CN111048163B - Shale oil hydrocarbon retention amount (S1) evaluation method based on high-order neural network - Google Patents
Shale oil hydrocarbon retention amount (S1) evaluation method based on high-order neural network Download PDFInfo
- Publication number
- CN111048163B CN111048163B CN201911312377.XA CN201911312377A CN111048163B CN 111048163 B CN111048163 B CN 111048163B CN 201911312377 A CN201911312377 A CN 201911312377A CN 111048163 B CN111048163 B CN 111048163B
- Authority
- CN
- China
- Prior art keywords
- shale oil
- neural network
- hydrocarbon
- sample
- logging curve
- 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
- 150000002430 hydrocarbons Chemical class 0.000 title claims abstract description 68
- 229930195733 hydrocarbon Natural products 0.000 title claims abstract description 67
- 239000004215 Carbon black (E152) Substances 0.000 title claims abstract description 59
- 239000003079 shale oil Substances 0.000 title claims abstract description 43
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 31
- 230000014759 maintenance of location Effects 0.000 title claims abstract description 28
- 238000011156 evaluation Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000005251 gamma ray Effects 0.000 claims abstract description 14
- 238000000197 pyrolysis Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 14
- 230000000717 retained effect Effects 0.000 claims description 9
- 230000005284 excitation Effects 0.000 claims description 4
- 230000007423 decrease Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract description 2
- 239000011435 rock Substances 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000011084 recovery Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002301 combined effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011005 laboratory method Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002522 swelling effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Production Of Liquid Hydrocarbon Mixture For Refining Petroleum (AREA)
Abstract
The invention discloses a shale oil hydrocarbon retention (S1) evaluation method based on a high-order neural network, which is characterized in that the core is to utilize shale pyrolysis data and perform light and heavy hydrocarbon compensation on S1 from the hydrocarbon generation dynamics perspective, so as to provide objective parameters for accurate evaluation of shale oil resource potential. At S 1 (original) And a correlation relation is established between the shale oil hydrocarbon retention amount evaluation method and a logging curve to determine a proper logging curve input, the logging curve with strong correlation, such as Density (DEN), resistivity (RT), gamma Ray (GR), neutron (CNL) and acoustic wave time difference (AC), is selected, and on the basis of improving the calculation speed, a high-order neural network method is adopted to carry out deep learning specially aiming at the weights of the logging curves, so that the accuracy and the timeliness of shale oil hydrocarbon retention amount (S1) evaluation are effectively improved, and the defects in the prior art are overcome.
Description
Technical Field
The invention relates to an evaluation method of hydrocarbon retention amount (S1) of shale oil in the field of shale oil development, and particularly relates to a shale oil hydrocarbon retention amount (S1) calculation method based on an artificial neural network, which can effectively improve the accuracy of evaluation of the hydrocarbon retention amount (S1) in the evaluation stage of a shale oil reservoir.
Background
The success of shale gas exploration and development shows that shale can be a perfect combination of source, storage and cover integration. At present, most of shale oil with industrial yield value is extracted from fractured shale, and the shale oil with large-scale yield is rarely extracted from pure mud and shale. According to the calculation result of the generation-discharge theory model, the hydrocarbon source rock is 20-50% of the total amount of the generated oil reserved by the great date, and the resource potential of the shale oil is very huge. Along with the large-scale exploration and development of compact oil, the shale oil exploration and development also shows better seedling heads, such as condensate oil of South Texas basin eagleFord shale series, williston basin Bakken shale series and the like. It is estimated that the amount of recoverable resources of shale oil in the world is about 2080X 10 8 t, shale oil related research work is also emerging. In China, a plurality of shale reservoirs are foundLayer, such as Sichuan, bohai Bay, songliao, jianghan, tarim basin. The amount of retained hydrocarbons (S1) is a basic index for evaluating the source rock, which reflects the potential of shale resources, and therefore, accurate and continuous prediction is urgently needed. However, direct laboratory methods are time consuming and expensive. In recent years, the relationship between geochemical parameters of source rock and well log information has been studied.
In the process of evaluating the potential of shale oil resources, a pyrolysis parameter S1 is often used for reflecting the oil content of the shale. S1 is defined as the retained hydrocarbon content in Rock, analyzed by Rock pyrolysis apparatus (Rock-Eval), and is the hydrocarbon volatilized when a Rock sample is heated to a temperature not exceeding 300 ℃. Meanwhile, S can also be obtained from the rock through pyrolysis analysis 2 Called cracked hydrocarbon, is a hydrocarbon product cracked by organic matters in the heating process after 300 ℃. But is influenced by the storage condition of the rock core, the experimental test analysis technology and the adsorption and swelling effects of kerogen, and retains hydrocarbon S 1 There is a loss of light and heavy hydrocarbons resulting in a measured value that is much lower than the actual value underground. Li progressive et al (2014) provide a set of pyrolysis parameters S from the perspective of extraction pyrolysis experiments and component hydrocarbon generation kinetics by analyzing a large amount of pyrolysis data of shale oil 1 The scheme for recovering light and heavy hydrocarbons provides objective parameters for potential evaluation of shale oil resources.
In the shale oil resource evaluation process, a logging curve has been widely used to evaluate the content of organic matters, and logging information related to the organic matters comprises Density (DEN), resistivity (RT), gamma Ray (GR), neutron (CNL), sound wave time difference (AC), and the like. Previous studies have shown that better prediction accuracy can only be obtained when DEN, AC, etc. are closely related to TOC. Each log response is the result of the combined effect of multiple geological factors, and the retained hydrocarbon (S) is evaluated by using a single log 1 ) The method of content is necessarily influenced by various factors. Therefore, we have attempted to predict the amount of retained hydrocarbons using multi-well logs. In practical application, S is 1 A complex nonlinear relation exists between the data and a logging curve, so that a neural network calculates S 1 More reliable and advanced. It has therefore been applied in many fields of oil engineering, in particular unconventionalAnd (5) evaluating resources. Wang et al (2019) propose CNN-based S 1 Prediction is carried out, but light and heavy hydrocarbon compensation is not carried out in a specific prediction process, so that inaccurate prediction can be caused.
The higher-order neural network is an extension of the multi-layer perceptron neural network. It adds auxiliary elements on the basic model of the sensor to change the input vector into N values combined with each other (taking second order as example, input parameter x in multi-layer sensor neural network) 1 、x 2 In higher order neural networks, it becomes
x 1 x 2 、x 1 、x 2 ). The network output corresponds to the input high-order correlation function, the calculation complexity is reduced, and even if the data size is large, the convergence speed is obviously superior. And the high-order neural network does not contain a hidden layer, so that a higher training speed can be obtained, local minimum values are not easy to appear, and the problems of the number of the hidden layers and the number of nodes are solved.
Accurate retained hydrocarbon content (S) can be obtained by using core analysis data 1 ) Information, but coring data is limited, continuous retained hydrocarbon content information is not available, and core analysis is costly and time consuming, while high longitudinal resolution log data can provide continuous distribution along the well profile. For a common multilayer perceptron neural network (one of the neural networks is the simplest and most common neural network), the number of layers and the number of nodes of the hidden layer are set according to experience, so that the convergence speed is slow when the data size is large, and the problem that the data size is easy to fall into a local minimum value exists. In order to reasonably solve the problem, the invention provides a shale oil hydrocarbon retention amount (S) based on a high-order neural network 1 ) Expected to further increase the hydrocarbon retention amount (S) to shale oil 1 ) The accuracy and the timeliness of the evaluation.
Disclosure of Invention
The invention aims to provide a shale oil hydrocarbon retention amount (S1) evaluation method based on a high-order neural network, which is based on a nonlinear mode recognition technology of an artificial neural network, utilizes five logging curves of Density (DEN), resistivity (RT), gamma Rays (GR), neutrons (CNL) and acoustic wave time difference (AC), and specially carries out deep learning on the logging curve weight influencing the shale oil hydrocarbon retention amount, thereby effectively improving the accuracy of comprehensive evaluation of the hydrocarbon retention amount (S1) in a shale oil reservoir evaluation stage and overcoming the defects in the prior art.
In order to achieve the above technical objects, the present invention provides the following technical solutions.
A shale oil hydrocarbon retention (S1) evaluation method based on a high-order neural network is characterized in that a proper logging curve is input, and logging curves with strong correlation, such as Density (DEN), resistivity (RT), gamma Rays (GR), neutrons (CNL) and sound wave time difference (AC), are selected to improve the calculation speed.
The core of the method is to utilize shale pyrolysis data and to generate hydrocarbon kinetics for S 1 And (4) performing light and heavy hydrocarbon compensation, providing objective parameters for accurate evaluation of the potential of shale oil resources, and determining appropriate logging curve input and solving of the weights of all logging curves. The method sequentially comprises the following steps:
(1) And (3) performing light and heavy hydrocarbon compensation on the S1 by utilizing the shale pyrolysis data from the hydrocarbon generation dynamics perspective, and providing objective parameters for accurately evaluating the potential of shale oil resources.
(2) In the original amount of retained hydrocarbons, denoted S 1 (original) A correlation relation is established between the data acquisition system and the logging curves to determine the appropriate logging curve input, and the logging curves with strong correlation, such as Density (DEN), resistivity (RT), gamma Ray (GR), neutron (CNL) and acoustic wave time difference (AC), are selected to improve the calculation speed;
(3) Normalizing the data to determine a training sample;
(4) Setting the order of a neural network, converting an input sample, and inputting;
(5) Randomly setting an initial connection right;
(6) Calculating actual output;
(7) Updating the connection weight according to the error between the expected output and the actual output, and continuously performing network training;
(8) And when all the samples are trained and the network precision requirement is met, determining the weight of each logging curve. And obtaining shale oil retention hydrocarbon evaluation models of all samples.
Drawings
FIG. 1 is a schematic diagram of a higher-order neural network model of a higher-order neural network-based shale oil hydrocarbon retention (S1) evaluation method provided by the invention;
FIG. 2 is a schematic flow chart of a method for evaluating the hydrocarbon retention amount (S1) of shale oil based on a higher-order neural network provided by the invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the present invention is calculated step by step according to the flowchart shown in fig. 2, and is described and illustrated below by taking a specific example as an example. The content is to explain the invention and not to limit the scope of protection of the invention.
The evaluation method of the hydrocarbon retention amount of the shale oil based on the high-order neural network in the evaluation stage of the shale oil reservoir sequentially comprises the following detailed steps:
the method comprises the following steps: and (3) performing light and heavy hydrocarbon compensation (formula 1) on the S1 by utilizing the shale pyrolysis data and from the hydrocarbon generation dynamics perspective, and providing objective parameters for accurately evaluating the potential of shale oil resources.
S 1 original ＝S 1 (measured value) +S 1 (heavy hydrocarbon recovery) +S 1 (light hydrocarbon recovery)
＝S 1 (measured value) +K Heavy hydrocarbons ×S 1 (measured value) +(S 1 (measured value) +K Heavy hydrocarbon ×S 1 (measured value) )×K Light hydrocarbon
(1)
Wherein:
in the formula: s 1 (original) The original hydrocarbon retention in the underground is taken as the amount; s. the 1 (measured value) For conventional pyrolysis of S 1 ；S 1 (heavy hydrocarbon recovery) The weight and light compensation amount is obtained; s 1 (light hydrocarbon recovery) The compensation amount is light; k Heavy hydrocarbon A heavy hydrocarbon compensation coefficient; k Light hydrocarbon The light hydrocarbon compensation coefficient; s. the 2 Values were measured for conventional pyrolysis experiments; s' is obtained by carrying out pyrolysis experiment on the extracted rock sample 2 。
Step two: at S 1 (original) A correlation relationship is established with the logging curves to determine a proper logging curve input, the logging curves with strong correlation, such as Density (DEN), resistivity (RT), gamma Ray (GR), neutron (CNL) and acoustic time difference (AC), are selected, and the calculation speed is improved
Step three: for each calculated S 1 (original) And reading corresponding DEN, RT, GR, CNL and AC data for statistics and normalization processing to obtain a plurality of input samples. From the first sample X 1 (equation 4) the operation was started.
X 1 ＝(x 1 ,x 2 ,x 3 ,x 4 ,x 5 ) (4)
Wherein x is 1 ＝DEN，x 2 ＝RT，x 3 ＝GR，x 4 ＝CNL，x 5 ＝AC。
Step four: setting the conversion order of the high-order neural network to be 2, namely changing the input sample into X 1 * (formula 5).
The square terms of the 5 input parameters have 5 terms, the quadratic terms of the pairwise product of the 5 input parameters have 10 terms, the primary terms of the 5 input parameters are 5 terms, the last term constant 1 is added, and the total term number is 21, namely, the 5 input parameters are converted into 21 parameters containing high-order independent variables.
Step five: let the first sample X 1 * The corresponding desired output is O 1 Setting X 1 * And O 1 The initial weight vector in between is W 1 ，W 1 The middle element can be randomly set to any value between 0 and 1 (equation 6) (fig. 1).
W 1 ＝(w 1 ,w 2 ,···,w 21 ) T (6)
Wherein, w 1 ,w 2 ,···,w 21 The weight coefficient of each item in step four.
Step six: calculating the actual output Z of the first output node 1 (formula 7).
Z 1 ＝f(W 1 T X 1 * ) (7)
Where f is an excitation function representing the functional relationship between the input samples and the output. Common stimulus functions include: sigmoid function, tanh function, reLU function, etc. The Sigmoid function is chosen here as the excitation function.
Step seven: output O according to expectation 1 And the actual output Z 1 Error of (3), updating the connection weight vector W 1 Is W 2 (formula 8), W 2 I.e. the initial weight vector for the second sample.
W 2 ＝W 1 +η(O 1 -Z 1 )X * (8)
Where η is the weight coefficient update step. η decreases gradually as the number of iterations increases. Typically with random initial valuesSet to a small positive value, where the initial value of the step size is set to η 1 ，η 1 The value is 0.1, which is set to multiply by 0.1 for 100 rounds per iteration. I.e. after all samples repeat the feedback training for 100 rounds, the step length becomes eta 2 ，η 2 ＝0.1η 1 And =0.1 × 0.1=0.01, and so on.
Step eight: and assuming that the total number of the samples is n, and circulating the step six and the step seven to sequentially obtain an initial weight vector of each sample.
Step eight: the average error E (equation 9) is calculated for all samples.
Wherein, O j And Z j The expected output and the actual output of the jth sample, respectively.
Step nine: when the average error E is less than or equal to epsilon (set
) The weights of the logs can then be determined. And obtaining an evaluation model of the hydrocarbon retention amount of the shale oil of all samples. Otherwise, returning to the step six.
The flow chart corresponding to the above steps is shown in fig. 2 below.
The foregoing shows and describes the general principles, principal features and advantages of the invention. Those skilled in the art will appreciate that the above-described embodiments are not intended to limit the invention in any way. All the technical solutions obtained by means of equivalent substitution or equivalent transformation fall within the protection scope of the present invention.
Claims (7)
1. A shale oil hydrocarbon retention amount (S1) evaluation method based on a higher-order neural network sequentially comprises the following steps:
the method comprises the following steps: performing light and heavy hydrocarbon compensation on the S1 by utilizing shale pyrolysis data from the hydrocarbon generation dynamics perspective, and providing objective parameters for accurate evaluation of shale oil resource potential;
step two: in the original amount of retained hydrocarbons, the amount of retained hydrocarbons is recordedIs S 1 (original) A correlation relation is established between the data and the logging curves, and the logging curves with strong correlation are selected, so that the calculation speed is improved; the logging curves with strong correlation are a density logging curve (DEN), a resistivity logging curve (RT), a gamma ray logging curve (GR), a neutron logging Curve (CNL) and a sound wave time difference logging curve (AC);
step three: for each calculated S 1 (original) Reading corresponding density logging curve, resistivity logging curve, gamma ray logging curve, neutron logging curve and sound wave time difference logging curve data for statistics and normalization processing to obtain a plurality of input samples; starting the run from the first sample;
step four: setting the order of the high-order neural network, and converting the order of the input sample in the step three;
step five: setting an initial weight vector of the converted first sample;
step six: outputting the converted first sample;
step seven: updating the connection weight vector of the first sample according to the error between the expected output and the actual output of the first sample, and setting the updated connection weight vector as the initial weight vector of the second sample;
step eight: circulating the sixth step and the seventh step to obtain the initial weight vector of each sample in turn;
step nine: and (5) calculating the average error of all samples, determining the weight of each logging curve when the average error meets the accurate reading requirement, calculating the hydrocarbon retention prediction models of all samples, and otherwise, returning to the sixth step.
2. The method for evaluating the hydrocarbon retention amount (S1) of shale oil based on the higher-order neural network according to claim 1, wherein the actual output method for calculating the first output node in the sixth step is as follows:
Z 1 ＝f(W 1 T X 1 * ) (7)
wherein Z is 1 Is the actual output; f is the function of the excitation and,representing a functional relationship between the input samples and the output; x 1 * For the first sample, its corresponding expected output is O 1 Set W 1 Is X 1 * And O 1 Initial weight vector of W 1 The medium element can be randomly set to any value between 0 and 1, W 1 T Is W 1 The transposed matrix of (2).
3. The higher-order neural network-based shale oil hydrocarbon retention amount (S1) evaluation method according to claim 2, wherein the excitation function is a Sigmoid function.
4. The method for evaluating the hydrocarbon retention amount (S1) of shale oil based on the higher-order neural network according to claim 1, wherein the method for updating the connection weight vector of the first sample in the seventh step is as follows:
W 2 ＝W 1 +η(O 1 -Z 1 )X * (8)
in the formula, W 1 To connect weight vectors, W 2 For updated connection weight vectors, O 1 To the desired output, Z 1 Eta is the updating step length of the weight coefficient for actual output; η decreases gradually as the number of iterations increases.
5. The method for evaluating the hydrocarbon retention amount (S1) of shale oil based on the higher-order neural network according to claim 4, wherein the method for setting the weight coefficient updating step size is as follows: the initial value is randomly set to a small positive value, where the initial value of the step size is set to η 1 ，η 1 The value is 0.1, 100 rounds of multiplication of the value per iteration is set to be 0.1, namely the step length becomes eta after all samples are repeatedly fed back and trained for 100 rounds 2 ，η 2 ＝0.1η 1 And =0.1 × 0.1=0.01, and so on.
6. The method for evaluating the hydrocarbon retention amount (S1) of the shale oil based on the higher-order neural network according to claim 1, wherein the method for calculating the average error of all samples in the ninth step is as follows:
wherein E is the average error of all samples; o is j And Z j The expected output and the actual output of the jth sample, respectively.
7. The method for evaluating the hydrocarbon retention amount (S1) of shale oil based on the high-order neural network as claimed in claim 1, wherein the accuracy requirement of the average error in the ninth step is 3 per thousand.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911312377.XA CN111048163B (en) | 2019-12-18 | 2019-12-18 | Shale oil hydrocarbon retention amount (S1) evaluation method based on high-order neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911312377.XA CN111048163B (en) | 2019-12-18 | 2019-12-18 | Shale oil hydrocarbon retention amount (S1) evaluation method based on high-order neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111048163A CN111048163A (en) | 2020-04-21 |
| CN111048163B true CN111048163B (en) | 2023-03-31 |
Family
ID=70237739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911312377.XA Active CN111048163B (en) | 2019-12-18 | 2019-12-18 | Shale oil hydrocarbon retention amount (S1) evaluation method based on high-order neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111048163B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111749677A (en) * | 2020-06-30 | 2020-10-09 | 宋立才 | Logging information processing method and device, electronic equipment and storage medium |
| CN111984928B (en) * | 2020-08-18 | 2024-02-20 | 中国石油化工股份有限公司 | Method for calculating organic carbon content of shale oil reservoir by logging data |
| CN112903737A (en) * | 2021-01-21 | 2021-06-04 | 西南石油大学 | Method for evaluating oil content of shale by utilizing pyrolysis before and after extraction |
| CN114429075B (en) * | 2021-09-13 | 2022-08-26 | 中国石油化工股份有限公司 | Shale specific surface area parameter modeling method based on BP neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278866A (en) * | 2013-06-07 | 2013-09-04 | 中国石油大学(华东) | Evaluation method of shale oil resource potential in shale strata series |
| CN103543470A (en) * | 2013-10-18 | 2014-01-29 | 中国石油大学(华东) | Correction method of light and heavy hydrocarbon of free hydrocarbon/residual hydrocarbon S1 in pyrolysis rock |
| WO2017024530A1 (en) * | 2015-08-11 | 2017-02-16 | 深圳朝伟达科技有限公司 | Method for calculating content of organic carbon in hydrocarbon source rock |
| CN109507733A (en) * | 2018-12-11 | 2019-03-22 | 中国石油天然气股份有限公司大港油田分公司 | A kind of method and device for predicting organic matter abundance in hydrocarbon source rock |
-
2019
- 2019-12-18 CN CN201911312377.XA patent/CN111048163B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278866A (en) * | 2013-06-07 | 2013-09-04 | 中国石油大学(华东) | Evaluation method of shale oil resource potential in shale strata series |
| CN103543470A (en) * | 2013-10-18 | 2014-01-29 | 中国石油大学(华东) | Correction method of light and heavy hydrocarbon of free hydrocarbon/residual hydrocarbon S1 in pyrolysis rock |
| WO2017024530A1 (en) * | 2015-08-11 | 2017-02-16 | 深圳朝伟达科技有限公司 | Method for calculating content of organic carbon in hydrocarbon source rock |
| CN109507733A (en) * | 2018-12-11 | 2019-03-22 | 中国石油天然气股份有限公司大港油田分公司 | A kind of method and device for predicting organic matter abundance in hydrocarbon source rock |
Non-Patent Citations (2)
| Title |
|---|
| 烃源岩测井定量评价方法探讨;杨涛涛等;《地球物理学进展》;20180215(第01期);全文 * |
| 页岩滞留液态烃的定量评价;朱日房等;《石油学报》;20150115(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111048163A (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111048163B (en) | Shale oil hydrocarbon retention amount (S1) evaluation method based on high-order neural network | |
| CN113052371B (en) | Residual oil distribution prediction method and device based on deep convolutional neural network | |
| CN112989708B (en) | Well logging lithology identification method and system based on LSTM neural network | |
| CN111027882A (en) | Method for evaluating brittleness index by utilizing conventional logging data based on high-order neural network | |
| CN111058840A (en) | Organic carbon content (TOC) evaluation method based on high-order neural network | |
| CN110807544A (en) | Oil field residual oil saturation distribution prediction method based on machine learning | |
| CN117236390A (en) | Reservoir prediction method based on cross attention diffusion model | |
| CN112633328A (en) | Dense oil reservoir transformation effect evaluation method based on deep learning | |
| CN115267935B (en) | Logging reservoir evaluation method and device driven by combination of data and physical model | |
| CN112948932A (en) | Surrounding rock grade prediction method based on TSP forecast data and XGboost algorithm | |
| CN114723095A (en) | Missing well logging curve prediction method and device | |
| Cornelio et al. | Physics-assisted transfer learning for production prediction in unconventional reservoirs | |
| Hou et al. | Data-driven optimization of brittleness index for hydraulic fracturing | |
| Lu et al. | Quality-relevant feature extraction method based on teacher-student uncertainty autoencoder and its application to soft sensors | |
| CN116911216B (en) | Reservoir oil well productivity factor assessment and prediction method | |
| Razak et al. | Embedding physical flow functions into deep learning predictive models for improved production forecasting | |
| CN117473305A (en) | Method and system for predicting reservoir parameters enhanced by neighbor information | |
| CN117236191A (en) | Method for predicting physical property parameters of reservoir based on deep learning technology | |
| Hou et al. | Identification of carbonate sedimentary facies from well logs with machine learning | |
| Gao et al. | Reduced-Degrees-of-Freedom Gaussian-Mixture-Model Fitting for Large-Scale History-Matching Problems | |
| Al-Bazzaz et al. | Permeability modeling using neural-network approach for complex Mauddud-Burgan carbonate reservoir | |
| Silva et al. | Generative network-based reduced-order model for prediction, data assimilation and uncertainty quantification | |
| Gheorghe | Non parametric Bayesian belief nets (NPBBNs) versus ensemble Kalman filter (EnKF) in reservoir simulation | |
| CN105893674A (en) | Method for performing geological attribute prediction with global covariance | |
| Tripathi et al. | Deep Learning–Based Production Forecasting and Data Assimilation in Unconventional Reservoir |
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 |