Using an acoustic device to identify external apparatus mounted to a tubular
A method, apparatus and system for locating external apparatus mounted to a tubular in a wellbore. The identification of apparatus, such as cable clamps, enables other tools in the string to operate more precisely. A computer model is used to locate the apparatus from acoustic images, which images are acquired using a downhole device having an acoustic sensor or acoustic array. The model may be a classifier, which may be machine trained to classify whether an apparatus is present, its location and its orientation. Automating this locating enables very long wellbores to be processed quickly.
1. A method of locating apparatus mounted external to a tubular, the method comprising:
deploying an imaging device having an acoustic sensor into the tubular;
creating acoustic images using the acoustic sensor from acoustic reflections from the tubular and portions of the apparatus contacting the tubular; and
processing the acoustic images with a computer model to determine a location of the apparatus; and
outputting the location of the apparatus.
2. The method of claim 1 , wherein the acoustic images extend longitudinally along the tubular and circumferentially around the tubular, the image further comprising depth data representing time of reflections into the tubular for each scan line.
3. The method of claim 1 , further comprising converting acoustic reflections to one or more intensity features of the image that represent at least one of: maximum intensity, average intensity, standard deviation of intensity, average intensities for plural radial ranges, or radius of center of intensity.
4. The method of claim 1 , wherein the acoustic images to be processed are axially-segmented frames from the imaged tubular.
5. The method of claim 1 , wherein processing the acoustic images comprises image processing to identify edges of the apparatus.
6. The method of claim 1 , further comprising determining an azimuthal location of the apparatus with respect to the tubular.
7. The method of claim 1 , further comprising creating a database of apparatus locations, the database storing their parameters and their locations, and de-duplicating the located apparatuses in the databased based on a comparison of the apparatus locations.
8. The method of claim 1 , wherein the computer model comprises one or more of a machine learning classifier and a Convolutional Neural Net (CNN).
9. The method of claim 1 , further comprising training a classifier of the computer model with a set of labelled training images of tubulars.
10. The method of claim 1 , wherein the computer model comprises a regression network to output a value for azimuthal location of the apparatus on the tubular.
11. The method of claim 1 , wherein the computer model comprises a store of templates of potential apparatuses to be located and a template matching algorithm.
12. A system for locating apparatus mounted external to a tubular, comprising:
an imaging device deployable into the tubular and comprising an acoustic sensor;
one or more processors; and
one or more memory units storing instructions that are operable by the one or more processors to perform operations comprising:
creating acoustic images using the acoustic sensor from acoustic reflections from the tubular and portions of the apparatus contacting the tubular;
storing the acoustic images in the one or more memory units;
processing the acoustic images with a computer model to determine a location of the apparatus; and
outputting the location of the apparatus.
13. The system of claim 12 , further comprising converting acoustic reflections to one or more intensity features of the image that represent at least one of: maximum intensity, average intensity, standard deviation of intensity, average intensities for plural radial ranges, or radius of center of intensity.
14. The system of claim 12 , wherein processing the acoustic images comprises image processing to identify edges of the apparatus.
15. The system of claim 12 , further comprising determining an azimuthal location of the apparatus with respect to the tubular.
16. The system of claim 12 , wherein the acoustic sensor comprises a phased-array of acoustic transducer elements, and further comprising beamforming the phased-array to optimize reflections from the apparatus.
17. The system of claim 12 , wherein the computer model comprises one or more of a machine learning classifier and a Convolutional Neural Net (CNN).
18. The system of claim 12 , further comprising training a classifier of the computer model with a set of labelled training images of tubulars.
19. The system of claim 12 , wherein the computer model comprises a regression network to output a value for azimuthal location of the apparatus on the tubular.
20. An apparatus, comprising:
one or more non-transitory memories storing a computer model of acoustic reflections from external apparatus;
a processor configured to execute instructions stored in the one or more non-transitory memories to:
receive acoustic images of tubulars and apparatus mounted externally thereto; and
convolve the acoustic images with the computer model to determine a location of any external apparatus detected; and
output the location of the any external apparatus.