WO2021147553A1 - 隧道火成岩风化程度确定系统及方法 - Google Patents

隧道火成岩风化程度确定系统及方法 Download PDF

Info

Publication number
WO2021147553A1
WO2021147553A1 PCT/CN2020/135314 CN2020135314W WO2021147553A1 WO 2021147553 A1 WO2021147553 A1 WO 2021147553A1 CN 2020135314 W CN2020135314 W CN 2020135314W WO 2021147553 A1 WO2021147553 A1 WO 2021147553A1
Authority
WO
WIPO (PCT)
Prior art keywords
rock
weathering
degree
feldspar
igneous
Prior art date
Application number
PCT/CN2020/135314
Other languages
English (en)
French (fr)
Inventor
许振浩
潘东东
刘福民
邵瑞琦
余腾飞
许建斌
王文扬
林鹏
Original Assignee
山东大学
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 山东大学 filed Critical 山东大学
Publication of WO2021147553A1 publication Critical patent/WO2021147553A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70—Machine learning, data mining or chemometrics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10056—Microscopic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30132—Masonry; Concrete

Definitions

  • the present disclosure belongs to the technical field of tunnel rock weathering detection, and relates to a system and method for determining the weathering degree of tunnel igneous rock.
  • TBM Torque Boring Machine
  • TBM tunneling Machine has been widely used in tunnel construction. It has the advantages of reduced labor intensity, fast construction speed, low environmental disturbance, and high safety.
  • the degree of weathering of the front rock has a great influence on the hardness and integrity of the rock mass, which plays a key role in smooth tunneling.
  • Feldspar In igneous rocks, minerals crystallize and form at different temperatures, and the crystallization order of different feldspars has an obvious relationship. Feldspar is not only distributed in a large area, but also has a variety of types due to its similarity problems. Feldspar is a common type of aluminosilicate rock-forming minerals containing calcium, sodium and potassium. It can be divided into two series: alkaline feldspar series (ie Or-Ab series) and plagioclase series (ie Ab -An series) (Or, Ab and An stand for KAlSi 3 O 8 , NaAlSi 3 O 8 and CaAl 2 Si 2 O 8 ). Different series of feldspar have different hardness and different weathering resistance, which has a great impact on the weathering resistance of igneous rocks.
  • the current judgment of the weathering degree of the front rock is mainly based on human observation, and the result depends on the professionalism of the operator, which has great limitations, and the observation result is not accurate.
  • the present disclosure proposes a tunnel igneous rock weathering degree determination system and method.
  • the present disclosure can quickly determine the front igneous rock weathering degree in real time and improve the tunneling efficiency, and the result is more accurate.
  • the present disclosure adopts the following technical solutions:
  • a system for determining the weathering degree of tunnel igneous rock including:
  • the data acquisition system is configured to obtain a rock sample in front of the palm, perform image scanning and composition detection on the rock sample, and make part of the sample into a glass slide;
  • the data transmission module is configured to transmit the slide specimens acquired by the data acquisition system to the data analysis system through a transmission belt, and the acquired image scanning results and rock composition information are wirelessly transmitted to the data analysis system;
  • the data analysis system is configured to construct a deep learning model that is trained based on the stored image scanning results and rock composition information to obtain the corresponding relationship between each image scanning result and the rock composition information and the corresponding degree of weathering, and receive the to-be-determined Scanning results of the front rock image and rock composition information are analyzed using the trained model to obtain the degree of weathering in front of the tunnel.
  • the data acquisition system includes a rock sampling module, an image scanning module, and a rock testing module.
  • the rock sampling module samples and slices rocks during tunnel excavation, and the sampling mechanism is mounted on a robotic arm, It includes a picking device and a drilling rig.
  • the picking device directly picks up the slag on the conveyor belt, and the drilling rig performs core drilling on the rock wall near the face.
  • the film production mechanism utilizes existing methods.
  • the equipment includes a ball mill, a slitting machine, and a tablet press.
  • the obtained slag or core is randomly selected for glass slide production, and the sampling robot can move in multiple dimensions;
  • the image scanning module is configured as a camera to take a photograph and scan of the outer morphology of the taken rock sample to obtain the characteristics of the outer morphology of the rock;
  • the rock test module includes an XRF test device and an XRD test device.
  • the XRF test device uses a handheld device.
  • the existing test box can directly obtain the element type and abundance information in the sample igneous rock.
  • the XRD device is equipped with a sample collecting bowl, which can directly The slag rock powder was tested, and different feldspar end members were identified and distinguished based on the different chemical composition of the feldspar.
  • the data analysis system includes a microscopic image module, a computer analysis module, and a deep learning module, wherein the microscopic image module is a polarized light microscopy device, which is made into a data acquisition system transmitted via a conveyor belt. Microscopic imaging of the rock slide samples to obtain the rock image under the polarized light microscope to assist in the selection of feldspar particles;
  • the computer analysis module is configured to obtain feldspar type and content diffraction pattern data based on XRF and XRD device related data, and to count the feldspar category and content, and compare the feldspar element content types and X-ray devices in books and documents.
  • the diffraction pattern data provided by the manufacturer is processed and corrected by the data obtained by the XRF and XRD devices;
  • the deep learning module is configured to learn and train data based on the neural network model.
  • the deep learning module when the deep learning module forms a discrimination model for different weathering degrees of igneous rocks, it integrates the training characteristics according to preset standard thresholds for different feldspar feature levels, and establishes weathering of igneous rocks according to preset classification standards. Degree automatic model evaluator.
  • the output model compares the characteristics of feldspar contained in the igneous rock to be evaluated with various information in the data storage center, and evaluates the weathering degree of the igneous rock to be evaluated by an automatic igneous rock model evaluator, and Different thresholds are specified.
  • the data acquisition system is mounted on a TBM robotic arm.
  • it also includes a data storage center configured to store the existing tunnel rock sample image scan results, rock composition information and corresponding weathering degree, and preset standard thresholds for different feldspar characteristics.
  • a method for determining the degree of weathering of igneous rock in a tunnel includes the following steps:
  • the classification of weathering degree of igneous rock includes:
  • feldspar in igneous rocks are the main consideration criteria. If the feldspar type is only potash feldspar—Class A; potash feldspar>plagioclase—Class B; potash feldspar ⁇ plagioclase—Class C; only Plagioclase—Grade D.
  • the euhedral content accounts for the highest proportion-grade a; the semi-automorphic content accounts for the highest proportion, self> it form-b grade, the semi-automorphic content accounts for the highest proportion, self ⁇ its form-c grade, The content accounts for the highest-level d.
  • the final judgment level of feldspar properties on the degree of weathering of the rock formation is finally determined: at least one A or B+a or 2 a is weak weathering, and there is only 1 a or 2 b It is moderate weathering, and if there is no A/a or B/b grade, it is strong weathering.
  • a computer-readable storage medium stores a plurality of instructions, and the instructions are adapted to be loaded by a processor of a terminal device and execute part or all of the steps of the method for determining the degree of weathering of tunnel igneous rocks.
  • a terminal device including a processor and a computer-readable storage medium, the processor is used to implement each instruction; the computer-readable storage medium is used to store a plurality of instructions, the instructions are suitable for being loaded by the processor and executed Part or all of the steps of the method for determining the degree of weathering of the tunnel igneous rock.
  • the present disclosure evaluates the degree of weathering of igneous rocks encountered during tunnel excavation, and provides guidance for the tunneling method.
  • the present disclosure judges the degree of weathering by studying the content of feldspar in the surrounding rock of the tunnel, which fills in the research on the degree of weathering of the surrounding rock of the tunnel. blank;
  • the present disclosure uses the composition and content of feldspar in combination with the weathering image of igneous rock to establish an evaluation model, which not only realizes the qualitative evaluation of the weathering degree of igneous rock, but also realizes the quantitative evaluation, and the qualitative evaluation is more accurate. After the evaluation model is obtained, continuous testing can be realized. , Which can serve the project schedule of rapid tunnel excavation;
  • the present disclosure makes more use of in-situ rock testing to provide a good testing method for TBM tunneling.
  • Figure 1 is a schematic diagram of the main flow of this embodiment
  • Figure 2 is a schematic side view of the detection in the tunnel of this embodiment
  • Fig. 3 is a schematic front view of the detection in the tunnel of this embodiment
  • Fig. 4 is a schematic diagram of the data analysis system of this embodiment.
  • 1. is the data acquisition system; 2. is the rock sampling module; 3. is the rock testing module; 4. is the image scanning module; 5. is the wireless transmission system; 6. is the computer analysis module; 7. is the microscopic image Module; 8. is the data analysis system; 9. is the deep learning module; 10. is the artificial auxiliary neural network trainer; 11. is the automatic model evaluator; 12. is the data output system and storage center; 13. is the transmission conveyor belt.
  • the igneous rock weathering degree evaluation system in the TBM tunnel considering the characteristics of feldspar includes a data acquisition system, a wireless transmission system, a data analysis system, a data output system and a storage center. Among them:
  • the data acquisition system is mounted on the TBM robotic arm, and the surrounding rock is tested with the movement of the robotic arm, and information is collected every time the TBM excavation is suspended, and it is collected into the TBM after the collection is completed.
  • the data acquisition system includes a rock sampling module, an image scanning module and a rock testing module.
  • the rock sampling module samples the rocks in the tunnel excavation process, and uses slag/rock block as the basic sample to serve for subsequent detection;
  • the image scanning module scans the appearance of the taken rock samples to obtain the appearance characteristics of the rock , Used for qualitative weathering of rock surface and determination of rock categories;
  • the rock element analysis module is configured as an XRF test device and an XRD test device.
  • the XRF test device obtains the element type and abundance information in the sample igneous rock, and the XRD device is based on The different chemical composition of feldspar has identified different feldspar end members.
  • feldspar The main components of feldspar are SiO 2 , Al 2 O 3 , K 2 O, Na 2 O, CaO, etc., such as potassium feldspar, the molecular formula is K 2 O ⁇ Al 2 O 3 ⁇ 6SiO 2 ; the albite, the molecular formula is Na 2 O ⁇ Al 2 O 3 ⁇ 6SiO 2 ; Anorthite, the molecular formula is CaO ⁇ Al 2 O 3 ⁇ 2SiO 2 .
  • the data analysis system includes a microscopic image module, a computer analysis module and a deep learning module.
  • the microscopic image module is configured as a polarized light microscopy device, which performs microscopic imaging of the sample rock, obtains images under the polarized light microscope of the rock, and assists in selecting feldspar particles;
  • the computer analysis module is configured with XRF and XRD devices on a computer Relevant data processing software obtains feldspar type and content diffraction pattern data through testing, and counts the feldspar type and content displayed in the supporting computer sample data processing software, and processes and corrects the data obtained by the equipment.
  • the deep learning module includes an artificial auxiliary neural network trainer and an automatic model evaluator.
  • the artificial auxiliary neural network trainer accepts a large amount of tunnel excavation rock data and various surface rock data as well as domestic oilfield and coalfield drilling lithology data in advance, and these data are stored in the data storage center, and the trainer can continuously store the data The center gets the data.
  • the trainer receives information from the elemental analysis module and the mineral quantification module, and through comparison and training with existing data, it can finally be classified according to the following principles:
  • the weathering resistance of potash feldspar is higher than that of plagioclase (that is, the weathering resistance of orthoclase is stronger than that of plagioclase), or the weathering resistance of alkaline feldspar is greater than that of plagioclase, and plagioclase is acidic Plagioclase is larger than neutral plagioclase and larger than basic plagioclase.
  • Principle 2 Crystal structure. If the mineral has sufficient crystallization time and growth space when it is crystallized, it will grow into a fixed shape according to its own crystal structure. Therefore, when the mineral crystallizes, it maintains its own crystal structure and growth.
  • the shape is called euhedral crystal; most of the remaining crystal shape is called semi-automorphic crystal; the complete loss of its own shape is called euhedral crystal, and the better the crystal shape of the mineral is, the better it is. The more stable, the lower the degree of rock weathering.
  • the percentage of feldspar in igneous rocks is different from other rock types.
  • the content of feldspar can reach a high proportion.
  • the content of feldspar in sedimentary rocks is generally not more than 50%, while the content of feldspar in igneous rocks can reach 80%-90%.
  • Feldspar is a kind of mineral that is more resistant to weathering.
  • the higher its content in the rock the stronger its resistance to weathering and the lower the degree of weathering.
  • due to different crystallization environments there are also differences.
  • the content of syenite and feldspar is higher than that of granite, but the weathering resistance is not necessarily better than that of granite, so this standard is only used as an auxiliary evaluation.
  • the type of feldspar in igneous rocks is the main consideration standard, if the type of feldspar is only potash feldspar-Class A; potash feldspar> plagioclase-Class B; potash feldspar ⁇ plagioclase -C level; only plagioclase-D level.
  • the euhedral content accounts for the highest proportion-grade a; the semi-automorphic content accounts for the highest proportion, self> it form-b grade, the semi-automorphic content accounts for the highest proportion, self ⁇ its form-c grade, The content accounts for the highest-level d.
  • the final judgment level of feldspar properties on the degree of weathering of the rock formation is finally determined: at least one A or B+a or 2 a is weak weathering, and there is only 1 a or 2 b It is moderate weathering, and if there is no A/a or B/b grade, it is strong weathering.
  • the trainer When the trainer forms a discrimination model for different degrees of weathering of igneous rocks, it imports preset standard thresholds of different feldspar characteristics into the data storage center as the evaluation basis for the evaluator to evaluate the degree of weathering of igneous rocks. Integrate the feature quantity trained by the trainer, give the level of weathering degree according to the preset classification standard, and establish an automatic model evaluator for the weathering degree of igneous rock controlled by the characteristics of feldspar. The evaluator can evaluate the weathering degree of the igneous rock encountered in front of the TBM tunneling in the tunnel according to the optimal model calculation of the response information obtained by the trainer.
  • the output model compares the characteristics of feldspar contained in the igneous rock to be evaluated with various information in the data storage center, and evaluates the weathering degree of the igneous rock to be evaluated by an automatic igneous rock model evaluator, and Different thresholds are specified.
  • the actual measurement and evaluation data of igneous rocks at different locations in the preliminary survey process are used as evaluation references, and the evaluation data of the weathering degree of igneous rocks are continuously obtained during the excavation process to continuously improve the accuracy of the model.
  • the system also includes a wireless transmission system and a data storage center.
  • the data storage center stores various feldspar composition and content data and preset igneous rock weathering evaluation thresholds.
  • the acquired rock data and the igneous rock weathering grade data evaluated by the data output system are stored in the data storage center.
  • the igneous rock samples of the TBM tunnel in the early stage of excavation were collected, and the image scanning device scanned the appearance of the rock samples to obtain the characteristics of the rock appearance; the XRF test device and XRD test device obtained the element types and abundance in the sample igneous rock.
  • Degree information, different chemical composition and content of feldspar use computer to analyze sample element and mineral data, and corresponding software to analyze element data and mineral data to obtain chemical classification and content characteristics of feldspar; extract the solution of target igneous rock by using microscopy device Physical characteristics, interference color characteristics, protrusion characteristics and crystal structure characteristics.
  • the above features are transferred to the deep learning module, through artificially preset evaluation standard thresholds, intelligent algorithms are used to learn the image information and feldspar feature information corresponding to the rock, and the weathering features of the igneous rock in the image are extracted, and the corresponding evaluation is set
  • the standard threshold is used as the main evaluation reference basis to assist the neural network trainer to learn to establish an automatic model evaluator.
  • the microscopic image module and computer analysis module in the data analysis system analyze the igneous rock microcrystal structure, chemical element and mineral composition content, and transfer the obtained feldspar feature information and image information to the deep learning module.
  • the automatic model evaluator evaluates the weathering degree of igneous rocks according to the previously obtained evaluation model, and transmits the evaluation results to the data storage center for storage, adds database data, and then continues to serve the next evaluation.
  • the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Geometry (AREA)
  • Artificial Intelligence (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

一种隧道火成岩风化程度确定系统及方法，通过构建深度学习模型，基于已存储的图像扫描结果和岩石成分信息进行训练，得到各图像扫描结果和岩石成分信息与相应风化程度的对应关系；获取掌子面前方岩石试样，对岩石试样进行图像扫描和成分检测，利用训练后的模型，对检测的结果进行分析，得到隧道前方火成岩风化程度。能够实时快捷的确定前方火成岩风化程度，提高掘进效率，且结果较为准确。

Description

隧道火成岩风化程度确定系统及方法 技术领域
本公开属于隧道岩石风化检测技术领域，涉及一种隧道火成岩风化程度确定系统及方法。
背景技术
本部分的陈述仅仅是提供了与本公开相关的背景技术信息，不必然构成在先技术。
TBM(岩石掘进机Tunnel Boring Machine)，已广泛应用于隧道施工，具有降低人工劳动强度、施工速度快、对环境扰动小、安全性高等优点。在TBM掘进过程中，前方岩石的风化程度对岩体硬度及完整性影响很大，这对是否能顺利掘进具有关键作用。
在火成岩石中，矿物在不同的温度下结晶形成，不同的长石其结晶顺序有明显的先后关系。长石不仅分布范围大，且由于其存在类质同象问题导致其种类也较为繁杂。长石是一类常见的含钙、钠和钾的铝硅酸盐类造岩矿物，可划分为两个系列：碱性长石系列(即Or-Ab系列)和斜长石系列(即Ab-An系列)(Or、Ab和An分别代表KAlSi 3O 8、NaAlSi 3O 8和CaAl 2Si 2O 8)。不同系列的长石硬度有差异，抗风化能力也截然不同，这对火成岩石抗风化能力造成很大影响。
据发明人了解，目前的前方岩石的风化程度判断主要是依托于人为观察，其结果依赖于操作人员的专业性，具有很大的局限性，且观测结果不精确。
发明内容
本公开为了解决上述问题，提出了一种隧道火成岩风化程度确定系统及方法，本公开能够实时快捷的确定前方火成岩风化程度，提高掘进效率，且结果较为准确。
根据一些实施例，本公开采用如下技术方案：
一种隧道火成岩风化程度确定系统，包括：
数据采集系统，被配置为获取掌子面前方岩石试样，对岩石试样进行图像扫描和成分检测，并将部分样品制成玻片；
数据传输模块，被配置为将数据采集系统获取的玻片标本通过传动带传输给数据分析系统，获取的图像扫描结果和岩石成分信息通过无线传输给数据分析系统；
数据分析系统，被配置为构建深度学习模型，所述模型基于已存储的图像扫描结果和岩石成分信息进行训练，得到各图像扫描结果和岩石成分信息与相应风化程度的对应关系，并接收待确定的前方岩石图像扫描结果和岩石成分信息，利用训练后的模型进行分析，得到隧道前方风化程度。
作为进一步的限定，所述数据采集系统包括岩石取样模块、图像扫描模块和岩石测试模块，其中，所述岩石取样模块对隧洞掘进过程中的岩石进行取样及制片，取样机构搭载于机械臂，包括拾取装置和钻机，拾取装置直接对传送带上岩渣进行拾取，钻机对位于掌子面附近的岩壁进行岩芯钻取。
制片机构利用现有方式，装置包括球磨机、剖光机和压片机，随机选取所获取的岩渣或岩芯进行玻片制作，取样机械臂可多维运动；
所述图像扫描模块配置为照相机，对所取岩石样品外表形貌进行拍照扫描， 获取岩石外表形貌特征；
所述岩石测试模块包括XRF测试装置和XRD测试装置，XRF测试装置利用手持式设备，现有的测试箱可直接获取样品火成岩中的元素种类及丰度信息，XRD装置配置样品收取钵，可直接对岩渣岩粉进行测试，基于长石的不同化学成分，鉴定区分出不同的长石端元。
作为进一步的限定，所述数据分析系统，包括显微图像模块、计算机分析模块和深度学习模块，其中，所述显微图像模块为偏光显微装置，对经由传送带传输过来的数据采集系统制成的岩石玻片样品进行显微成像，获取岩石偏光显微镜下图像，辅助挑选长石颗粒；
所述计算机分析模块被配置为基于XRF及XRD装置的相关数据，通过测试获取长石种类及含量衍射图谱数据，并统计长石类别及含量，对比书籍文献中长石元素含量类型及X射线装置厂家所提供的衍射图谱数据，对XRF及XRD装置获取的数据进行处理修正；
所述深度学习模块，被配置为基于神经网络模型对数据进行学习训练。
作为进一步的限定，所述深度学习模块在形成火成岩石不同风化程度判别模型时，根据预设的不同长石特征级别标准阈值，整合训练的特征量，按照预置的分类标准，建立火成岩石风化程度自动模型评价器。
所述数据输出系统，输出模型将待评价的火成岩中所含的长石特征与数据存储中心中的各种信息进行对比，通过火成岩石自动模型评价器对待评价的火成岩风化程度进行评价，并根据不同阈值作具体规定。
作为可选择的实施方式，所述数据采集系统搭载于TBM机械臂上。
作为可选择的实施方式，还包括数据存储中心，被配置为存储已有隧道岩石样本图像扫描结果和岩石成分信息与相应风化程度，预设的不同长石特征标准阈值。
一种隧道火成岩风化程度确定方法，包括以下步骤：
构建深度学习模型，基于已存储的图像扫描结果和岩石成分信息进行训练，得到各图像扫描结果和岩石成分信息与相应风化程度的对应关系；
获取掌子面前方岩石试样，对岩石试样进行图像扫描和成分检测，利用训练后的模型，对检测的结果进行分析，得到隧道前方火成岩风化程度。
火成岩风化程度的分级包括：
当长石中仅含有K元素时，其抗风化能力最强，Na元素其次，仅含有Ca元素时其抗风化能力最差，当同时含有Na和Ca元素时，其抗风化能力随着Ca元素含量的增多而增强，即正长石(钾长石)>酸性斜长石(钠长石)>中性斜长石(中长石)>基性斜长石(钙长石)；
岩体的晶体结构保存的越完好，风化程度越低；
长石所占的含量百分比越高，风化程度越低。
依据上述分级标准，提出如下判别等级：
火成岩中长石元素及成分类型为主要考虑标准，若长石类型仅为钾长石—A级；钾长石>斜长石—B级；钾长石<斜长石—C级；仅为斜长石—D级。
长石的晶体结构，自形含量占比最高—a级；半自形含量占比最高、自行＞它形—b级，半自形含量占比最高、自行＜它形—c级，它形含量占比最高—d级。
若长石在火成岩中含量超过60％—a级；20％-60％—b级；5％-20％—c级；<5％-d级。
按上述标准，最终定出长石特性对岩层风化程度的最后判断级别：至少存在一个A级或B+a级或2个a级则为弱风化，仅存在1个a级或2个b级则为中风化，不存在任何一个A/a级或B/b级则强风化。
一种计算机可读存储介质，其中存储有多条指令，所述指令适于由终端设备的处理器加载并执行所述的一种隧道火成岩风化程度确定方法的部分或全部步骤。
一种终端设备，包括处理器和计算机可读存储介质，处理器用于实现各指令；计算机可读存储介质用于存储多条指令，所述指令适于由处理器加载并执行所述的一种隧道火成岩风化程度确定方法的部分或全部步骤。
与现有技术相比，本公开的有益效果为：
本公开对隧洞掘进中遇到的火成岩石进行风化程度评价，为掘进方式提供指导，本公开通过研究隧道围岩中长石的含量来判断其风化程度，填补了隧道围岩风化程度方面研究的空白；
本公开利用长石成分及含量结合火成岩石风化图像建立评价模型，不仅实现了对火成岩石风化程度的定性评价，而且实现了定量评价，并且定性更为准确，得到评价模型后，可实现连续测试，能够服务于隧洞快速掘进的工程进度；
本公开更多利用岩石原位测试，为TBM掘进提供良好测试手段。
附图说明
构成本公开的一部分的说明书附图用来提供对本公开的进一步理解，本公开的示意性实施例及其说明用于解释本公开，并不构成对本公开的不当限定。
图1是本实施例的主要流程示意图；
图2是本实施例的隧洞内探测示意侧视图；
图3是本实施例的隧洞内探测示意前视图；
图4是本实施例的数据分析系统示意图。
其中，1.是数据采集系统；2.是岩石取样模块；3.是岩石测试模块；4.是图像扫描模块；5.是无线传输系统；6.是计算机分析模块；7.是显微图像模块；8.是数据分析系统；9.是深度学习模块；10.是人工辅助神经网络训练器；11.是自动模型评价器；12.是数据输出系统及存储中心；13.是传输传送带。
具体实施方式：
下面结合附图与实施例对本公开作进一步说明。
应该指出，以下详细说明都是例示性的，旨在对本公开提供进一步的说明。除非另有指明，本文使用的所有技术和科学术语具有与本公开所属技术领域的普通技术人员通常理解的相同含义。
需要注意的是，这里所使用的术语仅是为了描述具体实施方式，而非意图限制根据本公开的示例性实施方式。如在这里所使用的，除非上下文另外明确指出，否则单数形式也意图包括复数形式，此外，还应当理解的是，当在本说明书中使用术语“包含”和/或“包括”时，其指明存在特征、步骤、操作、器件、组件和/或它们的组合。
如图1所示，TBM隧洞内考虑长石特征的火成岩风化程度评价系统，包括数据采集系统，无线传输系统，数据分析系统，数据输出系统及存储中心，其中：
所述数据采集系统搭载于TBM机械臂上，随着机械臂的移动而对围岩进行测试，在每次TBM掘进暂停时进行信息采集，采集完成后被收进TBM内部。
数据采集系统包括岩石取样模块、图像扫描模块和岩石测试模块。
岩石取样模块对隧洞掘进过程中的岩石进行取样，以岩渣/岩块为基础样品，服务于后续检测；所述图像扫描模块对所取岩石样品外表形貌进行扫描，获取岩石外表形貌特征，用于岩石表层风化定性及岩石大类的确定；所述岩石元素分析模块配置为一XRF测试装置及一XRD测试装置，XRF测试装置获取样品火成岩中的元素种类及丰度信息，XRD装置基于长石的不同化学成分，鉴定区分出不同的长石端元。长石主要成分为SiO 2、Al 2O 3、K 2O、Na 2O、CaO等，如：钾长石，分子式为K 2O·Al 2O 3·6SiO 2；钠长石，分子式为Na 2O·Al 2O 3·6SiO 2；钙长石，分子式为CaO·Al 2O 3·2SiO 2。
所述数据分析系统，包括显微图像模块、计算机分析模块和深度学习模块。所述显微图像模块配置为一偏光显微装置，对样品岩石进行显微成像，获取岩石偏光显微镜下图像，辅助挑选长石颗粒；所述计算机分析模块为在计算机上配置XRF及XRD装置的相关数据处理软件，通过测试获取长石种类及含量衍射图谱数据，并统计在配套计算机样品数据处理软件中显示出的长石类别及含量，对设备获取的数据进行处理修正。所述深度学习模块，包括人工辅助神经网络训练器以及自动模型评价器。
其中人工辅助神经网络训练器先期接受大量的隧洞开挖岩石数据以及各类地表岩石数据以及国内油田及煤田的钻井岩性数据，且这些数据均存于数据存储中心，训练器可以不断从数据存储中心获得数据。训练器接受来自元素分析模块以及矿物定量模块的信息，通过与已有数据对比和训练，最终可按照以下原理进行分级：
原理一：火成岩中长石类型，此条作为主要考虑标准。矿物的结晶温度越低其抗风化能力便越强，在火成岩中，不同的长石其结晶顺序有明显的先后关系，钠长石与钙长石形成连续固溶体系列，一般以钙长石分子(CaAl 2Si 2O 8，An)百分比(按mol数计算)为基础将其划分为钠长石(Ab，An＝0～10％)、更长石(Olg，An＝10～30％)、中长石(And，An＝30～50％)、拉长石(Lab，An＝50～70％)、倍长石(Byt，An＝70～90％)和钙长石(An，An＝90～100％)，且An<30时称为酸性斜长石，An＝30～50％时称为中性斜长石，An>50％时称为基性斜长石。钾长石很容易被风化蚀变，基性斜长石比酸性斜长石更容易遭受风化。
因此钾长石的抗风化能力高于斜长石(即正长石比斜长石的抗风化能力强)，或碱性长石抗风化能力大于斜长石，而在斜长石中则酸性斜长石大于中性斜长石大于基性斜长石，综上可知，按照不同长石的种类提供判别标准来看，正长石(钾长石)>酸性斜长石(钠长石、奥长石)>中性斜长石(中长石)>基性斜长石(拉长石、培长石、钙长石)。通过对比其元素含量，本实施例提供一种更为简单的划分，既当长石中仅含有K元素时，其抗风化能力最强，Na元素其次， 仅含有Ca元素时其抗风化能力最差，当同时含有Na和Ca元素时，其风化能力随着Ca元素含量的增多而增强。
原理二：晶体结构，矿物在结晶时如果有较为充足的结晶时间和生长空间，其便会按照其自身具有的晶体结构生长为固定的形状，因此，当矿物结晶后保持了自身的晶体结构与形状，则称为自形晶体；保留的大部分晶体形状，则称为半自形晶体；完全丧失了其自身形状，则称为它形晶体，而矿物的晶体形状保存的越完好则说明其更加稳定，岩石风化程度也就越低。
原理三：火成岩石中长石所占的含量百分比，区别于其它岩石类型，可以长石含量达到很高占比，如沉积岩长石含量最多一般不超过50％，而火成岩中长石含量可以达到80％-90％。长石是一种较能抗风化的矿物，一般情况下，其在岩石中的含量越高，其抗风化能力就越强，风化程度也就越低。但由于结晶环境不同，也有差别，如正长岩长石含量是高于花岗岩中的，但抗风化能力不见得好于花岗岩，故此标准只作为辅助评价。
依据上述原理，提出如下判别等级：火成岩中长石类型为主要考虑标准，若长石类型仅为钾长石—A级；钾长石>斜长石—B级；钾长石<斜长石—C级；仅为斜长石—D级。
长石的晶体结构，自形含量占比最高—a级；半自形含量占比最高、自行＞它形—b级，半自形含量占比最高、自行＜它形—c级，它形含量占比最高—d级。
若长石在火成岩中含量超过60％—a级；20％-60％—b级；5％-20％—c级；<5％-d级。
按上述标准，最终定出长石特性对岩层风化程度的最后判断级别：至少存在一个A级或B+a级或2个a级则为弱风化，仅存在1个a级或2个b级则为中风化，不存在任何一个A/a级或B/b级则强风化。
训练器在形成火成岩石不同风化程度判别模型时，向数据存储中心导入预设的不同长石特征标准阈值，作为评价器评价火成岩石风化程度的评价依据。整合训练器训练的特征量，按照预置的分类标准给出风化程度的级别，建立由长石特征控制的火成岩风化程度自动模型评价器。评价器能够根据训练器得到的响应信息最优模型计算对隧洞中TBM掘进前方所遇到的火成岩的风化程度进行评价。
所述数据输出系统，输出模型将待评价的火成岩中所含的长石特征与数据存储中心中的各种信息进行对比，通过火成岩石自动模型评价器对待评价的火成岩风化程度进行评价，并根据不同阈值作具体规定。前期勘测过程中不同位置的火成岩石实测评价资料作为评价参考，以及在开挖过程中不断获得火成岩石风化程度评价资料，不断提高模型精度。
系统还包括无线传输系统和数据存储中心。数据存储中心存储各类长石成分及含量数据及预设的火成岩风化评价阈值，获取的岩石数据及经数据输出系统评价得到的火成岩风化等级数据存储在数据存储中心。
基于上述系统的工作方法，操作步骤如下：
前期采集TBM隧道在开挖前期的火成岩岩石样品，图像扫描装置对所取岩石样品外表形貌进行扫描，获取岩石外表形貌特征；XRF测试装置及XRD测试装置获取样品火成岩中的元素种类和丰度信息、长石的不同化学成分和含量； 利用计算机分析样品元素和矿物数据，相应配套软件分析元素数据以及矿物数据，得到长石化学分类特征及含量特征；利用显微装置提取目标火成岩的解理特征、干涉色特征、突起特征和晶体结构特征。
将上述特征传输至深度学习模块，通过人工预设评价标准阈值，利用智能算法学习岩石所对应的图像信息和长石特征信息，对图像中火成岩石风化特征进行提取，相应的所设定的评价标准阈值作为主要评价参考依据，辅助神经网络训练器学习建立自动模型评价器。
TBM在隧洞中掘进，掌子面及洞壁挖掘获得到的岩石样品，通过图像扫描模块和岩石测试模块对样品岩性及风化程度进行识别与初步估算，对样品中长石元素及矿物特征进行测试，得到不同火成岩石中的长石特征信息。通过无线传输系统将上述过程获得的数据传送至数据分析系统；
数据分析系统中显微图像模块及计算机分析模块对火成岩显微晶体结构及化学元素和矿物成分含量进行分析，将得到的长石特征信息并图像信息传输至深度学习模块。自动模型评价器根据之前得到的评价模型对火成岩石风化程度进行评价，并将评价结果传输至数据存储中心存储起来，增加数据库数据，进而继续服务于下一次评价。
本领域内的技术人员应明白，本公开的实施例可提供为方法、系统、或计算机程序产品。因此，本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开是参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
以上所述仅为本公开的优选实施例而已，并不用于限制本公开，对于本领域的技术人员来说，本公开可以有各种更改和变化。凡在本公开的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本公开的保护范围之内。
上述虽然结合附图对本公开的具体实施方式进行了描述，但并非对本公开保护范围的限制，所属领域技术人员应该明白，在本公开的技术方案的基础上， 本领域技术人员不需要付出创造性劳动即可做出的各种修改或变形仍在本公开的保护范围以内。

Claims (10)

  1. 一种隧道火成岩风化程度确定系统，其特征是：包括：
    数据采集系统，被配置为获取掌子面前方岩石试样，对岩石试样进行图像扫描和成分检测，并将部分样品制成玻片；
    数据传输模块，被配置为将数据采集系统获取的玻片标本通过传送带传输给数据分析系统，获取的图像扫描结果和岩石成分信息通过无线传输给数据分析系统；
    数据分析系统，被配置为构建深度学习模型，所述模型基于已存储的图像扫描结果和岩石成分信息进行训练，得到各图像扫描结果和岩石成分信息与相应风化程度的对应关系，并接收待确定的前方岩石图像扫描结果和岩石成分信息，利用训练后的模型进行分析，得到隧道前方风化程度。
  2. 如权利要求1所述的一种隧道火成岩风化程度确定系统，其特征是：所述数据采集系统包括岩石取样模块、图像扫描模块和岩石测试模块，其中，所述岩石取样模块对隧洞掘进过程中的岩石进行取样及制片，岩石取样模块包括取样机构和机械臂，取样机构搭载于机械臂，所述取样机构包括拾取装置和钻机，拾取装置直接对传送带上岩渣进行拾取，钻机用于对位于掌子面附近的岩壁进行岩芯钻取；
    所述图像扫描模块配置为照相机，对所取岩石样品外表形貌进行拍照扫描，获取岩石外表形貌特征；
    所述岩石测试模块包括XRF测试装置和XRD测试装置，XRF测试装置利用手持式设备，用于获取样品火成岩中的元素种类及丰度信息，XRD装置配置样品收取钵，用于对岩渣岩粉进行测试，基于长石的不同化学成分，鉴定区分出 不同的长石端元。
  3. 如权利要求1所述的一种隧道火成岩风化程度确定系统，其特征是：所述数据分析系统，包括显微图像模块、计算机分析模块和深度学习模块，其中，所述显微图像模块为偏光显微装置，对经由传送带传输过来的数据采集系统制成的岩石玻片样品进行显微成像，获取岩石偏光显微镜下图像，辅助挑选长石颗粒；
    所述计算机分析模块被配置为基于XRF及XRD装置的相关数据，通过测试获取长石种类及含量衍射图谱数据，并统计长石类别及含量，对比已有的长石元素含量类型及衍射图谱数据信息，对XRF及XRD装置获取的数据进行处理修正；所述深度学习模块，被配置为基于神经网络模型对数据进行学习训练。
  4. 如权利要求1所述的一种隧道火成岩风化程度确定系统，其特征是：所述深度学习模块在形成火成岩石不同风化程度判别模型时，根据预设的不同长石特征级别标准阈值，整合训练的特征量，按照预置的分类标准，建立火成岩石风化程度自动模型评价器。
  5. 如权利要求1所述的一种隧道火成岩风化程度确定系统，其特征是：所述数据输出系统，输出模型将待评价的火成岩中所含的长石特征与数据存储中心中的各种信息进行对比，通过火成岩石自动模型评价器对待评价的火成岩风化程度进行评价，并根据不同阈值作具体规定。
  6. 如权利要求1所述的一种隧道火成岩风化程度确定系统，其特征是：
    还包括数据存储中心，被配置为存储已有隧道岩石样本图像扫描结果和岩石成分信息与相应风化程度，预设的不同长石特征标准阈值。
  7. 一种隧道火成岩风化程度确定方法，其特征是：
    包括以下步骤：
    构建深度学习模型，基于已存储的图像扫描结果和岩石成分信息进行训练，得到各图像扫描结果和岩石成分信息与相应风化程度的对应关系；
    获取掌子面前方岩石试样，对岩石试样进行图像扫描和成分检测，利用训练后的模型，对检测的结果进行分析，得到隧道前方火成岩风化程度。
  8. 如权利要求7所述的方法，其特征是：火成岩风化程度的分级包括：
    当长石中仅含有K元素时，其抗风化能力最强，Na元素其次，仅含有Ca元素时其抗风化能力最差，当同时含有Na和Ca元素时，其抗风化能力随着Ca元素含量的增多而增强，即正长石>酸性斜长石>中性斜长石>基性斜长石；
    岩体的晶体结构保存的越完好，风化程度越低；
    长石所占的含量百分比越高，风化程度越低。
  9. 一种计算机可读存储介质，其特征是：其中存储有多条指令，所述指令适于由终端设备的处理器加载并执行权利要求7或8所述的一种隧道火成岩风化程度确定方法的部分或全部步骤。
  10. 一种终端设备，其特征是：包括处理器和计算机可读存储介质，处理器用于实现各指令；计算机可读存储介质用于存储多条指令，所述指令适于由处理器加载并执行权利要求7或8所述的一种隧道火成岩风化程度确定方法的部分或全部步骤。
PCT/CN2020/135314 2020-01-21 2020-12-10 隧道火成岩风化程度确定系统及方法 WO2021147553A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010071305.7A CN111261236A (zh) 2020-01-21 2020-01-21 隧道火成岩风化程度确定系统及方法
CN202010071305.7 2020-01-21

Publications (1)

Publication Number Publication Date
WO2021147553A1 true WO2021147553A1 (zh) 2021-07-29

Family

ID=70952457

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/135314 WO2021147553A1 (zh) 2020-01-21 2020-12-10 隧道火成岩风化程度确定系统及方法

Country Status (2)

Country Link
CN (1) CN111261236A (zh)
WO (1) WO2021147553A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111261236A (zh) * 2020-01-21 2020-06-09 山东大学 隧道火成岩风化程度确定系统及方法
CN113624649B (zh) * 2021-08-05 2023-12-08 西安航空学院 基于机器视觉的路用集料针片状含量检测系统及方法
CN114135277A (zh) * 2021-11-11 2022-03-04 山东大学 基于地化特征随钻感知的隧道超前地质预报方法及系统
CN114965315A (zh) * 2022-05-18 2022-08-30 重庆大学 一种基于高光谱成像的岩体损伤劣化快速评估方法
CN115082454B (zh) * 2022-07-27 2022-12-09 深圳市信润富联数字科技有限公司 岩芯判别方法、装置、电子设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103134555A (zh) * 2013-02-25 2013-06-05 北京化工大学 一种石质文物构件风化及安全等级定量评价方法
CN109256179A (zh) * 2018-10-12 2019-01-22 中石化石油工程技术服务有限公司 一种基于岩石元素的风化指数确定方法及装置
CN110031493A (zh) * 2019-04-04 2019-07-19 山东大学 基于图像与光谱技术的岩性智能识别系统与方法
CN110472597A (zh) * 2019-07-31 2019-11-19 中铁二院工程集团有限责任公司 基于深度学习的岩石图像风化程度检测方法及系统
CN111261236A (zh) * 2020-01-21 2020-06-09 山东大学 隧道火成岩风化程度确定系统及方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103913477B (zh) * 2014-04-16 2016-06-15 国家黄金钻石制品质量监督检验中心 一种泰山玉的产地鉴定方法
CN109163997B (zh) * 2018-09-18 2020-12-11 天津大学 一种基于声谱图深度学习的岩石表面强度测定方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103134555A (zh) * 2013-02-25 2013-06-05 北京化工大学 一种石质文物构件风化及安全等级定量评价方法
CN109256179A (zh) * 2018-10-12 2019-01-22 中石化石油工程技术服务有限公司 一种基于岩石元素的风化指数确定方法及装置
CN110031493A (zh) * 2019-04-04 2019-07-19 山东大学 基于图像与光谱技术的岩性智能识别系统与方法
CN110472597A (zh) * 2019-07-31 2019-11-19 中铁二院工程集团有限责任公司 基于深度学习的岩石图像风化程度检测方法及系统
CN111261236A (zh) * 2020-01-21 2020-06-09 山东大学 隧道火成岩风化程度确定系统及方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LI RIYUN, WU LINFENG: "RESEARCH ON CHARACTERISTIC INDEXES OF WEATHERING INTENSITY OF ROCKS", CHINESE JOURNAL OF ROCK MECHANICS AND ENGINEERING, INSTITUTE OF ROCK AND SOIL MECHANICS, CHINESE ACADEMY OF SCIENCES, vol. 23, no. 22, 1 November 2004 (2004-11-01), pages 3830 - 3833, XP055831300, ISSN: 1000-6915 *

Also Published As

Publication number Publication date
CN111261236A (zh) 2020-06-09

Similar Documents

Publication Publication Date Title
WO2021147553A1 (zh) 隧道火成岩风化程度确定系统及方法
WO2021147554A1 (zh) 基于长石特征的隧洞内碎屑岩抗风化能力判别系统与方法
WO2020181923A1 (zh) 基于tbm岩-机参数动态交互机制的隧洞可掘进预测方法及系统
CN105938611B (zh) 基于随钻参数对地下工程围岩快速实时分级的方法
CN102930253B (zh) 一种基于图像离散多小波变换的煤岩识别方法
CN104612675B (zh) 一种碳酸盐岩地层随钻岩性快速识别方法
CN109612943A (zh) 基于机器学习的隧洞岩石石英含量测试系统及方法
CN113685188B (zh) 一种基于岩渣物理特征的tbm掘进优化方法
CN111222683B (zh) 一种基于pca-knn的tbm施工围岩综合分级预测方法
CN109886534A (zh) 用于隧道围岩分级的辨识方法及装置
CN101923084A (zh) 一种矿用水源识别方法及识别设备
CN107764192A (zh) 一种滑坡多点位移智能监测装置及监测方法
US20210270987A1 (en) Method for creating statistics on content of rock debris in conglomerate reservoir
WO2019167030A1 (en) Identifying and logging properties of core samples
Kiipli et al. Composition and correlation of volcanic ash beds of Silurian age from the eastern Baltic
CN115062375A (zh) 一种用于隧道围岩的分级方法及系统
CN114330841A (zh) 一种基于机器学习的海底硫化物成矿定量预测方法
CN112801035B (zh) 基于知识与数据双驱动的搭载式岩性智能识别方法及系统
CN117522149B (zh) 一种隧道安全风险识别方法、装置和安全管理平台
CN106777707A (zh) 一种利用改进的蜘蛛网图进行测井岩性定量识别的方法
CN117789064A (zh) 一种基于多源数据的公路边坡无人机巡检预警系统
CN109656906A (zh) 一种基于大数据的勘查资料的处理方法
CN109886421B (zh) 基于集成学习的群智能采煤机切割模式识别系统
CN105350963B (zh) 一种基于相关性度量学习的煤岩识别方法
CN115046516A (zh) 基于单滑面r型深孔测斜曲线的滑动面位置精准确定方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20915212

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20915212

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20915212

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC