Prediction method of continental facies shale clay mineral development based on logging artificial intelligence learning
The construction of a clay mineral development prediction model through artificial intelligence learning methods based on well logging data solves the difficulty of traditional methods in predicting clay mineral types and content in terrestrial shale exploration, and achieves a more efficient and accurate prediction effect.
Patent Information
- Application Number
- CN202411877062.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-19
- Publication Date
- 2025-04-11
AI Technical Summary
Traditional methods are difficult to quickly and accurately predict clay mineral types and content in terrestrial shale exploration, especially in large-scale exploration areas, and prior art is difficult to distinguish certain clay mineral types.
Using an artificial intelligence learning method based on well logging data, a clay mineral development prediction model based on artificial intelligence is constructed by acquiring and preprocessing well logging data, combining rock sample test results, and optimizing the model through a backpropagation algorithm to improve prediction accuracy.
It improves the accuracy and efficiency of clay mineral development prediction, reduces the cost and time consumption of traditional methods, has strong generalization ability and adaptability, and can quickly provide valuable information for terrestrial shale exploration and development.
Smart Images
Figure CN119808559A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of geological exploration technology, and more specifically to a method for predicting the development of continental shale clay minerals based on well logging artificial intelligence learning. Background Art
[0002] In the exploration and development of continental shales, the development of clay minerals is of great significance for reservoir evaluation and oil and gas production. Traditional clay mineral analysis methods are usually based on rock thin section observation and chemical analysis, which are not only time-consuming and labor-intensive, but also difficult to make rapid and accurate predictions in large-scale exploration areas.
[0003] There are many methods to determine the type and content of clay minerals through logging data, the most common of which are the thorium-potassium crossplot method, the cation exchange capacity-hydrogen index crossplot method and the stepwise multiple regression method. The parameters of the thorium-potassium crossplot are easy to collect, but they can only qualitatively evaluate clay minerals. In view of this, predecessors proposed an improved thorium-potassium crossplot, which can more accurately determine the content and type of clay minerals, but cannot accurately distinguish kaolinite and illite with higher thorium content. The cation exchange capacity-hydrogen index crossplot method can distinguish montmorillonite and illite, but it is not easy to distinguish chlorite and kaolinite. The stepwise multiple regression method has a high interpretation accuracy, but the selection of the mathematical model is greatly interfered by human factors, and it is difficult to ensure that the optimal interpretation is obtained.
[0004] With the continuous development of logging technology and the application of artificial intelligence algorithms, a new approach has been provided for the prediction of clay mineral development in continental shales.
[0005] Therefore, it is an urgent problem for technical personnel in this field to propose a prediction method for the development of terrestrial shale clay minerals based on well logging artificial intelligence learning to solve the difficulties existing in the prior art. Summary of the invention
[0006] In view of this, the present invention provides a prediction method for the development of continental shale clay minerals based on well logging artificial intelligence learning, which is used to solve the technical problems existing in the prior art.
[0007] In order to achieve the above object, the present invention provides the following technical solutions:
[0008] A prediction method for the development of continental shale clay minerals based on well logging artificial intelligence learning comprises the following steps:
[0009] Obtain continental shale logging data and collect continental shale samples;
[0010] Carry out data preprocessing on the collected continental shale logging data;
[0011] Test continental shale samples to obtain the types and contents of clay minerals in shale development;
[0012] According to the pre-processed continental shale logging data and the types and contents of clay minerals in shale development, an artificial intelligence-based clay mineral development prediction model is constructed;
[0013] Optimize the artificial intelligence-based clay mineral development prediction model;
[0014] The development of clay minerals in continental shale is predicted through the optimized artificial intelligence-based prediction model of clay mineral development.
[0015] In the above method, optionally, the continental shale logging data include: density, natural potential, natural gamma, sonic time difference, well diameter, deep lateral resistivity, shallow lateral resistivity, and porosity.
[0016] In the above method, optionally, the specific contents of collecting continental shale samples are:
[0017] In the shale exploration area, shale cores are selected for shale rock sampling by observing the distribution characteristics of shale.
[0018] The above method can optionally test continental shale samples to obtain the specific contents of clay mineral types and contents in shale development:
[0019] Through XRD shale mineral type test and XRD clay mineral content test, the type and content of clay minerals in shale development can be obtained.
[0020] In the above method, optionally, the specific content of constructing a clay mineral development prediction model based on artificial intelligence is:
[0021] The preprocessed continental shale logging data and the types and contents of clay minerals in shale development are divided into training set and test set. The training set is input into the BP neural network model for training. During the training process, the BP neural network model is adjusted by the back propagation algorithm.
[0022] In the above method, optionally, the specific content of the back propagation algorithm is:
[0023] It includes 1 input layer, multiple hidden layers and 1 output layer. The formula for forward propagation is:
[0024]
[0025] Among them, z j is the net output value of the jth node, w ij is the weight value between the i-th node and the j-th node, x i is the input value of the i-th node, bj is the threshold of the jth node, M is the number of nodes in the input layer, x j is the output value of the jth node, f(z j ) is the sigmoid activation function;
[0026] The formula for back propagation is:
[0027]
[0028] Among them, E is the loss function, N is the number of nodes in the output layer, and y j is the label value of the jth node.
[0029] The above method may optionally include predicting the development of clay minerals in continental shale using an optimized prediction model of clay mineral development based on artificial intelligence, and the specific contents are as follows:
[0030] By comparing the predicted results with the actual observed values, the accuracy and reliability of the artificial intelligence-based clay mineral development prediction model are evaluated. If the prediction results are not ideal, we return to the optimization steps of the artificial intelligence-based clay mineral development prediction model for adjustment.
[0031] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a prediction method for the development of continental shale clay minerals based on well logging artificial intelligence learning, which has the following beneficial effects:
[0032] 1) It improves the accuracy and efficiency of prediction and can quickly provide valuable information for the exploration and development of continental shale;
[0033] 2) Reduce the cost and time consumption of traditional methods and avoid the complicated laboratory analysis process;
[0034] 3) Based on a large amount of actual logging data and advanced artificial intelligence algorithms, it has strong generalization ability and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0036] Figure 1 A flowchart of a method for predicting the development of continental shale clay minerals based on well logging artificial intelligence learning provided by the present invention;
[0037] Figure 2A clay mineral development prediction diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0039] See also Figure 1 As shown, the present invention discloses a method for predicting the development of continental shale clay minerals based on well logging artificial intelligence learning, comprising the following steps:
[0040] Obtain continental shale logging data and collect continental shale samples;
[0041] Carry out data preprocessing on the collected continental shale logging data;
[0042] Specifically, the collected logging data is cleaned, outliers and noise are removed, and data is standardized and normalized to improve data quality and availability.
[0043] Test continental shale samples to obtain the types and contents of clay minerals in shale development;
[0044] According to the pre-processed continental shale logging data and the types and contents of clay minerals in shale development, an artificial intelligence-based clay mineral development prediction model is constructed;
[0045] Optimize the artificial intelligence-based clay mineral development prediction model;
[0046] The development of clay minerals in continental shale is predicted through the optimized artificial intelligence-based prediction model of clay mineral development.
[0047] Furthermore, the continental shale logging data include: density, natural potential, natural gamma, sonic time difference, well diameter, deep lateral resistivity, shallow lateral resistivity, and porosity.
[0048] Furthermore, the specific contents of collecting continental shale samples are as follows:
[0049] In the shale exploration area, shale cores are selected for shale rock sampling by observing the distribution characteristics of shale.
[0050] Furthermore, the continental shale samples were tested to obtain the specific contents of the clay mineral types and contents in the shale development:
[0051] Through XRD shale mineral type test and XRD clay mineral content test, the type and content of clay minerals in shale development can be obtained.
[0052] XRD (X-ray diffraction) is a technique that uses the diffraction effect of X-rays in crystalline materials to analyze the structure of materials. When X-rays are projected into a crystal, they are scattered by the atoms in the crystal. These scattered waves are similar to spherical waves emitted from the center of the atoms. Since the atoms are arranged periodically in the crystal, there is a fixed phase relationship between these scattered spherical waves, resulting in the spherical waves in certain scattering directions reinforcing each other and canceling each other out in certain directions, resulting in diffraction.
[0053] By analyzing clay minerals with XRD technology, accurate mineral type identification results can be obtained. For example, kaolinite, montmorillonite, illite, etc. are common types of clay minerals, and their X-ray diffraction patterns have characteristic peak positions and peak shapes. By analyzing the experimental data, these different types of clay minerals can be clearly distinguished.
[0054] Furthermore, the specific contents of constructing the clay mineral development prediction model based on artificial intelligence are as follows:
[0055] The preprocessed continental shale logging data and the types and contents of clay minerals in shale development are divided into training set and test set. The training set is input into the BP neural network model for training. During the training process, the BP neural network model is adjusted by the back propagation algorithm.
[0056] Furthermore, the specific content of the back propagation algorithm is:
[0057] It includes 1 input layer, multiple hidden layers and 1 output layer. The formula for forward propagation is:
[0058]
[0059] Among them, z j is the net output value of the jth node, w ij is the weight value between the i-th node and the j-th node, x i is the input value of the i-th node, b j is the threshold of the jth node, N is the number of input layer nodes, x j is the output value of the jth node, f(z j ) is the sigmoid activation function;
[0060] The formula for back propagation is:
[0061]
[0062] Among them, E is the loss function, N is the number of nodes in the output layer, and yj is the label value of the jth node.
[0063] Specifically, the cross-validation method is adopted to avoid as much as possible the situation where the constructed model is not an optimal solution caused by randomly selecting data at one time, and to improve the generalization ability of the prediction model.
[0064] Furthermore, the specific contents of predicting the development of clay minerals in continental shale by using the optimized prediction model of clay mineral development based on artificial intelligence are as follows:
[0065] By comparing the predicted results with the actual observed values, the accuracy and reliability of the artificial intelligence-based clay mineral development prediction model are evaluated. If the prediction results are not ideal, we return to the optimization steps of the artificial intelligence-based clay mineral development prediction model for adjustment.
[0066] In a specific embodiment, the well logging data of continental shale in a certain area is obtained and continental shale samples are collected; data preprocessing is performed on the collected continental shale logging data; the continental shale samples are tested to obtain the types and contents of clay minerals in shale development; an artificial intelligence-based clay mineral development prediction model is constructed according to the preprocessed continental shale logging data and the types and contents of clay minerals in shale development; the artificial intelligence-based clay mineral development prediction model is optimized; the development of clay minerals in continental shale is predicted by the optimized artificial intelligence-based clay mineral development prediction model, and the amount prediction diagram of illite-montmorillonite mixed layer, illite, kaolinite, and chlorite can be found in Figure 2 shown.
[0067] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0068] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A prediction method for the development of continental shale clay minerals based on well logging artificial intelligence learning, characterized in that: The following steps are involved: Obtain continental shale logging data and collect continental shale samples; Carry out data preprocessing on the collected continental shale logging data; Test continental shale samples to obtain the types and contents of clay minerals in shale development; According to the pre-processed continental shale logging data and the types and contents of clay minerals in shale development, an artificial intelligence-based clay mineral development prediction model is constructed; Optimize the artificial intelligence-based clay mineral development prediction model; The development of clay minerals in continental shale is predicted through the optimized artificial intelligence-based prediction model of clay mineral development.
2. The method for predicting the development of continental shale clay minerals based on well logging artificial intelligence learning according to claim 1 is characterized in that: Continental shale logging data include: density, natural potential, natural gamma, acoustic time difference, well diameter, deep lateral resistivity, shallow lateral resistivity, and porosity.
3. The method for predicting the development of continental shale clay minerals based on well logging artificial intelligence learning according to claim 1 is characterized in that: The specific contents of collecting continental shale samples are as follows: In the shale exploration area, shale cores are selected for shale rock sampling by observing the distribution characteristics of shale.
4. The method for predicting the development of continental shale clay minerals based on well logging artificial intelligence learning according to claim 1, characterized in that: The specific contents of testing the continental shale samples and obtaining the types and contents of clay minerals in the shale development are as follows: Through XRD shale mineral type test and XRD clay mineral content test, the type and content of clay minerals in shale development can be obtained.
5. The method for predicting the development of clay minerals in continental shale based on well logging artificial intelligence learning according to claim 1, characterized in that: The specific contents of constructing the clay mineral development prediction model based on artificial intelligence are as follows: The preprocessed continental shale logging data and the types and contents of clay minerals in shale development are divided into training set and test set. The training set is input into the BP neural network model for training. During the training process, the BP neural network model is adjusted by the back propagation algorithm.
6. The method for predicting the development of clay minerals in continental shale based on well logging artificial intelligence learning according to claim 5, characterized in that: The specific content of the back propagation algorithm is: It includes 1 input layer, multiple hidden layers and 1 output layer. The formula for forward propagation is: Among them, z j is the net output value of the jth node, w ij is the weight value between the i-th node and the j-th node, x i is the input value of the i-th node, b j is the threshold of the jth node, M is the number of nodes in the input layer, x j is the output value of the jth node, f(z j ) is the sigmoid activation function; The formula for back propagation is: Among them, E is the loss function, N is the number of nodes in the output layer, and y j is the label value of the jth node.
7. The method for predicting the development of continental shale clay minerals based on well logging artificial intelligence learning according to claim 1, characterized in that: The specific contents of predicting the development of clay minerals in continental shale by using the optimized prediction model of clay mineral development based on artificial intelligence are as follows: By comparing the predicted results with the actual observed values, the accuracy and reliability of the artificial intelligence-based clay mineral development prediction model are evaluated. If the prediction results are not ideal, we return to the optimization steps of the artificial intelligence-based clay mineral development prediction model for adjustment.