CN117590465A - Advanced geological detection method and device carried on ultra-large diameter slurry shield - Google Patents
Advanced geological detection method and device carried on ultra-large diameter slurry shield Download PDFInfo
- Publication number
- CN117590465A CN117590465A CN202311621154.8A CN202311621154A CN117590465A CN 117590465 A CN117590465 A CN 117590465A CN 202311621154 A CN202311621154 A CN 202311621154A CN 117590465 A CN117590465 A CN 117590465A
- Authority
- CN
- China
- Prior art keywords
- signal
- denoising
- geological
- advanced
- seismic wave
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 109
- 239000002002 slurry Substances 0.000 title claims abstract description 59
- 238000012545 processing Methods 0.000 claims description 54
- 238000000034 method Methods 0.000 claims description 52
- 238000005457 optimization Methods 0.000 claims description 34
- 238000009412 basement excavation Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 20
- 238000003062 neural network model Methods 0.000 claims description 11
- 230000002194 synthesizing effect Effects 0.000 claims description 11
- 125000004122 cyclic group Chemical group 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 9
- 241000282461 Canis lupus Species 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 5
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 230000007787 long-term memory Effects 0.000 claims 1
- 230000006403 short-term memory Effects 0.000 claims 1
- 238000010276 construction Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006698 induction Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009172 bursting Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/282—Application of seismic models, synthetic seismograms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/30—Analysis
- G01V1/306—Analysis for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/36—Effecting static or dynamic corrections on records, e.g. correcting spread; Correlating seismic signals; Eliminating effects of unwanted energy
Abstract
The invention provides an advanced geological detection method and device carried on an ultra-large diameter slurry shield, wherein the geological detection method comprises the following steps: and acquiring a target seismic wave signal fed back in front of a tunnel face by using an advanced geological prediction system mounted on the ultra-large diameter slurry shield machine, performing primary denoising treatment on the target seismic wave signal to obtain a primary denoising signal, performing secondary denoising treatment on the primary denoising signal to obtain a secondary denoising signal, and identifying the secondary denoising signal through a bad geological body identification model to obtain a geological type identification result corresponding to the secondary denoising signal. The invention provides an advanced geological detection method carried on an oversized-diameter slurry shield, which can achieve the technical effect of improving the accuracy of poor geological detection.
Description
Technical Field
The invention belongs to the technical field of geological detection, and particularly relates to an advanced geological detection method and device carried on an ultra-large-diameter slurry shield.
Background
The ultra-large diameter slurry shield is used as an important underground tunnel construction technology and is widely applied to the fields of urban subways, traffic infrastructures, hydraulic engineering and the like. In actual engineering, geological conditions faced in the tunnel construction process are various and complex, and geological disasters such as stratum change, faults, karst cave, groundwater and the like can exist, and the geological disasters have direct influence on construction safety and efficiency.
At present, the tunnel construction in China rapidly develops, and the detection by utilizing the advanced geological prediction technology in the tunnel construction process is an indispensable link for ensuring the construction safety. However, single geophysical prospecting methods generally have multiple solutions, and the accuracy of forecasting is unstable compared with the methods which rely on geological awareness and forecasting experience of forecasting staff. Due to the limitation of geological exploration technology, some bad geological bodies are difficult to fully ascertain in a geological exploration stage, so that potential and uncertain bad geological factors exist in the tunnel construction process, and sudden accidents such as roof collapse, subsidence, water and mud bursting, gas explosion and the like are easily caused by the bad geology, so that deformation and damage of a supporting structure, casualties and property loss are caused.
Therefore, how to provide a advanced geological detection method carried on an ultra-large diameter slurry shield to improve the accuracy of poor geological detection is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to solve the technical problems that the existing geological detection adopts a single geophysical prospecting method implemented manually, the accuracy of poor geological detection is unstable, and the manual operation detection mode is complex and difficult for an ultra-large diameter shield.
In order to solve the above problems, in a first aspect, the present invention provides a method for advanced geological detection carried on an oversized-diameter slurry shield, the method comprising:
acquiring a target seismic wave signal fed back in front of a tunnel face by using an advanced geological prediction system carried on an oversized-diameter slurry shield machine;
performing primary denoising processing on the target seismic wave signal to obtain a primary denoising signal;
performing secondary denoising processing on the primary denoising signal to obtain a secondary denoising signal;
and identifying the secondary denoising signal through the bad geological body identification model to obtain a geological type identification result corresponding to the secondary denoising signal.
Preferably, before the secondary denoising signal is identified by the bad geological body identification model, the advanced geological detection method further comprises:
and performing model training on the basic model to obtain the bad geological body identification model.
Preferably, the model training on the basic model specifically includes:
acquiring historical data in front of a tunnel face, wherein the historical data comprises historical seismic wave signals fed back in front of the tunnel face and geological types corresponding to the historical seismic wave signals;
And taking the historical seismic wave signal as an input signal of a basic model, and taking a geological type corresponding to the historical seismic wave signal as an output signal of the basic model so as to perform model training on the basic model.
Preferably, the basic model is composed of a res net residual network model and a BliSTM two-way long-short-term memory cyclic neural network model, the input signal of the basic model is the historical seismic wave signal, the geological type corresponding to the historical seismic wave signal is the output signal of the basic model, so as to perform model training on the basic model, and the method comprises the following steps:
and inputting the historical seismic wave signal into the ResNet residual network model as an input signal to extract deep features of the historical seismic wave signal, inputting the deep features into the BliSTM bidirectional long-short-term memory cyclic neural network model to extract time sequence features of the deep features, and correlating a geological type corresponding to the historical seismic wave signal with the time sequence features to obtain an output signal corresponding to the time sequence features to model train the basic model.
Preferably, the performing a secondary denoising process on the primary denoising signal to obtain a secondary denoising signal specifically includes:
Optimizing decomposition parameters of an MVMD multi-variant modal signal decomposition algorithm according to a GWO gray wolf optimization algorithm to obtain an MVMD optimization algorithm;
decomposing the primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal;
and synthesizing a plurality of signal components corresponding to the primary denoising signals according to the MVMD optimization algorithm to obtain secondary denoising signals.
Preferably, the one-time denoising process includes a filtering process and a smoothing process.
Preferably, the method for acquiring the target seismic wave signal fed back in front of the tunnel face by using the advanced geological prediction system mounted on the ultra-large diameter slurry shield machine specifically comprises the following steps:
the TSP advanced detection forecasting system is carried on an oversized-diameter slurry shield machine, so that a first target seismic wave signal fed back in front of a tunnel face is obtained through the TSP advanced detection forecasting system;
the SSP-E advanced detection system is mounted on an oversized-diameter slurry shield machine, so that a second target seismic wave signal fed back in front of a tunnel face is obtained through the SSP-E advanced detection system;
the step of performing primary denoising processing on the target seismic wave signal to obtain a primary denoising signal comprises the following steps:
Performing primary denoising processing on the first target seismic wave signal to obtain a TSP primary denoising signal, and performing primary denoising processing on the second target seismic wave signal to obtain an SSP-E primary denoising signal;
the decomposing the primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal specifically includes: respectively decomposing the TSP primary denoising signal and the SSP-E primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal;
the method comprises synthesizing a plurality of signal components corresponding to the primary denoising signal according to the MVMD optimization algorithm to obtain a secondary denoising signal, and specifically comprises the following steps: and synthesizing a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal through the MVMD optimization algorithm to obtain a secondary denoising signal.
Preferably, the ultra-large diameter slurry shield machine includes a shield, a cutter head and a shield segment, and the TSP advanced detection prediction system is mounted on the ultra-large diameter slurry shield machine, so as to obtain a first target seismic wave signal fed back in front of a tunnel face through the TSP advanced detection prediction system, and specifically includes:
A plurality of source holes are formed in the shield, the plurality of source holes are symmetrically distributed on two sides of the shield, a plurality of detection receiving holes are formed in the shield, the plurality of detection receiving holes are symmetrically distributed on two sides of the shield, one source of the TSP advanced detection forecasting system is mounted in one source hole through an oil cylinder, and one detector of the TSP advanced detection forecasting system is mounted in one detection receiving hole through the oil cylinder;
pushing the seismic source and the detector to the direction of the wall of the excavation bin through the oil cylinder so as to prop the seismic source and the detector against the wall of the excavation bin;
and transmitting a seismic source wave signal through the seismic source, and receiving a first target seismic source wave signal fed back in front of the tunnel face through the detector.
Preferably, the SSP-E advanced detection system is mounted on an oversized diameter slurry shield machine, so as to obtain a second target seismic wave signal fed back in front of a tunnel face through the SSP-E advanced detection system, and the method specifically includes:
a through hole is formed in each of the cutterhead and the shield, the transmitting end of the SSP-E advanced detection system is mounted in the through hole of the cutterhead through an oil cylinder, a first part of sensors of the receiving end of the SSP-E advanced detection system are mounted in the through hole of the shield through the oil cylinder, and a second part of sensors of the receiving end are mounted in grouting holes of the shield segment through the oil cylinder;
Pushing the transmitting end from the through hole of the cutter disc to the front of a tunnel face through an oil cylinder and propping the tunnel face, pushing the first part of sensor from the through hole of the shield to the wall of the excavation bin through the oil cylinder and propping the first part of sensor on the wall of the excavation bin, and pushing the second part of sensor from the grouting hole of the shield segment through the oil cylinder and propping the second part of sensor on the wall of the excavation bin;
and transmitting the vibration source wave signal through the transmitting end, and receiving a second target vibration source wave signal fed back in front of the tunnel face through the first partial sensor and the second partial sensor.
In a second aspect, the present invention also provides an advanced geological detection device carried on an oversized diameter slurry shield, the advanced geological detection device comprising:
the acquisition module is used for acquiring a target seismic wave signal fed back in front of a tunnel face by using an advanced geological prediction system mounted on the ultra-large diameter slurry shield machine;
the first processing module is used for carrying out primary denoising processing on the target seismic wave signal to obtain a primary denoising signal;
the second processing module is used for carrying out secondary denoising processing on the primary denoising signal to obtain a secondary denoising signal;
And the geological condition determining module is used for identifying the secondary denoising signal through the bad geological body identification model to obtain a geological type identification result corresponding to the secondary denoising signal.
The beneficial effects are that: the invention provides an advanced geological detection method carried on an oversized-diameter slurry shield, which is applied to tunnel construction of the oversized-diameter slurry shield. According to the method, the primary denoising processing and the secondary denoising processing are carried out on the target seismic wave signals fed back in front of the tunnel face, so that interference signals in the target seismic wave signals are eliminated, and then the signals subjected to denoising processing are input into the bad geological body recognition model to obtain more accurate geological type detection results, and the accuracy of bad geological detection is improved.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for advanced geological exploration according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a TSP source and detector layout scenario in an embodiment of the present invention;
FIG. 3 is a schematic diagram of an SSP-E transmitting end and receiving end layout scene in an embodiment of the invention;
FIG. 4 is a schematic diagram of a bad geological body identification model according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an advanced geological exploration apparatus according to an embodiment of the present invention.
Reference numerals:
1. a tunnel;
11. a tunnel face;
12. excavating a bin hole wall;
2. an oversized-diameter slurry shield machine;
21. a cutterhead;
22. a shield;
3. an oil cylinder;
41. a seismic source;
42. a wave detector;
42. a signal acquisition instrument;
44. an inductive trigger;
51. a transmitting end;
52. and a receiving end.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Before describing the advanced geological exploration method provided in the present application, the background content related to the present application will be first described.
In the tunnel construction process, the geological condition in front of the tunnel face needs to be detected by utilizing an advanced geological prediction technology, so that the tunnel construction safety is ensured. However, in the current advanced geological prediction technology, a signal transmitting end and a signal receiving end are manually placed at proper positions, then signals are transmitted and received, but aiming at the condition of ultra-large-diameter slurry shield engineering, the positions of the signal transmitting end and the signal receiving end are difficult to set in a manual operation mode, and a single geophysical prospecting method generally has multiple solutions, so that the accuracy of prediction is unstable compared with the method depending on geological awareness capability and prediction experience of a predictor.
Example 1
As shown in fig. 1, the first embodiment provides a method for advanced geological detection carried on an oversized-diameter slurry shield, which specifically includes the following steps S110 to S140:
s110, acquiring a target seismic wave signal fed back in front of a tunnel face 11 of a tunnel 1 by using an advanced geological prediction system mounted on an oversized-diameter slurry shield machine 2;
the advanced geological prediction system is used for transmitting the seismic wave signals, when the seismic wave signals meet rock wave impedance difference interfaces (such as faults, broken zones, lithology changes and the like), a part of the seismic wave signals are reflected back, and a part of the seismic wave signals are transmitted into a front medium. The reflected seismic signal is received by a receiver or detector, i.e. the target seismic signal.
Step S120, performing primary denoising processing on the target seismic wave signal to obtain a primary denoising signal;
as an implementation manner, the denoising processing of the target seismic signal in the step S120 includes filtering processing and smoothing processing of the target seismic signal.
Specifically, by performing preprocessing such as filtering and smoothing on the target seismic wave signal, redundant signal interference during MVMD decomposition can be reduced.
Step S130, performing secondary denoising processing on the primary denoising signal to obtain a secondary denoising signal;
as an implementation manner, the step S130 performs a secondary denoising process on the primary denoising signal to obtain a secondary denoising signal, which specifically includes the following sub-steps:
optimizing decomposition parameters of an MVMD multi-variant modal signal decomposition algorithm according to a GWO gray wolf optimization algorithm to obtain an MVMD optimization algorithm;
decomposing the primary denoising signal according to an MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal;
and synthesizing a plurality of signal components corresponding to the primary denoising signals according to the MVMD optimization algorithm to obtain secondary denoising signals.
Specifically, parameters in an MVMD multi-variant modal signal decomposition algorithm are optimized according to a GWO gray wolf optimization algorithm, then a primary denoising signal is decomposed through the optimized MVMD algorithm to obtain a series of components, and then the components are processed and synthesized by utilizing the optimized MVMD algorithm to obtain a secondary denoising signal for further removing noise, so that an interference signal of an original seismic wave signal is further reduced, and the secondary denoising signal is used as an input signal of a bad geologic body identification model.
And step 140, identifying the secondary denoising signal through the bad geologic body identification model to obtain a geologic type identification result corresponding to the secondary denoising signal.
As an implementation manner, before the secondary denoising signal is identified by the bad geological body identification model in the step S140, the advanced geological detection method in the embodiment of the present invention further includes:
and performing model training on the basic model to obtain the bad geologic body identification model.
As an implementation manner, the model training on the basic model in the above steps specifically includes the following sub-steps:
historical data in front of the tunnel face 11 of the tunnel 1 is acquired, wherein the historical data comprise historical seismic wave signals fed back in front of the tunnel face 11 and geological types corresponding to the historical seismic wave signals, the historical seismic wave signals are used as input signals of a basic model, and the geological types corresponding to the historical seismic wave signals are used as output signals of the basic model, so that model training is conducted on the basic model.
Specifically, a great amount of historical data is obtained, wherein the historical data comprises historical seismic wave signals fed back in front of the face 11 and geological types corresponding to the historical seismic wave signals, the geological types comprise positions and scale conditions of bad geologic bodies, the base model is trained through the historical data to obtain a trained bad geologic body identification model, and further when target seismic wave signals subjected to noise removal processing are input into the trained bad geologic body identification model, geological type identification results in front of the face 11 can be obtained, and the geological type identification results can comprise types, positions and scale of bad geologic bodies.
As an achievable way, the basic model is composed of a res net residual network model and a BliSTM two-way long-short-term memory cyclic neural network model, wherein the step takes a historical seismic wave signal as an input signal of the basic model and takes a geological type corresponding to the historical seismic wave signal as an output signal of the basic model so as to perform model training on the basic model, and the method specifically comprises the following substeps:
the method comprises the steps of inputting a historical seismic wave signal into a ResNet residual network model as an input signal to extract deep features of the historical seismic wave signal, inputting the deep features into a BliSTM two-way long-short-term memory cyclic neural network model to extract time sequence features of the deep features, correlating a geological type corresponding to the historical seismic wave signal with the time sequence features to obtain an output signal corresponding to the time sequence features, and performing model training on a basic model.
The ResNet residual network model is a deep residual network, can be used for solving the problems of gradient elimination and network degradation in a deep neural network, allows training of a deeper neural network, is beneficial to extracting richer feature representations, and improves the performance of the model. The BliSTM two-way long-short-term memory cyclic neural network model is a neural network model capable of capturing sequence information, and by using two independent LSTMs, an input sequence is observed from the forward direction and the reverse direction at the same time, so that the accuracy of the model is improved.
The ResNet residual network model and the BliSTM two-way long-short-term memory cyclic neural network model are combined to form a basic model, and model training and testing are carried out on the basic model through a large amount of historical data to obtain a trained bad geologic body identification model, and the trained bad geologic body identification model is used for identifying geologic bodies in front of the tunnel face 11 of the construction site of the tunnel 1 to determine the front geologic condition.
The embodiment of the invention provides a advanced geological detection method carried on an oversized-diameter slurry shield, which is applied to the construction of a tunnel 1 of the oversized-diameter slurry shield, wherein an advanced geological prediction system is firstly carried on an oversized-diameter slurry shield machine 2, then a target seismic wave signal fed back in front of a tunnel face 11 of the tunnel 1 is acquired through the advanced geological prediction system, primary denoising processing is carried out on the received target seismic wave signal, a primary denoising signal is obtained, secondary denoising processing is carried out on the primary denoising signal, a secondary denoising signal is obtained, and finally a poor geological body recognition model is used for recognizing the secondary denoising signal, so that a geological type recognition result corresponding to the secondary denoising signal is obtained. According to the method, the primary denoising processing and the secondary denoising processing are carried out on the target seismic wave signals fed back in front of the tunnel face 11 of the tunnel 1, so that interference signals in the target seismic wave signals are eliminated, and then the signals subjected to the denoising processing are input into the bad geological body recognition model to obtain more accurate geological type detection results, so that the accuracy of bad geological detection is improved.
As an achievable manner, in the step S110, the target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1 is obtained by using the advanced geological prediction system mounted on the ultra-large diameter slurry shield machine 2, and specifically includes the following sub-steps:
the TSP advanced detection forecasting system is carried on the ultra-large-diameter slurry shield machine 2, so that a first target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1 is obtained through the TSP advanced detection forecasting system;
the SSP-E advanced detection system is mounted on the ultra-large diameter slurry shield machine 2 to obtain a second target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1 through the SSP-E advanced detection system;
in the step S110, performing a denoising process on the target seismic wave signal to obtain a denoising signal includes:
performing primary denoising processing on the first target seismic wave signal to obtain a TSP primary denoising signal, and performing primary denoising processing on the second target seismic wave signal to obtain an SSP-E primary denoising signal;
the above steps decompose the primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal, and specifically include: respectively decomposing the TSP primary denoising signal and the SSP-E primary denoising signal through an MVMD optimization algorithm to obtain a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal;
The steps are to synthesize a plurality of signal components corresponding to the primary denoising signal according to an MVMD optimization algorithm to obtain a secondary denoising signal, and specifically comprise the following steps: and synthesizing a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal through an MVMD optimization algorithm to obtain a secondary denoising signal.
As an achievable manner, the ultra-large diameter slurry shield machine 2 includes a shield 22, a cutterhead 21 and a shield segment, and the steps of the foregoing load a TSP advanced detection and prediction system on the ultra-large diameter slurry shield machine 2 to obtain a first target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1 through the TSP advanced detection and prediction system specifically includes the following sub-steps:
a plurality of source holes are formed in the shield 22, the plurality of source holes are symmetrically distributed on two sides of the shield 22, a plurality of detection receiving holes are formed in the shield 22, the plurality of detection receiving holes are symmetrically distributed on two sides of the shield 22, one source 41 of the TSP advanced detection forecasting system is carried in one source hole through the oil cylinder 3, and one detector 42 of the TSP advanced detection forecasting system is carried in one detection receiving hole through the oil cylinder 3;
pushing the seismic source 41 and the detector 42 towards the excavation cavity wall 12 through the oil cylinder 3 so as to enable the seismic source 41 and the detector 42 to be propped against the excavation cavity wall 12;
The source wave signal is transmitted by the source 41, and the first target source wave signal fed back in front of the face 11 of the tunnel 1 is received by the detector 42.
Specifically, the TSP advanced detection forecasting system generally includes a seismic source, a detector, a signal acquisition instrument and an induction trigger, where the seismic source and the detector are arranged on an opening of a shield to emit seismic wave signals through the seismic source, and the detector receives seismic wave signals reflected in front of a tunnel face, and the induction trigger is connected with the seismic source and used for triggering the seismic source to emit the seismic wave signals, and the signal acquisition instrument is connected with the detector and used for acquiring and analyzing the seismic wave signals reflected in front of the tunnel face received by the detector. The induction trigger and the signal acquisition instrument can be arranged at any position on the ultra-large diameter slurry shield machine, and only the shield operation and the signal transmitting and receiving operation are not influenced.
In a specific implementation manner, as shown in fig. 2, 8 source holes may be formed in the shield 22, the 8 source holes are symmetrically distributed on two sides of the shield 22, meanwhile, 8 detection receiving holes are formed in the shield 22, the 8 detection receiving holes are symmetrically distributed on two sides of the shield 22, wherein the source holes and the detection receiving holes are located at different positions of the shield, a source 41 connected with the oil cylinder 3 is arranged in each source hole, a detector 42 connected with the oil cylinder 3 is arranged in each detection receiving hole, and the corresponding source 41 can be pushed out from the source hole by starting the corresponding oil cylinder, or the detector 42 can be pushed out from the detection receiving hole.
As an achievable way, the above step is to mount an SSP-E advanced detection system on the ultra-large diameter slurry shield machine 2, so as to obtain, through the SSP-E advanced detection system, a second target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1, and specifically includes the following substeps:
a through hole is formed in each of the cutterhead 21 and the shield 22, a transmitting end 51 of the SSP-E advanced detection system is mounted in the through hole of the cutterhead 21 through an oil cylinder 3, a first part of sensors of a receiving end 52 of the SSP-E advanced detection system are mounted in the through hole of the shield 22 through the oil cylinder 3, and a second part of sensors of the receiving end 52 are mounted in grouting holes of shield segments through the oil cylinder 3;
pushing the transmitting end 51 from the through hole of the cutter head 21 to the front of the tunnel face 11 of the tunnel 1 through the oil cylinder 3 and propping the tunnel face 11, pushing the first part of sensors from the through hole of the shield 22 to the excavation chamber hole wall 12 through the oil cylinder 3 and propping the excavation chamber hole wall 12, pushing the second part of sensors from the grouting holes of the shield segment through the oil cylinder 3 and propping the excavation chamber hole wall 12;
and the transmitting end 51 transmits the vibration source wave signals, and the first partial sensor and the second partial sensor receive the second target vibration source wave signals fed back in front of the tunnel face 11 of the tunnel 1.
In a specific implementation manner, as shown in fig. 3, since the embodiment of the invention is applied to the tunnel of the ultra-large diameter slurry shield, when the advanced detection is performed by the SSP-E advanced detection system, two sensors are required to be arranged to receive the seismic wave signals sent by the transmitting end, so that the acquired second target seismic wave signals are more comprehensive and accurate. The SSP-E advanced detection system generally includes a transmitting end (probe), a receiving end (sensor), a signal processing unit for processing a signal received by the receiving end, and a data transmission module for transmitting the signal before or after processing to an external device. The signal processing unit and the data transmission module can be arranged at any position on the ultra-large diameter slurry shield machine, and only the shield operation and the signal transmitting and receiving operation are not affected.
Specifically, in this embodiment of the present application, the TSP advanced detection prediction system may be used alone to obtain the first target seismic wave signal, then perform primary denoising and secondary denoising on the first target seismic wave signal, and then input the denoised signal into the trained bad geologic body recognition model, so as to obtain the geologic condition in front of the tunnel face 11. The second target seismic wave signal can be obtained by an SSP-E advanced detection system alone, then the first denoising process and the second denoising process are carried out on the second target seismic wave signal, and then the signals after denoising process are input into a trained bad geologic body recognition model, so that the geologic condition in front of the face 11 can be obtained.
Furthermore, the TSP advanced detection prediction system and the SSP-E advanced detection system may be combined to obtain a first target seismic signal received by the TSP advanced detection prediction system and a second target seismic signal received by the SSP-E advanced detection system, then the first target seismic signal and the second target seismic signal are subjected to a denoising process, the first target seismic signal and the second target seismic signal subjected to the denoising process are input into the MVMD optimization algorithm to be decomposed and synthesized, so as to obtain a synthesized secondary denoising signal, and then the secondary denoising signal subjected to the secondary denoising process is input into a trained bad geologic body recognition model, so that a geologic condition in front of the face 11 may be obtained, and the geologic condition in front of the face 11 obtained in this manner is more accurate than that obtained by using one kind of advanced detection prediction system alone.
Example 2
The second embodiment provides an advanced geological detection device carried on an oversized-diameter slurry shield, where the geological detection device 200 includes:
an acquisition unit 201, configured to acquire a target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1 by using an advanced geological prediction system mounted on the ultra-large diameter slurry shield machine 2;
A first processing unit 202, configured to perform primary denoising processing on the target seismic wave signal to obtain a primary denoising signal;
a second processing unit 203, configured to perform secondary denoising processing on the primary denoising signal to obtain a secondary denoising signal;
the geological condition determining unit 204 is configured to identify the secondary denoising signal through the bad geological body identification model, and obtain a geological type identification result corresponding to the secondary denoising signal.
As one implementation, the geological exploration apparatus 200 further includes:
and the model training unit is used for carrying out model training on the basic model so as to obtain the bad geologic body identification model.
As an achievable way, the model training unit is further configured to perform the following steps:
acquiring historical data in front of a tunnel face 11 of a tunnel 1, wherein the historical data comprises historical seismic wave signals fed back in front of the tunnel face 11 and geological types corresponding to the historical seismic wave signals;
the historical seismic wave signals are used as input signals of the basic model, and the geological types corresponding to the historical seismic wave signals are used as output signals of the basic model, so that model training is conducted on the basic model.
As an achievable way, the basic model is composed of a res net residual network model and a BliSTM two-way long-short-term memory cyclic neural network model, and the model training unit is further configured to perform the following steps:
The method comprises the steps of inputting a historical seismic wave signal into a ResNet residual network model as an input signal to extract deep features of the historical seismic wave signal, inputting the deep features into a BliSTM two-way long-short-term memory cyclic neural network model to extract time sequence features of the deep features, correlating a geological type corresponding to the historical seismic wave signal with the time sequence features to obtain an output signal corresponding to the time sequence features, and performing model training on a basic model.
As an achievable way, the second processing unit 203 is further configured to perform the following steps:
optimizing decomposition parameters of an MVMD multi-variant modal signal decomposition algorithm according to a GWO gray wolf optimization algorithm to obtain an MVMD optimization algorithm;
decomposing the primary denoising signal according to an MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal;
and synthesizing a plurality of signal components corresponding to the primary denoising signals according to the MVMD optimization algorithm to obtain secondary denoising signals.
As one achievable way, the one-time denoising process includes a filtering process and a smoothing process.
As an implementation manner, the above-mentioned obtaining unit 201 is further configured to perform the following steps:
The TSP advanced detection forecasting system is carried on the ultra-large-diameter slurry shield machine 2, so that a first target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1 is obtained through the TSP advanced detection forecasting system;
the SSP-E advanced detection system is mounted on the ultra-large diameter slurry shield machine 2 to obtain a second target seismic wave signal fed back in front of the tunnel face 11 of the tunnel 1 through the SSP-E advanced detection system;
performing primary denoising processing on the target seismic wave signal to obtain a primary denoising signal, wherein the primary denoising processing specifically comprises the following steps: performing primary denoising processing on the first target seismic wave signal to obtain a TSP primary denoising signal, and performing primary denoising processing on the second target seismic wave signal to obtain an SSP-E primary denoising signal;
decomposing the primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal, wherein the method specifically comprises the following steps of: respectively decomposing the TSP primary denoising signal and the SSP-E primary denoising signal according to an MVMD optimization algorithm to obtain a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal;
synthesizing a plurality of signal components corresponding to the primary denoising signal according to the MVMD optimization algorithm to obtain a secondary denoising signal, wherein the method specifically comprises the following steps of: and synthesizing a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal through an MVMD optimization algorithm to obtain a secondary denoising signal.
As an implementation manner, the above-mentioned obtaining unit 201 is further configured to perform the following steps:
a plurality of source holes are formed in the shield 22, the plurality of source holes are symmetrically distributed on two sides of the shield 22, a plurality of detection receiving holes are formed in the shield 22, the plurality of detection receiving holes are symmetrically distributed on two sides of the shield 22, one source 41 of the TSP advanced detection forecasting system is carried in one source hole through the oil cylinder 3, and one detector 42 of the TSP advanced detection forecasting system is carried in one detection receiving hole through the oil cylinder 3;
pushing the seismic source 41 and the detector 42 towards the excavation cavity wall 12 through the oil cylinder 3 so as to enable the seismic source 41 and the detector 42 to be propped against the excavation cavity wall 12;
the source wave signal is transmitted by the source 41, and the first target source wave signal fed back in front of the face 11 of the tunnel 1 is received by the detector 42.
As an implementation manner, the above-mentioned obtaining unit 201 is further configured to perform the following steps:
a through hole is formed in each of the cutterhead 21 and the shield 22, a transmitting end 51 of the SSP-E advanced detection system is mounted in the through hole of the cutterhead 21 through an oil cylinder 3, a first part of sensors of a receiving end 52 of the SSP-E advanced detection system are mounted in the through hole of the shield 22 through the oil cylinder 3, and a second part of sensors of the receiving end 52 are mounted in grouting holes of shield segments through the oil cylinder 3;
Pushing the transmitting end 51 from the through hole of the cutter head 21 to the front of the tunnel face 11 of the tunnel 1 through the oil cylinder 3 and propping the tunnel face 11, pushing the first part of sensors from the through hole of the shield 22 to the excavation chamber hole wall 12 through the oil cylinder 3 and propping the excavation chamber hole wall 12, pushing the second part of sensors from the grouting holes of the shield segment through the oil cylinder 3 and propping the excavation chamber hole wall 12;
and the transmitting end 51 transmits the vibration source wave signals, and the first partial sensor and the second partial sensor receive the second target vibration source wave signals fed back in front of the tunnel face 11 of the tunnel 1.
The invention provides an advanced geological detection device 200 mounted on an oversized-diameter slurry shield, which is characterized in that an acquisition unit 201 acquires a target seismic wave signal fed back in front of a tunnel face 11 of a tunnel 1 by using an advanced geological prediction system mounted on an oversized-diameter slurry shield machine 2, a first processing unit 202 performs primary denoising processing on the target seismic wave signal to obtain a primary denoising signal, a second processing unit performs secondary denoising processing on the primary denoising signal to obtain a secondary denoising signal, and a geological condition determination unit 204 uses a bad geological body recognition model to recognize the secondary denoising signal to obtain a geological type recognition result corresponding to the secondary denoising signal. According to the embodiment of the invention, the primary denoising processing and the secondary denoising processing are carried out on the target seismic wave signals fed back in front of the tunnel face 11 of the tunnel 1, so that interference signals in the target seismic wave signals are eliminated, and then the signals subjected to the denoising processing are input into the bad geological body recognition model to obtain more accurate geological type detection results, so that the accuracy of bad geological detection is improved.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the above examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit of the corresponding technical solutions. Are intended to be encompassed within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Although embodiments of the present invention have been disclosed above, it is not limited to the details and embodiments shown and described, it is well suited to various fields of use for which the invention would be readily apparent to those skilled in the art, and accordingly, the invention is not limited to the specific details and illustrations shown and described herein, without departing from the general concepts defined in the claims and their equivalents.
Claims (10)
1. The advanced geological detection method carried on the ultra-large diameter slurry shield is characterized by comprising the following steps of:
acquiring a target seismic wave signal fed back in front of a tunnel face by using an advanced geological prediction system carried on an oversized-diameter slurry shield machine;
performing primary denoising processing on the target seismic wave signal to obtain a primary denoising signal;
performing secondary denoising processing on the primary denoising signal to obtain a secondary denoising signal;
and identifying the secondary denoising signal through the bad geological body identification model to obtain a geological type identification result corresponding to the secondary denoising signal.
2. The advanced geological exploration method carried on a slurry shield of ultra-large diameter according to claim 1, wherein said advanced geological exploration method further comprises, prior to said identifying said secondary denoising signal by a bad geological mass identification model:
and performing model training on the basic model to obtain the bad geological body identification model.
3. The advanced geological exploration method carried on an oversized slurry shield according to claim 2, wherein the model training of the basic model specifically comprises:
Acquiring historical data in front of a tunnel face, wherein the historical data comprises historical seismic wave signals fed back in front of the tunnel face and geological types corresponding to the historical seismic wave signals;
and taking the historical seismic wave signal as an input signal of a basic model, and taking a geological type corresponding to the historical seismic wave signal as an output signal of the basic model so as to perform model training on the basic model.
4. The advanced geological exploration method carried on an ultra-large diameter slurry shield according to claim 3, wherein said basic model is composed of a res net residual network model and a Bl is two-way long and short term memory cyclic neural network model, said taking said historical seismic wave signal as an input signal of the basic model and taking a geological type corresponding to said historical seismic wave signal as an output signal of the basic model, so as to model-train said basic model, comprising:
and inputting the historical seismic wave signal into the ResNet residual network model as an input signal to extract deep features of the historical seismic wave signal, inputting the deep features into the BliSTM bidirectional long-short-term memory cyclic neural network model to extract time sequence features of the deep features, and correlating a geological type corresponding to the historical seismic wave signal with the time sequence features to obtain an output signal corresponding to the time sequence features to model train the basic model.
5. The advanced geological detection method carried on an ultra-large diameter slurry shield according to claim 4, wherein the performing the secondary denoising process on the primary denoising signal to obtain a secondary denoising signal specifically comprises:
optimizing decomposition parameters of an MVMD multi-variant modal signal decomposition algorithm according to a GWO gray wolf optimization algorithm to obtain an MVMD optimization algorithm;
decomposing the primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal;
and synthesizing a plurality of signal components corresponding to the primary denoising signals according to the MVMD optimization algorithm to obtain secondary denoising signals.
6. The advanced geological exploration method carried on an oversized slurry shield according to claim 5, wherein said one denoising process comprises a filtering process and a smoothing process.
7. The advanced geological exploration method according to claim 6, wherein the acquiring the target seismic wave signal fed back in front of the tunnel face by using the advanced geological prediction system mounted on the ultra-large diameter slurry shield machine specifically comprises:
the TSP advanced detection forecasting system is carried on an oversized-diameter slurry shield machine, so that a first target seismic wave signal fed back in front of a tunnel face is obtained through the TSP advanced detection forecasting system;
The SSP-E advanced detection system is mounted on an oversized-diameter slurry shield machine, so that a second target seismic wave signal fed back in front of a tunnel face is obtained through the SSP-E advanced detection system;
the step of performing primary denoising processing on the target seismic wave signal to obtain a primary denoising signal comprises the following steps: performing primary denoising processing on the first target seismic wave signal to obtain a TSP primary denoising signal, and performing primary denoising processing on the second target seismic wave signal to obtain an SSP-E primary denoising signal;
the decomposing the primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the primary denoising signal specifically includes: respectively decomposing the TSP primary denoising signal and the SSP-E primary denoising signal according to the MVMD optimization algorithm to obtain a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal;
the method comprises synthesizing a plurality of signal components corresponding to the primary denoising signal according to the MVMD optimization algorithm to obtain a secondary denoising signal, and specifically comprises the following steps: and synthesizing a plurality of signal components corresponding to the TSP primary denoising signal and the SSP-E primary denoising signal through the MVMD optimization algorithm to obtain a secondary denoising signal.
8. The advanced geological detection method carried on the ultra-large diameter slurry shield according to claim 7, wherein the ultra-large diameter slurry shield machine comprises a shield, a cutter head and a shield segment, and the method is characterized in that a TSP advanced detection prediction system is carried on the ultra-large diameter slurry shield machine to obtain a first target seismic wave signal fed back in front of a tunnel face through the TSP advanced detection prediction system, and specifically comprises:
a plurality of source holes are formed in the shield, the plurality of source holes are symmetrically distributed on two sides of the shield, a plurality of detection receiving holes are formed in the shield, the plurality of detection receiving holes are symmetrically distributed on two sides of the shield, one source of the TSP advanced detection forecasting system is mounted in one source hole through an oil cylinder, and one detector of the TSP advanced detection forecasting system is mounted in one detection receiving hole through the oil cylinder;
pushing the seismic source and the detector to the direction of the wall of the excavation bin through the oil cylinder so as to prop the seismic source and the detector against the wall of the excavation bin;
and transmitting a seismic source wave signal through the seismic source, and receiving a first target seismic source wave signal fed back in front of the tunnel face through the detector.
9. The advanced geological detection method carried on a slurry shield with ultra-large diameter according to claim 8, wherein the step of carrying the SSP-E advanced detection system on the slurry shield with ultra-large diameter to obtain the second target seismic wave signal fed back in front of the tunnel face through the SSP-E advanced detection system specifically comprises:
a through hole is formed in each of the cutterhead and the shield, the transmitting end of the SSP-E advanced detection system is mounted in the through hole of the cutterhead through an oil cylinder, a first part of sensors of the receiving end of the SSP-E advanced detection system are mounted in the through hole of the shield through the oil cylinder, and a second part of sensors of the receiving end are mounted in grouting holes of the shield segment through the oil cylinder;
pushing the transmitting end from the through hole of the cutter disc to the front of a tunnel face through an oil cylinder and propping the tunnel face, pushing the first part of sensor from the through hole of the shield to the wall of the excavation bin through the oil cylinder and propping the first part of sensor on the wall of the excavation bin, and pushing the second part of sensor from the grouting hole of the shield segment through the oil cylinder and propping the second part of sensor on the wall of the excavation bin;
And transmitting the vibration source wave signal through the transmitting end, and receiving a second target vibration source wave signal fed back in front of the tunnel face through the first partial sensor and the second partial sensor.
10. An advanced geological detection device carried on an oversized-diameter slurry shield, characterized in that the advanced geological detection device comprises:
the acquisition unit is used for acquiring a target seismic wave signal fed back in front of a tunnel face by using an advanced geological prediction system mounted on the ultra-large diameter slurry shield machine;
the first processing unit is used for carrying out primary denoising processing on the target seismic wave signal to obtain a primary denoising signal;
the second processing unit is used for carrying out secondary denoising processing on the primary denoising signal to obtain a secondary denoising signal;
and the geological condition determining unit is used for identifying the secondary denoising signal through the bad geological body identification model to obtain a geological type identification result corresponding to the secondary denoising signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311621154.8A CN117590465A (en) | 2023-11-29 | 2023-11-29 | Advanced geological detection method and device carried on ultra-large diameter slurry shield |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311621154.8A CN117590465A (en) | 2023-11-29 | 2023-11-29 | Advanced geological detection method and device carried on ultra-large diameter slurry shield |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117590465A true CN117590465A (en) | 2024-02-23 |
Family
ID=89919788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311621154.8A Pending CN117590465A (en) | 2023-11-29 | 2023-11-29 | Advanced geological detection method and device carried on ultra-large diameter slurry shield |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117590465A (en) |
-
2023
- 2023-11-29 CN CN202311621154.8A patent/CN117590465A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110109895B (en) | Surrounding rock grading combined prediction method suitable for TBM tunneling tunnel and application | |
| CN102373923B (en) | Reservoir stratum identification method | |
| CN113050159B (en) | Coal rock hydraulic fracturing crack micro-seismic positioning and propagation mechanism monitoring method | |
| CN110529087B (en) | Method and device for evaluating hydraulic fracturing effect of stratum | |
| CN211291565U (en) | Tunnel construction dynamic monitoring and early warning system | |
| AU2013277928B2 (en) | Systems and methods for processing geophysical data | |
| US11789173B1 (en) | Real-time microseismic magnitude calculation method and device based on deep learning | |
| CN107703538A (en) | Underground unfavorable geology survey data acquisition analysis system and method | |
| CN110968840A (en) | Method for judging grade of tunnel surrounding rock based on magnetotelluric sounding resistivity | |
| CN106032750B (en) | Geological logging instrument based on drilling energy spectrum | |
| CN112230275B (en) | Method and device for identifying seismic waveform and electronic equipment | |
| CN113311487A (en) | Frequency domain induced polarization advanced water detection method and device for tunnel face emission | |
| CN117590465A (en) | Advanced geological detection method and device carried on ultra-large diameter slurry shield | |
| CN109738964B (en) | Tunnel prediction device, tunneling machine and method for seismic wave and electromagnetic wave joint inversion | |
| CN111983718A (en) | Remote advanced detection method for directional drilling and tunneling working face | |
| CN113126161B (en) | Method and system for predicting cave depth and size of karst cave based on shock waves | |
| Li et al. | Noise reduction method of microseismic signal of water inrush in tunnel based on variational mode method | |
| CN115950947A (en) | Real-time geological parameter prediction method of TBM tunnel based on vibration signal | |
| CN113189672B (en) | Tunnel advance geological forecast method based on multi-attribute inversion | |
| CN115759351A (en) | Slurry shield tunneling comprehensive early warning method and system and storage medium | |
| CN111025383B (en) | Method for qualitatively judging water filling condition of tunnel front karst cave based on diffracted transverse waves | |
| CN113327070A (en) | Method and device for intelligently surveying coal-based gas and electronic equipment | |
| CN117214958B (en) | Advanced geological detection sensing and forecasting system based on long-distance horizontal directional drilling | |
| CN117189146A (en) | TBM tunneling process-based geological information acquisition method | |
| CN116484670A (en) | Three-dimensional geological modeling and stress analysis method and system based on comprehensive geophysical prospecting |
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 |