Landmark Graphics Corporation

Manish Kumar Mittal

Robello Samuel

Aniket

Avinash Wesley

Nanda Kumar Nookala

(none) Aniket

The disclosure presents processes and methods for determining a packoff event at a location in a borehole undergoing a drilling operation. The packoff event can be represented by a packoff risk indicator (PRI) that presents, for example, a percentage risk of the packoff event occurring. The PRI can be utilized to initiate a remediation operation prior to the packoff event becoming more severe, such as a stuck drill string. In some aspects, the generation of the PRI can utilize an uncertainty model to provide a range of input parameters and an uncertainty parameter used by other systems to evaluate the risk of the potential packoff event has on borehole operations. In some aspects, the generation of the PRI can utilize machine learning algorithms or deep neural network algorithms to pre-process the input parameters to improve the accuracy of the PRI and of the models used to generate the PRI.

Predicting a drill string packoff event

Aspects and features of this disclosure relate to projecting physical drilling parameters to control a drilling operation. A computing system applies Bayesian optimization to a model incorporating the input data using varying values for an adverse drilling factor to produce a target function. The computing system determines a minimum value for the target function. The computing system provides a projected value for the physical drilling parameters based on the minimum value. The computing system generates an alert responsive to determining that the projected value for the physical drilling parameters exceeds a prescribed limit.

Physical parameter projection for wellbore drilling

A system is described for calculating and outputting micro invisible lost time (MILT). The system may include a processor and a non-transitory computer-readable medium comprising instructions that are executable by the processor to cause the processor to perform various operations. Time-stamp data that includes values of drilling parameters may be received about a drilling operation, and the values of drilling parameters may be classified into a rig state that includes rig activities. For each rig activity, an actual completion time may be determined and compared to an expected completion time for determining a deviation. At least one deviated activity, in which the deviation is greater than a threshold, may be determined. Deviations may be combined into MILT that can be output for controlling the drilling operation.

Micro invisible lost time in drilling operations

The disclosure presents processes and methods for determining an adjusted drag friction factor, where the adjusting utilizes a hole cleaning function. In some aspects, the drag friction factor utilizes viscous drag. In some aspects, the drag friction factor utilizes viscous torque. In some aspects, the drag friction factor can be utilized to determine one or more decomposed friction factors. The decomposed friction factors or the adjusted drag friction factor can be utilized in a friction processor to improve the efficiency of borehole operations. The hole cleaning function can utilize various parameters, for example, a cuttings density, a cuttings load, a cuttings shape, a cuttings size, a deviation, a drill pipe rotation rate, a drill pipe size, a flow regime, a hole size, a mud density, a mud rheology, a mud velocity, a pipe eccentricity, and other parameters. A system is disclosed that is capable of implementing the processes and methods.

Effect of hole cleaning on torque and drag

The disclosure presents processes and methods for decomposing friction factors and generating a calibrated friction factor and adjusted input parameters. The calibrated friction factor and adjusted input parameters can be utilized by a borehole system as an input to adjust borehole operations to improve the operational efficiency. The friction factors can be decomposed by type, such as geometrical, geomechanical, mechanical, and fluid. The disclosure also presents processes and methods for identifying an outlier portion of a friction factor, as identified by a deviation threshold that can be used to identify adjustments to borehole operations in that portion of the borehole. A system is disclosed that is capable of implementing the processes and methods in a borehole operation system, such as a downhole system, a surface system, or a distant system, for example, a data center, cloud environment, lab, corporate office, or other location.

Decomposed friction factor calibration

The disclosure presents processes and methods for utilizing one or more micro-services to generate a calibration of a factor of a borehole operation or to generate an optimization adjustment to the borehole operation. The micro-services selected for execution can be selected by an optimization workflow, where each type of borehole operation can have its own set of micro-services. The micro-services can be part of one or more computing systems, such as a downhole system, a surface system, a well site controller, a cloud service, a data center service, an edge computing system, other computing systems, or various combinations thereof. Also disclosed is a system for implementing micro-services on one or more computing systems to enable a light weight and fast response, e.g., real-time or near real-time response, to borehole operations.

Utilizing micro-services for optimization workflows of borehole operations

Multiple projected rate of penetration (ROP) values can be determined for purposes of adjusting well tools and well characteristics. For example, surface data can be determined based on a surface sensor signal. Downhole data can be determined based on a downhole sensor signal. A first value indicating a first projected ROP of a drill bit can be determined by providing the surface data as input to a first machine-learning model. A second value indicating a second projected ROP of the drill bit can be determined by providing the downhole data as input to a second machine-learning model. A third value indicating a third projected ROP of the drill bit can be determined by providing the first value and the second value input to a third machine-learning model. An operating characteristic of a well tool can be adjusted based on the third value.

Adjusting well tool operation to manipulate the rate-of-penetration (ROP) of a drill bit based on multiple ROP projections

Predicting casing wear, riser wear, and friction factors in drilling operations may be achieved with data-driven models that use discrete inversion techniques to updated casing wear models, riser wear models, and/or friction factor models. For example, a method may applying a linear inversion technique or a nonlinear inversion technique to one or more parameters of at least one of a casing wear model, a riser wear model, or a friction factor model using historical data from a previously drilled well as input data to produce at least one of an updated casing wear model, an updated riser wear model, or an updated friction factor model, respectively; and implementing the at least one of the updated casing wear model, the updated riser wear model, or the updated friction factor model when designing and/or performing a drilling operation.

Growing community of inventors

Houston, TX, United States of America

Manish Kumar Mittal