WO2021147554A1 - 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 - Google Patents

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 Download PDF

Info

Publication number
WO2021147554A1
WO2021147554A1 PCT/CN2020/135315 CN2020135315W WO2021147554A1 WO 2021147554 A1 WO2021147554 A1 WO 2021147554A1 CN 2020135315 W CN2020135315 W CN 2020135315W WO 2021147554 A1 WO2021147554 A1 WO 2021147554A1
Authority
WO
WIPO (PCT)
Prior art keywords
weathering
feldspar
rock
module
data
Prior art date
Application number
PCT/CN2020/135315
Other languages
English (en)
French (fr)
Inventor
李术才
许振浩
邵瑞琦
刘福民
谢辉辉
余腾飞
林鹏
潘东东
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
Priority to US17/619,203 priority Critical patent/US11933713B2/en
Publication of WO2021147554A1 publication Critical patent/WO2021147554A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light
    • 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
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/24—Earth materials
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N1/00—Sampling; Preparing specimens for investigation
    • G01N1/02—Devices for withdrawing samples
    • G01N1/04—Devices for withdrawing samples in the solid state, e.g. by cutting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N1/00—Sampling; Preparing specimens for investigation
    • G01N1/02—Devices for withdrawing samples
    • G01N1/04—Devices for withdrawing samples in the solid state, e.g. by cutting
    • G01N1/08—Devices for withdrawing samples in the solid state, e.g. by cutting involving an extracting tool, e.g. core bit
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N1/00—Sampling; Preparing specimens for investigation
    • G01N1/02—Devices for withdrawing samples
    • G01N1/04—Devices for withdrawing samples in the solid state, e.g. by cutting
    • G01N2001/045—Laser ablation; Microwave vaporisation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/07—Investigating materials by wave or particle radiation secondary emission
    • G01N2223/076—X-ray fluorescence
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/60—Specific applications or type of materials
    • G01N2223/616—Specific applications or type of materials earth materials
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
    • G01N23/223—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material by irradiating the sample with X-rays or gamma-rays and by measuring X-ray fluorescence
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
    • G01N23/225—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion
    • G01N23/2251—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion using incident electron beams, e.g. scanning electron microscopy [SEM]

Definitions

  • the present disclosure belongs to the field of rock and soil weathering resistance testing, and relates to a system and method for judging the weathering resistance of clastic rocks in tunnels based on the characteristics of feldspar.
  • Feldspar minerals are the most common silicate minerals in the earth's crust. As the most important rock-forming minerals in the lithosphere, their characteristics are closely related to the structure, hardness, compressive strength, and weathering resistance of rocks. The crystallization temperature of feldspar is lower, second only to quartz and muscovite, so it belongs to a class of minerals with strong resistance to weathering in nature. However, the traditional methods of research on rock hardness or its resistance to weathering mostly focus on the consideration of quartz, and the relative relationship between feldspar and rock resistance to weathering is rarely considered. However, the distribution of feldspar in the lithosphere is more extensive. Need to consider as much as possible to find a mineral factor that can be adapted to a variety of rocks, feldspar is a good choice.
  • the current evaluation of the resistance to weathering of clastic rocks lacks consideration of the characteristics of feldspar, and the lack of consideration of the characteristics of feldspar, resulting in fewer types of rocks that can be studied, and a small amount of use
  • the quartz content is used to infer the degree of weathering resistance of the rock and other phenomena, resulting in a large range of observation errors.
  • the present disclosure proposes a system and method for determining the anti-weathering ability of clastic rocks in tunnels based on the analysis of the characteristics of feldspar.
  • the present disclosure judges its anti-weathering ability by studying the characteristics of feldspars in the tunnel clastic rocks. The gaps in the prediction research on the anti-weathering ability of the surrounding rock of the tunnel are discussed.
  • the present disclosure adopts the following technical solutions:
  • the discrimination system for the anti-weathering ability of clastic rocks in the tunnel based on the analysis of feldspar characteristics including:
  • the automatic scanning module is configured to collect all-round images of the rock formation before the sample is obtained;
  • the element analysis module is configured to collect basic chemical element information contained in the sample
  • the microscopic image module is configured to extract the cleavage characteristics, interference color characteristics, protrusion characteristics and crystal structure characteristics of the feldspar in the sample;
  • the wireless transmission module is configured to transmit the data obtained by the automatic scanning module and the element analysis module to the data analysis center;
  • the data analysis center obtains cleavage information and crystal structure information by extracting image characteristics and element characteristics, and then determines the level of the anti-weathering ability of the rock formation.
  • the sampling mechanism includes a rock breaking mechanism and a sampling mechanical arm mounted on a TBM
  • the rock breaking mechanism includes a laser rock breaking device and a drilling rig, wherein the laser rock breaking system cuts a block sample by laser,
  • the drilling rig drills for powdered samples, and the sampling robotic arm can move in multiple dimensions.
  • the automatic scanning device is equipped with a high-definition fully automatic wide-angle camera lens to collect high-definition image information of the research rock formation.
  • the elemental analysis module includes an X-ray analysis device.
  • it also includes a mineral quantification module, including an electronic probe system, to quantitatively analyze the content of various feldspars in the sample.
  • a mineral quantification module including an electronic probe system, to quantitatively analyze the content of various feldspars in the sample.
  • the data analysis center includes a lithology comparison module and a deep learning module, where the lithology comparison module receives information obtained by the automatic scanning module, element analysis module, and microscopic image module, and works in collaboration with the deep learning module;
  • the deep learning module is configured to extract image features and element features to feed back basic lithology information, compare the element content of various feldspars with existing data, obtain cleavage information and crystal structure information, and then perform classification. Get the level of resistance to weathering of the rock formation.
  • the deep learning module includes an artificially assisted neural network trainer and an automatic model predictor.
  • the artificially assisted neural network trainer stores preliminary tunnel excavation rock data, various surface rock data, and oil and coal field data. Drilling lithology data is used as training data to obtain the type and content of feldspar in the rock to classify a single feature anti-weathering level, and to give the basic lithological characteristics of the rock; the automatic model predictor is configured to classify according to the degree of weathering resistance The model is expanded and classified, and the final prediction result is output.
  • block samples and powder samples were randomly taken on the tunnel face, and the tunnel face was scanned in all directions to obtain image information and analyze the element types in the sample;
  • the model is built through neural network learning, and through repeated comparisons with existing data, the cleavage type and interference color characteristics of feldspar are finally obtained , Protrusion features, etc., and the crystal structure features of feldspar are used to classify the weathering resistance level of a single feature;
  • the process of grading the anti-weathering grade of a single feature includes: according to different feldspar types to provide discrimination standards, orthoclase>acid plagioclase>neutral plagioclase>basic plagioclase
  • feldspar contains only K element, its anti-weathering ability is the strongest, Na element is second, and its anti-weathering ability is worst when it contains only Ca element.
  • it contains both Na and Ca elements its anti-weathering ability is the same as Na element. The increase in content increases.
  • the process of grading the anti-weathering grade of a single feature includes: the higher the content of feldspar in the rock, the stronger its anti-weathering ability.
  • the process of grading the anti-weathering grade of a single feature includes: the better the crystal shape of the mineral is preserved, the more stable it is, and the higher its anti-weathering ability is.
  • the present disclosure provides a method for evaluating the anti-weathering ability of clastic rocks in tunnels by using minerals that are more widely present in the earth's crust, overcomes the shortcomings of current experimental methods, is easy to operate, and can be used to detect the types, content, and crystal structure of feldspar in rock formations This information is combined with computer deep learning methods to integrate this information to judge the weathering resistance of clastic rocks containing different types of feldspar in the tunnel, and the judgment is highly accurate.
  • Figure 1 is a diagram of the overall system structure of this embodiment
  • FIG. 2 is a schematic diagram of the installation of the TBM data acquisition system and wireless transmission module in the tunnel;
  • Figure 3 is a schematic diagram of the installation of the sampling mechanism and the automatic scanning module in the data acquisition system on the TBM front-end robotic arm;
  • Figure 4 is a simplified diagram of the actual operation of data analysis, output and storage, display module and mineral quantitative analysis module.
  • the system and method for judging the anti-weathering ability of clastic rock in the tunnel based on the analysis of feldspar characteristics includes a data acquisition system, a wireless transmission system, a data analysis system, a data output and storage center, and each system includes There are different modules.
  • the sampling mechanism, automatic scanning module, and element analysis module in the data acquisition system are installed on the front end of the TBM through a robotic arm.
  • the sampling mechanism and automatic scanning module can be used when the TBM is stopped. Multi-directional random sampling and omni-directional image acquisition;
  • the element analysis module is equipped with an X-ray analyzer to collect basic chemical element information contained in the rock;
  • the microscopic image module and the mineral quantification module are placed in the remote control laboratory, and the data obtained is transmitted to the deep learning module;
  • the microscopic image module is equipped with a high-resolution partial microscope, which is mainly used to extract the cleavage characteristics, interference color characteristics, protrusion characteristics and crystal structure characteristics of feldspar to transmit to the learning module for grading;
  • the mineral quantification module is equipped with an electronic probe system. Because the X-ray system can only measure element types semi-quantitatively and cannot quantitatively study, the probe system can further quantitatively analyze the content of various feldspars for the learning system to analyze and grade;
  • the wireless transmission system is mounted at the end of the information acquisition system to transmit the data obtained by the automatic scanning module and element analysis module in the acquisition system to the data analysis system;
  • the data analysis system includes a lithology comparison module and a deep learning module;
  • the lithology comparison module receives information from the data acquisition system, and works with the deep learning module;
  • the lithology recognition system is embedded with the lithology library, and the learning module can feed back basic lithology information by extracting image features and element features;
  • the deep learning module includes artificial auxiliary neural network trainer and automatic model predictor;
  • the trainer has received a large amount of preliminary tunnel excavation rock data, various surface rock data and drilling lithology data of domestic oil fields and coal fields, and these data are stored in the data storage center, and the trainer can continuously obtain from the data storage center Training with new 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 principle one and principle two;
  • the trainer receives the microscopic image module information, performs image learning, and extracts data. It is also continuously compared with the existing data in the storage system to obtain cleavage information and crystal structure information, and perform classification according to principle three;
  • the trainer finally combines the three classifications to give the level of the anti-weathering ability of the rock formation according to the preset classification standards;
  • the predictor compares the results to be detected with the results of various rock samples manually analyzed in the data storage center, and uses the model trained by the trainer to determine the corresponding relationship between the feldspar in the rock and the anti-weathering ability as an auxiliary prediction.
  • the data acquisition system collects data on the tunnel face during any shutdown period of the TBM.
  • the automatic high-definition camera scans the tunnel face.
  • the laser rock breaking equipment is used to randomly sample the tunnel face, and the small impact drill takes powder samples.
  • Preliminary identification of various chemical elements in the rock formation is carried out through the equipped X-ray analysis equipment and the corresponding data interpretation system.
  • an electronic probe system is required for elemental compounds or minerals. Quantitative analysis.
  • the microscopic image module refers to the different microscopic characteristics of feldspar, such as: two groups of orthoclase intersect at 90°, while plagioclase does not cross at 90°.
  • the crystal shape is recognized (auto-shaped, semi-automatic). Shape, other shape), interference color recognition (the interference color of orthoclase is first-class gray-gray white, the interference color of plagioclase is first-class yellow, parallel extinction), protrusion recognition (positive feldspar is negative protrusion, plagioclase is positive Protrusion).
  • orthoclase (potassium feldspar)> acid plagioclase (albite, austenitic)> neutral plagioclase (medium feldspar)> basic plagioclase Feldspar (labradorite, feldspar, anorthite).
  • Principle 3 Crystal structure. If a mineral has sufficient crystallization time and growth space during crystallization, 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 it is, the higher its resistance to weathering.
  • the final judgement level of the feldspar characteristics on the degree of weathering of the rock formation is finally determined: at least one level 1 and level 2 or two level 2 are superior in weathering resistance, and only one level 1 or level 2 exists.
  • the anti-weathering ability is medium, and there is no one level 1 or 2, the anti-weathering ability is poor.
  • the working process mainly includes the following steps:
  • the information acquisition system (1) starts to work, in which the sampling module (2) starts to randomly sample block samples (2a) and powder samples (2b) on the face of the face, and the scanning module (3) starts to match the palms
  • the sub-surface starts to scan the acquired image information in all directions
  • the element analysis module (4) analyzes the element types in the sample, and finally transmits the data obtained in the above process to the lithology comparison module (8) through the wireless transmission system (7);
  • the microscopic image module (5) transfers the extracted images containing cleavage features, interference color features, protrusion features and crystal structure features to the data analysis system (9), and the trainer (10) learns through the neural network Establish a model, and through repeated comparisons with the existing data in the data storage space (13), it is finally necessary to obtain the cleavage type, interference color characteristics, protrusion characteristics, etc. of the feldspar and the crystal structure characteristics of the feldspar to classify the anti-weathering level of a single feature;
  • the mineral quantification module (6) can quantitatively obtain the main types of minerals in the sample, and the trainer (10) in the data analysis system (9) combines the mineral quantitative analysis results with the elemental analysis data from the lithology comparison module (8) As well as image data, the type and content of feldspar in the rock can be obtained through the model that has been established through the preliminary learning of the neural network to classify the anti-weathering level of a single feature, and the basic lithological characteristics of the rock can also be given;
  • the learning system will integrate all the above information, expand the classification through the embedded anti-weathering degree classification model, and output the final prediction result (12);
  • the data output system outputs the data to the storage center and stores it (13);
  • 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

  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Environmental & Geological Engineering (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Geology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Remote Sensing (AREA)
  • Biomedical Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Food Science & Technology (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Ecology (AREA)
  • Environmental Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

一种判别装置，基于长石特征对隧洞内碎屑岩抗风化能力进行判别，用于探测岩层中长石的种类以及含量、晶体结构等信息，并利用计算机深度学习整合信息，以判断隧洞内含不同类型长石的碎屑岩岩层的抗风化能力。判别装置克服了目前实验方法的不足，易于操作，准确度高。

Description

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 技术领域
本公开属于岩土抗风化测试领域，涉及一种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。
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。
长石类矿物是地壳中最为常见的硅酸盐矿物，作为岩石圈最为重要的造岩矿物，其特征与岩石的结构构造、硬度、抗压程度以及其抗风化能力有着非常紧密的联系，由于长石的结晶温度较低，仅次于石英和白云母，因此在自然界中属于抗风化能力较强的一类矿物。但传统方法对岩石硬度或其抗风化能力的研究多集中于对石英的考量，对长石与岩石抗风化能力的相对关系考虑很少，但是长石在岩石圈中的分布更为广泛，如果需要考虑尽可能找到一个可以适应于多种岩石的矿物因素，长石不失为一个很好的选择。
碎屑岩中的矿物多数是由岩浆岩风化后经过搬运而沉积的，长石作为已经风化后的产物而继续保存下来，说明其有很强的抗风化能力，尽管碎屑岩中同样也存在大量的石英，但长石对碎屑岩抗风化能力也同样有非常重要的影响。但据发明人了解,目前对于碎屑岩抗风化能力的评价中,缺少长石特征的考虑,而缺少对长石特征的考虑，致使所能研究的岩石类别较少，同时会出现利用少量的石英含量来推测岩石的抗风化程度等现象，导致观测的误差范围较大。
发明内容
本公开为了解决上述问题，提出了基于长石特征分析的隧洞内碎屑岩抗风化能力判别系统与方法，本公开通过研究隧道碎屑岩中长石的特征来判断其抗风化的能力，填补了研究隧道围岩在抗风化能力方面预测研究的空白。
根据一些实施例，本公开采用如下技术方案：
基于长石特征分析的隧洞内碎屑岩抗风化能力判别系统，包括：
取样机构，搭载于TBM前方，获取掌子面的岩块或/和岩粉试样；
自动扫描模块，被配置为对获取试样前的岩层进行全方位图像采集；
元素分析模块，被配置为对试样中所含基本化学元素信息进行采集；
显微图像模块，被配置为对试样中长石的解理特征、干涉色特征、突起特征以及晶体结构特征进行提取；
无线传输模块，被配置为将自动扫描模块、元素分析模块获取的数据传输至数据分析中心；
所述数据分析中心根据获取的信息，通过提取图像特征以及元素特征，获取解理信息与晶体结构信息，进而确定岩层抗风化能力的级别。
作为可选择的实施方式，所述取样机构包括搭载于TBM上的破岩机构和取样机械臂，所述破岩机构包括激光破岩装置和钻机，其中激光破岩系统通过激光切取块状样品，钻机钻取粉末状样品，取样机械臂可多维运动。
作为可选择的实施方式，自动扫描设备搭载有高清全自动广角拍照镜头，用以采集研究岩层的高清图像信息。
作为可选择的实施方式，所述元素分析模块包括X射线分析设备。
作为可选择的实施方式，还包括矿物定量模块，包括电子探针系统，对试样中各类长石的含量进行定量分析。
作为可选择的实施方式，数据分析中心包括岩性对比模块与深度学习模块，其中，岩性对比模块接收自动扫描模块、元素分析模块和显微图像模块获取的信息，与深度学习模块协同工作；
深度学习模块被配置为提取图像特征以及元素特征，以反馈出基本的岩性信息，根据各类长石的元素含量与已有数据进行对比，获取解理信息与晶体结构信息，进而进行分级，得到岩层抗风化能力的级别。
作为可选择的实施方式，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预测器，所述人工辅助神经网络训练器存储有先期隧洞开挖岩石数据以及各类地表岩石数据以及油田及煤田的钻井岩性数据，作为训练数据，获得岩石中长石的类型和含量用以划分单个特征抗风化级别，给出岩石的基本岩性特征；所述自动模型预测器被配置为根据抗风化程度分级模型展开分级，并输出最终预测结果。
基于长石特征分析的隧洞内碎屑岩抗风化能力判别系统与方法，包括以下步骤：
提前采集隧道在开挖前期的碎屑岩岩石样品、地表碎屑岩岩石样品、油田或煤田钻井岩心样品，获取其图像特征、元素特征、显微特征、晶体特征以及矿物特征等，利用不同风化等级的判定标准来完成训练模型；
在TBM停机期间，在掌子面随机采取块状样和粉末样，对掌子面开始全方位扫描已获取图像信息，分析样品中的元素类型；
根据提取到的包含解理特征、干涉色特征、突起特征和晶体结构特征的图像，通过神经网络学习建立模型，通过与已有数据反复对比，最终需得到长石的解理类型、干涉色特征、突起特征等和长石的晶体结构特征用以划分单个特征抗风化级别；
定量的获取样品中矿物的主要类型，结合矿物定量分析结果和元素分析数据以及图像数据，通过神经网络先期学习已建立起的模型获得岩石中长石的类型和含量用以划分单个特征抗风化级别，给出岩石的基本岩性特征；
将整合上述所有信息，并通过已嵌入的抗风化程度分级模型展开分级，并输出最终预测结果。
作为可选择的实施方式，单个特征抗风化级别的分级的过程包括：按照不同长石的种类提供判别标准来看，正长石>酸性斜长石>中性斜长石>基性斜长石，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Na元素含量的增多而增强。
作为可选择的实施方式，单个特征抗风化级别分级的过程包括：长石本在岩石中的含量越高，其抗风化能力就越强。
作为可选择的实施方式，单个特征抗风化级别分级的过程包括：矿物的晶体形状保存的越完好则说明其更加稳定，其抗风化能力也越高。
与现有技术相比，本公开的有益效果为：
本公开提供一种利用地壳中更为广泛存在的矿物来评价隧洞内碎屑岩的抗风化能力，克服目前实验方法的不足，易于操作，可用于探测岩层中长石的种 类以及含量、晶体结构等信息，并结合计算机深度学习的方法整合这些信息来判断隧洞内含不同类型长石的碎屑岩的抗风化能力，判断准确度高。
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是本实施例整体系统结构图；
图2是隧道内TBM数据采集系统与无线传输模块安装示意图；
图3是TBM前端机械臂上数据采集系统中采样机构和自动扫描模块安装示意图；
图4是数据分析、输出与储存以及显模块和矿物定量分析模块实际运行简图。
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，基于长石特征分析的隧洞内碎屑岩抗风化能力判别系统与方法，其包括数据采集系统、无线传输系统、数据分析系统、数据输出与存储中心，各个系统中又包含有不同模块。
如图2、图3和图4所示，数据采集系统中的取样机构、自动扫描模块和元素分析模块通过机械臂安装于TBM前端，其中取样机构和自动扫描模块可在TBM停机时对掌子面进多方位随机取样以及全方位图像采集；
元素分析模块搭载有X射线分析仪，对岩石中所含基本化学元素信息进行采集；
此外，显微图像模块和矿物定量模块置于远程控制实验室，其所获得的数据传送至深度学习模块；
其中显微图像模块搭载有高分辨率的偏关显微镜主要用以提取长石的解理特征、干涉色特征、突起特征以及晶体结构特征以传输给学习模块进行分级；
矿物定量模块搭载电子探针系统，由于X射线系统只能半定量的测量元素类别，无法定量研究，因此探针系统可进一步定量分析各类长石的含量以供学习系统开展分析并定级；
无线传输系统搭载于信息采集系统末端，用以将采集系统中自动扫描模块和元素分析模块获得的数据传输至数据分析系统；
数据分析系统至于远程控制室，包括岩性对比模块与深度学习模块；
其中岩性对比模块接收来自数据采集系统的信息，通过与深度学习模块协同工作；
岩性识别系统嵌入了岩性库，学习模块通过提取图像特征以及元素特征后可以反馈出基本的岩性信息；
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预测器；
其中训练器已经接收了大量的先期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新的数据开展训练；
训练器接收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，最终可按照原理一和原理二进行分级；
训练器接收显微图像模块信息，进行图像学习，提取数据，同样是与存储系统中已有的数据不断进行对比，获取解理信息与晶体结构信息，依据原理三进行分级；
训练器最终结合三类分级按照预置的分类标准给出岩层抗风化能力的级别；
预测器将待检测的结果与数据存储中心中人工分析的各类岩样结果进行比较，通过训练器训练出的模型判断岩石中长石与抗风化能力的对应关系类，作为辅助预测。
数据采集系统在TBM任何停机期间进行对掌子面进行数据采集，全自动高清摄像头对掌子面进行扫描，使用激光破岩设备对掌子面开展随机取块样，小型冲击钻机取粉末样，通过搭载的X射线分析设备及对应的数据解译系统进行岩层中各类化学元素初步识别，但由于长石发育有大量的类质同象问题，从而需要电子探针系统进行元素化合物或者矿物的定量分析。
显微图像模块是指依据长石的显微特性不同，如：正长石两组节理呈90°相交，斜长石不呈90°，此外，对其晶体形状进行识别(自形、半自形、它形)，干涉色识别(正长石干涉色为一级灰—灰白，斜长石干涉色一级黄，平行消光)，突起识别(正长石为负突起、斜长石为正突起)。
原理一：矿物的结晶温度越低其抗风化能力便越强，不同的长石其结晶顺序有明显的先后关系，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，而在斜长石中则以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，我们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，其抗风化能力随Na元素含量的增多而增强。
原理二：长石在碎屑岩石的碎屑中所占的比重，在碎屑岩中，长石本是原岩经过风化后的产物，这说明其本身具有较强的抗风化能力，因此，其在岩石中的含量越高，其抗风化能力就越强。
原理三：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，其抗风化能力也越高。
依据上述原理，并结合岩石圈中岩石的基本特征提出如下判别等级：若碎屑岩中的长石类型仅为钾长石—1级；钾长石>斜长石—2级；钾长石<斜长石—3级；仅为斜长石—4级。
若长石在碎屑岩占碎屑含量超过50％—1级；15％-50％—2级；5％-15％—3级；<5％-4级。
长石的晶体结构，自形含量>半自形+它形—1级；自形含量+半自形>它形—2级；自形含量≈半自形+它形—3级；自形含量+半自形<它形—4级。
按上述三个标准，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1级和2级或2个2级则抗风化能力为优，仅存在1个1级或2级则抗风化能力为中，不存在任何一个1级或2级则抗风化能力差。
基于长石特征分析的隧洞内碎屑岩抗风化能力判别系统与方法，其工作过程主要包括以下步骤：
1.采集隧道在开挖前期的碎屑岩岩石样品、地表碎屑岩岩石样品、油田、煤田钻井岩心样品，获取其图像特征、元素特征、显微特征、晶体特征，矿物特征等，将这些数据导入数据存储中心(13)以及训练器(10)，提供不同风化等级的判定标准来完成训练模型；
2.在TBM停机期间，信息采集系统(1)开始工作，其中取样模块(2)开始在掌子面随机采取块状样(2a)和粉末样(2b)，扫描模块(3)开始对掌子面开始全方位扫描已获取图像信息，元素分析模块(4)分析样品中的元素类型，最后通过无线传输系统(7)将上述过程获得的数据传送至岩性对比模块(8)；
3.同时，显微图像模块(5)将提取到的包含解理特征、干涉色特征、突起特征和晶体结构特征的图像传输至数据分析系统(9)，训练器(10)通过神经网络学习建立模型，通过与数据储存空间(13)已有数据反复对比，最终需得到长石的解理类型、干涉色特征、突起特征等和长石的晶体结构特征用以划分单个特征抗风化级别；
4.矿物定量模块(6)可以定量的获取样品中矿物的主要类型，数据分析系统(9)中的训练器(10)结合矿物定量分析结果和来自岩性对比模块(8)的元素分析数据以及图像数据，通过神经网络先期学习已建立起的模型可以获得岩石中长石的类型和含量用以划分单个特征抗风化级别，还可以给出岩石的基本岩性特征；
5.通过深度学习模块分析后，学习系统将整合上述所有信息，并通过已嵌入的抗风化程度分级模型展开分级，并输出最终预测结果(12)；
6.数据输出系统将数据输出到存储中心并储存(13)；
7.在TBM掘进过程中，系统未工作时，可不断用室内标准样品以及隧道开挖的岩块中获取的信息不断进行学习，以在最大程度上提高其准确可靠性；
8.重复2-7，开展下一阶段测试与分析。
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. 一种基于长石特征对隧洞内碎屑岩抗风化能力的判别装置，包括：
    取样机构，搭载于TBM前方，获取掌子面的岩块或/和岩粉试样；
    自动扫描模块，被配置为对获取试样前的岩层进行全方位图像采集；
    元素分析模块，被配置为对试样中所含基本化学元素信息进行采集；
    显微图像模块，被配置为对试样中长石的解理特征、干涉色特征、突起特征以及晶体结构特征进行提取；
    无线传输模块，被配置为将自动扫描模块、元素分析模块获取的数据传输至数据分析中心；
    所述数据分析中心根据获取的信息，通过提取图像特征以及元素特征，获取解理信息与晶体结构信息，进而确定岩层抗风化能力的级别。
  2. 如权利要求1所述的一种基于长石特征对隧洞内碎屑岩抗风化能力的判别装置，其特征是：所述取样机构包括搭载于TBM上的破岩机构和取样机械臂，所述破岩机构包括激光破岩装置和钻机，其中激光破岩系统通过激光切取块状样品，钻机钻取粉末状样品，取样机械臂可多维运动。
  3. 如权利要求1所述的一种基于长石特征对隧洞内碎屑岩抗风化能力的判别装置，其特征是：自动扫描设备搭载有高清全自动广角拍照镜头，用以采集研究岩层的高清图像信息。
  4. 如权利要求1所述的一种基于长石特征对隧洞内碎屑岩抗风化能力的判别装置，其特征是：所述元素分析模块包括X射线分析设备。
  5. 如权利要求1所述的一种基于长石特征对隧洞内碎屑岩抗风化能力的判 别装置，其特征是：还包括矿物定量模块，包括电子探针系统，对试样中各类长石的含量进行定量分析。
  6. 如权利要求1所述的一种基于长石特征对隧洞内碎屑岩抗风化能力的判别装置，其特征是：数据分析中心包括岩性对比模块与深度学习模块，其中，岩性对比模块接收自动扫描模块、元素分析模块和显微图像模块获取的信息，与深度学习模块协同工作；
    深度学习模块被配置为提取图像特征以及元素特征，以反馈出基本的岩性信息，根据各类长石的元素含量与已有数据进行对比，获取解理信息与晶体结构信息，进而进行分级，得到岩层抗风化能力的级别。
  7. 如权利要求1所述的一种基于长石特征对隧洞内碎屑岩抗风化能力的判别装置，其特征是：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预测器，所述人工辅助神经网络训练器存储有先期隧洞开挖岩石数据以及各类地表岩石数据以及油田及煤田的钻井岩性数据，作为训练数据，获得岩石中长石的类型和含量用以划分单个特征抗风化级别，给出岩石的基本岩性特征；所述自动模型预测器被配置为根据抗风化程度分级模型展开分级，并输出最终预测结果。
  8. 一种基于长石特征对隧洞内碎屑岩抗风化能力的判别方法，其特征是：包括以下步骤：
    提前采集隧道在开挖前期的碎屑岩岩石样品、地表碎屑岩岩石样品、油田或煤田钻井岩心样品，获取其图像特征、元素特征、显微特征、晶体特征以及矿物特征等，利用不同风化等级的判定标准来完成训练模型；
    在TBM停机期间，在掌子面随机采取块状样和粉末样，对掌子面开始全方位扫描已获取图像信息，分析样品中的元素类型；
    根据提取到的包含解理特征、干涉色特征、突起特征和晶体结构特征的图像，通过神经网络学习建立模型，通过与已有数据反复对比，最终需得到长石的解理类型、干涉色特征、突起特征等和长石的晶体结构特征用以划分单个特征抗风化级别；
    定量的获取样品中矿物的主要类型，结合矿物定量分析结果和元素分析数据以及图像数据，通过神经网络先期学习已建立起的模型获得岩石中长石的类型和含量用以划分单个特征抗风化级别，给出岩石的基本岩性特征；
    将整合上述所有信息，并通过已嵌入的抗风化程度分级模型展开分级，并输出最终预测结果。
  9. 如权利要求8所述的方法，其特征是：单个特征抗风化级别的分级的过程包括：按照不同长石的种类提供判别标准来看，正长石>酸性斜长石>中性斜长石>基性斜长石，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Na元素含量的增多而增强。
  10. 如权利要求8所述的方法，其特征是：单个特征抗风化级别分级的过程包括：长石本在岩石中的含量越高，其抗风化能力就越强；
    或，矿物的晶体形状保存的越完好则说明其更加稳定，其抗风化能力也越高。
PCT/CN2020/135315 2020-01-21 2020-12-10 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 WO2021147554A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/619,203 US11933713B2 (en) 2020-01-21 2020-12-10 Determining system and method for weathering resistant capability of clastic rocks in tunnel based on feldspar features

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010071313.1 2020-01-21
CN202010071313.1A CN111220616B (zh) 2020-01-21 2020-01-21 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

Publications (1)

Publication Number Publication Date
WO2021147554A1 true WO2021147554A1 (zh) 2021-07-29

Family

ID=70829691

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/135315 WO2021147554A1 (zh) 2020-01-21 2020-12-10 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

Country Status (3)

Country Link
US (1) US11933713B2 (zh)
CN (1) CN111220616B (zh)
WO (1) WO2021147554A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118551331A (zh) * 2024-07-30 2024-08-27 国网山东省电力公司电力科学研究院 基于鸟类定位的运行状态数据监测方法及设备

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111220616B (zh) * 2020-01-21 2021-06-01 山东大学 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
CN113435458B (zh) * 2021-02-08 2024-08-06 中国石油化工股份有限公司 基于机器学习的岩石薄片图像分割方法、装置及介质
CN112801035B (zh) * 2021-02-24 2023-04-07 山东大学 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
CN115761038B (zh) * 2022-10-19 2023-06-30 山东大学 一种基于图像光谱技术的隧道掌子面地质素描方法及系统
CN116718753B (zh) * 2023-05-31 2024-05-07 中国地质大学（北京） 一种土壤地球化学风化基因sg01及其构建方法和应用
CN116913416B (zh) * 2023-09-12 2023-12-26 中国地质大学（北京） 海蚀崖岩石风化程度定量评价及预测方法及装置
CN117332240B (zh) * 2023-12-01 2024-04-16 中铁四局集团有限公司 岩爆预测模型构建方法、存储介质、岩爆预测方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10105546A (ja) * 1996-09-26 1998-04-24 Pub Works Res Inst Ministry Of Constr 岩盤の風化度判定方法
DE102004063019A1 (de) * 2004-12-22 2006-07-13 Kurth, André Verfahren zur Herstellung von Abbildungen auf Naturstein
CN106485223A (zh) * 2016-10-12 2017-03-08 南京大学 一种砂岩显微薄片中岩石颗粒的自动识别方法
CN206016814U (zh) * 2016-09-18 2017-03-15 中铁工程装备集团有限公司 一种记录与分析tbm渣片的装置
CN109765097A (zh) * 2018-12-21 2019-05-17 中铁三局集团有限公司 一种基于rpd钻机的隧道围岩快速分类方法
CN110516730A (zh) * 2019-08-20 2019-11-29 中铁工程装备集团有限公司 基于pso-svm算法和图像识别的围岩质量在线分级方法
CN111220616A (zh) * 2020-01-21 2020-06-02 山东大学 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

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102261250A (zh) * 2010-05-31 2011-11-30 三一重型装备有限公司 一种硬岩液压破碎式掘进机
CN102053268B (zh) * 2010-11-18 2012-07-25 中国石油天然气股份有限公司 一种蚀变火山岩岩性识别方法及装置
KR101382381B1 (ko) * 2012-05-29 2014-04-08 대한민국 표면 반발 경도계를 이용한 암석의 풍화도지수 산출방법
CN102866099B (zh) * 2012-08-14 2015-04-08 北京矿产地质研究院 一种岩石风化深度的测定方法
CN102967548B (zh) * 2012-11-09 2015-08-19 中国水利水电科学研究院 一种岩石风化速度的测定方法
CN103744109B (zh) * 2013-12-26 2017-02-08 中国石油天然气股份有限公司 一种无井覆盖区碎屑岩风化壳结构的识别方法
CN105717149B (zh) * 2016-01-27 2018-08-24 中南大学 一种玄武岩风化程度的判别方法
CN108593531B (zh) * 2018-03-13 2021-11-23 成都理工大学 一种岩体风化程度快速量化评价方法及其应用
CN109187161B (zh) * 2018-08-30 2020-07-10 中国石油大学(北京) 一种碎屑岩中长石溶蚀程度的定量评价方法
CN109374456A (zh) * 2018-09-03 2019-02-22 山东大学 适用于隧道围岩质量分级及风化程度判别装置及方法
CN109256179B (zh) * 2018-10-12 2020-09-15 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
CN109344516B (zh) * 2018-10-12 2023-08-04 中石化石油工程技术服务有限公司 一种地质录井中随钻岩石风化势能指数确定方法及装置
CN109612943B (zh) * 2019-01-14 2020-04-21 山东大学 基于机器学习的隧洞岩石石英含量测试系统及方法
CN109886329A (zh) * 2019-02-18 2019-06-14 中国铁建重工集团有限公司 围岩破碎等级检测方法、检测系统和掘进设备
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
CN111221024B (zh) * 2019-09-06 2021-07-06 山东大学 Tbm搭载式隧道前方围岩放射性预报系统及方法
US20230105649A1 (en) * 2021-10-05 2023-04-06 Saudi Arabian Oil Company Determining weathering indices by x-ray diffraction

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10105546A (ja) * 1996-09-26 1998-04-24 Pub Works Res Inst Ministry Of Constr 岩盤の風化度判定方法
DE102004063019A1 (de) * 2004-12-22 2006-07-13 Kurth, André Verfahren zur Herstellung von Abbildungen auf Naturstein
CN206016814U (zh) * 2016-09-18 2017-03-15 中铁工程装备集团有限公司 一种记录与分析tbm渣片的装置
CN106485223A (zh) * 2016-10-12 2017-03-08 南京大学 一种砂岩显微薄片中岩石颗粒的自动识别方法
CN109765097A (zh) * 2018-12-21 2019-05-17 中铁三局集团有限公司 一种基于rpd钻机的隧道围岩快速分类方法
CN110516730A (zh) * 2019-08-20 2019-11-29 中铁工程装备集团有限公司 基于pso-svm算法和图像识别的围岩质量在线分级方法
CN111220616A (zh) * 2020-01-21 2020-06-02 山东大学 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

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118551331A (zh) * 2024-07-30 2024-08-27 国网山东省电力公司电力科学研究院 基于鸟类定位的运行状态数据监测方法及设备

Also Published As

Publication number Publication date
CN111220616B (zh) 2021-06-01
US11933713B2 (en) 2024-03-19
CN111220616A (zh) 2020-06-02
US20220317021A1 (en) 2022-10-06

Similar Documents

Publication Publication Date Title
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
WO2021147553A1 (zh) 隧道火成岩风化程度确定系统及方法
CN109612943B (zh) 基于机器学习的隧洞岩石石英含量测试系统及方法
CN104612675B (zh) 一种碳酸盐岩地层随钻岩性快速识别方法
US20230144184A1 (en) Advanced geological prediction method and system based on perception while drilling
CN102930253B (zh) 一种基于图像离散多小波变换的煤岩识别方法
CN111222683B (zh) 一种基于pca-knn的tbm施工围岩综合分级预测方法
CN113685188B (zh) 一种基于岩渣物理特征的tbm掘进优化方法
CN110244344A (zh) 一种基于深度学习的tbm超前地质预报方法
CN109271755B (zh) 一种应用随钻数据计算岩石强度的方法和系统
CN101923084A (zh) 一种矿用水源识别方法及识别设备
CN111722270A (zh) 一种基于随钻监测设备的短距离超前地质预报方法
CN109765097B (zh) 一种基于rpd钻机的隧道围岩快速分类方法
Zhang et al. Deep learning‐based automatic detection of muck types for earth pressure balance shield tunneling in soft ground
CN116291271A (zh) 一种基于随钻测试的岩土体参数反演方法及系统
CN104678455A (zh) 一种陆相缝洞型储层识别方法
Dickmann et al. Towards the integration of smart techniques for tunnel seismic applications
CN111706322B (zh) 一种岩石钻进响应的预测方法和预测系统
CN109886421B (zh) 基于集成学习的群智能采煤机切割模式识别系统
Fernández et al. Ore/waste identification in underground mining through geochemical calibration of drilling data using machine learning techniques
CN116299733A (zh) 利用常规测井曲线识别地层中含硫储层的方法
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
CN105840175A (zh) 三维裂缝建模方法
CN110728074A (zh) 混积细粒岩岩性连续解释的方法及其模型的建模方法

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: 20915827

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: 20915827

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 (EPO FORM 1205A DATED 27/01/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20915827

Country of ref document: EP

Kind code of ref document: A1