Expert system for flame analysis

Combustion is the most important source of energy for power generation, heating, and transportation in the world. In this paper, we propose the use of infrared thermography for flame analysis. Various features available in the flame are process indicators and can provide great assistance in controlling the combustion system as well as the study of the combustion performance. Use of important parameters inherently available in the flame is the basic objective of proposed system. While building this system, there are two basic modules: generating the standard data base, commissioning system for controlling of combustion system. An image obtained from IR camera is the query image. Our searching algorithm makes use of multi-resolution wavelet decompositions of the query and database images. The coefficients of these decompositions are distilled into small "signatures" for each image. We introduce an "image querying metric" that operates on these signatures. This metric essentially compares how many significant wavelet coefficients the query has in common with potential targets. After retrieval of the matching image from flame image databases, it will then provide input to the process control computer thus monitoring the combustion processes