CN115759351A - Slurry shield tunneling comprehensive early warning method and system and storage medium - Google Patents
Slurry shield tunneling comprehensive early warning method and system and storage medium Download PDFInfo
- Publication number
- CN115759351A CN115759351A CN202211315527.4A CN202211315527A CN115759351A CN 115759351 A CN115759351 A CN 115759351A CN 202211315527 A CN202211315527 A CN 202211315527A CN 115759351 A CN115759351 A CN 115759351A
- Authority
- CN
- China
- Prior art keywords
- data
- shield
- geological
- early warning
- machine learning
- 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
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The invention discloses a comprehensive early warning method, a comprehensive early warning system and a storage medium for slurry shield tunneling.A geological exploration data of a shield construction area, an advanced remote geological detection data of a front geological condition and a shield operation parameter data in a shield tunneling process are collected at first, and data capable of reflecting the machine-rock interaction in the slurry shield tunneling process is extracted from the geological exploration data and the advanced remote geological detection data and the shield operation parameter data to serve as a machine learning database; decomposing the running parameter data of the shield machine into a trend component and a fluctuation component, and performing data noise reduction; then, establishing a mapping model between the trend component and the fluctuation component of the shield operation parameter data and geological data through a long-time memory neural network machine learning method, predicting the trend component and the fluctuation component in real time according to the mapping model, and adding the prediction results of the trend component and the fluctuation component to obtain a prediction result; and when the prediction result reaches the early warning condition or reaches the risk area determined by detection, sending out early warning. The method has high accuracy and high prediction precision.
Description
Technical Field
The invention relates to the technical field of slurry shield control, in particular to a slurry shield tunneling comprehensive early warning method, a slurry shield tunneling comprehensive early warning system and a storage medium.
Background
The slurry shield has the advantage of being capable of meeting various stratum requirements, and is widely applied to underground engineering construction such as river-crossing tunnels and the like. With the continuous development of scientific technology, the slurry shield gradually develops towards the direction of large diameter, long distance and high water pressure, and the fine, intelligent and unmanned shield control has become a trend. In the process of large shield tunneling construction, the tunnel can penetrate through sandstone, soil-rock composite strata, fault fracture zones, karst areas and other complex strata, and challenges are brought to shield safe tunneling. The shield tunneling real-time early warning is an important guarantee for shield safety construction, however, the existing slurry shield tunneling real-time early warning still has certain difficulty, and various collected data cannot be fully utilized. At present, the risk early warning in the slurry shield construction is judged according to the change trend of cutter torque, thrust and working bin liquid level in the construction process. However, signals acquired by the shield tunneling machine in real time contain a large amount of fluctuation components and noise, so that the constructors are difficult to identify abnormal change trends in time, and the identification and prediction accuracy of potential risks is reduced. If the air inlet danger of the shield machine cannot be early warned in time, the emergency can be quickly and effectively dealt with, and engineering accidents such as head falling, sinking and the like of the shield machine can be caused.
Disclosure of Invention
The invention aims to: aiming at the problems in the prior art, the invention provides a slurry shield tunneling comprehensive early warning method, a slurry shield tunneling comprehensive early warning system and a storage medium, wherein the slurry shield tunneling comprehensive early warning method has higher prediction accuracy and higher prediction precision.
The technical scheme is as follows: the slurry shield tunneling comprehensive early warning method comprises the following steps:
(1) Collecting geological exploration data of a shield construction area, advanced remote geological exploration data of front geological conditions and shield operation parameter data in a shield tunneling process;
(2) Extracting data capable of reflecting machine-rock interaction in the slurry shield tunneling process from geological exploration data, advanced remote geological exploration data and shield operation parameter data to serve as a machine learning database;
(3) Decomposing shield machine operation parameter data in a machine learning database into trend components and fluctuation components, and performing data noise reduction;
(4) Establishing a mapping model between a trend component and a fluctuation component of shield operation parameter data and geological data respectively by a long-time memory neural network machine learning method, wherein the geological data are geological exploration data and advanced remote geological exploration data in a machine learning database;
(5) Predicting trend components and fluctuation components of shield operation parameter data in real time according to the mapping model, and adding prediction results of the trend components and the fluctuation components to obtain a final prediction result;
(6) And when the prediction result reaches the early warning condition or reaches the risk area judged in the advanced remote geological detection data, sending out early warning.
Further, the advanced remote geological detection data is collected through TST.
Further, the trend component and the fluctuation component are obtained by the following method: and decomposing and analyzing the operation parameters of the shield machine by adopting a variational modal decomposition and trend-removing fluctuation analysis method to obtain a trend component and a fluctuation component.
Further, the geological data specifically includes: surrounding rock grade, each stratum thickness, tunnel buried depth, underground water level and transverse and longitudinal wave velocity.
Further, the shield machine operation parameter data in the machine learning database includes: the rotating speed of the cutter head, the advancing speed, the torque of the cutter head, the thrust of the cutter head and the liquid level of the bubble chamber.
Furthermore, in the long-time memory neural network machine learning process, 80% of data in the machine learning database is randomly selected as a training set, and the remaining 20% of data is a test set.
The slurry shield tunneling comprehensive early warning system comprises:
the data acquisition module is used for acquiring geological exploration data of a shield construction area and advanced remote geological exploration data of front geological conditions in the shield tunneling process so as to obtain shield operation parameter data;
the machine learning database comprises data which can reflect the machine-rock interaction in the slurry shield tunneling process and is extracted from geological exploration data, advanced remote geological detection data and shield operation parameter data;
the data processing module is used for decomposing the shield machine operation parameter data in the machine learning database into a trend component and a fluctuation component and carrying out data noise reduction;
the machine learning module is used for establishing a mapping model between a trend component and a fluctuation component of shield operation parameter data and geological data respectively through a long-time memory neural network machine learning method, wherein the geological data are geological exploration data and advanced remote geological detection data in a machine learning database;
the prediction module is used for predicting the trend component and the fluctuation component of the shield operation parameter data in real time according to the mapping model, and adding the prediction results of the trend component and the fluctuation component to obtain a final prediction result;
and the early warning module is used for sending out early warning when the prediction result of the prediction module reaches an early warning condition or reaches a risk area judged in the advanced remote geological detection data.
The storage medium of the present invention contains computer-executable instructions for performing the above-described method when executed by a computer processor.
Has the beneficial effects that: compared with the prior art, the invention has the remarkable advantages that: the method adopts a variational modal decomposition and trend-removing fluctuation analysis method to decompose the running parameter signals of the shield machine into trend components and fluctuation components and carry out data noise reduction; the method adopts a deep learning method to respectively establish a trend component prediction model and a fluctuation component prediction model of the shield machine operation parameters, and then adds the trend component prediction model and the fluctuation component prediction model to obtain a real-time prediction value of the shield machine operation parameters, thereby greatly improving the accuracy of prediction. The shield operation parameter deep learning model can predict shield operation parameter changes in a certain time in the future, identify abnormal change trends in time, realize real-time early warning and is high in prediction precision. The geological exploration data, the TST advanced detection data and the shield tunneling machine operation parameters are fully utilized, comprehensive early warning is carried out on shield tunneling safety risks through the actual measurement data and the machine learning prediction model, early warning precision is improved, and safe tunneling of the slurry shield is better guaranteed.
Drawings
FIG. 1 is a schematic flow chart of a slurry shield tunneling comprehensive early warning method provided by the invention;
fig. 2 is a block structure diagram of the slurry shield tunneling comprehensive early warning system provided by the invention.
Detailed Description
Example one
The embodiment provides a comprehensive early warning method for slurry shield tunneling, which comprises the following steps as shown in fig. 1:
(1) And collecting geological exploration data of a shield construction area, advanced remote geological detection data of front geological conditions and shield operation parameter data in the shield tunneling process.
The advanced remote geological detection data remotely detects the geological condition in front of shield tunneling through a TST advanced geological prediction technology, and the positions, forms and scales of faults and unfavorable geology of an influence zone, a joint fracture development zone, karst, underground water and the like are mastered.
(2) And extracting data capable of reflecting the machine-rock interaction in the slurry shield tunneling process from geological exploration data, advanced remote geological exploration data and shield operation parameter data to serve as a machine learning database.
The data which can reflect the machine-rock interaction in the slurry shield tunneling process and is extracted from geological exploration data and advanced remote geological detection data comprises the following steps: the method comprises the following steps of combining the data of surrounding rock grades, the thickness of each stratum, the buried depth of a tunnel, the underground water level and the transverse and longitudinal wave speeds into geological data, wherein the data extracted from shield operation parameter data and capable of reflecting the machine-rock interaction in the slurry shield tunneling process comprises the following steps: the rotating speed of the cutter head, the advancing speed, the torque of the cutter head, the thrust of the cutter head and the liquid level of the bubble chamber.
(3) And decomposing the shield machine operation parameter data in the machine learning database into a trend component and a fluctuation component, and performing data noise reduction.
Specifically, a variation modal decomposition and trend-removing fluctuation analysis method is adopted to decompose the running parameter signals of the shield tunneling machine into trend components and fluctuation components.
(4) And establishing a mapping model between the trend component and the fluctuation component of the shield operation parameter data and the geological data respectively by a long-time memory neural network machine learning method.
In the long-time memory neural network machine learning process, 80% of data in a machine learning database is randomly selected as a training set, and the rest 20% of data is taken as a test set. In order to reduce the risk of overfitting in the training process and evaluate the training effect of the model in real time, 80% of data are randomly extracted from the training set for training in the process of each iterative training, and the rest 20% of data are used as a verification set. In the model training process, the Root Mean Square Error (RMSE) is used as an evaluation index of a loss function, and in the test process, the average absolute error (MAE), the Root Mean Square Error (RMSE) and the R2 fraction are used for comprehensively evaluating the model.
(5) And predicting the trend component and the fluctuation component of the shield operation parameter data in real time according to the mapping model, and adding the prediction results of the trend component and the fluctuation component to obtain a final prediction result.
(6) And when the prediction result reaches the early warning condition or reaches the risk area judged in the advanced remote geological detection data, sending out early warning.
When the mutation rate of the shield operation parameters reaches a preset safety threshold value, early warning is triggered, or when a risk area judged in advanced remote geological detection data is reached, early warning is also triggered. At the moment, the shield tunneling machine is stopped from advancing, the states of the cutterhead and the tunnel face are observed through the telescopic camera in the excavation cabin, and the tunneling risk is confirmed.
Example two
The embodiment provides a comprehensive early warning system for slurry shield tunneling, which can be implemented in a software and/or hardware manner, and can be configured in a terminal device, as shown in fig. 2, and includes:
the data acquisition module is used for acquiring geological exploration data of a shield construction area, advanced remote geological detection data of a front geological condition and shield operation parameter data in the shield tunneling process;
the machine learning database comprises data which can reflect the machine-rock interaction in the slurry shield tunneling process and is extracted from geological exploration data, advanced remote geological detection data and shield operation parameter data;
the data processing module is used for decomposing the shield machine operation parameter data in the machine learning database into a trend component and a fluctuation component and carrying out data noise reduction;
the machine learning module is used for establishing a mapping model between a trend component and a fluctuation component of shield operation parameter data and geological data respectively through a long-time memory neural network machine learning method, wherein the geological data are geological exploration data and advanced remote geological exploration data in a machine learning database;
the prediction module is used for predicting the trend component and the fluctuation component of the shield operation parameter data in real time according to the mapping model, and adding the prediction results of the trend component and the fluctuation component to obtain a final prediction result;
and the early warning module is used for sending out early warning when the prediction result of the prediction module reaches an early warning condition or reaches a risk area judged in the advanced remote geological detection data.
The system of the embodiment corresponds to the method of the embodiment one by one, can be used for executing the method, and has corresponding functions and beneficial effects of the executing method.
It should be noted that, the included units and modules are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for the convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
EXAMPLE III
The present embodiments provide a storage medium containing computer-executable instructions which, when executed by a computer processor, are operable to perform the above-described pre-warning method.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (8)
1. A comprehensive early warning method for slurry shield tunneling is characterized by comprising the following steps:
(1) Collecting geological exploration data of a shield construction area, advanced remote geological detection data of front geological conditions and shield operation parameter data in a shield tunneling process;
(2) Extracting data capable of reflecting the machine-rock interaction in the slurry shield tunneling process from geological exploration data, advanced remote geological exploration data and shield operation parameter data to serve as a machine learning database;
(3) Decomposing shield machine operation parameter data in a machine learning database into trend components and fluctuation components, and performing data noise reduction;
(4) Establishing a mapping model between a trend component and a fluctuation component of shield operation parameter data and geological data respectively by a long-time memory neural network machine learning method, wherein the geological data are geological exploration data and advanced remote geological exploration data in a machine learning database;
(5) Predicting trend components and fluctuation components of shield operation parameter data in real time according to the mapping model, and adding prediction results of the trend components and the fluctuation components to obtain a final prediction result;
(6) And when the prediction result reaches the early warning condition or reaches the risk area determined in the advanced remote geological detection data, sending out early warning.
2. The slurry shield tunneling comprehensive early warning method according to claim 1, characterized in that: and the advanced remote geological detection data are acquired through TST.
3. The slurry shield tunneling comprehensive early warning method according to claim 1, characterized in that: the trend component and the fluctuation component are obtained by the following method: and decomposing and analyzing the operation parameters of the shield machine by adopting a variational modal decomposition and trend-removing fluctuation analysis method to obtain a trend component and a fluctuation component.
4. The slurry shield tunneling comprehensive early warning method according to claim 1, characterized in that: the geological data are specifically: surrounding rock grade, each stratum thickness, tunnel buried depth, underground water level and transverse and longitudinal wave velocity.
5. The slurry shield tunneling comprehensive early warning method according to claim 1, characterized in that: the shield machine operation parameter data in the machine learning database comprises: the rotating speed of the cutter head, the advancing speed, the torque of the cutter head, the thrust of the cutter head and the liquid level of the bubble chamber.
6. The slurry shield tunneling comprehensive early warning method according to claim 1, characterized in that: in the long-time memory neural network machine learning process, 80% of data in a machine learning database is randomly selected as a training set, and the rest 20% of data is taken as a test set.
7. The utility model provides a early warning system is synthesized in shield tunnelling of muddy water which characterized in that includes:
the data acquisition module is used for acquiring geological exploration data of a shield construction area, advanced remote geological detection data of front geological conditions and shield operation parameter data in the shield tunneling process;
the machine learning database comprises data which can reflect the machine-rock interaction in the slurry shield tunneling process and is extracted from geological exploration data, advanced remote geological detection data and shield operation parameter data;
the data processing module is used for decomposing the shield machine operation parameter data in the machine learning database into a trend component and a fluctuation component and carrying out data noise reduction;
the machine learning module is used for establishing a mapping model between a trend component and a fluctuation component of shield operation parameter data and geological data respectively through a long-time memory neural network machine learning method, wherein the geological data are geological exploration data and advanced remote geological detection data in a machine learning database;
the prediction module is used for predicting the trend component and the fluctuation component of the shield operation parameter data in real time according to the mapping model, and adding the prediction results of the trend component and the fluctuation component to obtain a final prediction result;
and the early warning module is used for sending out early warning when the prediction result of the prediction module reaches an early warning condition or reaches a risk area judged in the advanced remote geological detection data.
8. A storage medium containing computer-executable instructions for performing the method of any one of claims 1-6 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211315527.4A CN115759351A (en) | 2022-10-26 | 2022-10-26 | Slurry shield tunneling comprehensive early warning method and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211315527.4A CN115759351A (en) | 2022-10-26 | 2022-10-26 | Slurry shield tunneling comprehensive early warning method and system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115759351A true CN115759351A (en) | 2023-03-07 |
Family
ID=85353224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211315527.4A Pending CN115759351A (en) | 2022-10-26 | 2022-10-26 | Slurry shield tunneling comprehensive early warning method and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115759351A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117646657A (en) * | 2024-01-30 | 2024-03-05 | 中电建铁路建设投资集团有限公司 | Monitoring and early warning system for slurry shield downward penetrating technology |
-
2022
- 2022-10-26 CN CN202211315527.4A patent/CN115759351A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117646657A (en) * | 2024-01-30 | 2024-03-05 | 中电建铁路建设投资集团有限公司 | Monitoring and early warning system for slurry shield downward penetrating technology |
| CN117646657B (en) * | 2024-01-30 | 2024-04-16 | 中电建铁路建设投资集团有限公司 | Monitoring and early warning system for slurry shield downward penetrating technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108510112B (en) | Mine disaster prediction and early warning method combining field monitoring and numerical simulation | |
| WO2019042483A2 (en) | Tbm boring rock state real-time sensing system and method | |
| CN103670516B (en) | A kind of recognition methods of rock burst hazard micro seismic monitoring early warning key point | |
| CN103306722B (en) | Micro-seismic multi-dimensional information comprehensive region detection and evaluation method for impact danger region | |
| Guo et al. | Advance prediction of collapse for TBM tunneling using deep learning method | |
| CN102926810B (en) | Forecasting method of coal and gas outburst | |
| CN103615236A (en) | Method for monitoring formation pressure in real time through remote logging information | |
| CN108764032B (en) | Intelligent monitoring method and device for coal mine water exploration and drainage, computer equipment and storage medium | |
| CN109356602A (en) | A kind of judgment method and system of shield machine driving state | |
| CN115239108B (en) | Weak broken surrounding rock sensing method based on TBM real-time broken rock data | |
| CN115759351A (en) | Slurry shield tunneling comprehensive early warning method and system and storage medium | |
| CN115358494A (en) | Danger early warning method for subway shield underpass construction | |
| CN115688251A (en) | Earthquake multi-occurrence-zone tunnel risk decision method and system based on deep learning | |
| CN113818929A (en) | Mine underground water dynamic monitoring system, control method and application | |
| CN112580165A (en) | Prediction method and system for open type TBM passing through unfavorable geological cutter head jamming machine | |
| CN113326661B (en) | RS-XGboost-based tunnel advanced drilling quantitative interpretation method and device | |
| Li et al. | Cross-project utilisation of tunnel boring machine (TBM) construction data: A case study using big data from Yin-Song diversion project in China | |
| CN116777085B (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| CN117593853A (en) | Geological disaster auxiliary monitoring system and method based on change of through-the-earth communication signals | |
| CN117590465A (en) | Advanced geological detection method and device carried on ultra-large diameter slurry shield | |
| LIANG et al. | Stratum identification based on multiple drilling parameters and probability classification | |
| Li et al. | Noise reduction method of microseismic signal of water inrush in tunnel based on variational mode method | |
| CN115898442A (en) | Method and system for determining grade of surrounding rock in tunneling based on shield construction parameters | |
| Zhu et al. | Research on feature vector construction and classification recognition of typical mine microseismic waveforms | |
| CN115950947A (en) | Real-time geological parameter prediction method of TBM tunnel based on vibration signal |
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 |