Premium
On‐line Fault Detection and Diagnosis in Industrial Processes Using Hidden Markov Model
Author(s) -
Zhou ShaYuan,
Wang ShuQing
Publication year - 2005
Publication title -
developments in chemical engineering and mineral processing
Language(s) - English
Resource type - Journals
eISSN - 1932-2143
pISSN - 0969-1855
DOI - 10.1002/apj.5500130322
Subject(s) - fault (geology) , fault detection and isolation , hidden markov model , process (computing) , sliding window protocol , computer science , pattern recognition (psychology) , principal component analysis , identification (biology) , markov chain , window (computing) , line (geometry) , feature (linguistics) , variable (mathematics) , alarm , markov model , artificial intelligence , data mining , engineering , machine learning , mathematics , mathematical analysis , linguistics , philosophy , botany , geometry , seismology , aerospace engineering , actuator , biology , geology , operating system
For many on‐line fault diagnosis schemes based on process data, a moving time window is an indispensable technique to track dynamic data. In this paper, a novel approach combining variable moving window and hidden Markov model (HMM) for on‐line identification of abnormal operating conditions is proposed. The main feature of this method is that the window length can be changed with time. Before fault diagnosis, some process measurements are used for fault alarm. As a tool for feature extraction, principal component analysis (PCA) is employed in order to reduce the large number of correlated variables. The effectiveness of the approach is illustrated by case studies from the Tennessee Eastman process.