【24h】

Data-driven design of fault diagnosis systems

机译:故障诊断系统的数据驱动设计

获取原文
           

摘要

To ensure the safety and reliability of modern industrial process, a fault diagnosis system is of prime importance in process design nowadays. Since the analytical process model is difficult to obtain for large-scale applications, the main objective of this book is to develop efficient data-driven fault diagnosis systems under different operating conditions. The work is firstly dedicated to the modifications on the standard multivariate statistical approaches under stationary operating condition. For dynamic processes, a subspace aided data-driven approach, which directly identifies parameters of residual generator, is further developed. Advanced design schemes like multiple residuals generator and state observer are also investigated for process monitoring and control purposes. For the large-scale processes involving changes, a novel data-driven adaptive scheme is proposed with desired stability and convergence performance. Three industrial benchmark processes are finally utilized to illustrate the effectiveness of the derived data-driven approaches under different operating conditions.
机译:为了确保现代工业过程的安全性和可靠性,故障诊断系统在当今的过程设计中至关重要。由于难以针对大规模应用获得分析过程模型,因此本书的主要目的是在不同的操作条件下开发有效的数据驱动的故障诊断系统。该工作首先致力于在固定工况下对标准多元统计方法的修改。对于动态过程,进一步开发了直接识别残差生成器参数的子空间辅助数据驱动方法。还对先进的设计方案(例如多个残差生成器和状态观察器)进行了研究,以进行过程监视和控制。对于涉及变化的大规模过程,提出了一种具有所需稳定性和收敛性能的新型数据驱动自适应方案。最后利用三个行业基准过程来说明在不同的操作条件下导出的数据驱动方法的有效性。

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