Weather radar's life prediction using support vector regression

被引:0
作者
Rui, Fang [1 ]
Xiangmei, Li [2 ]
机构
[1] Chengdu University of Information Technology, Chengdu
[2] Chengdu University of Information Technology, Chengdu
关键词
Life; Prediction; Support vector regression; Weather radar;
D O I
10.4156/jcit.vol7.issue12.9
中图分类号
学科分类号
摘要
The life of weather radar represent the time period from now on to the radar failure (not working), an accurate the life prediction is not only an indispensable element of cycle management system, but also the key technologies of improving reliability, security, maintainability of weather radar. In this paper, we present a novel methodology for predicting weather radar's life. The major contributions are: (1)We convert the weather radar's life prediction problem into a multiple regression prediction problem, and present a multiple regression framework for life prediction;(2) we induce Support Vector Regression(SVR) to solve the multivariate regression problem of weather radar's life and propose a SVR-based weather radar's life predicting algorithm. (3) In order to remove redundant and ineffective components of characteristic parameters, we propose a feature subset selection SVR algorithm. Finally, simulation results demonstrate the effectiveness of the proposed prediction algorithm.
引用
收藏
页码:69 / 75
页数:6
相关论文
共 13 条
[1]  
Mohanty J.R., Verma B.B., Ray P.K., Et al., Application of artificial neural network for fatigue life prediction under interspersed mode-1 spike overload[J], Journal of Testing and Evaluation, 38, 2, pp. 96-101, (2010)
[2]  
Natarajan U., Periasamy V.M., Saravanan R., Application of particle swarm optimization in artificial neural network for the prediction of tool life[J], International Journal of Advanced Manufacturing Technology, 31, 9-10, pp. 871-876, (2007)
[3]  
Kim Y.H., Song J.H., Park J.H., An expert system for fatigue life prediction under variable loading[J], Expert Systems With Applications, 3, pp. 4996-5008, (2009)
[4]  
Pawar P.M., Ganguli R., Fuzzy-logic-based health monitoring and residual-life prediction for composite helicopter rotor[J], Journal of Aircraft, 44, 3, pp. 981-995, (2007)
[5]  
Bukkapatnam S.T.S., Sadananda K., A genetic algorithm for unified approach-based predictive modeling of fatigue crack growth[J], International Journal of Fatigue, 27, 10-12, pp. 1354-1359, (2005)
[6]  
Research on life prediction method of electronic equipment on the missile [J], Journal of Naval Aeronautical Engineering Institute, 22, 6, pp. 667-669, (2007)
[7]  
Zhaohui W., Laibin Z., Lizhu T., Forecast technology for equipment to be maintained using chaos theory, JOURNAL of the UNIVERSITY of PETROLEUM,CHINAEDITION of NATURAL SCIENCE, (2004)
[8]  
Weixian L., Review On Reliability Life Prediction of Nuclear Machinery Equipment Using Small Sample [J], S4, pp. 305-328, (1999)
[9]  
Scholkopf B., Smola A.J., Learning With Kernels [M], (2002)
[10]  
Smola A.J., Scholkopf B., A tutorial on support vector regression [J], Statistics and Computing, 14, 3, pp. 199-222, (2004)