Suction Flowrate Prediction Model for a Boiler Feed Pump

摘要

Proposed in this paper is a prediction model to estimate the suction flowrate of a boiler feed pump. The prediction model is developed by using the multiple regression technique, and consists of a response variable (Suction flowrate) and eight candidates of predictor variables (Discharge pressure, Discharge temperature, Suction pressure, BP suction pressure, Suction temperature, Speed reference, Speed, and Main steam pressure). For an accurate multiple regression equation, it is necessary to evaluate the relative importance of a predictor variable in a regression equation, which is determined by the proportion of the variance in the response variable accounted for by the predictor variable. Three different methods (Product measure, General dominance index, and Relative weight) have been applied to identify major predictor variables, and we develop multiple regression models by using identified major predictor variables.