Title :
Unsteady airflow classification by artificial neural networks
Author :
McGibney, S. ; Zaknich, A.
Author_Institution :
Dept. of Electr. & Electron. Eng., Western Australia Univ., Nedlands, WA, Australia
Abstract :
A multilayer perceptron classifier is applied to the classification of gas flow states. A number of suitable discriminate features are determined heuristically for the categorization of gas flow states, including the background (machinery and wind tunnel noise), laminar flow (sinusoidal signal), transition 1 (frequency-resonant shifts), transition 2 (instantaneous changes in phase and turbulent characteristics) and turbulent flow (random noise). This technique can be used to develop an automatic real-time classifier for gas flow
Keywords :
aerodynamics; computational fluid dynamics; laminar flow; laminar to turbulent transitions; multilayer perceptrons; pattern classification; real-time systems; turbulence; artificial neural networks; automatic real-time classifier; background; flow transitions; gas flow state classification; heuristically determined discriminate features; laminar flow; multilayer perceptron classifier; turbulent flow; unsteady airflow classification; Artificial intelligence; Artificial neural networks; Fluid flow; Fluid flow measurement; Intelligent networks; Probes; Signal processing; Temperature sensors; Velocity measurement; Wire;
Conference_Titel :
Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-5871-6
DOI :
10.1109/ICONIP.1999.844688
