Method and Apparatus for Neutron Porosity Measurement Using a Neural Network
AssigneeBaker Hughes Incorporated
InventorsQianmei Zhang, Constantyn Chalitsios
Life of this patent
Estimating the term…
Abstract
A method of estimating formation porosity using a neural network for neutron porosity tools. In the training stage, the near-to-far ratio, environmental variables, such as mineralogy, borehole size, standoff etc., are fed to the inputs and the neural network is trained for obtaining the related true porosity (the output). The trained neural network is implanted into tool's firmware for the real time porosity measurement, accounting for the environmental effects considered during training
Claims14
A method of evaluating an earth formation, the method comprising:
- using a sensor conveyed in a borehole for making a measurement indicative of a property of the earth formation;
- using at least one additional sensor for making at least one additional measurement indicative of at least one environmental factor affecting the measurement made by the sensor;
- using a trained neural network (NN) for estimating a value of the property of the formation by simultaneously using the measurement and the at least one additional measurement;
- and
- performing further operations using the estimated value of the property.
An apparatus configured to evaluate an earth formation, the apparatus comprising:
- a sensor configured to be conveyed in a borehole and make a measurement indicative of a property of the earth formation;
- at least one additional sensor configured to make at least one additional measurement indicative of at least one environmental factor affecting the measurement made by the sensor;
- a trained neural net (NN) configured to estimate a value of the property of the formation by simultaneously using the measurement and the at least one additional measurement;
- and
- a processor configured to perform further operations using the estimated value of the property.
Dependencies are inferred from the claim text.