US 12,394,252 B2
Prognostic and health monitoring system for a device with a rotating component
Balasubramanya Raju B K, Bangalore (IN); Manu Shastry C R, Bangalore (IN); and Raghavendra Muniraju, Bangalore (IN)
Assigned to Honeywell International Inc., Charlotte, NC (US)
Filed by Honeywell International Inc., Charlotte, NC (US)
Filed on Mar. 28, 2022, as Appl. No. 17/705,612.
Claims priority of application No. 202211007366 (IN), filed on Feb. 11, 2022.
Prior Publication US 2023/0260332 A1, Aug. 17, 2023
Int. Cl. G07C 5/08 (2006.01); B64F 5/60 (2017.01); G07C 5/00 (2006.01)
CPC G07C 5/008 (2013.01) [G07C 5/0808 (2013.01); B64F 5/60 (2017.01)] 17 Claims
OG exemplary drawing
 
1. A prognostic and health monitoring system for a device with a rotating component, the system comprising:
a plurality of sensors, each sensor configured to sense a parameter and output sensor signals based on the sensed parameter;
a controller in communication with the output sensor signals, the controller based on instructions stored in a memory configured to,
filter the output sensor signals based on operational speed data of the rotating component of the device to obtain normalized sensor data,
construct multivariate gaussian distribution parameters from the normalized sensor data using a central limit theorem,
compare parameters of a model generated with a learning algorithm applied to previous constructed multivariate gaussian distribution parameters with the constructed multivariate gaussian distribution parameters, and
determine a state of the device based at least in part on the comparison of the parameters of the model with the constructed multivariate gaussian distribution parameters, wherein determining the state of the device includes at least one of,
inferring probable device failures by monitoring data shifts in patterns between the model and the constructed multivariate gaussian distribution parameters using edge inferencing with a decision tree, and
predicting device failures using one of linear and multiple polynomial regression methods based on the parameters of the model and the constructed multivariate gaussian distribution parameters;
a communication system in communication with the controller to communicate the determined state of the device to a remote location.