Abstract: System and methods for event prediction during drilling operations are provided. Regression data associated with coefficients of a predictive model are retrieved for a downhole event during a drilling operation along a planned path of a wellbore. The regression data includes a record of changes in historical coefficient values associated with prior occurrences of the event. As the wellbore is drilled over different stages of the operation, a value of an operating variable is estimated based on values of the coefficients and real-time data acquired during each stage. A percentage change in coefficient values adjusted between successive stages of the operation is tracked. An occurrence of the downhole event is estimated, based on a correlation between the percentage change tracked for at least one coefficient and a corresponding change in the historical coefficient values. The path of the wellbore is adjusted, based on the estimated occurrence of the event.

Abstract: A container stack configurator can build customized software applications and deploy the applications to a wellbore computing network or through offline installer devices. The stack configurator can receive a selection from a user of a configuration repository. The stack configurator can determine available branches of the configuration repository including images, tags, and container names. The stack configurator can present a list of services associated with the container names to the user using a user interface. The stack configurator can receive a selection of an installer type and generate a customized build of the installer type. The customized build of the installer can be an offline installer that is deployable on an offline target machine using a first communication media or an online installer that is deployable to an online target machine using a second communication media.

Abstract: Introduced herein are techniques that can create descriptive taxonomies of expected data streams and identify and associate each incoming data stream with the taxonomies automatically. The introduced techniques can significantly reduce the human intervention and efforts and hence the number of human errors in identifying and mapping signals. The introduced techniques can also automatically store values of the data streams and their corresponding taxonomies as facts and dimensions in a business intelligence (BI) data repository/warehouse. Doing so, the techniques create a BI data repository with various sets of logically nested dimensions and facts that can be used to analyze performances of various assets in petroleum service environment. Leveraging their similar hierarchical structures and elements, the techniques can expand and combine taxonomies and allow an end user to, not only analyze performances of assets in a specific rig, but across multiple rigs and projects, which were not possible before.

Abstract: A container stack configurator can build customized software applications and deploy the applications to a wellbore computing network or through offline installer devices. The stack configurator can receive a selection from a user of a configuration repository. The stack configurator can determine available branches of the configuration repository including images, tags, and container names. The stack configurator can present a list of services associated with the container names to the user using a user interface. The stack configurator can receive a selection of an installer type and generate a customized build of the installer type. The customized build of the installer can be an offline installer that is deployable on an offline target machine using a first communication media or an online installer that is deployable to an online target machine using a second communication media.

Abstract: Systems and methods can automatically and dynamically determine an optimum frequency for data being input into a drilling optimization tool in order to provide predictive modeling for well drilling operations. The methods and systems selectively input sets of data having different frequencies into the drilling optimization tool to build different predictive models at different frequencies. An optimization algorithm such as Bayesian optimization is then applied to the models to identify in real time an optimum frequency for the data sets being input into the drilling optimization tool based on current operational and environmental parameters.

Abstract: Fluid production can be simulated using a reservoir model and a tubing model. For example, pressure data and saturation data can be received from a reservoir model simulating a hydrocarbon reservoir in a subterranean formation. A tubing model can be generated by performing nodal analysis using the pressure data and the saturation data. A well-test result can be received that indicates an amount of fluid produced by the wellbore at a particular time. A tuned tubing model can be generated by adjusting the tubing model such that a tubing-model estimate of the amount of fluid produced by the wellbore at the particular time matches the well-test result. An estimated amount of fluid produced by the wellbore can then be determined using the tuned tubing model. The estimated amount of fluid produced by the wellbore may be used for production allocation or controlling a well tool.

Abstract: A method of generating, at an IIOT device mounted to equipment of a drilling system, a relay variable, a measurement variable, or a control variable and a message having an IP address. Classifying, by application services of a cloud service provider, the relay variable, the measurement variable, or the control variable; identifying a category or a category and sub-category from a plurality of categories and sub-categories based on variable; cataloguing the relay variable, the measurement variable, or the control variable based on the category or the category and the sub-category; selecting from a library of catalogued relay variables, measurement variables, and control variables, at least one selected from a group comprising a parameter and a value; and identifying a pattern using a statistics based algorithm, the statistics based algorithm using a standard operating procedure, the parameter and the value, the pattern indicating a deviation in the standard operating procedure.

Abstract: An apparatus used to provide preprocessed variables to a predictive engine. The predictive engine generates predictive results, based on the variables, to automate well site operations. The apparatus comprises an analysis module, a pattern recognition module, and a library module. The analysis module identifies a well site operation by examining a well site operation variable, determines categories and standard operating procedures associated with the categories using the well site operation and a-priori information, and searches a library of historical information using the categories. The historical information comprising classified procedures and recommendations of historic well site operations. The pattern recognition module identifies a pattern using a statistics based algorithm. The algorithm uses the standard operating procedures, the categories, and the classified procedures and recommendations. The pattern indicating a deviation in the standard operating procedure.

Abstract: System and methods for event prediction during drilling operations are provided. Regression data associated with coefficients of a predictive model are retrieved for a downhole event during a drilling operation along a planned path of a wellbore. The regression data includes a record of changes in historical coefficient values associated with prior occurrences of the event. As the wellbore is drilled over different stages of the operation, a value of an operating variable is estimated based on values of the coefficients and real-time data acquired during each stage. A percentage change in coefficient values adjusted between successive stages of the operation is tracked. An occurrence of the downhole event is estimated, based on a correlation between the percentage change tracked for at least one coefficient and a corresponding change in the historical coefficient values. The path of the wellbore is adjusted, based on the estimated occurrence of the event.

Abstract: Systems and methods can automatically and dynamically determine an optimum frequency for data being input into a drilling optimization tool in order to provide predictive modeling for well drilling operations. The methods and systems selectively input sets of data having different frequencies into the drilling optimization tool to build different predictive models at different frequencies. An optimization algorithm such as Bayesian optimization is then applied to the models to identify in real time an optimum frequency for the data sets being input into the drilling optimization tool based on current operational and environmental parameters.

Abstract: Aspects of the subject technology relate to systems and methods for predicting dysfunctions in physical systems. A dysfunction codex can be provided that includes a plurality of dysfunction models for predicting one or more dysfunctions in a physical system based on one or more specific contexts of the physical system. The dysfunction codex can be applied by selecting a dysfunction model of the plurality of dysfunction models within the dysfunction codex to apply based on the one or more specific contexts of the physical system. Further, a dysfunction of the physical system can be predicted by applying the dysfunction model to input system data of the physical system to predict the dysfunction of the physical system.

Abstract: Fluid production can be simulated using a reservoir model and a tubing model. For example, pressure data and saturation data can be received from a reservoir model simulating a hydrocarbon reservoir in a subterranean formation. A tubing model can be generated by performing nodal analysis using the pressure data and the saturation data. A well-test result can be received that indicates an amount of fluid produced by the wellbore at a particular time. A tuned tubing model can be generated by adjusting the tubing model such that a tubing-model estimate of the amount of fluid produced by the wellbore at the particular time matches the well-test result. An estimated amount of fluid produced by the well-bore can then be determined using the tuned tubing model. The estimated amount of fluid produced by the wellbore may be used for production allocation or controlling a well tool.