公开(公告)号：US20210388710A1

公开(公告)日：2021-12-16

申请号：US16899946

申请日：2020-06-12

Applicant: Landmark Graphics Corporation

Inventor： Srinath Madasu

IPC: E21B44/00 ,  E21B47/07 ,  G05B13/04 ,  G05B13/02 ,  G06N3/08 ,  G06N3/04 ,  G06F30/27

Abstract: A system includes equipment for at least one of formation of, stimulation of, or production from a wellbore, a processor, and a non-transitory memory device. The processor is communicatively coupled to the equipment. The non-transitory memory device contains instructions executable by the processor to cause the processor to perform operations comprising training a hybrid deep generative physics neural network (HDGPNN), iteratively computing a plurality of projected values for wellbore variables using the HDGPNN, comparing the projected values to measured values, adjusting the projected values using the HDGPNN until the projected values match the measured values within a convergence criteria to produce an output value for at least one controllable parameter, and controlling the equipment by applying the output value for the at least one controllable parameter.

公开(公告)号：US20210355805A1

公开(公告)日：2021-11-18

申请号：US16651859

申请日：2019-12-05

Applicant: Landmark Graphics Corporation

Inventor： Keshava Prasad Rangarajan ,  Raja Vikram R. Pandya ,  Srinath Madasu ,  Shashi Dande

IPC: E21B44/00 ,  E21B49/00 ,  E21B7/06 ,  G06N5/02 ,  G06N20/00 ,  G01V99/00

Abstract: A system for controlling operations of a drill in a well environment. The system comprises a predictive engine, a ML engine, a controller, and a secure, distributed storage network. The predictive engine receives a variables associated with surface and sub-surface sensors and predicts an earth model based on the variables, predictor variable(s), outcome variable(s), and relationships between the predictor variable(s) and the outcome variable(s). The predictive engine is also configured to predict a drill path(s) ahead of the drill based on using stochastic modeling, an outcome variable(s), the predicted earth model, and a drilling model(s). The controller is configured to generate a system response(s) based on the predicted drill path(s) and a current state of the drill. The ML engine stores the earth model, the drill path(s), and the variables in the distributed storage network, trains data, and creates the drilling model(s).

公开(公告)号：US20210123334A1

公开(公告)日：2021-04-29

申请号：US17257234

申请日：2019-04-30

Applicant: Landmark Graphics Corporation

Inventor： Srinath Madasu ,  Keshava Prasad Rangarajan

IPC: E21B43/26 ,  G06F30/27 ,  G06F30/23 ,  G06N3/04 ,  G06N3/08 ,  E21B44/02

Abstract: System and methods for simulating fluid flow during downhole operations are provided. Measurements of an operating variable at one or more locations within a formation are obtained from a downhole tool disposed in a wellbore within the formation during a current stage of a downhole operation being performed along the wellbore. The obtained measurements are applied as inputs to a hybrid model of the formation. The hybrid model includes physics-based and machine learning models that are coupled together within a simulation grid. Fluid flow within the formation is simulated, based on the inputs applied to the hybrid model. A response of the operating variable is estimated for a subsequent stage of the downhole operation along the wellbore, based on the simulation. Flow control parameters for the subsequent stage are determined based on the estimated response. The subsequent stage of the operation is performed according to the determined flow control parameters.

公开(公告)号：US20210055442A1

公开(公告)日：2021-02-25

申请号：US17000117

申请日：2020-08-21

Applicant: Landmark Graphics Corporation

Inventor： Keshava Prasad Rangarajan ,  Raja Vikram R. Pandya ,  Srinath Madasu ,  Shashi Dande

IPC: G01V1/40 ,  H04L9/06 ,  G06K9/62 ,  G06N20/00

Abstract: A system, for controlling well site operations, comprising a machine learning engine, a predictive engine, a node system stack, and a blockchain. The learning engine includes a machine learning algorithm, an algorithmically generated earth model, and control variables. The learning algorithm generates a trained data model using the algorithmically generated earth model. The predictive engine includes an Artificial Intelligence (AI) algorithm. The AI algorithm generates a trained AI algorithm using the trained data model and earth model variables using the trained AI algorithm. The system stack is communicable coupled to the predictive engine, the learning engine, the blockchain, sensors, and a machine controller. The blockchain having a genesis block and a plurality of subsequent blocks. Each subsequent block comprising a well site entry and a hash of a previous entry. The well site entry comprises transacted operation control variables. The transacted variables are based on the generated earth model variables.

公开(公告)号：US20210027144A1

公开(公告)日：2021-01-28

申请号：US16981080

申请日：2018-05-15

Applicant: LANDMARK GRAPHICS CORPORATION

Inventor： Srinath Madasu ,  Yevgeniy Zagayevskiy ,  Terry Wong ,  Dominic Camilleri ,  Charles Hai Wang ,  Courtney Leeann Beck ,  Hanzi Mao ,  Hui Dong ,  Harsh Biren Vora

IPC: G06N3/04 ,  G06N3/08 ,  G06F30/20 ,  G01V99/00

Abstract: Using production data and a production flow record based on the production data, a deep neural network (DNN) is trained to model a proxy flow simulation of a reservoir. The proxy flow simulation of the reservoir is performed, using an ensemble Kalman filter (EnKF), based on the trained DNN. The EnKF assimilates new data through updating a current ensemble to obtain history matching by minimizing a difference between a predicted production output from the proxy flow simulation and measured production data from a field. Using the updated current ensemble, a second proxy flow simulation of the reservoir is performed based on the trained DNN. The assimilating and the performing are repeated while new data is available for assimilating. Predicted behavior of the reservoir is determined based on the proxy flow simulation of the reservoir. An indication of the predicted behavior is provided to facilitate production of fluids from the reservoir.

公开(公告)号：US20200248540A1

公开(公告)日：2020-08-06

申请号：US16652171

申请日：2017-12-18

Applicant: Landmark Graphics Corporation

Inventor： Srinath Madasu ,  Yogendra Narayan Pandey ,  Keshava Prasad Rangarajan

IPC: E21B43/16 ,  G06N3/08 ,  E21B47/00 ,  G06N3/04

Abstract: A method includes performing a first wellbore treatment operation of a wellbore, determining an operational attribute of the well in response to the first wellbore treatment operation, and determining a predicted response using a recurrent neural network and based on the operational attribute. The method also includes setting a controllable wellbore treatment attribute based, on the predicted response, and performing a second wellbore treatment operation of the wellbore based on the controllable well bore treatment attribute.

公开(公告)号：US12104489B2

公开(公告)日：2024-10-01

申请号：US17619784

申请日：2020-02-10

Applicant: Landmark Graphics Corporation

Inventor： Raja Vikram Raj Pandya ,  Srinath Madasu ,  Keshava Prasad Rangarajan ,  Shashi Dande ,  Yashas Malur Saidutta

IPC: E21B7/04 ,  E21B44/02

CPC classification number: E21B7/04 ,  E21B44/02

Abstract: Geosteering can be used in a drilling operation to create a wellbore that is used to extract hydrocarbons from a defined zone within the subterranean formation. According to some aspects, generating paths for the wellbore may include using path-planning protocols and pure-pursuit protocols. The pure-pursuit protocol may be executed to output a plurality of candidate drilling paths. The output may also include control parameters for controlling the drill bit. A trajectory optimizer may determine a result of multi-objective functions for each candidate path. A cost function may represent a cost or loss associated with a candidate path. Additionally, the trajectory optimizer may perform an optimization protocol, such as Bayesian optimization, on the cost functions to determine which candidate path to select. The selected candidate path may correspond to new control parameters for controlling the drill bit to reach the target location.

公开(公告)号：US12061980B2

公开(公告)日：2024-08-13

申请号：US16642452

申请日：2017-12-26

Applicant: Landmark Graphics Corporation

Inventor： Andrey Filippov ,  Jianxin Lu ,  Avinash Wesley ,  Keshava P. Rangarajan ,  Srinath Madasu

IPC: G06N3/08 ,  G06F30/23 ,  G06F30/27 ,  G06F30/28 ,  G06F113/08 ,  G06T17/20

CPC classification number: G06N3/08 ,  G06F30/23 ,  G06F30/27 ,  G06F30/28 ,  G06T17/20 ,  G06F2113/08

Abstract: System and methods for training neural network models for real-time flow simulations are provided. Input data is acquired. The input data includes values for a plurality of input parameters associated with a multiphase fluid flow. The multiphase fluid flow is simulated using a complex fluid dynamics (CFD) model, based on the acquired input data. The CFD model represents a three-dimensional (3D) domain for the simulation. An area of interest is selected within the 3D domain represented by the CFD model. A two-dimensional (2D) mesh of the selected area of interest is generated. The 2D mesh represents results of the simulation for the selected area of interest. A neural network is then trained based on the simulation results represented by the generated 2D mesh.

公开(公告)号：US11873707B2

公开(公告)日：2024-01-16

申请号：US16629231

申请日：2018-03-09

Applicant: LANDMARK GRAPHICS CORPORATION

Inventor： Srinath Madasu ,  Nishant Raizada ,  Keshava Rangarajan ,  Robello Samuel

IPC: E21B44/02 ,  G06N20/00 ,  E21B7/04 ,  E21B45/00

CPC classification number: E21B44/02 ,  E21B7/04 ,  E21B45/00 ,  G06N20/00

Abstract: 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.

公开(公告)号：US11668684B2

公开(公告)日：2023-06-06

申请号：US16956605

申请日：2019-07-23

Applicant: Landmark Graphics Corporation

Inventor： Srinivasan Jagnnathan ,  Oluwatosin Ogundare ,  Srinath Madasu ,  Keshava Rangarajan

IPC: G01N29/44 ,  G06N3/047

CPC classification number: G01N29/4472 ,  G01N29/4481 ,  G06N3/047 ,  G01N2291/2634

Abstract: Methods and systems for solving inverse problems arising in systems described by a physics-based forward propagation model use a Bayesian approach to model the uncertainty in the realization of model parameters. A Generative Adversarial Network (“GAN”) architecture along with heuristics and statistical learning is used. This results in a more reliable point estimate of the desired model parameters. In some embodiments, the disclosed methodology may be applied to automatic inversion of physics-based modeling of pipelines.