WO2021203491A1 - 一种采动围岩地压灾害智能预测方法及系统 - Google Patents

一种采动围岩地压灾害智能预测方法及系统 Download PDF

Info

Publication number
WO2021203491A1
WO2021203491A1 PCT/CN2020/086431 CN2020086431W WO2021203491A1 WO 2021203491 A1 WO2021203491 A1 WO 2021203491A1 CN 2020086431 W CN2020086431 W CN 2020086431W WO 2021203491 A1 WO2021203491 A1 WO 2021203491A1
Authority
WO
WIPO (PCT)
Prior art keywords
surrounding rock
data
prediction
stress
mining
Prior art date
Application number
PCT/CN2020/086431
Other languages
English (en)
French (fr)
Inventor
吕祥锋
Original Assignee
北京科技大学
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 北京科技大学 filed Critical 北京科技大学
Publication of WO2021203491A1 publication Critical patent/WO2021203491A1/zh

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E21—EARTH OR ROCK DRILLING; MINING
    • E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
    • E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
    • E—FIXED CONSTRUCTIONS
    • E21—EARTH OR ROCK DRILLING; MINING
    • E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
    • E21F17/00—Methods or devices for use in mines or tunnels, not covered elsewhere
    • E21F17/18—Special adaptations of signalling or alarm devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Definitions

  • the invention relates to the technical field of disaster prediction, in particular to a method and system for intelligent prediction of ground pressure disasters in mining surrounding rocks.
  • the present invention aims to provide an intelligent prediction method and system for ground pressure disasters of mining surrounding rocks, which can complete the preliminary prediction of ground pressure disasters through machine learning models, and perform prediction results through certain standards and theoretical models. Verification, with excellent accuracy and practicability.
  • a method for intelligently predicting ground pressure disasters of mining surrounding rocks which includes the following steps:
  • S1 Data collection Set a plurality of sensor modules in the mining surrounding rock.
  • the sensor modules include a stress-strain sensor module and an environment sensor module.
  • the sensor modules are used to collect surrounding rock data and external environment information;
  • S2 data preprocessing constructing a stress-strain curve using the surrounding rock data collected by the stress-strain induction module, extracting the data before the surrounding rock stress reaches the ultimate stress as the pre-peak data, and the data after reaching the ultimate stress as the post-peak data;
  • S3 Preliminary disaster prediction Substitute the continuous pre-peak data and/or post-peak data for a period of time into the machine learning model for disaster imminent warning, and obtain preliminary prediction results;
  • the collected data is divided into pre-peak data and post-peak data according to the yield point in the full stress-strain curve model of the surrounding rock, and the pre-peak data is used to predict the yield point and determine the stress of surrounding rock within a certain period of time. Whether it will reach the yield point; the post-peak data or the combination of the pre-peak data and the post-peak data are used to predict the instability of the surrounding rock and determine whether the surrounding rock will be fractured or not in a certain period of time.
  • the stress and strain sensing module includes a stress sensor and a strain sensor; the environment sensing module includes a temperature sensor, an acoustic emission sensor, and a microseismic sensor.
  • the surface of the mining surrounding rock is provided with boreholes, and the sensors are arranged inside the boreholes.
  • the S4 result evaluation specifically includes:
  • the external environment information includes temperature, noise, and vibration.
  • the preliminary prediction of the S3 disaster specifically includes:
  • S31 Preliminarily construct a machine learning model based on the characteristics of the long-term indicators before the disaster peak and the near indicators after the peak;
  • S33 Use the machine learning model to perform preliminary analysis and prediction on the pre-peak data and/or post-peak data in S2 that are continuous for a period of time;
  • step S43 specifically includes:
  • the second prediction result is the same as the preliminary prediction result: at this time, the preliminary prediction result is directly used as the final disaster prediction result;
  • the re-prediction result is different from the preliminary prediction result: at this time, the period in S3 will be extended, the steps S3-S4 will be repeated, and the evaluation result will be re-output; if the re-predicted result is still different from the preliminary prediction result, this time
  • the re-prediction result is taken as the final disaster prediction result, and the machine learning model in S3 is trained and optimized using the re-prediction result and the pre-peak data and/or post-peak data within a period of time after expansion.
  • an intelligent prediction system for ground pressure disasters caused by mining surrounding rocks is used to execute the method according to the first aspect of the present invention and includes: a collection unit, a preprocessing unit, and a prediction unit. Unit, evaluation unit and decision-making unit;
  • the acquisition unit is used to collect surrounding rock data and includes a stress and strain sensing module and an environment sensing module.
  • the stress and strain sensing module is used to obtain the stress and strain of the surrounding rock in the borehole in real time
  • the environment sensing module is used for Obtain the temperature, noise and vibration of the surrounding rock in the borehole in real time;
  • the preprocessing unit is configured to receive the surrounding rock data and preprocess the surrounding rock data
  • the prediction unit is used to preliminarily predict the occurrence of a disaster
  • the evaluation unit is used to evaluate the preliminary prediction result based on the surrounding rock instability theory and the external environment information collected by the environment sensing module;
  • the decision-making unit is used to complete the final disaster decision-making.
  • the preprocessing unit includes a transmitting base station and a ground receiving terminal platform, and the transmitting base station can encrypt and batch transmit the surrounding rock data to the ground receiving terminal platform.
  • stress and strain sensing module and the environment sensing module are co-located at the end of the borehole away from the roadway.
  • the borehole extends to the mining surrounding rock in a direction perpendicular to the sidewall of the roadway, and the borehole includes an extension part and a monitoring part. One end of the extension part is connected to the roadway, and the other end is connected to the mining surrounding rock through the monitoring part. .
  • the monitoring part includes a first accommodating space, a second accommodating space, and a third accommodating space, and the first accommodating space, the second accommodating space, and the third accommodating space extend perpendicular to the extension part The directions are connected in turn.
  • the temperature sensor and the acoustic emission sensor are arranged in sequence along the extension direction perpendicular to the extension portion, and the temperature sensor and the acoustic emission sensor are both arranged in the second accommodating space.
  • the stress sensor and the strain sensor are both arranged in the first accommodating space, one end of the stress sensor and the strain sensor is connected to the second accommodating space, and the other end is connected to the mining surrounding rock.
  • microseismic sensor is arranged in the third accommodating space, one end of the microseismic sensor is connected to the second accommodating space, and the other end is connected to the mining surrounding rock.
  • the intelligent prediction method and system for mining surrounding rock and ground pressure disasters of the present invention are simple to operate, easy to use, high in accuracy and accurate in judgment, and has the following outstanding features:
  • Fig. 1 is a flowchart of a method for intelligently predicting ground pressure disasters caused by mining surrounding rocks according to an embodiment of the present invention
  • Fig. 2 is a schematic diagram of a full stress-strain curve according to an embodiment of the present invention
  • FIG. 3 is an overall schematic diagram of the intelligent prediction system for ground pressure disasters of mining surrounding rocks according to an embodiment of the present invention
  • FIG. 4 is a schematic diagram of a collection unit of an intelligent prediction system for ground pressure disasters of mining surrounding rocks according to an embodiment of the present invention
  • Fig. 5 is the rupture model of the two sides of the weaker roadway side according to the first embodiment of the present invention.
  • Fig. 6 is a unidirectional compression model of the shallow rock mass of the upper part according to the first embodiment of the present invention.
  • a and/or B can mean: A alone exists, A and B exist at the same time, and B exists alone.
  • an intelligent prediction method for ground pressure disasters in mining surrounding rocks includes the following steps:
  • S1 Data collection Set multiple sensor modules in the mining surrounding rock 1.
  • the sensor modules include a stress-strain sensor module and an environmental sensor module.
  • the sensor module is used to collect surrounding rock data and external environmental information;
  • S2 data preprocessing use the surrounding rock data collected by the stress-strain induction module to construct a stress-strain curve, extract the data before the surrounding rock stress reaches the ultimate stress as pre-peak data, and the data after reaching the ultimate stress as post-peak data;
  • S3 Preliminary disaster prediction Substitute the continuous pre-peak data and/or post-peak data for a period of time into the machine learning model for disaster imminent warning, and obtain preliminary prediction results;
  • the collected data is divided into pre-peak data and post-peak data according to the yield point in the full stress-strain curve model of the surrounding rock.
  • the pre-peak data is used to predict the yield point and determine whether the surrounding rock stress will reach within a certain period of time.
  • Yield point The post-peak data or the combination of pre-peak data and post-peak data are used to complete the prediction of surrounding rock instability, and to determine whether the surrounding rock will undergo fracture instability within a certain period of time.
  • the O-A section in Figure 2 is the original fracture compaction stage.
  • the deformation of the surrounding rock is mainly the compaction of small cracks and tiny cavities in the surrounding rock. Compaction. Deformation is mainly manifested in the form of plastic deformation. In relatively dense surrounding rock, this stage has a short duration and small deformation (if the upper and lower loading ends of the surrounding rock specimens are not completely level due to laboratory processing errors, the deformation of the OA stage will also occur at the beginning of loading) .
  • Section A-B is the elastic deformation stage of the peak front line.
  • the deformation characteristic curve of the surrounding rock will show a linear upward trend, while the slope of the curve remains constant.
  • the slope is mainly determined by the elastic constant of the surrounding rock material.
  • the surrounding rock deformation mainly manifests the form of elastic deformation.
  • the elastic limit value As the load increases, from a mesoscopic point of view, there will be extremely small cracks in the surrounding rock; from a macro point of view, it appears as a linear deformation stage, and the stress value at point B in the curve is called the surrounding rock material The elastic limit value.
  • Section B-C is the transitional stage of fracture stability elasto-plasticity.
  • the stress-strain curve of the surrounding rock starts to deviate from the linear rise from point B. Although it continues to maintain an upward trend, it shows a downward bending trend, and the slope of the curve gradually decreases.
  • small cracks in the surrounding rock expand in a small area, and the deformation of the surrounding rock is mainly reflected in the expansion of newly generated cracks, and finally manifests as a characteristic of plastic deformation.
  • the small cracks in the surrounding rock continue to increase. Under the expansion of the surrounding rock, the volume of the surrounding rock changes from the first compression deformation to expansion deformation. The value of point C is called the yield limit.
  • the C-D section is the stage of accelerated fracture plastic deformation.
  • the stress-strain curve of the surrounding rock continues to rise from point C to the upper right, and the upward trend can still be maintained, and the slope of the curve gradually decreases.
  • the microcracks inside the surrounding rock further expand and breed.
  • the rupture speed of the surrounding rock increases at this time, and the volume continues to accelerate expansion under the effect of capacity expansion.
  • the D-E section is the post-peak intensity macroscopic failure stage. After the stress state of the surrounding rock reaches the peak strength, in this stage, the mechanical characteristics of rock failure can be divided into two situations, as shown in the two types of curves: the first type of curve shows a "gradual, slow and steady" trend decline; The second type of curve appears as a "rapid and abrupt" decline.
  • the E-F section is the post-peak residual intensity stage.
  • the accelerated failure of the surrounding rock changes from the initial macro-fracture to a macro-fracture.
  • the damage of the surrounding rock is manifested as an instability slip along its fracture surface.
  • the internal cohesive force of the surrounding rock reaches zero.
  • the surrounding rock still has a certain residual strength due to the frictional occlusion between the rock blocks.
  • the stress-strain sensing module includes a stress sensor and a strain sensor; the environmental sensing module includes a temperature sensor, an acoustic emission sensor, and a microseismic sensor.
  • a borehole 2 is provided on the surface of the mining surrounding rock 1, and a sensor is arranged inside the borehole 2.
  • the S4 result evaluation specifically includes:
  • the external environment information includes temperature, noise, and vibration.
  • S31 Preliminarily construct a machine learning model based on the characteristics of the long-term indicators before the disaster peak and the near indicators after the peak;
  • the evaluation result in step S43 specifically includes:
  • the second prediction result is the same as the preliminary prediction result: at this time, the preliminary prediction result is directly used as the final disaster prediction result;
  • the re-prediction result is different from the preliminary prediction result: At this time, the period in S3 will be extended, steps S3-S4 will be repeated, and the evaluation result will be re-output; if the re-predicted result is still different from the preliminary prediction result, the result will be predicted again at this time.
  • the machine learning model in S3 is trained and optimized by using the re-prediction result and the pre-peak data and/or post-peak data within a period of time after the expansion.
  • an intelligent prediction system for mining surrounding rock and ground pressure disasters is used to implement the method according to the first aspect of the present invention, and includes: a collection unit, a preprocessing unit, a prediction unit, an evaluation unit, and a decision-making unit;
  • the acquisition unit is used to collect surrounding rock data, including a stress-strain sensing module and an environmental sensing module.
  • the stress-strain sensing module is used to obtain the stress and strain of the surrounding rock in borehole 2 in real time
  • the environmental sensing module is used to obtain the inside of borehole 2 in real time. The temperature, noise and vibration of surrounding rock;
  • the preprocessing unit is used to receive the surrounding rock data and preprocess the surrounding rock data
  • Prediction unit used to initially predict the occurrence of disasters
  • the evaluation unit is used to evaluate the preliminary prediction results based on the surrounding rock instability theory and the external environmental information collected by the environmental sensing module;
  • the decision-making unit is used to complete the final disaster decision.
  • the preprocessing unit includes a transmitting base station and a ground receiving terminal platform.
  • the transmitting base station can encrypt and batch transmit surrounding rock data to the ground receiving terminal platform.
  • the stress and strain sensing module and the environment sensing module are co-located at the end of the borehole 2 away from the roadway.
  • the borehole 2 extends in the direction perpendicular to the sidewall of the roadway to the mining surrounding rock 1.
  • the borehole 2 includes an extension part and a monitoring part. One end of the extension part is connected to the roadway, and the other end is connected to the mining surrounding rock through the monitoring part. 1.
  • the monitoring part includes a first accommodating space 4, a second accommodating space 3, and a third accommodating space 5.
  • the first accommodating space 4, the second accommodating space 3 and the third accommodating space 5 are perpendicular to the extending direction of the extension part Connect in order.
  • the temperature sensor and the acoustic emission sensor are arranged in sequence along the extending direction perpendicular to the extension part, and both the temperature sensor and the acoustic emission sensor are arranged in the second accommodating space 3.
  • Both the stress sensor and the strain sensor are arranged in the first accommodating space 4, one end of the stress sensor and the strain sensor is connected to the second accommodating space 3, and the other end is connected to the mining surrounding rock 1.
  • the microseismic sensor is arranged in the third accommodating space 5, one end of the microseismic sensor is connected to the second accommodating space 3, and the other end is connected to the mining surrounding rock 1.
  • This embodiment will take the instability of the two sides of the surrounding rock as an example to illustrate how to obtain the intermediate prediction result in step S41.
  • the two sides of the surrounding rock are generally weaker rock formations. Because of their low strength, after the excavation of the surrounding rock, if there is no supporting force, because the vertical stress is the maximum principal stress in the compressive stress field, the surrounding rock The section will undergo compression-shear failure, and the stress and deformation state can be similar to the one-way compression state. However, since only one side of the side has a free surface, the surrounding rock section has a "V"-shaped fracture area similar to a horizontal arch. With the expansion and loosening of the rupture area, under the action of transverse dilatancy and gravity, the two sides will appear flaky, which will eventually lead to the instability of the two sides.
  • Figure 5 shows the two sides of weak weak surrounding rock and two sides of fracture model
  • Figure 6 shows the unidirectional compression model of the surrounding rock.
  • the main failure form of rock mass is compression-shear rupture, and the instability condition of brittle dilatancy rupture of rock mass can be considered as the rock mass under vertical pressure.
  • the rock mass is unstable.
  • the instability criterion is based on the form of shear strength.
  • m s is a dimensionless test constant
  • s characterizes the integrity of the rock mass
  • complete rock s 1
  • m is related to lithology and other factors, they can be determined through experiments or engineering classification of rock mass.
  • Rock mass failure and instability If the rock mass
  • Temperature, noise, and vibration will all affect the allowable strength of the surrounding rock. This embodiment will take the effect of temperature on granite as an example to illustrate the effect of external environmental information on the allowable strength.
  • quartz is the most important component mineral of granite. As the temperature changes, quartz particles will undergo the following changes, and the volume will also change:
  • the granite subjected to 400°C is rapidly cooled in water, and the axial peak strain suddenly decreases, and after the radial peak strain exceeds 400°C, it also drops rapidly as the temperature increases. It can be inferred that after the temperature of 400°C, when the granite is cooled in water, the thermal activation effect is significant, and more silicon-oxygen bonds are replaced by hydroxyl bonds. The sudden strong thermal activation causes the axial strain to decrease rapidly, and the diameter exceeds 400°C. The strain toward the peak also drops rapidly.
  • Thermochemical effects The mineral composition of the rock largely determines the physical and mechanical properties of the rock.
  • granite minerals undergo a chemical reaction to transform the mineral composition.
  • SiO2 and CaO react to form CaSiO3.
  • CaO and Fe2O react to form calcium ferrite.
  • CaO reacts with CO2 to form CaCO3.
  • CaCO3 decomposes into CaO.
  • CO2O3 reacts with CaO at about 700°C to form iron olivine.
  • the chemical composition of biotite is K(Mg,Fe)3AISi3O1o(OH)2. Due to the presence of (OH), there is a thermal decomposition tendency from 200°C. When it is higher than 450°C, it begins to thermally decompose, the thickness expands, and the temperature reaches 600. The thermal decomposition is intensified when the temperature is above °C, and it is almost completely decomposed at 900°C.
  • the mineral composition produced by the decomposition of biotite is also different at different temperatures, mainly magnetite and potash feldspar.
  • the mineral composition in the rock will change to different degrees, which will affect the physical and mechanical properties of granite and reduce the allowable strength of the rock.
  • the technical solution of the present invention essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to make a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.
  • a terminal which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mining & Mineral Resources (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geochemistry & Mineralogy (AREA)
  • Geology (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
  • Geophysics And Detection Of Objects (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)

Abstract

一种采动围岩（1）地压灾害智能预测方法及系统，涉及深部开采地压灾害预测及防治技术领域。方法包括以下步骤：S1：在采动围岩（1）中设置传感器采集围岩数据；S2：利用采集的围岩数据构建应力应变曲线，提取围岩应力达到极限应力前的数据作为峰前数据，达到极限应力后的数据作为峰后数据；S3：将一段时间内连续的峰前数据或峰后数据代入机器学习模型进行灾害临近预警，得到初步预测结果；S4：基于围岩失稳理论和外部环境信息对初步预测结果进行评估，得到评估结果；S5：根据评估结果完成最终灾害决策。能够通过机器学习模型完成对地压灾害的初步预测，并通过一定的标准和模型对预测结果进行验证，兼具优异的准确率与实用性。

Description

一种采动围岩地压灾害智能预测方法及系统 技术领域
本发明涉及灾害预测技术领域，尤其是涉及一种采动围岩地压灾害智能预测方法及系统。
背景技术
在巷(隧)道施工过程中，深部开采地压灾害危害程度极大，涌水、突泥、塌方等地质灾害是影响巷(隧)道施工安全和成本的重要因素。如果能在地质灾害发生前,提前预测到灾害的发生，然后采取相应的处理，将会极大地降低施工风险和节约施工成本。
我国现对采动围岩地压灾害的预测成功率虽然显著提升，但目前大多数预测方法是借助人工经验的方式实现的，且这些方法的原理、工作方式、解释应用等都还不够成熟、准确，很难满足实际工程需要。在实际施工中还是不断发生涌水涌沙、泥石流及塌方等安全事故，造成了重大的人员伤亡和经济损失。因此，我们还需不断加强采动围岩地压灾害预测，制定合理的应对策略，最大程度降低灾害的发生。
发明内容
有鉴于此，本发明旨在提供一种采动围岩地压灾害智能预测方法及系统，能够通过机器学习模型完成对地压灾害的初步预测，并通过一定的标准和理论模型对预测结果进行验证，兼具优异的准确率与实用性。
根据本发明的第一方面，提供了一种采动围岩地压灾害智能预测方法，包括以下步骤：
S1数据采集：在采动围岩中设置多个传感器模块，所述传感器模块包括应力应变感应模块和环境感应模块，所述传感器模块用于采集围岩数据及外部环境信息；
S2数据预处理：利用所述应力应变感应模块采集的围岩数据构建应力应变曲线，提取围岩应力达到极限应力前的数据作为峰前数据，达到极限应力后的数据作为峰后数据；
S3灾害初步预测：将一段时间内连续的峰前数据和/或峰后数据代入机器学习模型进行灾害临近预警，得到初步预测结果；
S4结果评估：基于围岩失稳理论及环境感应模块采集的外部环境信息对所述初步预测结果进行评估，得到评估结果；
S5最终决策：根据所述评估结果完成最终灾害决策。
进一步的，将采集的数据根据围岩的全应力应变曲线模型中的屈服点划分为峰前数据和峰后数据，将峰前数据用于完成对屈服点的预测，判断一定时间内围岩应力是否会达到屈服点；将峰后数据或峰前数据与峰后数据的结合用于完成对围岩失稳的预测，判断一定时间内围岩是否会发生断裂失稳。
进一步的，所述应力应变感应模块包括应力传感器和应变传感器；所述环境感应模块包括温度传感器、声发射传感器、微震传感器。
进一步的，所述采动围岩表面设有钻孔，传感器设在钻孔内部。
进一步的，所述S4结果评估具体包括：
S41：根据围岩的全应力应变曲线模型判断围岩所处的变形阶段，基于所述变形阶段下围岩的失稳方式与围岩不同部分的失稳机理对采集的围岩数据进行分析预测，得到中间预测结果；
S42：结合采集的外部环境信息对所述中间预测结果进行调整，得到再次预测结果；
S43：将所述再次预测结果与所述初步预测结果比较，得到评估结果。
进一步的，所述外部环境信息包括温度、噪声、振动。
进一步的，温度越高，则认为围岩易失稳，应适当降低许用应力；
噪声越大，则认为围岩易失稳，应适当降低许用应力；
振动越大，则认为围岩易失稳，应适当降低许用应力。
进一步的，所述S3灾害初步预测，具体包括：
S31：依据灾难峰前长期指标和峰后临近指标特征初步构建机器学习模型；
S32：取现有灾难数据中的峰前长期数据和峰后临近数据作为训练集，完成机器学习模型的初步训练；
S33：利用所述机器学习模型对一段时间内连续的所述S2中的峰前数据和/或峰后数据进行初步分析预测；
S34：当所述S2中的峰前数据和峰后数据数量满足训练需求时，将所述S2中的峰前数据和峰后数据为新的训练集，完成所述机器学习模型的迭代优化。
进一步的，步骤S43中的所述评估结果具体包括：
再次预测结果与初步预测结果相同：此时将初步预测结果直接作为最终灾害预测结果；
再次预测结果与初步预测结果不同：此时将扩展所述S3中的一段时间，重复所述步骤S3-S4，重新输出评估结果；若重新得到的再次预测结果与初步预测结果仍不同，此时 将再次预测结果作为最终灾害预测结果，并利用再次预测结果和扩展后的一段时间内的峰前数据和/或峰后数据对S3中的所述机器学习模型进行训练优化。
根据本发明的第二方面，提供了一种采动围岩地压灾害智能预测系统，所述系统用于执行如本发明第一方面所述的方法，包括：采集单元、预处理单元、预测单元、评估单元及决策单元；
所述采集单元，用于采集围岩数据，包括应力应变感应模块和环境感应模块，所述应力应变感应模块用于实时获取钻孔内采动围岩的应力与应变，所述环境感应模块用于实时获取钻孔内采动围岩的温度、噪声和振动；
所述预处理单元，用于接收所述围岩数据并对所述围岩数据进行预处理；
所述预测单元，用于初步预测灾害发生；
所述评估单元，用于基于围岩失稳理论及环境感应模块采集的外部环境信息对初步预测结果进行评估；
所述决策单元，用于完成最终灾害决策。
进一步的，所述预处理单元包括传送基站和地面接收终端平台，所述传送基站能够加密并批量传输所述围岩数据至所述地面接收终端平台。
进一步的，所述应力应变感应模块和环境感应模块同位设置在远离巷道方向的钻孔末端。
进一步的，所述钻孔沿垂直于巷道侧壁方向向采动围岩延伸，所述钻孔包括延伸部和监测部，所述延伸部一端连接巷道，另一端通过监测部连接采动围岩。
进一步的，所述监测部包括第一容置空间、第二容置空间和第三容置空间，所述第一容置空间、第二容置空间和第三容置空间垂直于延伸部延伸方向依次连接。
进一步的，所述温度传感器和声发射传感器沿垂直于延伸部延伸方向依次设置，所述温度传感器和声发射传感器均设置在第二容置空间内。
进一步的，所述应力传感器和应变传感器均设置在第一容置空间内，所述应力传感器和应变传感器的一端连接第二容置空间，另一端连接采动围岩。
进一步的，所述微震传感器设置在第三容置空间内，所述微震传感器一端连接第二容置空间，另一端连接采动围岩。
相对于现有技术，本发明所述的一种采动围岩地压灾害智能预测方法及系统操作简单、易于使用，且精度高、判定准确，并具有以下突出特点：
1、将采集的数据根据围岩的全应力应变曲线模型中的屈服点划分为峰前数据和峰后 数据，将峰前数据用于完成对屈服点的预测，判断一定时间内围岩应力是否会达到屈服点；将峰后数据或峰前数据与峰后数据结合用于完成对围岩失稳的预测，判断一定时间内围岩是否会发生断裂失稳，通过设置对不同数据的用途，本发明所述的方法可达到迅速准确的实时做出预测的效果；
2、通过机器学习模型，实时完成对灾害的初步预测，并基于围岩失稳理论及外部环境信息对初步预测结果进行评估判断，保证灾害不会漏报错报，从而避免造成难以挽回的损失。
附图说明
构成本发明的一部分的附图用来提供对本发明的进一步理解，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1为本发明实施例所述的采动围岩地压灾害智能预测方法的流程图；
图2为本发明实施例所述的全应力-应变曲线的示意图；
图3为本发明实施例所述的采动围岩地压灾害智能预测系统的整体示意图；
图4为本发明实施例所述的采动围岩地压灾害智能预测系统的采集单元示意图；
图5为本发明实施例1所述的两帮较软弱型巷道帮部破裂模型；
图6为本发明实施例1所述的帮部浅部岩体单向受压模型。
其中，图中：
1-采动围岩，2-钻孔，3-第二容置空间，4-第一容置空间，5-第三容置空间。
具体实施方式
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
本公开的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
多个，包括两个或者两个以上。
和/或，应当理解，对于本公开中使用的术语“和/或”，其仅仅是一种描述关联对象的关联关系，表示可以存在三种关系。例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。
如图1所示的一种采动围岩地压灾害智能预测方法，包括以下步骤：
S1数据采集：在采动围岩1中设置多个传感器模块，传感器模块包括应力应变感应模块和环境感应模块，传感器模块用于采集围岩数据及外部环境信息；
S2数据预处理：利用应力应变感应模块采集的围岩数据构建应力应变曲线，提取围岩应力达到极限应力前的数据作为峰前数据，达到极限应力后的数据作为峰后数据；
S3灾害初步预测：将一段时间内连续的峰前数据和/或峰后数据代入机器学习模型进行灾害临近预警，得到初步预测结果；
S4结果评估：基于围岩失稳理论及环境感应模块采集的外部环境信息对初步预测结果进行评估，得到评估结果；
S5最终决策：根据评估结果完成最终灾害决策。
将采集的数据根据围岩的全应力应变曲线模型中的屈服点划分为峰前数据和峰后数据，将峰前数据用于完成对屈服点的预测，判断一定时间内围岩应力是否会达到屈服点；将峰后数据或峰前数据与峰后数据的结合用于完成对围岩失稳的预测，判断一定时间内围岩是否会发生断裂失稳。
其中，图2中O-A段为原始裂隙压实阶段。围岩在初始受载阶段,由于载荷的累积增加，围岩应力—应变曲线呈上弯形变化趋势，曲线斜率逐渐增加，围岩变形主要是将围岩内部的细小裂纹，微小空洞的压实压密。变形主要表现为以塑性变形形式。在比较致密的围岩内，这一阶段持续时间短，变形微小(如果围岩试件上下受载端由于实验室加工的误差，不完全水平，同样在加载初期会出现O-A阶段的变形情况)。
A-B段为峰前线弹性变形阶段。围岩在该变形过程中，同样由于载荷的累积增加，围岩变形特性曲线将呈线性上升变化趋势，同时曲线斜率保持固定值不变，其斜率主要决定于围岩材料的弹性常数。在该阶段内，围岩变形主要表现弹性变形形式。随着载荷增加，围岩内部从细观角度来看，会出现极其微小的破裂产生；从宏观角度来看，表现为一个线性变形阶段，同时曲线中B点处的应力值称作围岩材料的弹性极限值。
B-C段为裂隙稳定弹塑性过渡阶段。围岩在该变形阶段内，随着载荷的累积增加，围岩应力—应变曲线开始从B点偏离线性上升，虽然继续保持上升趋势，但是表现为下 弯形趋势，曲线斜率慢慢变小。在该阶段内，围岩内部微小裂纹小范围内扩展，围岩的变形主要是体现于新产生裂缝进行扩容，最终表现为塑性变形特征。在该变形阶段内，随着载荷不断增加，围岩微小裂隙不断增加，在围岩的扩容作用下，围岩的体积由最先的压缩变形转变为膨胀变形，C点值称为屈服极限。
C-D段为加速破裂塑性变形阶段。围岩在该变形阶段内，随着载荷的累积增加，围岩应力—应变曲线从C点继续向右上方上升，仍然能保持上升趋势，曲线斜率慢慢变小。随着载荷不断增加，围岩内部的微裂纹进一步扩展滋生,接近于峰值顶点D处时，此时围岩破裂速度加快，体积在扩容效应下，继续加速膨胀。
D-E段为峰后强度宏观破坏阶段。围岩的应力状态达到峰值强度后,在这个阶段内，岩石破坏的力学特征可分为两种情况，如图所示中的两类曲线：第一类曲线呈现“渐进缓稳”趋势下降；第二类曲线表现为“急速陡然”下降。
E-F段为峰后残余强度阶段。在峰后残余强度过程中,围岩的加速破坏从最初的宏观破裂转变成宏观断裂,围岩破坏形式表现为沿其断裂面失稳滑移,此时围岩内部黏聚力达到零值，但是由于岩块之间摩擦咬合作用，围岩仍具有一定的残余强度。
应力应变感应模块包括应力传感器和应变传感器；环境感应模块包括温度传感器、声发射传感器、微震传感器。
采动围岩1表面设有钻孔2，传感器设在钻孔2内部。
S4结果评估具体包括：
S41：根据如图2所示的围岩的全应力应变曲线模型判断围岩所处的变形阶段，基于变形阶段下围岩的失稳方式与围岩不同部分的失稳机理对采集的围岩数据进行分析预测，得到中间预测结果；
S42：结合采集的外部环境信息对中间预测结果进行调整，得到再次预测结果；
S43：将再次预测结果与初步预测结果比较，得到评估结果。
外部环境信息包括温度、噪声、振动。
温度越高，则认为围岩易失稳，应适当降低许用应力；
噪声越大，则认为围岩易失稳，应适当降低许用应力；
振动越大，则认为围岩易失稳，应适当降低许用应力。
S3灾害初步预测，具体包括：
S31：依据灾难峰前长期指标和峰后临近指标特征初步构建机器学习模型；
S32：取现有灾难数据中的峰前长期数据和峰后临近数据作为训练集，完成机器学习 模型的初步训练；
S33：利用机器学习模型对一段时间内连续的S2中的峰前数据和/或峰后数据进行初步分析预测；
S34：当S2中的峰前数据和峰后数据数量满足训练需求时，将S2中的峰前数据和峰后数据为新的训练集，完成机器学习模型的迭代优化。
步骤S43中的评估结果具体包括：
再次预测结果与初步预测结果相同：此时将初步预测结果直接作为最终灾害预测结果；
再次预测结果与初步预测结果不同：此时将扩展S3中的一段时间，重复步骤S3-S4，重新输出评估结果；若重新得到的再次预测结果与初步预测结果仍不同，此时将再次预测结果作为最终灾害预测结果，并利用再次预测结果和扩展后的一段时间内的峰前数据和/或峰后数据对S3中的机器学习模型进行训练优化。
如图3所示的一种采动围岩地压灾害智能预测系统，系统用于执行如本发明第一方面的方法，包括：采集单元、预处理单元、预测单元、评估单元及决策单元；
采集单元，用于采集围岩数据，包括应力应变感应模块和环境感应模块，应力应变感应模块用于实时获取钻孔2内围岩的应力与应变，环境感应模块用于实时获取钻孔2内围岩的温度、噪声和振动；
预处理单元，用于接收围岩数据并对围岩数据进行预处理；
预测单元，用于初步预测灾害发生；
评估单元，用于基于围岩失稳理论及环境感应模块采集的外部环境信息对初步预测结果进行评估；
决策单元，用于完成最终灾害决策。
预处理单元包括传送基站和地面接收终端平台，传送基站能够加密并批量传输围岩数据至地面接收终端平台。
应力应变感应模块和环境感应模块同位设置在远离巷道方向的钻孔2末端。
如图4所示，钻孔2沿垂直于巷道侧壁方向向采动围岩1延伸，钻孔2包括延伸部和监测部，延伸部一端连接巷道，另一端通过监测部连接采动围岩1。
监测部包括第一容置空间4、第二容置空间3和第三容置空间5，第一容置空间4、第二容置空间3和第三容置空间5垂直于延伸部延伸方向依次连接。
温度传感器和声发射传感器沿垂直于延伸部延伸方向依次设置，温度传感器和声发 射传感器均设置在第二容置空间3内。
应力传感器和应变传感器均设置在第一容置空间4内，应力传感器和应变传感器的一端连接第二容置空间3，另一端连接采动围岩1。
微震传感器设置在第三容置空间5内，微震传感器一端连接第二容置空间3，另一端连接采动围岩1。
实施例1
本实施例将以围岩两帮失稳为例，说明步骤S41中如何得到中间预测结果。
围岩两帮一般均为较软弱岩层，由于其强度较低，因而在围岩开挖之后，若无支护力的作用，由于以垂直应力为最大主应力的压应力场中，围岩帮部将发生压剪破坏，受力变形状态可近似于单向受压状态，但由于帮部只有一侧出现自由面，因而围岩帮部出现“V”字形近似于横拱形的破裂区域，随着破裂区域的扩展松动，在横向剪胀力与重力作用下，两帮出现片帮，最终导致两帮失稳。如图5为两帮软弱型围岩两帮破裂模型，图6为围岩单向受压模型。
岩体在单向压缩作用下，其主要破坏形式体现为压剪破裂，而岩体发生脆性剪胀破裂的失稳条件可以认为岩体在垂直压力作用下，当施加载荷超过其极限强度之后，岩体发生失稳。关于岩体的压剪破裂,其失稳判据依据抗剪强度形式判别。
以抗剪强度的形式表达：
Figure PCTCN2020086431-appb-000001
Figure PCTCN2020086431-appb-000002
Figure PCTCN2020086431-appb-000003
Figure PCTCN2020086431-appb-000004
式中：
A—经验常数；
B—材料压缩系数；
τ f—岩体抗剪强度；
σ C—岩体单轴抗压强度；
σ—剪切破裂面正应力；
β—剪切滑动角；
τ—剪切斜面剪应力；
m,s为无量纲试验常数，s表征岩体的完整性,完整岩石s＝1，m与岩性等因素有关，它们可通过试验确定,也可通过岩体的工程分类确定。
岩体破坏失稳：若|τ|≥τ f岩体则产生滑动失稳，可判断岩体破坏失稳，滑动角可以由式4-3求得。
实施例2
温度、噪声、震动均会影响围岩许用强度，本实施例将以温度对花岗岩的影响为例，说明外部环境信息对许用强度的影响。
高温作用下花岗岩的损伤机理：
(1)热破裂作用。花岗岩是由多种矿物颗粒组成，在温度作用下，由于花岗岩内部各种矿物颗粒粒径、热膨胀系数和热弹性性能的不同，引起颗粒边界的热膨胀不一致，矿物颗粒之间或颗粒内部产生拉、压应力，即结构热应力，使花岗岩内部产生微裂纹，随后，原生以及次生裂纹扩展、贯通，宏观.上就表现为花岗岩物理力学性能的劣化。
此外，在高温作用下，某些矿物会发生同质多象变体，并伴有体积变化，这进:步加剧了花岗岩的热破裂及物理力学性能的改变。例如，石英是花岗岩的最重要的组成矿物，石英颗粒随着温度的改变会发生以下变化，体积也随之改变：
Figure PCTCN2020086431-appb-000005
Figure PCTCN2020086431-appb-000006
Figure PCTCN2020086431-appb-000007
Figure PCTCN2020086431-appb-000008
Figure PCTCN2020086431-appb-000009
Figure PCTCN2020086431-appb-000010
(2)热激活作用。岩石晶体质点的热运动或应力作用，会促使岩石晶体产生缺陷(如位错，即局部晶格沿原子面发生--定的晶格滑移。晶体缺陷直到晶格内部，在晶格已滑移部分和未滑移部分的分界处质点错乱排列)，从而使材料容易断裂。岩石经历400℃左右的高温时，试件中-0H原子团受热激活作用后，原先的硅氧键被羟基键取代，从而促进了岩石晶体中的位错增大，对试样起到弱化作用。在本文中，经400℃作用的花岗岩，在水中快速冷却后，轴向峰值应变突然降低，以及径向峰值应变超过400℃后随着温度的增 加也迅速下降。可以推测:在400℃温度作用后，花岗岩在水中冷却时，受热激活作用显著，更多的硅氧键被羟基键取代，突然强烈的热激活作用使轴向应变迅速降低,超过400℃后径向峰值应变也迅速下降。
(3)热化学作用。岩石的矿物组成很大程度决定了岩石的物理力学性能。在高温环境下，花岗岩矿物发生化学反应使矿物成分发生转变。300℃左右，SiO2和CaO反应，生成CaSiO3，400℃～550℃时，CaO和Fe2O发生反应，生成铁酸钙，同时CaO又和CO2反应，生成CaCO3，而超过800℃后CaCO3又分解成CaO和CO2。到600℃时，MgO和Fe2O3固相反应生成镁铁混晶。700℃左右Fe2O3与CaO反应，生成铁橄榄石。黑云母的化学组成为K(Mg,Fe)3AISi3O1o(OH)2,由于含(OH)，从200℃开始就有热分解趋势，高于450℃时就开始热分解,厚度膨胀,温度达600℃以上时热分解加剧，到900℃时几乎完全分解，温度不同，黑云母分解产生的矿物成分也有明显差异，主要有磁铁矿和钾长石等。
因此，高温环境下，岩石中矿物成分会发生不同程度的改变，进而影响了花岗岩的物理力学性能，使得岩石的许用强度降低。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本发明各个实施例所述的方法。
上面结合附图对本发明的实施例进行了描述，但是本发明并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本发明的启示下，在不脱离本发明宗旨和权利要求所保护的范围情况下，还可做出很多形式，这些均属于本发明的保护之内。

Claims (15)

  1. 一种采动围岩地压灾害智能预测方法，其特征在于，包括以下步骤：
    S1数据采集：在采动围岩中设置多个传感器模块，所述传感器模块包括应力应变感应模块和环境感应模块，所述传感器模块用于采集围岩数据及外部环境信息；
    S2数据预处理：利用所述应力应变感应模块采集的围岩数据构建应力应变曲线，提取围岩应力达到极限应力前的数据作为峰前数据，达到极限应力后的数据作为峰后数据；
    S3灾害初步预测：将一段时间内连续的峰前数据和/或峰后数据代入机器学习模型进行灾害临近预警，得到初步预测结果；
    S4结果评估：基于围岩失稳理论及环境感应模块采集的外部环境信息对所述初步预测结果进行评估，得到评估结果；
    S5最终决策：根据所述评估结果完成最终灾害决策。
  2. 根据权利要求1所述的一种采动围岩地压灾害智能预测方法，其特征在于，所述应力应变感应模块包括应力传感器和应变传感器；所述环境感应模块包括温度传感器、声发射传感器、微震传感器。
  3. 根据权利要求2所述的一种采动围岩地压灾害智能预测方法，其特征在于，所述采动围岩表面设有钻孔，传感器设在钻孔内部。
  4. 根据权利要求1所述的一种采动围岩地压灾害智能预测方法，其特征在于，所述S4结果评估具体包括：
    S41：根据围岩的全应力应变曲线模型判断围岩所处的变形阶段，基于所述变形阶段下围岩的失稳方式与围岩不同部分的失稳机理对采集的围岩数据进行分析预测，得到中间预测结果；
    S42：结合采集的外部环境信息对所述中间预测结果进行调整，得到再次预测结果；
    S43：将所述再次预测结果与所述初步预测结果比较，得到评估结果。
  5. 根据权利要求4所述的一种采动围岩地压灾害智能预测方法，其特征在于，所述外部环境信息包括温度、噪声、振动。
  6. 根据权利要求1所述的一种采动围岩地压灾害智能预测方法，其特征在于，所述S3灾害初步预测，具体包括：
    S31：依据灾难峰前长期指标和峰后临近指标特征初步构建机器学习模型；
    S32：取现有灾难数据中的峰前长期数据和峰后临近数据作为训练集，完成机器学习模型的初步训练；
    S33：利用所述机器学习模型对一段时间内连续的所述S2中的峰前数据和/或峰后数据进行初步分析预测；
    S34：当所述S2中的峰前数据和峰后数据数量满足训练需求时，将所述S2中的峰前数据和峰后数据为新的训练集，完成所述机器学习模型的迭代优化。
  7. 根据权利要求4所述的一种采动围岩地压灾害智能预测方法，其特征在于，步骤S43中的所述评估结果具体包括：
    再次预测结果与初步预测结果相同：此时将初步预测结果直接作为最终灾害预测结果；
    再次预测结果与初步预测结果不同：此时将扩展所述S3中的一段时间，重复所述步骤S3-S4，重新输出评估结果；若重新得到的再次预测结果与初步预测结果仍不同，此时将再次预测结果作为最终灾害预测结果，并利用再次预测结果和扩展后的一段时间内的峰前数据和/或峰后数据对S3中的所述机器学习模型进行训练优化。
  8. 一种采动围岩地压灾害智能预测系统，所述系统用于执行如权利要求1-7任一项所述的方法，其特征在于，包括：采集单元、预处理单元、预测单元、评估单元及决策单元；
    所述采集单元，用于采集围岩数据，包括应力应变感应模块和环境感应模块，所述应力应变感应模块用于实时获取钻孔内采动围岩的应力与应变，所述环境感应模块用于实时获取钻孔内采动围岩的温度、噪声和振动；
    所述预处理单元，用于接收所述围岩数据并对所述围岩数据进行预处理；
    所述预测单元，用于初步预测灾害发生；
    所述评估单元，用于基于围岩失稳理论及环境感应模块采集的外部环境信息对初步预测结果进行评估；
    所述决策单元，用于完成最终灾害决策。
  9. 根据权利要求8所述的一种采动围岩地压灾害智能预测系统，其特征在于，所述预处理单元包括传送基站和地面接收终端平台，所述传送基站能够加密并批量传输所述围岩数据至所述地面接收终端平台。
  10. 根据权利要求8所述的一种采动围岩地压灾害智能预测系统，其特征在于，所述应力应变感应模块和环境感应模块同位设置在远离巷道方向的钻孔末端。
  11. 根据权利要求10所述的一种采动围岩地压灾害智能预测系统，其特征在于，所述钻孔沿垂直于巷道侧壁方向向采动围岩延伸，所述钻孔包括延伸部和监测部，所述延伸部一端连接巷道，另一端通过监测部连接采动围岩。
  12. 根据权利要求11所述的一种采动围岩地压灾害智能预测系统，其特征在于，所述监测部包括第一容置空间、第二容置空间和第三容置空间，所述第一容置空间、第二容置空间和第三容置空间垂直于延伸部延伸方向依次连接。
  13. 根据权利要求12所述的一种采动围岩地压灾害智能预测系统，其特征在于，所述温度传感器和声发射传感器沿垂直于延伸部延伸方向依次设置，所述温度传感器和声发射传感器均设置在第二容置空间内。
  14. 根据权利要求12所述的一种采动围岩地压灾害智能预测系统，其特征在于，所述应力传感器和应变传感器均设置在第一容置空间内，所述应力传感器和应变传感器的一端连接第二容置空间，另一端连接采动围岩。
  15. 根据权利要求12所述的一种采动围岩地压灾害智能预测系统，其特征在于，所述微震传感器设置在第三容置空间内，所述微震传感器一端连接第二容置空间，另一端连接采动围岩。
PCT/CN2020/086431 2020-04-07 2020-04-23 一种采动围岩地压灾害智能预测方法及系统 WO2021203491A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010265209.6 2020-04-07
CN202010265209.6A CN111472840B (zh) 2020-04-07 2020-04-07 一种采动围岩地压灾害智能预测方法及系统

Publications (1)

Publication Number Publication Date
WO2021203491A1 true WO2021203491A1 (zh) 2021-10-14

Family

ID=71749860

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/086431 WO2021203491A1 (zh) 2020-04-07 2020-04-23 一种采动围岩地压灾害智能预测方法及系统

Country Status (3)

Country Link
CN (1) CN111472840B (zh)
LU (1) LU502697B1 (zh)
WO (1) WO2021203491A1 (zh)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113868897A (zh) * 2021-11-19 2021-12-31 大连海事大学 一种热-力耦合条件下层状岩石统计损伤计算方法
CN114383717A (zh) * 2021-12-10 2022-04-22 中煤科工开采研究院有限公司 冲击地压巷道安全监测方法及装置
CN114611835A (zh) * 2022-03-31 2022-06-10 安徽理工大学 一种坚硬顶板矿井冲击地压灾害危险性预测分析方法
CN114994746A (zh) * 2022-06-20 2022-09-02 广西大学 一种基于隧道钢拱架的微震传感器安装装置及使用方法
CN115508548A (zh) * 2022-11-22 2022-12-23 山东科技大学 应力环境和围岩结构相结合的支护结构的确定方法及系统
WO2023115811A1 (zh) * 2021-12-24 2023-06-29 广西大学 硬岩多尺度破裂的多频段声信号监测方法、装置、设备以及存储介质
CN116777085A (zh) * 2023-08-23 2023-09-19 北京联创高科信息技术有限公司 基于数据分析和机器学习技术的煤矿水害预测系统
CN116792155A (zh) * 2023-06-26 2023-09-22 华南理工大学 一种基于分布式光纤传感的隧道健康状态监测预警方法
CN117074171A (zh) * 2023-07-21 2023-11-17 中国矿业大学(北京) 一种深部煤岩应力场耦合诱发煤岩失稳预警方法
CN117967405A (zh) * 2024-03-28 2024-05-03 山东金恒力建工有限公司 一种基于煤矿充填智能化监视及控制系统
CN114611835B (zh) * 2022-03-31 2024-05-31 安徽理工大学 一种坚硬顶板矿井冲击地压灾害危险性预测分析方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112215438B (zh) * 2020-11-09 2021-05-14 广东新禾道信息科技有限公司 一种应急灾害预警分析数据处理方法及系统
CN113756869A (zh) * 2021-08-16 2021-12-07 中煤科工开采研究院有限公司 一种冲击地压局部监测预警系统及方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SU1171676A1 (ru) * 1984-05-14 1985-08-07 Новосибирский государственный университет им.Ленинского комсомола Устройство дл измерени давлени горных пород в скважинах
CN102505965A (zh) * 2011-11-11 2012-06-20 中国矿业大学(北京) 一种岩体破坏失稳预警识别的方法
CN105260575A (zh) * 2015-11-17 2016-01-20 中国矿业大学 一种基于神经网络的巷道围岩变形预测方法
CN105759010A (zh) * 2016-02-04 2016-07-13 山东大学 一种采动影响巷道动态监测与稳定评价方法
CN107563092A (zh) * 2017-09-19 2018-01-09 山东蓝光软件有限公司 一种矿山动力灾害的全息预警方法
CN110159347A (zh) * 2019-05-05 2019-08-23 北京科技大学 一种深部高应力坚硬顶板采场动力灾害监测预警方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8498853B2 (en) * 2009-07-20 2013-07-30 Exxonmobil Upstream Research Company Petrophysical method for predicting plastic mechanical properties in rock formations
CN102155231B (zh) * 2011-03-18 2013-05-08 大连海事大学 一种隧道施工过程的快速反馈分析方法及装置
CN103883352B (zh) * 2014-04-08 2016-07-06 中煤科工集团重庆研究院有限公司 一种井下煤体失稳动力灾害的声发射预警方法
CN104198679B (zh) * 2014-09-17 2016-06-01 辽宁工程技术大学 一种煤岩变形破裂过程全波形同步综合监测系统及方法
CN105866835B (zh) * 2016-03-28 2018-11-02 中国石油大学(华东) 一种基于地应力分布的断层三维封闭性定量评价方法
CN106959748A (zh) * 2017-02-20 2017-07-18 西安科技大学 一种基于虚拟现实的巷道围岩灾害应急预案系统及方法
CN107590357B (zh) * 2017-10-31 2020-07-17 石家庄铁道大学 一种不同施工阶段隧道稳定性判别的方法
CN109918696B (zh) * 2018-11-13 2023-05-26 山西潞安环保能源开发股份有限公司常村煤矿 一种冲击地压强度等级的分类方法及装置
CN109632016A (zh) * 2019-02-20 2019-04-16 湖北理工学院 岩土体硐室开挖与围岩应力、应变监测试验装置及其方法
CN110390800B (zh) * 2019-06-06 2021-04-20 北京市地质研究所 网式灾害监测预警系统
CN210071003U (zh) * 2019-07-22 2020-02-14 北京市地质研究所 岩土体表面应变应力采集设备和网式灾害监测预警系统
CN110928181B (zh) * 2019-12-13 2021-04-13 东北大学 一种真三轴面扰动下硬岩峰后破坏过程智能控制方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SU1171676A1 (ru) * 1984-05-14 1985-08-07 Новосибирский государственный университет им.Ленинского комсомола Устройство дл измерени давлени горных пород в скважинах
CN102505965A (zh) * 2011-11-11 2012-06-20 中国矿业大学(北京) 一种岩体破坏失稳预警识别的方法
CN105260575A (zh) * 2015-11-17 2016-01-20 中国矿业大学 一种基于神经网络的巷道围岩变形预测方法
CN105759010A (zh) * 2016-02-04 2016-07-13 山东大学 一种采动影响巷道动态监测与稳定评价方法
CN107563092A (zh) * 2017-09-19 2018-01-09 山东蓝光软件有限公司 一种矿山动力灾害的全息预警方法
CN110159347A (zh) * 2019-05-05 2019-08-23 北京科技大学 一种深部高应力坚硬顶板采场动力灾害监测预警方法

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113868897A (zh) * 2021-11-19 2021-12-31 大连海事大学 一种热-力耦合条件下层状岩石统计损伤计算方法
CN114383717A (zh) * 2021-12-10 2022-04-22 中煤科工开采研究院有限公司 冲击地压巷道安全监测方法及装置
CN114383717B (zh) * 2021-12-10 2023-11-17 中煤科工开采研究院有限公司 冲击地压巷道安全监测方法及装置
WO2023115811A1 (zh) * 2021-12-24 2023-06-29 广西大学 硬岩多尺度破裂的多频段声信号监测方法、装置、设备以及存储介质
CN114611835A (zh) * 2022-03-31 2022-06-10 安徽理工大学 一种坚硬顶板矿井冲击地压灾害危险性预测分析方法
CN114611835B (zh) * 2022-03-31 2024-05-31 安徽理工大学 一种坚硬顶板矿井冲击地压灾害危险性预测分析方法
CN114994746A (zh) * 2022-06-20 2022-09-02 广西大学 一种基于隧道钢拱架的微震传感器安装装置及使用方法
CN114994746B (zh) * 2022-06-20 2024-06-11 广西大学 一种基于隧道钢拱架的微震传感器安装装置及使用方法
CN115508548A (zh) * 2022-11-22 2022-12-23 山东科技大学 应力环境和围岩结构相结合的支护结构的确定方法及系统
CN116792155A (zh) * 2023-06-26 2023-09-22 华南理工大学 一种基于分布式光纤传感的隧道健康状态监测预警方法
CN116792155B (zh) * 2023-06-26 2024-06-07 华南理工大学 一种基于分布式光纤传感的隧道健康状态监测预警方法
CN117074171A (zh) * 2023-07-21 2023-11-17 中国矿业大学(北京) 一种深部煤岩应力场耦合诱发煤岩失稳预警方法
CN117074171B (zh) * 2023-07-21 2024-03-08 中国矿业大学(北京) 一种深部煤岩应力场耦合诱发煤岩失稳预警方法
CN116777085B (zh) * 2023-08-23 2023-11-10 北京联创高科信息技术有限公司 基于数据分析和机器学习技术的煤矿水害预测系统
CN116777085A (zh) * 2023-08-23 2023-09-19 北京联创高科信息技术有限公司 基于数据分析和机器学习技术的煤矿水害预测系统
CN117967405A (zh) * 2024-03-28 2024-05-03 山东金恒力建工有限公司 一种基于煤矿充填智能化监视及控制系统
CN117967405B (zh) * 2024-03-28 2024-06-07 山东金恒力建工有限公司 一种基于煤矿充填智能化监视及控制系统

Also Published As

Publication number Publication date
CN111472840A (zh) 2020-07-31
CN111472840B (zh) 2020-11-13
LU502697B1 (en) 2022-10-14

Similar Documents

Publication Publication Date Title
WO2021203491A1 (zh) 一种采动围岩地压灾害智能预测方法及系统
CN106777772B (zh) 一种基于煤岩动力系统的矿井冲击地压危险性预测方法
Duan et al. Unloading-induced failure of brittle rock and implications for excavation-induced strain burst
Zhang et al. Numerical simulation of failure modes of concrete gravity dams subjected to underwater explosion
Zhu Numerical prediction of crater blasting and bench blasting
Das et al. Effect of rock shapes on brittle fracture using Smoothed Particle Hydrodynamics
Meng et al. Experimental study of factors affecting fault slip rockbursts in deeply buried hard rock tunnels
Wang et al. Investigation into different numerical methods in predicting the response of aluminosilicate glass under quasi-static and impact loading conditions
Dong et al. Study of mode I crack dynamic propagation behaviour and rock dynamic fracture toughness by using SCT specimens
Wang et al. Blast induced crack propagation and damage accumulation in rock mass containing initial damage
Wang et al. Investigation of microcracking behaviors in brittle rock using polygonal grain‐based distinct method
CN116127752B (zh) 一种冲击地压的预测方法及系统
CN110751337A (zh) 煤与瓦斯突出及其次生灾害危险区范围的预测方法
Kaiser Excavation vulnerability and selection of effective rock support to mitigate rockburst damage
Feng et al. Anisotropy and microcrack-induced failure precursor of shales under dynamic splitting
Fan et al. Study on dynamic loading characteristics and energy evolution of sandstone with double cracks
Yang et al. Influence of dynamic disturbance on rock creep from time, space and energy aspects
Jacobsz et al. Modelling cave mining in the geotechnical centrifuge
Hu et al. Fracture characteristics and geometric fractal of damaged sandstone under impact load
Pierce et al. A hybrid methodology for secondary fragmentation prediction in cave mines
Zhao et al. Analysis of rock damage characteristics based on particle discrete element model
CN112364489B (zh) 一种控制基岩损伤和振动效应的二氧化碳爆破施工方法
Trofimov et al. Simulation fragmentation of samples of rock at explosive loading
Gao et al. Experimental study on dynamic mechanical characteristics and energy evolution of sandstone under cyclic impact loading
Chamanzad et al. Sensitivity Analysis of Stress and Cracking in Rock Mass Blasting using Numerical Modelling

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: 20929824

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20929824

Country of ref document: EP

Kind code of ref document: A1