首页> 外文会议>International Modal Analysis Conference >CROSS VALIDATION AND 'L'-CURVES FOR THE REGULARISATION OF ILL-CONDITIONED EQUATIONS IN MODEL UPDATING
【24h】

CROSS VALIDATION AND 'L'-CURVES FOR THE REGULARISATION OF ILL-CONDITIONED EQUATIONS IN MODEL UPDATING

机译:跨验证和模型更新中不成条件方程正规化的'l'-曲线

获取原文

摘要

In this paper the problem of selecting a side constraint to regularise a system of ill-conditioned model-updating equations, and determining the regularisation parameter, is considered. A method of truncating the singular values by a generalised cross-validation criterion, and the L-curves method, are found to be reliable in locating the regularisation parameter. Both approaches lead to the satisfaction of Morozov's complementation condition.
机译:在本文中,考虑了选择侧限制以规则化的侧面约束的问题,并考虑了不调节的模型更新方程式和确定正则化参数。通过广义交叉验证标准和L曲线方法截断奇异值的方法,在定位正则化参数时被发现可靠。两种方法都导致莫罗佐夫的互补条件满意。

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