Fuzzy Modeling for Optical Sensor for Diagnostics of Pulverized Coal Burner

Abstract The premise for the exploration of new sensors and methods of diagnostics of the combustion process are the difficulties encountered during the implementation of low emission combustion technology. Averaging and delay are the main drawbacks of traditional methods of measurement of the majority of combustion parameters. There is a lack of method that allows measurement of output parameters of an individual burner. It is therefore necessary to use indirect optical methods. They are noninvasive, virtually not delayed and additionally spatially selective. Although they provide large amounts of information, their interpretation requires the use of complex data processing techniques. The authors prove that it is possible to obtain quantitative information, in the article it is demonstrated on the example of nitrogen oxides. The paper describes the use of processing methods with a relatively small computational complexity. Tests were made using 1:10 scale rig with single swirl burner.