US 11,940,586 B2
Noise elimination or reduction in drilling operation measurements using machine learning
Jie Yang, Houston, TX (US); and Songhua Chen, Katy, TX (US)
Assigned to Halliburton Energy Services, Inc., Houston, TX (US)
Filed by Halliburton Energy Services, Inc., Houston, TX (US)
Filed on Nov. 2, 2021, as Appl. No. 17/517,234.
Claims priority of provisional application 63/126,181, filed on Dec. 16, 2020.
Prior Publication US 2022/0187489 A1, Jun. 16, 2022
Int. Cl. G01V 3/14 (2006.01); E21B 47/12 (2012.01); G01P 15/00 (2006.01); G05B 13/02 (2006.01)
CPC G01V 3/14 (2013.01) [E21B 47/12 (2013.01); G01P 15/00 (2013.01); G05B 13/0265 (2013.01); E21B 2200/20 (2020.05)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a processor; and
a memory that includes instructions executable by the processor for causing the processor to:
receive one or more measured signals in a logging-while-drilling process for drilling a wellbore, the one or more measured signals comprising noise that includes at least one of vibration-related noise or motion-related noise, wherein the one or more measured signals are in a spectrum domain format comprising a plurality of bin values;
determine a coupling factor for noise for each bin value of the plurality of bin values using a machine learning process;
determine an overall coupling factor for noise in the one or more measured signals based on the coupling factor for each bin value of the plurality of bin values, wherein the overall coupling factor is a variable;
generate a corrected signal by removing the noise multiplied by the overall coupling factor from the one or more measured signals; and
control a drilling operation in the wellbore based on the corrected signal.