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.
Claims15
A method of evaluating an earth formation, the method comprising:
- using a neutron porosity tool conveyed in a borehole for making a measurement indicative of a porosity of the earth formation, the neutron porosity tool having a plurality of detectors;
- 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) in the tool for estimating a value of the porosity of the formation in real time while drilling by simultaneously using the measurement and the at least one additional measurement as a set of input values;
- and
- performing further operations using the estimated value of the porosity, wherein estimating the value of the porosity further comprises estimating a ratio between a measurement made by a first one of the plurality of detectors and a second one of the plurality of detectors.
An apparatus configured to evaluate an earth formation, the apparatus comprising:
- a neutron porosity tool configured to be conveyed in a borehole and make a measurement indicative of a porosity of the earth formation, the neutron porosity tool having a plurality of detectors;
- 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) in the tool configured to estimate a value of the porosity of the formation in real time while drilling by simultaneously using the measurement and the at least one additional measurement as a set of input values;
- and
- a processor configured to perform further operations using the estimated value of the porosity, wherein estimating the value of the porosity further comprises estimating a ratio between a measurement made by a first one of the plurality of detectors and a second one of the plurality of detectors.
A method of evaluating an earth formation, the method comprising:
- using a gamma ray density tool having a plurality of detectors conveyed in a borehole for making a measurement indicative of a density 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 gamma ray density tool;
- using a trained neural network (NN) in the tool for estimating a value of the density of the formation in real time while drilling by simultaneously using the measurement and the at least one additional measurement as a set of input values;
- and
- performing further operations relating to the earth formation using the estimated value of the property.
An apparatus configured to evaluate an earth formation, the apparatus comprising:
- a gamma ray density tool configured to be conveyed in a borehole and make a measurement indicative of a density of the earth formation, the neutron porosity tool having a plurality of detectors;
- 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) in the tool configured to estimate a value of the density of the formation in real time while drilling by simultaneously using the measurement and the at least one additional measurement as a set of input values;
- and
- a processor configured to perform further operations relating to the earth formation using the estimated value of the density.
Dependencies are inferred from the claim text.