Halliburton Energy Services, Inc.

Halliburton Services

Junwen Dai

Ahmed Elsayed Fouda

Christopher Michael Jones

Li Pan

Freeman Lee Hill, Iii

Xusong Wang

Xiang Wu

Ilker R Capoglu

Burkay Donderici

Wei Zhang

Baris Guner

David R Beard

Sushovon Singha Roy

Freeman Hill

Described herein are systems and techniques for monitoring for monitoring and evaluating conditions associated with a wellbore and wellbore operations that use neural operators instead of computationally intensive iterative differential equations. Such systems and techniques allow for determinations to be made as operations associated with a wellbore are performed. Instead of having to wait for computationally intensive tasks to be performed or take risks of proceeding with a wellbore operation without real-time evaluations being performed, these wellbore operations may be continued while determinations are timely made, thus improving operation of computing systems that perform evaluations and that make decisions regarding safely and efficiently performing wellbore operations such as drilling a wellbore, cementing wellbore casings in place, or injecting fluids into formations of the Earth.

Three-dimensional inversion of multi-component electromagnetic measurements using a fast proxy model

Provided are methods and system for hydrocarbon exploration. The method may include using a downhole reconfigurable pipe inspection tool for electromagnetic logging. The method may also include using the electromagnetic pipe inspection tool for inspecting wellbore pipes. The tool may include at least two modules, a signal generator for exciting the transmitter coil; and a receiver circuitry for measuring voltage across the receiver coil, wherein at least one tool parameter is reconfigurable. The first module houses a transmitter coil, a first end, and a second opposing end, wherein the first and second ends each have a connector thereon. The second module houses a receiver coil, a first end, and a second opposing end, wherein the first and second ends of the second module each have a connector thereon.

Reconfigurable downhole pipe inspection tool

Electromagnetic logging tools are optimized using synthetic logs for the purpose of pre-job planning and accuracy/resolution estimation. One, two and three-dimensional forward modeling are used to generate accurate inspection tool responses. A radial one-dimensional (R1D) electromagnetic forward model is also used to compute an approximate log. By constructing non-linear mapping functions between the R1D model-based log and the 2D model-based log, and mapping the R1D synthetic log using the non-linear mapping functions, a quasi 2D log is computed. The quasi 2D log is processed using model-based inversion, thereby providing estimates of pipe parameters. By analyzing the estimates of pipe parameters, tool performance metrics are obtained and analyze to determine the performance of the tool. The tool parameters are adjusted in order to optimize the performance metrics.

Downhole well pipe inspection using optimized inspection tools

Aspects of the subject technology relate to systems, methods, and computer-readable media for accounting for artifacts in pipe measurements made by an electromagnetic pipe inspection tool. Measurements gathered in a plurality of pipes across different depth points are accessed. Initial estimates of an attribute associated with the plurality of pipes are made for each pipe and a total estimate of the attribute for the plurality of pipes as a whole are made across the different depth points. Corresponding initial estimates of the attribute for each pipe are filtered to remove an artifact present in at least one of the corresponding initial estimates while the total estimate is preserved. Corresponding final estimates of the attribute for each pipe are determined based on both the measurements and corresponding filtered initial estimates of the attribute for each pipe. Integrity of each pipe can be determined based on the corresponding final estimates of the attribute.

Electromagnetic pipe inspection inversion with adaptive filter for artifact removal

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

A method for identifying a collar using machine learning may include acquiring one or more measurements from one or more depth points within a wellbore including a tubular string, training a machine learning model using a training dataset to create a trained machine learning model, and identifying at least one hyperparameter using the trained machine learning model. The method may further include creating a synthetic model, wherein the synthetic model is defined by one or more pipe attributes, minimizing a mismatch between the one or more measurements and the synthetic model utilizing the at least one hyperparameter, updating the synthetic model to form an updated synthetic model, and repeating the minimizing the mismatch with the updated synthetic model until a threshold is met.

Multi-channel machine learning model-based inversion

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.

A system for inspecting a tubular may comprise an electromagnetic (EM) logging tool and information handling system. The EM logging tool may further include a mandrel, one or more sensor pads attached to the mandrel by one or more extendable arms, and one or more partial saturation eddy current sensors disposed on each of the one or more sensor pads.

Downhole tubular inspection using partial-saturation eddy currents

Electromagnetic logging tools to inspect nested pipes using hybrid frequency- and time-domain logging techniques are disclosed. The disclosed logging system and processing workflows combine frequency-domain and time-domain techniques to overcome the disadvantages of using frequency-domain or time domain tools in isolation.

Downhole nested pipe inspection using hybrid frequency and time domain logging technique

A method for estimating a pipe property for a plurality of nested tubulars. The method may comprise disposing an electromagnetic (EM) logging tool in a wellbore. The electromagnetic logging tool may comprise a transmitter disposed on the electromagnetic logging tool and a receiver disposed on the electromagnetic logging tool. The method may further comprise transmitting an electromagnetic field from the transmitter into one or more tubulars, measuring the eddy current in the pipe string with the receiver on at least one channel to obtain a plurality of measurements, forming an EM log from the plurality of measurements, extracting data and distinct features from the EM log, forming a relationship between the EM log data and a database, wherein the database is formed from one or more high-resolution measurements, and producing a mapping function between the EM log and the database.

Identifying corrosion from electromagnetic corrosion measurements and high-resolution circumferential measurements

A system may include an electromagnetic (EM) logging tool for inspecting downhole tubulars. The EM logging tool may include a mandrel, at least one low-frequency transmitter coil disposed on the mandrel, at least one-low frequency receiver coil disposed on the mandrel, and at least one-high frequency sensor configured to measure one or more electromagnetic properties of a tubular.

Downhole tubular inspection combining partial saturation and remote field eddy currents

A method for enhancing a formation property image may include taking at least one set of formation property measurements with a borehole imaging device, arranging the at least one set of formation property measurements into a two-dimensional image with a buffer, feeding the two-dimensional image into a deep-learning neural network (DNN), and forming a corrected formation property image from the two-dimensional image. The method may further include inverting the at least one set of formation property measurements to form at least one set of inverted formation property measurements and arranging the at least one set of inverted formation property measurements into a two-dimensional image with a buffer.

Deep learning methods for enhancing borehole images

A method and system for estimating a pipe property for a plurality of nested pipes. The method may comprise disposing an electromagnetic logging tool in a wellbore. The electromagnetic logging tool may comprise a transmitter disposed on the electromagnetic logging tool and a receiver disposed on the electromagnetic logging tool. The method may further comprise transmitting an electromagnetic field from the transmitter into a pipe string to energize the pipe string with the electromagnetic field thereby producing an eddy current that emanates from the pipe string, measuring the eddy current in the pipe string with the receiver on at least one channel to obtain a plurality of measurements, forming a log from the plurality of measurements, zoning the log into a plurality of zones based at least in part on a well plan, and extracting a representative signal for each zone of the plurality of zones.

Multi-zone processing of pipe inspection tools

Methods and systems for leak detection are provided herein. A method for leak detection can comprise conveying an acoustic leak detection tool inside the innermost tubular of the multiple nested tubulars; taking measurements of the multiple nested tubulars at multiple measurement depths with the acoustic leak detection tool; arranging the measurements into a response image; and feeding the response image to a pre-trained deep neural network (DNN) to produce a flow likelihood image, wherein the DNN comprises at least one convolutional layer, and wherein the flow likelihood image comprises a representation of one or more flow patterns in at least one annulus formed by the multiple nested tubulars.

Growing community of inventors

The Woodlands, TX, United States of America

Junwen Dai