Halliburton Energy Services, Inc.

Halliburton Company

John M Richardson

Roger Lynn Schultz

Bruce H Storm, Jr

John R Dennis

Leonard R Case

Larry Thomas Watters

Thomas E Allen

Richard L Duncan

Mark A Clark

Gary E Folmnsbee

Freddie L Sabins

James M Macadam

Gary D Arnold

Jerry L Gammill

A method of optimizing performance of a well system utilizes a neural network. In a described embodiment, the method includes the step of accumulating data indicative of the performance of the well system in response to variable influencing parameters. The data is used to train a neural network to model an output of the well system in response to the influencing parameters. An output of the neural network may then be input to a valuing model, e.g., to permit optimization of a value of the well system. The optimization process yields a set of prospective influencing parameters which may be incorporated into the well system to maximize its value.

Field/reservoir optimization utilizing neural networks

Methods are provided for downhole sensing and flow control utilizing neural networks. In a described embodiment, a temporary sensor is positioned downhole with a permanent sensor. Outputs of the temporary and permanent sensors are recorded as training data sets. A neural network is trained using the training data sets. When the temporary sensor is no longer present or no longer operational in the well, the neural network is capable of determining the temporary sensor's output in response to the input to the neural network of the permanent sensor's output.

Downhole sensing and flow control utilizing neural networks

A method of evaluating a slurry mixing and placing process, such as a cementing process, for an oil or gas well comprises identifying and measuring specific subprocesses and parameters thereof, statistically summarizing the parameters and creating a database thereof, and analyzing the statistically summarized parameters to identify or compare against process capabilities to reduce variation, thereby improving specific job performance and the overall process.

Method of evaluating oil or gas well fluid process

A method of discriminating between linear and nonlinear regions of measured data is based upon two hypotheses, one of which is a hypothesis that a response is merely a result of inherent randomness and the other of which is a hypothesis that the response is a result of a true nonlinear change greater than a value M. It is also based upon a relative cost between accepting the latter hypothesis when the former is true versus accepting the former hypothesis when the latter is true. A resulting probabilistic criterion (M/2)+(.sigma..sup.2 /M) [1n(P.sub.H0 /P.sub.H1)C] is graphically implemented for deriving offset values which can be used in a specific embodiment to construct tabular values defining linear/nonlinear regions from a presumed hypothetical straight line response.

Dynamically adjustable linear data discriminator

Growing community of inventors

Norman, OK, United States of America

John M Richardson