CN111783825A - Well logging lithology identification method based on convolutional neural network learning - Google Patents
Well logging lithology identification method based on convolutional neural network learning Download PDFInfo
- Publication number
- CN111783825A CN111783825A CN202010456323.7A CN202010456323A CN111783825A CN 111783825 A CN111783825 A CN 111783825A CN 202010456323 A CN202010456323 A CN 202010456323A CN 111783825 A CN111783825 A CN 111783825A
- Authority
- CN
- China
- Prior art keywords
- lithology
- neural network
- convolutional neural
- well
- training
- 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
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 238000005553 drilling Methods 0.000 claims abstract description 16
- 238000011176 pooling Methods 0.000 claims abstract description 8
- 238000004140 cleaning Methods 0.000 claims abstract description 5
- 238000003062 neural network model Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 17
- 230000004913 activation Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 230000006698 induction Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims 1
- 239000011435 rock Substances 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 229910021532 Calcite Inorganic materials 0.000 description 1
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 229910000514 dolomite Inorganic materials 0.000 description 1
- 239000010459 dolomite Substances 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
Abstract
The invention discloses a well logging lithology recognition method based on convolutional neural network learning, which comprises the following steps of 1, taking a data curve acquired by well drilling coring as an input characteristic; taking the lithology result of the well drilling as an input characteristic label, cleaning sample data and establishing a learning data sample; 2. sequentially arranging three porosity, three resistivity and three lithology curves, classifying the lithology of the drilling well into four types, and then classifying the learning data samples into a training set and a testing set; 3. extracting characteristic parameters by adopting primary convolution and primary pooling, linking a Softmax regression layer, and establishing a convolution neural network model; 4. training a convolutional neural network model, testing the accuracy of the convolutional neural network model by using a test set, putting the convolutional neural network model into practice if the required accuracy is met, and increasing the training amount if the required accuracy is not met; 5. and identifying the lithology of the new well by using the trained convolutional neural network model. The rock stratum information can be identified more accurately, and the convergence speed is high.
Description
Technical Field
The invention belongs to the field of rock stratum exploration, and relates to a well logging lithology identification method based on convolutional neural network learning.
Background
Lithology is the overall reflection of the deposition, structure and mineral combination of underground rocks, and accurate identification of lithology has important significance for reservoir division, hydrocarbon reservoir identification and oil reservoir evaluation.
The stratum lithology identification comprises a plurality of methods such as field outcrop, well drilling coring, seismic inversion, well logging interpretation and the like, the well logging interpretation is usually based on one or two empirical formulas of well logging curves, lithology is judged by calculating the content of components such as argillaceous substances, coal, calcite, dolomite and the like, and identification methods such as a cross plot method, stratum element well logging and the like are also available, but the methods cannot fully excavate lithology information in all the well logging curves and have certain limitations. Secondly, methods such as a support vector machine, a random forest, a BP neural network and the like are used for automatically identifying lithology in a logging curve, but the convergence rate of the methods is low, the methods are easy to enter gradient disappearance, gradient explosion and the like, and the generalization is not ideal.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a well logging lithology identification method based on convolutional neural network learning, which can identify rock stratum information more accurately and has high convergence rate.
In order to achieve the purpose, the invention adopts the following technical scheme to realize the purpose:
a well logging lithology recognition method based on convolutional neural network learning comprises the following steps;
taking a data curve acquired by well drilling coring as an input characteristic, wherein the data curve comprises natural potential, natural gamma, well diameter, deep induction, eight lateral directions, acoustic time difference, compensation neutrons and volume density; taking the lithology result of the well drilling as an input characteristic label, cleaning sample data and establishing a learning data sample;
sequentially arranging three porosity, three resistivity and three lithology curves, classifying the lithology of the drilling well into four types, and then classifying the learning data sample into a training set and a testing set;
extracting characteristic parameters by adopting primary convolution and primary pooling, linking a Softmax regression layer, and establishing a convolution neural network model;
training a convolutional neural network model, testing the accuracy of the convolutional neural network model by using a test set, putting the convolutional neural network model into practice if the required accuracy is met, and increasing the training amount if the required accuracy is not met;
and step five, using the trained convolutional neural network model to identify the lithology of the new well.
Preferably, in the first step, when the sample data is cleaned, the data samples of the thin layer, the lithologic abrupt change section and the well wall collapse section are removed.
Preferably, in the first step, the data curve is subjected to depth correction and then discretized into data with a sampling interval of 0.125 m.
Further, depth correction is carried out by matching the porosity analysis result and the sound wave time difference calculation result.
Preferably, in the second step, the lithology of the drilled well is divided into four types, namely fine sandstone, argillaceous siltstone, silty mudstone and mudstone.
Preferably, in step three, Sigmoid is adopted for the activation function, adaptive gradient descent is adopted for gradient descent, square error function is adopted for the loss function, and L2 regularization is adopted for regularization.
Preferably, in the third step, the sample convolution matrix is a 3 × 3 matrix, and the convolution kernels of the four types of drilling lithology adopt a 2 × 2 matrix; the output layer is a four-dimensional probability matrix, the fine sandstone is [1,0,0,0], the argillaceous siltstone is [0,1,0,0], the silty mudstone is [0,0,1,0], and the mudstone is [0,0,0,1 ].
Preferably, in step four, during training, the training sample size Bachsize of a single batch is 128, and the Epoch of the training round is 40000.
Compared with the prior art, the invention has the following beneficial effects:
by acquiring nine data curves, the invention enables the extracted logging curve characteristics to be more, reflects the formation lithology information more comprehensively and can identify the formation lithology in higher dimensionality. Secondly, the convolutional neural network model is adopted, and nine data curves are sequenced and classified, so that the convergence rate of the convolutional neural network model is higher, overfitting and underfitting can be effectively prevented, and the applicability of the model is improved.
Drawings
FIG. 1 is a schematic diagram of a well-logging lithology identification process of the present invention;
FIG. 2 is a schematic diagram of a convolutional neural network architecture of the present invention;
FIG. 3 is a schematic diagram of three activation functions of the present invention;
FIG. 4 is a three-dimensional visual screenshot of the training process of the present invention;
FIG. 5 is a graph of the new well lithology autoprediction outcome of the present invention compared to well logging coring.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The embodiment defines a convolutional neural network with the programming interface API provided by tensrflow in fig. 1, which is an open source software library developed for google that employs dataflow graphs for numerical calculations. Based on the source program, the flow of the automatic identification method for the well logging lithology based on the convolutional neural network machine learning is shown in the attached drawing 1, and all the steps can be automatically operated by a person skilled in the art by adopting a computer software technology. The embodiment specifically realizes the following processes:
step 1.1, obtaining sample data: acquiring logging curve natural potential, natural gamma, well diameter, deep induction, eight lateral directions, acoustic time difference, compensation neutrons and volume density, and dispersing the logging curve natural potential, the natural gamma, the well diameter, the deep induction, the eight lateral directions, the acoustic time difference and the compensation neutrons into data with sampling interval of 0.125m after depth correction;
step 1.2, sample label formulation: and calibrating the well logging interpretation result according to the lithology description result of the well drilling coring. The coring data are matched with the porosity analysis result and the acoustic wave time difference calculation result to carry out depth correction;
step 1.3, sample data cleaning: and removing data samples of the thin layer, the lithologic abrupt change section and the well wall collapse section, and reserving data of the stratum sedimentation stable layer section.
step 2.1, arranging the data according to the three porosity, the three resistivity and the three lithology in sequence, and conveniently carrying out convolution operation;
step 2.2, dividing lithologic data into four types of fine sandstone, argillaceous siltstone, silty mudstone and mudstone according to geological characteristics of a research area; redundant samples are deleted, so that the four types of lithologic samples are evenly distributed, and the machine learning result is prevented from having tendency; and dividing the data into a training set and a verification set to form a machine learning sample library. The labels of the four lithologies are represented by a matrix: fine sandstone: [1,0,0,0], argillaceous siltstone: [0,1,0,0], silty mudstone: [0,0,1,0], mudstone: [0,0,0,1 ];
fig. 2 shows activation functions of the pooling layer and the Softmax layer, which are commonly used in three types, namely Sigmoid, Relu and Tanh functions.
Step 3.1, building a convolutional neural network according to the input parameter form, selecting an optimal global variable, setting an important parameter adjustment table, and manually searching for an optimal parameter;
step 3.2, connecting the pooling layer by using the convolution layer, then connecting a network structure of the Softmax regression layer, wherein the activation function adopts Sigmoid, the gradient descent adopts an adaptive gradient descent method Adagrad, the loss function adopts a square error function, and the regularization adopts L2 regularization;
FIG. 2 is a schematic diagram of a convolutional neural network framework of the present invention, which includes a convolutional layer, a pooling layer, and a Softmax layer. Arranging the 9 logging curves according to the sequence in the drawing to form a matrix capable of being convoluted, wherein a convolution kernel adopts a 2 x 2 matrix; the output layer is a four-dimensional probability matrix, and the corresponding relation is as follows: fine sandstone: [1,0,0,0], argillaceous siltstone: [0,1,0,0], silty mudstone: [0,0,1,0], mudstone: [0,0,0,1 ];
1) the sample convolution matrix is a 3 × 3 matrix, the convolution kernel is a 2 × 2 matrix, and the arrangement order is as follows:
and (3) convolution kernel:
2) the parameter of the pooling layer is 32, namely, 32 feature vectors are finally extracted;
3) the activation function adopts a Sigmoid function, and the calculation method is expressed by the following formula:
wherein: x is a vector representing the value of the input layer;
(x) is a vector representing the weight matrix of the output layer;
4) the gradient descent algorithm adopts an adaptive gradient descent method Adagrrad, and the calculation method is expressed by the following formula:
wherein G istFor a diagonal matrix, each diagonal position i, i is the corresponding parameter θiThe sum of squares of the gradients from round 1 to round t ∈ is a smoothing term to avoid the denominator being zero, and θ represents an argument, i.e., one of the 9 data curves.
5) The loss function is a squared error function, and the calculation method is expressed by the following formula:
where C is a loss function x representing the sample, y (x) represents the output,
representing the actual value and n the total number of samples.
A schematic diagram of the three activation functions is shown in fig. 3.
FIG. 4 is a process screenshot of the training process visualization check in a Tensoboard after the model of the invention is trained and optimized and saved. As can be seen from the figure, after 10000 rounds of training, 4 lithologies are gradually separated, and the classification effect is good.
And 4, training the network model, adjusting the training parameters to enable the model to be fast converged, and testing the accuracy of the model by using the test set.
Step 4.1, feeding the training set sample into a neural network, and adjusting key hyper-parameters, including parameters such as learning rate, Batchsize and Epoch; wherein the training sample size Bachsize of a single batch is 128, the Epoch of a training round is 40000, the accuracy and the loss function are observed, the model convergence is ensured, the loss function is smoothly reduced, the accuracy is stably increased, and the stability level is reached;
step 4.2, feeding the sample data of the test set into a neural network to obtain a loss function and accuracy;
and 4.3, repeating the steps 4.1 and 4.2, and considering that the trained model has practical value when the test accuracy rate is not improved greatly and reaches more than 85%. For each group of parameter combination, testing on the test set every time the training of the number of samples of one round of iterative training is carried out, obtaining the error of the current model on the test set, and stopping the training when the number of sample iterations reaches Epoch times or the error does not decrease on the test set; and finally, obtaining an optimized model by taking the minimum super-parameter combination on the test set, wherein the accuracy of the training set is 96.3 percent, and the accuracy of the test set is 85.2 percent.
FIG. 5 is a comparison graph of the effect of the trained artificial intelligence model in new well treatment, and by comparing the interpretation of the convolution network algorithm with the lithology and the lithology of logging coring, the prediction accuracy is better, most lithology identification is correct, only a few mudstone segments are identified and are different from the actual one, and the production requirement can be basically met.
And 5, automatically predicting the lithology of the new well.
And 5.1, finding out data of a new well, arranging the data according to network setting, feeding the data into a network model to obtain a lithology prediction result, comparing the lithology prediction result with the drilling coring data, and evaluating the practicability of the lithology prediction result.
And 5.2, processing the new wells in batches, and carrying out regional lithology prediction and reservoir evaluation.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (8)
1. A well logging lithology recognition method based on convolutional neural network learning is characterized by comprising the following steps;
taking a data curve acquired by well drilling coring as an input characteristic, wherein the data curve comprises natural potential, natural gamma, well diameter, deep induction, eight lateral directions, acoustic time difference, compensation neutrons and volume density; taking the lithology result of the well drilling as an input characteristic label, cleaning sample data and establishing a learning data sample;
sequentially arranging three porosity, three resistivity and three lithology curves, classifying the lithology of the drilling well into four types, and then classifying the learning data sample into a training set and a testing set;
extracting characteristic parameters by adopting primary convolution and primary pooling, linking a Softmax regression layer, and establishing a convolution neural network model;
training a convolutional neural network model, testing the accuracy of the convolutional neural network model by using a test set, putting the convolutional neural network model into practice if the required accuracy is met, and increasing the training amount if the required accuracy is not met;
and step five, using the trained convolutional neural network model to identify the lithology of the new well.
2. The method for identifying the lithology of the well logging based on the convolutional neural network learning of claim 1, wherein in the first step, when sample data is cleaned, data samples of a thin layer, a lithology mutation section and a well wall collapse section are removed.
3. The method for identifying lithology logging based on convolutional neural network learning of claim 1, wherein in the first step, the data curve is subjected to depth correction and then is discretized into data with a sampling interval of 0.125 m.
4. The method of claim 3, wherein the depth correction is performed by matching a porosity analysis result with a sound wave time difference calculation result.
5. The method for identifying the lithology of the well logging based on the convolutional neural network learning of claim 1, wherein in the second step, the lithology of the well drilling is divided into four types of fine sandstone, argillaceous siltstone, siltstone mudstone and mudstone.
6. The method for identifying the lithology of the well logging based on the convolutional neural network learning of claim 1, wherein in the third step, an activation function adopts Sigmoid, gradient descent adopts an adaptive gradient descent method, a loss function adopts a square error function, and regularization adopts L2 regularization.
7. The method for identifying the lithology of the well logging based on the convolutional neural network learning of claim 1, wherein in the third step, the convolution matrix of the sample is a 3 x 3 matrix, and the convolution kernels of the lithology of the four types of the well drilling adopt a 2 x 2 matrix; the output layer is a four-dimensional probability matrix, the fine sandstone is [1,0,0,0], the argillaceous siltstone is [0,1,0,0], the silty mudstone is [0,0,1,0], and the mudstone is [0,0,0,1 ].
8. The method of claim 1, wherein in step four, the training sample size Bachsize of a single batch is 128 and the Epoch of the training round is 40000 during training.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010456323.7A CN111783825A (en) | 2020-05-26 | 2020-05-26 | Well logging lithology identification method based on convolutional neural network learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010456323.7A CN111783825A (en) | 2020-05-26 | 2020-05-26 | Well logging lithology identification method based on convolutional neural network learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111783825A true CN111783825A (en) | 2020-10-16 |
Family
ID=72753181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010456323.7A Pending CN111783825A (en) | 2020-05-26 | 2020-05-26 | Well logging lithology identification method based on convolutional neural network learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783825A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100930A (en) * | 2020-11-11 | 2020-12-18 | 中国石油大学(华东) | Formation pore pressure calculation method based on convolutional neural network and Eaton formula |
| CN112253087A (en) * | 2020-10-20 | 2021-01-22 | 河南理工大学 | Biological disturbance reservoir physical property calculation method based on multi-source logging data |
| CN112396130A (en) * | 2020-12-09 | 2021-02-23 | 中国能源建设集团江苏省电力设计院有限公司 | Intelligent identification method and system for rock stratum in static sounding test, computer equipment and medium |
| CN112597826A (en) * | 2020-12-08 | 2021-04-02 | 核工业北京地质研究院 | Method for lithologic classification of hyperspectral SASI data |
| CN112712025A (en) * | 2020-12-29 | 2021-04-27 | 东北石油大学 | Complex lithology identification method based on long-term and short-term memory neural network |
| CN112784980A (en) * | 2021-01-05 | 2021-05-11 | 中国石油天然气集团有限公司 | Intelligent logging horizon division method |
| CN112796746A (en) * | 2021-02-26 | 2021-05-14 | 西安石油大学 | Drilling method for petroleum geological exploration |
| CN112906465A (en) * | 2021-01-15 | 2021-06-04 | 阳泉煤业（集团）股份有限公司 | Coal measure stratum acoustic curve reconstruction method and system based on stratum factors |
| CN112990320A (en) * | 2021-03-19 | 2021-06-18 | 中国矿业大学(北京) | Lithology classification method and device, electronic equipment and storage medium |
| CN113159136A (en) * | 2021-03-30 | 2021-07-23 | 中铁第四勘察设计院集团有限公司 | In-hole data fusion stratum dividing method, device, equipment and storage medium |
| CN113177919A (en) * | 2021-04-28 | 2021-07-27 | 成都艾立本科技有限公司 | Lithology classification and principal component element content detection method combining LIBS and deep learning |
| CN113344050A (en) * | 2021-05-28 | 2021-09-03 | 中国石油天然气股份有限公司 | Lithology intelligent identification method and system based on deep learning |
| CN113392924A (en) * | 2021-06-29 | 2021-09-14 | 中海油田服务股份有限公司 | Method for identifying acoustoelectric imaging log and related equipment |
| CN113642698A (en) * | 2021-06-15 | 2021-11-12 | 中国科学技术大学 | Geophysical logging intelligent interpretation method, system and storage medium |
| CN114114414A (en) * | 2021-11-18 | 2022-03-01 | 电子科技大学长三角研究院(湖州) | Artificial intelligence prediction method for 'dessert' information of shale reservoir |
| CN114200524A (en) * | 2021-10-29 | 2022-03-18 | 五季数据科技(北京)有限公司 | Logging density curve correction method based on artificial intelligence deep learning |
| CN114896468A (en) * | 2022-04-24 | 2022-08-12 | 北京月新时代科技股份有限公司 | File type matching method and intelligent data entry method based on neural network |
| CN115393656A (en) * | 2022-10-26 | 2022-11-25 | 中石化经纬有限公司 | Automatic classification method for stratum classification of logging-while-drilling image |
| CN115659245A (en) * | 2022-10-24 | 2023-01-31 | 东华理工大学 | Sandstone-type uranium deposit rock stratum type identification method and device based on machine learning |
| CN117235628A (en) * | 2023-11-10 | 2023-12-15 | 天津花栗鼠软件科技有限公司 | Well logging curve prediction method and system based on hybrid Bayesian deep network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5251286A (en) * | 1992-03-16 | 1993-10-05 | Texaco, Inc. | Method for estimating formation permeability from wireline logs using neural networks |
| CN109670539A (en) * | 2018-12-03 | 2019-04-23 | 中国石油化工股份有限公司 | A kind of silt particle layer detection method based on log deep learning |
| US20200065606A1 (en) * | 2018-08-24 | 2020-02-27 | Petrochina Company Limited | Method and apparatus for automatically extracting image features of electrical imaging well logging |
| CN111178441A (en) * | 2019-12-31 | 2020-05-19 | 中国矿业大学(北京) | Lithology identification method based on principal component analysis and full-connection neural network |
-
2020
- 2020-05-26 CN CN202010456323.7A patent/CN111783825A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5251286A (en) * | 1992-03-16 | 1993-10-05 | Texaco, Inc. | Method for estimating formation permeability from wireline logs using neural networks |
| US20200065606A1 (en) * | 2018-08-24 | 2020-02-27 | Petrochina Company Limited | Method and apparatus for automatically extracting image features of electrical imaging well logging |
| CN109670539A (en) * | 2018-12-03 | 2019-04-23 | 中国石油化工股份有限公司 | A kind of silt particle layer detection method based on log deep learning |
| CN111178441A (en) * | 2019-12-31 | 2020-05-19 | 中国矿业大学(北京) | Lithology identification method based on principal component analysis and full-connection neural network |
Non-Patent Citations (1)
| Title |
|---|
| 陈钢花等: "卷积神经网络在岩性识别中的应用", 测井技术, vol. 43, no. 2, 30 April 2019 (2019-04-30), pages 130 - 133 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112253087A (en) * | 2020-10-20 | 2021-01-22 | 河南理工大学 | Biological disturbance reservoir physical property calculation method based on multi-source logging data |
| CN112100930A (en) * | 2020-11-11 | 2020-12-18 | 中国石油大学(华东) | Formation pore pressure calculation method based on convolutional neural network and Eaton formula |
| CN112597826A (en) * | 2020-12-08 | 2021-04-02 | 核工业北京地质研究院 | Method for lithologic classification of hyperspectral SASI data |
| CN112396130A (en) * | 2020-12-09 | 2021-02-23 | 中国能源建设集团江苏省电力设计院有限公司 | Intelligent identification method and system for rock stratum in static sounding test, computer equipment and medium |
| CN112712025A (en) * | 2020-12-29 | 2021-04-27 | 东北石油大学 | Complex lithology identification method based on long-term and short-term memory neural network |
| CN112784980A (en) * | 2021-01-05 | 2021-05-11 | 中国石油天然气集团有限公司 | Intelligent logging horizon division method |
| CN112906465A (en) * | 2021-01-15 | 2021-06-04 | 阳泉煤业（集团）股份有限公司 | Coal measure stratum acoustic curve reconstruction method and system based on stratum factors |
| CN112906465B (en) * | 2021-01-15 | 2023-12-22 | 阳泉煤业（集团）股份有限公司 | Coal measure stratum acoustic curve reconstruction method and system based on stratum factors |
| CN112796746B (en) * | 2021-02-26 | 2022-06-07 | 西安石油大学 | Drilling method for petroleum geological exploration |
| CN112796746A (en) * | 2021-02-26 | 2021-05-14 | 西安石油大学 | Drilling method for petroleum geological exploration |
| CN112990320A (en) * | 2021-03-19 | 2021-06-18 | 中国矿业大学(北京) | Lithology classification method and device, electronic equipment and storage medium |
| CN113159136A (en) * | 2021-03-30 | 2021-07-23 | 中铁第四勘察设计院集团有限公司 | In-hole data fusion stratum dividing method, device, equipment and storage medium |
| CN113177919A (en) * | 2021-04-28 | 2021-07-27 | 成都艾立本科技有限公司 | Lithology classification and principal component element content detection method combining LIBS and deep learning |
| CN113177919B (en) * | 2021-04-28 | 2022-08-05 | 成都艾立本科技有限公司 | Lithology classification and principal component element content detection method combining LIBS and deep learning |
| CN113344050A (en) * | 2021-05-28 | 2021-09-03 | 中国石油天然气股份有限公司 | Lithology intelligent identification method and system based on deep learning |
| CN113344050B (en) * | 2021-05-28 | 2024-03-26 | 中国石油天然气股份有限公司 | Lithology intelligent recognition method and system based on deep learning |
| CN113642698B (en) * | 2021-06-15 | 2024-04-02 | 中国科学技术大学 | Geophysical well logging intelligent interpretation method, system and storage medium |
| CN113642698A (en) * | 2021-06-15 | 2021-11-12 | 中国科学技术大学 | Geophysical logging intelligent interpretation method, system and storage medium |
| CN113392924A (en) * | 2021-06-29 | 2021-09-14 | 中海油田服务股份有限公司 | Method for identifying acoustoelectric imaging log and related equipment |
| CN114200524A (en) * | 2021-10-29 | 2022-03-18 | 五季数据科技(北京)有限公司 | Logging density curve correction method based on artificial intelligence deep learning |
| CN114114414A (en) * | 2021-11-18 | 2022-03-01 | 电子科技大学长三角研究院(湖州) | Artificial intelligence prediction method for 'dessert' information of shale reservoir |
| CN114896468A (en) * | 2022-04-24 | 2022-08-12 | 北京月新时代科技股份有限公司 | File type matching method and intelligent data entry method based on neural network |
| CN114896468B (en) * | 2022-04-24 | 2024-02-02 | 北京月新时代科技股份有限公司 | File type matching method and data intelligent input method based on neural network |
| CN115659245A (en) * | 2022-10-24 | 2023-01-31 | 东华理工大学 | Sandstone-type uranium deposit rock stratum type identification method and device based on machine learning |
| CN115393656A (en) * | 2022-10-26 | 2022-11-25 | 中石化经纬有限公司 | Automatic classification method for stratum classification of logging-while-drilling image |
| CN117235628A (en) * | 2023-11-10 | 2023-12-15 | 天津花栗鼠软件科技有限公司 | Well logging curve prediction method and system based on hybrid Bayesian deep network |
| CN117235628B (en) * | 2023-11-10 | 2024-01-26 | 天津花栗鼠软件科技有限公司 | Well logging curve prediction method and system based on hybrid Bayesian deep network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111783825A (en) | Well logging lithology identification method based on convolutional neural network learning | |
| US10329900B2 (en) | Systems and methods employing cooperative optimization-based dimensionality reduction | |
| CN110674841B (en) | Logging curve identification method based on clustering algorithm | |
| EP2310880B1 (en) | Systems and methods employing cooperative optimization-based dimensionality reduction | |
| US11226424B2 (en) | Method for detecting geological objects in a seismic image | |
| CN111596978A (en) | Web page display method, module and system for lithofacies classification by artificial intelligence | |
| US11893495B2 (en) | Dual neural network architecture for determining epistemic and aleatoric uncertainties | |
| CN115659245A (en) | Sandstone-type uranium deposit rock stratum type identification method and device based on machine learning | |
| CN114723095A (en) | Missing well logging curve prediction method and device | |
| WO2022051357A1 (en) | Core-level high resolution petrophysical characterization method | |
| Brown et al. | Machine learning on Crays to optimize petrophysical workflows in oil and gas exploration | |
| Lu et al. | Lithology identification using graph neural network in continental shale oil reservoirs: A case study in Mahu Sag, Junggar Basin, Western China | |
| Akinyokun et al. | Well log interpretation model for the determination of lithology and fluid | |
| CN111626377A (en) | Lithofacies identification method, device, equipment and storage medium | |
| CN115809411A (en) | Improved decision tree lithology identification method based on logging data | |
| Chikhi et al. | Probabilistic neural method combined with radial-bias functions applied to reservoir characterization in the Algerian Triassic province | |
| CN114755744A (en) | Total organic carbon well logging interpretation method and system based on mud shale heterogeneity characteristics | |
| Liu et al. | Machine learning assisted recovery of subsurface energy: a review | |
| Bhattacharya | Unsupervised time series clustering, class-based ensemble machine learning, and petrophysical modeling for predicting shear sonic wave slowness in heterogeneous rocks | |
| Tse et al. | Unsupervised learning on scientific ocean drilling datasets from the South China Sea | |
| Kuchin et al. | Machine learning methods for identifying composition of uranium deposits in Kazakhstan | |
| Emelyanova et al. | Unsupervised identification of electrofacies employing machine learning | |
| Wang et al. | Auto recognition of carbonate microfacies based on an improved back propagation neural network | |
| CN117407841B (en) | Shale layer seam prediction method based on optimization integration algorithm | |
| de Oliveira et al. | Ensemble of heterogeneous classifiers applied to lithofacies classification using logs from different wells |
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 |