Prediction on thrust calibration slope based on FIG-SVR for attitude control rocket engine
Chen Wen-li · Journal of Rocket Propulsion · 2015
In order to predict the trend of thrust calibration slope for attitude control engine space simulation test,a method of time series prediction based on fuzzy information granulation(FIG) and support vector regression(SVR) is proposed in this paper.With the method of FIG,the thrust calibration slope is mapped as fuzzy information granulations(including minimum value Low,medium value R and maximum value Up) to reduce the dimension of the samples.The extracted parameters mentioned above are applied to SVR for proceeding regressive modeling.The prediction result shows that this method based on FIG-SVR can effectively predict the trend of the thrust calibration slope.