期刊文献+

基于SVM-GA的剩余使用寿命预测方法研究

Research on Remaining Useful Life Prediction Based on SVM-GA
下载PDF
导出
摘要 提出了基于支持向量机和遗传算法的齿轮剩余使用寿命预测方法,该方法包含退化特征提取、状态数优化和寿命预测三个过程。齿轮箱全寿命数据用来对方法进行验证,通过分析单步和30步预测结果,充分说明了该预测方法的有效性,为后续工作奠定了基础。 In this paper, a remaining useful life prediction method based on support vector machine and genetic algorithm is proposed. This method contains three steps: feature extraction, state optimization and life prediction. The full life test data is used to validate the proposed method. The results of one-step and thirty step prediction are analyzed and the effectiveness of this method is validated. It makes a fundamental for next step work.
机构地区 军械工程学院 [
出处 《价值工程》 2013年第31期48-50,共3页 Value Engineering
关键词 寿命预测 支持向量机 遗传算法 life prediction support vector machine genetic algorithm
  • 相关文献

参考文献3

  • 1A.K.S. Jardine, D. Lin, and D. Banjevic. A review on machinery diagnostics and prognostics implementing condition- based maintenance [J]. Mechanical Systems and Signal Processing, vol.20,2006 : 1483-1510.
  • 2P. Demartines, J. H6rault. Curvilinear Component Analysis: A Self-Organizing Neural Network for Nonlinear Mapping of Data Sets[J]. IEEE Transactions on Neural Networks, 1997,8: 148-154.
  • 3A.J. Lee, A. Lendasse, M. Verleysen. Curvilinear distance analysts versus Isomap [J].European Symposium on Artificial Neural Networks, 2002: 185-192.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部