Halliburton Energy Services, Inc.

Li Pan

Hsu-Hsiang Wu

YiJing Fan

Jin Ma

Rencheng Song

Ahmed Elsayed Fouda

Glenn Andrew Wilson

Junwen Dai

Burkay Donderici

Yi Jing Fan

Chao-Fu Wang

Luis Emilio San Martin

Weixin Dong

Michael S Bittar

Junsheng Hou

Wei Hsuan Huang

Clint Paul Lozinsky

Hsu Hsiang Wu

Iftikhar Ahmed

A system can calibrate inconsistencies in a wellbore tool. The system can receive a first set of measurements and a second set of measurements with respect to different electromagnetic antennas. The system can decouple a first multi-components tensor corresponding to the first set of measurements and a second multi-components tensor corresponding to the second set of measurements. The system can determine, using the decoupled first and second multi-components tensors, a scaling factor. The system can apply the scaling factor to a raw measurement received with respect to an electromagnetic antenna of the wellbore tool positioned in a wellbore to decouple a third multi-components tensor or to decoupled components of a fourth multi-components tensor for controlling a wellbore operation.

Scaling factor for calibrating antennas of a wellbore tool

Methods and systems for inspecting the integrity of multiple nested tubulars are included herein. A method for inspecting the integrity of multiple nested tubulars can comprise conveying an electromagnetic pipe inspection tool inside the innermost tubular of the multiple nested tubulars; taking measurements of the multiple nested tubulars with the electromagnetic pipe inspection tool; arranging the measurements into a response image representative of the tool response to the tubular integrity properties of the multiple nested tubulars; and feeding the response image to a pre-trained deep neural network (DNN) to produce a processed image, wherein the DNN comprises at least one convolutional layer, and wherein the processed image comprises a representation of the tubular integrity property of each individual tubular of the multiple nested tubulars.

Deep learning methods for wellbore pipe inspection

Some aspects relate to techniques for calibrating a logging tool. In some implementations, the logging tool may estimate certain unknown properties of a signal based on distances between transmitters and receivers of the logging tool and based on frequencies used by the transmitters and receivers. The logging tool may estimate the unknown properties by interpolating values into a mathematical function related to the above-noted distances and frequencies. After estimating the unknown properties, the logging tool may be deployed into the wellbore, where it may use the estimated properties to process signals received through a subsurface formation.

Cross-component response interpolation for coaxially oriented antennas in an electromagnetic tool

Systems and methods of the present disclosure relate to calibration of resistivity logging tool. A method to calibrate a resistivity logging tool comprises disposing the resistivity logging tool into a formation; acquiring a signal at each logging point with the resistivity logging tool; assuming a formation model for a first set of continuous logging points in the formation; inverting all of the signals for unknown model parameters of the formation model, wherein the formation model is the same for all of the continuous logging points in the first set; assigning at least one calibration coefficient to each type of signal, wherein the calibration coefficients are the same for the first set; and building an unknown vector that includes the unknown model parameters and the calibration coefficients, to calibrate the resistivity logging tool.

Accurate and cost-effective inversion-based auto calibration methods for resistivity logging tools

Methods and systems for inspecting the integrity of multiple nested tubulars are provided. A method for inspecting the integrity of multiple nested tubulars can comprise conveying an electromagnetic pipe inspection tool inside the innermost tubular of the multiple nested tubulars; taking measurements of the multiple nested tubulars with the electromagnetic pipe inspection tool; inverting the measurements for a tubular integrity property of each individual tubular of the multiple nested tubulars to provide inverted tubular integrity properties; arranging the inverted integrity properties into an inverted image representative of an estimated tubular integrity property of each individual tubular; and feeding the inverted image to a pre-trained deep neural network (DNN) to produce a corrected image, wherein the DNN comprises at least one convolutional layer, and wherein the corrected image comprises a representation of the tubular integrity property of each individual tubular of the multiple nested tubulars.

Borehole images can be corrected using machine-learning models. For example, a system can train a machine-learning model based on a training dataset. The training dataset can include a first set of borehole images correlated to a second set of borehole images, where the second set of borehole images are less precise versions of the first set of borehole images. The system can then execute the trained machine-learning model in relation to an input borehole image to receive a corrected borehole image as output from the trained machine-learning model. The corrected borehole image can be a visually corrected version of the input borehole image. The system may then perform one or more operations based on the corrected borehole image, such as generating a graphical user interface that includes the corrected borehole image for display on a display device.

Correcting borehole images using machine-learning models

A system and method for evaluating a subterranean formation includes a logging tool that includes transmitter and receiver antennae. The transmitter antenna transmits a first electromagnetic signal into the formation at a plurality of depths. The receiver antenna receives a plurality of second electromagnetic signals emitted by the formation in response to the first signal. The system and method also include a processor configured to calculate resistivity values for the second signals, calculate solutions to an inversion algorithm of the formation, filter the solutions into a plurality of convergent solutions, pixilate the convergent solutions into pixilated solutions, calculate ensemble statistics for the pixilated solutions, calculate a difference in resistivity value between successive pixels, identify presumptive layer boundaries based on the differences in resistivity values, calculate composite resistivity statistics from the pixilated solutions based on the presumptive layer boundaries and the ensemble statistics, and generate a formation model.

System and methods for evaluating a formation using pixelated solutions of formation data

A method and system for identifying a blind spot in one or more decoupled measurements. The method may comprise disposing an electromagnetic well measurement system into a wellbore. The electromagnetic well measurement system comprise an electromagnetic transmitter and a plurality of electromagnetic receivers. The method may further comprise transmitting electromagnetic fields into a formation with the electromagnetic transmitter, measuring the electromagnetic fields with the plurality of electromagnetic receivers as one or more measurements at one or more depths in the wellbore, decoupling the one or more measurements to form decoupled measurements, identifying if a blind spot is in the decoupled measurements, and performing an inversion with the decoupled measurements.

Compound signal for logging while drilling resistivity inversion

A geosignal is calculated based on a signal detected by a multicomponent resistivity tool () to facilitate determination of formation properties and infer location of the resistivity tool with respect to formation boundaries. The resistivity tool () detects an electromagnetic field response signal () at a series of azimuth angles () during one tool rotation. The signal measured at each azimuth angle is decoupled to obtain nonzero electromagnetic field tensor components for input into the geosignal calculation. The results of the geosignal calculation for at least a top bin (i.e., an azimuth angle of 360 degrees) and a bottom bin (i.e., an azimuth angle of 180 degrees) are evaluated to determine whether the tool () is near a formation boundary. If the tool is determined to be near a formation boundary, the resistivity of the layers of the formation on each side of the detected boundary can be inferred.

Determining formation properties based on multi-component azimuthal measurements

A method includes detecting, via first and second receivers of a tool that are oriented at a first and a third tilt angle, respectively, a first and second measurement of a first signal transmitted by a transmitter of the tool that is oriented at a second tilt angle into a substantially non-conductive material. The method includes determining, based on the first and second measurements, a first tensor and conveying the tool into a first wellbore formed in a subsurface formation. The method includes detecting, via the first receiver and the second receiver, a third and fourth measurement, respectively, of a second signal transmitted by the transmitter and determining, based on the third and fourth measurements, a second tensor and determining a third tensor (having values independent of the first, second, and third tilt angles) based on a relationship between the first and second tensors.

Electromagnetic tool calibration for tilted antennas with undetermined orientation angles

Certain aspects of the present disclosure relate to calibrating a formation signal for a mixed set measurement device. A first air-hang response of a first measurement device for a tubular string associated with a drilling operation can be measured. A second air-hang response of a second measurement device for the tubular string associated with the drilling operation can be measured. The first air-hang response and the second air-hang response can be used to determine a mixed air-hang response of the mixed set measurement device. The mixed air-hang response can be used to calibrate a formation signal for the mixed set measurement device.

Mixed air-hang response for correcting a formation signal of a mixed set measuring device

A method and system for determining a position of a second production wellbore. The method may comprise inducing a first current into a first conductive member with a first source, emitting a first magnetic field generated by the first current from the first conductive member into a formation, inducing a second current into a second conductive member with a second source, emitting a second magnetic field generated by the second current from the second conductive member into the formation, disposing an electromagnetic sensor system into the second production wellbore, recording the first magnetic field with the at least one sensor from the formation, and recording the second magnetic field with the at least one sensor from the formation. The system may comprise a first source, an electromagnetic sensor system, at least one sensor and an information handling system configured to determine the position of the second production wellbore.

Multiple surface excitation method for determining a location of drilling operations to existing wells

Systems and methods of the present disclosure relate to calibration of a resistivity tool. A method for in-situ calibration of a resistivity logging tool, comprises transmitting signals with transmitters of the resistivity logging tool; measuring voltages at two or more receivers located at different distances to the transmitters of the resistivity logging tool; decoupling two or more sets of multi-component tensors at two or more receivers based on the measured voltages; calculating a ratio signal from two or more sets of multi-component tensors; obtaining an apparent resistivity based on the ratio signal; simulating a dipole response tensor at the first receiver based on the apparent resistivity; comparing the first set of multi-component tensor with the dipole response tensor to acquire an in-situ calibration factor; and applying the in-situ calibration factor to multi-components for an inversion input.

In-situ calibration for multi-component signals

A method includes generating a ranging model of a drilling wellbore to be drilled and generating a predicted signal along measured depths of the drilling wellbore based on the ranging model. The method includes performing the following operations until the drilling wellbore has been drilled to a defined depth. The following operations include drilling, with a drill string, the drilling wellbore to an increment of the defined depth and detecting, by a sensor positioned on the drill string, an electromagnetic field emanating from a target wellbore. The following operations include determining ranging measurements to the target wellbore at the increment based on the electromagnetic field and calibrating the predicted signal based on the ranging measurements. The following operations include determining ranging accuracy for all deeper depths in the wellbore and making drilling decisions or adjusting drilling operations based on the predicted ranging accuracy for deeper depths.

Real-time calibration of excitation ranging for tracking wellbore drilling

A pixelation-based approach to summarize downhole inversion results acquires inversion solutions and generates an initial model. Each layered solution is pixelated into pixels where each pixel contains the resistivity value of the initial model. A weighted function that weighs pixels according to their proximity to the logging tool may be used to generate the pixelated model to thereby improve accuracy. A statistical summary study is performed to identify the best pixelated model, which is then used to determine one or more formation characteristics.

Growing community of inventors

Singapore, Singapore

Li Pan