The application of a neural network approach to on-line nitrogen CARS thermometry was developed for a standard setup with PC-based data acquisition in a LABview environment. The method utilized is based on initial clustering of the training network. The main advantage of the neural network method is speed with the potential for on-line temperature extraction. Results of space-resolved temperature measurements are presented in the case of an industrial CH4-air burner operating at atmospheric pressure. The resulting temperatures were compared with values extracted from the data using conventional least-squares fitting. Copyright (C) 2000 John Wiley and Sons, Ltd.
|Pages (from-to)||697 - 701|
|Number of pages||5|
|Journal||Journal of Raman Spectroscopy|
|Publication status||Published - 2000|
All Science Journal Classification (ASJC) codes
- Materials Science(all)
Fantoni, R., Colao, F., De Dominicis, L., Giorgi, M., D'Apice, M., Giammartini, S., & Van Der Steen, H. J. L. (2000). On-line nitrogen CARS thermometry on a 130 kW burner by using a neural network approach. Journal of Raman Spectroscopy, 31(8-9), 697 - 701. https://doi.org/10.1002/1097-4555(200008/09)31:8/9<697::AID-JRS595>3.0.CO;2-M