Abstract:
Methods, computing systems, and machine-readable media for detecting downhole sand entry points are provided. A computing device receives a sand detection output of a product sand detection tool and a raw timeseries waveform corresponding to an input to the product sand detection tool. Based on the sand detection output, at least one downhole sand entry point is detected at a logging depth. In response to the detecting of the at least one downhole sand entry point. the computing device extracts a subset of features based on the raw timeseries waveform. The computing device determines whether the detecting is a true positive or a false positive based on the extracted subset of the features and a trained Random Forest classifier. A remedial action is performed regarding the at least one downhole sand entry point responsive to the determining that the detecting is the true positive.
Abstract:
A method of producing a geothermal well includes obtaining site information including at least a site volume; obtaining drilling parameters; determining lengths and orientations of planned wellbores based at least partially on the site information and the drilling parameters.
Abstract:
The disclosure relates to a method for flagging at least an event of interest in an unlabeled time series of a parameter relative to a wellsite (including to the well, formation or a wellsite equipment), wherein the time series of the parameter is a signal of the parameter as a function of time. The disclosure also relates to a method for evaluation a downhole operation such as a pressure test using a pressure time series. Such methods comprises collecting a time series, extracting at least an unlabeled subsequence of predetermined duration in the time series, and assigning an event of interest a label, in particular representative of the status of the downhole operation, to at least one of the unlabeled subsequences. A command may be sent to a wellsite operating system based on assigned label.
Abstract:
The present disclosure introduces an apparatus including a toolstring for use in a tubular extending into a subterranean formation. The toolstring includes modular components that include one or more caliper modules and a power and control (P/C) module. The one or more caliper modules each include radially rotatable fingers for sensing an internal diameter of the tubular. The P/C module is operable for distributing power and control signals to the one or more caliper modules. The caliper and P/C modules are mechanically and electrically interconnected by common lower interfaces of the caliper and P/C modules.
Abstract:
The disclosure relates to a method and system for downhole processing of data, such as images, including using a set of downhole sensors to measure parameters relative to the borehole at a plurality of depths and azimuths and detecting predetermined features of the borehole, using a downhole processor, with a trained machine-learning model and extracting characterization data, characterizing the shape and position of the predetermined features that are transmitted to the surface. It also provides a method and system for providing an image of a geological formation at the surface including transmitting a first dataset to the surface that will be used for reconstructing an image at the surface, downhole processing of a second dataset to detect predetermined features and extract characterization data that are transmitted at the surface and displaying a combined image comprising the predetermined features overlaid on the first image.
Abstract:
The techniques and device provided herein relate to receiving, via a processor, image data representative of a borehole of a well. The technique may include generating dequantized image data based on the image data, such that the dequantized image data filters one or more artifacts present in a Hough transformed version of the image data. One or more dip orientations (inclination and azimuth) associated with one or more formation dips present in the image data may be determined based on the dequantized image data. The technique may also include performing an a-contration validation algorithm for for the one or more formation dips to verify whether at least a formation dip having the or one of the possible dip orientation is present at a predetermined measured depth in the image data.
Abstract:
A logging method and a logging tool for approximating a logging tool response in a layered formation are provided. The method includes obtaining a first layered profile of at least one first measurement log provided by a logging tool using a squaring process, obtaining a filtered measurement log from the first layered profile using a forward physical model for the logging tool, and estimating an approximation of the forward physical model using a parameterized function so as to provide a first logging tool response.
Abstract:
A method can include receiving remarks associated with one or more field operations; processing the remarks for event detection using a dependency matcher and a machine learning model, where, responsive to the dependency matcher failing to detect an event, the processing implements the machine learning model to detect the event; and outputting at least the detected event.
Abstract:
A general-purpose workflow for automatic borehole sonic data classification to identify data into different physical categories and logging conditions, which are traditionally manually evaluated. The workflow uses machine learning techniques and physical knowledge for data classification, including pre-processing the high-dimensional high-quality dispersion modes extracted using a recently developed physical-driven ML enabled approach.
Abstract:
Planning a wellbore includes determining drillability values from surface drilling parameters for an offset wellbore. The drillability values are used to prepare a protein code sequence of protein codes assigned to a range of drillability values. The protein code sequence from the offset wellbore is used to develop a protein code sequence for a planned wellbore. A machine learning model analyzes the offset surface drilling parameters and protein code sequence, and provides target surface drilling parameters for the planned wellbore.