A vibration cavitation sensitivity parameter based on spectral and statistical methods

• Published in: Expert systems with applications Vol. 42; no. 1; pp. 67 - 78
• Main Authors: McKee, Kristoffer K., Forbes, Gareth L., Mazhar, Ilyas, Entwistle, Rodney, Hodkiewicz, Melinda, Howard, Ian
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.01.2015; Elsevier
• Subjects: Acoustics; Applied sciences; Cavitation; Centrifugal pumps; Computer science; control theory; systems; Condition based monitoring; Data processing. List processing. Character string processing; Drops and bubbles; Exact sciences and technology; Flashing; Fluid dynamics; Fundamental areas of phenomenology (including applications); Impellers; Memory organisation. Data processing; Nonhomogeneous flows; Octave band analysis; Physics; Principal component analysis; Pumps; Software; Solid mechanics; Statistical methods; Structural and continuum mechanics; Underwater sound; Vibration; Vibration, mechanical wave, dynamic stability (aeroelasticity, vibration control...); Volutes; Centrifugal pumps; Octave band analysis; Vibration; Condition based monitoring; Cavitation; Principal component analysis; Modeling; Adaptive method; Turbine wheel; Bubble; Efficiency; Classification; ISO standard; Monitoring; Damaging; Implosion; Flash evaporation; Spectral method; Statistical analysis; Probabilistic approach; Octave; Durability; Pipe; Longevity; Experimental study; Operating conditions; Centrifugal pump; Piping

•Octave band analysis and PCA used on RMS velocity to obtain key indicators.•Mahalanobis distance is used to set thresholds since data is normally distributed.•Pump health separated into no cavitation, incipient, and fully formed condition.•Method works on a range of types and sizes of centrifugal p...