CN117214958B - Advanced geological detection sensing and forecasting system based on long-distance horizontal directional drilling - Google Patents
Advanced geological detection sensing and forecasting system based on long-distance horizontal directional drilling Download PDFInfo
- Publication number
- CN117214958B CN117214958B CN202311486605.1A CN202311486605A CN117214958B CN 117214958 B CN117214958 B CN 117214958B CN 202311486605 A CN202311486605 A CN 202311486605A CN 117214958 B CN117214958 B CN 117214958B
- Authority
- CN
- China
- Prior art keywords
- resistivity
- time sequence
- training
- autocorrelation
- geological
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005553 drilling Methods 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- 238000005728 strengthening Methods 0.000 claims abstract description 40
- 230000002159 abnormal effect Effects 0.000 claims abstract description 32
- 239000013598 vector Substances 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 87
- 238000010586 diagram Methods 0.000 claims description 47
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 230000015572 biosynthetic process Effects 0.000 description 14
- 238000005755 formation reaction Methods 0.000 description 14
- 238000012545 processing Methods 0.000 description 12
- 239000011435 rock Substances 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000010276 construction Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 239000002689 soil Substances 0.000 description 6
- 230000005641 tunneling Effects 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000001965 increasing effect Effects 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 238000012300 Sequence Analysis Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000013277 forecasting method Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Abstract
The invention discloses a advanced geological detection sensing and forecasting system based on a long-distance horizontal directional drill, which is used for acquiring resistivity of a plurality of preset time points in a preset time period acquired by a drill bit; transmitting the resistivity of the plurality of predetermined points in time to a server through a drill pipe electrically connected to the drill bit; at the server, arranging the resistivities of the plurality of predetermined time points into a resistivity time sequence input vector according to a time dimension; carrying out resistivity time sequence feature extraction and feature autocorrelation strengthening treatment on the resistivity time sequence input vector to obtain resistivity time sequence features; and determining whether a geological abnormal body exists or not and confirming whether an early warning prompt is generated or not based on the resistivity time sequence characteristics. Therefore, detection and judgment of geological abnormal bodies can be carried out, so that real-time monitoring and adjustment of the drilling direction are realized, geological abnormal bodies such as faults, karst, water cellars and the like are timely found and avoided in the drilling process, and the drilling efficiency and safety are improved.
Description
Technical Field
The invention relates to the technical field of intelligent geological detection, in particular to a long-distance horizontal directional drilling-based advanced geological detection sensing and forecasting system.
Background
In the process of determining schemes such as investment decision making, line selection, construction method selection, equipment selection and configuration, support form and parameters, construction period and construction cost of tunnel engineering, fine and accurate survey data such as engineering geology, hydrogeology, rock mass parameters and the like are indispensable supports.
However, the application of conventional advanced geological exploration methods in tunnels faces a number of difficulties. In advanced geological exploration construction, tunneling construction needs to be interrupted, which occupies normal tunneling time and increases economic and time costs. In addition, bad geologic bodies such as faults, karst cave, karst water-containing bodies, fault breaking zones and the like have strong concealment, and the difficulty is increased for exploring tunnel geology. The advanced geological detection depth of the current tunnel is shallow, and the drilling direction is uncontrollable, so that the risk of tunnel engineering is further increased.
Accordingly, a system for advanced geological exploration-aware forecasting based on long-range horizontal directional drilling is desired.
Disclosure of Invention
The embodiment of the invention provides a sensing and forecasting system for advanced geological detection based on long-distance horizontal directional drilling, which is used for acquiring resistivity of a plurality of preset time points in a preset time period acquired by a drill bit; transmitting the resistivity of the plurality of predetermined points in time to a server through a drill pipe electrically connected to the drill bit; at the server, arranging the resistivities of the plurality of predetermined time points into a resistivity time sequence input vector according to a time dimension; carrying out resistivity time sequence feature extraction and feature autocorrelation strengthening treatment on the resistivity time sequence input vector to obtain resistivity time sequence features; and determining whether a geological abnormal body exists or not and confirming whether an early warning prompt is generated or not based on the resistivity time sequence characteristics. Therefore, detection and judgment of geological abnormal bodies can be carried out, so that real-time monitoring and adjustment of the drilling direction are realized, geological abnormal bodies such as faults, karst, water cellars and the like are timely found and avoided in the drilling process, and the drilling efficiency and safety are improved.
The embodiment of the invention also provides a sensing and forecasting system for advanced geological detection based on the long-distance horizontal directional drill, which comprises the following steps:
a geological resistivity acquisition module for acquiring resistivity at a plurality of predetermined time points within a predetermined time period acquired by the drill bit;
the data transmission module is used for transmitting the resistivities of the preset time points to a server through a drill rod electrically connected with the drill bit;
the resistivity time sequence information arrangement module is used for arranging the resistivities of the plurality of preset time points into a resistivity time sequence input vector according to a time dimension at the server;
the resistivity time sequence feature analysis module is used for carrying out resistivity time sequence feature extraction and feature autocorrelation strengthening treatment on the resistivity time sequence input vector so as to obtain resistivity time sequence features;
and the geological abnormal body detection early warning module is used for determining whether geological abnormal bodies exist or not and confirming whether early warning prompts are generated or not based on the resistivity time sequence characteristics.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a block diagram of a sensing and forecasting system for advanced geological exploration based on long-distance horizontal directional drilling in an embodiment of the invention.
Fig. 2 is a flowchart of a method for advanced geological exploration sensing prediction based on long-distance horizontal directional drilling provided in an embodiment of the invention.
Fig. 3 is a schematic diagram of a system architecture based on a long-distance horizontal directional drilling advanced geological exploration sensing prediction method according to an embodiment of the present invention.
Fig. 4 is an application scenario diagram of a advanced geological detection sensing prediction system based on long-distance horizontal directional drilling provided by the embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Unless defined otherwise, all technical and scientific terms used in the examples of this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In the description of the embodiments of the present application, unless otherwise indicated and defined, the term "connected" should be construed broadly, and for example, may be an electrical connection, may be a communication between two elements, may be a direct connection, or may be an indirect connection via an intermediary, and it will be understood by those skilled in the art that the specific meaning of the term may be understood according to the specific circumstances.
It should be noted that, the term "first\second\third" in the embodiments of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
The application of conventional advanced geological exploration methods in tunnels does face a number of difficulties. Conventional advanced geological exploration methods typically require interruption of the tunneling construction of the tunnel for geological exploration and data collection, which can take up normal tunneling time, increasing economic and time costs. Tunnel engineering typically has a strict schedule and budget, so such interruptions may lead to project delays and cost outages. Some bad geologic bodies, such as faults, karsts, karst water-containing bodies and fault breaking zones, have strong concealment, and the geologic bodies are not easily perceived in the ground, so that the difficulty in detecting tunnel geology is increased. Traditional advanced geological detection methods may not accurately detect these bodies, resulting in accidents during construction. Conventional advanced geological detection methods typically detect only at shallow subsurface depths, which may not provide sufficient information for deep buried tunnels. In addition, control of the drilling direction is also a challenge, and conventional methods often cannot precisely control the drilling direction, resulting in limited accuracy of the detection results.
Therefore, in the application, a advanced geological detection sensing prediction system based on long-distance horizontal directional drilling is provided, and geological anomalies possibly existing outside a sensing hole can be detected in a drilling hole.
The system utilizes the electromagnetic wave communication technology between the drill bit and the drill rod to transmit the geological information at the drill bit to the ground in real time, thereby realizing real-time monitoring and adjustment of the drilling direction. The system also adopts various geological detection methods, such as resistivity, natural gamma, sound waves and the like, so as to improve detection accuracy and reliability. The system has the main advantages that geological abnormal bodies such as faults, karst, water cellars and the like can be timely found and avoided in the drilling process, so that the drilling efficiency and the safety are improved.
In one embodiment of the present invention, fig. 1 is a block diagram of a sensing and forecasting system based on advanced geological exploration of long-distance horizontal directional drilling provided in the embodiment of the present invention. As shown in fig. 1, a long-distance horizontal directional drilling-based advanced geological exploration-aware forecasting system 100 according to an embodiment of the present invention includes: a geological resistivity acquisition module 110 for acquiring resistivity at a plurality of predetermined points in time within a predetermined period of time acquired by the drill bit; a data transmission module 120 for transmitting the resistivities of the plurality of predetermined time points to a server through a drill rod electrically connected to the drill bit; a resistivity timing information arrangement module 130, configured to arrange, at the server, resistivities at the plurality of predetermined time points into a resistivity timing input vector according to a time dimension; the resistivity time sequence feature analysis module 140 is configured to perform resistivity time sequence feature extraction and feature autocorrelation strengthening processing on the resistivity time sequence input vector to obtain resistivity time sequence features; and the geological anomaly detection early warning module 150 is used for determining whether geological anomalies exist or not and confirming whether early warning prompt is generated or not based on the resistivity time sequence characteristics.
In the geological resistivity acquisition module 110, the resistivity of a plurality of predetermined points in time acquired by the drill bit over a predetermined period of time is acquired. When the module is used, the drill bit can accurately collect the resistivity data, and the preset time point is reasonably selected so as to fully cover the geological condition of the tunnel. Through geological resistivity acquisition module, can acquire tunnel geology's resistivity information, the resistivity is one of the important characteristics of underground rock mass, can provide the information about geologic body nature and structure, helps knowing the geological environment around the tunnel.
Resistivity refers to the degree of resistance of a formation to current flow, with different types of formations having different resistivity characteristics. By measuring the resistivity between the drill pipe and the formation, the resistivity profile of the subsurface formation can be obtained. The operator can identify different geologic formations from the resistivity data and classify and interpret the formations. For example, a high resistivity may represent a hard formation such as rock or sandstone, while a low resistivity may represent an aquifer or soft soil layer. Through comprehensive analysis of the resistivity data, operators can better understand the properties and the compositions of the stratum, and misjudgment on poor geological conditions is reduced.
In the data transmission module 120, resistivity data at a plurality of predetermined time points is transmitted to a server through a drill pipe. In the transmission process, the accuracy and the integrity of data are ensured, and meanwhile, the stability and the instantaneity of transmission are considered. The data transmission module can rapidly transmit the acquired resistivity data to the server for processing and analysis, so that the underground geological condition can be monitored and evaluated in real time, and potential geological anomalies can be found in time.
In the resistivity timing information arrangement module 130, resistivities at a plurality of predetermined time points are arranged as a resistivity timing input vector in a time dimension on a server. When the arrangement is performed, time continuity and sequence correctness are ensured. Through the resistivity time sequence information arrangement module, the resistivity data at a plurality of time points can be organized according to time sequence to form a resistivity time sequence input vector, so that the time sequence analysis and the processing of the resistivity data are facilitated, and the evolution process of the underground geology is better known.
In the resistivity timing feature analysis module 140, feature extraction and feature autocorrelation enhancement are performed on the resistivity timing input vector to obtain a resistivity timing feature. When the feature analysis is carried out, a proper feature extraction method and an autocorrelation processing algorithm are selected, and the accuracy and reliability of the result are ensured. Through the resistivity time sequence characteristic analysis module, key geological characteristics can be extracted from the resistivity time sequence data, and the characteristics can reflect the change trend and abnormal condition of underground geology, so that further analysis and identification of geological abnormal bodies are facilitated.
In the geological anomaly detection early warning module 150, it is determined whether geological anomalies exist based on the resistivity timing characteristics, and it is confirmed whether an early warning prompt is generated. When geological abnormal body detection and early warning are carried out, reasonable judgment standards and algorithms are required to be established, and accuracy and reliability of results are ensured. The geological abnormal body detection early warning module can judge whether geological abnormal bodies exist underground according to the resistivity time sequence characteristics, and timely generate early warning prompts, so that engineers can timely take corresponding measures, geological disasters are avoided or reduced, and the safety and reliability of tunnel engineering are improved.
The use of the modules can improve the effect of advanced geological detection of the tunnel, provide more accurate and comprehensive geological information, help engineers to better know geological environment around the tunnel, discover geological anomalies in time and take corresponding measures, thereby improving the safety and efficiency of tunnel engineering.
According to the technical scheme, the advanced geological detection sensing prediction system based on the long-distance horizontal directional drilling is provided, geological anomalies possibly existing outside the sensing hole can be detected in the drilling, so that geological detection can be carried out under the condition of not interrupting tunneling, and economic and time costs are reduced. Specifically, by utilizing an electromagnetic wave communication technology between the drill bit and the drill rod, geological information such as resistivity at the drill bit is transmitted to the ground in real time, and a data processing and analyzing algorithm is introduced at the rear end to perform time sequence analysis of the resistivity, so that detection and judgment of geological abnormal bodies are performed, and real-time monitoring and adjustment of the drilling direction are realized. Therefore, geological abnormal bodies such as faults, karst, water cellars and the like can be timely found and avoided in the drilling process, and therefore drilling efficiency and safety are improved.
Specifically, in the technical solution of the present application, first, the resistivity at a plurality of predetermined time points within a predetermined period of time acquired by a drill bit is acquired. It should be understood that resistivity refers to the degree of resistance of a formation to current flow, with different types of formations having different resistivity characteristics. By measuring the resistivity between the drill pipe and the formation, the resistivity profile of the subsurface formation can be obtained, and thus different geological formations can be identified from the resistivity data and the formation can be classified and interpreted. For example, a high resistivity may represent a hard formation such as rock or sandstone, while a low resistivity may represent an aquifer or soft soil layer. By comprehensively analyzing the resistivity data, the property and the composition of the stratum can be better known, and misjudgment on poor geological conditions is reduced. Then, after the resistivity is collected by the drill bit, the resistivities at the plurality of predetermined time points are transmitted to a server through a drill rod electrically connected with the drill bit, so that data processing and analysis can be performed in the server.
Next, considering that the resistivity has a time-sequential dynamic change rule in a time dimension during the detection of the resistivity, that is, the resistivity at the plurality of predetermined time points has a time-sequential association relationship, the resistivity at the plurality of predetermined time points is arranged as a resistivity time-sequential input vector according to the time dimension at the server, so as to integrate the distribution information of the resistivity in time sequence.
Then, since resistivity is a physical property of the subsurface rock or soil, it changes as geological conditions change. By collecting and analyzing resistivity data at a plurality of predetermined time points over a predetermined period of time, the change in resistivity of the subsurface rock or soil over time can be obtained. However, analysis using only the resistivity timing input vector may not intuitively exhibit the timing variation trend of the resistivity. Therefore, in order to better express and analyze the time sequence change of the resistivity, in the technical scheme of the application, the resistivity time sequence input vector is further passed through a vector-image format converter to obtain a resistivity time sequence image. By converting the resistivity timing input vector into the resistivity timing image, the timing data may be converted into a form of an image, thereby more intuitively presenting the timing change of resistivity. Meanwhile, the image has rich information expression capability, and patterns, trends and anomalies of the resistivity data can be captured in a visual mode.
Then, a resistivity time sequence feature extractor based on a convolutional neural network model with excellent performance in terms of implicit feature extraction of the images is used for feature extraction of the resistivity time sequence images so as to extract time sequence feature distribution information about resistivity in the resistivity time sequence images, thereby obtaining a resistivity time sequence feature graph.
In a specific embodiment of the present application, the resistivity timing profile module includes: a format conversion unit for passing the resistivity timing input vector through a vector-image format converter to obtain a resistivity timing image; the resistivity time sequence feature extraction unit is used for carrying out feature extraction on the resistivity time sequence image through a resistivity time sequence feature extractor based on a deep neural network model so as to obtain a resistivity time sequence feature map; and the resistivity time sequence characteristic strengthening unit is used for carrying out characteristic autocorrelation strengthening treatment on the resistivity time sequence characteristic graph to obtain an autocorrelation strengthening expression resistivity time sequence characteristic graph serving as the resistivity time sequence characteristic.
The deep neural network model is a convolutional neural network model.
It should be appreciated that by converting the resistivity timing input vector into a resistivity timing image, the data may be converted from a vector form into a more intuitive and visual image form, which helps engineers more intuitively observe and analyze the resistivity timing data for rules and anomalies therein. By using a feature extractor based on a deep neural network model, important geological features can be extracted from the resistivity time sequence image, and the features can capture the change trend and abnormal situation of underground geology, thereby being beneficial to more accurately identifying and analyzing the geological body. By carrying out characteristic autocorrelation strengthening treatment on the resistivity time sequence characteristic diagram, the correlation between the characteristics can be enhanced, more representative geological characteristics are further extracted, the evolution process and the abnormal condition of underground geology can be described more accurately, and the detection accuracy of geological abnormality is improved.
Converting the resistivity timing data into an image form makes the data easier to understand and analyze. And extracting geological features in the resistivity time sequence image through the deep neural network model, and improving the accuracy and the expression capacity of the features. Through the characteristic autocorrelation strengthening treatment, the correlation among the characteristics is enhanced, and the detection accuracy and reliability of geological anomalies are improved.
The beneficial effects can further improve the effect of advanced geological detection of the tunnel, provide more accurate and comprehensive geological information, help engineers to better understand geological environment around the tunnel, discover geological anomalies in time and take corresponding measures, and improve the safety and efficiency of tunnel engineering.
Further, in geological exploration, since the resistivity time sequence characteristic diagram is a characteristic expression of the resistivity of underground rock or soil with time, the resistivity time sequence characteristic diagram contains rich information, but certain correlation exists between the resistivity characteristics of different underground rock or soil in the resistivity time sequence characteristic diagram. Therefore, in the technical scheme of the application, the resistivity time sequence characteristic diagram needs to be subjected to characteristic autocorrelation strengthening expression processing so as to further strengthen the correlation between the resistivity time sequence characteristics of the underground substances, thereby better capturing the characteristics of geological anomalies. Based on the characteristic, the resistivity time sequence characteristic diagram is further processed through a characteristic autocorrelation strengthening expression module to obtain an autocorrelation strengthening expression resistivity time sequence characteristic diagram. It should be understood that the characteristic autocorrelation enhancement module can measure the correlation between different time points in the time series data, that is, by performing autocorrelation operation on the resistivity time series characteristic diagram, the correlation strength of the resistivity of the underground material between different time points can be calculated, and the information can be fused into the characteristic diagram. Meanwhile, through autocorrelation enhancement, important relevant features in time sequence data can be highlighted, noise and irrelevant information are restrained, and therefore the expression capacity and distinguishing degree of the features are improved. This helps to more accurately capture the time-series-related characteristics of the resistivity of different substances in the subsurface, thereby improving the discrimination and discrimination of geologic anomalies and reducing the possibility of erroneous and missed decisions.
In one specific embodiment of the present application, the resistivity timing feature reinforcing unit is configured to: and the resistivity time sequence characteristic diagram is subjected to a characteristic autocorrelation strengthening expression module to obtain the autocorrelation strengthening expression resistivity time sequence characteristic diagram.
Feature autocorrelation enhancement is a processing method that enhances the expressive power of features by calculating the correlation between features. By applying the characteristic autocorrelation strengthening treatment, the correlation between the characteristics in the resistivity time sequence characteristic diagram can be enhanced, the evolution process and the abnormal condition of underground geology can be better captured, and the reliability and the accuracy of the geological characteristics can be improved. The self-correlation strengthening expression resistivity time sequence characteristic diagram can better highlight the characteristics of the geological abnormal body, and the self-correlation strengthening treatment can highlight the unique characteristics of the abnormal body, so that the characteristic diagram is more obvious and remarkable, engineers can be helped to detect and identify geological abnormality more easily, corresponding measures can be taken early, and the safety and reliability of tunnel engineering are improved. The feature autocorrelation strengthening treatment can reduce the possibility of misjudgment, can reduce misinformation caused by noise or other uncorrelated factors by strengthening the correlation among the features, is beneficial to improving the detection accuracy of geological anomalies and reducing the risk of false alarm, so that engineers can judge the underground geological conditions more accurately.
The characteristic self-correlation strengthening expression module is used for processing the resistivity time sequence characteristic diagram, so that the correlation between the characteristics can be enhanced, the geological abnormality detection capability is improved, and the misjudgment rate is reduced. The method has the beneficial effects that engineers can better understand the underground geological environment, timely find geological anomalies and take corresponding measures, and the safety and efficiency of tunnel engineering are improved.
And then, the self-correlation enhanced expression resistivity time sequence characteristic diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether geological anomalies exist or not. That is, the classification processing is performed by the time series characteristic distribution information on the resistivity after the characteristic autocorrelation correlation reinforcement expression processing, so that the detection of the geological abnormality which may exist outside the sensing hole is performed in the borehole. Therefore, geological abnormal bodies possibly existing outside the sensing hole can be detected in the drilled hole in real time, so that geological detection can be carried out under the condition of not interrupting tunneling, economic and time costs are reduced, early warning prompts are timely sent out when abnormal bodies are detected, and drilling efficiency and safety are improved.
In a specific embodiment of the present application, the geological anomaly detection early warning module includes: the geological anomaly detection unit is used for enabling the autocorrelation reinforced expression resistivity time sequence feature diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether geological anomalies exist or not; and the early warning prompt generation unit is used for confirming whether to generate an early warning prompt or not based on the classification result.
By inputting the self-correlation enhanced expression resistivity time sequence characteristic diagram into the classifier, the geological anomaly detection unit can carry out classification judgment on geological anomalies, and the classification result is used for indicating whether geological anomalies exist or not, namely judging whether the underground geological environment is different from the normal condition or not, so that engineers can be helped to timely identify and position the geological anomalies, and important reference information is provided so as to take corresponding measures to cope with potential risks.
The early warning prompt generation unit confirms whether to generate an early warning prompt or not based on the classification result of the geological abnormal body detection unit. When the classification result shows that the geological abnormal body exists, the early warning prompt generation unit can generate a corresponding early warning prompt to give a warning to engineers, so that the engineers are reminded of paying attention to possible geological risks, preventive or countermeasures are timely taken, and the safety and stability of tunnel engineering are ensured.
The geological abnormal body detection unit classifies the autocorrelation reinforced expression resistivity time sequence characteristic diagram through a classifier, and judges whether geological abnormal bodies exist or not. The early warning prompt generation unit generates corresponding early warning prompts according to the classification results to remind engineers of paying attention to potential geological risks, and the beneficial effects are beneficial to the engineers to timely find and cope with underground geological anomalies, so that the safety and efficiency of tunnel engineering are improved, and potential risks and losses are reduced.
In one embodiment of the present application, the advanced geological exploration sensing prediction system based on long-distance horizontal directional drilling further comprises a training module for training the resistivity time sequence feature extractor based on the convolutional neural network model, the feature autocorrelation strengthening expression module and the classifier. The training module comprises: a training geological resistivity acquisition unit for acquiring training resistivities at a plurality of predetermined time points within a predetermined period of time acquired by the drill bit, and whether a true value of a geological anomaly exists; the training data transmission unit is used for transmitting the training resistivities of the preset time points to a training server through a drill rod electrically connected with the drill bit; the training resistivity time sequence information arrangement unit is used for arranging the training resistivities of the plurality of preset time points into training resistivity time sequence input vectors according to a time dimension at the training server; the training format conversion unit is used for enabling the training resistivity time sequence input vector to pass through the vector-image format converter so as to obtain a training resistivity time sequence image; the training resistivity time sequence feature extraction unit is used for carrying out feature extraction on the training resistivity time sequence image through a resistivity time sequence feature extractor based on a deep neural network model so as to obtain a training resistivity time sequence feature map; the training resistivity time sequence characteristic strengthening unit is used for carrying out characteristic autocorrelation strengthening treatment on the training resistivity time sequence characteristic graph to obtain a training autocorrelation strengthening expression resistivity time sequence characteristic graph serving as the resistivity time sequence characteristic; the training optimization unit is used for optimizing the position-by-position characteristic values of the training autocorrelation reinforced expression resistivity time sequence characteristic diagram to obtain an optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram; the training geological anomaly detection unit is used for enabling the optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram to pass through a classifier to obtain a classification loss function value; and the training unit is used for training the resistivity time sequence feature extractor, the feature autocorrelation strengthening expression module and the classifier based on the convolutional neural network model based on the classification loss function value.
In particular, in the technical scheme of the application, after the training resistivity time sequence image passes through the resistivity time sequence feature extractor based on the convolutional neural network model, each feature matrix of the obtained training resistivity time sequence feature image expresses the local time domain-local time domain resistivity time sequence correlation feature under the local time domain determined by the global time domain through vector-image format conversion, and each feature matrix accords with the channel distribution of the convolutional neural network model, so after the training resistivity time sequence feature image passes through the feature autocorrelation enhancement expression module, the channel dimension can be restrained based on the local time domain-local time domain time sequence correlation of the feature matrix on the space distribution dimension, and the training autocorrelation enhancement expression resistivity time sequence feature image integrally has the multi-scale time sequence correlation feature distribution based on the global-local time domain.
However, considering that the multi-scale time-sequence-associated feature distribution difference brings local feature distribution sparsification to the overall feature representation of the training autocorrelation enhanced expression resistivity time sequence feature graph, namely, the sub-manifold is thinned out of the distribution relative to the overall high-dimensional feature manifold, the method can cause poor convergence of the training autocorrelation enhanced expression resistivity time sequence feature graph to the predetermined class probability class representation in the probability space when the training autocorrelation enhanced expression resistivity time sequence feature graph is subjected to class probability regression mapping through a classifier, and the accuracy of the classification result is affected.
Therefore, preferably, the training autocorrelation reinforced expression resistivity time sequence feature map is optimized by position feature value, specifically: optimizing the position-by-position characteristic values of the training autocorrelation reinforced expression resistivity time sequence characteristic diagram by using the following optimization formula to obtain an optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram; wherein, the optimization formula is:
wherein,is the training autocorrelation reinforced expression resistivity time sequence characteristic diagram +.>Characteristic value of>Is the characteristic value of the optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram, +.>Representing the calculation of a value of a natural exponent function that is a power of a value.
That is, sparse distribution in high-dimensional feature space is processed by regularization based on heavy probabilities to activate the training autocorrelation-enhanced representation resistivity timing feature mapNatural distribution transfer of geometric manifold into probability space in high-dimensional feature space, thereby enhancing expression of resistivity timing feature map by autocorrelation of the training +.>The method for carrying out the re-probability-based smoothing regularization on the distributed sparse sub-manifold of the high-dimensional characteristic manifold improves the class convergence of the complex high-dimensional characteristic manifold with high space sparsity under the predetermined class probability, thereby improving the training autocorrelation reinforced expression resistivity time sequence characteristic diagram->The accuracy of the classification result obtained by the classifier. Therefore, geological abnormal bodies possibly existing outside the sensing hole can be detected in real time in the drilling hole, and early warning prompt is timely sent out when the abnormal bodies are detected.
In a specific embodiment of the present application, the training geological anomaly detection unit is configured to: the classifier processes the optimized training autocorrelation reinforced expression resistivity timing feature diagram with a training classification formula to generate a training classification result, wherein the classification formula is:
wherein->Representing projection of the optimized training autocorrelation reinforced expression resistivity timing feature diagram as a vector, +.>To->Is a weight matrix>To->Representing a bias matrix; and calculating a cross entropy value between the training classification result and a true value as the classification loss function value.
In summary, the advanced geological detection sensing prediction system 100 based on long-distance horizontal directional drilling according to the embodiment of the present invention is illustrated, which transmits geological information, such as resistivity, at the drill bit to the ground in real time by using an electromagnetic wave communication technology between the drill bit and the drill rod, and introduces a data processing and analysis algorithm at the rear end to perform time sequence analysis of the resistivity, so as to perform detection and judgment of geological anomalies, thereby realizing real-time monitoring and adjustment of the drilling direction. Therefore, geological abnormal bodies such as faults, karst, water cellars and the like can be timely found and avoided in the drilling process, and therefore drilling efficiency and safety are improved.
As described above, the advanced geological exploration awareness forecasting system 100 based on long-distance horizontal directional drilling according to the embodiment of the present invention may be implemented in various terminal devices, such as a server or the like for advanced geological exploration awareness forecasting based on long-distance horizontal directional drilling. In one example, the long-range horizontal directional drilling-based advanced geological exploration awareness forecasting system 100 may be integrated into the terminal device as a software module and/or hardware module in accordance with an embodiment of the present invention. For example, the long-range horizontal directional drilling-based advanced geological exploration awareness forecasting system 100 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the advanced geological exploration awareness forecasting system 100 based on long-range horizontal directional drilling can also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the long-range horizontal directional drilling-based advanced geological exploration awareness forecasting system 100 and the terminal device may be separate devices, and the long-range horizontal directional drilling-based advanced geological exploration awareness forecasting system 100 may be connected to the terminal device through a wired and/or wireless network and communicate interactive information in accordance with a agreed data format.
Fig. 2 is a flowchart of a method for advanced geological exploration sensing prediction based on long-distance horizontal directional drilling provided in an embodiment of the invention. Fig. 3 is a schematic diagram of a system architecture based on a long-distance horizontal directional drilling advanced geological exploration sensing prediction method according to an embodiment of the present invention. As shown in fig. 2 and 3, a sensing and forecasting method based on advanced geological exploration of long-distance horizontal directional drilling includes: 210, acquiring resistivity at a plurality of preset time points in a preset time period acquired by a drill bit; 220 transmitting the resistivity of the plurality of predetermined points in time to a server through a drill pipe electrically connected to the drill bit; 230, at the server, arranging the resistivities of the plurality of predetermined time points into a resistivity timing input vector according to a time dimension; 240, carrying out resistivity time sequence feature extraction and feature autocorrelation strengthening treatment on the resistivity time sequence input vector to obtain resistivity time sequence features; 250, based on the resistivity timing characteristics, determining whether a geological anomaly exists and confirming whether an early warning prompt is generated.
It will be appreciated by those skilled in the art that the specific operation of each step in the above-described advanced geological exploration and perception forecasting method based on long-distance horizontal directional drilling has been described in detail in the above description of the advanced geological exploration and perception forecasting system based on long-distance horizontal directional drilling with reference to the drawings, and thus, repetitive description thereof will be omitted.
Fig. 4 is an application scenario diagram of a advanced geological detection sensing prediction system based on long-distance horizontal directional drilling provided by the embodiment of the invention. As shown in fig. 4, in this application scenario, first, the resistivities at a plurality of predetermined time points within a predetermined period of time acquired by the drill bit are acquired (e.g., C as illustrated in fig. 4); the acquired resistivity is then input into a server (e.g., S as illustrated in fig. 4) deployed with a long-range horizontal directional drill-based advanced geological exploration, perception and prediction algorithm, wherein the server is capable of processing the resistivity based on the long-range horizontal directional drill-based advanced geological exploration, perception and prediction algorithm to determine whether geological anomalies are present and to confirm whether an early warning prompt is generated.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (3)
1. An advanced geological detection sensing and forecasting system based on a long-distance horizontal directional drill is characterized by comprising the following steps:
a geological resistivity acquisition module for acquiring resistivity at a plurality of predetermined time points within a predetermined time period acquired by the drill bit;
the data transmission module is used for transmitting the resistivities of the preset time points to a server through a drill rod electrically connected with the drill bit;
the resistivity time sequence information arrangement module is used for arranging the resistivities of the plurality of preset time points into a resistivity time sequence input vector according to a time dimension at the server;
the resistivity time sequence feature analysis module is used for carrying out resistivity time sequence feature extraction and feature autocorrelation strengthening treatment on the resistivity time sequence input vector so as to obtain resistivity time sequence features;
the geological abnormal body detection early warning module is used for determining whether geological abnormal bodies exist or not and confirming whether early warning prompts are generated or not based on the resistivity time sequence characteristics;
wherein, the resistivity timing profile module comprises:
a format conversion unit for passing the resistivity timing input vector through a vector-image format converter to obtain a resistivity timing image;
the resistivity time sequence feature extraction unit is used for carrying out feature extraction on the resistivity time sequence image through a resistivity time sequence feature extractor based on a deep neural network model so as to obtain a resistivity time sequence feature map;
the resistivity time sequence characteristic strengthening unit is used for carrying out characteristic autocorrelation strengthening treatment on the resistivity time sequence characteristic graph to obtain an autocorrelation strengthening expression resistivity time sequence characteristic graph as the resistivity time sequence characteristic;
wherein, the resistivity time sequence characteristic strengthening unit is used for: the resistivity time sequence characteristic diagram is subjected to a characteristic autocorrelation strengthening expression module to obtain the autocorrelation strengthening expression resistivity time sequence characteristic diagram;
wherein, geological anomaly detection early warning module includes:
the geological anomaly detection unit is used for enabling the autocorrelation reinforced expression resistivity time sequence feature diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether geological anomalies exist or not;
the early warning prompt generation unit is used for confirming whether to generate an early warning prompt or not based on the classification result;
the device comprises a convolutional neural network model, a resistivity time sequence feature extractor, a feature autocorrelation strengthening expression module and a classifier, wherein the resistivity time sequence feature extractor, the feature autocorrelation strengthening expression module and the classifier are used for training the resistivity time sequence feature extractor, the feature autocorrelation strengthening expression module and the classifier based on the convolutional neural network model;
wherein, training module includes:
a training geological resistivity acquisition unit for acquiring training resistivities at a plurality of predetermined time points within a predetermined period of time acquired by the drill bit, and whether a true value of a geological anomaly exists;
the training data transmission unit is used for transmitting the training resistivities of the preset time points to a training server through a drill rod electrically connected with the drill bit;
the training resistivity time sequence information arrangement unit is used for arranging the training resistivities of the plurality of preset time points into training resistivity time sequence input vectors according to a time dimension at the training server;
the training format conversion unit is used for enabling the training resistivity time sequence input vector to pass through the vector-image format converter so as to obtain a training resistivity time sequence image;
the training resistivity time sequence feature extraction unit is used for carrying out feature extraction on the training resistivity time sequence image through a resistivity time sequence feature extractor based on a deep neural network model so as to obtain a training resistivity time sequence feature map;
the training resistivity time sequence characteristic strengthening unit is used for carrying out characteristic autocorrelation strengthening treatment on the training resistivity time sequence characteristic graph to obtain a training autocorrelation strengthening expression resistivity time sequence characteristic graph serving as the resistivity time sequence characteristic;
the training optimization unit is used for optimizing the position-by-position characteristic values of the training autocorrelation reinforced expression resistivity time sequence characteristic diagram to obtain an optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram;
the training geological anomaly detection unit is used for enabling the optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram to pass through a classifier to obtain a classification loss function value;
the training unit is used for training the resistivity time sequence feature extractor, the feature autocorrelation strengthening expression module and the classifier based on the convolutional neural network model based on the classification loss function value;
the training autocorrelation reinforced expression resistivity time sequence characteristic diagram is subjected to position-by-position characteristic value optimization, and specifically comprises the following steps: optimizing the position-by-position characteristic values of the training autocorrelation reinforced expression resistivity time sequence characteristic diagram by using the following optimization formula to obtain an optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram; the optimization formula is as follows:
wherein (1)>Is the training autocorrelation reinforced expression resistivity time sequence characteristic diagram +.>Characteristic value of>Is the characteristic value of the optimized training autocorrelation reinforced expression resistivity time sequence characteristic diagram, +.>Representing the calculation of a value of a natural exponent function that is a power of a value.
2. The advanced geological exploration-aware forecast system based on long-range horizontal directional drilling of claim 1, wherein said deep neural network model is a convolutional neural network model.
3. The advanced geological exploration sensing forecast system based on long-distance horizontal directional drilling according to claim 2, wherein the training geological anomaly detection unit is configured to:
the classifier processes the optimized training autocorrelation reinforced expression resistivity timing feature diagram with a training classification formula to generate a training classification result, wherein the classification formula is:
wherein->Representing projection of the optimized training autocorrelation reinforced expression resistivity timing feature diagram as a vector, +.>To->Is a weight matrix>To->Representing a bias matrix; and
and calculating a cross entropy value between the training classification result and a true value as the classification loss function value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311486605.1A CN117214958B (en) | 2023-11-09 | 2023-11-09 | Advanced geological detection sensing and forecasting system based on long-distance horizontal directional drilling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311486605.1A CN117214958B (en) | 2023-11-09 | 2023-11-09 | Advanced geological detection sensing and forecasting system based on long-distance horizontal directional drilling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117214958A CN117214958A (en) | 2023-12-12 |
| CN117214958B true CN117214958B (en) | 2024-01-26 |
Family
ID=89044815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311486605.1A Active CN117214958B (en) | 2023-11-09 | 2023-11-09 | Advanced geological detection sensing and forecasting system based on long-distance horizontal directional drilling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117214958B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6603313B1 (en) * | 1999-09-15 | 2003-08-05 | Exxonmobil Upstream Research Company | Remote reservoir resistivity mapping |
| CN102495428A (en) * | 2011-12-12 | 2012-06-13 | 山东大学 | Resistivity real-time imaging monitoring method and system for water-bursting geological disaster in construction period of underground engineering |
| CN106907145A (en) * | 2017-02-09 | 2017-06-30 | 武汉地大华睿地学技术有限公司 | A kind of apparent resistivity measuring system and method with brill advanced prediction |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6534986B2 (en) * | 2000-05-01 | 2003-03-18 | Schlumberger Technology Corporation | Permanently emplaced electromagnetic system and method for measuring formation resistivity adjacent to and between wells |
| CN112647965B (en) * | 2020-12-09 | 2022-03-04 | 山东大学 | Method and system suitable for real-time card-blocking prediction of TBM tunneling tunnel |
| CN113156518B (en) * | 2021-04-20 | 2022-07-08 | 中国矿业大学 | Real-time advanced detection method for vector resistivity of water-containing disaster body |
-
2023
- 2023-11-09 CN CN202311486605.1A patent/CN117214958B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6603313B1 (en) * | 1999-09-15 | 2003-08-05 | Exxonmobil Upstream Research Company | Remote reservoir resistivity mapping |
| CN102495428A (en) * | 2011-12-12 | 2012-06-13 | 山东大学 | Resistivity real-time imaging monitoring method and system for water-bursting geological disaster in construction period of underground engineering |
| CN106907145A (en) * | 2017-02-09 | 2017-06-30 | 武汉地大华睿地学技术有限公司 | A kind of apparent resistivity measuring system and method with brill advanced prediction |
Non-Patent Citations (3)
| Title |
|---|
| Advanced geological detection instrument for TBM tunneling based on AC induced polarization method;Haojie Jian 等;2016 12th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA);全文 * |
| 巷道快速智能掘进超前探测技术与发展;张平松 等;煤炭学报;第46卷(第7期);第2158-2173页 * |
| 矿井巷道震电联合超前探测原理及应用;张修峰;;江苏建筑职业技术学院学报;第15卷(第04期);第13-17页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117214958A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110109895B (en) | Surrounding rock grading combined prediction method suitable for TBM tunneling tunnel and application | |
| CN102930253B (en) | Coal and rock identification method based on image discrete multi-wavelet transform | |
| AU2013277928B2 (en) | Systems and methods for processing geophysical data | |
| Li et al. | Abnormality detection for drilling processes based on Jensen–Shannon divergence and adaptive alarm limits | |
| CN104373153A (en) | Coal and rock property identification method and system for underground coal mine full-mechanized caving face | |
| CN116256803B (en) | Coal mine microseismic region positioning method integrating mining information and geological information | |
| CN111396035B (en) | Method for identifying interface and resistivity of coal bed and surrounding rock based on electromagnetic measurement while drilling signal | |
| CN115128663A (en) | Mine safety production detection system based on Internet of things and detection method thereof | |
| CN117214958B (en) | Advanced geological detection sensing and forecasting system based on long-distance horizontal directional drilling | |
| Li et al. | Waveform recognition and process interpretation of microseismic monitoring based on an improved LeNet5 convolutional neural network | |
| CN116044501A (en) | Advanced geological forecast dynamic monitoring and early warning system and method | |
| CN109598049B (en) | Method for drilling rock fracture development degree and regional rock fracture development rule | |
| CN114118166A (en) | Transformer fault diagnosis system and method based on intelligent frequency spectrum monitoring | |
| CN105204066A (en) | Spectral decomposition-based method for directly indicating intrusion position of igneous rock into coal seam | |
| CN112927767A (en) | Multi-element geochemical anomaly identification method based on graph attention self-coding | |
| CN104933199A (en) | Geological big data fusion system and method based on trusted mechanism | |
| CN112712484B (en) | Method for delineating goaf resistivity image anomalies by adopting fuzzy mathematical theory | |
| CN113466951B (en) | Mine electrical method resistivity abnormal response monitoring rapid identification method | |
| CN117590465A (en) | Advanced geological detection method and device carried on ultra-large diameter slurry shield | |
| Hu et al. | Discriminator of mining blasts and microseismic events based on multi-scale discrete wavelet transform | |
| CN117350543A (en) | Underground water permeability accident prediction method based on AI algorithm and distributed hydrological sensor | |
| CN117593853A (en) | Geological disaster auxiliary monitoring system and method based on change of through-the-earth communication signals | |
| Geng et al. | A Kriging-Random Forest Hybrid Model for Real-time Ground Property Prediction during Earth Pressure Balance Shield Tunneling | |
| Nair et al. | Integration of Ground-Penetrating Radar and Artificial Intelligence for Soil Piping-A Review | |
| Zhou et al. | Quantitative Risk Assessment of Rock Tunnel Faces Using Stacked Deep Learning and Multi-Source Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |