US 11,703,846 B2
Equipment failure diagnostics using Bayesian inference
Oleg O. Medvedev, Missouri City, TX (US); and Marcus D. Sprenkel, Houston, TX (US)
Assigned to CAMERON INTERNATIONAL CORPORATION, Houston, TX (US)
Appl. No. 17/595,536
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
PCT Filed May 28, 2020, PCT No. PCT/US2020/034915
§ 371(c)(1), (2) Date Nov. 18, 2021,
PCT Pub. No. WO2020/243297, PCT Pub. Date Dec. 3, 2020.
Claims priority of provisional application 62/854,748, filed on May 30, 2019.
Prior Publication US 2022/0244716 A1, Aug. 4, 2022
Int. Cl. G05B 23/02 (2006.01); G06N 20/00 (2019.01); G06F 18/2415 (2023.01)
CPC G05B 23/024 (2013.01) [G05B 23/0275 (2013.01); G06F 18/24155 (2023.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
registering a first failure at a first processing unit of a processing facility comprising a plurality of processing units;
using a Bayesian inference engine to determine a probability that a second processing unit of the processing facility experienced a second failure based on occurrence of the first failure;
in the event that the probability is above a predetermined threshold, determining whether the second processing unit experienced the second failure;
in the event that it is determined that the second processing unit experienced the second failure, remediating a condition of the second processing unit that caused the second failure; and
updating the Bayesian inference engine with occurrence or non-occurrence of the first and second failures.