CN115660235B - Method for predicting yield of one-well multi-purpose coal bed gas well in whole production process - Google Patents
Method for predicting yield of one-well multi-purpose coal bed gas well in whole production process Download PDFInfo
- Publication number
- CN115660235B CN115660235B CN202211687606.8A CN202211687606A CN115660235B CN 115660235 B CN115660235 B CN 115660235B CN 202211687606 A CN202211687606 A CN 202211687606A CN 115660235 B CN115660235 B CN 115660235B
- Authority
- CN
- China
- Prior art keywords
- mining
- coal
- goaf
- well
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses a method for predicting the yield of a one-well multi-purpose coal bed gas well in the whole production process, belonging to the technical field of mining; the invention considers that an important difference between a one-well multi-purpose production process and conventional coal bed gas production is that a reservoir structure is influenced by coal mining and has space-time structure evolution, the whole production process of the one-well multi-purpose coal bed gas well is divided into three stages of in-situ coal layer area mining, mining area mining and goaf mining according to the sequence of reservoir mining disturbance, a three-region permeability space-time evolution calculation method is established based on the structure space-time evolution rule of the in-situ coal layer area, the mining area and the goaf on the basis of comprehensive geological conditions, hydraulic fracturing parameters and mining parameters by utilizing a neural network analysis method, and a yield prediction method of the whole production process of the one-well multi-purpose coal bed gas well is formed and provides reference for the evaluation of the development potential of the one-well multi-purpose coal bed gas and the optimization of a development scheme.
Description
Technical Field
The invention relates to the technical field of mining, in particular to a method for predicting the yield of a multi-purpose coal bed gas well in the whole production process.
Background
The basic idea of one-well multi-purpose coal bed gas development is to arrange a ground development well in a recently planned mining area, and with the advance of an underground working face, the coal bed gas ground development well is changed into an in-situ area drainage and goaf drainage well, and one coal bed gas well provides gas extraction service for the whole process of coal mine production, so that the drilling utilization rate is improved.
The key technology of modifying a mining (air) well series by using a ground coalbed methane pre-pumping well is innovatively researched and developed, the concept of 'one well with multiple purposes' of repeatedly using the ground pre-pumping well to extract in-situ coal seam area, mining area and goaf is really realized for years in the industry, the repeated construction of the pre-pumping well, the mining well and the goaf on the same working face is avoided, and a low-cost solution is provided for the ground treatment of the gas.
The coal bed gas well productivity directly influences the economic benefit of coal bed gas development, and reasonable prediction of the coal bed gas development productivity is an important basis for designing a development scheme and adjusting a later development scheme. Although a great deal of research has been conducted at home and abroad on the yield prediction of coal-bed gas wells, the gas yield prediction research is mainly directed to in-situ coal seam zones. One important difference between the one-well multi-purpose coal bed methane mining and the traditional in-situ coal bed area coal bed methane mining is that the one-well multi-purpose coal bed methane production process needs to go through three stages of an in-situ coal bed area, a mining area and a goaf, and anti-reflection measures and space-time evolution of a reservoir structure caused by coal mining exist in the three stages. Therefore, the method is based on the space-time evolution characteristics of the reservoir structure in three stages of the in-situ coal seam area, the mining area and the goaf, and realizes the whole-process yield prediction of the production of the multi-purpose coal-bed gas well in one well on the basis of determining the space-time evolution characteristics of the permeability of the coal-bed gas in different mining stages by using a neural network analysis method.
Disclosure of Invention
The invention aims to provide a method for predicting the yield of a multipurpose coal bed gas well production overall process so as to solve the problems in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for predicting the yield of a one-well multi-purpose coal bed gas well in the whole production process comprises the following steps:
s1, dividing the whole production process of the multi-purpose coal bed gas well of one well into three stages of in-situ coal bed area mining, mining of a mining area and mining of a goaf according to the sequence of mining disturbance of a reservoir;
s2, calculating and determining the ranges of the in-situ coal seam area, the mining area and the goaf by using a similar physical experiment and a neural network analysis method;
s3, in the in-situ coal seam area, calculating a permeability spatiotemporal evolution rule under hydraulic fracturing according to fracture network spatiotemporal evolution characteristics under hydraulic fracturing, and predicting the gas production rate of the coal seam gas well in the in-situ coal seam area under the hydraulic fracturing condition by using the obtained evolution rule;
s4, in the mining area, according to a permeability space-time evolution rule caused by mining, simulation and prediction of a mining output numerical value of a coal bed gas well in the mining area are completed, and compared with field data, a prediction simulation method is perfected;
s5, acquiring adsorption characteristics of lump coal, three-dimensional distribution of voidage of the goaf and the overlying rock stratum and spatial and temporal evolution of permeability of the goaf in the goaf according to the three-dimensional distribution of the voidage of the goaf and the overlying rock stratum and the distribution of the lump degree of the residual coal in the goaf, and completing prediction of coalbed methane yield of the goaf based on the spatial and temporal evolution of the void space and the permeability on the basis;
s6, integrating the operations of S3-S5, and constructing and obtaining a multi-purpose method for predicting the gas production rate of the coal bed gas in the whole process of the original coal bed area, the mining area and the goaf in one well.
Preferably, the permeability spatiotemporal evolution law under hydraulic fracturing mentioned in S3 is specifically obtained as follows:
and collecting the in-situ coal seam area fracture network development conditions under different geological and hydraulic fracturing parameters in domestic and foreign documents, and determining the in-situ coal seam area fracture network spatial-temporal evolution rule under the multi-factor comprehensive action by adopting a neural network analysis method.
Preferably, the permeability spatiotemporal evolution law of the mining region mentioned in S4 is obtained by:
collecting the distribution characteristics of fracture zones and collapse zones of the mining area under different geological and mining conditions in domestic and foreign documents, and determining the spatiotemporal evolution characteristics and rules of the reservoir structure of the mining area by adopting a neural network analysis method and an overburden structure theory.
Preferably, the three-dimensional distribution of the void ratios of the goaf and the overburden rock stratum and the distribution of the residual coal block degrees of the goaf mentioned in the step S5 are obtained by the following method:
based on the three-dimensional distribution of the void ratios of the goaf and the overlying strata and the distribution data of the remaining coal block degrees under different geological and mining conditions in domestic and foreign documents, the three-dimensional distribution of the void ratios of the goaf and the overlying strata and the distribution rule of the remaining coal block degrees are determined by adopting a neural network analysis method and an overlying strata structure theory. .
Compared with the prior art, the invention provides a method for predicting the yield of a multi-purpose coal bed gas well in the whole production process, which has the following beneficial effects:
(1) In the one-well multi-purpose process, different main control mechanisms influencing reservoir structure evolution at different stages are different, the reservoir structure evolution directly influences permeability space-time evolution, and the permeability space-time evolution is the basis of one-well multi-purpose yield prediction in coal and coal bed gas co-mining.
(2) Although reservoir structure evolution is a main control factor in the process of co-production of coal and coal bed gas by one well, other factors also have influence on the yield of the coal bed gas, and the reservoir structure evolution is also a result of the common influence of multiple factors. The method is a nonlinear problem of complex multi-factor comprehensive action no matter the precise representation of the space-time evolution of reservoir structures at different stages or the accurate prediction of the yield of the coal bed gas. Therefore, the method analyzes the spatial-temporal evolution rules of the structures and the permeabilities of different stages of the in-situ coal seam area, the mining area and the goaf by using a neural network analysis method, and further realizes the accurate prediction of the yield of the coal seam gas.
Drawings
FIG. 1 is a schematic illustration of in-situ coal seam area mining in example 1 of the present invention;
FIG. 2 is a schematic diagram of mining of a mining area in example 1 of the present invention;
fig. 3 is a schematic view of goaf mining in example 1 of the present invention.
The numbering in the figures illustrates:
1. a coal bed gas extraction well; 2. an overburden; 3. a coal seam.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example 1:
referring to fig. 1-3, the method for predicting the overall process yield of the production of the one-well multi-purpose coal-bed gas well comprises the following steps:
s1: carrying out similar physical experiments, researching the influence ranges of different geology (overlying strata lithology, different rock stratum thicknesses and coal seam burial depth) and mining conditions (mining height, working face size and working face propelling speed) on an in-situ coal seam region, a mining area and a goaf, wherein the specific value range of the experiments depends on the size of an in-situ measured value, controlling other variables to be equal to the in-situ measured value in the research process, setting the experimental variables to be 0.2M, 0.5M, 1M, 1.2M and 1.5M, setting M to be the measured value, and calculating the ranges of the in-situ coal seam region, the mining area and the goaf by using the similar physical experiments;
s2: collecting the spatial-temporal distribution data of an in-situ coal seam area, a mining area and a goaf under different geologies (overburden lithology, different rock stratum thicknesses and coal seam burial depth) and mining conditions (mining height, working face size and working face propelling speed) in domestic and foreign documents, calculating the spatial-temporal distribution range of the in-situ coal seam area, the mining area and the goaf by utilizing a neural network analysis method and an overburden structure theory (an overburden structure theory, a pressure arch theory, a cantilever beam theory, a preformed fracture theory, a masonry beam theory, a transmission rock beam theory, a key layer and the like), and comprehensively analyzing the analysis results of the similar physical experiment result and the neural network method analysis result to determine a final result;
the neural network method is characterized in that an Artificial Neural Network (ANN) is used for training selected input features and output features, normalization processing is firstly carried out on data in the process, 80% of the data are used for a training set, and 20% of the data are used for a testing set. Due to the difference between the initial weight and the threshold, the Genetic Algorithm (GA) is used for carrying out super-parameter adjustment optimization on the ANN structure, and finally the optimal number of hidden layers and the number of neurons in each layer are obtained. The correlation coefficient (R) and Mean Square Error (MSE) are used for measuring the accuracy of the prediction of the space-time distribution range of the in-situ coal seam area, the mining area and the goaf;
s3: collecting the in-situ coal seam area fracture network development conditions under different geological and hydraulic fracturing parameters in domestic and foreign documents, and constructing an in-situ coal seam area fracture network spatial-temporal evolution model under the multi-factor comprehensive action by utilizing a neural network analysis method;
s4: constructing a permeability spatiotemporal evolution model under hydraulic pressure based on fracture network spatiotemporal evolution characteristics, and further forming a method for predicting the gas production rate of the coal bed gas well in the in-situ coal bed area under the hydraulic fracturing condition;
s5: collecting mining area space-time distribution data under different geology (overburden lithology, different rock stratum thicknesses and coal seam burial depths) and mining conditions (mining height, working face size and working face propelling speed) in domestic and foreign documents, calculating mining area space-time distribution characteristics by utilizing a neural network analysis method and an overlying strata structure theory (an overlying strata structure theory, a pressure arch theory, a cantilever beam theory, a preformed fracture theory, a masonry beam theory, a rock transfer beam theory, a key layer theory and the like), further constructing a gas seepage model under multi-field coupling of the mining area under the mining influence condition, and finally forming a mining area coal-bed gas well gas production rate prediction method;
s6: collecting three-dimensional distribution of void ratios of a goaf and an overlying rock and distribution data of residual coal blocks of the goaf under different geologies (overlying rock lithology, different rock stratum thicknesses and coal seam burial depths) and mining conditions (mining height, working face size and working face propelling speed) in domestic and foreign documents, and constructing a determination method of the void ratios of the goaf and the overlying rock and the distribution of the residual coal blocks of the goaf by utilizing a neural network analysis method and an overlying rock structure theory (the overlying rock structure theory, a pressure arch theory, a cantilever beam theory, a preformed fracture theory, a masonry beam theory, a rock beam transmission theory, a key layer and the like); on the basis of obtaining the adsorption characteristic of lump coal, the three-dimensional distribution of the voidage of the goaf and the overlying rock stratum and the spatial and temporal evolution of the permeability of the goaf, establishing a goaf coalbed methane yield prediction method based on the spatial and temporal evolution of the void space and the permeability;
s7: integrating the gas yield prediction methods of three stages of in-situ coal seam area mining, mining area mining and goaf mining, and establishing a one-well multi-purpose method for predicting the gas yield of the coal seam in the whole process of the in-situ coal seam area, the mining area and the goaf.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (1)
1. The method for predicting the yield of the whole production process of the one-well multi-purpose coal-bed gas well is characterized by comprising the following steps of:
s1, dividing the whole production process of the multi-purpose coal bed gas well of one well into three stages of in-situ coal bed area mining, mining of a mining area and mining of a goaf according to the sequence of mining disturbance of a reservoir;
s2, calculating and determining the ranges of the in-situ coal seam region, the mining region and the goaf by using a similar physical experiment and a neural network analysis method;
s3, in the in-situ coal seam area, according to the fracture network spatial-temporal evolution characteristics under hydraulic fracturing, by collecting the in-situ coal seam area fracture network development conditions under different geological and hydraulic fracturing parameters in domestic and foreign documents, determining the in-situ coal seam area fracture network spatial-temporal evolution rule under the multi-factor comprehensive action by adopting a neural network analysis method, and completing the prediction of the gas production rate of the coal seam gas well of the in-situ coal seam area under the hydraulic fracturing condition by utilizing the obtained evolution rule;
s4, in the mining area, determining the spatial-temporal evolution characteristics and rules of the reservoir structure of the mining area by collecting the distribution characteristics of fracture zones and collapse zones of the mining area under different geological and mining conditions in domestic and foreign documents and adopting a neural network analysis method and an overlying strata structure theory, and completing the simulation and prediction of the extraction yield numerical value of the coal-bed gas well in the mining area by utilizing the obtained evolution rules, comparing the simulation and prediction with field data, and perfecting a prediction simulation method;
s5, determining the three-dimensional distribution of the void ratios of the goaf and the overlying strata and the distribution rule of the block degrees of the left coal in the goaf based on the three-dimensional distribution of the void ratios of the goaf and the overlying strata and the distribution data of the block degrees of the left coal under different geology and mining conditions in domestic and foreign documents by adopting a neural network analysis method and an overlying strata structure theory, further obtaining the adsorption characteristics of the blocky coal, the three-dimensional distribution of the void ratios of the goaf and the overlying strata and the spatial and temporal evolution of the permeability of the goaf, and completing the prediction of the coal bed gas yield of the goaf based on the spatial and spatial evolution of the permeability on the basis;
s6, integrating the operations of S3-S5, and constructing and obtaining a multi-purpose method for predicting the gas production rate of the coal bed gas in the whole process of the original coal bed area, the mining area and the goaf in one well.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687606.8A CN115660235B (en) | 2022-12-28 | 2022-12-28 | Method for predicting yield of one-well multi-purpose coal bed gas well in whole production process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687606.8A CN115660235B (en) | 2022-12-28 | 2022-12-28 | Method for predicting yield of one-well multi-purpose coal bed gas well in whole production process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115660235A CN115660235A (en) | 2023-01-31 |
| CN115660235B true CN115660235B (en) | 2023-03-31 |
Family
ID=85022348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211687606.8A Active CN115660235B (en) | 2022-12-28 | 2022-12-28 | Method for predicting yield of one-well multi-purpose coal bed gas well in whole production process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660235B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10428626B2 (en) * | 2010-10-18 | 2019-10-01 | Schlumberger Technology Corporation | Production estimation in subterranean formations |
| AU2017267994B2 (en) * | 2016-05-20 | 2020-07-09 | Gas Technology Institute | Hydraulic fracturing system and method |
| CN114165196A (en) * | 2021-12-06 | 2022-03-11 | 中国矿业大学 | Comprehensive efficient extraction method for closing coal bed gas in-situ-goaf of coal mine |
| CN114263457B (en) * | 2021-12-30 | 2024-04-02 | 中国地质大学（武汉） | Coalbed methane well gas production simulation platform and yield analysis and prediction method |
| CN114048932A (en) * | 2022-01-13 | 2022-02-15 | 西南石油大学 | Coal-bed gas well gas production rate prediction method based on LSTM |
| CN114809992B (en) * | 2022-04-20 | 2023-08-08 | 太原理工大学 | Low permeability reservoir coal gas full life cycle efficient extraction method |
-
2022
- 2022-12-28 CN CN202211687606.8A patent/CN115660235B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115660235A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009705B (en) | Shale reservoir compressibility evaluation method based on support vector machine technology | |
| CN114708393B (en) | Mine stress field twinning modeling assimilation system and method in full-time air mining process | |
| CN102041995B (en) | System for monitoring complicated oil deposit flooding conditions | |
| CN104992468A (en) | Fracture-cavern type carbonate hydrocarbon reservoir three-dimensional geological modeling method | |
| CN103472484A (en) | Horizontal well track optimization method based on RS three-dimensional sensitivity seismic attribution analysis | |
| CN111305891B (en) | Three-dimensional comprehensive efficient and accurate treatment technical method for coal-oil-gas coexisting mine | |
| CN106569288B (en) | Fractured reservoir quality evaluation method based on reservoir fracture effectiveness cluster analysis | |
| CN113177322B (en) | Fracturing single well control reserve calculation method | |
| CN107237627A (en) | A kind of well spacing method for karst carbonate reservoir | |
| CN115163025B (en) | In-situ leaching accurate mining method for sandstone type uranium ores | |
| CN106401574A (en) | Method for predicting stratum pressure of high temperature geothermal well before drilling | |
| CN110069751A (en) | A kind of non-undercompacted formation pore pressure prediction method | |
| CN115660235B (en) | Method for predicting yield of one-well multi-purpose coal bed gas well in whole production process | |
| CN110851991B (en) | Underground water flow numerical simulation method | |
| CN110390154A (en) | A method of improving Complex reservoir reservoir numerical simulation efficiency | |
| CN110532507A (en) | A method of the fine and close oily reservoir Drilling ratio of well of improving the standard | |
| CN116122801A (en) | Shale oil horizontal well volume fracturing compressibility comprehensive evaluation method | |
| CN112948924A (en) | Near unconsolidated formation mining water flowing fractured zone height determination method based on overlying strata structure | |
| Zhang et al. | BP neural network with genetic algorithm optimization for prediction of geo-stress state from wellbore pressures | |
| CN114809992B (en) | Low permeability reservoir coal gas full life cycle efficient extraction method | |
| CN116956420A (en) | Tunnel structure integrated analysis method based on three-dimensional geological model | |
| CN108921350A (en) | Metal mine goaf top covering rockmass Mobile Space-time law forecasting method | |
| CN111898267A (en) | Method for evaluating dangerousness of rock burst based on sedimentary geological conditions | |
| CN116842789B (en) | Encryption well wall stability analysis method considering production time window | |
| CN117372639B (en) | Three-dimensional geological-geophysical modeling method combining sparse diaphysis section with auxiliary surface at any position |
Legal Events
| 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 |