Landmark Graphics Corporation

Halliburton Energy Services, Inc.

Nishant Raizada

Srinath Madasu

Keshava Prasad Rangarajan

Robello Samuel

Mahdi Parak

Matthew Edwin Wise

Egidio Marotta

Jeffery L Grable

Moray Lamond Laing

Dale McMullin

Dale Mcmullin

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.

Dynamic drilling dysfunction codex

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.

Event prediction using state-space mapping during drilling operations

A system and method for controlling a drilling tool inside a wellbore makes use of projection of optimal rate of penetration (ROP) and optimal controllable parameters such as weight-on-bit (WOB), and rotations-per-minute (RPM) for drilling operations. Optimum controllable parameters for drilling optimization can be predicted using a data generation model to produce synthesized data based on model physics, an ROP model, and stochastic optimization. The synthetic data can be combined with real-time data to extrapolate the data across the WOB and RPM space. The values for WOB an RPM can be controlled to steer a drilling tool. Examples of models used include a non-linear model, a linear model, a recurrent generative adversarial network (RGAN) model, and a deep neural network model.

Rate of penetration optimization for wellbores using machine learning

A system for real-time steering of a drill bit includes a drilling arrangement and a computing device in communication with the drilling arrangement. The system iteratively, or repeatedly, receives new data associated the wellbore. At each iteration, a model, for example an engineering model, is applied to the new data to produce an objective function defining the selected drilling parameter. The objective function is modified at each iteration to provide an updated value for the selected drilling parameter and an updated value for at least one controllable parameter. In one example, the function is modified using Bayesian optimization The system iteratively steers the drill bit to obtain the updated value for the selected drilling parameter by applying the updated value for at least one controllable parameter over the period of time that the wellbore is being formed.

Iterative real-time steering of a drill bit

System and methods for optimizing parameters for drilling operations are provided. Real-time data including values for input variables associated with a current stage of a drilling operation along a planned well path are acquired. A neural network model is trained to produce an objective function defining a response value for at least one operating variable of the drilling operation. The response value for the operating variable is estimated based on the objective function produced by the trained neural network model. Stochastic optimization is applied to the estimated response value so as to produce an optimized response value for the operating variable. Values of controllable parameters are estimated for a subsequent stage of the drilling operation, based on the optimized response value of the operating variable. The subsequent stage of the drilling operation is performed based on the estimated values of the controllable parameters.

Growing community of inventors

Richmond, TX, United States of America

Nishant Raizada