The Application of Fuzzy Data Mining in Coal-Fired Boiler Combustion system
YU Xi-ning, Cheng-lin Niu, Jianqiang Li · 2005
Coal-fired boiler combustion system is a complex multi-input and multi-output plant with strong nonlinear and large time-delay. Currently the research of optimizing the combustion process is monitor oriented instead of decision oriented. So it lacks the interaction and decision making with the user. To improve the performance of combustion process, the key point is to decide the optimization values for the main controllable parameters. This paper proposed a fuzzy data mining algorithm to decide the optimization values from the history data sets. In order to soften the partition boundary of the domain, the fuzzy sets theory was introduced into the association mining process. This method can translate quantitative association rules problem (QARP) into Boolean association rules problem (BARP). Finally some results of instance analysis based on the practical parameters of 300 MW power plant unit are given to prove that the fuzzy mining method has good accuracy and interpretability. The effective results are achieved by guiding actual operating based on the optimizing values gotten from the fuzzy data mining process.