprises the following steps:
a. vault subsidence and peripheral convergence data were acquired: the data are continuous sedimentation data actually measured at a certain observation point in a period of time;
b. mechanism knowledge analysis: drawing a curve graph of vault settlement and peripheral convergence change, and performing preliminary analysis and judgment on a curve change rule and a tunnel surrounding rock deformation rule to eliminate the situation that actual measurement data in a construction period is obviously abnormal due to special bad geological reasons;
c. preprocessing data: normalizing the data by using a Python built-in function MinMaxScale, and converting the time sequence data into supervised data by using a series_to_supervised function;
d. dividing the data set: the method comprises the steps that a train_test_split function is utilized, the first 67% of data is used as a training set, the last 33% of data is used as a test sample, and 20% of the training set is used as a verification set to verify the generalization capability of a model;
e. constructing an LSTM vault settlement and peripheral convergence prediction model by using a Keras frame built in Python;
f. setting up a parameter optimization model by utilizing a Hyperopt Bayesian parameter adjustment module built in Python, and setting Bayes optimization parameters and a search space;
g. optimizing the LSTM model: setting initial parameters, training a vault subsidence and peripheral convergence prediction model of the LSTM, using MSE as a loss function, adopting a parameter optimization model in f to repeatedly train the LSTM, judging a model fitting effect according to the loss of a training set verification set, and selecting a group of super-parameter combinations with minimum loss to construct the LSTM model;
h. loading a trained LSTM vault settlement and peripheral convergence prediction model, predicting test set data, and outputting a predicted value y;
i. and (3) performing inverse normalization on the obtained prediction data in h by using an invertase_transform function built in Python.
In the step f, bayes optimization parameters comprise the size of a hidden layer in an LSTM unit, the selection of an optimizer, the learning rate and the iteration times; the search space of the size of the hidden layer in the LSTM unit is 2-64, the selection of the optimizer is 'adam', 'rmsporop', 'adamax', the search space of the learning rate is 0.001-0.01, and the search space of the iteration times is 100-300.
In step g, training the dome subsidence and peripheral convergence prediction model of the LSTM includes:
construction of forgetting gate (forget gate) f t ：f t ＝σ(W f h t-1 +W f x t +b f )；
Building an input gate (i) t ：i t ＝σ(W i h t-1 +W i x t +b i )；
New unit information C at present moment t ：C t ＝f t ×C t-1 +i t ×tanh(W c h t-1 +W c x t +b c )；
Output gate (output gate) o is calculated t ：o t ＝σ(W o h t-1 +W o x t +b o )；
Calculate the final output h t ：h t ＝o t ×tanh(C t )；
Wherein W and b respectively represent a weight matrix and a bias parameter, sigma is a sigmoid function, i t Determining the required information to update into the cellular state, C t New sheet for time tMeta information o t An output section for determining the cell state, h t Indicated at time x t The output of the corresponding cell.
In step g, the preferred mean square error MSE is the loss function,wherein y is i As a result of the actual measurement of the value,is a predicted value.
In the step g, when the gate output is 0, all information is forbidden to pass through; when the gate output is 1, this indicates that all information is allowed to pass.
In the step g, the LSTM surrounding rock deformation prediction model is a double-layer LSTM model, and the Bayes parameter optimization method is adopted for optimizing, so that the optimal parameters are found.
Examples:
as shown in fig. 1, the specific steps of the present invention are:
a. obtaining vault settlement and peripheral convergence data in the construction period of a highway tunnel: the data are continuous sedimentation data actually measured at a certain observation point in a period of time;
table 1 vault settlement gauge example
Table 2 peripheral convergence measured data example
b. Mechanism knowledge analysis: drawing a curve graph of vault settlement and peripheral convergence change, and performing preliminary analysis and judgment on a curve change rule and a tunnel surrounding rock deformation rule to eliminate the situation that actual measurement data in a construction period are obviously abnormal due to reasons such as special bad geology;
c. preprocessing data: normalizing the data by using a Python built-in function MinMaxScale, converting the time sequence data into supervised data by using a series_to_supervised function, and predicting third day data by using accumulated sedimentation data and monitoring days of the first two days as characteristic factors because of discontinuous monitoring days, wherein C1 is taken as an example, as shown in table 3;
table 3 C1 supervised data example
d. Dividing the data set: the method comprises the steps that a train_test_split function is utilized, the first 67% of data is used as a training set, the last 33% of data is used as a test sample, and 20% of the training set is used as a verification set to verify the generalization capability of a model;
e. constructing an LSTM vault settlement and peripheral convergence prediction model by using a Keras framework built in Python;
f. setting up a parameter optimization model by utilizing a Hyperopt Bayesian parameter adjustment module built in Python, and setting Bayes optimization parameters and a search space;
g. optimizing the LSTM model: setting initial parameters, training a vault subsidence and peripheral convergence prediction model of the LSTM, using MSE as a loss function, adopting a parameter optimization model in f to repeatedly train the LSTM, judging a model fitting effect according to the loss of a training set verification set, and selecting a group of super-parameter combinations with minimum loss;
TABLE 4 parameter space for dome settlement Bayes optimization and optimal parameter examples thereof
Table 5 peripheral convergence optimal parameters example
h. Loading a trained LSTM vault settlement and peripheral convergence prediction model, predicting test set data, and outputting a predicted value y;
i. and (3) performing inverse normalization on the obtained prediction data in h by using an invertase_transform function built in Python.
The content of the invention is not limited to the examples listed, and any equivalent transformation to the technical solution of the invention that a person skilled in the art can take on by reading the description of the invention is covered by the claims of the invention.
Claims (5)
1. The method for predicting surrounding rock deformation in the construction period of the highway tunnel based on the Bayes-LSTM model is characterized by comprising the following steps of:
the method comprises the following steps:
a. vault subsidence and peripheral convergence data were acquired: the data are continuous sedimentation data actually measured at a certain observation point in a period of time;
b. mechanism knowledge analysis: drawing a curve graph of vault settlement and peripheral convergence change, and performing preliminary analysis and judgment on a curve change rule and a tunnel surrounding rock deformation rule to eliminate the situation that actual measurement data in a construction period is obviously abnormal due to special bad geological reasons;
c. preprocessing data: normalizing the data by using a Python built-in function MinMaxScale, and converting the time sequence data into supervised data by using a series_to_supervised function;
d. dividing the data set: the method comprises the steps that a train_test_split function is utilized, the first 67% of data is used as a training set, the last 33% of data is used as a test sample, and 20% of the training set is used as a verification set to verify the generalization capability of a model;
e. constructing an LSTM vault settlement and peripheral convergence prediction model by using a Keras frame built in Python;
f. setting up a parameter optimization model by utilizing a Hyperopt Bayesian parameter adjustment module built in Python, and setting Bayes optimization parameters and a search space;
g. optimizing the LSTM model: setting initial parameters, training a vault subsidence and peripheral convergence prediction model of the LSTM, using MSE as a loss function, adopting a parameter optimization model in f to repeatedly train the LSTM, judging a model fitting effect according to the loss of a training set verification set, and selecting a group of super-parameter combinations with minimum loss to construct the LSTM model;
h. loading a trained LSTM vault settlement and peripheral convergence prediction model, predicting test set data, and outputting a predicted value y;
i. inverse normalization is carried out on the obtained prediction data in the h by utilizing an invertase_transform function built in the Python;
in step g, training the dome subsidence and peripheral convergence prediction model of the LSTM includes:
construction of forgetting gate (foretgate) f t ：f t ＝σ(W f h t-1 +W f x t +b f )；
Building an input gate (input gate) i t ：i t ＝σ(W i h t-1 +W i x t +b i )；
New unit information C at present moment t ：C t ＝f t ×C t-1 +i t ×tanh(W c h t-1 +W c x t +b c )；
Calculate output gate (output gate) o t ：o t ＝σ(W o h t-1 +W o x t +b o )；
Calculate the final output h t ：h t ＝o t ×tanh(C t )；
Wherein W and b respectively represent a weight matrix and a bias parameter, sigma is a sigmoid function, i t Determining the required information to update into the cellular state, C t For new unit information at time t, o t An output section for determining the cell state, h t Indicated at time x t The output of the corresponding cell.
2. The method for predicting surrounding rock deformation in construction period of highway tunnel based on Bayes-LSTM model as claimed in claim 1, wherein the method comprises the following steps:
in the step f, bayes optimization parameters comprise the size of a hidden layer in an LSTM unit, the selection of an optimizer, the learning rate and the iteration times; the search space of the size of the hidden layer in the LSTM unit is 2-64, the selection of the optimizer is 'adam', 'rmsporop', 'adamax', the search space of the learning rate is 0.001-0.01, and the search space of the iteration times is 100-300.
3. The method for predicting surrounding rock deformation in construction period of highway tunnel based on Bayes-LSTM model as claimed in claim 2, wherein the method comprises the following steps:
in step g, the preferred mean square error MSE is the loss function,wherein y is i For actual measurement, ->Is a predicted value.
4. The method for predicting surrounding rock deformation in construction period of highway tunnel based on Bayes-LSTM model as claimed in claim 3, wherein the method comprises the following steps:
in the step g, when the gate output is 0, all information is forbidden to pass through; when the gate output is 1, this indicates that all information is allowed to pass.
5. The method for predicting surrounding rock deformation in construction period of highway tunnel based on Bayes-LSTM model as claimed in claim 4, wherein the method comprises the following steps:
in the step g, the LSTM surrounding rock deformation prediction model is a double-layer LSTM model, and the Bayes parameter optimization method is adopted for optimizing, so that the optimal parameters are found.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593891.6A CN113408190B (en) | 2021-05-28 | 2021-05-28 | Surrounding rock deformation prediction method for highway tunnel construction period based on Bayes-LSTM model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593891.6A CN113408190B (en) | 2021-05-28 | 2021-05-28 | Surrounding rock deformation prediction method for highway tunnel construction period based on Bayes-LSTM model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113408190A CN113408190A (en) | 2021-09-17 |
| CN113408190B true CN113408190B (en) | 2023-09-08 |
Family
ID=77675094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110593891.6A Active CN113408190B (en) | 2021-05-28 | 2021-05-28 | Surrounding rock deformation prediction method for highway tunnel construction period based on Bayes-LSTM model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408190B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115929406B (en) * | 2022-12-07 | 2023-08-18 | 河海大学 | Surrounding rock stability prediction method, system and storage medium based on neural network |
| CN117494483B (en) * | 2024-01-02 | 2024-03-19 | 中铁上海工程局集团第七工程有限公司 | Numerical optimization method for deformation data of double-hole tunnel section |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105180888A (en) * | 2015-10-23 | 2015-12-23 | 中铁二十局集团有限公司 | Method for determining deformation allowance of high-ground-stress soft surrounding rock tunnel in excavation |
| CN107341328A (en) * | 2017-09-05 | 2017-11-10 | 中交第公路勘察设计研究院有限公司 | Based on the Ground Settlement method for improving Verhulst curves |
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
| CN110647980A (en) * | 2019-09-18 | 2020-01-03 | 成都理工大学 | Time sequence prediction method based on GRU neural network |
| CN111181773A (en) * | 2019-12-13 | 2020-05-19 | 西安交通大学 | Delay prediction method for multi-component application of heterogeneous border cloud collaborative intelligent system |
| CN111460737A (en) * | 2020-04-09 | 2020-07-28 | 昆山阳翎机器人科技有限公司 | Intelligent settlement prediction method and system for slurry air pressure balance shield |
| CN111475948A (en) * | 2020-04-07 | 2020-07-31 | 青岛理工大学 | Novel prediction method for settlement during subway tunnel construction based on L STM network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11074495B2 (en) * | 2013-02-28 | 2021-07-27 | Z Advanced Computing, Inc. (Zac) | System and method for extremely efficient image and pattern recognition and artificial intelligence platform |
-
2021
- 2021-05-28 CN CN202110593891.6A patent/CN113408190B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105180888A (en) * | 2015-10-23 | 2015-12-23 | 中铁二十局集团有限公司 | Method for determining deformation allowance of high-ground-stress soft surrounding rock tunnel in excavation |
| CN107341328A (en) * | 2017-09-05 | 2017-11-10 | 中交第公路勘察设计研究院有限公司 | Based on the Ground Settlement method for improving Verhulst curves |
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
| CN110647980A (en) * | 2019-09-18 | 2020-01-03 | 成都理工大学 | Time sequence prediction method based on GRU neural network |
| CN111181773A (en) * | 2019-12-13 | 2020-05-19 | 西安交通大学 | Delay prediction method for multi-component application of heterogeneous border cloud collaborative intelligent system |
| CN111475948A (en) * | 2020-04-07 | 2020-07-31 | 青岛理工大学 | Novel prediction method for settlement during subway tunnel construction based on L STM network |
| CN111460737A (en) * | 2020-04-09 | 2020-07-28 | 昆山阳翎机器人科技有限公司 | Intelligent settlement prediction method and system for slurry air pressure balance shield |
Non-Patent Citations (1)
| Title |
|---|
| 山岭隧洞已开挖段围岩体大形变监测预报案例分析探究;生显伟;《交通节能与环保》;第16卷(第3期);第128-131页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113408190A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492822B (en) | Air pollutant concentration time-space domain correlation prediction method | |
| CN111292525B (en) | Traffic flow prediction method based on neural network | |
| CN109063247B (en) | Landslide disaster forecasting method based on deep belief network | |
| CN113408190B (en) | Surrounding rock deformation prediction method for highway tunnel construction period based on Bayes-LSTM model | |
| CN113723010B (en) | Bridge damage early warning method based on LSTM temperature-displacement correlation model | |
| Wang et al. | Application of artificial neural network in tunnel engineering: a systematic review | |
| Feng et al. | Modeling non-linear displacement time series of geo-materials using evolutionary support vector machines | |
| CN110083125B (en) | Machine tool thermal error modeling method based on deep learning | |
| CN113610945B (en) | Ground stress curve prediction method based on hybrid neural network | |
| CN113807031A (en) | Foundation pit disaster prediction early warning method based on LSTM and depth residual error neural network | |
| CN113378939B (en) | Structure digital twin modeling and parameter identification method based on physical driving neural network | |
| CN111475948A (en) | Novel prediction method for settlement during subway tunnel construction based on L STM network | |
| CN113792372A (en) | Ground continuous wall deformation dynamic prediction method based on CV-LSTM combined model | |
| CN112307536B (en) | Dam seepage parameter inversion method | |
| CN116451556A (en) | Construction method of concrete dam deformation observed quantity statistical model | |
| CN114358434A (en) | Drilling machine drilling speed prediction method based on LSTM recurrent neural network model | |
| CN115130375A (en) | Rock burst intensity prediction method | |
| CN114862035B (en) | Combined bay water temperature prediction method based on transfer learning | |
| CN114548482A (en) | Creep type landslide kinetic energy change rate face-slip early warning method | |
| CN115545272A (en) | Long-term and short-term intelligent prediction and early warning method for microseismic frequency and energy of rock burst mine | |
| CN115983465A (en) | Rock burst time sequence prediction model construction method based on small sample learning | |
| CN115221793A (en) | Tunnel surrounding rock deformation prediction method and device | |
| CN113156492B (en) | Real-time intelligent early warning method applied to TBM tunnel rockburst disasters | |
| CN112836789A (en) | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm | |
| Hoan et al. | Novel time series bagging based hybrid models for predicting historical water levels in the Mekong delta region, Vietnam |
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 |