87 results about "Curve reconstruction" patented technology

The invention discloses a submarine cable shape monitoring method based on an ultra-weak fiber bragg grating, which comprises the following steps of: obtaining curvatures # imgabs0 #, # imgabs1 # and # imgabs2 # in X-axis and Y-axis directions from curvatures in two orthogonal directions of curvatures calculated by three uniformly distributed optical fibers, representing angle offset from an ith sensing unit to an X-axis positive direction, and obtaining a bending curvature, an arc angle and a direction angle; and coordinate information in the space is further obtained by combining rotation and translation matrix iterative calculation of a shape reconstruction algorithm, namely, three-dimensional space coordinates of the measured curve can be determined point by point, and finally, complete shape reconstruction and other steps are realized. According to the invention, high-precision large-scale three-dimensional deformation monitoring can be realized. By optimizing the eccentric distance and the strain transmission efficiency of the optical fiber, the tiny deformation of the submarine cable is accurately captured, and by combining an innovative three-dimensional curve reconstruction algorithm, the bending, inclination and other deformation states of the cable can be accurately reflected in different environments. Therefore, the method has obvious advantages in a monitoring task with a high-precision requirement, especially in a complex marine environment.

The invention discloses an intelligent energy consumption distribution method for a multi-source energy system. The method comprises the steps of energy supply data fusion, dual-channel joint prediction, energy response lag correction, multi-objective optimization and intelligent energy consumption distribution. The invention relates to the technical field of data processing of power management and resource scheduling, and the method comprises the steps: carrying out the unified collection and archiving of operation control data and environment information of power grid energy, distributed photovoltaic energy and an energy storage system, and constructing an energy supply fusion data set; respectively extracting energy availability and user load characteristics by adopting a double-domain attention decoupling fusion joint supply and demand prediction method, and realizing double-channel joint modeling; modeling, estimating and correcting response lags of different energy sources in combination with a dynamic response curve reconstruction method; and further constructing a layered target penalty function containing real-time response error, economic cost, carbon emission and response penalty terms, and embedding the layered target penalty function into a particle swarm optimization algorithm to obtain an energy distribution strategy under multi-target optimization.

The invention discloses a geological map-oriented breakpoint repairing and closed curve reconstruction method and system and a medium. The method comprises the following steps of: preprocessing an original geological map to obtain a grayscale image; carrying out binarization and morphological closed operation processing to obtain a grayscale image of the edge of the smooth contour curve; performing pixel skeletonization to obtain a pixel-level skeleton diagram; performing secondary edge extraction, connected domain marking and endpoint statistics on the pixel-level skeleton diagram, and screening out a non-closed curve and an endpoint set; carrying out nearest neighbor retrieval by adopting KD-Tree to obtain a candidate pairing set of each end point; performing priority pairing in combination with the spatial distance and the direction smoothness; and generating a transition line segment according to a pairing result to supplement the fracture part of the non-closed curve. According to the method, non-closed breakpoints generated by scanning or drawing errors in the geological map can be automatically restored, and a closed curve with topological integrity and a smooth boundary is generated.

The invention provides a bidirectional recurrent neural network acoustic logging curve reconstruction method. The reconstruction method comprises the steps of S1, acquiring data and performing sequence segmentation; s2, carrying out normalization processing on the logging curve; s3, carrying out superposition networking and training on the bidirectional recurrent neural network structure block; s4, model testing and parameter storage; and S5, reading the model parameter file to reload the model, importing the to-be-reconstructed logging data, generating a prediction curve, and storing and exporting a result. A bidirectional recurrent neural network algorithm of artificial intelligence deep learning is adopted, bidirectional depth sequence information contained in a logging curve is effectively captured, the curve reconstruction accuracy is improved, unmeasured, missing and low-quality curves are reconstructed, multi-curve information is fused, and the sensitivity of a reconstructed acoustic curve is improved. The system has the advantages of being low in cost, high in efficiency and high in precision.

The invention relates to the technical field of photovoltaic cell testing, and discloses a volt-ampere characteristic curve testing system for a high-power photovoltaic cell. The system comprises a multi-source data acquisition module, a cross-modal feature fusion module, a volt-ampere curve reconstruction module and a dynamic parameter adjustment module. The multi-source data acquisition module synchronously acquires real-time irradiance time sequence data, assembly temperature distribution data and a current and voltage sampling data set of a target photovoltaic array; the cross-modal feature fusion module performs feature interaction processing on the multi-source data to generate a fusion electrical feature matrix; a volt-ampere curve reconstruction module performs dynamic curve fitting based on the matrix to generate a volt-ampere characteristic curve under a standard test condition; and the dynamic parameter adjustment module executes parameter calibration according to the curve and outputs a test parameter dynamic adjustment strategy to the acquisition module. The system can eliminate environmental interference, optimize test parameters, guarantee long-term stable operation, and meet accurate test requirements of high-power photovoltaic cells.

The present application belongs to the technical field of geophysical well logging data processing, and particularly relates to a multi-scale dual-branch neural network well logging curve reconstruction method based on seismic constraint, which comprises reading in well-seismic and interpreted horizon data, target interval sublayering and facies belt division based on three-dimensional seismic interpretation, pyramid multi-scale training set sample construction by fusing multi-curve and well flanking seismic trace information, residual-Transformer dual-branch neural network training model establishment taking a composite loss function as the core, three-stage progressive training strategy and reconstruction of target well missing section and result evaluation. The method still maintains high stability and robustness under the condition of complex heterogeneous reservoirs; on the basis of seismic data constraint, geological sublayering and facies belt division and other interpretation information are fused, so that the reconstruction result is more in line with geological laws; and the obtained reconstructed curve provides reliable support for re-interpretation of old data and full use of incomplete well logging data.

The invention discloses a three-dimensional Gaussian splashing method and system for sparse view curve reconstruction, and the method reconstructs a three-dimensional curve scene through a sparse image: firstly, obtaining a dense point cloud and a camera pose, extracting a two-dimensional line segment graph, employing a line segment guide Gaussian initialization strategy, and obtaining a three-dimensional curve scene; generating an initial Gaussian set on the basis of the dense point cloud and the two-dimensional line segment graph; structure perception Gaussian pruning is executed in the optimization process of the initial Gaussian set, and spatial outliers and visibility redundant gauss are removed; and finally, calculating the total loss containing sparse regular terms through the difference between the rendered image and the sparse image, and iteratively optimizing Gaussian parameters until the total loss converges, thereby obtaining a final three-dimensional curve reconstruction result. According to the method, the problem of geometric prior deficiency under a sparse view is solved through line segment guide initialization, overfitting and artifacts are effectively inhibited by using structure pruning and sparse constraint, and high-quality three-dimensional curve reconstruction is realized.

The invention provides a nonlinear torsion compensation method and calibration device for spiral multi-core optical fiber shape sensing, and belongs to the field of optical fiber shape sensing. The method comprises the following steps: firstly, acquiring the total strain of the spiral multi-core optical fiber when the spiral multi-core optical fiber is bent and twisted through an optical frequency reflectometer; then the bending curvature, the torsional strain and the strain noise of the optical fiber to be measured are obtained according to the total strain decoupling principle; applying different torsion rates, and demodulating the torsion strain corresponding to the spiral multi-core optical fiber; then, according to the theoretical model of the spiral optical fiber subjected to external torsion, the torsion sensitivity is solved by using an iterative algorithm; and finally, fitting by utilizing the linear relationship between the torsion sensitivity and the torsion rate to obtain the nonlinear relationship between the torsion strain and the torsion rate, and further performing nonlinear torsion compensation on the bending angle in shape reconstruction. According to the method, good curve reconstruction performance can be obtained, and particularly, the reconstruction precision can be obviously improved under the condition that the optical fiber is twisted and bent at the same time.

The embodiment of the invention relates to the technical field of exploration and development, and provides a well logging curve reconstruction method, device and equipment, a storage medium and a product, the method comprises the steps that an original well logging curve in a specified time period is obtained, the original well logging curve comprises a to-be-reconstructed well logging curve and a plurality of basic well logging curves, carrying out representation learning on the original logging curve to obtain an initial feature vector matrix; the initial feature vector matrix is input into a pre-trained curve reconstruction model, a reconstruction curve of the to-be-reconstructed logging curve is obtained, the curve reconstruction model comprises at least one decoding layer, and the decoding layer comprises an asymmetric causal attention layer, a first normalization layer, a feedforward network layer and a second normalization layer; the asymmetric causal attention layer is used for extracting the space-time correlation weight of the initial feature vector matrix. According to the embodiment of the invention, the reconstruction precision of the logging curve can be improved, so that accurate and reliable data support is provided for exploration and development decisions of oil and gas fields.

The invention discloses an underwater intelligent cable spatial form reconstruction system based on fusion of fiber bragg grating sensing and underwater acoustic positioning, and belongs to the technical field of underwater measurement and sensing. A plurality of fiber bragg grating sensors are inscribed on a three-core fiber in the intelligent cable of the system along the length direction to measure multi-point strain data along the length direction. According to the strain distribution, the bending curvature and the torsion of each measuring point are calculated, a continuous curvature and torsion function is constructed, the tangent vector, the normal vector and the sub-normal vector of each point of the cable are solved in combination with a Freen-Serret algorithm, and the tangent vector is integrated to obtain the space curve form of the cable. And determining the absolute position of the cable terminal in the three-dimensional space according to the acoustic ranging result. And realizing spatial form and attitude recognition of the whole underwater cable through constraint fusion of a curve reconstruction result and an end point position. According to the system, an inertial measurement unit is arranged on a cable to obtain local attitude information, so that the accuracy and the stability of curve reconstruction are improved. The method can be widely applied to space state monitoring of underwater long cable operation.

The invention discloses a logging curve abnormal section reconstruction method based on an attribute co-occurrence relation. The logging curve abnormal section reconstruction method comprises the steps of research area data preprocessing, attribute correlation analysis, curve trend characteristic extraction, modeling of a nonlinear correlation relation between curves, generation of attribute co-occurrence relation characteristics of a missing section and construction of an ACF-Informer curve reconstruction model. According to the method, co-occurrence attributes are screened by using Spearman correlation coefficients, nonlinear equations among the attributes in all periods are modeled through polynomial regression, and ACR features are fused to an Informer encoder-decoder architecture in stages as priori knowledge; the multi-strategy ACR features are fused by adopting integrated learning, so that the model can adapt to the spatial variability of the high-heterogeneity geological environment; a sub-model is constructed through a plurality of feature fusion strategies, and final output is optimized by adopting an integrated learning technology, so that the robustness and prediction precision of the model in a complex geological environment are improved.

The invention provides an environmental protection equipment energy consumption optimization and energy-saving regulation and control method based on multi-source data fusion, and relates to the technical field of environmental protection equipment energy-saving control, and the method comprises the steps: collecting the operation data of environmental protection equipment, carrying out the multi-scale feature extraction, recognizing the energy consumption abnormity through combining the energy efficiency curve reconstruction, and carrying out the energy-saving control of the environmental protection equipment; energy consumption sensitive parameters are extracted, energy-saving space is calculated based on load fluctuation, and an optimized parameter adjusting scheme and an optimized time sequence control sequence are generated by integrating the environment load change rate and the equipment thermal inertia coefficient. The energy consumption abnormity can be accurately identified, the energy-saving space is scientifically quantified, the intelligent optimization and dynamic regulation and control of the energy consumption of the environmental protection equipment are realized, and the operation efficiency of the equipment is obviously improved.

The invention belongs to the technical field of geophysical logging data processing, and particularly relates to a multi-scale double-branch neural network logging curve reconstruction method based on seismic constraints. Comprising the steps of reading in well seismic and interpreting horizon data, performing target layer section layering and phase belt division based on three-dimensional seismic interpretation, fusing multiple curves and well-side seismic channel information to construct a pyramid multi-scale training set sample, establishing a residual-Transformer double-branch neural network training model by taking a composite loss function as a core, and constructing a multi-scale training set sample based on the residual-Transformer double-branch neural network training model. And a three-stage progressive training strategy is adopted, and target well missing section reconstruction and result evaluation are carried out. According to the method, high stability and robustness are still kept under the condition of a complex heterogeneous reservoir; interpretation information such as geological layering and phase belt division is fused on the basis of seismic data constraints, so that a reconstruction result better conforms to geological laws; and the obtained reconstruction curve provides reliable support for re-explanation of old data and full utilization of incomplete logging data.

The invention discloses a surface blasting full-time-history vibration synthesis prediction method which comprises the following steps: S1, acquiring geological parameters of a surface blasting area, blast hole arrangement parameters and explosive quantity parameters, and arranging vibration monitoring points in a protection area of the blasting area; and S2, on the basis of the Anderson theory, a single-hole vibration curve reconstruction model is established when the free surface condition is not changed in combination with an on-site limited single-hole blasting experiment, and the model takes the quantitative mapping relation between the vibration velocity peak value and the explosive quantity, the distance from the blast hole to the monitoring point and the site factor as the core. According to the method, accurate prediction of large-scale open blasting full-time-history vibration is realized, and a reliable technical means is provided for collaborative optimization of blasting vibration control and a crushing effect.

The application relates to a lithium battery state of charge evaluation method based on charging curve reconstruction, which comprises the following steps: presetting charging cutoff conditions, discharging cutoff conditions and cycle cutoff conditions, continuously charging and discharging the lithium battery according to the preset cutoff conditions, and recording data information in the experiment process; collecting charging curve data of the lithium battery, performing data cleaning, and removing error data; pre-processing the cleaned data, filling in missing values by adopting a linear interpolation method, and obtaining voltage-time sequence data of the lithium battery; forming a data set by sliding a window to the voltage-time sequence data; training the data set, and constructing a charging curve reconstruction model; verifying the performance of the charging curve reconstruction model by using a test set and a verification set, and calculating the battery power based on the charging curve reconstruction model; and the lithium battery state of charge evaluation method can strengthen short-term time sequence feature extraction and provide data support for lithium battery health management.

The application discloses a screw motor stator-rotor linear optimization method for directional drilling, relates to the technical field of directional drilling of oil and natural gas, and comprises the following steps: according to the design requirements of a screw motor for directional drilling, design parameters of an eccentricity, a rotor head number, a stator head number, a base circle diameter and a theoretical equidistance radius are determined, and an initial linear data set containing discrete data points is generated based on an internal or external cycloid equation; a non-uniform rational B-spline method is used to perform curve reconstruction on the initial linear data set, local fairing treatment is performed on regions with curvature mutations by adjusting control point weight factors and node vectors of the non-uniform rational B-spline curve, and a smooth linear parameter model is generated; and based on the smooth linear parameter model, a thermodynamic coupling simulation model based on a rubber viscoelastic constitutive relation is established to simulate periodic plunger movement of the screw motor under a rated working condition.

The present application relates to the technical field of reservoir capacity curve reconstruction, in particular to a reservoir capacity curve reconstruction method and system based on multi-source data fusion, comprising the following steps: obtaining multi-source data fusion elevation information, reconstructing the water level-storage capacity relationship curve, and outputting the reservoir capacity curve reconstruction graphical expression result. In the present application, the water body boundary surface information is obtained by fusing the unmanned aerial vehicle remote sensing image to identify the boundary pixel area, the abnormal water level line number is identified by combining the difference index comparison, the complete three-dimensional fusion data set is constructed by matching the water point cloud and the underwater elevation data, the grid network is generated according to the unified projection and the abnormal elevation points are corrected, the continuous trajectory line sequence is established and integrated to form the two-dimensional boundary expression, which can quickly identify the reservoir capacity change in the dynamic environment, effectively avoid the incomplete boundary extraction and the data precision decline caused by the complex terrain and the tedious operation in the traditional measurement method, and improve the comprehensive performance of the reservoir capacity curve reconstruction in the spatial coverage, data updating and expression precision.

The invention belongs to the technical field of power system relay protection, and particularly relates to a distribution network load characteristic identification method and system, electronic equipment and a storage medium. The method comprises the steps that an original power distribution network load curve is processed, a load curve reconstruction model based on cubic spline interpolation is constructed, and time sequence synchronization of multi-source load data is achieved; constructing a power distribution network load identification model based on a deep neural network; an automatic framework search mechanism based on Bayesian optimization is provided, the number of network layers and neuron parameters are dynamically optimized, and an optimal network framework is obtained; based on the monitoring data and the optimal network architecture, decoupling and fine analysis of the equipment-level electrical load are carried out; and carrying out multi-dimensional analysis on the load characteristics of the power distribution network based on decoupling and refined analysis results. According to the method, the engineering applicability of load characteristic identification is remarkably improved, the problem of data distortion under the complex working condition of the distribution network is effectively solved, and the matching precision of the low-frequency load shedding control strategy and the actual working condition of the system is improved.

This invention discloses a LiDAR human motion capture method based on Bézier curve degradation modeling, comprising: acquiring a continuous multi-frame LiDAR point cloud sequence; constructing a trajectory-aware Bézier motion degradation module to fit the original joint trajectory and gradually reduce control points through a trajectory preservation strategy to generate a multi-level motion representation from coarse to fine; designing a progressive motion reconstruction module, using a multi-timescale motion transformer (TMT) to predict Bézier motion curves at multiple time scales based on point cloud features, and using a multi-level motion aggregator (MMA) to adaptively fuse the multi-scale curves to reconstruct a detailed and temporally coherent 3D human posture sequence. This invention effectively alleviates the posture jitter or failure problem caused by occlusion, noise, and sparse point clouds, significantly improving the accuracy and temporal continuity of motion capture, and is suitable for complex open scenarios such as autonomous driving and robotics.

The application provides a kind of open-circuit voltage curve reconstruction method for vehicle-mounted lithium ion battery, belongs to the technical field of battery management system, including collecting and storing the multistage constant current charging data of vehicle-mounted lithium ion battery, and the data is segmented processing;Establish the first-order equivalent circuit model of battery, and the optimal parameters of the model are identified by using the white whale optimization algorithm enhanced by random reset strategy;According to the model parameters, the open-circuit voltage curve in each segment is solved;The open-circuit voltage curve combination is reconstructed.The application can complete the reconstruction of the open-circuit voltage curve of the battery only by using the data of single charging of the vehicle.

The invention discloses an optimal arrangement and curve estimation method based on IMU nodes, and belongs to the technical field of three-dimensional curve measurement and restoration. According to the method, initial nodes are generated through uniform sampling on a curve, and the sensitivity value of each node to a curve recovery error is calculated by using local attitude information collected by an IMU sensor, so that a local error distribution function is constructed. And aiming at the error sensitivities of different nodes, a density adaptive sampling strategy is adopted to realize the optimization of the overall node distribution. According to the method, the validity of the optimization point distribution strategy is quantitatively verified by combining an error evaluation index. Through the combination of density adaptive point distribution and spherical interpolation restoration, the method can significantly reduce curve reconstruction errors, improves the space efficiency of IMU arrangement, and is suitable for flexible cables and other three-dimensional curve accurate measurement scenes. The method has the advantages of being simple in algorithm, capable of achieving automatic point distribution, high in error control precision and the like, and an efficient and reliable technical scheme is provided for three-dimensional curve measurement and restoration.

The present application relates to a kind of aviation blade profile numerical control milling program adaptive adjustment and compensation method, comprising the following steps: step one, part is installed to three coordinate measuring machine according to detection requirement, and the clamping of part is completed;Step two, blade profile size detection;Step three, calculate the size deviation of part;Step four, determine whether the part is qualified;Step five, cross-sectional curve compensation direction determination;Step six, each cross-sectional curve reconstruction;Step seven, cross-sectional line profile degree determination;Step eight, tool radius compensation value determination;Step nine, update tool path;Step ten, output numerical control program, complete numerical control processing.The present application not only solves the automation compensation and processing quality control of multiple model blade part blade profile numerical control milling, but also can be applied to the numerical control processing and repair of integral blisk, structural parts and other parts.

This application relates to the fields of mechanical engineering and automated inspection technology, and discloses a method and system for detecting the edge drop of strip steel based on the collaborative operation of multiple measuring heads of edge drop gauges. It aims to solve the technical problems in existing technologies, such as spatial misalignment of data from multiple thickness gauges, distortion of the edge drop curve reconstruction, and inability to accurately reflect the thickness distribution of the same cross-section caused by the high-speed operation and speed fluctuations of the strip steel. The method includes: synchronously acquiring thickness data using multiple non-contact thickness gauges arranged in a linear array; obtaining the actual displacement of the strip steel using a high-resolution rotary encoder to establish a spatiotemporal mapping relationship between the thickness data and the physical cross-section; reconstructing a distortion-free cross-sectional thickness distribution curve using a dynamic interpolation algorithm based on a preset sampling interval, and calculating the edge drop value. This application significantly improves the accuracy and dynamic response capability of edge drop detection through a synchronization mechanism and interpolation reconstruction based on the actual displacement of the strip steel, providing high-fidelity data support for strip shape control.

The invention relates to the technical field of geophysical well logging, in particular to a well logging curve reconstruction-oriented AI large model construction method, reconstruction method and device, electronic equipment and a storage medium, comprising an LB-DALR model, a specific curve trend semantic embedding preprocessing unit obtains a numerical matrix and a semantic embedding vector, the feature extraction and fusion unit extracts numerical features through a numerical path and extracts trend semantic features through a semantic path, and multi-scale fusion features are obtained after fusion; and the decoding reconstruction unit reconstructs the logging curve. According to the method, the problem that in the geological logging curve reconstruction process of a single-mode model, the curve reconstruction deviation is large when the single-mode model faces complex geological logging data and data interfered by a severe underground environment is solved, and numerical features and trend semantic features are extracted from a numerical path and a semantic path which are operated in parallel; and the high-precision reconstruction is realized through the synergistic effect of the CrossModal multi-head cross attention mechanism and the FusionGate autocorrelation dynamic gating.

The present application belongs to the technical field of rotating machinery state monitoring and industrial deployment, and particularly relates to a reducer input shaft end-to-end rotating speed adaptive inference method based on variable-length sequence. In view of the fact that actual monitoring data is a continuous sequence of any length, and a deep learning model usually relies on fixed-length input, and traditional sliding window inference is prone to introducing phase discontinuity and splicing artifacts at the boundary, the present application establishes a deployment paradigm of "fixed-length training and variable-length inference". The continuous variable-length sequence is divided by a sliding window with an overlap rate, and a backtracking interception strategy is designed for the case of insufficient end sequence. After batch inference using a pre-trained model, the local prediction results are integrated and smoothed by using an overlap addition mechanism and a weighted average algorithm. The present application effectively eliminates the Gibbs effect at the window boundary, ensures the phase integrity of the terminal, and realizes seamless and smooth rotating speed curve reconstruction of continuous monitoring data of any length.

The invention relates to the technical field of electricity market electricity price prediction, and discloses a spot clearing electricity price prediction system fusing new energy output fluctuation characteristics, and the system comprises a fluctuation characteristic extraction module which carries out the variational mode decomposition of a new energy output prediction sequence, and generates fluctuation impact momentum and duration; the climbing scarcity calculation module is used for calculating a reference equivalent climbing scarcity in combination with the polymerization residual climbing capability and the fluctuation impact momentum; the hysteresis state correction module is used for correcting and generating a scarcity degree state index by using a state attenuation parameter based on fluctuation duration; the supply curve reconstruction module is used for generating a dynamic effective supply curve by carrying out linear deformation on the reference residual supply curve by utilizing the physical capacity cut-off quantity mapped by the index and a quotation slope correction coefficient; and the clearing electricity price solving module is used for outputting a predicted value based on the curve. The new energy fluctuation impact and hysteresis effect are effectively quantified, and the prediction precision is improved.

The invention provides a multi-modal surface data processing optimization system based on a spherical Transform. The multi-modal surface data processing optimization system comprises an image acquisition and preprocessing module, a spherical uniform symmetric grid surface generation module, a spherical convolution and pooling module, a spherical Transform module, a spherical upper sampling and lower sampling module and an application analysis module. The image acquisition and preprocessing module is used for segmenting a region of interest, reconstructing a surface curved surface, completing rigid registration and extracting features at the vertex of the curved surface; the application analysis module integrates a spherical convolution and pooling module, a spherical Transform module and a spherical upper sampling and lower sampling module, establishes a spherical auto-encoder model, a segmentation model and a classification model, and is used for target identification, risk prediction or anomaly detection tasks. According to the method, a complex mode which is difficult to extract by a traditional CNN can be captured, multi-source feature complementarity is improved based on a cross-modal attention mechanism, and efficient multi-source data fusion is realized.

The embodiment of the specification relates to the technical field of exploration and development, and provides a well logging curve reconstruction method, device, equipment, storage medium and product. The method comprises the following steps: acquiring original well logging curves in a specified period, the original well logging curves comprising a to-be-reconstructed well logging curve and a plurality of basic well logging curves; performing characterization learning on the original well logging curves to obtain an initial feature vector matrix; inputting the initial feature vector matrix into a pre-trained curve reconstruction model to obtain a reconstructed curve of the to-be-reconstructed well logging curve, wherein the curve reconstruction model comprises at least one decoding layer, the decoding layer comprises an asymmetric causal attention layer, a first normalization layer, a feedforward network layer and a second normalization layer, and the asymmetric causal attention layer is used for extracting a space-time correlation weight of the initial feature vector matrix. Through the embodiment of the specification, the reconstruction accuracy of the well logging curve can be improved, thereby providing accurate and reliable data support for exploration and development decision of an oil and gas field.

The present application discloses a pseudo-acoustic wave curve reconstruction method, device and storage medium. The method includes: calculating localized rock physical modeling parameters based on the rock physical modeling parameters of the area to be measured; substituting the localized rock physical modeling parameters into the rock physical model to obtain the bulk modulus and shear modulus of the first rock; obtaining a lithologic sensitivity curve based on the rock physical modeling parameters of the area to be measured and the bulk modulus and shear modulus of the first rock; performing low-frequency filtering on the lithologic sensitivity curve to obtain medium- and high-frequency information; performing medium- and high-frequency filtering on the original acoustic wave curve to obtain low-frequency information; fusing the medium- and high-frequency information with the low-frequency information to obtain a pseudo-acoustic wave curve. This method constructs a lithologic sensitivity curve and reconstructs a pseudo-acoustic wave curve by fusing the constructed lithologic sensitivity curve with the original acoustic wave curve, which can highlight the difference between the reservoir and the surrounding rock and facilitate the identification of lithology.

The present invention discloses a method and device for processing azimuth gamma data while drilling based on MWD, which relates to the technical field of data processing. Among them, the method for processing azimuth gamma data while drilling includes: collecting azimuth gamma data, processing the azimuth gamma data to obtain target azimuth gamma data, and determining the coordinates of the sampling points indicated by each target gamma value in the target azimuth gamma data based on the well depth associated with each gamma value. Based on the drilling speed associated with each sampling point, determine the coordinates of the insertion points inserted between every two adjacent sampling points, and perform smoothing processing on each inflection point to adjust the coordinates of each preset insertion point. Based on the coordinates of each sampling point and the coordinates of each insertion point, use the Bezier curve reconstruction strategy to draw the gamma curve. The present invention solves the technical problem of the low smoothness and resolution of the gamma curve drawn in the related art.