Electric Power Research Institute Incorporated

Leonard Charles Angello

David Robert Noble

Timothy Charles Lieuwen

Benjamin Emerson

Jared Kee

Tim Lieuwen

John Alexander Miltner

Andrew Mueller

Brian Poole

Scott Sheppard

A non-transitory computer readable medium with instructions stored thereon, the instructions executable by one or more processors for calculating base swirl in a gas turbine; and calculating relative swirl in the gas turbine. Also, a method for gas turbine maintenance, comprising identifying a combustor in need of repair or replacement within a gas turbine; and repairing or replacing the combustor; wherein said identifying comprises calculating base swirl of the gas turbine and calculating relative swirl of the gas turbine in order to associate a gas path from a thermocouple to the combustor in need of repair or replacement.

Gas turbine swirl detection

A non-transitory computer readable medium with instructions stored thereon, the instructions executable by one or more processors for selecting infrequent or frequent autotuning of a combustor; and determining the health of a combustor. Also, a method of monitoring a combustor within a gas turbine engine system, comprising providing a gas turbine engine system, wherein the gas turbine engine includes an autotuning system; selecting infrequent or frequent autotuning of the combustor; and determining the health of the combustor; wherein said determining the health of a combustor comprises receiving real-time fuel gas temperature data from at least one thermocouple.

Gas turbine

A method for detecting blowout precursors in at least one gas turbine combustor comprising: receiving combustion dynamics acoustic data measured by an acoustic measuring device associated with the combustor in real time; performing wavelet analysis on the acoustic data using simplified Mexican Hat wavelet transform analysis; and determining the existence of a blowout precursor based at least in part on the wavelet analysis. Provided also is a system and a non-transitory computer readable medium configured to perform the method.

Lean blowout precursor detection for gas turbines

A system and method for anomaly detection is provided. The system () and method () include utilizing one or more processors, such as in a server, for receiving () operational and dynamics data () from sensors associated with devices (), filtering the data, establishing a set of baseline dynamics data and eliminating data dependencies (). The system and method further include generating an expected level of data variation (), identifying an anomaly based on a deviation of the device data from the baseline data normalized by the expected level of data variation (), optionally correlating an anomaly with potential causes, and providing an output indicating an anomaly ().

Growing community of inventors

Mountain View, CA, United States of America

Leonard Charles Angello