技术领域Technical field
本发明涉及煤矿井下通风安全技术领域，特别涉及一种基于监测数据计算的煤层瓦斯基础参数动态可视化方法。The invention relates to the technical field of underground ventilation safety in coal mines, and in particular to a dynamic visualization method of coal seam gas basic parameters calculated based on monitoring data.
背景技术Background technique
在煤层瓦斯预抽过程中，煤层瓦斯压力和含量的计算方法主要是人工监测，通过直接测定煤层残余瓦斯压力或残余瓦斯含量等参数来进行预抽煤层瓦斯效果检验。此方法虽然直接易操作，但瓦斯抽采到什么样的时间阶段后适宜进行煤层残余瓦斯压力或残余瓦斯含量直接测定却不易掌控，而现场反复多次施钻取样测定，整个测定过程中极大地造成了人力物力和时间上的浪费，无法及时地对预抽效果进行反馈，造成瓦斯治理成本的提高；还可能因为多次施工钻孔造成煤体状态破坏，从而导致得到的测定结果不准确。此外，测定过程中测定钻孔的选取存在大量的留白区，测定出来的结果并不精细化。In the process of coal seam gas pre-drainage, the calculation method of coal seam gas pressure and content is mainly manual monitoring, and the pre-drainage coal seam gas effect is tested by directly measuring parameters such as coal seam residual gas pressure or residual gas content. Although this method is direct and easy to operate, it is not easy to control at what time period after gas extraction it is appropriate to directly measure the residual gas pressure or residual gas content of the coal seam. However, repeated drilling and sampling measurements on site will greatly affect the entire measurement process. This results in a waste of manpower, material resources and time, and the inability to provide timely feedback on the pre-pumping effect, resulting in an increase in gas control costs; it may also cause damage to the coal body due to multiple construction drillings, resulting in inaccurate measurement results. In addition, there are a large number of blank areas in the selection of measurement drilling holes during the measurement process, and the measurement results are not refined.
在煤层瓦斯预抽过程中，现有的瓦斯关键参数监测及抽采效果的评判方法主要是人工监测，通过直接测定煤层残余瓦斯压力或残余瓦斯含量等参数来进行预抽煤层瓦斯效果检验。此方法虽然直接易操作，但瓦斯抽采到什么样的时间阶段后适宜进行煤层残余瓦斯压力或残余瓦斯含量直接测定却不易掌控，而现场反复多次施钻取样测定，整个评价过程中极大地造成了人力物力和时间上的浪费，无法及时地对预抽效果进行反馈，造成瓦斯治理成本的提高；还可能因为多次施工钻孔造成煤体状态破坏，从而导致得到的测定结果不准确。During the coal seam gas pre-drainage process, the existing methods for monitoring key gas parameters and evaluating the drainage effect are mainly manual monitoring, and the pre-drainage coal seam gas effect is tested by directly measuring parameters such as coal seam residual gas pressure or residual gas content. Although this method is direct and easy to operate, it is not easy to control at what time period after gas extraction it is appropriate to directly measure the residual gas pressure or residual gas content of the coal seam. However, repeated drilling and sampling measurements on site have greatly affected the entire evaluation process. This results in a waste of manpower, material resources and time, and the inability to provide timely feedback on the pre-pumping effect, resulting in an increase in gas control costs; it may also cause damage to the coal body due to multiple construction drillings, resulting in inaccurate measurement results.
发明内容Contents of the invention
为了克服以上技术问题，本发明的目的在于提供一种基于监测数据计算的煤层瓦斯基础参数动态可视化方法，通过构建煤层瓦斯抽采过程中的监测数据对于煤层瓦斯参数的反演模型，利用监测数据反演煤层抽采过程中的瓦斯压力，建立基于深度学习的数据处理方法对煤层瓦斯监测数据进行预测，利用预测数据反演未来煤层瓦斯压力的分布变化规律，并借助SURFER软件实现煤层瓦斯抽采参数过程中的动态可视化。In order to overcome the above technical problems, the purpose of the present invention is to provide a dynamic visualization method of coal seam gas basic parameters calculated based on monitoring data, by constructing an inversion model of coal seam gas parameters based on monitoring data during the coal seam gas extraction process, and using the monitoring data Invert the gas pressure during the coal seam drainage process, establish a data processing method based on deep learning to predict the coal seam gas monitoring data, use the predicted data to invert the distribution change pattern of coal seam gas pressure in the future, and use SURFER software to realize coal seam gas drainage Dynamic visualization of parameter processes.
为了实现上述目的，本发明采用的技术方案是：In order to achieve the above objects, the technical solution adopted by the present invention is:
一种基于监测数据计算的煤层瓦斯基础参数动态可视化方法，包括以下步骤；A dynamic visualization method of coal seam gas basic parameters calculated based on monitoring data, including the following steps;
(1)通过气体状态方程，质量守恒定律，煤层气流动连续性方程和煤层气运动方程得到煤层气在煤的“孔隙—裂隙”双重介质中渗流—扩散的混合非稳定流动特征，建立煤层瓦斯流场控制方程，确立方程的边界条件和初始条件，求出方程的解析解和数值解，建立煤层气抽采流量与煤层中煤层气压力的关系式；构成含瓦斯煤的流固耦合模型；(1) Through the gas state equation, the law of conservation of mass, the coal bed methane flow continuity equation and the coal bed methane motion equation, the mixed unsteady flow characteristics of coal bed methane seepage and diffusion in the "pore-fissure" dual medium of coal are obtained, and the coal bed methane is established Flow field control equation, establish the boundary conditions and initial conditions of the equation, find the analytical and numerical solutions of the equation, establish the relationship between the coalbed methane extraction flow rate and the coalbed methane pressure in the coal seam; form a fluid-solid coupling model for gas-containing coal;
(2)收集目标煤层的相关参数；(2) Collect relevant parameters of the target coal seam;
(3)结合目标煤层，确立几何模型的长、宽、高的具体尺寸，边界条件和初始条件；(3) Combined with the target coal seam, establish the specific dimensions, boundary conditions and initial conditions of the geometric model’s length, width and height;
(4)收集目标煤层预抽本煤层钻孔的抽采监测数据；(4) Collect the extraction monitoring data of the target coal seam pre-extraction drilling holes in this coal seam;
(5)将计算出的煤层原位瓦斯压力通过SURFER软件画出瓦斯压力的等值线图，从而实现煤层瓦斯压力的可视化。(5) Use the calculated in-situ gas pressure of the coal seam to draw a gas pressure contour map through SURFER software, thereby realizing the visualization of the coal seam gas pressure.
(6)通过深度学习算法对瓦斯抽采过程中关键参数进行预测，结合煤层原位瓦斯压力计算方法实现煤层瓦斯压力的动态可视化。(6) Use deep learning algorithms to predict key parameters in the gas drainage process, and combine with the coal seam in-situ gas pressure calculation method to achieve dynamic visualization of coal seam gas pressure.
所述步骤(1)中的含瓦斯煤的流固耦合模型具体为：The fluid-solid coupling model of gas-containing coal in step (1) is specifically:
其中各参数所代表的定义分别为：The definitions represented by each parameter are:
ui,j(i,j＝1,2,3)----质点的位移矢量ui,j (i,j＝1,2,3)----displacement vector of particle
εij----应变分量εij ----strain component
Km----煤基质的体积模量，PaKm ----Bulk modulus of coal matrix, Pa
βM----湿涨系数，m3/m3βM ----Wet expansion coefficient, m3 /m3
αsg----吸附解吸导致的体应变系数，kg·m-3αsg ---- volumetric strain coefficient caused by adsorption and desorption, kg·m-3
Vsg----吸附的瓦斯含量，m3·kg-1Vsg ----Adsorbed gas content, m3 ·kg-1
c1----压力系数，MPa-1c1 ----Pressure coefficient, MPa-1
c2----为温度系数，K-1c2 ---- is the temperature coefficient, K-1
VL----为朗格缪尔体积常数，m3·kg-1VL ---- is Langmuir volume constant, m3 ·kg-1
pL----朗格缪尔压力常数，PapL ---- Langmuir pressure constant, Pa
T----煤层温度，KT----Coal seam temperature, K
Tt----吸附解吸试验中的参考温度，K，取298Tt ----Reference temperature in adsorption and desorption test, K, taken as 298
E----弹性模量，PaE---- elastic modulus, Pa
v----泊松比v----Poisson's ratio
λ,G----拉梅常数λ,G----Lame constant
φm0----初始孔隙率φm0 ----Initial porosity
εm----煤基质体积应变εm ----coal matrix volume strain
KY----体积压缩系数，MPa-1KY ----Volume compressibility coefficient, MPa-1
Ks----骨架体积模量Ks ----skeleton bulk modulus
φm----基质孔隙率φm ----matrix porosity
φf----基质裂隙率φf ----matrix crack rate
km----基质孔隙渗透率km ----matrix pore permeability
kf----基质裂隙渗透率kf ----matrix crack permeability
pm----基质瓦斯压力，Papm ----matrix gas pressure, Pa
pf----裂隙瓦斯压力，Papf ---- fissure gas pressure, Pa
τ----瓦斯解吸扩散的时间，sτ----gas desorption and diffusion time, s
Mg----瓦斯的摩尔质量，kg/molMg ----molar mass of gas, kg/mol
VL----朗缪尔体积常数，m3/kgVL ----Langmuir volume constant, m3 /kg
PL----朗缪尔压力常数，PaPL ----Langmuir pressure constant, Pa
ρs----骨架密度，kg/m3ρs ----skeleton density, kg/m3
其中，公式1为含瓦斯煤应力场控制方程，是煤体受力变形的本构方程；公式2为瓦斯基质孔隙率控制方程，公式3为孔隙渗透率控制方程，公式4为瓦斯裂隙率控制方程，公式5为裂隙渗透率控制方程；公式6是瓦斯在基质中的扩散控制方程，公式7是瓦斯在裂隙中的渗流控制方程，这两个方程表达了瓦斯在煤层中渗流扩散运动方程；7个方程共同组成了含瓦斯煤的流固耦合模型；Among them, Formula 1 is the stress field control equation of gas-containing coal, which is the constitutive equation of coal mass deformation; Formula 2 is the gas matrix porosity control equation, Formula 3 is the pore permeability control equation, and Formula 4 is the gas fissure rate control equation. Equation, Formula 5 is the governing equation of fracture permeability; Formula 6 is the governing equation of gas diffusion in the matrix, and Formula 7 is the governing equation of gas seepage in fractures. These two equations express the equation of motion of gas seepage and diffusion in coal seams; Seven equations together form the fluid-solid coupling model of gas-containing coal;
煤是一种具有孔隙和裂隙的双重介质，孔隙率，裂隙率和其对应的渗透率是决定瓦斯含量和瓦斯运移的重要因素，同时也是影响含瓦斯煤体流固耦合过程中的关键因素。在钻孔瓦斯抽采过程中，瓦斯的流动会同时影响煤层内部的瓦斯压力和地应力，引起煤体的骨架所受有效应力发生变化，使煤体骨架发生相应的变形，造成孔隙率和渗透率发生动态变化。因此，考虑气固耦合作用下煤体的孔隙率和渗透率动态变化特征是研究扰动煤体的变形和其造成瓦斯运移的气固耦合作用机理的前提条件。Coal is a dual medium with pores and fissures. Porosity, fissure ratio and their corresponding permeability are important factors that determine the gas content and gas migration. They are also key factors that affect the fluid-solid coupling process of gas-containing coal. . During the process of borehole gas drainage, the flow of gas will simultaneously affect the gas pressure and ground stress inside the coal seam, causing changes in the effective stress on the skeleton of the coal body, causing corresponding deformation of the skeleton of the coal body, resulting in porosity and permeability. The rate changes dynamically. Therefore, considering the dynamic change characteristics of porosity and permeability of coal bodies under the action of gas-solid coupling is a prerequisite for studying the deformation of disturbed coal bodies and the gas-solid coupling mechanism that causes gas migration.
所述步骤(2)具体为：The step (2) is specifically:
对含瓦斯煤的流固耦合模型中的参数进行收集：Collect parameters in the fluid-solid coupling model of coal containing gas:
根据煤安规程，煤矿在进行煤矿开采前和瓦斯抽采前都会进行相关的实验和现场测试，会出具相应的报告；通过收集煤矿的《煤层煤与瓦斯突出危险性评估报告》、《矿井瓦斯涌出量预测方法》、《煤矿瓦斯抽采工程设计标准》、《煤矿安全设施设计》和《煤层瓦斯参数基础参数测试报告》中的资料可以收集到上述所有的参数；According to coal safety regulations, coal mines will conduct relevant experiments and on-site tests before coal mining and gas drainage, and corresponding reports will be issued; by collecting the coal mine's "Coal Seam Coal and Gas Outburst Hazard Assessment Report", "Mine Gas All the above-mentioned parameters can be collected from the information in "Method for Eruption Prediction", "Design Standards for Coal Mine Gas Drainage Engineering", "Design of Coal Mine Safety Facilities" and "Basic Parameter Test Report of Coal Seam Gas Parameters";
所述步骤(3)具体为：The step (3) is specifically:
将边界条件和初始条件(初始条件和边界条件根据不同的目标煤层都是不一样的，边界包括：边界荷载，边界位移，边界流通等。初始条件包括：煤岩初始位移、煤岩初始应力、初始瓦斯压力)带入含瓦斯煤的流固耦合模型当中，利用COMSOL或者FLUENT计算流体力学的软件对控制方程进行求解；通过数值计算软件对公式1的耦合模型的解算，能够得到公式2和3的数据，对数据进行拟合即可得到公式2和3，从而计算出煤层距离钻孔x距离处的瓦斯压力对于煤层抽采钻孔的变化规律；通过变化规律数据图拟合煤层瓦斯压力和钻孔流量的函数关系式和钻孔流量沿着钻孔长度的衰减规律，即：The boundary conditions and initial conditions (initial conditions and boundary conditions are different according to different target coal seams. The boundaries include: boundary load, boundary displacement, boundary circulation, etc. The initial conditions include: initial displacement of coal rock, initial stress of coal rock, Initial gas pressure) is brought into the fluid-solid coupling model of gas-containing coal, and the control equations are solved using COMSOL or FLUENT computational fluid dynamics software. By solving the coupling model of Formula 1 through numerical calculation software, Formulas 2 and 2 can be obtained. 3 data, formulas 2 and 3 can be obtained by fitting the data, thereby calculating the change pattern of the gas pressure at a distance x from the borehole to the coal seam drainage borehole; fitting the coal seam gas pressure through the change pattern data chart The functional relationship between the borehole flow rate and the attenuation law of the borehole flow rate along the borehole length is:
QL＝f(L) (2)QL =f(L) (2)
其中Px----距离钻孔x距离处的煤层原位瓦斯压力，QL----沿孔长距离孔口L处的瓦斯预抽钻孔监测流量，L----沿孔长距离孔口的距离。Among them, Px ---- the in-situ gas pressure of the coal seam at a distance The distance from the long orifice.
将收集好的单一钻孔的瓦斯数据中的瓦斯钻孔流量带入公式(2)和(3)得出目标煤层原位残余瓦斯压力在抽采过程中网格化的数值，通过SURFER软件将各个数值代入即可实现目标煤层瓦斯在抽采过程的可视化效果。Put the gas borehole flow rate in the collected gas data of a single borehole into formulas (2) and (3) to obtain the gridded value of the in-situ residual gas pressure of the target coal seam during the drainage process, and use SURFER software to By substituting each numerical value, the visualization effect of the target coal seam gas in the drainage process can be achieved.
所述步骤(4)具体为：The step (4) is specifically:
即钻孔抽采工况流量，瓦斯浓度，瓦斯纯流量，抽采负压；将每个钻孔收集的数据进行预处理，每个钻孔的数据利用步骤(3)中拟合的反演公式计算出煤层总距离该钻孔距离x处的煤层原位瓦斯压力。That is, the flow rate of borehole extraction conditions, gas concentration, pure gas flow rate, and drainage negative pressure; the data collected from each borehole are preprocessed, and the data of each borehole is inverted using the fitting in step (3) The formula calculates the in-situ gas pressure of the coal seam at the total distance x from the coal seam to the drilling distance.
所述步骤(5)具体为：The step (5) is specifically:
利用循环神经网络中的GRU模型对煤层瓦斯预抽历史监测数据进行训练，将预处理后的数据集分为训练集，验证集和测试集；利用训练集对模型进行训练，将训练结果利用验证集进行验证，最后利用测试集对模型准确性进行测试；最终形成煤层瓦斯抽采关键参数的预测模型和预测数据；The GRU model in the recurrent neural network is used to train the coal seam gas pre-pumping historical monitoring data, and the preprocessed data set is divided into a training set, a verification set and a test set; the training set is used to train the model, and the training results are verified using The set is used for verification, and finally the test set is used to test the accuracy of the model; finally a prediction model and prediction data for key parameters of coal seam gas drainage are formed;
将预测的数据与煤层瓦斯反演模型相结合，计算出煤层瓦斯抽采过程中原位瓦斯压力，利用SURFER软件实现可视化效果，从而实现煤层原位瓦斯压力的动态预测和反演。The predicted data is combined with the coal seam gas inversion model to calculate the in-situ gas pressure during the coal seam gas extraction process, and the SURFER software is used to achieve visualization effects, thereby achieving dynamic prediction and inversion of the coal seam in-situ gas pressure.
一种煤层瓦斯综合参数测定系统，包括抽放系统、瓦斯抽采负压、流量、气体浓度、温度传感器和工业环网和数据服务器；A coal seam gas comprehensive parameter measurement system, including a drainage system, gas drainage negative pressure, flow rate, gas concentration, temperature sensor, industrial ring network and data server;
所述抽放系统连接传感器，传感器连接工业环网，工业环网将接收到的数据传递至数据服务器。The pumping system is connected to a sensor, the sensor is connected to an industrial ring network, and the industrial ring network transmits the received data to the data server.
通过调节抽放系统上的单钻孔的开关阀，能够实现对预抽钻孔的单孔的数据在线监测；By adjusting the on-off valve of a single borehole on the drainage system, online data monitoring of a single hole in a pre-drainage borehole can be realized;
抽放系统对接煤层瓦斯预抽钻孔，通过调节抽放系统上的单钻孔的开关阀，实现对单个钻孔的开关，当抽放系统和传感器需要对某一钻孔中的气体数据进行测定的时候，通过开关阀将该条线路其他钻孔关掉，保留需要测定的钻孔，实现对单一钻孔的测定，将测定数据通过工业环网之间的传输最终保存到数据服务器。The drainage system is connected to the coal seam gas pre-drainage borehole. By adjusting the on-off valve of a single borehole on the drainage system, the opening and closing of a single borehole is realized. When the drainage system and sensors need to perform gas data in a certain borehole, During measurement, other boreholes in the line are turned off through the switch valve, and the boreholes that need to be measured are retained to achieve the measurement of a single borehole, and the measurement data is finally saved to the data server through transmission between industrial ring networks.
钻孔管道连接抽放泵，抽放泵再对接瓦斯抽采负压、流量、气体浓度和温度传感器。The drilled pipeline is connected to the drainage pump, which is then connected to the gas drainage negative pressure, flow rate, gas concentration and temperature sensors.
本发明的有益效果。beneficial effects of the present invention.
本发明提供的精细化划分煤层瓦斯压力高低区域并且实现动态可视化的方法，能够弥补传统测定煤层瓦斯压力方法的宽泛性、模糊性和静态化等不足之处。The method provided by the present invention to finely divide the high and low areas of coal seam gas pressure and realize dynamic visualization can make up for the shortcomings of the traditional method of measuring coal seam gas pressure such as broadness, fuzziness and staticity.
本发明提供的精细化划分煤层瓦斯压力高低区域并且实现动态可视化的方法，通过精细化监测设备对现场单一钻孔的数据监测，建立含瓦斯煤的流固耦合模型解算出钻孔抽采流量对于煤层瓦斯残余压力的反演模型和钻孔流量沿孔长的衰减规律，结合基于深度学习的多传感器融合瓦斯参数多步预测方法，能够弥补传统测定煤层瓦斯压力方法的宽泛性、模糊性和静态化等不足之处。The method provided by the present invention to finely divide the high and low areas of coal seam gas pressure and realize dynamic visualization uses refined monitoring equipment to monitor the data of a single borehole on site, and establishes a fluid-solid coupling model of gas-containing coal to calculate the relationship between borehole drainage flow and The inversion model of coal seam gas residual pressure and the attenuation law of borehole flow along the hole length, combined with the multi-sensor fusion multi-step prediction method of gas parameters based on deep learning, can make up for the broadness, fuzziness and staticity of the traditional method of measuring coal seam gas pressure. and other deficiencies.
附图说明：Picture description:
图1为本煤层预抽钻孔布置示意图。Figure 1 is a schematic diagram of the layout of pre-drainage boreholes in this coal seam.
图2为煤层工作面瓦斯预抽钻孔参数现场监测系统。Figure 2 shows the on-site monitoring system for gas pre-extraction drilling parameters in coal seam working faces.
图3为小波去噪流程图。Figure 3 is the flow chart of wavelet denoising.
图4为异常点数据处理示意图。Figure 4 is a schematic diagram of outlier data processing.
图5为噪声值数据处理示意图。Figure 5 is a schematic diagram of noise value data processing.
图6为GRU结构图。Figure 6 is the GRU structure diagram.
图7为基于监测数据的煤层瓦斯参数动态可视化方法的流程示意图。Figure 7 is a schematic flow chart of the dynamic visualization method of coal seam gas parameters based on monitoring data.
图8为某矿原始瓦斯分布区域示意图。Figure 8 is a schematic diagram of the original gas distribution area of a mine.
图9为本发明目标煤层瓦斯分布示意图。Figure 9 is a schematic diagram of gas distribution in the target coal seam of the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅为本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.
如图1-图9所示：煤层的预抽钻孔一般分布比较密集，通常为钻孔的间距为3-6m。本发明能够利用单一钻孔的监测数据，通过反演模型实现对目标煤层精细化的煤层瓦斯压力和含量的参数化计算，从而能够达到目前技术达不到的精细测定。相当于将目标煤层网格化，如图1所示。As shown in Figures 1 to 9: Pre-extraction boreholes in coal seams are generally distributed densely, and the spacing between boreholes is usually 3-6m. The present invention can utilize the monitoring data of a single borehole and realize the parameterized calculation of refined coal seam gas pressure and content of the target coal seam through the inversion model, thereby achieving precise measurement that cannot be achieved by current technology. It is equivalent to gridding the target coal seam, as shown in Figure 1.
此外，本发明通过深度学习循环神经网络建立预测模型对瓦斯预抽监测历史数据进行训练，从而对未来瓦斯监测数据关键参数进行预测，通过预测值与反演模型结合，实现煤层瓦斯抽采过程中的瓦斯压力和含量的动态可视化。In addition, the present invention establishes a prediction model through a deep learning circular neural network to train the historical data of gas pre-extraction monitoring, thereby predicting the key parameters of future gas monitoring data. By combining the prediction value with the inversion model, the process of coal seam gas extraction can be realized. Dynamic visualization of gas pressure and content.
相关技术中，煤层瓦斯预抽过程中瓦斯原位压力的标定是通过人工测量的方式来确定的，测量结果对于指导整个煤层意义来说很宽泛，不精细；此外测量过程耗费大量人力物力。本发明解决的技术问题是针对矿井煤层瓦斯预抽过程中煤层原位瓦斯压力不清晰不透明的问题，同时煤层瓦斯压力缺乏动态可视化方法。In related technologies, the calibration of gas in-situ pressure during coal seam gas pre-extraction is determined by manual measurement. The measurement results are very broad and not precise in guiding the entire coal seam. In addition, the measurement process consumes a lot of manpower and material resources. The technical problem solved by this invention is to address the problem that the in-situ gas pressure of the coal seam is unclear and opaque during the pre-extraction process of coal seam gas in mines. At the same time, the coal seam gas pressure lacks a dynamic visualization method.
本发明第一方面提供了一种基于煤层预抽瓦斯监测数据反演煤层原位瓦斯压力的方法，具体操作如下：The first aspect of the present invention provides a method for inverting the in-situ gas pressure of a coal seam based on coal seam pre-extraction gas monitoring data. The specific operations are as follows:
(1)通过气体状态方程，质量守恒定律，煤层气流动连续性方程和煤层气运动方程推导出煤层气在煤的“孔隙—裂隙”双重介质中渗流—扩散的混合非稳定流动特征，建立煤层瓦斯流场控制方程，确立方程的边界条件和初始条件，求出方程的解析解和数值解，建立煤层气抽采流量与煤层中煤层气压力的关系式。瓦斯的流固耦合模型如(1) Through the gas state equation, the law of conservation of mass, the coal bed methane flow continuity equation and the coal bed methane motion equation, the mixed unsteady flow characteristics of coal bed methane seepage and diffusion in the "pore-fissure" dual medium of coal are deduced, and the coal bed methane is established. The gas flow field control equation, establish the boundary conditions and initial conditions of the equation, obtain the analytical and numerical solutions of the equation, and establish the relationship between the coalbed methane extraction flow rate and the coalbed methane pressure in the coal seam. The fluid-structure coupling model of gas is as follows:
式1所示Shown in formula 1
上式中包含了瓦斯煤体的应力变形模型，孔隙率与渗透率动态变化模型，裂隙率与渗透率动态变化模型和瓦斯在煤层中渗流扩散模型。The above formula includes the stress deformation model of the gas coal body, the dynamic change model of porosity and permeability, the dynamic change model of fracture rate and permeability, and the gas seepage and diffusion model in the coal seam.
(2)收集目标煤层的相关参数，参数收集表如下所示，各个参数取值来自于目标矿井的实际测定数值或物质固定参数。(2) Collect relevant parameters of the target coal seam. The parameter collection table is as follows. The values of each parameter come from the actual measured values or material fixed parameters of the target mine.
参数取值Parameter value
(3)结合目标煤层，确立几何模型的长、宽、高的具体尺寸，边界条件和初始条件。将边界条件和初始条件带入耦合模型当中，利用COMSOL或这个FLUENT等计算流体力学的软件对控制方程进行求解，从而可以计算出煤层距离钻孔x距离处的瓦斯压力对于煤层抽采钻孔的变化规律。通过变化规律数据图拟合煤层瓦斯压力和钻孔流量的函数关系式，即：(3) Combined with the target coal seam, establish the specific dimensions, boundary conditions and initial conditions of the geometric model's length, width and height. Bring the boundary conditions and initial conditions into the coupled model, and use computational fluid dynamics software such as COMSOL or FLUENT to solve the control equations, so that the gas pressure at x distance from the coal seam to the borehole can be calculated. Change patterns. The functional relationship between coal seam gas pressure and borehole flow rate is fitted through the change pattern data chart, that is:
其中Px----距离钻孔x距离处的煤层原位瓦斯压力，Q----瓦斯预抽钻孔监测流量。Among them,P
(4)收集目标煤层预抽本煤层钻孔的抽采监测数据，即钻孔抽采工况流量，瓦斯浓度，瓦斯纯流量，抽采负压。将每个钻孔收集的数据进行预处理，每个钻孔的数据利用步骤(3)中拟合的反演公式计算出煤层总距离该钻孔距离x处的煤层原位瓦斯压力。(4) Collect the drainage monitoring data of the target coal seam pre-drainage borehole, that is, the borehole drainage working condition flow rate, gas concentration, gas pure flow rate, and drainage negative pressure. The data collected from each borehole are preprocessed, and the in-situ gas pressure of the coal seam at the borehole distance x from the total distance of the coal seam is calculated using the inversion formula fitted in step (3).
(5)将计算出的煤层原位瓦斯压力通过SURFER软件画出瓦斯压力的等值线图，从而实现煤层瓦斯压力的可视化。(5) Use the calculated in-situ gas pressure of the coal seam to draw a gas pressure contour map through SURFER software, thereby realizing the visualization of the coal seam gas pressure.
第五步实现了可视化，但是只是静态的可视化结果，通过对某一时刻的监测数据实现当下时刻的煤层残余瓦斯压力的可视化。后面的步骤是通过对实时在线监测的数据进行预测，将静态的可视化动起来，实现动态化可视化，可以通过现有的监测数据能够预知为了煤层残余瓦斯压力的动态变化趋势。The fifth step realizes visualization, but it is only a static visualization result. Through monitoring data at a certain moment, the residual gas pressure of the coal seam at the current moment can be visualized. The next step is to predict the real-time online monitoring data and animate the static visualization to achieve dynamic visualization. The existing monitoring data can be used to predict the dynamic change trend of the residual gas pressure in the coal seam.
(6)为了更好的实现煤层瓦斯参数的动态反演，本发明还提供了一种煤层瓦斯综合参数测定系统，系统有抽放管路，瓦斯抽采负压、流量、气体浓度、温度等传感器，工业环网和数据服务器等组成，通过调节抽放系统上的单钻孔的开关阀，能够实现对预抽钻孔的单孔的数据在线监测。(6) In order to better realize the dynamic inversion of coal seam gas parameters, the present invention also provides a coal seam gas comprehensive parameter measurement system. The system has a drainage pipeline, gas drainage negative pressure, flow rate, gas concentration, temperature, etc. It consists of sensors, industrial ring networks and data servers. By adjusting the on-off valve of a single borehole on the drainage system, online data monitoring of a single hole in a pre-drainage borehole can be realized.
(7)将收集好的瓦斯钻孔监测数据进行预处理。针对数据的缺失值，异常值和噪声值进行处理，分别采用三指数平滑法，自回归模型和小波去噪法进行处理。(7) Preprocess the collected gas drilling monitoring data. To deal with the missing values, outliers and noise values of the data, the three-exponential smoothing method, the autoregressive model and the wavelet denoising method are used respectively.
处理方法如下所示：The processing method is as follows:
A：三次指数平滑法可以使补充的缺失值具备平滑性，并维持原有时间序列的变化趋势。针对采集的煤层气时间序列样本点Xt(t＝1,2,3…,N)中某一时刻的缺失值，对其进行三次指数平滑处理，公式如下所示：A: The cubic exponential smoothing method can smooth the supplementary missing values and maintain the changing trend of the original time series. For the missing values at a certain moment in the collected coal bedmethane time series sample points
式中：l为插入的数据点数与平滑处理的步距；Xt+l为应求的缺失值；at,bt,ct分别为三次指数平滑法的预测参数；为t时刻的一次指数平滑值，/>为t时刻的二次指数平滑指，/>为t时刻的三次指数平滑指；α为平滑系数。计算公式如下所示：In theformula :l is the number of inserted data points and the step size of the smoothing process; is the exponential smoothing value at time t,/> is the quadratic exponential smoothing index at time t,/> is the cubic exponential smoothing index at time t; α is the smoothing coefficient. The calculation formula is as follows:
式中：Xt为煤层气浓度缺失值；为t-1时刻的一次指数平滑值；/>为t-1时刻的二次指数平滑值；/>为t-1时刻的三次指数平滑值。通过以上公式计算，最终得出应补充的缺失值Xt+l。In the formula: Xt is the missing value of coalbed methane concentration; Is the exponential smoothing value at time t-1;/> Is the quadratic exponential smoothing value at time t-1;/> is the cubic exponential smoothing value at time t-1. Calculated through the above formula, the missing value Xt+l that should be supplemented is finally obtained.
B:处理异常值数据时一般采用剔除或替代的方法，本文采用时间序列的自回归模型(Auto-Regressive model，AR)来处理少量的异常值，具体处理步骤如下：B: When processing outlier data, the method of elimination or replacement is generally used. This article uses the time series auto-regressive model (AR) to handle a small number of outliers. The specific processing steps are as follows:
确定需要处理的样本。根据阈值设定找出异常值，在异常值出现之前的监测数据中选取建模样本，选取的样本中应尽量避免需要替代的数据；Determine the samples that need to be processed. Find outliers based on threshold settings, and select modeling samples from the monitoring data before the outliers appear. The selected samples should try to avoid data that needs replacement;
标准化处理。为了提升模型的运算效率，使用前文提到的数据标准化处理方法对数据进行标准化处理；Standardized processing. In order to improve the computing efficiency of the model, the data is standardized using the data standardization method mentioned above;
模型参数估计和定阶。估计模型的参数用Burg法确定，模型阶数由赤池信息准则(Akaike Information Criterion，AIC)确定，函数如下式所示：Model parameter estimation and ordering. The parameters of the estimated model are determined by the Burg method, and the model order is determined by the Akaike Information Criterion (AIC). The function is as follows:
AIC(p)＝-2lnL+2p (10)AIC(p)＝-2lnL+2p (10)
其中，p为模型阶数，L为似然函数,L的公式可表示为：Among them, p is the model order, L is the likelihood function, and the formula of L can be expressed as:
异常数据的替换。根据异常值的个数i，分别利用AR模型进行i次预测，将各个预测值进行标准化处理逆转换后替代各异常值。C：小波变换是将基本小波的函数作位移τ后，在不同尺度α下，与待分析信号x(t)作内积，由于所取的时间序列数据属于离散型，本申请主要介绍结合离散小波变换阈值消噪方法，小波阈值去噪过程如下图3所示：Replacement of abnormal data. According to the number i of outliers, the AR model is used to perform i predictions respectively, and each predicted value is normalized and reverse transformed to replace each outlier. C: Wavelet transform is to convert the basic wavelet After the displacement τ is made as a function of The threshold denoising process is shown in Figure 3 below:
①小波变换多尺度分解。通过确定最佳小波函数，分解层数L，对时间序列xt进行多层小波分解，得到各层小波系数αj,k，x(k)为xt的采样数据，xt的正交小波变换分解公式为：① Multi-scale decomposition by wavelet transform. By determining the optimal wavelet function and decomposing the number of layers L, multi-layer wavelet decomposition is performed on the time series xt to obtain the wavelet coefficients αj, k of eachlayer . The transformation decomposition formula is:
其中，αj,k是小波系数，αj,k是尺度系数，αj,k和g为一对正交镜像滤波器组，j为分解层数，n为离散采样点。Among them, αj,k is the wavelet coefficient, αj,k is the scale coefficient, αj,k and g are a pair of orthogonal mirror filter groups, j is the number of decomposition layers, and n is the discrete sampling point.
②阈值处理。通常阈值的处理方法包括硬阈值和软阈值，硬阈值去噪法即当小波系数αj,k的绝对值小于给定阈值时，令其为0；大于阈值时，令其保持不变，其中为新的小波系数，其表达式为：②Threshold processing. Usually threshold processing methods include hard threshold and soft threshold. The hard threshold denoising method means that when the absolute value of the wavelet coefficient αj,k is less than a given threshold, let it be 0; when it is greater than the threshold, let it remain unchanged, where is the new wavelet coefficient, and its expression is:
软阈值去噪法即当小波系数αj,k的绝对值小于给定的阈值时，令其为0；大于阈值时，令其都减去阈值，其表达式为：The soft threshold denoising method means that when the absolute value of the wavelet coefficient αj,k is less than the given threshold, let it be 0; when it is greater than the threshold, let it all subtract the threshold, and its expression is:
③小波逆变换重构信号。通过阈值处理过后的新的小波系数和尺度系数βj,k重构消噪后的信号，其表达式为：③Inverse wavelet transform reconstructs the signal. New wavelet coefficients after threshold processing and scale coefficient βj,k to reconstruct the denoised signal, its expression is:
(8)利用循环神经网络中的GRU模型对煤层瓦斯预抽历史监测数据进行训练，其中训练步骤如下：(8) Use the GRU model in the recurrent neural network to train the historical monitoring data of coal seam gas pre-pumping. The training steps are as follows:
门控循环单元(Gated Recurrent Unit，GRU)为循环神经网络中的一种，GRU模型结构由两个逻辑门组成，分别为更新门(update gate)和重置门(reset gate)，GRU中更新门决定前段时刻的信息是否被保存到当前时刻；重置门控制历史信息不被保存到下一时刻。GRU模型结构如图6所示。Gated Recurrent Unit (GRU) is a type of recurrent neural network. The GRU model structure consists of two logic gates, namely update gate and reset gate. The update gate in GRU The gate determines whether the information from the previous moment is saved to the current moment; the reset gate controls that the historical information is not saved to the next moment. The GRU model structure is shown in Figure 6.
其中rt为重置门，Zt为更新门，Ut为重置信息，ht和ht-1分别为输入信息和输出信息，Xt为时间为t时的输入序列，yt时间为t时的输出序列。GRU模型运行原理公式如下所示。Among them, rt is the reset gate, Zt is the update gate, Ut is the reset information, ht and ht-1 are the input information and output information respectively, Xt is the input sequence at time t, and yt time is the output sequence at time t. The operating principle formula of the GRU model is as follows.
更新门计算公式：Update gate calculation formula:
Zt＝σ(Wz·[ht-1,xt])Zt =σ(Wz ·[ht-1 ,xt ])
＝σ(Whz·ht-1+Wxz·xt) (17)=σ(Whz ·ht-1 +Wxz ·xt ) (17)
重置门计算公式：Reset gate calculation formula:
rt＝σ(Wr·[ht-1,xt])rt =σ(Wr ·[ht-1 ,xt ])
＝σ(Whr·ht-1+Wxr·xt) (18)=σ(Whr ·ht-1 +Wxr ·xt ) (18)
更新参数：Update parameters:
(9)将预测的数据与煤层瓦斯反演模型相结合，收集煤层预抽钻孔内瓦斯流量和抽采负压参数，将数据利用煤层瓦斯关键参数深度学习预测模型进行训练和预测，然后预测后的数据带入反演模型当中，计算出煤层瓦斯抽采过程中原位瓦斯压力，利用SURFER软件实现可视化效果，从而实现煤层原位瓦斯压力的动态预测和反演。(9) Combine the predicted data with the coal seam gas inversion model, collect the gas flow and drainage negative pressure parameters in the coal seam pre-drainage borehole, train and predict the data using the coal seam gas key parameter deep learning prediction model, and then predict The resulting data is brought into the inversion model to calculate the in-situ gas pressure during the coal seam gas extraction process, and the SURFER software is used to achieve visualization effects, thereby achieving dynamic prediction and inversion of the in-situ gas pressure of the coal seam.
实施例：Example:
通过本发明的方法可以实现将215工作面的煤层瓦斯压力分布情况精细化表示，以某矿215工作面的本煤层预抽钻孔316号钻孔到416号钻孔为例，该区域内本煤层预抽钻孔为平行布置，钻孔间距为6m，目标煤层长度为600m，则利用煤层预抽钻孔的瓦斯流量和浓度的监测数据，结合反演模型和预测模型，可以得到如下的精细化煤层抽采过程中瓦斯压力的可视化展示。The method of the present invention can achieve a refined representation of the coal seam gas pressure distribution in the 215 working face. Taking the coal seam pre-drainage boreholes No. 316 to No. 416 in the 215 working face of a mine as an example, the coal seam gas pressure distribution in this area is The coal seam pre-drainage boreholes are arranged in parallel, the borehole spacing is 6m, and the target coal seam length is 600m. Using the monitoring data of gas flow and concentration of the coal seam pre-pumping boreholes, combined with the inversion model and prediction model, the following fine-grained results can be obtained Visual display of gas pressure during coal seam drainage.
从前后示意图9可以看出，本发明的煤层瓦斯压力计算方法更为精细化且能够实现动态展示，能够更好地指导煤层瓦斯预抽系统的调控；例如：It can be seen from the before and after schematic diagram 9 that the coal seam gas pressure calculation method of the present invention is more refined and can achieve dynamic display, and can better guide the regulation of the coal seam gas pre-extraction system; for example:
1.能够降低赋存瓦斯区域的抽采钻孔的负压，加大高瓦斯赋存区域的抽采钻孔的抽采负压，从而降低煤层的整体消突的预抽采时间。1. It can reduce the negative pressure of drainage boreholes in gas-rich areas and increase the negative pressure of drainage boreholes in high gas-rich areas, thereby reducing the pre-drainage time for the overall outburst elimination of coal seams.
2.能够更好地预估煤层瓦斯预抽采达标的具体时间。2. Ability to better estimate the specific time for coal seam gas pre-drainage to reach standards.
3.能够更好地对单一钻孔的抽采效果给出具体评价。3. Able to provide a better detailed evaluation of the extraction effect of a single borehole.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818679.4ACN116861813B (en) | 2023-07-05 | 2023-07-05 | Coal bed gas basic parameter dynamic visualization method based on monitoring data calculation |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310818679.4ACN116861813B (en) | 2023-07-05 | 2023-07-05 | Coal bed gas basic parameter dynamic visualization method based on monitoring data calculation |
| Publication Number | Publication Date |
|---|---|
| CN116861813Atrue CN116861813A (en) | 2023-10-10 |
| CN116861813B CN116861813B (en) | 2024-12-24 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310818679.4AActiveCN116861813B (en) | 2023-07-05 | 2023-07-05 | Coal bed gas basic parameter dynamic visualization method based on monitoring data calculation |
| Country | Link |
|---|---|
| CN (1) | CN116861813B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663276A (en)* | 2023-05-23 | 2023-08-29 | 中国矿业大学 | Synchronous inversion method for coal bed gas pressure and permeability |
| CN117266804A (en)* | 2023-11-13 | 2023-12-22 | 东营中威石油技术服务有限公司 | Jet pump drainage control method and system |
| CN118128600A (en)* | 2024-04-18 | 2024-06-04 | 安徽理工大学 | A system and method for monitoring gas distribution in coal seam drilling holes |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140019047A1 (en)* | 2011-03-30 | 2014-01-16 | China University Of Mining And Technology | Multi-information coupling prediction method of coal and gas outburst danger |
| CN111425185A (en)* | 2020-03-23 | 2020-07-17 | 湖南科技大学 | A control method of a dynamic visualization system for eliminating outbursts in coal mining working face and reaching the extraction standard |
| CN112727534A (en)* | 2021-01-15 | 2021-04-30 | 重庆大学 | Gas drilling hole arrangement method based on true three-dimensional stress and permeability dynamic change |
| CN113392567A (en)* | 2021-08-16 | 2021-09-14 | 中国矿业大学(北京) | Method and system for predicting coal bed gas of double-pore coal body |
| CN115983097A (en)* | 2022-12-05 | 2023-04-18 | 陕煤集团神木柠条塔矿业有限公司 | Fast inversion method of coal seam gas drainage characteristic parameters based on borehole drainage data |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140019047A1 (en)* | 2011-03-30 | 2014-01-16 | China University Of Mining And Technology | Multi-information coupling prediction method of coal and gas outburst danger |
| CN111425185A (en)* | 2020-03-23 | 2020-07-17 | 湖南科技大学 | A control method of a dynamic visualization system for eliminating outbursts in coal mining working face and reaching the extraction standard |
| CN112727534A (en)* | 2021-01-15 | 2021-04-30 | 重庆大学 | Gas drilling hole arrangement method based on true three-dimensional stress and permeability dynamic change |
| CN113392567A (en)* | 2021-08-16 | 2021-09-14 | 中国矿业大学(北京) | Method and system for predicting coal bed gas of double-pore coal body |
| CN115983097A (en)* | 2022-12-05 | 2023-04-18 | 陕煤集团神木柠条塔矿业有限公司 | Fast inversion method of coal seam gas drainage characteristic parameters based on borehole drainage data |
| Title |
|---|
| 郭军: "地下煤自燃隐蔽火源探测方法综述及新技术展望", 《中国安全科学学报》, 31 August 2022 (2022-08-31)* |
| 郭涛: "钻孔抽放瓦斯流固耦合分析及数值模拟", 《硕士论文全文库》, 15 March 2011 (2011-03-15)* |
| 陈月霞: "瓦斯抽采过程中参数演化及钻孔优化数值模 拟研究", 《硕士论文全文库》, 15 April 2019 (2019-04-15)* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663276A (en)* | 2023-05-23 | 2023-08-29 | 中国矿业大学 | Synchronous inversion method for coal bed gas pressure and permeability |
| CN116663276B (en)* | 2023-05-23 | 2024-01-05 | 中国矿业大学 | Synchronous inversion method for coal bed gas pressure and permeability |
| CN117266804A (en)* | 2023-11-13 | 2023-12-22 | 东营中威石油技术服务有限公司 | Jet pump drainage control method and system |
| CN118128600A (en)* | 2024-04-18 | 2024-06-04 | 安徽理工大学 | A system and method for monitoring gas distribution in coal seam drilling holes |
| Publication number | Publication date |
|---|---|
| CN116861813B (en) | 2024-12-24 |
| Publication | Publication Date | Title |
|---|---|---|
| CN116861813A (en) | A dynamic visualization method of coal seam gas basic parameters based on monitoring data calculation | |
| EP1984860B1 (en) | Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| US8504341B2 (en) | Methods, systems, and computer readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| CN104535472B (en) | Method and device for detecting dynamic permeability of coal petrography | |
| CN109345140B (en) | Auxiliary method for early warning of water inrush disaster of coal mine | |
| CN106680451A (en) | Underground rapid measurement method for coal and gas outburst parameter as well as apparatus thereof | |
| Liang et al. | An sand plug of fracturing intelligent early warning model embedded in remote monitoring system | |
| CN114707222A (en) | Seepage-considered tailing dam body stability real-time online analysis and prediction method | |
| CN105092813A (en) | Method for determining gas contents of coal beds | |
| CN107701238A (en) | Coal and gas outburst early warning device and method | |
| CN113703053B (en) | Microseismic dynamic monitoring method and system for water damage on working surfaces | |
| CN114595504A (en) | A method for inversion and interpretation of production profiles of fracturing horizontal wells in shale gas reservoirs | |
| CN116402387A (en) | System and method for mining gas extraction parameters and evaluating standard | |
| CN116976146A (en) | Fracturing well yield prediction method and system coupled with physical driving and data driving | |
| CN116658246B (en) | Coal mine water damage monitoring and early warning system and method | |
| CN115455791A (en) | Method for improving landslide displacement prediction accuracy rate based on numerical simulation technology | |
| CN119047343B (en) | Wellbore stability control method, device, equipment and storage medium for dynamically adjusting drilling fluid ratio | |
| CN115860197A (en) | Data-driven coal bed gas yield prediction method and system | |
| CN114971070A (en) | Method for predicting underground water level of mining area | |
| CN111982567B (en) | Method for constructing gas loss compensation model in deep hole reverse circulation sampling process | |
| Tao et al. | An anthropomorphic fuzzy model for the time-spatial assessment of sandstone seepage damage | |
| Zhang et al. | An ANN-based soft-sensor to estimate the sand content of drilling fluid | |
| CN110807265A (en) | A method for judging combustion and explosion hazard in closed fire area based on atmospheric disturbance | |
| CN108868756A (en) | A kind of coal seam reservoirs rock texture complexity evaluation method based on well logging information | |
| CN118966082B (en) | A database-based method for evaluating the ability of oil and gas wells to prevent gas channeling |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |