作者: Wanxu Zhang , Xiangnan Li , Lin Wang
DOI: 10.2991/IIICEC-15.2015.459
关键词: Pressure measurement 、 Algorithm 、 Generalization 、 Artificial neural network 、 Data model 、 Support vector machine 、 Engineering 、 Set (abstract data type)
摘要: With the problem that pressure of flexible pipe in aerial refueling was hard to be measured directly by sensors, a measurement algorithm based on support vector regression (SVR) with parameter optimization proposed this paper. First, data model large amount historical SVR set up. Then parameters were optimized cross-validation and grid-search method. Experimental results show method has high prediction precision good generalization ability comparing BP neural network.