General Electric Company

Baker Hughes Oilfield Operations LLC

Nurali Virani

Scott Charles Evans

Naresh Sundaram Iyer

Samuel Bryan Shartzer

Samuel Davoust

Johan Michael Reimann

Mahendra L Joshi

Stephen William Piche

Danian Zheng

Andrew Walter Crapo

Yan Liu

Varish Vyankatesh Mulwad

Jason Michael Nichols

Brian Allen Rittenhouse

Fred Francis Pickard

Guoxiang Liu

Dewey Lavonne Parkey, Jr

Robert Klenner

Sara Simonne Louisa Delport

Dhiraj Arora

Hayley Stephenson

Abhishek Srivastav

Alvaro Enrique Gil

Robert Nicholas Petro

Raul Munoz

Glenn Richard Murrell

Zhaoyuan Yang

Ricardo Zetina

A system, method, and computer-readable medium to extract information from at least one of code and text documentation, the extracted information conforming to a base ontology and being extracted in the context of a knowledge graph; add the extracted information to the knowledge graph; generate, in a mixed interaction with a user selectively in communication with the system, computational models including scientific knowledge; and persist, in a memory, a record of the generated computational models.

Method and system for principled approach to scientific knowledge representation, extraction, curation, and utilization

A system and method including receiving a set of deep neural networks (DNN) including DNNs trained with an embedded trojan and DNNs trained without any embedded trojan, each of the trained DNNs being represented by a mathematical formulation learned by the DNNs and expressing a relationship between an input of the DNNs and an output of the DNNs; extracting at least one characteristic feature from the mathematical formulation of each of the trained DNNs; statistically analyzing the at least one characteristic feature to determine whether there is a difference between the DNNs trained with the embedded trojan and the DNNs trained without any embedded trojan; generating, in response to the determination indicating there is a difference, a detector model to execute the statistical analyzing on deep neural networks; and storing a file including the generated detector model in a memory device.

Fast identification of trustworthy deep neural networks

A method for determining a location and trajectory for a new wellbore relative to an adjacent wellbore includes: receiving controllable variable data and uncontrollable variable data related to fracturing a formation by a stimulation operation in a first wellbore penetrating the formation; receiving pressure communication event or pressure non-communication event identification data related to identification of a pressure communication event or pressure non-communication event in a second wellbore penetrating the formation in response to the fracturing; extracting features from the controllable and uncontrollable variable data to provide extracted features; detecting a pressure communication event using the extracted features and the pressure communication event or pressure non-communication event identification data using an analytic technique; identifying one or more quantified causes of the detected pressure communication event using an artificial intelligence technique; and determining the location and trajectory of the new wellbore using the one or more quantified causes.

Process for infill well development in a subsurface reservoir

According to some embodiments, a system, method and non-transitory computer-readable medium are provided comprising a Hypothesis Generation Engine (HGE) to receive one or more property target values for a material; a memory for storing program instructions; an HGE processor, coupled to the memory, and in communication with the HGE, and operative to execute program instructions to: receive the one or more property target values for the material; analyze the one or more property target values as compared to one or more known values in a knowledge base; generate, based on the analysis, an initial set of hypothetical structures, wherein each hypothetical structure includes at least one property target value; execute a likelihood model for each candidate material to generate a likelihood probability for each hypothetical structure, wherein the likelihood probability is a measure of the likelihood that the hypothetical structure will have the target property value; convert each hypothetical structure into a natural language representation; execute an abduction kernel on the natural language representation with the at least one likelihood probability, to output at least one proposed structure that satisfies a likelihood threshold for having the property target value; and receive the output of the executed abduction kernel at a testing module to determine whether the output satisfies the property target values. Numerous other aspects are provided.

Autonomous reasoning and experimentation agent for molecular discovery

A control system is disclosed. The control system includes a wind turbine, at least one sensor configured to detect at least one property of the wind turbine to generate measurement data, and a controller communicatively coupled to the wind turbine and the at least one sensor. The controller includes at least one processor in communication with at least one memory device. The at least one processor is configured to control, during a training phase, the wind turbine according to at least one test parameter, receive, from the at least one sensor, during the training phase, first measurement data, generate, based on the at least one test parameter and the received first measurement data, a control model, receive, during an operating phase, second measurement data from the at least one sensor, and update the control model continuously based on the second measurement data.

Systems and methods for continuous machine learning based control of wind turbines

According to some embodiments a competence module is provided to: receive an objective; select a machine learning model associated with the objective; receive data from the at least one data source; determine at least one next input based on the received data; determine whether the at least one next input is in a competent region or is in an incompetent region of the machine learning model; when the at least one next input is inside the competent region, generate an output; determine an estimate of uncertainty for the generated output; when the uncertainty is below an uncertainty threshold, the machine learning model is competent and when the uncertainty is above the uncertainty threshold, the machine learning model is incompetent; and operate the physical asset based on one of the competent and incompetent state of the machine learning model. Numerous other aspects are provided.

Method and system for competence monitoring and contiguous learning for control

A method for assessing or validating wind turbine or wind farm performance produced by one or more upgrades is provided. Measurements of operating data from wind turbines in a wind farm are obtained. Baseline models of performance are generated, and each of the baseline models is developed from a different portion of the operating data. A generating step filters the wind turbines so that they are in a balanced randomized state. An optimal baseline model of performance is selected from the baseline models and the optimal baseline model includes direction. The optimal baseline model of performance and an actual performance of the wind farm or wind turbine is compared. The comparing step determines a difference between an optimal baseline model of power output and an actual power output of the wind farm/turbine. The difference is reflective of a change in the power output produced by the upgrades.

System and method for assessing and validating wind turbine and wind farm performance

A system that includes: a gas turbine having a combustion system; a control system operably connected to the gas turbine for controlling an operation thereof; and a combustion auto-tuner, which is communicatively linked to the control system, that includes an optimization system having an empirical model of the combustion system and an optimizer; sensors configured to measure the inputs and outputs of the combustion system; a hardware processor; and machine-readable storage medium on which is stored instructions that cause the hardware processor to execute a tuning process for tuning the operation of the combustion system. The tuning process includes the steps of: receiving current measurements from the sensors for the inputs and outputs; given the current measurements received from the sensors, using the optimization system to calculate an optimized control solution for the combustion system; and communicating the optimized control solution to the control system.

Control and tuning of gas turbine combustion

A method for controlling operation of a wind turbine includes collecting training data, training a machine learning model, obtaining recent data, and applying the machine learning model the recent data to output a reference power or reference power differential corresponding to the recent data. The machine learning model is then applied to the recent data to output at least one of estimated power or estimated power differential corresponding to values of the pitch setpoints and the tip speed ratio setpoints which differ from the recent data. A turbine setting is determined by comparing the estimated power or estimated power differential to the reference power or reference power differential, and then applying the turbine setting to the wind turbine if the estimated power or estimated power differential is greater than or equal to a threshold amount above the reference power or reference power differential.

Method for controlling operation of a wind turbine

Growing community of inventors

Niskayuna, NY, United States of America

Nurali Virani