Halliburton Energy Services, Inc.

The University of Texas System

National University of Singapore

Zoom Communications, Inc.

Yang Liu

Ketan Chimanlal Bhaidasna

Nazli Demirer

Kaixiao Tian

Robert Phillip Darbe

Hyunsoo Yang

John R Hardin

Julien Marck

Vy Pho

Dongmei Chen

He Zhang

Shuyuan Shi

Kaiming Cai

Saisamarth Rajesh Phaye

Kennedy J Kirkhope

Shichao Xu

Jiamin Xu

Qiyong Liu

A method that may comprise disposing a bottom hole assembly into a formation, wherein the bottom hole assembly comprises a mud motor, identifying a first segmented data set for a slide mode of the mud motor, and identifying a second segmented data set for a rotate mode of the mud motor. The method may further comprise calibrating the mud motor at least in part using a Reversible Jump Markov Chain Monte Carlo (RJMCMC), wherein the RJMCMC uses at least in part the first segmented data set and the second segmented data set.

Real-time tool yield calibration of mud motor

Artificial intelligence models are trained with training datasets of known input/output values. Test datasets are used to evaluate the trained artificial intelligence models. Context mismatch between the training dataset and the test dataset can slow down the development of artificial intelligence models. The described systems and methods can identify context similar datasets for the purpose of training and testing an artificial intelligence model. In one embodiment, a context similarity detector can ingest and combine a training dataset and a test dataset and generate a context similarity score for the two. If the score is above a threshold, the datasets are similar, and the relevant artificial intelligence model can be trained with one and tested with the other.

Context similarity detector for artificial intelligence

In directional drilling, a nonlinear Delay Differential Equation (DDE) model may be used for its high precision in predicting how a borehole may be drilled according to a well plan. To address challenges associated with real-time control of a drill drilling wellbore, techniques of generalized feedback linearization, finite element concept, and zero-order hold discretization may be used to transform a nonlinear DDE model into discretized domain with a linear Ordinary Differential Equation (ODE) form. Following this transformation, a novel optimization framework may be used to concurrently determine optimal control inputs and solve a linear complementarity problem (LCP). The validity of both the discretized model and the optimization strategy may be verified by comparing modeled results with real-world results. Subsequent closed-loop simulations demonstrate the ability of the proposed model predictive control to maintain alignment of a drill string with a planned well trajectory, even in the presence of disturbances and noise.

Nonlinear model predictive control for directional drilling applications

The disclosed embodiments include systems and methods to determine the steering of a bit. The method includes receiving input parameters associated with a model of a bottomhole assembly having a housing and a shaft that runs through an interior of the housing. The method also includes analyzing the housing as a first beam, and analyzing the shaft as a second beam that is nested within the first beam. The method further includes estimating a force and moment at a contact point between the shaft and the housing, determining a housing deflection based on the force and the moment, determining a shaft deflection at the contact point, and determining whether the shaft deflection is within a threshold of the housing deflection. In response to a determination that the shaft deflection is within the threshold of the housing deflection, the method further includes providing an output indicative of steering of a bit.

Systems and methods to determine the steering of a bit

Described is a spin torque device, and a spintronics device Incorporating the spin torque device. The spin torque device comprises a magnetic layer having a switchable magnetisation direction along a first axis, and a spin source layer adapted to generate a spin current from a current Injected along a second axis perpendicular to the first axis. Electrons of different spins in the spin source layer are rearranged by scattering so the spin current is generated in a plane perpendicular to the second axis and polarized at an angle to the first axis, so that the spin current diffuses into the magnetic layer to produce spin torque to switch the magnetisation direction.

Spin torque device having a spin current polarized at a canting angle of out-of-plane spin

Growing community of inventors

Singapore, Singapore

Yang Liu