×

Gas turbine sensor failure detection utilizing a sparse coding methodology

  • US 10,557,719 B2
  • Filed: 09/03/2015
  • Issued: 02/11/2020
  • Est. Priority Date: 09/10/2014
  • Status: Active Grant
First Claim
Patent Images

1. A method for detecting gas turbine sensor failure based upon collected readings from at least one sensor, comprising:

  • creating a dictionary of basis vectors defining values associated with known sensor readings for normal operating conditions;

    applying a sparse coding process to a set of sensor reading data, using the created dictionary, to identify a set of L-1 norm residual data;

    evaluating the L-1 norm residual data to categorize a predetermined subset of the largest-valued L-1 norm residual data as abnormal sensor readings;

    comparing the abnormal sensor readings to a plurality of prior sensor readings and defining the designated abnormal sensor readings as associated with a sensor failure if a predefined number of the prior sensor readings are also designated as abnormal sensor readings;

    transmitting a sensor failure signal to gas turbine personnel, identifying the particular sensor; and

    removing the failed sensor from service, and repairing or replacing the failed sensor.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×