On-Line Fuel Identification Using Digital Signal Processing and Soft-Computing Techniques

This paper presents a novel approach for on-line fuel identification using digital signal processing and soft-computing techniques. Aflame detector containing three photodiodes is used to derive multiple signals covering a wide spectrum of the flame from infrared to ultraviolet through visible band Advanced digital signal processing and soft-computing techniques are deployed to identify the dynamic 'finger-prints' of the flame both in the time and frequency domains and ultimately the type of fuel being burnt. A series of experiments was carried out using a 0.5MW(th) combustion test facility operated by Innogy plc, UK. The results obtained demonstrate that this approach can be used to identify the type of fuel being burnt under steady combustion conditions.