Compressor Stall Warning Using Nonlinear Feature Extraction Algorithms

Bookmark/Download	Download as PDF
Track Code	2019-LOU-68639
Categories	Aeronautics Mechanical Engineering
Keywords	Aeronautics Aircraft Algorithm Centrifugal Compressor combustion controls Compressor Data Data Processing Detection Energy Engines Fracture Resistant Gas Turbine Jet Engine Pneumatics Stability Turbine Engines Turbomachinery Turbulence
Public Abstract	Researchers at Purdue University have developed robust algorithms which can detect small disturbances and therefore trigger stall warnings sooner than traditional compressor stall warnings. The technique works for both modal-type and spike-type stall inception, and is compatible with a variety of compressors. By reading inputs from transducers, changes in engine operating conditions can be logged such that the system can react before catastrophe takes place. This cutting-edge gas turbine technology ensures safe operations for compressors and gas turbine engines. Advantages: -Detection of small nonlinear disturbances prior to compressor stall -Extremely accurate -Works for variety of compressor types -Works with both modal and spike type stall inceptions -Eliminates flow instability Potential Applications: -Gas turbinesin aviation and power -Process compressors -Aircraft operations -Engine health monitoring (EHM)
People	Key, Nicole Leanne (Project leader) Lou, Fangyuan
Intellectual Property	Application Date Jul 1, 2020 Type Utility Patent Country of Filing United States Patent Number 11,415,139 Issue Date Aug 16, 2022 Application Date Jul 1, 2020 Type PCT-Patent Country of Filing WO Patent Number (None) Issue Date (None) Application Date Jul 8, 2019 Type Provisional-Patent Country of Filing United States Patent Number (None) Issue Date (None)
Contact OTC	Purdue Office of Technology Commercialization The Convergence Center 101 Foundry Drive, Suite 2500 West Lafayette, IN 47906 Phone: (765) 588-3475 Fax: (765) 463-3486 Email: otcip@prf.org