CN110259442B - Coal measure stratum hydraulic fracturing fracture horizon identification method - Google Patents
Coal measure stratum hydraulic fracturing fracture horizon identification method Download PDFInfo
- Publication number
- CN110259442B CN110259442B CN201910571709.XA CN201910571709A CN110259442B CN 110259442 B CN110259442 B CN 110259442B CN 201910571709 A CN201910571709 A CN 201910571709A CN 110259442 B CN110259442 B CN 110259442B
- Authority
- CN
- China
- Prior art keywords
- fracture
- elastic wave
- hydraulic fracturing
- stratum
- coal
- 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
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
- E21B43/25—Methods for stimulating production
- E21B43/26—Methods for stimulating production by forming crevices or fractures
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B49/00—Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Abstract
The invention discloses a method for identifying a hydraulic fracturing fracture layer of a coal measure stratum, which comprises the following steps of 1, selecting the coal measure stratum to be fractured, drilling a stratum core by using a core drilling machine, and carrying out a hydraulic fracturing fracture elastic wave detection experiment on each stratum to obtain the hydraulic fracturing fracture elastic wave characteristics of each stratum; step 2, training the corresponding relation between the fracture elastic wave characteristics and the coal bed by utilizing a neural network, and establishing a fracture elastic wave layer position identification model; and 3, identifying a model from the fracture elastic wave layer position according to the on-site hydraulic fracturing fracture elastic waves to identify an actual fracture layer position. The invention has the technical effects that: the real-time monitoring of the hydraulic fracturing fracture process is realized, and whether the rock stratum is fractured or not is judged according to the fracture characteristics of the rock stratum and the coal bed, so that the fracturing process can be adjusted in time, and the hydraulic fracturing efficiency is improved; the method is suitable for monitoring and evaluating the hydraulic fracture of the coal bed gas.
Description
Technical Field
The invention belongs to the technical field of coal bed gas development and utilization, and particularly relates to a coal measure stratum hydraulic fracturing fracture horizon identification method for evaluating coal bed gas hydraulic fracturing.
Background
The hydraulic fracturing technology is an important technical means in coal bed gas development due to the strong and effective permeability increasing capability. By applying the hydraulic fracturing technology to the underground coal mine, the underground gas outburst danger is effectively eliminated, and the efficient extraction of gas is promoted.
At present, the judgment of the fracturing range and the monitoring of the fracturing process are the difficulties of the hydraulic fracturing research of coal mines. The fracturing range not only comprises a coal seam, but also comprises a coal seam top and bottom plate; the top and bottom coal seams are fractured while the coal seams are fractured due to hydraulic fracturing. A large amount of coal seams are broken, so that gas extraction in the later period is facilitated, but too many rock strata are broken, so that a large amount of fracturing water leakage is caused, and the coal seam fracturing effect is reduced.
The existing hydraulic fracturing is still lack of a technical means for effectively judging the fracturing range, so that a coal rock layer fracture identification method in the hydraulic fracturing process is needed to be found, which layer is fractured is judged in real time, the hydraulic fracturing process is adjusted in time, and the hydraulic fracturing efficiency is improved.
Disclosure of Invention
Aiming at the problem that the coal seam or rock stratum is difficult to determine to break in the conventional hydraulic fracturing, the invention aims to provide a method for identifying the hydraulic fracturing layer position of a coal measure stratum, which monitors the hydraulic fracturing process in real time, adjusts the hydraulic fracturing process in time and improves the hydraulic fracturing efficiency.
The technical problem to be solved by the invention is realized by the technical scheme, which comprises the following steps:
step 1, selecting a coal-series stratum to be fractured, drilling a stratum core by using a core drilling machine, and performing a hydraulic fracturing elastic wave detection experiment on each stratum to obtain the hydraulic fracturing elastic wave characteristics of each stratum;
and 3, identifying the actual fractured position according to the fracture elastic wave of the hydraulic fracturing on site through the fracture elastic wave position identification model.
The invention has the technical effects that:
1. the real-time monitoring of the hydraulic fracturing fracture process is realized, and whether the rock stratum is fractured or not is judged according to the fracture characteristics of the rock stratum and the coal bed, so that the fracturing process can be adjusted in time, and the hydraulic fracturing efficiency is improved.
2. The method belongs to a nondestructive testing method, has small engineering quantity, is easy to implement, and is suitable for monitoring and evaluating the hydraulic fracturing of the coal bed gas.
Drawings
The drawings of the invention are illustrated below:
FIG. 1 is a diagram of neural network operation;
FIG. 2 is a diagram of Matlab neural network tools and data management windows;
FIG. 3 is a diagram illustrating the recognition effect of the embodiment.
In FIG. 2, input Data is an Input Data area; target Data is a Target Data area; the Input Delay States is an Input Delay switching area; nets are network areas; output Data is an Output Data area; error Data is an Error Data area; layer Delay States is a Layer Delay state area; the method includes the steps that buttons are needed to be operated when data variables are imported from space or data files; new. is a button to be operated when a new network or a variable is built; open.. Is a button that needs to be operated when a variable or a neural network is turned on; export. Delete is a button which needs to be operated when a variable or a network is deleted; help is a button which needs to be operated when Help information of a Matlab neural network tool and a data management window is displayed; close is a button that needs to be operated when closing the data management window.
In fig. 3, a is the signal identification result in the case of only coal seam breakage; b is the signal identification error under the condition that only the coal bed is broken; c is the signal identification result under the condition that only the sandstone layer is fractured; d is the signal identification error in the case of only sandstone layer fracture; d is a signal identification result under the condition that both the coal bed and the sandstone layer are fractured; f is the signal identification error under the condition that the coal bed and the sandstone layer are broken.
Detailed Description
The invention is further illustrated with reference to the following figures and examples:
the invention comprises the following steps:
step 1, selecting a coal measure stratum to be fractured, drilling a stratum core by using a core drilling machine, and performing a hydraulic fracturing elastic wave detection experiment on each stratum to obtain the hydraulic fracturing elastic wave characteristics of each stratum.
The method specifically comprises the following steps:
11 Taking out the rock core with the diameter of 100 mm of the pre-fractured coal measure stratum by using a core drilling machine;
12 ) layering the taken out cores according to the layer relation, and numbering the layers from shallow to deep in sequence asC（C=1,2, 3,...,k）. In this example, there are two layers, one of which is coal numbered 1; the other layer is rock numbered 2. Then part each layer, utilize the unipolar press to compress the experiment with the position that parts in proper order, utilize elastic wave detecting instrument to gather the position simultaneously and compress experiment elastic wave signal, then extract that every position compression is not less than 50 when destroying fracture elastic wave time spectrum as pending data. The embodiment obtains elastic wave time spectrums of 100 rock formations and coal bed fractures as data to be processed.
13 And) carrying out FFT operation on the data to be processed obtained in the step 12) one by one to obtain frequency spectrum data. Then, taking the frequency corresponding to the maximum amplitude in the frequency spectrum data as a main frequency; the quotient of the amplitude value integrated with the frequency and divided by the frequency bandwidth is taken as the average frequency. Secondly, taking the time interval from the amplitude of the time spectrum signal obtained in the step 12) to the maximum amplitude after the amplitude of the time spectrum signal firstly crosses a threshold set by an elastic wave acquisition instrument as rising time; taking the time interval from the amplitude to finally fall to the threshold after the amplitude crosses the threshold for the first time as the duration; and taking the sum of squares of the amplitudes in the duration as energy. Finally, the result of each data processing is assigned to a fracture elastic wave feature sequence Pa = [ dominant frequency, average frequency, rise time, duration, energy ].
And 2, training the corresponding relation between the fracture elastic wave characteristics and the rock stratum by utilizing a neural network, and establishing a fracture elastic wave layer position identification model.
As shown in figure 1, the neural network comprises an input layer, a hidden layer and an output layer, wherein input nodes are elements in a fracture elastic wave feature sequence Pa, and the output result is the coal rock layer numberC. The method for establishing the fracture elastic wave horizon identification model specifically comprises the following steps:
21 Matlab software, enter nntool in the command window and press Enter key, open Neural Network/Data Manager window as shown in FIG. 2.
22 Create input data and target data. Clicking a new.. Button in a Neural Network/Data Manager window, selecting a Data tab, inputting a variable name P, selecting a variable type as Inputs, copying all the characteristic sequences Pa obtained in the step 1 to a Value window, and clicking a Create button to finish creation. And creating target data T by the same method, wherein the value of T is the rock stratum number corresponding to Pa. In this example P contains the fracture signature sequences for each 50 groups of coal and sandstone.
23 ) creating a network. Press new.. Button in the new Network/Data Manager window, select Network tab, output Network name and Network type. In this embodiment, the network name is a default value, and the network type selects a strict Radial basis (Radial basis). P is selected in an Input data pulldown box, and T is selected in a Target data pulldown box. Spread takes a default value.
24 Network training. The embodiment adopts the radial basis network and does not need training. For the Network needing training, selecting the created Network in a Neural Network/Data Manager window, clicking an open.
And 3, identifying the actual fractured position according to the fracture elastic wave of the hydraulic fracturing on site through the fracture elastic wave position identification model.
The method specifically comprises the following steps:
31 ) and field elastic wave collection. And (3) performing hydraulic fracturing on the selected coal-based stratum construction drill hole, selecting a place with a smaller disturbance seismic source within 100 meters from the bottom of a fracturing hole, drilling a hole with the construction diameter of 50mm to a hard and stable stratum, filling a solid metal rod into the drill hole, and sealing the hole by using super glue to ensure that the metal rod is in close contact with a rock body. An elastic wave detector is fixed at the exposed end of the metal rod and connected with an elastic wave acquisition instrument to acquire an elastic wave signal in the hydraulic fracturing process;
32 ) and extracting the field signal characteristics. Extracting a characteristic sequence Pt of the elastic wave of the on-site fracture by the method of the step 13) in the step 1, = [ dominant frequency, average frequency, rising time, duration and energy ];
33 ) a field signal input. Pt is created as input data according to step 22) in step 2. This example uses a known rupture signal and rupture layer data to test the model. Pt in this example comes from three situations, the first being the signal Ptestcoal with only coal fractures, the second being the signal Ptestrock with only sandstone fractures, and the third being the signal Ptestcoal with both coal and sandstone fractures, as shown in fig. 2. In order to examine the accuracy of the model, it is necessary to calculate the error between the recognition result and the actual fracture horizon, and in this embodiment, three output data corresponding to Ptestcoal, ptestrock and Ptestcoal are created, which are Ttestcoal, ttestrock and Ttestcoal, respectively, when the corresponding fracture horizon is known in advance.
34 Identification of fracture horizon. Selecting the created Network in a Neural Network/Data Manager window, clicking an open. In the same way, ptestrock and Ptestcoalrock are identified.
35 ) observing the recognition result. In the Neural Network/Data Manager window, clicking the Export. The recognition results were plotted in Matlab using a plotting tool, as shown in fig. 3:
in the embodiment, a network model is obtained by using 50 groups of training data of each coal rock, and then the actual fracture horizon is identified. In fig. 3a, 10 test sample signals are input, and the identification result is 1, which belongs to coal seam breakage; in fig. 3c, 10 test sample signals are input, and the recognition result is 2, which belongs to formation fracture; in fig. 3e, 1-5 test sample signals are input, the identification result is 1, 6-10 test sample signals are input, and the identification result is 2, i.e. 1-5 test sample signals are coal seam fracture signals, and 6-10 test sample signals are rock formation fracture signals.
As can be seen from the identification results of 30 test samples, the identification accuracy rate reaches 100%, the identification error is almost 0, and the effectiveness of the method is verified.
The invention overcomes the problem that which layer is cracked cannot be judged in the traditional hydraulic fracturing process, realizes the real-time monitoring of the hydraulic fracturing process, and provides an effective technical scheme for the monitoring and evaluation of hydraulic fracturing.
Claims (4)
1. A hydraulic fracturing fracture horizon identification method for a coal measure stratum is characterized by comprising the following steps:
step 1, selecting a coal measure stratum to be fractured, drilling a stratum core by using a core drilling machine, and performing a hydraulic fracturing elastic wave detection experiment on each stratum to obtain a hydraulic fracturing elastic wave characteristic sequence Pa = [ dominant frequency, average frequency, rise time, duration and energy ] of each stratum;
step 2, training a corresponding relation between the fracture elastic wave characteristics and the coal bed by utilizing a neural network, and establishing a fracture elastic wave layer position identification model;
and 3, identifying the actual fractured position by the fracture elastic wave position identification model according to the elastic wave signals collected within 100 meters from the bottom of the fracturing hole in the hydraulic fracturing process.
2. The method for identifying the hydraulic fracturing fracture horizon of the coal measure stratum according to claim 1, wherein in the step 1, the method specifically comprises the following steps:
11 Taking out the rock core with the diameter of 100 mm of the pre-fractured coal measure stratum by using a core drilling machine;
12 B), layering the taken out rock cores according to the horizon relation, numbering each layer from shallow to deep as C, C =1,2,3, \8230, k, then separating each layer, sequentially performing a compression experiment on the separated horizons by using a single-shaft press, simultaneously detecting elastic wave signals of the horizon compression experiment by using an elastic wave detector, and then extracting not less than 50 fracture elastic wave signals of each horizon compression failure as data to be processed;
13 Processing the data to be processed obtained in the step 12) one by one to obtain a fracture elasticity wave feature sequence Pa = [ dominant frequency, average frequency, rise time, duration and energy ].
3. The method for identifying the hydraulic fracturing fracture horizon of the coal measure stratum as claimed in claim 2, wherein in the step 2, a Matlab neural network tool is used for network design, training and identification.
4. The method for identifying the hydraulic fracturing fracture horizon of the coal-based formation according to claim 2 or 3, wherein the step 3 comprises the following steps:
31 Performing hydraulic fracturing on the selected coal measure strata construction drill hole, and simultaneously selecting a place with a smaller disturbance seismic source within 100 meters from the bottom of a fracturing hole to install an elastic wave sensor to acquire an elastic wave signal in the hydraulic fracturing process;
32 According to the method of the step 13) in the step 1), extracting a field fracture elastic wave feature sequence Pt = [ main frequency, average frequency, rising time, duration and energy ];
33 Using the fracture layer identification model obtained in the step 2, inputting field elastic data Pt to obtain a field fracture and fracture layerC。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910571709.XA CN110259442B (en) | 2019-06-28 | 2019-06-28 | Coal measure stratum hydraulic fracturing fracture horizon identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910571709.XA CN110259442B (en) | 2019-06-28 | 2019-06-28 | Coal measure stratum hydraulic fracturing fracture horizon identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110259442A CN110259442A (en) | 2019-09-20 |
| CN110259442B true CN110259442B (en) | 2022-10-21 |
Family
ID=67922609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910571709.XA Active CN110259442B (en) | 2019-06-28 | 2019-06-28 | Coal measure stratum hydraulic fracturing fracture horizon identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110259442B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11834943B2 (en) | 2019-11-15 | 2023-12-05 | Peck Tech Consulting Ltd. | Systems, apparatuses, and methods for determining rock-coal transition with a drilling machine |
| CN111636859B (en) * | 2020-07-09 | 2022-08-16 | 中煤科工集团重庆研究院有限公司 | Coal rock while-drilling self-identification method based on micro-fracture wave detection |
| CN112906595A (en) * | 2021-03-03 | 2021-06-04 | 中国矿业大学(北京) | Landslide prediction method and system based on elastic waves |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106223918A (en) * | 2016-08-18 | 2016-12-14 | 西南石油大学 | Fracturing fracture pressure preparation method and device |
| WO2018117890A1 (en) * | 2016-12-21 | 2018-06-28 | Schlumberger Technology Corporation | A method and a cognitive system for predicting a hydraulic fracture performance |
| CN109209356A (en) * | 2017-07-06 | 2019-01-15 | 中国石油化工股份有限公司 | A method of stratum compressibility is determined based on tension fracture and shear fracture |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009056992A2 (en) * | 2007-11-01 | 2009-05-07 | Schlumberger Canada Limited | Reservoir fracture simulation |
| US8392165B2 (en) * | 2009-11-25 | 2013-03-05 | Halliburton Energy Services, Inc. | Probabilistic earth model for subterranean fracture simulation |
| US10073185B2 (en) * | 2010-12-27 | 2018-09-11 | Baker Hughes, A Ge Company, Llc | Predicting hydraulic fracture propagation |
| RU2461026C1 (en) * | 2011-05-31 | 2012-09-10 | Шлюмберже Текнолоджи Б.В. | Method of determining geometric characteristics of hydraulic fracture cracks |
| CN104975836B (en) * | 2015-06-30 | 2018-12-25 | 中国石油天然气股份有限公司 | Rock sample hydraulic fracture form sound emission diagnostic test method and device |
| CN105181927B (en) * | 2015-08-05 | 2017-11-28 | 河南能源化工集团研究院有限公司 | The hypotonic coal seam hydraulic fracture simulation experiment method of multi- scenarios method |
| US20170145793A1 (en) * | 2015-08-20 | 2017-05-25 | FracGeo, LLC | Method For Modeling Stimulated Reservoir Properties Resulting From Hydraulic Fracturing In Naturally Fractured Reservoirs |
| US20170131192A1 (en) * | 2015-11-06 | 2017-05-11 | Baker Hughes Incorporated | Determining the imminent rock failure state for improving multi-stage triaxial compression tests |
| CA3034219C (en) * | 2016-08-18 | 2023-03-21 | Seismos, Inc. | Method for evaluating and monitoring formation fracture treatment using fluid pressure waves |
| CN106988739B (en) * | 2017-05-19 | 2020-05-22 | 中国石油集团川庆钻探工程有限公司 | Shale reservoir fracturing fracture identification and interpretation evaluation method |
| CN107676126B (en) * | 2017-10-16 | 2019-01-29 | 重庆大学 | It is a kind of to utilize the concordant region hydraulic fracturing method for intercepting control |
| CN107503727B (en) * | 2017-10-16 | 2019-05-03 | 重庆大学 | It is a kind of that a layer hydraulic fracturing range investigation method is worn based on in-situ stress monitoring |
| CN108007784B (en) * | 2017-11-20 | 2023-06-06 | 西安科技大学 | Coupling fracturing cavity volume visualization test system and fracture development analysis method |
| CN108829993B (en) * | 2018-06-23 | 2019-07-02 | 东北石油大学 | Coal seam pulsed hydraulic fracturing amplitude and Frequency Design method |
| CN109342298B (en) * | 2018-12-18 | 2022-03-25 | 重庆大学 | Experimental method for high-power pulse wave induced cracking of gas-containing coal body |
-
2019
- 2019-06-28 CN CN201910571709.XA patent/CN110259442B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106223918A (en) * | 2016-08-18 | 2016-12-14 | 西南石油大学 | Fracturing fracture pressure preparation method and device |
| WO2018117890A1 (en) * | 2016-12-21 | 2018-06-28 | Schlumberger Technology Corporation | A method and a cognitive system for predicting a hydraulic fracture performance |
| CN109209356A (en) * | 2017-07-06 | 2019-01-15 | 中国石油化工股份有限公司 | A method of stratum compressibility is determined based on tension fracture and shear fracture |
Non-Patent Citations (2)
| Title |
|---|
| "径向井—脉动水力压裂对煤层应力扰动效果的影响规律研究";陆沛青;《中国优秀博士论文全文库工程科技I辑》;20180215(第2期);全文 * |
| "微地震监测与模拟技术在裂缝研究中的应用";王爱国;《中国优秀博士论文全文库工程科技I辑》;20090715(第7期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110259442A (en) | 2019-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110259442B (en) | Coal measure stratum hydraulic fracturing fracture horizon identification method | |
| CN113050159B (en) | Coal rock hydraulic fracturing crack micro-seismic positioning and propagation mechanism monitoring method | |
| Zhu et al. | Interpretation of the extent of hydraulic fracturing for rockburst prevention using microseismic monitoring data | |
| Li et al. | Characteristics of microseismic waveforms induced by hydraulic fracturing in coal seam for coal rock dynamic disasters prevention | |
| CN204462405U (en) | A kind of rock burst omen early warning system based on acoustic emission | |
| MX2011005549A (en) | Method for determining the closure pressure of a hydraulic fracture. | |
| NO334626B1 (en) | Procedure for monitoring fracture | |
| Sinha et al. | A novel screening method for selection of horizontal refracturing candidates in shale gas reservoirs | |
| CN108374657B (en) | Automatic well breakpoint identification method | |
| CN111025392B (en) | Coal rock body fracturing crack real-time rapid monitoring and evaluation method utilizing microseismic signals | |
| CN203783570U (en) | Comprehensive logging integrated formation pressure detecting device in process of drilling | |
| CN206220950U (en) | Afflux drawing type producing profile testing tubing string in a kind of oil pipe of horizontal well | |
| CN104005747B (en) | A kind of confined pressure hydraulic fracturing experiments device and using method thereof | |
| CN105930604A (en) | Shale gas production degree determining method and apparatus | |
| CN110020785A (en) | Thick oil thermal extraction well cementation evaluation system based on deep learning | |
| CN107701179A (en) | Conventional logging data-based compressibility evaluation method for shale gas reservoir | |
| US20130056201A1 (en) | Method for evaluating hydrocarbon-containing subterrean formations penetrated by a directional wellbore | |
| CN104678455A (en) | Terrestrial fracture-cavern reservoir identification method | |
| Rucker et al. | Low cost field application of pressure transient communication for rapid determination of the upper limit of horizontal well spacing | |
| CN206091981U (en) | Rock natural frequency tester in shale gas well | |
| CN105064987A (en) | Interpretation and evaluation method for water layer recognition by logging while drilling Q parameter | |
| Reyes-Montes et al. | Validation of a synthetic rock mass model using excavation induced microseismicity | |
| Qiu et al. | Risk prediction of coal and gas outburst based on abnormal gas concentration in blasting driving face | |
| CN105891904A (en) | Continental facies fracture-cavity type reservoir stratum identification method | |
| CN112412390B (en) | Method and device for evaluating second interface of well cementation based on deep learning model |
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 |