US 11,776,330 B2
Closed-loop diagnostic model maturation for complex systems
Timothy J. Wilmering, Chesterfield, MO (US); Stanley C. Ofsthun, O'Fallon, MO (US); Seema Chopra, Bengaluru (IN); Nazrul Bayen, Bengaluru (IN); Rohit Kumar, Bengaluru (IN); and Gurpreet Singh, Bengaluru (IN)
Assigned to The Boeing Company, Chicago, IL (US)
Filed by The Boeing Company, Chicago, IL (US)
Filed on Sep. 22, 2020, as Appl. No. 17/27,890.
Claims priority of provisional application 62/922,231, filed on Dec. 9, 2019.
Prior Publication US 2021/0174612 A1, Jun. 10, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G07C 5/08 (2006.01); G07C 5/00 (2006.01); B64F 5/60 (2017.01); B64D 45/00 (2006.01); G06F 30/27 (2020.01)
CPC G07C 5/0808 (2013.01) [B64D 45/00 (2013.01); B64F 5/60 (2017.01); G06F 30/27 (2020.01); G07C 5/008 (2013.01); B64D 2045/0085 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An off-board computer for maintaining an onboard reasoner for diagnosing failures on an aircraft that includes aircraft systems configured to report faults to the onboard reasoner, the off-board computer comprising:
memory configured to store computer-readable program code including an off-board reasoner; and
processing circuitry configured to access the memory and execute the computer-readable program code to cause the off-board computer to at least:
access diagnostic data received from an onboard computer of the aircraft that includes the onboard reasoner, the diagnostic data including a plurality of fault reports of failed tests reported by respective ones of the aircraft systems, and a plurality of diagnosed failure modes of at least some of the aircraft systems that caused the failed tests;
build, using the off-board reasoner, an off-board diagnostic causal model that describes causal relationships between the failed tests and the plurality of diagnosed failure modes, the off-board diagnostic causal model built using a theoretic machine learning algorithm trained using historical diagnostic data;
compare the diagnostic data to the off-board diagnostic causal model; and based thereon,
determine a new causal relationship in the causal relationships described by the off-board diagnostic causal model that is new relative to known causal relationships; and
update an onboard diagnostic causal model to further describe the new causal relationship, including the off-board computer caused to produce an updated onboard diagnostic causal model, and upload the updated onboard diagnostic causal model to the onboard computer using a loadable software airplane part upload tool set;
wherein the plurality of fault reports include a fault report that indicates those of the failed tests caused by a diagnosed failure mode of the plurality of diagnosed failure modes, and the off-board computer is further caused to:
diagnose, by the off-board reasoner, a corresponding failure mode of at least one of the aircraft systems, from those of the failed tests caused by the diagnosed failure mode, and using the theoretic machine learning algorithm and a graph; and
report any discrepancy between the corresponding failure mode and the diagnosed failure mode of the plurality of diagnosed failure modes from the diagnostic data received from the onboard computer.