Abstract:
Large number of flow meters are used in the production of thermal power plant. Because of the complex status, the data of the flow have the characteristic of high nonlinears and variability, which have a high impact on the monitoring and controlling of the production system. However, the conventional model of dataprocessing could hardly meet the requirements of systems. Based on the mathematical statistics laws of errors probability distribution, a new model is presented in this paper to extract realtime data features. The adjustment of the model can be automatically done according to the data features. Experimental results show that the proposed dataprocessing method is more effective on plant flow data than the previous ones.