AU2020342222A1 - Predicting system and method for quartz content of surrounding rock in tunnel based on image identification and analysis - Google Patents
Predicting system and method for quartz content of surrounding rock in tunnel based on image identification and analysis Download PDFInfo
- Publication number
- AU2020342222A1 AU2020342222A1 AU2020342222A AU2020342222A AU2020342222A1 AU 2020342222 A1 AU2020342222 A1 AU 2020342222A1 AU 2020342222 A AU2020342222 A AU 2020342222A AU 2020342222 A AU2020342222 A AU 2020342222A AU 2020342222 A1 AU2020342222 A1 AU 2020342222A1
- Authority
- AU
- Australia
- Prior art keywords
- surrounding rock
- quartz
- drive link
- quartz content
- image
- 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.)
- Granted
Links
- 239000011435 rock Substances 0.000 title claims abstract description 109
- 239000010453 quartz Substances 0.000 title claims abstract description 108
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 title claims abstract description 12
- 230000001681 protective effect Effects 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 11
- 238000005286 illumination Methods 0.000 claims description 7
- 238000013459 approach Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 description 11
- 238000009412 basement excavation Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 6
- 229910052500 inorganic mineral Inorganic materials 0.000 description 6
- 239000011707 mineral Substances 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000002441 X-ray diffraction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 239000005341 toughened glass Substances 0.000 description 2
- IPWKGIFRRBGCJO-IMJSIDKUSA-N Ala-Ser Chemical compound C[C@H]([NH3+])C(=O)N[C@@H](CO)C([O-])=O IPWKGIFRRBGCJO-IMJSIDKUSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Electromagnetism (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
An image identification and analysis-based system and method for predicting the quartz content of surrounding rock in a tunnel, the system comprising: a base (1) for fixation with a tunnel boring machine, an image acquisition module, a first driving connecting rod (2) and a sixth driving connecting rod (15) that are retractable, a control module and a quartz content prediction module, wherein the base (1) is connected to the image acquisition module by means of the first driving connecting rod (2), and a rod body of the first driving connecting rod (2) and the base (1) are connected one to the other by means of the sixth driving connecting rod (15); and the control module is used to send control instructions to the first driving connecting rod (2), the sixth driving connecting rod (15) and the image acquisition module, receive surrounding rock images transmitted by the image acquisition module, and send the images to the quartz content prediction module for quartz content prediction. The system is highly flexible, may acquire surrounding rock images of the entire tunnel space, and quickly obtain the quartz content on the basis of the surrounding rock images.
Description
Field of the Invention The present disclosure belongs to the technical field of quartz content test of the surrounding rock in tunnels, and particularly relates to a predicting system and method for the quartz content of the surrounding rock in a tunnel based on image identification and analysis.
Background of the Invention The statement of this section merely provides background art information related to the present disclosure, and does not necessarily constitute the prior art. Using Tunnel Boring Machines (TBMs) to excavate tunnels has the advantages of fast excavation speed, small disturbance to surrounding rock, good construction safety, high comprehensive benefits, etc. TBMs have become the most promising mechanical equipment for tunnel excavation, and have been widely used in tunnel projects such as highway tunnels, railway tunnels, and diversion tunnels. Prediction of TBM excavation speed and excessive wear of tools are important problems gradually revealed in TBM construction. The wear of a TBM tool is not only a material feature, but also relates to the wear process of interaction between the tool and the rock. Quartz minerals in the rock are one of the main reasons that cause the wear of a TBM cutter head and restrict the TBM excavation speed. Timely grasp of the surrounding rock status and reasonable predictions on tool status and excavation speed are important guarantees for the quality and construction progress of TBM tunnel excavation. At present, the quartz content in the rock is mainly measured by X-ray diffraction (XRD) or a near-infrared mineral analyzer, but these testing methods have the following defects: (1) the test results are inaccurate, for example, when the quartz content is measured by the XRD technology, less than half a gram of sample is measured each time, so the too little test sample cannot fully reflect the content of quartz in the surrounding rock, which is also concluded from the near-infrared mineral analyzer; (2) a test takes a long time, such as several minutes or even tens of minutes for the XRD technology; (3) too much preparation is needed, the preparation of samples is complicated, and the rock needs to be ground into rock powder before the quartz content is measured by the XRD technology, because the particle size is strictly limited; (4) manually operating, each test requires manual operation on instruments; and (5) data analysis and processing are complex, and the test results are often not mineral content but mineral spectra, which requires professional software and experienced engineers to perform data analysis. It can be seen from the above that the existing quartz content detection technology cannot meet real-time, unmanned, and rapid quartz content detection requirements in tunnels.
Summary of the Invention In order to overcome the above deficiencies of the prior art, the present disclosure provides a predicting system and method for the quartz content of the surrounding rock in a tunnel based on image identification and analysis, which can obtain a total-space surrounding rock image of the tunnel and quickly obtain the quartz content on the basis of the surrounding rock image. In order to achieve the above objective, one or more embodiments of the present disclosure provide the following technical solutions: A predicting system for the quartz content of the surrounding rock in a tunnel based on image identification and analysis, including: a base for fixing with a tunnel boring machine, an image acquisition module, a telescopic first drive link, a telescopic sixth drive link, a control module, and a quartz content prediction module; wherein the base is connected with the image acquisition module by the first drive link, and a rod body of the first drive link and the base are connected by the sixth drive link; the control module is configured to send control instructions to the first drive link, the sixth drive link and the image acquisition module, and receive a surrounding rock image transmitted by the image acquisition module, and send the surrounding rock image to the quartz content prediction module for quartz content prediction. Further, the image acquisition module is arranged in a protective box, and the protective box is connected with the first drive link by a connector. Further, the image acquisition module includes an industrial camera, a shooting base and a plurality of telescopic drive links, wherein the industrial camera is fixed in the center of the shooting base, and the lower surface of the shooting base is connected with the protective box by the plurality of telescopic drive links. Further, a plurality of laser range finders and a plurality of Led lights are further arranged around the industrial camera on the shooting base. Further, an illuminometer is further arranged on the protective box, and the two are connected by a telescopic third drive link. One or more embodiments provide a predicting method for the quartz content of the surrounding rock in a tunnel based on the system, including the following steps: the control module sends control instructions to the first drive link, the sixth drive link, and the plurality of drive links in the protective box respectively, to adjust the positional relationship between the image acquisition module and the surrounding rock; and the control module sends a shooting instruction to the industrial camera to obtain an image and sends the image to the quartz content prediction module for quartz content prediction. Further, during the process of adjusting the positional relationship between the image acquisition module and the surrounding rock, the control module receives distance data sent by the plurality of laser range finders, determines whether the shooting base and the surrounding rock are kept relatively parallel, and if not, continues to adjust the positional relationship between the image acquisition module and the surrounding rock. Further, if the shooting base and the surrounding rock are kept relatively parallel, the control module sends a control instruction to the third drive link, to control the illuminometer to approach the surrounding rock; the control module receives illumination data collected by the illuminometer, determines whether the illumination intensity meets a preset standard, and if not meet, sends a brightness adjustment instruction to the Led lights; and if meets, the control module sends a shooting instruction to the industrial camera. Further, there are six laser range finders, and determining whether the shooting base and the surrounding rock are kept relatively parallel includes: calculates whether ,( - 706 702 -- 5705+703 -5704) is less than a set threshold, and if so, considers that the shooting base and the surrounding rock are kept relatively parallel, where 6701 to 6706are the distances from the surrounding rock detected by the six laser range finders, respectively. Further, the quartz content prediction includes the following steps: inputs the image into a Faster Region-Convolutional Neural Network (R-CNN) model to obtain candidate region boxes of quartz; for each candidate region box of quartz, marks pixels with gray values greater than a threshold as growing seed points of a quartz region, and obtaining a quartz region in the candidate region box on the basis of a region growing method; counts the number of pixels in all the quartz regions of each candidate region box, and obtains a quartz feature vector of the surrounding rock image by combining a pre-measured rock density of the surrounding rock; and inputs the quartz feature vector into a pre-trained quartz content prediction model to obtain the quartz content. One or more of the above technical solutions have the following beneficial effects: The present disclosure provides an image data acquisition system with high flexibility, in which the distance from the surrounding rock is adjusted by means of the first drive link connected between the base and the image acquisition module, and the angle is adjusted by means of the sixth drive link connected between the base and the first drive link; further, a plurality of drive links are arranged between the image acquisition module and the protective box, to realize fine adjustment of the shooting angle, which can obtain high-quality images, thereby providing a guarantee for subsequent accurate calculation of the quartz content. In combination with the construction characteristics of TBM, the exposed surrounding rock just excavated is shot and calculated, without collection, secondary processing and grinding, so on-site shooting and on-site calculation can be achieved; and automatic operation is achieved, without artificial attendant, thereby saving labor, reducing construction risks and reducing engineering costs. The quartz content prediction method proposed by the present disclosure accurately extracts the location of quartz in the image on the basis of a Faster R-CNN and a region growing method, and comprehensively considers the quartz quantity and the density of the surrounding rock to construct the feature vector, which ensures the strong correlation between the feature vector and the quartz content and boosts the prediction accuracy of the quartz content. The quartz content of the surrounding rock is tested in real time, and it takes less than 1 minute from shooting to calculation of an image each time, which can meet the requirements of rapid construction for the acquisition of the surrounding rock parameters, and does not require secondary processing for data, and the status of the surrounding rock can be quickly grasped by general construction personnel.
Brief Description of the Drawings The accompanying drawings constituting a part of the present disclosure are used for providing a further understanding of the present disclosure, and the schematic embodiments of the present disclosure and the descriptions thereof are used for interpreting the present disclosure, rather than constituting improper limitations to the present disclosure. FIG. 1 is a schematic frame diagram of a predicting system for the quartz content of the surrounding rock in a tunnel according to one or more embodiments of the present disclosure;
FIG. 2 is a schematic diagram of an image acquisition module and a mechanical module in the predicting system for the quartz content of the surrounding rock in a tunnel according to one or more embodiments of the present disclosure; FIG. 3 is a schematic layout diagram of Led lights and laser range finders according to one or more embodiments of the present disclosure; FIG. 4 is a schematic diagram showing the positional relationship between the devices and the surrounding rock when the predicting system for the quartz content of the surrounding rock in a tunnel is used according to one or more embodiments of the present disclosure; FIG. 5 is a flowchart of an algorithm for a quartz content prediction module according to one or more embodiments of the present disclosure. In which: 1. Base, 2. First drive link, 3. Connecting block, 4. Second drive link, 5. Shooting base, 6. Transparent tempered glass, 701. Laser range finder I, 702. Laser range finder II, 703. Laser range finder III, 704. Laser range finder IV, 705. Laser range finder V, 706. Laser range finder VI, 8. Industrial camera, 9. Led light, 10. Illuminometer, 11. Third drive link, 12. Protective box, 13. Fourth drive link, 14. Fifth drive link, 15. Sixth drive link, 16. Surrounding rock.
Detailed Description of the Embodiments It should be pointed out that the following detailed descriptions are all exemplary and aim to further illustrate the present disclosure. Unless otherwise specified, all technical and scientific terms used in the descriptions have the same meanings generally understood by those of ordinary skill in the art of the present disclosure. It should be noted that the terms used herein are merely for describing specific embodiments, but are not intended to limit exemplary embodiments according to the present disclosure. As used herein, unless otherwise clearly stated in the context, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "include" and/or "comprise" are used in the specification, they indicate features, steps, operations, devices, components, and/or combinations thereof. The embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflicts. One or more embodiments of the present disclosure disclose a predicting system for the quartz content of the surrounding rock in a tunnel based on image identification and analysis, as shown in FIG. 1, including: a control module, a fixing module, an image acquisition module, and a quartz content prediction module.
As shown in FIG. 2 and FIG. 3, the fixing module includes a base 1, a first drive link 2, a connecting block 3, and a sixth drive link 15. The base 1 is used to fix the main body of the system on a TBM; the protective box 12 is a hollow shell with an image acquisition module body inside, and the upper end surface of the protective box 12 is a transparent cover, specifically transparent tempered glass 6, which can meet the shooting requirements of an industrial camera. The protective box 12 is used to protect components of the image acquisition module from being damaged by the falling rock. The first drive link 2 can freely extend and retract to connect with the connecting block 3 and the base 1 respectively. Specifically, the first drive link 2 is a telescopic rod, which is a two-stage telescopic rod in this embodiment and is composed of an outer telescopic rod and an inner telescopic rod. One end of the outer telescopic rod of the first drive link 2 is rotatably connected to the base 1, and one end of the inner telescopic rod is connected to the bottom surface of the protective box 12 by the connecting block 3. The distance between the image acquisition module in the protective box 12 and the surrounding rock can be adjusted by adjusting the extension and retraction of the first drive link 2. A sixth drive link 15 is further arranged between the base 1 and the first drive link 2. The sixth drive link 15 is also configured as a telescopic rod, which is a two-stage telescopic rod in this embodiment and is composed of an outer telescopic rod and an inner telescopic rod. One end of the outer telescopic rod of the sixth drive link 15 is rotatably connected with the base 1, and one end of the inner telescopic rod is hinged to a rod body of the outer telescopic rod of the first drive link 2. The angle of the protective box 12 relative to the base 1 can be adjusted by adjusting the extension and retraction of the sixth drive link 15, so that the image acquisition module rotates within the cross section of the tunnel, thereby expanding the range of shooting. The image acquisition module inside the protective box 12 includes a second drive link 4, ashooting base 5, alaserrange finderI701, alaserrange finderII702, alaser range finder III703, a laser range finder IV 704, a laser range finder V 705, a laser range finder VI 706, an industrial camera 8, Led lights 9, an illuminometer 10, a third drive link 11, a fourth drive link 13, and a fifth drive link 14. The industrial camera 8 is arranged on the shooting base 5, and the shooting base 5 is connected to the bottom surface of the protective box 12 by the second drive link 4, the fourth drive link 13, and the fifth drive link 14. The second drive link 4, the fourth drive link 13, and the fifth drive link 14 are all telescopic rods, which are all two-stage telescopic rods in this embodiment, including an outer telescopic rod and an inner telescopic rod. One ends of the outer telescopic rods of the second drive link 4, the fourth drive link 13 and the fifth drive link 14 are fixed on the bottom surface of the protective box 12, and one ends of the inner telescopic rods are hinged to the bottom surface of the shooting base. The shooting base can be controlled to rotate within a certain range by adjusting the telescopic degrees of the three telescopic rods respectively. Those skilled in the art can understand that the number of drive links for connecting the protective box and the shooting base is not limited herein, as long as the drive links can be extended and retracted to adjust the angle of the shooting base. A plurality of laser range finders and a plurality of Led lights 9 are further arranged around the industrial camera 8 on the shooting base 5. The plurality of laser range finders obtain the distance between the shooting base and the surrounding rock, and the plurality of Led lights are used to provide light for the industrial camera. In this embodiment, the shooting base 5 is in the shape of a disc, and the industrial camera is arranged in the center of the disc. The laser range finder I701, the laser range finder II702, the laser range finder III703, and the laser range finder IV 704 are evenly arranged on the circle with the industrial camera as the origin; and the Led lights are evenly arranged in two circles on the circle with the center of the shooting base 5 as the origin. Those skilled in the art can understand that the numbers of laser range finders and Led lights are not limited herein. The illuminometer 10 is further fixed on the protective box 12 by means of the third drive link 11 to sense the brightness around the image acquisition module. The control module is connected with the first drive link 1, the sixth drive link 15, the second drive link 4, the fourth drive link 13, the fifth drive link 14, the laser range finder I 701, the laser range finder II702, the laser range finder III703, the laser range finder IV 704, the laser range finder V 705, the laser range finder VI 706, the industrial camera 8, the Led lights 9, the illuminometer 10 and the third drive link 11, respectively. The control module receives data transmitted from the laser range finder I701, the laser range finder II 702, the laser range finder III 703, the laser range finder IV 704, the laser range finder V 705, the laser range finder VI 706, the industrial camera 8, the Led lights 9, and the illuminometer 10. The working principle of the above system is as follows: A. The control module controls the first drive link 2 and the sixth drive link 15 to push the image acquisition module to approach the surrounding rock, as shown in FIG. 4; B. The control module controls the six laser range finders 701-706 to test whether the distance between the shooting base 5 and the surrounding rock meets the requirements; if not, step A is performed; if so, next step is performed;
C. The control module controls the six laser range finders 701-706 to test whether the shooting base and the surrounding rock are kept relatively parallel; if not, the control module controls the second drive link 4, the third drive link 13, and the fourth drive link 14 to work until the shooting base and the surrounding rock are kept relatively parallel, and the following formula is used to determine the parallel status:
Z: I 7 O1J- ( 061+O(7 7 2 - (705 + (703 - g7O4) 1 Where 6701 to 6706 are respectively the distances between the surrounding rock detected by the laser range finders 701-706 and the shooting base 5. When the value of this formula is less than a set threshold, it is considered that the shooting base is relatively parallel to the surrounding rock. D. The control module controls the third drive link 11 to push the illuminometer 10 to approach the surrounding rock; E. The control module controls the illuminometer 10 to work and checks whether the illumination intensity meets the standard, and if not, the control module controls the Led lights 9 to change the illumination intensity until the illumination intensity of a region to be measured meets the standard; F. The control module controls the industrial camera 8 to capture images, and the industrial camera 8 transmits the captured surrounding rock images to the control module; G. The control module transmits the surrounding rock images to the quartz content prediction module. The quartz content prediction module predicts the quartz content after receiving the surrounding rock images acquired by the image acquisition module; H. The control module controls the drive links to drive the entire device back to a standby position and a standby state. The quartz content prediction module stores relevant algorithms and files, including a quartz positioning algorithm and a matched trained model file, a region growing algorithm, a quartz content calculation algorithm and a matched trained model file. As shown in FIG. 5, after receiving the surrounding rock images, the quartz content prediction module performs the following process: Step 1: the surrounding rock images are preprocessed uniformly with reference to a standard image; specifically, the images are scaled according to the imaging principle; considering the distance between the camera and the surrounding rock and the shooting focal lengths of images, the surrounding rock images are processed into surrounding rock images under unified conditions (fixed distance between the camera and the surrounding rock and fixed shooting focal length of images);
Step 2: the processed surrounding rock images are input into a Faster Region-Convolutional Neural Network (R-CNN) model to obtain candidate region boxes of quartz; Step 2 specifically includes: Step 2.1: a surrounding rock feature image is extracted from an original image processed in step 1 by means of a series of convolutional layers and pooling layers (CNN); Step 2.2: the surrounding rock feature image is segmented into a plurality of small regions by a Region Proposal Network (RPN), which small regions show quartz and which show other minerals or impurities are identified, and approximate locations of quartz in the rock image are obtained; Step 3: the surrounding rock image processed in step 1 is grayed; Step 4: for each candidate region box of quartz, pixels with gray values greater than a threshold are marked as growing seed points of a quartz region, and a quartz region in the candidate region box is obtained on the basis of a region growing method; Where the threshold is obtained by counting the gray values of all pixels in the candidate region box. Step 4 specifically includes: Step 4.1: the gray values of all pixels in a rectangular box of the rock region are averaged to form a screening threshold BO; the gray values of all the pixels in the rock region box are determined, if the gray values are greater than BO, the pixels are determined as quartz points, and preliminary quartz region growing seeds are formed; Step 4.2: pop up the growing seed points sequentially in the quartz region, and the relationship between 8 neighborhoods around a seed point is determined; if the absolute values of differences between the gray values of the 8 neighborhood pixels and the seed pixel are less than a certain threshold T, the point can be regarded as a seed point for next growth; this step is repeated until every point in the quartz region box is assigned, and the growth ends; Step 5: the number of pixels in all quartz regions of each candidate region box is counted, and a quartz feature vector of the surrounding rock image is obtained by combining a pre-measured rock density of the surrounding rock; specifically, the quartz feature vector is a one-dimensional vector in the form of [ni,n2,--,ni,...,fn., where p represents the
pre-measured rock density of the surrounding rock, ni represents the number of quartz regions with a pixel number i in the image, and m represents a preset maximum possible pixel number of the quartz regions; Step 6: the quartz feature vector is input into the pre-trained quartz content prediction model to calculate the quartz content; Where the quartz content prediction model is constructed on the basis of a fully connected neural network. Specifically, a large number of surrounding rock images are collected in advance and the quartz contents therein are measured, the feature vector of each surrounding rock image is obtained according to steps 1-5, and the feature vectors of these images and the corresponding quartz contents are used as training data to train the fully connected neural network to obtain the quartz content prediction model. The above one or more embodiments have the following technical effects: The present disclosure provides an image data acquisition system with high flexibility, in which the distance from the surrounding rock is adjusted by means of the first drive link connected between the base and the image acquisition module, and the angle is adjusted by means of the sixth drive link connected between the base and the first drive link; further, a plurality of drive links are arranged between the image acquisition module and the protective box, to realize fine adjustment of the shooting angle, which can obtain high-quality images, thereby providing a guarantee for subsequent accurate calculation of the quartz content. In combination with the construction characteristics of TBM, the exposed surrounding rock just excavated is shot and calculated, without collection, secondary processing and grinding, so on-site shooting and on-site calculation can be achieved; and automatic operation is achieved, without artificial attendant, thereby saving labor, reducing construction risks and reducing engineering costs. In the present disclosure, the quartz content of the surrounding rock is tested in real time, and it takes less than 1 minute from shooting to calculation of an image each time, which can meet the requirements of rapid construction for the acquisition of the surrounding rock parameters, and does not require secondary processing for data, and the status of the surrounding rock can be quickly grasped by general construction personnel. The quartz content prediction method proposed by the present disclosure accurately extracts the location of quartz in the image on the basis of a Faster R-CNN and a region growing method, and comprehensively considers the quartz quantity and the density of the surrounding rock to construct a feature vector, which ensures the strong correlation between the feature vector and the quartz content and improves the prediction accuracy of the quartz content. It should be appreciated by those skilled in the art that the modules or steps of the present disclosure can be implemented by a general computer device, alternatively, can be implemented by program codes executable by a computing device, and thus can be stored in a storage device and executed by the computing device, or in some cases, the modules or steps are respectively fabricated into individual integrated circuit modules, or a plurality of modules or steps of them are fabricated into a single integrated circuit module. The present disclosure is not limited to any particular combination of hardware and software. Described above are merely preferred embodiments of the present disclosure, and the present disclosure is not limited thereto. Various modifications and variations may be made to the present disclosure for those skilled in the art. Any modification, equivalent substitution or improvement made within the spirit and principle of the present disclosure shall fall into the protection scope of the present disclosure. Although the specific embodiments of the present disclosure are described above in conjunction with the accompanying drawings, they do not limit the protection scope of the present disclosure. Those skilled in the art should understand that various modifications or deformations that can be made by those skilled in the art on the basis of the technical solutions of the present disclosure without any creative effort are still within the protection scope of the present disclosure.
Claims (10)
1. A predicting system for quartz content of surrounding rock in a tunnel based on image
identification and analysis, comprising a base for fixing with a tunnel boring machine, an
image acquisition module, a telescopic first drive link, a telescopic sixth drive link, a control
module, and a quartz content prediction module;
wherein the base is connected with the image acquisition module by the first drive link,
and a rod body of the first drive link and the base are connected by the sixth drive link;
the control module is configured to send control instructions to the first drive link, the
sixth drive link and the image acquisition module, receive a surrounding rock image
transmitted by the image acquisition module, and send the surrounding rock image to the
quartz content prediction module for quartz content prediction.
2. The predicting system for quartz content of surrounding rock in the tunnel based on
image identification and analysis according to claim 1, wherein the image acquisition module
is arranged in a protective box, and the protective box is connected with the first drive link by
a connector.
3. The predicting system for quartz content of surrounding rock in the tunnel based on
image identification and analysis according to claim 2, wherein the image acquisition module
comprises an industrial camera, a shooting base and a plurality of telescopic drive links,
wherein the industrial camera is fixed in the center of the shooting base, and the lower surface
of the shooting base is connected with the protective box by the plurality of telescopic drive
links.
4. The predicting system for quartz content of surrounding rock in the tunnel based on
image identification and analysis according to claim 3, wherein a plurality of laser range
finders and a plurality of Led lights are further arranged around the industrial camera on the
shooting base.
5. The predicting system for quartz content of surrounding rock in the tunnel based on
image identification and analysis according to any one of claims 2-4, wherein an
illuminometer is further arranged on the protective box, and the two are connected by a
telescopic third drive link.
6. A method system for quartz content of surrounding rock in a tunnel based on the
system according to any one of claims 1-5, comprising the following steps: the control module sends control instructions to the first drive link, the sixth drive link, and the plurality of drive links in the protective box respectively, to adjust the positional relationship between the image acquisition module and surrounding rock; and the control module sends a shooting instruction to the industrial camera to obtain an image, and sends the image to the quartz content prediction module for quartz content test.
7. The method system for quartz content of surrounding rock in the tunnel according to
claim 6, wherein during the process of adjusting the positional relationship between the image
acquisition module and the surrounding rock, the control module receives distance data sent
by the plurality of laser range finders, determines whether the shooting base and the
surrounding rock are kept relatively parallel, and if not, continues to adjust the positional
relationship between the image acquisition module and the surrounding rock.
8. The method system for quartz content of surrounding rock in the tunnel according to
claim 7, wherein if the shooting base and the surrounding rock are kept relatively parallel, the
control module sends a control instruction to the third drive link, to control the illuminometer
to approach the surrounding rock; the control module receives illumination data collected by
the illuminometer, determines whether the illumination intensity meets a preset standard; and
if not meet, sends a brightness adjustment instruction to the Led lights; and if meets, the
control module sends a shooting instruction to the industrial camera.
9. The method system for quartz content of surrounding rock in the tunnel according to
claim 7, wherein six laser range finders are used to determine whether the shooting base and
the surrounding rock are kept relatively parallel comprises
calculates whether -(706 702 -(70s 3701 703 -6704) is less than a set threshold,
and if so, considers that the shooting base and the surrounding rock are kept relatively
parallel, where 6701 to 6706 are the distances from the surrounding rock detected by the six
laser range finders respectively.
10. The method system for quartz content of surrounding rock in the tunnel according to
claim 6, wherein the quartz content test comprises the following steps
inputs the image into a Faster R-CNN model to obtain candidate region boxes of quartz;
for each candidate region box of quartz, marks pixels with gray values greater than a
threshold as growing seed points of a quartz region, and obtains a quartz region in the candidate region box on the basis of a region growing method; counts the number of pixels in all the quartz regions of each candidate region box, and obtains a quartz feature vector of the surrounding rock image by combining a pre-measured rock density of the surrounding rock; and inputs the quartz feature vector into a pre-trained quartz content prediction model to obtain the quartz content.
Applications Claiming Priority (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910843117.9 | 2019-09-06 | ||
| CN201910843117 | 2019-09-06 | ||
| CN202010070790.6A CN111272753B (en) | 2019-09-06 | 2020-01-21 | Tunnel inner wall rock quartz content prediction system and method based on image recognition and analysis |
| CN202010070790.6 | 2020-01-21 | ||
| PCT/CN2020/113817 WO2021043308A1 (en) | 2019-09-06 | 2020-09-07 | Image identification and analysis-based system and method for predicting quartz content of surrounding rock in tunnel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| AU2020342222A1 true AU2020342222A1 (en) | 2022-04-28 |
| AU2020342222B2 AU2020342222B2 (en) | 2023-10-12 |
Family
ID=70996915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2020342222A Active AU2020342222B2 (en) | 2019-09-06 | 2020-09-07 | Predicting system and method for quartz content of surrounding rock in tunnel based on image identification and analysis |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN111272753B (en) |
| AU (1) | AU2020342222B2 (en) |
| WO (1) | WO2021043308A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111272753B (en) * | 2019-09-06 | 2021-04-13 | 山东大学 | Tunnel inner wall rock quartz content prediction system and method based on image recognition and analysis |
| CN113960667A (en) * | 2021-06-09 | 2022-01-21 | 新疆建筑科学研究院（有限责任公司） | Surrounding rock quality prediction method, prediction system, computer device, medium and terminal |
| CN115407046B (en) * | 2022-08-05 | 2024-04-16 | 西南石油大学 | Comprehensive abrasiveness characterization method based on rock microstructure and equivalent quartz content |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AT14252U1 (en) * | 2013-07-30 | 2015-07-15 | Montanuniversität Leoben | System for determining a face breast image |
| CN203661164U (en) * | 2013-11-14 | 2014-06-18 | 北京市轨道交通建设管理有限公司 | Camera protective hood and monitoring camera shooting device for underground excavation of tunnel construction tunnel face |
| CN104599262A (en) * | 2014-12-18 | 2015-05-06 | 浙江工业大学 | Multichannel pulse coupling neural network based color image segmentation technology |
| CN205506703U (en) * | 2016-03-21 | 2016-08-24 | 长安大学 | Trailer is fixed to tunnel slot image data collection instrument |
| CN106161864A (en) * | 2016-07-18 | 2016-11-23 | 哈尔滨理工大学 | A kind of multiconductor image collecting device |
| CN205912093U (en) * | 2016-07-22 | 2017-01-25 | 深圳亿和源科技有限公司 | Mobile terminal with angularly adjustable camera |
| CN206016814U (en) * | 2016-09-18 | 2017-03-15 | 中铁工程装备集团有限公司 | A kind of record and the device for analyzing TBM slag pieces |
| CN107784661B (en) * | 2017-09-08 | 2021-10-08 | 上海电力学院 | Transformer substation equipment infrared image classification and identification method based on region growing method |
| CN107563388A (en) * | 2017-09-18 | 2018-01-09 | 东北大学 | A kind of convolutional neural networks object identification method based on depth information pre-segmentation |
| CN208248116U (en) * | 2018-06-04 | 2018-12-18 | 江西冠翔科技有限公司 | Vehicle top lifting filming apparatus |
| CN208836243U (en) * | 2018-08-29 | 2019-05-07 | 安徽华磊工程科技有限公司 | A kind of adjustable high-definition monitoring camera |
| CN109612943B (en) * | 2019-01-14 | 2020-04-21 | 山东大学 | Tunnel rock quartz content testing system and method based on machine learning |
| CN111272753B (en) * | 2019-09-06 | 2021-04-13 | 山东大学 | Tunnel inner wall rock quartz content prediction system and method based on image recognition and analysis |
-
2020
- 2020-01-21 CN CN202010070790.6A patent/CN111272753B/en active Active
- 2020-09-07 AU AU2020342222A patent/AU2020342222B2/en active Active
- 2020-09-07 WO PCT/CN2020/113817 patent/WO2021043308A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021043308A1 (en) | 2021-03-11 |
| CN111272753B (en) | 2021-04-13 |
| CN111272753A (en) | 2020-06-12 |
| AU2020342222B2 (en) | 2023-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020342222B2 (en) | Predicting system and method for quartz content of surrounding rock in tunnel based on image identification and analysis | |
| AU2019439936B2 (en) | TBM-mounted advanced geological prediction system and method based on identification of lithology and adverse geology precursor characteristics | |
| CN108037770B (en) | Unmanned aerial vehicle power transmission line inspection system and method based on artificial intelligence | |
| EP3001138B1 (en) | Measuring device for determining the spatial location of a measuring aid | |
| US11796493B2 (en) | System and method for identifying lithology based on images and XRF mineral inversion | |
| CN112348034A (en) | Crane defect detection system based on unmanned aerial vehicle image recognition and working method | |
| Chen et al. | Automated in-field leaf-level hyperspectral imaging of corn plants using a Cartesian robotic platform | |
| LU500120B1 (en) | Multi-arm robot for automatic tunnel maintenance and control method thereof | |
| WO2021147553A1 (en) | System and method for determining degree of weathering of igneous rock in tunnel | |
| CN111638200B (en) | Geological forecasting system and method based on Raman spectrum analysis | |
| CN115753643A (en) | Rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum | |
| US20220351353A1 (en) | Mining equipment inspection system, mining equipment inspection method, and mining equipment inspection device | |
| CN110942520B (en) | Auxiliary positioning method, device and system for operation equipment and storage medium | |
| CN114067094A (en) | Multispectral camera system for rock drilling jumbo and intelligent surrounding rock identification method | |
| CN112332541A (en) | Monitoring system and method for transformer substation | |
| CN113297962B (en) | Unmanned aerial vehicle carried type XRF and image fusion lithology identification system and method | |
| CN112765874B (en) | Method and device for acquiring surrounding rock parameters applicable to open TBM tunnel | |
| CN207295453U (en) | A kind of bridge quick visualization detection device and its system | |
| CN105043544B (en) | A kind of image spectrum tracking and system | |
| CN115901640B (en) | Poor geology advanced forecasting method and system integrating spectrum imaging and space-time distribution | |
| CN107155863A (en) | A kind of method that automated analysis benthophyte upgrowth situation is rebuild based on 3D | |
| CN113312991A (en) | Front-end intelligent recognition system based on unmanned aerial vehicle | |
| CN112801035A (en) | Knowledge and data dual-drive-based carrying type lithology intelligent identification method and system | |
| Kutyrev et al. | Strawberry yield monitoring based on a convolutional neural network using high-resolution aerial orthoimages | |
| Giménez-Gallego et al. | Image-based sensor for on-tree automatic color tracking in pomegranate orchards |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| DA3 | Amendments made section 104 |
Free format text: THE NATURE OF THE AMENDMENT IS: AMEND THE INVENTION TITLE TO READ PREDICTING SYSTEM AND METHOD FOR QUARTZ CONTENT OF SURROUNDING ROCK IN TUNNEL BASED ON IMAGE IDENTIFICATION AND ANALYSIS |
|
| FGA | Letters patent sealed or granted (standard patent) |