Chinese Academy of Sciences

Baidu Online Network Technology (beijing) Co., Ltd.

Beijing Baidu Netcom Science and Technology Co., Ltd.

Fei Tian

Wenhao Zheng

Qingyun Di

Yongyou Yang

Wenjing Cao

Wenxiu Zhang

Zhongxing Wang

Jiangyun Zhang

Wang Zhang

Renzhong Pei

Xiaocai Shan

Tianxin Zhang

Changchun Yang

Jing Liu

Yujie Yang

Guanfang Li

Zongwei Li

Xu Xue

Yongjian Zhou

Wenyang Wang

Naigui Liu

Boye Fu

Yongwen Yang

Muming Xia

Canyun Wang

The present invention is in the field of geological measurement, and particularly relates to a method and system for intelligent removal of multi-dimensional logging data outliers, aiming to solve the problem that it is difficult to achieve stable parameter acquisition in the drilling process when there are more outliers in the prior art. The present invention comprises: acquiring a multi-dimensional logging curve; obtaining two-dimensional logging curve data by using the Umap dimensionality reduction algorithm to perform dimensionality reduction; establishing a first data point index of the multi-dimensional logging curve and the two-dimensional logging curve data; obtaining valid logging data by processing outliers with an isolation forest algorithm based on the two-dimensional logging curve data; acquiring a second data point index based on the first data point index and valid logging data; finding marked data points where the second data point index exists in the multi-dimensional logging curve data.

Method and system for intelligent removal of multi-dimensional logging data outliers

The present disclosure relates to the technical field of acoustic detection while drilling, in particular to a method and a device for identifying near-bit lithology based on intelligent voiceprint identification, including acquiring rock sound data; pre-processing the acquired rock sound data; extracting voiceprint features of pretreated rock sounds; establishing a rock voiceprint feature database; training the intelligent voiceprint identification algorithms according to the lithology labels and voiceprint feature data in the rock voiceprint feature database; intelligently identifying or predicting the rock voiceprint features using the intelligent voiceprint identification algorithms and outputting the lithology identification results. The present disclosure can greatly enhance the real-time availability and accuracy of obtaining near-bit stratum lithology data in-site, which can effectively improve the reservoir drilling rate and timely avoid drilling risks.

Method and device for identifying near-bit lithology based on intelligent voiceprint identification

The present invention belongs to the technical field of geological exploration deep Earth. The system of the present invention is configured to: collect seismic data, and preprocess original seismic data to obtain standardized gamma ray logging parameters; extract features from the standardized gamma ray logging parameters to obtain a variance attribute curve while drilling; obtaining a formation thickness prediction model of each set based on the variance attribute curve while drilling; acquire frequency-division seismic data based on the standardized seismic data by means of a frequency-division processing method based on wavelet transform; acquire optimal seismic frequency band information based on a predicted formation thickness value of each set; establish a geological prediction model of the current formation based on the frequency-division seismic data, the optimal seismic frequency band information, historical gamma ray logging parameters and the standardized gamma ray logging parameters.

System for updating clastic rock lithology model by well-to-seismic integration with deep earth oil and gas precision navigation

A sand shale formation lithology evaluation method and system for precise deep oil and gas navigation aims to solve the problem in the prior art, that is, the accuracy of the logging-while-drilling (LWD) azimuthal resistivity is insufficient due to an equipment or technology deficiency. The method includes: acquiring density distribution data, gamma distribution data, and resistivity distribution data of a target location; amplifying the data to acquire amplified logging distribution data; clustering the data to acquire clustered logging data; adding stratigraphic information to the clustered data; performing dimensionality reduction by a principal component analysis (PCA) method, and taking dimensionality-reduced data as a weight of azimuthal logging data to acquire an LWD feature dataset; predicting missing LWD photoelectric data through the LWD feature dataset; and acquiring a formation lithology evaluation result based on an LWD photoelectric data prediction curve. The method and system improves the accuracy of LWD lithology evaluation.

Sand shale formation lithology evaluation method and system for precise deep oil and gas navigation

A sand shale formation physical property evaluation method and system for precise deep oil and gas navigation aims to solve the problem that the prior art cannot acquire a real-time and accurate logging-while-drilling (LWD) Rt curve. The method includes: acquiring basic data of a target well location as well as basic data and an LWD resistivity (Rt) of an adjacent well; dividing the data into different groups; retaining data with a maximum correlation value with the LWD Rt in each group of data; eliminating outliers, and performing standardization; constructing a two-dimensional input feature map by taking the correlation value and standardized data as a weight; acquiring an LWD Rt prediction curve based on the two-dimensional input feature map; calculating a hydrocarbon parameter in a window based on the LWD Rt prediction curve; and locating an area with a high hydrocarbon potential based on the hydrocarbon parameter at each position.

Sand shale formation physical property evaluation method and system for precise deep oil and gas navigation

The present disclosure belongs to the field of geological prospecting and particularly relates to an intelligent real-time updating method and system for a stratigraphic framework with geosteering-while-drilling, aiming to solve the problems of insufficient precision in position and dipping angle of a stratigraphic framework due to differences in parameters measured by different instruments for well logging and mud logging while drilling. The method of the present disclosure comprises: obtaining existing well data, and acquiring well logging data and images imaged while-drilling in real time; constructing an initial stratigraphic framework model, eliminating abnormal values, and conducting dimensionality reduction; and based on dimensionality reduction well logging data, conducting non-linear clustering through a density peak clustering method, obtaining a marker layer primary prediction result through a marker layer prediction model of a depth belief network and conducting correction, to obtain a corrected stratigraphic framework model and to adjust a drilling trajectory.

Intelligent real-time updating method and system for stratigraphic framework with geosteering-while-drilling

The present invention is in the field of geological exploration and particularly relates to a method and system for gamma ray (GR) while drilling parameter data optimization for deep-filed oil and gas precise navigation, aiming to solve the problem of insufficient measurement accuracy of the depth of a well in the existing drilling technology. The present invention comprises: eliminating outliers from the obtained GR while drilling parameter data and determining the rationality of the eliminated outlier; performing derivation on a real-time updated variance attribute while drilling curve to obtain a real-time updated formation change-point detection result; searching the formation change-point detection result of a pre-drilling predicted well curve; and correcting the drilling depth by comparing the two formation change-point detection results to obtain the accurate depth while drilling.

Method and system for GR LWD curve optimization for deep-field oil and gas precise navigation

The present invention belongs to the field of deep navigation, and in particular to a high-precision modeling method and system of three-dimensional velocity field for precise navigation of deep oil and gas. The present invention includes: extracting wave impedance characteristics based on standardized well logging data to obtain a wave impedance curve; acquiring a velocity vector of each location at current depth, to obtain a one-dimensional velocity curve; based on the one-dimensional velocity curve, training a velocity value prediction model based on wave impedance at the current depth; performing wave impedance inversion based on the wave impedance curve at the current depth to obtain a wave impedance inversion data volume; and based on the wave impedance inversion data volume, through the velocity value prediction model based on wave impedance at the current depth, acquiring a three-dimensional high-accuracy velocity volume.

High-precison modeling method and system of three-dimensional velocity field for precise navigation of deep oil and gas

The present invention belongs to the field of geologic survey, and particularly relates to a real-time calibration method and system of acoustic logging data while drilling for precise navigation of deep oil and gas, aiming to solve a problem of inability to automatically identify stratum boundaries to adapt to geology at various different depths in an existing drilling process. The method of the present invention includes: acquiring standardized acoustic parameter data while drilling; acquiring time-depth relationship of historical acoustic curve data of drilled wells, and current actual drilling time-depth relationship; performing interpolation based on the current actual drilling time-depth relationship, to acquire interpolated current actual drilling time-depth relationship; correcting the interpolated current actual drilling time-depth relationship; and completing current precise depth correction based on the current actual drilling acoustic curve.

Real-time calibration method and system of acoustic logging data while drilling for precise navigation of deep oil and gas

A precise deep oil and gas navigation system based on structural evaluation of a sand/shale formation, and a device are provided. The precise deep oil and gas navigation system is implemented by: acquiring basic data of a target well location as well as basic data and an acoustic LWD curve of an adjacent well; dividing a basic data group; retaining extremely strongly correlated data and strongly correlated data of the basic data group, and performing dimensionality reduction; constructing a three-dimensional fusion feature data volume based on a dimensionality-reduced fusion feature parameter and a time-frequency spectrum; predicting a missing curve according to the three-dimensional fusion feature data volume; and correcting a stratigraphic structure model based on the missing curve to guide the design of a drilling trajectory.

Precise deep oil and gas navigation system based on structural evaluation of sand/shale formation, and device

The present disclosure relates to a method and a system for updating a three-dimensional lithology model for precision navigation of deep oil and gas in real time, aiming to solve the problem that an existing while drilling model is difficult to adapt to a real-time update of the model in a strong heterogeneous reservoir, which leads to a decrease in accuracy of an established prediction model and a lack of a drilling ratio. The present disclosure includes: dividing pre-processed seismic data into three pieces of single-frequency seismic waveform data by a wavelet frequency division method; selecting an optimal single-frequency combination according to a correlation coefficient between gamma ray prediction curves and measured curves at different depths; and computing a single-frequency gamma ray prediction model while drilling, updated with drilling, and a full-band gamma ray distribution model while drilling, updated with drilling, by means of the optimal single-frequency combination.

Method and system for updating three-dimensional lithology model for precision navigation of deep oil and gas in real time

The present description relates to the field of geological exploration, and discloses a method and system for extracting features of logging while drilling and drilling-time logging based on Unet dual-channel output, aiming at solving the problem that the prior art 5 cannot integrate various types of information for lithology classification. The present invention comprises: acquiring stratum data of different wells; eliminating outliers, normalizing and resampling; performing data reconstruction via a self-encoder-based artificial neural network based on the pre-trained data to obtain stratum reconstructed data for training; inputting the data to be analyzed from shallow to deep in segments, performing 10 dynamic optimization while drilling on the pre-trained self-encoder-based artificial neural network by a quantile loss function; and extracting the independent components output by the encoder dual-channel for unsupervised clustering, and fitting to obtain a stratum lithology determination result corresponding to the current data to be analyzed.

Method and system for extracting features of logging while drilling and drilling-time logging based on UNET dual-channel output

The present invention belongs to the field of environment monitoring, particularly relates to a COstorage state networking monitoring device, system and method with multi-information fusion. The present invention comprises: obtaining orientation electrical signal data and real-time pressure signals, analyzing a fluid flowing state at a view of a pressure sensor through the real-time pressure signals, and obtaining a COflowing state through the orientation electrical signal data; and obtaining a COregional storage state by combining an orientation COcontent, a COflowing state and the fluid flowing condition at the view of the pressure sensor. By combining accurate short-range COboundary monitoring of orientation electrodes with long-range monitoring of pressure sensors to achieve a wide range of COflowing state monitoring, the present invention can observe more data with higher reliability and effectively aims at the problem of strong inter-well heterogeneity.

COstorage state networking monitoring device, system and method with multi-information fusion

The present invention belongs to the field of geological exploration and specifically relates to the fault characterization method and system for precise navigation of deep oil and gas based on image fusion, aiming to solve the problem that faults in deep formations are difficult to characterize with conventional seismic interpretation methods. The present invention includes: obtaining amplitude gradient images by calculating amplitude gradient vectors; calculating dip attribute images based on the enhanced seismic data; fusing gradient amplitude attribute fault confidence region with dip angle attribute data volume that defines the fault position through a hierarchical wavelet transform method to obtain a superimposed fault attribute map; dividing bead-like structures based on superimposed fault attribute maps; calculating the score of branch fault data points based on the center point position of bead-like structures, and dividing and analyzing the dominant fault areas.

Fault characterization method and system for precise navigation of deep oil and gas based on image fusion

The invention belongs to the field of environmental monitoring, and in particular relates to a method for optimally selecting a carbon storage site based on multi-frequency band seismic data. The method comprises the steps of: performing seismic wavelet spread spectrum simulation based on three-dimensional post-stack seismic data to obtain spread spectrum simulated wavelets; building an isochronous stratigraphic framework model of a target horizon, and calculating the geometric structure and spatial distribution of a fault-karst; then performing waveform-indicated inversion to obtain a wave impedance inversion data volume, and obtaining a stable stratum wave impedance data volume through a virtual well cross-well wave impedance interpolation; calculating the difference between the stable stratum wave impedance data volume and the wave impedance inversion data volume to obtain an abnormal wave impedance data volume, then obtaining a fault-karst reservoir bed interpretation model, and determining the position of a carbon storage box.

Growing community of inventors

Beijing, China

Fei Tian