US 12,229,138 B2
Data preprocessing system module used to improve predictive engine accuracy
Moray Lamond Laing, Spring, TX (US); Mahdi Parak, Katy, TX (US); Nazaad Baksh, Conroe, TX (US); and Andreas G. Sadlier, The Woodlands, TX (US)
Assigned to Halliburton Energy Services, Inc., Houston, TX (US)
Filed by Halliburton Energy Services, Inc., Houston, TX (US)
Filed on Dec. 16, 2020, as Appl. No. 17/123,200.
Prior Publication US 2022/0188675 A1, Jun. 16, 2022
Int. Cl. G06F 16/00 (2019.01); G06F 16/2455 (2019.01); G06F 18/2321 (2023.01); G06N 20/00 (2019.01); G06F 16/2458 (2019.01); G06F 16/35 (2019.01); G06F 16/954 (2019.01); G06F 17/18 (2006.01); G06F 18/15 (2023.01)
CPC G06F 16/2455 (2019.01) [G06F 18/2321 (2023.01); G06N 20/00 (2019.01); G06F 16/2462 (2019.01); G06F 16/35 (2019.01); G06F 16/954 (2019.01); G06F 17/18 (2013.01); G06F 18/15 (2023.01)] 27 Claims
OG exemplary drawing
 
1. An apparatus used to provide preprocessed data variables to a predictive engine, predictive results from the predictive engine used for guiding well site operations, the apparatus comprising:
an analysis module configured by a processor to:
identify a well site operation by examining at least one well site operation variable;
determine at least one semantic category and a standard operating procedure associated with the at least one semantic category using the well site operation;
search a library of historical information using the at least one semantic category, the historical information comprising classified procedures and recommendations of historic well site operations;
a pattern recognition module configured by the processor to identify at least one pattern using a statistics based algorithm, the statistics based algorithm using the standard operating procedure, the at least one semantic category, the classified procedures and recommendations, the at least one pattern indicating a deviation in the standard operating procedure; and
a predictive engine interface module configured by the processor to generate at least one pattern recognition variable comprising the at least one pattern, to generate a control variable from the at least one pattern recognition variable, and to communicate the control variable to a well site sensor bank and controller to control the well site operation.