US 12,493,287 B2
Devices, systems and methods for automatically predicting maintenance events
Alexandre Erriquez, Chene-Bourg (CH); Arnaud Dubreuil, Bassy (FR); Travis A. Busen, Chicago, IL (US); Stephen Berning, Germantown Hills, IL (US); Davide Gerbaudo, Peron (FR); Jose Pitteloud, Chene-Bourg (CH); Brandon Bill, Washington, IL (US); and Guillaume Gard, Geneva (CH)
Assigned to Caterpillar Inc., Peoria, IL (US)
Filed by Caterpillar Inc., Peoria, IL (US)
Filed on Mar. 24, 2022, as Appl. No. 17/703,557.
Claims priority of provisional application 63/169,085, filed on Mar. 31, 2021.
Prior Publication US 2022/0317678 A1, Oct. 6, 2022
Int. Cl. G05B 23/02 (2006.01)
CPC G05B 23/0283 (2013.01) 18 Claims
OG exemplary drawing
 
1. A method for providing future maintenance event predictions for an industrial machine based on partial maintenance history data for the industrial machine, the method comprising:
receiving information associated with a past maintenance event of the industrial machine, the information comprising an indication of geographic location in which the industrial machine was used prior to the past maintenance event;
identifying, based at least partially on the received information, maintenance information associated with the past maintenance event, including (i) a type of the industrial machine, (ii) a component of the industrial machine that was serviced during the past maintenance event, wherein the component is associated with one or more parts, and (iii) a category of the past maintenance event;
determining, based on the geographic location, a part wear rate for the one or more parts;
predicting, based at least partially on the type of the industrial machine, the component that was serviced during the past maintenance event, the category of the past maintenance event, and the determined part wear rate determined based on the geographic location, a time until a future maintenance event for the industrial machine;
generating a recommendation for the one or more parts, wherein the recommendation comprises: (i) the time until the future maintenance event and (ii) a recommended production level for the one or more parts determined using the predicted time until the future maintenance event; and
operating the one or more parts, using additional sensor data, according to the generated recommendation.