【24h】

Uncertainty Estimation for Empirical Signal Validation Modeling

机译:经验信号验证建模的不确定性估计

获取原文
获取原文并翻译 | 示例

摘要

Empirical modeling techniques have been applied to on-line process monitoringrnto detect equipment and instrumentation degradations. However, few applicationsrnprovide prediction uncertainty estimates, which can provide a measure of confidence inrnyour decisions. This paper presents the development of analytical prediction intervalrnestimate methods for three common non-linear empirical modeling strategies: artificialrnneural networks (ANN), neural network partial least squares (NNPLS), and localrnpolynomial regression (LPR). The techniques are applied to nuclear power plantrnoperational data for sensor calibration monitoring and verified via bootstrap simulationrnstudies.
机译:经验建模技术已应用于在线过程监控,以检测设备和仪器的性能下降。但是,很少有应用程序提供预测不确定性估计,这可以提供对决策的置信度的度量。本文介绍了三种常见的非线性经验建模策略的分析预测区间估计方法的发展:人工神经网络(ANN),神经网络偏最小二乘(NNPLS)和局部多项式回归(LPR)。该技术被应用于核电厂的运行数据,以进行传感器校准监控,并通过自举仿真研究进行验证。

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