A study of polynomial fit-based methods for qualitative trend analysis. (January 2016)

• Record Type: Journal Article
• Authors: Zhou, Bo; Ye, Hao
• Is Part Of: Journal of process control. Volume 37(2016:Jan.)
• Page Start: 21
• Page End: 33
• Publication Date: 2016-01
• Subjects: Qualitative trend analysis -- Trend extraction -- Polynomial fit -- Process monitoring and diagnosis; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2015.11.003
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: Several new polynomial fit based trend extraction algorithms are developed. These algorithms determine parameters automatically in the hypothesis testing framework. Both trend extraction and trend analysis are carried out to form a complete qualitative trend analysis. A comprehensive performance comparison of these algorithms is made. Abstract: Qualitative trend analysis (QTA) of sensor data is a useful tool for process monitoring, fault diagnosis and data mining. However, because of the varying background noise characteristics and different scales of sensor trends, automated and reliable trend extraction remains a challenge for trend-based analysis systems. In this paper, several new polynomial fit-based trend extraction algorithms are first developed, which determine the parameters automatically in the hypothesis testing framework. An existing trend analysis method developed by Dash et al. (2004) is then modified and added to the abovementioned trend extraction algorithms, which form a complete solution for QTA. The performance comparison of these algorithms is made on a set of simulated data and Tennessee Eastman process data based on several metrics.