...
首页> 外文期刊>Electric power systems research >A new interior point solver with generalized correntropy for multiple gross error suppression in state estimation
【24h】

A new interior point solver with generalized correntropy for multiple gross error suppression in state estimation

机译:一种新的具有广义熵的内点解算器,用于状态估计中的多个总误差抑制

获取原文
获取原文并翻译 | 示例
           

摘要

This paper provides an answer to the problem of State Estimation (SE) with multiple simultaneous gross errors, based on Generalized Error Correntropy instead of Least Squares and on an interior point method algorithm instead of the conventional Gauss-Newton algorithm. The paper describes the mathematical model behind the new SE cost function and the construction of a suitable solver and presents illustrative numerical cases. The performance of SE with the data set contaminated with up to five simultaneous gross errors is assessed with confusion matrices, identifying false and missed detections. The superiority of the new method over the classical Largest Normalized Residual Test is confirmed at a 99% confidence level in a battery of tests. Its ability to address cases where gross errors fall on critical measurements, critical sets or leverage points is also confirmed at the same level of confidence.
机译:本文基于广义误差Correntropy而不是最小二乘和基于内点法而不是传统的Gauss-Newton算法,为具有多个同时严重误差的状态估计(SE)问题提供了答案。本文描述了新的SE成本函数背后的数学模型以及合适的求解器的构造,并给出了说明性的数值案例。使用混淆矩阵评估SE的性能,该数据集被多达五个同时出现的严重错误污染,从而识别错误和遗漏的检测结果。在一系列测试中,以99%的置信度确认了新方法相对于经典的最大归一化残差测试的优越性。它在处理重大错误落在关键度量,关键集合或杠杆点上的情况下的能力也以相同的置信度得到确认。

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