Research on Data Mining Based on Rough Set and Its Application in Fault Diagnosis of Steam Turbine

For overcoming shortages of some current knowledge attaining methods, a novel approach for fault forecast and diagnosis of steam turbine based on rough set data mining theory is brought forward. Data pretreatment, knowledge reduction and rule abstraction are three important problems in the research of rough set theory.The historical fault data of steam turbine is processed with fuzzy and scatter method. The processed data is used to structure the fault diagnosis decision-making table that is treated as "knowledge database". This paper introduced rough sets data mining method to take potential diagnosis rule from the fault diagnosis decision-making table of steam turbine. These rules can offer effective fault diagnosis service for steam turbine. The algorithm for classified rule learning and reducing is brought forward, and an experimental system for fault forecast and diagnosis of steam turbine based on rough set data mining theory is implemented. Their diagnosis precision is above 88%. And experiments do prove that it is feasible to use the method to develop a system for fault forecast and diagnosis of steam turbine, which is valuable for further study in more depth.