US 11,892,003 B2
Application of machine learning to process high-frequency sensor signals of a turbine engine
James Ryan Reepmeyer, Cincinnati, OH (US); Johan Michael Reimann, Ballston Spa, NY (US); Gagan Adibhatla, Cincinnati, OH (US); Evin Nathaniel Barber, Cincinnati, OH (US); Stefan Joseph Cafaro, Maineville, OH (US); Rahim Panjwani, Cincinnati, OH (US); Frederick John Menditto, III, Maineville, OH (US); Aaron James Schmitz, Cincinnati, OH (US); Suchot Kongsomboonvech, Mason, OH (US); and Richard Anthony Zelinski, Cincinnati, OH (US)
Assigned to General Electric Company, Schenectady, NY (US)
Filed by General Electric Company, Schenectady, NY (US)
Filed on Mar. 6, 2019, as Appl. No. 16/294,358.
Prior Publication US 2020/0284265 A1, Sep. 10, 2020
Int. Cl. F04D 27/00 (2006.01); G01M 15/14 (2006.01); G05B 13/02 (2006.01); G06N 3/04 (2023.01); F04D 27/02 (2006.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01)
CPC F04D 27/001 (2013.01) [F04D 27/02 (2013.01); F04D 27/0207 (2013.01); F04D 27/0246 (2013.01); F04D 27/0253 (2013.01); G01M 15/14 (2013.01); G05B 13/027 (2013.01); G06N 3/04 (2013.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); F05D 2270/101 (2013.01); F05D 2270/709 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A control system for an engine having a compressor element, the control system comprising:
one or more computing devices having one or more memory devices and one or more processing devices, the one or more memory devices storing computer-readable instructions that can be executed by the one or more processing devices to perform operations, in performing the operations, the one or more processing devices are configured to:
receive data indicative of an operating characteristic associated with the compressor element;
splice the received data into data subsets indicative of the operating characteristic associated with the compressor element, each data subset of the data subsets includes a time series of data having a plurality of data points between an initial time and an end time, the plurality of data points of each data subset having a unique initial time; and
determine, by a machine-learned model, a stall margin remaining of the compressor element based at least in part on the data subsets.