Abstract: A method of data preparation for artificial intelligence models includes receiving data characterizing a first plurality of images. The method further includes annotating a first subset of images of the first plurality of images based at least in part on a first user input to generate annotated first subset of images. The annotating includes labelling one or more features of the first subset of images. The method also includes generating, by a training code, an annotation code, the training code configured to receive the annotated first subset of images as input and output the annotation code. The training and the annotation code includes computer executable instructions. The method also includes annotating, by the annotation code, a second subset of images of the first plurality of images to generate annotated second subset of images, wherein the annotating includes labelling one or more features of the second subset of images.

Abstract: A method of data preparation for artificial intelligence models includes receiving data characterizing a first plurality of images. The method further includes annotating a first subset of images of the first plurality of images based at least in part on a first user input to generate annotated first subset of images. The annotating includes labelling one or more features of the first subset of images. The method also includes generating, by a training code, an annotation code, the training code configured to receive the annotated first subset of images as input and output the annotation code. The training and the annotation code includes computer executable instructions. The method also includes annotating, by the annotation code, a second subset of images of the first plurality of images to generate annotated second subset of images, wherein the annotating includes labelling one or more features of the second subset of images.

Abstract: An inspection method includes receiving a plurality of training images and an image of a target object obtained from inspection of the target object. The method further includes generating, by one or more training codes, a plurality of inference codes. The one or more training codes are configured to receive the plurality of training images as input and output the plurality of inference codes. The one or more training codes and the plurality of inference codes includes computer executable instructions. The method further includes selecting one or more inference codes from the plurality inference codes based on a user input and/or one or more characteristics of at least a portion of the received plurality of training images. The method also includes inspecting the received image using the one or more inference codes of the plurality of inference codes.

Abstract: A stochastic control method includes determining a property of a solid present in a drilling fluid circulating within a mud circulation system and identifying a mud circulation model that dictates operation of the mud circulation system. The mud circulation model is based on one or more models of one or more uncertainties encountered during a wellbore drilling operation. The method further includes determining an accuracy of the mud circulation model based on a difference between the determined property of the solid present in the drilling fluid and a solid property of the drilling fluid as provided by the mud circulation model, and programming a controller of the mud circulation system based on the mud circulation model to modify operation of the mud circulation system.

Abstract: A distributed monitoring and analytics system is configured to automatically monitor conditions in a remote oil field. The distributed monitoring and analytics system generally includes one or more mobile monitoring units that each includes a vehicle, a sensor package within the vehicle that is configured to produce one or more sensor outputs as the mobile monitoring unit traverses the remote oil field, and an onboard computer configured to process the output from the sensor package. The sensor package can include any number of sensors, including a camera that outputs a video signal for computer vision analysis and a gas detector that outputs a gas detection signal based on the detection of fugitive gas emissions within the remote oil field.

Abstract: A method of estimating a state of a rotary steerable drilling system comprising applying a control input to a rotary steerable drilling system, sensing an actual output of the rotary steerable drilling system, inputting the control input into a mathematical model of the rotary steerable drilling system, receiving an estimated output of the rotary steerable drilling system from the mathematical model, generating an error compensation signal based on a difference between the actual output and the estimated output, and applying the error compensation signal to the mathematical model.

Abstract: In accordance with some embodiments of the present disclosure, systems and methods for a nonlinear toolface control system for a rotary steerable drilling tool is disclosed. The method includes determining a desired toolface of a drilling tool, calculating a toolface error by determining a difference between a current toolface and the desired toolface, generating a model to describe the dynamics of the drilling tool, modify the model, based on at least one intermediate variable, to create a modified model, calculating a correction to reduce the toolface error, the correction based on the modified model, transmitting a signal to the drilling tool such that the signal adjusts the current toolface based on the correction, and drilling a wellbore with a drill bit oriented at the desired toolface.

Abstract: In accordance with some embodiments of the present disclosure, systems and methods for an advanced toolface control system for a rotary steerable drilling tool is disclosed. The method includes determining a desired toolface of a drilling tool, calculating a toolface error by determining a difference between a current toolface of the drilling tool and the desired toolface, decoupling a response of a first component of the drilling tool, calculating a correction to reduce the toolface error based on a model of the drilling tool containing information about a source of the toolface error, transmitting a signal to a second component of the drilling tool such that the signal adjusts the current toolface based on the correction, and drilling a wellbore with a drill bit oriented at the desired toolface.

Abstract: In accordance with some embodiments of the present disclosure, systems and methods for a gain scheduling based toolface control system for a rotary steerable drilling tool are disclosed. The method includes determining a desired toolface of a drilling tool, calculating a toolface error by determining a difference between a current toolface and the desired toolface, determining a plurality of operating points of the drilling tool, selecting one of the plurality of operating points based on a current operating point of the drilling tool, determining a model based on the selection, calculating a correction to correct the toolface error, the correction based on the model, transmitting a signal to the drilling tool such that the signal adjusts the current toolface based on the correction, and drilling a wellbore with a drill bit oriented at the desired toolface.

Abstract: A stochastic control method includes determining a property of a solid present in a drilling fluid circulating within a mud circulation system and identifying a mud circulation model that dictates operation of the mud circulation system. The mud circulation model is based on one or more models of one or more uncertainties encountered during a wellbore drilling operation. The method further includes determining an accuracy of the mud circulation model based on a difference between the determined property of the solid present in the drilling fluid and a solid property of the drilling fluid as provided by the mud circulation model, and programming a controller of the mud circulation system based on the mud circulation model to modify operation of the mud circulation system.

Abstract: In some aspects, the present disclosure includes systems and methods for optimizing one or more of a number of sensors on a drillstring or the locations of the sensors on the drillstring, or the types of the sensors. The method includes determining a number of sensors to place on a drillstring, a location for each of the sensors based, and types of sensors based, at least in part, on one or more of a state reduction technique and an optimization framework. The method includes disposing the selected number of sensors along the drilling and performing a drilling operation.

Abstract: A stochastic control method includes measuring a fluid property of a drilling fluid circulating within a mud circulation system and identifying a mud circulation model that dictates operation of the mud circulation system. The mud circulation model is based on one or more models of one or more uncertainties encountered during a wellbore drilling operation. The method further includes determining an accuracy of the mud circulation model based on a residue between the measured fluid property of the drilling fluid and a fluid property of the drilling fluid as provided by the mud circulation model, and programming a controller of the mud circulation system based on the mud circulation model to modify operation of the mud circulation system.

Abstract: A system including an energy industry operation component and a processing system associated with the energy industry operation component is provided. The processing system includes an accelerator and is configured to perform at least one of image segmentation and vision analysis for authenticated lockout, image segmentation and vision analysis for performance audit, or augmented reality rendering and streaming.

Abstract: Methods and systems are provided for optimizing a drill path from the surface to a target area below the surface. A method for operating an automated drilling program may comprise drilling to a target location along a drill path, updating a drilling path model based at least on data obtained during the state of drilling to the target location, creating a modified drill path to the target location based on at least the drilling path model in real-time as the step of drilling to the target location along the drill path is being performed, and drilling to the target location along the modified drill path.

Abstract: Methods and systems for enhancing workflow performance in the oil and gas industry may include modeling preferred sensor locations, sensor types, and sampling frequency for effective and efficient monitoring of a mud circulation system. For example, a method may include circulating a mud through a mud circulation system that includes a plurality of sensors that include at least one of: a pressure sensor, a stroke counter, a flow sensor, a viscosity sensor, or density sensor; and modeling the plurality of sensors using a state reduction approach to determine at least one selected from the group consisting of preferred locations, preferred sensory types, preferred sensor frequency resolution, and a combination thereof that effectively represent or substantially impact conditions of the mud circulation system, thereby providing a preferred sensor scheme.

Abstract: In accordance with some embodiments of the present disclosure, systems and methods for a feedback based toolface control system for a rotary steerable drilling tool is disclosed. The method includes determining a desired toolface of a drilling tool, calculating a toolface error, calculating a correction to correct the toolface error by: estimating, using a model, an output of each of a plurality of states of the model based on an input to each of the states of the model and determining a desired input to each of the plurality of states, beginning at the toolface, based on a desired output of at least one of the plurality of states connected to a particular state, transmitting the signal to the input component of the drilling tool such that the signal adjusts the current toolface based on the correction, and drilling a wellbore with a drill bit oriented at the desired toolface.

Abstract: During drilling operations various drilling mud properties may be measured and predicted. Uncertainties in the measured or predicted values may also be calculated. The estimated uncertainties may then be used to optimize mud sampling interval and/or control a mud mixer. A decision making algorithm may be performed to optimize a surface mud sampling interval such that the uncertainties are maintained within a bounded region with minimal number of sampling times.

Abstract: Two control strategies may be implemented to optimize mud circulation in a drilling mud circulation system. In a networked control strategy, the mud circulation system does not involve any centralized controller yet all the local controllers can exchange information in real-time via a central data storage. The master-slave control strategy involves a centralized optimizer, and the subsystems are treated as slave systems and are driven by a visual master control system.

Abstract: A stochastic control method includes measuring a fluid property of a drilling fluid circulating within a mud circulation system and identifying a mud circulation model that dictates operation of the mud circulation system. The mud circulation model is based on one or more models of one or more uncertainties encountered during a wellbore drilling operation. The method further includes determining an accuracy of the mud circulation model based on a residue between the measured fluid property of the drilling fluid and a fluid property of the drilling fluid as provided by the mud circulation model, and programming a controller of the mud circulation system based on the mud circulation model to modify operation of the mud circulation system.

Abstract: A method of estimating a state of a rotary steerable drilling system comprising applying a control input to a rotary steerable drilling system, sensing an actual output of the rotary steerable drilling system, inputting the control input into a mathematical model of the rotary steerable drilling system, receiving an estimated output of the rotary steerable drilling system from the mathematical model, generating an error compensation signal based on a difference between the actual output and the estimated output, and applying the error compensation signal to the mathematical model.