CN110596166A - Method for identifying type and content of oil-gas reservoir space - Google Patents
Method for identifying type and content of oil-gas reservoir space Download PDFInfo
- Publication number
- CN110596166A CN110596166A CN201910857195.4A CN201910857195A CN110596166A CN 110596166 A CN110596166 A CN 110596166A CN 201910857195 A CN201910857195 A CN 201910857195A CN 110596166 A CN110596166 A CN 110596166A
- Authority
- CN
- China
- Prior art keywords
- content
- type
- layer
- identifying
- neural network
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/286—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q involving mechanical work, e.g. chopping, disintegrating, compacting, homogenising
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/34—Purifying; Cleaning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
- G01N23/2202—Preparing specimens therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
- G01N23/225—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion
- G01N23/2251—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion using incident electron beams, e.g. scanning electron microscopy [SEM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/286—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q involving mechanical work, e.g. chopping, disintegrating, compacting, homogenising
- G01N2001/2866—Grinding or homogeneising
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
Abstract
A method for identifying the type and content of oil-gas storage space comprises the steps of preparing samples of rock cores in different types of rocks, observing the samples and acquiring images; manually identifying the sample, and identifying the type and the content of the pores; constructing a convolutional neural network structure; inputting an original rock image, and training the original rock image by using a convolutional neural network; carrying out convolution to extract rock characteristics, and acquiring a new characteristic diagram by utilizing nonlinear mapping; extracting the maximum value or the average value of the characteristic values, and reserving image characteristic information; extracting characteristic information and reducing the calculation amount; inputting the finally extracted feature vectors into a full-connection layer, and outputting the type and the content of the reservoir space through a softmax layer; and calculating the error between the actual output and the expected output, stopping training if the accuracy requirement is met, and otherwise, automatically identifying and calculating the content of the reservoir space type in the oil-gas reservoir to obtain an accurate and reliable artificial intelligence classification result.
Description
Technical Field
The invention relates to a technology for identifying the type and the content of a reservoir space in the field of geology, in particular to a method for identifying the type and the content of an oil-gas reservoir space.
Background
The conventional identification means of the type and the content of the reservoir space is to identify the type and calculate the content of the reservoir space on common rock slices and cast body slices through electron microscope scanning or manual observation. The traditional mode is not only extremely low in efficiency, but also too dependent on experimenters, so that the obtained conclusion is lack of objectivity. In order to solve the problem, Matlab software is applied to automatically characterize the compact sandstone reservoir pores in Jiubao et al (2018), so that the characterization efficiency and objectivity of the reservoir space content are effectively improved, but the pore type is not identified. The chiffon (2019) proposes that a JMicro Vision image analysis software is used for analyzing the scanning electron microscope image of the shale so as to determine parameters such as pore type, content and the like. However, according to the shape of different reservoir spaces, the method needs to manually perform a series of operations such as sketching and setting a scale, the process is complex, and the objectivity cannot be ensured due to excessive manual intervention.
Disclosure of Invention
In order to solve the defects of the prior art, the invention aims to provide a method for identifying the type and the content of the oil and gas storage space, which can automatically identify and calculate the content of the storage space in an oil and gas storage layer to obtain an accurate and reliable artificial intelligence classification result.
In order to achieve the technical purpose, the invention provides the following technical scheme:
a method for identifying the type and content of a hydrocarbon reservoir space comprises the following steps:
the method comprises the following steps: carrying out sample preparation on rock cores in different types of rocks, wherein the specifications of the samples are as follows: the thickness is 0.03 mm; acquiring a rock core sample image through a microscope or a scanning electron microscope, and manually distinguishing the type and the content of a storage space from the acquired rock core sample image;
step two: constructing a convolutional neural network structure, wherein the structural form of the convolutional neural network is as follows: the method comprises the following steps of (1) an input layer, a rolling layer, a pooling layer, a repeated rolling layer and a pooling layer, a full-connection layer, a softmax layer and an output layer;
step three: inputting the core sample image extracted in the step one, and directly training the core sample image by using the convolutional neural network obtained in the step two;
step four: performing convolution to extract characteristics of the rock core sample, and acquiring a new characteristic diagram by utilizing nonlinear mapping of an activation function;
step five: extracting the maximum value or the average value of the characteristic values, retaining the characteristic information of the image of the rock core sample, namely the shape, color and space relation of different reservoir space types, and further reducing the operation amount;
step six: and repeating the fourth step and the fifth step, and further extracting the following characteristic information: shape, color, spatial relationship, and reduce the amount of computation;
step seven: inputting the finally extracted feature vectors into a full-connection layer, and outputting the type and the content of the reservoir space through a softmax layer;
step eight: calculating the error between the type and the content of the storage space identified by the actual output convolutional neural network and the type and the content of the storage space identified by human, and stopping training if the accuracy requirement is met; otherwise, returning to the third step.
The preparation of the core sample in the first step comprises the following steps:
the first step is as follows: cutting the rock into small pieces of about 25mm in length by 25mm in width by 5mm in thickness with a manual rapid cutter;
the second step is that: grinding and polishing the bonding surface by using an automatic precise grinding and polishing machine;
the third step: removing residual grinding scraps, grinding materials and mineral scraps by using an ultrasonic cleaning machine;
the fourth step: bonding the polished surface on the glass slide by using resin adhesive;
the fifth step: putting the bonded sample into a vacuum drying oven to accelerate the resin adhesive to solidify;
and a sixth step: thinning the sample wafer to 0.5mm by using a manual rapid cutting machine;
the seventh step: grinding the sample to 0.03mm by using an automatic precision grinding and polishing machine on the premise of ensuring the parallelism of two surfaces of the sample, and performing polishing treatment;
eighth step: cover with an overlying glass slide.
The degree of repeating the convolution layer and the pooling layer in the step two is as follows: until no further image features can be extracted.
And step three, training the rock core sample image by using a convolutional neural network, wherein the specific method comprises the following steps: and identifying the type and the content of the reservoir space in the core sample image by using a convolutional neural network.
The activating function in the step four is a sigmoid function:tan h function:or relu function: f (x) max (0, x), x is an argument.
The invention has the beneficial effects that:
because the convolutional neural network is adopted to automatically identify the type and the content of the reservoir space in the oil and gas reservoir, the problems of non-objectivity and inaccuracy caused by manual identification at present can be effectively solved, and the identification method has the advantages of high efficiency, objectivity, accuracy and the like.
Drawings
FIG. 1 is a block diagram of a convolutional neural network of the present invention.
FIG. 2 is a flow chart of the method identification of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
A method for identifying the type and content of a hydrocarbon reservoir space comprises the following steps:
the method comprises the following steps: carrying out sample preparation on rock cores in different types of rocks, wherein the specifications of the samples are as follows: about 0.03mm in thickness; acquiring a rock core sample image through a microscope or a scanning electron microscope, and manually distinguishing the type and the content of a storage space from the acquired rock core sample image;
step two: constructing a convolutional neural network structure, wherein the structural form of the convolutional neural network is as follows: the method comprises the following steps of (1) an input layer, a rolling layer, a pooling layer, a repeated rolling layer and a pooling layer, a full-connection layer, a softmax layer and an output layer;
step three: inputting the core sample image extracted in the step one, and directly training the core sample image by using the convolutional neural network obtained in the step two;
step four: performing convolution to extract characteristics of the rock core sample, and acquiring a new characteristic diagram by utilizing nonlinear mapping of an activation function;
step five: extracting the maximum value or the average value of the characteristic values, and reserving the image characteristic information of the rock core sample: such as the shapes, colors, spatial relationships and the like of different reservoir space types, the operation amount is further reduced;
step six: and repeating the fourth step and the fifth step, and further extracting the following characteristic information: shape, color, spatial relationship, etc., and reduces the amount of computation;
step seven: inputting the finally extracted feature vectors into a full-connection layer, and outputting the type and the content of the reservoir space through a softmax layer;
step eight: calculating the error between the type and the content of the storage space identified by the actual output convolutional neural network and the type and the content of the storage space identified by human, and stopping training if the accuracy requirement is met; otherwise, returning to the third step.
The preparation of the core sample in the first step comprises the following steps:
the first step is as follows: cutting the rock into small pieces of 25mm in length, 25mm in width and 5mm in thickness by using a SYJ-200H manual rapid cutting machine;
the second step is that: grinding and polishing the bonding surface by using a UNIPOL-1202 automatic precise grinding and polishing machine until minerals such as quartz and the like in the rock sample reach a mirror surface effect, and no bubbles are generated when the sample is fixed on a glass slide;
the third step: removing residual grinding scraps, abrasive materials and mineral scraps by using a VGT-1620QTD ultrasonic cleaning machine;
the fourth step: bonding the polished surface on the glass slide by using resin adhesive;
the fifth step: putting the bonded sample into a DZF-series vacuum drying oven, and accelerating the resin adhesive solidification, wherein the temperature of the drying oven is 60 degrees, and the drying time is 30 minutes;
and a sixth step: thinning the sample wafer to 0.5mm by using an SYJ-200H manual rapid cutting machine;
the seventh step: grinding the sample to 0.03mm by using a POL-1202 automatic precise grinding and polishing machine on the premise of ensuring the parallelism of two surfaces of the sample, and performing polishing treatment until minerals such as quartz in the rock sample reach a mirror surface effect and no bubbles are generated when the sample is fixed on a glass slide;
eighth step: cover with an overlying glass slide.
The degree of repeating the convolution layer and the pooling layer in the step two is as follows: until no further image features can be extracted.
And step three, training the rock core sample image by using a convolutional neural network, wherein the specific method comprises the following steps: and identifying the type and the content of the reservoir space in the core sample image by using a convolutional neural network.
The activating function in the step four is a sigmoid function:tan h function:or relu function: f (x) max (0, x).
Example 1:
a method for identifying the type and content of a hydrocarbon reservoir space comprises the following steps:
the method comprises the following steps: cutting granite into small blocks of 25mm in length, 25mm in width and 5mm in thickness by using a SYJ-200H manual rapid cutting machine; grinding and polishing the bonding surface by using a UNIPOL-1202 automatic precise grinding and polishing machine until minerals such as quartz and the like in the rock sample reach a mirror surface effect, and no bubbles are generated when the sample is fixed on a glass slide; removing residual grinding scraps, abrasive materials and mineral scraps by using a VGT-1620QTD ultrasonic cleaning machine; bonding the polished surface on the glass slide by using resin adhesive; putting the bonded sample into a DZF-series vacuum drying oven, and accelerating the resin adhesive solidification, wherein the temperature of the drying oven is 60 degrees, and the drying time is 30 minutes; thinning the sample wafer to 0.5mm by using an SYJ-200H manual rapid cutting machine; grinding the sample to 0.03mm by using a POL-1202 automatic precise grinding and polishing machine on the premise of ensuring the parallelism of two surfaces of the sample, and performing polishing treatment until minerals such as quartz in the rock sample reach a mirror surface effect and no bubbles are generated when the sample is fixed on a glass slide; covering with an upper cover glass sheet;
step two: constructing a convolutional neural network structure, wherein the structural form of the convolutional neural network is as follows: the method comprises the steps of inputting a layer, namely a rolling layer, a pooling layer, repeating the rolling layer and the pooling layer until image characteristics cannot be further extracted, namely a full connection layer, a Softmax layer and an outputting layer;
step three: inputting the core sample image extracted in the step one, and directly identifying the type and the content of the storage space in the core sample image by using the convolutional neural network obtained in the step two;
step four: and (3) carrying out convolution to extract characteristics of the rock core sample, and taking an activation function as a sigmoid function:tan h function:or relu function: f, (x) max (0, x) to obtain a new feature map;
step five: extracting the maximum value or the average value of the characteristic values, retaining the characteristic information of the image of the rock core sample, namely the shape, color and space relation of different reservoir space types, and further reducing the operation amount;
step six: and repeating the fourth step and the fifth step, and further extracting the following characteristic information: shape, color, spatial relationship, and reduce the amount of computation;
step seven: inputting the finally extracted feature vectors into a full-connection layer, and outputting the type and the content of the reservoir space through a softmax layer;
step eight: calculating the error between the type and the content of the storage space identified by the actual output convolutional neural network and the type and the content of the storage space identified by human, and stopping training if the accuracy requirement is met; otherwise, returning to the third step.
Claims (5)
1. A method for identifying the type and content of a hydrocarbon storage space is characterized by comprising the following steps: the method comprises the following steps:
a method for identifying the type and content of a hydrocarbon reservoir space comprises the following steps:
the method comprises the following steps: carrying out sample preparation on rock cores in different types of rocks, wherein the specifications of the samples are as follows: the thickness is 0.03 mm; acquiring a rock core sample image through a microscope or a scanning electron microscope, and manually distinguishing the type and the content of a storage space from the acquired rock core sample image;
step two: constructing a convolutional neural network structure, wherein the structural form of the convolutional neural network is as follows: the method comprises the following steps of (1) an input layer, a rolling layer, a pooling layer, a repeated rolling layer and a pooling layer, a full-connection layer, a softmax layer and an output layer;
step three: inputting the core sample image extracted in the step one, and directly training the core sample image by using the convolutional neural network obtained in the step two;
step four: performing convolution to extract characteristics of the rock core sample, and acquiring a new characteristic diagram by utilizing nonlinear mapping of an activation function;
step five: extracting the maximum value or the average value of the characteristic values, retaining the characteristic information of the image of the rock core sample, namely the shape, color and space relation of different reservoir space types, and further reducing the operation amount;
step six: and repeating the fourth step and the fifth step, and further extracting the following characteristic information: shape, color, spatial relationship, and reduce the amount of computation;
step seven: inputting the finally extracted feature vectors into a full-connection layer, and outputting the type and the content of the reservoir space through a softmax layer;
step eight: calculating the error between the type and the content of the storage space identified by the actual output convolutional neural network and the type and the content of the storage space identified by human, and stopping training if the accuracy requirement is met; otherwise, returning to the third step.
2. The method of identifying hydrocarbon reservoir space type and content thereof as recited in claim 1 further comprising: the preparation of the core sample in the first step comprises the following steps:
the first step is as follows: cutting the rock into small pieces of about 25mm in length by 25mm in width by 5mm in thickness with a manual rapid cutter;
the second step is that: grinding and polishing the bonding surface by using an automatic precise grinding and polishing machine;
the third step: removing residual grinding scraps, grinding materials and mineral scraps by using an ultrasonic cleaning machine;
the fourth step: bonding the polished surface on the glass slide by using resin adhesive;
the fifth step: putting the bonded sample into a vacuum drying oven to accelerate the resin adhesive to solidify;
and a sixth step: thinning the sample wafer to 0.5mm by using a manual rapid cutting machine;
the seventh step: grinding the sample to 0.03mm by using an automatic precision grinding and polishing machine on the premise of ensuring the parallelism of two surfaces of the sample, and performing polishing treatment;
eighth step: cover with an overlying glass slide.
3. The method of identifying hydrocarbon reservoir space type and content thereof as recited in claim 1 further comprising: the degree of repeating the convolution layer and the pooling layer in the step two is as follows: until no further image features can be extracted.
4. The method of identifying hydrocarbon reservoir space type and content thereof as recited in claim 1 further comprising: and step three, training the rock core sample image by using a convolutional neural network, wherein the specific method comprises the following steps: and identifying the type and the content of the reservoir space in the core sample image by using a convolutional neural network.
5. The method of identifying hydrocarbon reservoir space type and content thereof as recited in claim 1 further comprising: the activating function in the step four is a sigmoid function: tan h function:or relu function: f (x) max (0, x), x is an argument.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910857195.4A CN110596166A (en) | 2019-09-11 | 2019-09-11 | Method for identifying type and content of oil-gas reservoir space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910857195.4A CN110596166A (en) | 2019-09-11 | 2019-09-11 | Method for identifying type and content of oil-gas reservoir space |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110596166A true CN110596166A (en) | 2019-12-20 |
Family
ID=68858754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910857195.4A Pending CN110596166A (en) | 2019-09-11 | 2019-09-11 | Method for identifying type and content of oil-gas reservoir space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110596166A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5828981A (en) * | 1995-05-11 | 1998-10-27 | Texaco Inc. | Generating pore types and synthetic capillary pressure curves from wireline logs using neural networks |
| US20080015782A1 (en) * | 2004-05-27 | 2008-01-17 | Saltzer Rebecca L | Method For Predicting Lithology And Porosity From Seismic Reflection Data |
| US20080192987A1 (en) * | 2004-09-07 | 2008-08-14 | Petro-Model Ehf | Apparatus and Method For Analysis of Size, Form and Angularity and For Compositional Analysis of Mineral and Rock Particles |
| CN104568545A (en) * | 2015-01-20 | 2015-04-29 | 中国石油大学(华东) | Manufacturing method of shale rock lamina |
| CN105092334A (en) * | 2015-08-25 | 2015-11-25 | 成都理工大学 | Resin casting system for effective storage spaces of oil and gas reservoir cores and implementation method of resin casting system |
| CN107145903A (en) * | 2017-04-28 | 2017-09-08 | 武汉理工大学 | A kind of Ship Types recognition methods extracted based on convolutional neural networks picture feature |
| CN108444881A (en) * | 2016-11-03 | 2018-08-24 | 中国石油化工股份有限公司 | A kind of characterizing method suitable for terrestrial facies mud shale micro-nano-scale reservoir space |
| CN109117897A (en) * | 2018-08-09 | 2019-01-01 | 百度在线网络技术（北京）有限公司 | Image processing method, device and readable storage medium storing program for executing based on convolutional neural networks |
| CN109389128A (en) * | 2018-08-24 | 2019-02-26 | 中国石油天然气股份有限公司 | Electric imaging logging image characteristic automatic extraction method and device |
| CN109615010A (en) * | 2018-12-13 | 2019-04-12 | 济南大学 | Chinese traditional medicinal materials recognition method and system based on double scale convolutional neural networks |
| CN109856029A (en) * | 2019-02-01 | 2019-06-07 | 中海石油(中国)有限公司上海分公司 | A kind of porosity evaluation method based on image analysis |
| CN110070552A (en) * | 2019-05-07 | 2019-07-30 | 西南石油大学 | A kind of rock image porosity type recognition methods based on semantic segmentation |
| CN110110661A (en) * | 2019-05-07 | 2019-08-09 | 西南石油大学 | A kind of rock image porosity type recognition methods based on unet segmentation |
| CN110346831A (en) * | 2019-07-19 | 2019-10-18 | 同济大学 | A kind of intelligent earthquake Fluid Identification Method based on random forests algorithm |
| CN111894563A (en) * | 2019-05-05 | 2020-11-06 | 中国石油天然气股份有限公司 | Method and system for determining classification of fractured reservoir in buried hill section |
-
2019
- 2019-09-11 CN CN201910857195.4A patent/CN110596166A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5828981A (en) * | 1995-05-11 | 1998-10-27 | Texaco Inc. | Generating pore types and synthetic capillary pressure curves from wireline logs using neural networks |
| US20080015782A1 (en) * | 2004-05-27 | 2008-01-17 | Saltzer Rebecca L | Method For Predicting Lithology And Porosity From Seismic Reflection Data |
| US20080192987A1 (en) * | 2004-09-07 | 2008-08-14 | Petro-Model Ehf | Apparatus and Method For Analysis of Size, Form and Angularity and For Compositional Analysis of Mineral and Rock Particles |
| CN104568545A (en) * | 2015-01-20 | 2015-04-29 | 中国石油大学(华东) | Manufacturing method of shale rock lamina |
| CN105092334A (en) * | 2015-08-25 | 2015-11-25 | 成都理工大学 | Resin casting system for effective storage spaces of oil and gas reservoir cores and implementation method of resin casting system |
| CN108444881A (en) * | 2016-11-03 | 2018-08-24 | 中国石油化工股份有限公司 | A kind of characterizing method suitable for terrestrial facies mud shale micro-nano-scale reservoir space |
| CN107145903A (en) * | 2017-04-28 | 2017-09-08 | 武汉理工大学 | A kind of Ship Types recognition methods extracted based on convolutional neural networks picture feature |
| CN109117897A (en) * | 2018-08-09 | 2019-01-01 | 百度在线网络技术（北京）有限公司 | Image processing method, device and readable storage medium storing program for executing based on convolutional neural networks |
| CN109389128A (en) * | 2018-08-24 | 2019-02-26 | 中国石油天然气股份有限公司 | Electric imaging logging image characteristic automatic extraction method and device |
| CN109615010A (en) * | 2018-12-13 | 2019-04-12 | 济南大学 | Chinese traditional medicinal materials recognition method and system based on double scale convolutional neural networks |
| CN109856029A (en) * | 2019-02-01 | 2019-06-07 | 中海石油(中国)有限公司上海分公司 | A kind of porosity evaluation method based on image analysis |
| CN111894563A (en) * | 2019-05-05 | 2020-11-06 | 中国石油天然气股份有限公司 | Method and system for determining classification of fractured reservoir in buried hill section |
| CN110070552A (en) * | 2019-05-07 | 2019-07-30 | 西南石油大学 | A kind of rock image porosity type recognition methods based on semantic segmentation |
| CN110110661A (en) * | 2019-05-07 | 2019-08-09 | 西南石油大学 | A kind of rock image porosity type recognition methods based on unet segmentation |
| CN110346831A (en) * | 2019-07-19 | 2019-10-18 | 同济大学 | A kind of intelligent earthquake Fluid Identification Method based on random forests algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 徐洁磐: "《人工智能导论》", 31 July 2019, 中国铁道出版社有限公司 * |
| 赵琦琳: "《人工神经网络在环境科学与工程中的设计应用》", 31 March 2019, 中国环境出版集团 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10540760B2 (en) | Method of separating, identifying and characterizing cracks in 3D space | |
| CN110473173A (en) | A kind of defect inspection method based on deep learning semantic segmentation | |
| CN113609696B (en) | Multi-scale multi-component digital core construction method and system based on image fusion | |
| CN112150430B (en) | Numerical analysis method for digital image by using rock microstructure | |
| CN110097974A (en) | A kind of nasopharyngeal carcinoma far-end transfer forecasting system based on deep learning algorithm | |
| CN113658117B (en) | Method for identifying and dividing aggregate boundary in asphalt mixture based on deep learning | |
| CN103810522B (en) | Counting method and device for corn ear grains | |
| CN108509947A (en) | A kind of automatic identification polishing process based on artificial neural network | |
| CN112730326A (en) | Intelligent identification device and method for rock slices | |
| CN108061697B (en) | Method for calculating three-dimensional porosity of soil body | |
| CN106871901A (en) | A kind of underwater terrain matching air navigation aid based on terrain feature matching | |
| CN116373304A (en) | In-situ repair path planning method for composite damaged member | |
| CN103983492B (en) | A kind of jade Non-Destructive Testing instance model and preparation method thereof | |
| CN110596166A (en) | Method for identifying type and content of oil-gas reservoir space | |
| CN105160685A (en) | Computer digital image recognition method of rock pore and particle system | |
| CN115170479A (en) | Automatic extraction method for asphalt pavement repairing diseases | |
| Mehra et al. | A novel technique for producing three-dimensional data using serial sectioning and semi-automatic image classification | |
| CN112784806A (en) | Lithium-containing pegmatite vein extraction method based on full convolution neural network | |
| CN116595834A (en) | Sapphire crack prediction method based on SPH simulation and image processing | |
| CN114972186A (en) | Block filling foundation bearing capacity estimation method and system based on image recognition | |
| CN113724223B (en) | YOLOv3 data set production method and system based on optical microscope | |
| Dabek et al. | Grain segmentation in sandstone thin-section based on computer analysis of microscopic images | |
| CN107167400B (en) | Method for detecting crude oil density in petroleum inclusion | |
| CN113270156B (en) | Detection modeling and detection method and system of machine-made sandstone powder based on image processing | |
| CN110044900B (en) | Characterization method of two-phase composite material tissue structure |
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 |