Incorporating Supervisory Learning through Type–2 Fuzzy Expert System for Increasing Productivity of a Boiler

The ways of maximization of net steam output from Chemical Recovery Boilers has been a puzzle over the years. To lend support to the same, a type 2 fuzzy expert system has been designed which takes into account a large number of parameters. The composition of Black liquor solids ( fuel) is dependent on a large number of factors right from raw materials like wood and bagasse down through chemicals used for Paper manufacture and pulping since it is the source of heat and power for producing paper of quality at high productivity level. The choice of parameters playing a significant role in the same has to be determined. Pruning is carried out by performing sensitivity analysis. It has been observed that Boiler Liquor solids flow, Moisture content in fuel and Gross Calorific value are found to be more sensitive while parameters like flue gas outlet temperature hardly makes an impact in the process. These apart, apportioning of combustion air at three levels does play a part in productivity. The parameters with a larger impact have been grouped together using c-means clustering. It has been observed in the real world that some measurements are being omitted owing to carelessness of the operators. C-Means clustering could deal with missing data The existing system gives emphasis to operator’s experience and specialists expertise. A temporary lack of focus or the absence of a specialist can lead to major consequences. There arises a need for designing a Type 2 Fuzzy logic system to ensure better performance at all times of operation.