当前位置：
X-MOL 学术
›
Ind. Eng. Chem. Res.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Dynamic Stationary Subspace Analysis for Monitoring Nonstationary Dynamic Processes
Industrial & Engineering Chemistry Research ( IF 3.8 ) Pub Date : 2020-11-16 , DOI: 10.1021/acs.iecr.0c04059 Dehao Wu 1 , Li Sheng 2 , Donghua Zhou 1, 3 , Maoyin Chen 1
Industrial & Engineering Chemistry Research ( IF 3.8 ) Pub Date : 2020-11-16 , DOI: 10.1021/acs.iecr.0c04059 Dehao Wu 1 , Li Sheng 2 , Donghua Zhou 1, 3 , Maoyin Chen 1
Affiliation
|
With the increasing demand for process safety and production efficiency, many research efforts have been made for nonstationary process monitoring in recent years. However, existing methods usually neglect dynamic characteristics of industrial processes, which may lead to misleading results. Only few literature studies address the problem of nonstationary dynamic process monitoring, and most of them are mainly based on the assumption that nonstationary variables are integrated with the same order I = 1. In order to deal with the general case, where nonstationary variables are integrated with different or higher orders, dynamic stationary subspace analysis (DSSA) is proposed in this paper. In DSSA, the time shift technique is introduced to model dynamic relationships, and an optimization problem is described to estimate the stationary projection matrix similar to stationary subspace analysis (SSA). Different from traditional SSA, the alternating direction method of multipliers is utilized to solve the optimization problem, and detailed iteration expressions are derived. After the stationary projection matrix is obtained, the Mahalanobis distance is adopted for monitoring stationary components of augmented data. The monitoring performance of DSSA is demonstrated by case studies on a simulated nonstationary dynamic process, a nonstationary continuous stirred tank reactor, and a practical ultra-supercritical power plant.
中文翻译：
动态平稳子空间分析，用于监视非平稳动态过程
随着对过程安全性和生产效率的日益增长的需求，近年来对于非平稳过程监控已经进行了许多研究工作。但是，现有方法通常会忽略工业过程的动态特性，这可能会导致误导性结果。只有极少数文学研究解决非平稳动态过程监控的问题，其中大部分主要是基于这样的假设非平稳变量与同阶单整我= 1.为了处理一般情况，其中非平稳变量以不同或更高阶积分，本文提出了动态平稳子空间分析（DSSA）。在DSSA中，引入了时移技术来建立动态关系模型，并描述了一个优化问题来估计固定投影矩阵，类似于固定子空间分析（SSA）。与传统的SSA不同，利用乘法器的交替方向法解决了优化问题，并推导了详细的迭代表达式。在获得固定投影矩阵之后，采用马氏距离来监视增强数据的固定分量。通过模拟非平稳动态过程的案例研究证明了DSSA的监控性能，
更新日期：2020-11-25
中文翻译：
动态平稳子空间分析，用于监视非平稳动态过程
随着对过程安全性和生产效率的日益增长的需求，近年来对于非平稳过程监控已经进行了许多研究工作。但是，现有方法通常会忽略工业过程的动态特性，这可能会导致误导性结果。只有极少数文学研究解决非平稳动态过程监控的问题，其中大部分主要是基于这样的假设非平稳变量与同阶单整我= 1.为了处理一般情况，其中非平稳变量以不同或更高阶积分，本文提出了动态平稳子空间分析（DSSA）。在DSSA中，引入了时移技术来建立动态关系模型，并描述了一个优化问题来估计固定投影矩阵，类似于固定子空间分析（SSA）。与传统的SSA不同，利用乘法器的交替方向法解决了优化问题，并推导了详细的迭代表达式。在获得固定投影矩阵之后，采用马氏距离来监视增强数据的固定分量。通过模拟非平稳动态过程的案例研究证明了DSSA的监控性能，
京公网安备 11010802027423号