Localized, adaptive recursive partial least squares regression for dynamic system modeling

• Main Authors: Brown, Steven D., Ni, Wangdong, Tan, Soon Keat, Ng, Wun Jern
• Other Authors: School of Civil and Environmental Engineering
• Format: Article
• Language: English
• Published: 2013
• Subjects: DRNTU::Engineering::Environmental engineering
• Online Access: https://hdl.handle.net/10356/100953; http://hdl.handle.net/10220/16707
• Institution: Nanyang Technological University

A localized and adaptive recursive partial least squares algorithm (LARPLS), based on the local learning framework, is presented in this paper. The algorithm is used to address, among other issues in the recursive partial least-squares (RPLS) regression algorithm, the “forgetting factor” and sensitivity of variable scaling. Two levels of local adaptation, namely, (1) local model adaptation and (2) local time regions adaptation, and three adaptive strategies, (a) means and variances adaptation, (b) adaptive forgetting factor, and (c) adaptive extraction of local time regions, are provided using the LARPLS algorithm. Compared to RPLS, the LARPLS model is proven to be more adaptive in the face of process change, maintaining superior predictive performance, as demonstrated in the modeling of three different types of processes.