Well logging while drilling curve self-adaptive scale coarsening method

Abstract

The invention discloses an adaptive scale coarsening method for a logging-while-drilling curve, and belongs to the field of logging-while-drilling data processing in exploration and development of petroleum and natural gas. The method comprises the steps that intelligent analysis is conducted on the logging curve through a deep learning technology, and a coarsening strategy is dynamically adjusted; therefore, collaborative optimization of data dimension reduction, noise filtering and key geological feature reservation is realized. The method is suitable for multiple scenes such as intelligent steerable drilling, reservoir parameter calculation, three-dimensional geological modeling and well-to-seismic joint inversion, and relates to the technical fields of signal processing, deep learning and geological data analysis. The cross fusion of the fields makes the self-adaptive coarsening of the logging curve possible, and lays a technical foundation for improving the logging data processing efficiency and the geological interpretation precision.

Description

Technical Field

[0001] The present invention belongs to the field of logging-while-drilling data processing in oil and gas exploration and development, and particularly relates to a method for adaptively scaling coarsening of logging-while-drilling curves. Background Art

[0002] Logging technology is an indispensable means in oil and gas exploration and development. By recording the changes in formation physical parameters, high-resolution logging curves are generated, providing core data support for reservoir evaluation, geological modeling, and oil and gas development. However, with the progress of modern logging instruments, the sampling resolution of logging data has been significantly improved, and the common sampling interval can reach the centimeter level or even the millimeter level. For example, an array acoustic logging tool can generate hundreds of data points per unit depth. While this high-resolution data provides rich geological information, it also poses significant challenges: a large amount of data, high storage requirements, and increased computational complexity. Especially in real-time drilling monitoring, large-scale reservoir simulation, or joint analysis of multi-well data, traditional processing methods are difficult to meet the dual requirements of efficiency and accuracy.

[0003] The limitations of traditional methods are mainly reflected in the following aspects: (1) Insufficient resolution matching: Fixed coarsening strategies cannot flexibly adjust according to the resolution differences of logging curves, resulting in information loss in high-resolution regions or redundancy in low-resolution regions. (2) Unintelligent noise processing: Logging data often contains instrument noise, formation heterogeneity interference, etc., and traditional filtering is difficult to distinguish noise from geological signals. (3) Geological information loss: Fixed coarsening provides insufficient protection for geological features, affecting the geological interpretation value of the coarsened data. (4) Lack of adaptability: Different application scenarios have different requirements for coarsening resolution, and traditional methods require manual parameter adjustment, resulting in low efficiency. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method for adaptively scaling coarsening of logging-while-drilling curves, including: preprocessing the original logging curve, including outlier processing, missing value imputation, sampling point alignment, normalization, adaptive slicing, filling, and masking, and dividing the processed data into a training set and a test set; using a multi-layer one-dimensional convolutional network to extract a preliminary feature sequence, calculating global dependencies through the self-attention mechanism of the Transformer to generate a global feature representation, and dynamically adjusting the convolutional kernel parameters of the one-dimensional convolutional network; training the model using the training set and testing the trained model using the test set; inputting the logging data to be coarsened after preprocessing into the model to generate an importance scoring vector; determining coarsening parameters according to the importance scoring vector, including the downsampling rate and smoothing intensity; coarsening the preprocessed logging curve according to the coarsening parameters, including downsampling and smoothing, and restoring the physical dimension to generate a final coarsened curve.

[0005] Preferably, the process of adaptive slicing includes: calculating the local variance feature of the logging curve to determine the signal resolution; dynamically adjusting the slice length through linear mapping based on eigenvalues, using a shorter segmentation length in the high-resolution region and a longer segmentation length in the low-resolution region; traversing the data in depth order, slicing according to the dynamic slice length, and marking the starting depth of each segment.

[0006] Preferably, the process of padding and masking includes: setting the maximum slice length, padding the slices shorter than this length, and using a special value -1 for the padding value; generating a mask tensor for each slice, marking the actual data points as 1 and the padding points as 0.

[0007] Preferably, during the process of using a multi-layer one-dimensional convolutional network to extract the preliminary feature sequence, the mask is applied to calculate only at the positions where the mask value is 1.

[0008] Preferably, when calculating the global dependencies through the self-attention mechanism of the Transformer, an attention mask is used to ignore the padding positions; the Transformer generates weights through the Gumbel-Softmax function to dynamically adjust the convolutional kernel parameters of the one-dimensional convolutional network.

[0009] Preferably, the process of determining the coarsening parameters according to the importance scoring vector includes: using the Sigmoid function to map the importance score to the downsampling rate; using a linear method to map the importance score to the smoothing intensity to complete the generation of the coarsening parameters.

[0010] Preferably, the steepness parameter, threshold, and user influence parameter of the Sigmoid function are adjusted according to geological requirements; the user influence parameter of the linear method is adjusted according to geological requirements.

[0011] Preferably, the process of coarsening the preprocessed logging curve according to the coarsening parameters includes: downsampling the preprocessed logging curve according to the downsampling rate to obtain the downsampled point set and the corresponding depth; smoothing the downsampled point set using mean filtering with an intensity equal to the smoothing intensity; and anti-normalizing the smoothed point set to restore the physical dimension to generate the final coarsened curve.

[0012] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computing program stored in the memory and executable on the processor. When the processor executes the computing program, the method is implemented.

[0013] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method is implemented.

[0014] Compared with the prior art, the present invention has the following advantages and technical effects: The present invention provides a method for adaptively scaling and coarsening logging-while-drilling curves, which has significant technical advantages compared with traditional logging curve coarsening methods. First, by slicing the high- and low-resolution characteristic sections of the logging curve at different lengths, and performing slice completion and position masking. Then, by extracting the local features of the logging curve through a one-dimensional convolutional neural network and combining the global dependency modeling of the Transformer model, it can dynamically identify high-importance regions and low-importance regions in the data, and then map them to coarsening parameters that can be adaptively adjusted, avoiding the problem of key feature loss caused by traditional fixed-rule coarsening methods. Second, the Transformer optimizes the convolutional kernel parameters through the self-attention mechanism, further improving the accuracy and adaptability of feature extraction, making the coarsening process more in line with the actual geological characteristics of logging data. In addition, this algorithm supports users to adjust the input influence parameters according to specific needs and further optimize the coarsening effect through manual intervention, with high flexibility and practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings: Figure 1 is a schematic flowchart of the method according to an embodiment of the present invention; Figure 2 is a flowchart of model training according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the drawings and combine the embodiments to detail this application.

[0017] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0018] Embodiment 1: As Figure 1 - Figure 2 shown, this embodiment provides a method for adaptively scaling and coarsening logging-while-drilling curves, including: Preprocess the original logging curves, including outlier handling, missing value imputation, sampling point alignment, normalization, adaptive slicing, padding, and masking, and divide the processed data into a training set and a test set; use a multi-layer one-dimensional convolutional network to extract preliminary feature sequences, and calculate global dependencies through the self-attention mechanism of the Transformer to generate global feature representations, while dynamically adjusting the convolutional kernel parameters of the one-dimensional convolutional network; use the training set to train the model and the test set to test the trained model; input the logging data to be coarsened into the model after preprocessing to generate an importance scoring vector; determine the coarsening parameters according to the importance scoring vector, including the downsampling rate and the smoothing intensity; coarsen the preprocessed logging curves according to the coarsening parameters, including downsampling and smoothing, and restore the physical dimension to generate the final coarsened curve.

[0019] S1: Logging curve data processing.

[0020] S11: Perform preliminary cleaning on the input original logging curves, identify and handle outliers.

[0021] S12: For possible missing values or non-uniform sampling problems in the logging curves, use interpolation methods to fill in the missing data and align the sampling points. The interpolation formula is: ; where z is the depth, x(z) is the value of the interpolation point, z 1 、z 2 are the depths of adjacent sampling points.

[0022] S13: Normalize the cleaned and aligned logging curves, map the data value range to [0,1], and eliminate the differences in different physical dimensions. The min-max normalization formula is: ; where x is the original data value, x' is the normalized value, min(x) and max(x) are the minimum and maximum values of the data respectively.

[0023] S14: Perform adaptive slicing on the logging curves according to the signal characteristics to adapt to different resolution characteristics - use a shorter segmentation length in the high-resolution region and a longer segmentation length in the low-resolution region. Determine the signal resolution by calculating the local variance characteristics of the local signal, and use a window size W of 20. The calculation formula is: ; where, is the local variance of the data points, W is the size of the local window, is the value of the data points within the window, is the mean of the data points within the window.

[0024] Dynamically adjust the slice length through linear mapping based on the eigenvalue, and set the maximum slice length to 50. The mapping rule is: ; where Segment_length is the slice length of the data point in the section, is the local variance.

[0025] Finally, traverse the data in depth order, and perform slicing according to the dynamic slice length. Mark the starting depth for each segment and record it as , where is the m-th slice.

[0026] S15: Perform padding and masking on slices of different lengths to unify the input shape. Set the same maximum slice length as in S14. Pad the slices shorter than this length with a special value "-1" that has nothing to do with the curve value to distinguish the actual data from the padded part. Generate a mask tensor for each slice, marking the actual data points as 1 and the padded points as 0. For example: for a slice of length 10, pad it to 50 points, , (the first 10 are 1 and the last 40 are 0).

[0027] S16: Divide the processed data into a training set and a test set in a ratio of 70% and 30% to prepare for subsequent model training and evaluation.

[0028] S2: Coarse model training and use.

[0029] S21: Use a multi-layer one-dimensional convolutional network to extract the preliminary feature sequence. Initialize the size and number of convolutional kernels, and input the padded slices and masks into the one-dimensional convolutional network. The one-dimensional convolutional network applies the mask during the convolutional operation and only calculates at the positions where the mask value is 1 to ensure that the padded value does not affect feature extraction, and generates the preliminary feature sequence.

[0030] S22: Calculate the global dependencies based on the preliminary feature sequence through the self-attention mechanism of the Transformer, and ignore the padded positions through the attention mask to generate the preliminary global feature representation. Based on the preliminary global features, the Transformer learns the optimal size and number of convolutional kernels and generates weights through the Gumbel-Softmax function. Gumbel-Softmax is a differentiable approximation method specifically designed for discrete choice problems. By introducing Gumbel noise and temperature parameter τ, the discrete choice is approximated as a continuous probability distribution, and its formula is: ; where , , where τ is the temperature parameter, is the original probability of the category.

[0031] Feed these weights back to S21 to dynamically adjust the convolutional kernel parameters of the one-dimensional convolutional network.

[0032] S23: The one-dimensional convolution uses the optimized convolutional kernel to perform convolution operation on the input data again, and outputs the final feature sequence.

[0033] S24: The Transformer adds positional encoding to the final feature sequence again, and generates an importance scoring vector for each section through the self-attention mechanism, which is used for subsequent coarsening parameter adjustment.

[0034] S25: Use the training set divided by S1 to train the model and optimize the parameters of the convolutional network and the Transformer. Use the test set divided by S1 to test the trained model. Verify the performance of the model on unseen data through evaluation metrics.

[0035] S26: Input the well logging data to be recognized into the model after being processed by the preprocessing steps in S1, and generate an importance scoring vector for use in the third step S3.

[0036] S3: Receive the importance scoring vector from S26 , and map it to the coarsening parameters of the well logging curve. First, determine the scoring granularity. Through uniform distribution, expand the importance scoring to the level of each data point within the section. Use the Sigmoid function to map the downsampling rate. The formula is: ; where, is the minimum value of the downsampling rate, set to 0.2, is the maximum value of the downsampling rate, set to 0.9, is the importance scoring of the i-th point, k is the steepness parameter of the Sigmoid function, set to 10, is the threshold of the Sigmoid, set to 0.5, is the user influence parameter, which controls the conservativeness of the retention probability. The user can input an appropriate influence parameter according to geological requirements, and the default value is 1. A high corresponds to a high to retain more points, and a low corresponds to a low to greatly compress.

[0037] Use a linear method to map the smoothing intensity. The formula is: ; Among them, is the minimum value of the smoothing intensity, set to 3, is the maximum value of the smoothing intensity, set to 15, is the user influence parameter, which controls the conservativeness of the smoothing intensity, and the default value is 1. A high corresponds to a small to retain details, and a low corresponds to a large to increase smoothing.

[0038] S4: Coarsen the preprocessed well logging curve to be measured based on the coarsening parameter in S3. First, according to perform downsampling to obtain the set of points after downsampling and the corresponding depth . Secondly, perform smoothing on , use mean filtering, and the intensity is . Calculate the mean value of the retained points in the neighborhood of each point to obtain the smoothed set of points . Then, is anti-normalized to restore the physical dimension to generate the final coarsened curve. The formula is: ; where x is the original data value, x' is the normalized value, and min(x) and max(x) are the minimum and maximum values of the data respectively.

[0039] The above is only the preferred specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in this application should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A method for adaptively scaling a while-drilling logging curve, characterized in that: include: The original logging curve is preprocessed, including outlier processing, missing value interpolation, sampling point alignment, normalization, adaptive slicing, padding and masking, and the processed data is divided into training set and test set; a multi-layer one-dimensional convolutional network is used to extract the preliminary feature sequence, and the global dependency is calculated through the self-attention mechanism of Transformer to generate the global feature representation, and the convolution kernel parameters of the one-dimensional convolutional network are dynamically adjusted; the model is trained with the training set, and the trained model is tested with the test set; the logging data to be coarsened is input into the model after preprocessing to generate the importance score vector; the coarsening parameters, including the downsampling rate and the smoothing strength, are determined according to the importance score vector; the preprocessed logging curve is coarsened according to the coarsening parameters, including downsampling and smoothing, and the physical dimension is restored to generate the final coarsening curve.

2. The method according to claim 1, characterized in that The process of adaptive slicing includes: calculating the local variance characteristics of the logging curve to determine the signal resolution; dynamically adjusting the slice length through linear mapping based on the characteristic value, using a shorter segment length in the high-resolution area and a longer segment length in the low-resolution area; traversing the data in depth order, dividing it according to the dynamic slice length, and marking the starting depth of each segment.

3. The method according to claim 1, characterized in that The process of padding and masking includes: setting a maximum slice length, padding slices shorter than the length, and using a special value -1 as the padding value; generating a mask tensor for each slice, marking the actual data points as 1 and the padding points as 0.

4. The method according to claim 1, characterized in that: In the process of extracting the preliminary feature sequence using the multi-layer one-dimensional convolutional network, a mask is applied to calculate only the positions where the mask value is 1.

5. The method according to claim 1, characterized in that When calculating the global dependency through the self-attention mechanism of the Transformer, the padding position is ignored using the attention mask; the Transformer generates weights through the Gumbel-Softmax function and dynamically adjusts the convolution kernel parameters of the one-dimensional convolutional network.

6. The method according to claim 1, characterized in that The process of determining the coarsening parameter according to the importance score vector includes: using a Sigmoid function to map the importance score to a downsampling rate; using a linear method to map the importance score to a smoothing intensity, thereby completing the generation of the coarsening parameter.

7. The method according to claim 6, characterized in that The steepness parameter, threshold value and user influence parameter of the Sigmoid function are adjusted according to geological requirements; the user influence parameter of the linear method is adjusted according to geological requirements.

8. The method according to claim 1, characterized in that: The process of coarsening the preprocessed logging curve according to the coarsening parameters includes: downsampling the preprocessed logging curve according to the downsampling rate to obtain the downsampled point set and the corresponding depth; smoothing the downsampled point set, using mean filtering, and the intensity is the smoothing intensity; denormalizing the smoothed point set to restore the physical dimension to generate the final coarsening curve.

9. An electronic device comprising a memory, a processor, and a computing program stored in the memory and executable on the processor, characterized in that: When the processor executes the computing program, the method described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method described in any one of claims 1 to 8 is implemented.

Images