An Association Rules Analysis Of Performance Based On The Data Of Power Plant

With the popularization of DCS system in electrical industry, there is a large number of DCS system data collected in power plant. There is lots of valuable information, which benefits to enhancing the economic performance and safety of power plant, hidden behind of the data. But because of not being mind and used effectively, there must be lots of data resource waste. Data mining techniques can intelligently and automatically discover knowledge from database. In this paper, association rules mining, which belongs to data mining techniques, is applied to make full use of the function of the data collected in DCS system in power plant, which can direct electric power production.Firstly, in this paper, many kinds of association rules mining methods are discussed such as apriori arithmetic and FP-growth arithmetic and multilevel association rules mining arithmetic and multidimensional association rules mining arithmetic. Then the process of developing association rules mining system 1.0, which is towards the data in power plant, is introduced. In the paper, it is the first time that association rules mining is attempted to applied towards the analysis of the data of steam turbo-generator unit in thermal power plant, and valuable result has been gained. Through the analysis of the result, we found that this technique not only can be used in the analysis of the performance of the unit in power plant and condition monitoring and fault diagnosis and condition based maintenance, but also can provide technical support towards realizing both condition based maintenance and SIS system in power plant. It is very significant. Tian Zhiyou(Thermal engineering) Directed by prof. Fu Zhongguang...