A Well Logging Image Filling Method and System Based on Attention Mechanism-Constrained Encoder-Decoder Architecture

Abstract

This invention provides a well logging image filling method and system with an attention-constrained encoder-decoder architecture. The method acquires multiple well logging electrical imaging images with repair needs based on well logging data, preprocesses them to obtain the images to be repaired, and then inputs the images to be repaired and their corresponding mask images into a pre-constructed image filling network model. Based on the constraints of the attention mechanism, selective decoding processing is performed on the encoded image data to be repaired, achieving accurate filling of blank bars in the well logging electrical imaging images. Compared with conventional deep learning network models, this scheme connects the convolutional combination layers of the encoder and decoder within the network, allowing pixel-level feature information contained in the lower layers of the encoder network to be transmitted to the decoder. By combining the features of each layer of the encoder, it can take into account both global and local predictions. Combined with different attention constraints of the attention mechanism, it can efficiently and accurately fill multiple well logging image data.

Description

Technical Field

[0001] This invention relates to the field of well logging data interpretation and processing technology, and in particular to a well logging image filling method and system based on an attention mechanism-constrained encoder-decoder architecture. Background Technology

[0002] Electrical imaging logging has been widely used in well logging evaluation of complex reservoirs such as carbonate rocks, conglomerate, and igneous rocks, playing a crucial role in calculating porosity, identifying fractures, and classifying lithology. However, in large-diameter wells, electrical imaging images cannot achieve full wellbore coverage, inevitably resulting in blank bands on the images. To ensure the accuracy of subsequent logging processing and interpretation, it is necessary to fill these blank bands.

[0003] The currently used blank strip filling method is mainly based on the Filtersim algorithm of multi-point geostatistics. However, in areas with complex texture structures, the bedding continuity after filling is not strong, and the filling effect cannot be well obtained.

[0004] With the development of deep learning, it has gradually become an important research direction in fields such as computer data processing and speech recognition. However, deep learning algorithms often require large-scale training samples, and for electrical imaging logging, obtaining a large amount of real wellbore image data is difficult to implement in practice. Based on this, existing researchers have studied corresponding filling schemes for single-image electrical logging images. They utilize the idea that deep neural network structures can capture sufficient prior information of image statistics, and achieve blank strip filling of single-image electrical logging images by constructing an encoder-decoder network model. However, this method uses a conventional encoder-decoder architecture, which is highly dependent on massive prior information. Furthermore, it directly uses the feature map obtained from the top layer of the encoder network as the input of the decoder network. Such feature maps contain high-level features that remain unchanged for small changes. For dense image processing tasks such as image filling that require precise pixel information, important relationships may be abstracted, failing to effectively reflect the required feature information. This is not conducive to the deep learning network model's understanding of image details, thus making it difficult to effectively and accurately fill images.

[0005] The information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or implication in any way that such information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] To address the above problems, this invention provides a well logging image filling method based on an attention mechanism-constrained codec architecture. In one embodiment, the method includes:

[0007] The steps for obtaining the filling object are as follows: Based on the logging data, obtain the logging electrical imaging image with repair needs, and use it as the image to be repaired after preprocessing;

[0008] The filling implementation steps involve inputting the image to be repaired, along with the corresponding mask image and random noise image, into a pre-constructed image filling network model. The image filling network model then encodes and selectively decodes the data of the image to be repaired based on a preset network depth to obtain a filled logging image.

[0009] The image filling network model is constructed through a model building step based on a network of multi-convolutional combined layer encoder and multi-convolutional combined layer decoder. The encoder layers are connected to the decoder layers through a connection strategy with attention mechanism constraints.

[0010] In a preferred embodiment, the preprocessing of the well logging electrical imaging image includes:

[0011] The logging electrical imaging image is processed into a sub-logging image that meets the set size requirements;

[0012] Noise reduction and grayscale processing were performed on each sub-logging image;

[0013] A mask image is generated from the grayscale image to be repaired.

[0014] Furthermore, in one embodiment, the preprocessing of the well logging electrical imaging image further includes:

[0015] Priority labels are assigned to each sub-logging image based on the acquisition time and logging conditions of each logging electrical imaging image.

[0016] In one embodiment of this application, during the construction of the image filling network model,

[0017] The multi-convolutional combined layer encoder is configured such that the convolutional layers from shallow to deep are connected by a downsampling method;

[0018] The multi-convolutional combination layer decoder is configured such that the convolutional layers from shallow to deep are connected by upsampling; each convolutional combination layer, which has convolutional layers and activation layers, also includes a batch normalization operation layer.

[0019] In one specific embodiment, during the model building step, skip connections are introduced between the encoder and the decoder, connecting each convolutional combination layer of the encoder to the decoder and its corresponding convolutional combination layer.

[0020] Furthermore, in one embodiment, an attention mechanism module is introduced into the skip connection stage, employing cascaded channel attention mechanisms and / or spatial attention mechanisms to selectively extract features from the output of the connected encoder convolutional layers.

[0021] In an optional embodiment, an attention mechanism module is introduced into the skip connection stage, employing parallel channel attention and / or spatial attention mechanisms to selectively extract features from the output of the connected encoder convolutional layers.

[0022] Specifically, in one embodiment, during the infilling implementation step, the image infilling network model processes the output information of the i-th convolutional combination layer of the encoder as follows:

[0023] The output of the corresponding downsampling layer is used as the input of the (i+1)th combination layer after processing by the corresponding downsampling layer.

[0024] Simultaneously, the output of the i-th convolutional combination layer of the encoder is extracted and processed through the attention mechanism module.

[0025] The output of the attention mechanism module is added to or multiplied by the output of the (i+1)th combination layer in the decoder and used as the input of the ith combination layer in the decoder.

[0026] In the claimed embodiment of this invention, the process of constructing the image filling network model further includes:

[0027] The parameter optimization steps are as follows: a 2-channel grid grayscale image of the same size as the image to be repaired is input into the constructed image filling network model, the output of the model is obtained and compared with the electrical logging image to be repaired, and the parameters of the model are optimized, trained and updated using an optimization algorithm with backpropagation of error. The optimization algorithm is repeated until the set requirements are met, and the current image filling network model is used as the target image filling network model for application.

[0028] Based on other aspects of the methods described in any one or more of the above embodiments, the present invention also provides a well logging image filling system with an attention mechanism constrained codec architecture, characterized in that the system performs the methods described in any one or more of the above embodiments.

[0029] Compared with the closest prior art, the present invention also has the following beneficial effects:

[0030] The present invention provides a well logging image filling method and system with an attention mechanism constrained codec architecture. After obtaining multiple well logging electrical imaging images with repair needs based on well logging data, the method preprocesses them to ensure the balance of the model input image data and avoid noise data information affecting the timeliness and reliability of the filling process.

[0031] In addition, the model for implementing the filling operation in this invention adopts a deep learning network that connects each layer of the encoder to each layer of the decoder by setting a connection strategy. This overcomes the drawback of the prior art that only uses the top feature map data of the encoder network. It utilizes the pixel-level feature information contained in the bottom layer of the encoder network and combines the features of each layer of the encoder for application, which can take into account both global prediction and local prediction.

[0032] Furthermore, the present invention introduces an attention mechanism constraint in the connection link, which enables selective processing of encoder output feature data. While ensuring the reliability of the filling results, it also takes into account the timeliness of processing, which helps to provide strong support for the subsequent application and analysis of well logging data.

[0033] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0034] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0035] Figure 1 This is a schematic diagram illustrating the principle of a deep learning network model used in the prior art, as provided in this embodiment of the invention.

[0036] Figure 2 This is a schematic diagram illustrating the implementation flow of a well logging image filling method based on an attention mechanism-constrained codec architecture provided in an embodiment of the present invention.

[0037] Figure 3 This is a schematic diagram of the network model used in the well logging image filling method based on the attention mechanism constrained encoder-decoder architecture in this embodiment of the invention.

[0038] Figure 4 This is a schematic diagram illustrating the operational principle of the attention mechanisms applied in different modes provided in the embodiments of the present invention;

[0039] Figure 5 This is a schematic diagram of the cascaded mode attention mechanism applied in the well logging image filling method of the attention mechanism constrained codec architecture according to another embodiment of the present invention;

[0040] Figure 6 This is a schematic diagram of the well logging image filling system with an attention mechanism-constrained encoder-decoder architecture provided in an embodiment of the present invention. Detailed Implementation

[0041] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples. Those skilled in the art will then fully understand how the present invention uses technical means to solve technical problems and achieve technical effects, and will be able to implement the present invention specifically based on the above-described implementation process. It should be noted that, as long as there is no conflict, the various embodiments and features of the present invention can be combined with each other, and the resulting technical solutions are all within the protection scope of the present invention.

[0042] Although the flowchart describes the operations as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. The order of the operations can be rearranged. A process can terminate when its operation is complete, but it may also have additional steps not included in the diagram. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0043] Computer equipment includes user equipment and network equipment. User equipment or clients include, but are not limited to, computers, smartphones, PDAs, etc.; network equipment includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Computer equipment can operate independently to implement this invention, or it can connect to a network and implement this invention through interaction with other computer equipment in the network. The network in which the computer equipment is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, VPN network, etc.

[0044] The terms “first,” “second,” etc., may be used herein to describe various units, but these units should not be limited by these terms; they are used merely to distinguish one unit from another. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. When a unit is referred to as “connected” or “coupled” to another unit, it may be directly connected or coupled to said other unit, or there may be intermediate units present.

[0045] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms “a” and “an” as used herein are also intended to include the plural. It should also be understood that the terms “comprising” and / or “including” as used herein specify the presence of the stated features, integers, steps, operations, units, and / or components, without excluding the presence or addition of one or more other features, integers, steps, operations, units, components, and / or combinations thereof.

[0046] In practical applications, for large-diameter wells, electrical imaging logging images cannot achieve full wellbore coverage, resulting in blank bands on the images. To ensure the accuracy of subsequent logging processing and interpretation, it is necessary to fill these blank bands.

[0047] The current mainstream blank strip filling method is based on the Filtersim algorithm of multi-point geostatistics. However, in areas with complex texture structures, the bedding continuity after filling is not strong, and the filling effect cannot be well obtained.

[0048] Deep learning has become a research hotspot in computer vision, image processing, and speech recognition. However, conventional deep learning algorithms require a large number of training samples, which is impractical for electrical logging imaging, as obtaining a large amount of real wellbore images is unrealistic. Wang Zhefeng et al. utilized the idea that deep neural network structures can capture a large amount of prior statistical information about images, and constructed an encoder-decoder network model to achieve blank strip filling in single electrical logging images. A simplified diagram of the filling principle is attached. Figure 1 As shown, this method employs a conventional encoder-decoder architecture, meaning it does not utilize the precise pixel-level information contained in the lower layers of the encoder network. Instead, it uses only the feature map obtained from the top layer of the encoder network as input to the decoder network. While this feature map contains high-level features that are invariant to small changes, this invariance is crucial for some high-level tasks (such as object recognition). However, it is not ideal for dense image processing tasks like image filling, which require precise pixel information. This is because important relationships may be abstracted away, hindering the network's understanding of image details and thus impeding effective and accurate image filling.

[0049] To address the aforementioned issues, this invention provides a well logging image filling method and system based on an attention-constrained encoder-decoder architecture. The solution provided by this invention is implemented through an end-to-end model, based on an encoder-decoder deep learning network model constrained by an attention mechanism. The input consists of a random noise image, a well logging electrical imaging image with blank stripes, and a mask image. The output is automatically filled complete well logging electrical imaging image data.

[0050] The following describes the detailed flow of the method according to an embodiment of the present invention with reference to the accompanying drawings, the steps of which can be executed in a computer system containing, for example, a set of computer-executable instructions. Although the logical order of the steps is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0051] Example 1

[0052] Figure 2This diagram illustrates a flow chart of the well logging image filling method based on the attention mechanism-constrained codec architecture provided in Embodiment 1 of the present invention. (Refer to...) Figure 2 As can be seen, the method includes the following steps.

[0053] Steps for obtaining filling targets: Based on well logging data, obtain well logging electrical imaging images that require repair, and use them as images to be repaired after preprocessing;

[0054] The filling implementation steps are as follows: The image to be repaired, combined with the corresponding mask image and random noise image, is input into a pre-constructed image filling network model. The image filling network model encodes and selectively decodes the data of the image to be repaired based on a preset network depth to obtain a filled logging image.

[0055] The image filling network model is constructed through a model building step based on a network of multi-convolutional combined layer encoder and multi-convolutional combined layer decoder. The encoder layers are connected to the decoder layers through a connection strategy with attention mechanism constraints.

[0056] Based on the above logic, an end-to-end image filling network model can be used to efficiently and reliably fill blanks in well logging image data to be repaired. When processing the input image data, the image filling network model selectively decodes the encoder output information, overcoming the defect of excessive data volume. It selects only the set effective feature data for processing, ensuring the accuracy of the filling result while improving the efficiency and practicality of data processing.

[0057] Furthermore, considering the uneven scale of well logging electrical imaging image data in the well logging data, and the large amount of data per unit file, in order to ensure the balance of data processing in the filling implementation step, the collected well logging electrical imaging image data is preprocessed based on the following aspects before filling: (1) equalize the image size and filter out invalid data; (2) reduce noise and pixel grayscale processing; (3) generate a mask image from the grayscale image to be repaired, so as to avoid the impact of the imbalance of input data and interference signals on the selective processing of image features, which would reduce the processing timeliness.

[0058] Therefore, in one embodiment, the process of preprocessing the well logging electrical imaging image includes:

[0059] The logging electrical imaging image is processed into a sub-logging image that meets the set size requirements;

[0060] Noise reduction and grayscale processing were performed on each sub-logging image;

[0061] A mask image is generated from the grayscale image to be repaired.

[0062] In practical applications, the mask image is usually extracted from the blank stripe portion of the well logging electrical imaging image. Specifically, the RGB pixel values ​​of the blank stripe portion of the grayscale electrical imaging image are set to (0, 0, 0), and the image pixel values ​​of the non-blank stripe portion are set to (255, 255, 255), thus generating the mask image of the well logging image.

[0063] Furthermore, the researchers of this invention considered that well logging image data from different regions or operating conditions inevitably have varying degrees of urgency. For example, for well logging image data at risk of failure, the earlier the backfilling process is performed, the better it can support subsequent well logging data analysis processes and help prevent further expansion and deterioration of the failure. Therefore, it is necessary to prioritize each sub-well logging image based on its source and operating condition information. This ensures that well logging images with different levels of urgency are backfilled in an orderly manner, providing timely support for subsequent analysis and application of the well logging data.

[0064] Therefore, in a preferred embodiment, the preprocessing of the well logging electrical imaging image further includes:

[0065] Priority labels are assigned to each sub-logging image based on the acquisition time and logging conditions of each logging electrical imaging image.

[0066] This invention applies an encoder-decoder deep learning network model to fill blank stripes in well logging electrical imaging images. Considering the technical problems of existing single-image well logging processing schemes based on deep learning networks, and to overcome their dependence on massive amounts of prior statistical information from images, this invention designs an encoder-decoder deep learning network model based on an attention mechanism constraint, which is an improvement on the conventional encoder-decoder architecture. Figure 3 The diagram shows the model principle of the well logging image filling method based on the attention mechanism constrained encoder-decoder architecture in an embodiment of the present invention, as shown below. Figure 3 As shown, the neural network model used in this invention no longer uses the conventional encoder-decoder architecture to directly use the feature map obtained from the top layer of the encoder network as the input of the decoder network. Instead, it uses the precise pixel-level information contained in the bottom layer of the encoder network to process image details.

[0067] Based on the above logic, this invention uses an encoder-decoder deep learning network model to fill blank stripes in well logging electrical imaging images, and introduces skip connections between the encoder and the decoder, connecting each convolutional combination layer of the encoder to its corresponding convolutional combination layer of the decoder.

[0068] Specifically, in one embodiment, during the construction of the image filling network model,

[0069] The multi-convolutional combined layer encoder is configured such that the convolutional layers from shallow to deep are connected by a downsampling method;

[0070] The multi-convolutional combination layer decoder is configured such that the convolutional layers from shallow to deep are connected by upsampling; each convolutional combination layer, which has convolutional layers and activation layers, also includes a batch normalization operation layer.

[0071] Furthermore, in one embodiment, skip connections are introduced between the encoder and the decoder, connecting each convolutional combination layer of the encoder to the decoder and its corresponding convolutional combination layer.

[0072] In practical applications, the convolutional combination layers of the encoder are connected to their corresponding convolutional combination layers of the decoder. This can be done by connecting all the convolutional combination layers of the encoder to their corresponding convolutional combination layers of the decoder, or by connecting a limited number of convolutional combination layers from all the convolutional combination layers of the encoder to their corresponding convolutional combination layers of the decoder.

[0073] Since the lower layers of the encoder network often contain precise pixel-level information, skip connections allow this information to be passed directly to the decoder. In addition, by combining the features of each layer of the encoder, both global and local predictions can be taken into account, which helps to produce better filling results.

[0074] The encoder-decoder network model is constructed with a depth of N, typically an integer between 3 and 10. The encoder has N convolutional layer combinations, connected by downsampling from shallowest to deepest. Each convolutional layer combination includes a convolutional layer, an activation layer, and a batch normalization layer. Convolutional and activation layers are mandatory, and multiple combinations are allowed; the batch normalization layer is optional. The decoder also has N convolutional layer combinations, connected by upsampling from deepest to shallowest. Each convolutional layer combination includes a convolutional layer, an activation layer, and a batch normalization layer, where convolutional and activation layers are mandatory, and the batch normalization layer is optional.

[0075] The encoder has N convolutional layers, numbered 1, 2, ..., N from shallowest to deepest, and the decoder has M convolutional layers, numbered 1, 2, ..., M from shallowest to deepest. Usually, N = M.

[0076] For the pixel-level feature information output by each convolutional combination layer of the encoder, a set feature selection mechanism is used for recognition processing to achieve selective decoding of the encoder output features, thereby using truly useful information to fill the logging electrical imaging image. For example, an attention mechanism is introduced into the skip connection link to achieve different degrees of attention to the features of different channels of the encoder, and then the attention-constrained features are passed to the corresponding convolutional combination layer of the decoder to participate in the decoding operation.

[0077] The attention mechanism works by applying different levels of attention to different feature maps, thereby enhancing useful information while compressing useless information, thus improving the network's ability to represent target features. This attention mechanism module includes a channel attention mechanism module and a spatial attention mechanism module. The principle of the channel attention mechanism module is as follows: Figure 4 As shown, the overall idea is to process the feature map obtained from convolution to obtain a one-dimensional vector with the same number of channels as the evaluation score for each channel. This score is then applied to the corresponding channels to achieve different levels of attention for different channels. The spatial attention mechanism module extracts key information by performing corresponding spatial transformations on the spatial domain information in the image. In this invention, the two attention mechanism modules can interact as follows: Figure 5 The cascaded mode shown can also be a parallel mode. The two can be combined arbitrarily in a cascaded or parallel manner, or only one of them can be used.

[0078] Therefore, specifically, in one embodiment, an attention mechanism module is introduced into the skip connection stage, and a cascaded channel attention mechanism and / or spatial attention mechanism is used to selectively extract features from the output of the connected encoder convolutional layer;

[0079] In another alternative embodiment, an attention mechanism module is introduced into the skip connection stage, employing parallel channel attention and / or spatial attention mechanisms to selectively extract features from the output of the connected encoder convolutional layers.

[0080] Specifically, in one embodiment, during the infilling implementation step, the image infilling network model processes the output information of the i-th convolutional combination layer of the encoder as follows:

[0081] The output of the corresponding downsampling layer is used as the input of the (i+1)th combination layer after processing by the corresponding downsampling layer.

[0082] Simultaneously, the output of the i-th convolutional combination layer of the encoder is extracted and processed through the attention mechanism module.

[0083] The output of the attention mechanism module is added to or multiplied by the output of the (i+1)th combination layer in the decoder and used as the input of the ith combination layer in the decoder.

[0084] In practical applications, attention mechanism constraints are added to the encoder-decoder network model structure. The encoder has N convolutional combination layers, numbered 1, 2, ..., N from shallowest to deepest, and the decoder has M combination layers, numbered 1, 2, ..., M from shallowest to deepest. For the output of the i-th convolutional combination layer of the encoder, two operations are performed: 1. Passing it through a downsampling layer, with the output of the downsampling layer serving as the input to the (i+1)-th combination layer; 2. Passing it through an attention mechanism module or a cascaded or parallel module of two attention mechanism modules, with the output of this module added to or multiplied by the output of the (i+1)-th combination layer in the decoder, serving as the input to the i-th combination layer in the decoder.

[0085] Furthermore, during the training of the image filling network model, the actual input for training is a 2-channel grid grayscale image of the same size as the image to be repaired. To obtain the optimal model parameters, the network output is compared with the well logging electrical imaging image to be repaired at the output end to update the network parameters in reverse. Through multiple iterations, the network parameters are repeatedly updated to achieve the optimal blank strip filling effect. Therefore, in one embodiment, the process of constructing the image filling network model further includes:

[0086] The parameter optimization steps are as follows: a 2-channel grid grayscale image of the same size as the image to be repaired is input into the constructed image filling network model, the output of the model is obtained and compared with the electrical logging image to be repaired, and the parameters of the model are optimized, trained and updated using an optimization algorithm with backpropagation of error. The optimization algorithm is repeated until the set requirements are met, and the current image filling network model is used as the target image filling network model for application.

[0087] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0088] The present invention provides a method for filling blank strips in well logging electrical imaging based on an attention-constrained deep learning model. When filling blank strips in well logging electrical imaging images, an encoder-decoder deep learning network model is used. Skip connections are introduced between the encoder and decoder to connect each convolutional combination layer of the encoder to its corresponding convolutional combination layer of the decoder. Simultaneously, an attention mechanism is introduced to constrain and control the skip connections, enabling selective decoding of the encoder's output features. The input consists of a random noise image, a well logging electrical imaging image with blank strips, and a corresponding mask image. The output is a fully filled well logging electrical imaging image. The filling effect is superior to existing well logging electrical imaging blank strip filling methods.

[0089] Specifically, for the above network model structure, let the parameters of the encoder-decoder network be θ, and the input of the encoder be a random noise image z∈R. 3×H′×W′ The decoder outputs x = f, along with a well logging electrical imaging image x0 containing blank stripes and a mask image m. θ (z), the objective function is:

[0090] E(x; x0) = ||(x-x0)⊙m|| 2

[0091] Where ⊙ represents matrix dot product.

[0092] The Adam stochastic gradient descent (SGD) optimization algorithm is used for model training and parameter θ solving, where θ = argmin. θ E(f θ (z); x0), and then through backpropagation of the network model error, the network parameters are updated.

[0093] Repeat the above training process until the preset maximum number of iterations is reached or the loss function error reaches an acceptable range, and then use the obtained network parameters θ * Estimated image inpainting result x * =f θ* (z).

[0094] It should be noted that, in other embodiments of the present invention, the method can also combine one or more of the above embodiments to obtain a new attention mechanism constrained codec architecture for well logging image filling, so as to achieve accurate processing of well logging electrical imaging data.

[0095] It should be noted that, based on the methods in any one or more embodiments of the present invention described above, the present invention also provides a storage medium storing program code that can implement the methods described in any one or more embodiments. When the program code is executed by the operating system, it can implement the well logging image filling method with the attention mechanism constrained codec architecture described above.

[0096] Example 2

[0097] The methods described in detail in the above-disclosed embodiments of the present invention can be implemented using various forms of devices or systems. Therefore, based on other aspects of the methods described in any one or more of the above embodiments, the present invention also provides a well logging image filling system with an attention mechanism constrained codec architecture. This system is used to execute the well logging image filling method with an attention mechanism constrained codec architecture described in any one or more of the above embodiments. Specific embodiments are given below for detailed description.

[0098] Specifically, Figure 6 The diagram shows a schematic of the well logging image filling system based on the attention mechanism-constrained codec architecture provided in an embodiment of the present invention. Figure 6 As shown, the system includes:

[0099] The filling object acquisition module is configured to acquire well logging electrical imaging images with repair needs based on well logging data, preprocess them and use them as images to be repaired, wherein the images to be repaired contain multiple well logging image data;

[0100] The filling implementation module is configured to input the image to be repaired, along with the corresponding mask image and random noise image, into a pre-constructed image filling network model. The image filling network model encodes and selectively decodes the data of the image to be repaired based on a preset network depth to obtain a filled logging image.

[0101] The image filling network model is constructed by the model building module based on a network of multi-convolutional combined layer encoder and multi-convolutional combined layer decoder. The encoder layers are connected to the decoder layers through a connection strategy with attention mechanism constraints.

[0102] In one embodiment, the filling object acquisition module preprocesses the logging electrical imaging image through the following operations:

[0103] The logging electrical imaging image is processed into a sub-logging image that meets the set size requirements;

[0104] Noise reduction and grayscale processing were performed on each sub-logging image;

[0105] A mask image is generated based on the grayscale image to be repaired.

[0106] Furthermore, in one embodiment, the filling object acquisition module also preprocesses the logging electrical imaging image through the following operations:

[0107] Priority labels are assigned to each sub-logging image based on the acquisition time and logging conditions of each logging electrical imaging image.

[0108] Specifically, in one embodiment, the model building module is configured as follows:

[0109] The multi-convolutional combined layer encoder is configured such that the convolutional layers from shallow to deep are connected by a downsampling method;

[0110] The multi-convolutional combination layer decoder is configured such that the convolutional layers from shallow to deep are connected by upsampling; each convolutional combination layer, which has convolutional layers and activation layers, also includes a batch normalization operation layer.

[0111] Furthermore, in one embodiment, the model building module is configured to introduce skip connections between the encoder and the decoder, connecting each convolutional combination layer of the encoder to the decoder and its corresponding convolutional combination layer.

[0112] In an optional embodiment, the model building module introduces an attention mechanism module into the skip connection stage, employing a cascaded channel attention mechanism and / or spatial attention mechanism to selectively extract features from the output of the connected encoder convolutional layers.

[0113] In another optional embodiment, the model building module introduces an attention mechanism module into the skip connection stage, employing parallel channel attention and / or spatial attention mechanisms to selectively extract features from the output of the connected encoder convolutional layers.

[0114] Furthermore, in a specific embodiment, during the infilling implementation step, the image infilling network model processes the output information of the i-th convolutional combination layer of the encoder as follows:

[0115] The output of the corresponding downsampling layer is used as the input of the (i+1)th combination layer after processing by the corresponding downsampling layer.

[0116] Simultaneously, the output of the i-th convolutional combination layer of the encoder is extracted and processed through the attention mechanism module.

[0117] The output of the attention mechanism module is added to or multiplied by the output of the (i+1)th combination layer in the decoder and used as the input of the ith combination layer in the decoder.

[0118] Specifically, in one embodiment, the model building module includes:

[0119] The parameter optimization unit is configured to input a 2-channel grid grayscale image of the same size as the image to be repaired into the constructed image filling network model, obtain the output of the model and compare it with the electrical logging image to be repaired, use an optimization algorithm with backpropagation of error to optimize and update the parameters of the model, repeat the optimization algorithm until the set requirements are met, and then use the current image filling network model as the target image filling network model for application.

[0120] In the well logging image filling system with attention mechanism constrained encoder-decoder architecture provided in this embodiment of the invention, each module or unit structure can operate independently or in combination according to actual filling and processing needs to achieve the corresponding technical effects.

[0121] It should be understood that the embodiments disclosed herein are not limited to the specific structures, processing steps, or materials disclosed herein, but should be extended to equivalent substitutions of these features as understood by those skilled in the art. It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.

[0122] The phrase "an embodiment" in the specification means that a specific feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Therefore, the phrase "an embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0123] While the embodiments disclosed in this invention are as described above, the content is merely for the purpose of facilitating understanding of the invention and is not intended to limit the invention. Any person skilled in the art to which this invention pertains may make any modifications and variations in form and detail of the implementation without departing from the spirit and scope disclosed herein; however, the scope of patent protection for this invention shall still be determined by the scope defined in the appended claims.

Claims

1. A well logging image filling method with an attention mechanism-constrained encoder-decoder architecture, characterized in that, The method includes: The steps for obtaining the filling object are as follows: Based on the logging data, obtain the logging electrical imaging image with repair needs, and use it as the image to be repaired after preprocessing; The filling implementation steps involve inputting the image to be repaired, along with the corresponding mask image and random noise image, into a pre-constructed image filling network model. The image filling network model then encodes and selectively decodes the data of the image to be repaired based on a preset network depth to obtain a filled logging image. The image infilling network model is constructed through a model building step based on a multi-convolutional combined layer encoder and a multi-convolutional combined layer decoder. Specifically, a connection strategy with attention mechanism constraints connects each layer of the encoder to each layer of the decoder; skip connections are introduced between the encoder and decoder, connecting each convolutional combined layer of the encoder to its corresponding convolutional combined layer of the decoder; all convolutional combined layers of the encoder are connected to their corresponding convolutional combined layers of the decoder; and combining the features of each layer of the encoder, considering both global and local predictions, helps to produce better infilling results. The preprocessing process for well logging electrical imaging images includes: The logging electrical imaging image is processed into a sub-logging image that meets the set size requirements; Denoising and grayscale processing were performed on each sub-logging image; A mask image is generated from the grayscale image to be repaired; the blank stripe portion extracted from the well logging electrical imaging image with blank stripe is used as the corresponding mask image. Specifically, the RGB pixel values ​​of the blank stripe portion of the grayscale electrical imaging image are set to (0, 0, 0), and the image pixel values ​​of the non-blank stripe portion are set to (255, 255, 255). In the model construction step, the attention mechanism module is introduced into the skip connection stage, and parallel channel attention mechanism and / or spatial attention mechanism are used to selectively extract the features output by the connected encoder convolutional layer. In the filling implementation step, let the parameters of the encoder-decoder network be θ, and the input of the encoder be a random noise image. And well logging electrical imaging images with blank bands. and mask image The decoder output is The objective function E() is: in This represents the matrix dot product.

2. The method as described in claim 1, characterized in that, The preprocessing of well logging electrical imaging images also includes: Priority labels are assigned to each sub-logging image based on the acquisition time and logging conditions of each logging electrical imaging image.

3. The method as described in claim 1, characterized in that, In the process of constructing the image filling network model The multi-convolutional combined layer encoder is configured such that the convolutional layers from shallow to deep are connected by a downsampling method; The multi-convolutional combination layer decoder is configured such that the convolutional layers from shallow to deep are connected by upsampling; each convolutional combination layer, which has convolutional layers and activation layers, also includes a batch normalization operation layer.

4. The method as described in claim 1, characterized in that, An attention mechanism module is introduced into the skip connection stage, and a cascaded channel attention mechanism and / or spatial attention mechanism are used to selectively extract features from the output of the connected encoder convolutional layer.

5. The method as described in claim 1, characterized in that, In the infilling implementation step, the image infilling network model processes the output information of the i-th convolutional combination layer of the encoder as follows: The corresponding downsampling layer is used for processing, and the output of the downsampling layer is used as the input of the (i+1)th combination layer. Simultaneously, the output of the i-th convolutional combination layer of the encoder is extracted and processed through the attention mechanism module. The output of the attention mechanism module is added to or multiplied by the output of the (i+1)th combination layer in the decoder and used as the input of the ith combination layer in the decoder.

6. The method as described in claim 1, characterized in that, The process of constructing the image filling network model also includes: The parameter optimization steps are as follows: a 2-channel grid grayscale image of the same size as the image to be repaired is input into the constructed image filling network model, the output of the model is obtained and compared with the electrical logging image to be repaired, and the parameters of the model are optimized, trained and updated using an optimization algorithm with backpropagation of error. The optimization algorithm is repeated until the set requirements are met, and the current image filling network model is used as the target image filling network model for application.

7. A well logging image filling system with an attention mechanism-constrained encoder-decoder architecture, characterized in that, The system performs the method as described in any one of claims 1 to 6.

Images