【24h】

DEVELOPMENT OF ALGORITHMS FOR HELICOPTER PROGNOSTICS

机译:直升机预测算法的发展

获取原文
获取原文并翻译 | 示例

摘要

The current health monitoring and diagnostics systems for helicopters do not have a clearly defined prognostics capability. In this paper, as an effort for developing the needed prognostics capability, the development of algorithms for helicopter prognostics is presented. The prognostics algorithms are developed based on the modeling and learning capability of the hidden semi-Markov models (HSMMs) and a data-grouping algorithm called Mahalanobis Distance Group Index (MDGI) algorithm. The MDGI algorithm projects the multi-dimensional data into one-dimensional projection line so that a single dimensional group index (GI) can be computed and the complex multi-dimensional data-grouping problem solved easily. Effective and robust prognostics models can be built based the data groups computed by the MDGI algorithm. The developed prognostics algorithms are validated using real helicopter data supplied by Goodrich.
机译:当前用于直升机的健康监测和诊断系统没有明确定义的预测能力。在本文中,作为开发所需的预测能力的一项工作,提出了直升机预测算法的开发。基于隐藏的半马尔可夫模型(HSMM)的建模和学习能力以及称为马氏距离组索引(MDGI)的数据分组算法,开发了预测算法。 MDGI算法将多维数据投影到一维投影线中,从而可以计算一维组索引(GI),并轻松解决复杂的多维数据分组问题。可以基于由MDGI算法计算出的数据组来建立有效而强大的预测模型。使用Goodrich提供的真实直升机数据验证了开发的预测算法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号