基于FIG-SVR的姿控发动机推力校准斜率预测  

Prediction on thrust calibration slope based on FIG-SVR for attitude control rocket engine

作　　者：陈文丽[1] 马军强[1] 杨思锋[1] 田国华[1] 

机构地区：[1]北京航天试验技术研究所,北京100074

出　　处：《火箭推进》2015年第3期103-107,共5页Journal of Rocket Propulsion

摘　　要：为了对某型号姿控发动机高空模拟试验推力现场校准斜率进行趋势预测,提出了一种模糊信息粒化(fuzzy information granulation,FIG)和支持向量回归机(support vector regression,SVR)相结合的时间序列预测方法。借助模糊信息粒化方法将推力现场校准的斜率映射为包含区间最小值Low、中值R和最大值Up 3个参数的模糊信息粒,以降低样本的维数,并以其为输入构建SVR回归模型。预测结果表明,基于模糊信息粒化SVR确定的预测区间较好地反映了推力现场校准斜率的变化趋势。In order to pf＇edict 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 thnlst calibration slope.

关 键 词：姿控火箭发动机试验 推力校准斜率 FIG-SVR 预测 

分 类 号：V434-34[航空宇航科学与技术—航空宇航推进理论与工程]