SCI和EI收录∣中国化工学会会刊

Chin.J.Chem.Eng. ›› 2015, Vol. 23 ›› Issue (1): 162-172.doi: 10.1016/j.cjche.2014.10.006

• PROCESS SYSTEMS ENGINEERING AND PROCESS SAFETY • Previous Articles     Next Articles

A new process monitoring method based on noisy time structure independent component analysis

Lianfang Cai, Xuemin Tian   

  1. College of Information and Control Engineering, China University of Petroleum, Qingdao 266580, China
  • Received:2013-04-07 Revised:2013-06-16 Online:2015-01-28 Published:2015-01-24
  • Contact: Xuemin Tian E-mail:tianxm@upc.edu.cn
  • Supported by:

    Supported by the National Natural Science Foundation of China (61273160), the Natural Science Foundation of Shandong Province (ZR2011FM014), the Fundamental Research Funds for the Central Universities (12CX06071A), and the Postgraduate Innovation Funds of China University of Petroleum (CX2013060).

Abstract: Conventional process monitoring method based on fast independent component analysis (FastICA) cannot take the ubiquitous measurement noises into account and may exhibit degraded monitoring performance under the adverse effects of themeasurement noises. In this paper, a newprocessmonitoring approach based on noisy time structure ICA (NoisyTSICA) is proposed to solve such problem. A NoisyTSICA algorithm which can consider the measurement noises explicitly is firstly developed to estimate the mixing matrix and extract the independent components (ICs). Subsequently, a monitoring statistic is built to detect process faults on the basis of the recursive kurtosis estimations of the dominant ICs. Lastly, a contribution plot for the monitoring statistic is constructed to identify the fault variables based on the sensitivity analysis. Simulation studies on the continuous stirred tank reactor system demonstrate that the proposed NoisyTSICA-based monitoring method outperforms the conventional FastICA-based monitoring method.

Key words: Process monitoring, Independent component analysis, Measurement noises, Kurtosis, Mixing matrix, Contribution plot, Sensitivity analysis