CN108596251A - One kind carrying out fluid identification of reservoir method based on committee machine using log data - Google Patents
One kind carrying out fluid identification of reservoir method based on committee machine using log data Download PDFInfo
- Publication number
- CN108596251A CN108596251A CN201810377375.8A CN201810377375A CN108596251A CN 108596251 A CN108596251 A CN 108596251A CN 201810377375 A CN201810377375 A CN 201810377375A CN 108596251 A CN108596251 A CN 108596251A
- Authority
- CN
- China
- Prior art keywords
- reservoir
- committee
- data
- log data
- log
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses one kind and carrying out fluid identification of reservoir method using log data based on committee machine, the described method comprises the following steps：1) select log data as input data；2) input data is normalized；3) fluid type of reservoir through is obtained according to formation testing result；4) log data and fluid type are constituted into data set；5) data set is randomly assigned to training dataset and test data set；6) pre-sorting device is selected；7) each pre-sorting device is trained, obtains corresponding disaggregated model；8) using test data set as input, a classification is provided by each disaggregated model respectively；9) it is directed to each group of input data, the category combinations that each disaggregated model is provided provide final class categories using Committee Decision mechanism.The decision-making mechanism of the method Mock-Up Board joins together multiple pre-sorting devices, can reduce and be absorbed in Local Minimum, keeps the decision of the committee more scientific, more acurrate.
Description
Technical field
The invention belongs to fluid identification of reservoir technical fields in oil exploration, and in particular to one kind is based on committee machine profit
Fluid identification of reservoir method is carried out with log data.
Background technology
Geophysical log is the continuous and in situ earth physical parameters measurement technology along wellbore, and measurement data includes mainly
Reservoir division may be implemented using these data in natural gamma, natural potential, deep and shallow resistivity, sound wave, density, neutron etc., stream
Body identification, porosity, permeability and saturation computation.The logging response character for studying the reservoir containing different fluid, can carry out reservoir
Fluid identification.It was verified that its logging response character of some reservoirs is apparent, it is easy to realize fluid identification, but for low hole
Low permeability reservoir, low-resistivity reservoir and complex lithology formation, the fluid in hole is small to the contribution of log response, different fluid property
It is nonlinear relationship between reservoir and a variety of log responses, it is larger using the qualitative progress fluid identification difficulty of log response.Cause
This, for the not high situation of tight sand low porosity permeability, RESERVOIR RECOGNITION accuracy rate, both at home and abroad correlation scholar be utilized neural network,
The intelligent algorithms such as fuzzy system solve the problems, such as well log interpretation.At present when carrying out fluid identification using neural network method, lead to
The log data to fluid sensitive is often selected then to select certain single machine learning algorithm (such as BP neural network) as input
It being trained, training set comes from the reservoir of known test result, after training network, then unknown input fluid type reservoir
Log data utilizes neural network prediction and the fluid type for judging the reservoir.
The core for carrying out Fluid Identification Method using log data based on neural network is used machine learning algorithm.
At present frequently with the single learning algorithm such as BP networks, decision tree, support vector machines, these methods have respective advantage and disadvantage, lead to
It crosses single decision-making mechanism to classify, each algorithm often will appear over training, and robustness is bad.Therefore, it is using
Single intelligent algorithm may can be absorbed in local minimum when being trained and predicting because of over-fitting, and cause generalization ability bad.
For this purpose, in view of each intelligent algorithm has different advantage and function, a variety of method joints, which can reduce, to be absorbed in
The risk of local minimum, the present invention intend on core intelligence algorithm using the united Committee Decision classification plan of multi-intelligence algorithm
Slightly, and keep the decision of the committee more scientific by excellent decision-making mechanism, it is more acurrate.
BP (back propagation) neural network is 1986 by the science headed by Rumelhart and McClelland
The concept that family proposes, is a kind of multilayer feedforward neural network trained according to error backpropagation algorithm, is most widely used at present
General neural network.
Decision tree (Decision Tree) be it is known it is various happen probability on the basis of, pass through constitute decision tree
Desired value to seek net present value (NPV) is more than or equal to zero probability, and assessment item risk judges the method for decision analysis of its feasibility,
It is a kind of intuitive graphical method for using probability analysis.Since this decision branch is drawn as limb of the figure like one tree, therefore claim
Decision tree.In machine learning, decision tree is a prediction model, and what he represented is one kind between object properties and object value
Mapping relations.
Support vector machines (Support Vector Machine, SVM) is that Corinna Cortes and Vapnik are equal to
What nineteen ninety-five proposed first, it shows many distinctive advantages in solving small sample, the identification of non-linear and high dimensional pattern, and
It can promote the use of in the other machines problem concerning study such as Function Fitting.
In machine learning, support vector machines is supervised learning model related with relevant learning algorithm, can be analyzed
Data, recognition mode, for classification and regression analysis.
Adaptive Neuro-fuzzy Inference is a kind of novel mould organically combining fuzzy logic and neuroid
Inference system structure is pasted, premise parameter and consequent parameter are adjusted using back-propagation algorithm and the hybrid algorithm of least square method,
And If-Then rules can be automatically generated.Fuzzy inference system ANFIS (Adaptive based on adaptive neural network
Network-based Fuzzy Inference System) neural network is organically combined with fuzzy reasoning, both sent out
The advantages of having waved the two, and compensate for respective deficiency.
Invention content
In order to solve over-fitting existing for single intelligent classification algorithm, be absorbed in Local Minimum, and cause generalization ability bad
The problem of, the present invention provides one kind and utilizes log data to carry out fluid identification of reservoir method, the method based on committee machine
Committee Decision mechanism is used on the basis of multiple intelligent classification algorithms, realizes that the identification to reservoir fluid is classified.The side
Method combines the classification results of multiple intelligent classification algorithms, with a kind of decision-making mechanism of the similar committee, at multiple points
On the basis of class result, final classification results are determined, be effectively combined the advantage of different intelligent sorting algorithm, improved most
The accuracy classified eventually.
To realize that above-mentioned target, the present invention use following technical scheme：
One kind carrying out fluid identification of reservoir method based on committee machine using log data, and the method includes following steps
Suddenly：
1) select the log data to fluid sensitive as input data；
2) each attribute value of input data is normalized；
3) fluid type of reservoir through is obtained according to formation testing result；
4) each layer of log data and fluid type of reservoir through are combined into composition data set；
5) data set is randomly assigned to two classes, one kind is training dataset, and another kind of is test data set；
6) select several intelligent classification algorithm as pre-sorting device；
7) using training dataset as input, each pre-sorting algorithm is trained respectively, obtains corresponding point
Class model；
8) using test data set as input, a classification is provided by each disaggregated model respectively；
9) it is directed to each group of input data, the category combinations that each disaggregated model is provided are determined using a kind of committee
Plan mechanism provides final class categories.
Preferably, in the step 1), choose interval transit time (AC), neutron density (CNL), compensation density (DEN), from
The log datas such as right gamma (GR), deep investigation induction log (ILD), medium investigation induction log (ILM) are as input data.
Preferably, the Reservoir type involved in the step 3) includes dried layer, water layer, oil-containing water layer, oil-water common-layer and oil
Layer.
Preferably, in the step 5), training dataset and test data set account for 80% He of data set total amount respectively
20%.
Preferably, the intelligent classification algorithm used in the step 6) includes BP neural network, support vector machines and adaptive
Answer NN-FR detecting section system.
Preferably, the Committee Decision mechanism in the step 9) combines the output of each intelligent classification model using ballot method
Type generates final classification output type.
Preferably, the ballot method includes three classes：Absolute majority ballot method is predicted if certain type gained vote is more than half
For the type, otherwise refusal prediction；Relative majority ballot method, is predicted as who gets the most votes's type, if there is multiple types to obtain simultaneously
Ticket highest then therefrom randomly selects one；Weighted voting algorithm assigns one weighted value of each intelligence system to calculate each type
Number of votes obtained.
The advantages of the present invention are：The present invention proposes a variety of intelligent classifications on core classification algorithms selection
The united thought of algorithm, i.e. committee machine, similar to a committee has been set up, each committee member corresponds to different intelligent classifications
Algorithm, each sorting algorithm all different advantage and function.The decision-making mechanism of the committee machine Mock-Up Board, by excellent
Decision-making mechanism these single intelligent classification algorithms are joined together, can reduce and be absorbed in Local Minimum, make the decision of the committee
It is more scientific, it is more acurrate.Therefore, this method is more superior than single intelligent classification system, and training degree is high, and prediction result is more preferable.
Description of the drawings
Attached drawing 1 is the fundamental diagram of the fluid identification of reservoir method of the present invention based on log data.
Attached drawing 2 is the work flow diagram of the fluid identification of reservoir method of the present invention based on log data.
Attached drawing 3 is the confusion matrix figure of the fluid identification of reservoir classification prediction of the present invention based on log data.
Attached drawing 4 be the fluid identification of reservoir method of the present invention based on log data in embodiment with each single intelligence
The comparison diagram of algorithm classification estimated performance.
Specific implementation mode
Referring to attached drawing 1, attached drawing 2, one kind carrying out fluid identification of reservoir method, institute based on committee machine using log data
The method of stating includes the following steps：
1) select the log data to fluid sensitive as input data；
2) each attribute value of input data is normalized；
3) fluid type of reservoir through is obtained according to formation testing result；
4) each layer of log data and fluid type of reservoir through are combined into composition data set；
5) data set is randomly assigned to two classes, one kind is training dataset, and another kind of is test data set；
6) select several intelligent classification algorithm as pre-sorting device；
7) using training dataset as input, each pre-sorting algorithm is trained respectively, obtains corresponding point
Class model；
8) using test data set as input, a classification is provided by each disaggregated model respectively；
9) it is directed to each group of input data, the category combinations that each disaggregated model is provided are determined using a kind of committee
Plan mechanism provides final class categories.
In the step 1), interval transit time, neutron density, compensation density, natural gamma, deep investigation induction log, middle sense are chosen
It the log datas such as should log well as input data.
Reservoir type involved in the step 3) includes dried layer, water layer, oil-containing water layer, oil-water common-layer and oil reservoir.
In the step 5), training dataset and test data set account for the 80% and 20% of total amount of data respectively.
The intelligent classification algorithm used in the step 6) includes BP neural network, support vector machines and adaptive neural network net
Network-fuzzy inference system.
Committee Decision mechanism in the step 9) combines the output type of each intelligent classification model, production using ballot method
Raw final classification output type.
The ballot method is using any one in absolute majority ballot method, relative majority ballot method and weighted voting algorithm.
With reference to embodiment, the invention will be further described.
Embodiment
The log data and formation testing result data of several mouthfuls of the area in selection Red River wells carry out classification committee member as data set
It can machine experiment.It operates according to the following steps：
1) selection is to the interval transit time of fluid sensitive, neutron density, compensation density, gamma (GR), deep investigation induction log, middle sense
It should log well with log datas such as laterolog 8s (LL8) as input data；
2) normalized is done to the data of 7 input feature vectors, normalization formula is：
In formula,xmin、xmaxThe average value of all data, minimum value, maximum value in respectively a certain attribute, x are to wait returning
One data changed.After normalized, the data of 7 input feature vectors are in [- 1,1]；
3) classified to reservoir according to formation testing result, class object be five kinds of Reservoir types, respectively dried layer, water layer,
Oil-containing water layer, oil-water common-layer and oil reservoir are indicated with number 1~5 respectively in an experiment；
4) each layer of log data and fluid type of reservoir through are combined into composition data set；
5) data set is randomly assigned to two classes, 80% data are as training set, and 20% data are as test set, portion
Divide training set data as shown in table 1, partial test collection data are as shown in table 2；
6) select BP neural network, support vector machines and neuro fuzzy systems as pre-sorting device；
7) using training dataset as input, each pre-sorting algorithm is trained respectively, obtains corresponding point
Class model；
8) test data set is utilized, BP neural network, support vector machines and neuro fuzzy systems are obtained by training respectively
These three models input xi to each sample, and three models output a classification marker, O respectivelyBPNN, i、OSVM, iWith
OANFIS.i, the value collection of wherein classification marker is combined into { 1,2,3,4,5 }, as committee machine structure experimental data, portion
Divided data is as shown in table 3；
9) it is directed to each group of input data, the category combinations that each disaggregated model is provided are voted using relative majority
Combination strategy of the method as the committee.In relative majority ballot method, the committee counts a most label conduct of number of votes obtained
The final output of the committee；If the label of three models output is different, randomly choosed from three labels.It is logical
Relative majority ballot is crossed, the committee finally obtains the classification to each sample predictions, that is, the fluid for completing reservoir to be explained is known
Not.
Part training data of the table 1 for committee's experiment of classifying
Partial test data of the table 2 for committee's experiment of classifying
Part pre-sorting device output data of the table 3 for committee's structure of classifying
Comparative example
Made with the performance of accuracy rate and mean square error characterization classification prediction in order to illustrate the performance of classification committee method
With test data to the committee and three committee members --- the classification of BP neural network, support vector machines and neuro fuzzy systems
Performance is tested, and by the prediction result for the committee of classifying and three committee members --- BP neural network, support vector machines and god
Performance through fuzzy system in the classification problem is compared.Test result is：The classification accuracy of committee's model is
96.1%, the mean square error of output valve and desired value is 6.8%, and the confusion matrix for prediction of classifying is as shown in Fig. 3；The committee
The mean square error of the single committee member's system of the Mean Square Error Ratio of model prediction result and desired value will be low, and based on classification committee member
Can predictablity rate also above the accuracy rate of any one single committee member's system, comparative situation is as shown in Fig. 4.
Finally it should be noted that：Obviously, the above embodiment is merely an example for clearly illustrating the present invention, and simultaneously
The non-restriction to embodiment.For those of ordinary skill in the art, it can also do on the basis of the above description
Go out other various forms of variations or variation.There is no necessity and possibility to exhaust all the enbodiments.And thus drawn
The obvious changes or variations of stretching are still in the protection scope of this invention.
Claims (7)
1. one kind carrying out fluid identification of reservoir method based on committee machine using log data, which is characterized in that the method
Include the following steps：
1) select the log data to fluid sensitive as input data；
2) each attribute value of input data is normalized；
3) fluid type of reservoir through is obtained according to formation testing result；
4) each layer of log data and fluid type of reservoir through are combined into composition data set；
5) data set is randomly assigned to two classes, one kind is training dataset, and another kind of is test data set；
6) select several intelligent classification algorithm as pre-sorting device；
7) using training dataset as input, each pre-sorting algorithm is trained respectively, obtains corresponding classification mould
Type；
8) using test data set as input, a classification is provided by each disaggregated model respectively；
9) each group of input data, the category combinations that each disaggregated model is provided, using a kind of Committee Decision machine are directed to
System, provides final class categories.
2. a kind of committee machine that is based on according to claim 1 carries out fluid identification of reservoir method using log data,
It is characterized in that：In the step 1), choose interval transit time, neutron density, compensation density, natural gamma, deep investigation induction log, in
The log datas such as induction logging are as input data.
3. a kind of committee machine that is based on according to claim 1 carries out fluid identification of reservoir method using log data,
It is characterized in that：Reservoir type involved in the step 3) includes dried layer, water layer, oil-containing water layer, oil-water common-layer and oil reservoir.
4. a kind of committee machine that is based on according to claim 1 carries out fluid identification of reservoir method using log data,
It is characterized in that：In the step 5), training dataset and test data set account for the 80% and 20% of data set total amount respectively.
5. a kind of committee machine that is based on according to claim 1 carries out fluid identification of reservoir method using log data,
It is characterized in that：The intelligent classification algorithm used in the step 6) includes BP neural network, support vector machines and adaptive god
Through network-fuzzy inference system.
6. a kind of committee machine that is based on according to claim 1 carries out fluid identification of reservoir method using log data,
It is characterized in that, the Committee Decision mechanism in the step 9) combines the output class of each intelligent classification model using ballot method
Type generates final classification output type.
7. one kind according to claim 1 or 6 is based on committee machine and carries out fluid identification of reservoir side using log data
Method, which is characterized in that the ballot method includes three classes：Absolute majority ballot method is predicted as if certain type gained vote is more than half
The type, otherwise refusal prediction；Relative majority ballot method, is predicted as who gets the most votes's type, if there is multiple types to win the vote simultaneously
Highest then therefrom randomly selects one；Weighted voting algorithm assigns one weighted value of each intelligence system to calculate each type
Number of votes obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810377375.8A CN108596251A (en) | 2018-04-25 | 2018-04-25 | One kind carrying out fluid identification of reservoir method based on committee machine using log data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810377375.8A CN108596251A (en) | 2018-04-25 | 2018-04-25 | One kind carrying out fluid identification of reservoir method based on committee machine using log data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596251A true CN108596251A (en) | 2018-09-28 |
Family
ID=63609113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810377375.8A Pending CN108596251A (en) | 2018-04-25 | 2018-04-25 | One kind carrying out fluid identification of reservoir method based on committee machine using log data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596251A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
| CN110056348A (en) * | 2019-04-25 | 2019-07-26 | 中国海洋石油集团有限公司 | A kind of method and system of measurement formation fluid composition and property |
| CN110674841A (en) * | 2019-08-22 | 2020-01-10 | 中国石油天然气集团有限公司 | Logging curve identification method based on clustering algorithm |
| CN111695635A (en) * | 2020-06-15 | 2020-09-22 | 中国地质大学（北京） | Dynamic classification committee machine logging fluid identification method and system |
| CN111881287A (en) * | 2019-09-10 | 2020-11-03 | 马上消费金融股份有限公司 | Classification ambiguity analysis method and device |
| CN112099087A (en) * | 2020-09-27 | 2020-12-18 | 中国石油天然气股份有限公司 | Geophysical intelligent prediction method, device and medium for oil reservoir seepage characteristic parameters |
| CN112230278A (en) * | 2019-07-15 | 2021-01-15 | 中国石油天然气集团有限公司 | Seepage field characteristic parameter determination method and device |
| CN112862139A (en) * | 2019-11-27 | 2021-05-28 | 北京国双科技有限公司 | Fluid type prediction model construction method, fluid type prediction method and device |
| CN113592028A (en) * | 2021-08-16 | 2021-11-02 | 中国地质大学（北京） | Method and system for identifying logging fluid by using multi-expert classification committee machine |
| CN115961952A (en) * | 2023-02-21 | 2023-04-14 | 成都理工大学 | Reservoir fluid comprehensive discrimination method based on combination parameters in oil and gas reservoir |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634717A (en) * | 2009-08-26 | 2010-01-27 | 中国石油大学(华东) | Fine shear-wave (S-wave) impedance access technology based on logging and prestack channel set seismic data |
| CN101930082A (en) * | 2009-06-24 | 2010-12-29 | 中国石油集团川庆钻探工程有限公司 | Method for discriminating reservoir fluid type by using resistivity data |
| CN106980872A (en) * | 2017-02-17 | 2017-07-25 | 北京维弦科技有限责任公司 | K arest neighbors sorting techniques based on polling committee |
-
2018
- 2018-04-25 CN CN201810377375.8A patent/CN108596251A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930082A (en) * | 2009-06-24 | 2010-12-29 | 中国石油集团川庆钻探工程有限公司 | Method for discriminating reservoir fluid type by using resistivity data |
| CN101634717A (en) * | 2009-08-26 | 2010-01-27 | 中国石油大学(华东) | Fine shear-wave (S-wave) impedance access technology based on logging and prestack channel set seismic data |
| CN106980872A (en) * | 2017-02-17 | 2017-07-25 | 北京维弦科技有限责任公司 | K arest neighbors sorting techniques based on polling committee |
Non-Patent Citations (1)
| Title |
|---|
| 王黎雪: "裂缝性致密砂岩测井解释方法研究 ——以红河油田长8为例", 《中国优秀硕士学位论文全文数据库（电子期刊）基础科学辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919184A (en) * | 2019-01-28 | 2019-06-21 | 中国石油大学(北京) | A kind of more well complex lithology intelligent identification Methods and system based on log data |
| CN110056348A (en) * | 2019-04-25 | 2019-07-26 | 中国海洋石油集团有限公司 | A kind of method and system of measurement formation fluid composition and property |
| CN110056348B (en) * | 2019-04-25 | 2021-05-11 | 中国海洋石油集团有限公司 | Method and system for determining formation fluid composition and properties |
| CN112230278A (en) * | 2019-07-15 | 2021-01-15 | 中国石油天然气集团有限公司 | Seepage field characteristic parameter determination method and device |
| CN110674841A (en) * | 2019-08-22 | 2020-01-10 | 中国石油天然气集团有限公司 | Logging curve identification method based on clustering algorithm |
| CN110674841B (en) * | 2019-08-22 | 2022-03-29 | 中国石油天然气集团有限公司 | Logging curve identification method based on clustering algorithm |
| CN111881287B (en) * | 2019-09-10 | 2021-08-17 | 马上消费金融股份有限公司 | Classification ambiguity analysis method and device |
| CN111881287A (en) * | 2019-09-10 | 2020-11-03 | 马上消费金融股份有限公司 | Classification ambiguity analysis method and device |
| CN112862139A (en) * | 2019-11-27 | 2021-05-28 | 北京国双科技有限公司 | Fluid type prediction model construction method, fluid type prediction method and device |
| CN111695635A (en) * | 2020-06-15 | 2020-09-22 | 中国地质大学（北京） | Dynamic classification committee machine logging fluid identification method and system |
| CN111695635B (en) * | 2020-06-15 | 2023-08-08 | 中国地质大学（北京） | Dynamic classification committee machine logging fluid identification method and system |
| CN112099087A (en) * | 2020-09-27 | 2020-12-18 | 中国石油天然气股份有限公司 | Geophysical intelligent prediction method, device and medium for oil reservoir seepage characteristic parameters |
| CN113592028A (en) * | 2021-08-16 | 2021-11-02 | 中国地质大学（北京） | Method and system for identifying logging fluid by using multi-expert classification committee machine |
| CN115961952A (en) * | 2023-02-21 | 2023-04-14 | 成都理工大学 | Reservoir fluid comprehensive discrimination method based on combination parameters in oil and gas reservoir |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596251A (en) | One kind carrying out fluid identification of reservoir method based on committee machine using log data | |
| CN108665109A (en) | A kind of reservoir parameter log interpretation method based on recurrence committee machine | |
| DAVIS et al. | Machine-learning algorithms for credit-card applications | |
| Akgüngör et al. | An artificial intelligent approach to traffic accident estimation: Model development and application | |
| Zhang et al. | Bilateral sensitivity analysis: a better understanding of a neural network | |
| Larbani et al. | A novel method for fuzzy measure identification. | |
| Srisaeng et al. | An adaptive neuro-fuzzy inference system for forecasting Australia's domestic low cost carrier passenger demand | |
| CN106919980A (en) | A kind of increment type target identification system based on neuromere differentiation | |
| US20120109865A1 (en) | Using affinity measures with supervised classifiers | |
| Jha et al. | Extracting low‐dimensional psychological representations from convolutional neural networks | |
| CN115907001A (en) | Knowledge distillation-based federal diagram learning method and automatic driving method | |
| Shokir et al. | Permeability estimation from well log responses | |
| Gimblett et al. | Autonomous rule generation and assessment for complex spatial modeling | |
| Zhong et al. | A new fuzzy clustering algorithm based on clonal selection for land cover classification | |
| CN108873706A (en) | Evaluation of trap intelligent expert recommended method based on deep neural network | |
| Putra et al. | Implementation of neural network to determine the new college students | |
| Mohaghegh et al. | Application of artificial intelligence in the upstream oil and gas industry | |
| Ouallane et al. | Towards intelligent road traffic management based on neutrosophic logic: a brief review | |
| Samimi et al. | A comparison between different data mining algorithms in freight mode choice | |
| Lahsasna et al. | Intelligent credit scoring model using soft computing approach | |
| Khoukhi et al. | A data-driven genetic neuro-fuzzy system to PVT properties prediction | |
| Wei et al. | Study on battlefield situation assessment model of simulation entity based on stacked auto-encoder network | |
| Zhang et al. | An interpretable neural model with interactive stepwise influence | |
| Djemaiel et al. | A dynamic hybrid rbf/elman neural networks for credit scoring using big data | |
| Srisaeng et al. | An adaptive neuro-fuzzy inference system for modelling Australia's regional airline passenger demand |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180928 |