US 11,656,595 B2
System and method for machine monitoring
Anthony W. Allison, Champaign, IL (US); Scott A. Zacek, Savoy, IL (US); Vijay K. Yalamanchili, Champaign, IL (US); and Karl P. Schneider, Decatur, IL (US)
Assigned to Caterpillar Inc., Peoria, IL (US)
Filed by Caterpillar Inc., Peoria, IL (US)
Filed on Aug. 27, 2020, as Appl. No. 17/4,546.
Prior Publication US 2022/0066408 A1, Mar. 3, 2022
Int. Cl. G05B 19/042 (2006.01); G06N 20/00 (2019.01); G01L 1/00 (2006.01); G01P 3/00 (2006.01); G01P 15/00 (2006.01)
CPC G05B 19/0428 (2013.01) [G01L 1/00 (2013.01); G01P 3/00 (2013.01); G01P 15/00 (2013.01); G06N 20/00 (2019.01); G05B 2219/24015 (2013.01)] 20 Claims
OG exemplary drawing
 
10. A system for monitoring operation of a machine, comprising:
at least one processor; and
at least one non-transitory computer readable medium storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations including:
receiving machine operation data, via an input circuitry, including a first data channel indicative of a sensed condition at a first location on the machine, the machine operation data corresponding to one or more work cycles of the machine;
extracting, via a data extraction circuitry, at least a portion of the machine operation data, including data associated with the first data channel;
identifying, via an event identification circuitry, one or more types of events involving an environment in which the machine operates and that occurred during the one or more work cycles of the machine by classifying the extracted machine operation data wherein identifying the one or more types of events is performed at least in part with a trained machine learning model that identifies the one or more types of events by classifying the extracted machine operation data based on training data used to train the trained machine learning model, the training data including at least one of: one or more simulated events or measured data associated with one or more predetermined events;
estimating, via a condition estimation circuitry, a condition at a second location on the machine during the one or more work cycles of the machine based on the identified one or more types of events; and
logging, via an event logging circuitry, the identified one or more types of events with a plurality of additional identified types of events to represent a plurality of work cycles during operation of the machine over time.