Accessibility navigation


Multimodal continual learning for process monitoring: a novel weighted canonical correlation analysis with attention mechanism

Zhang, J., Xiao, J., Chen, M. and Hong, X. ORCID: https://orcid.org/0000-0002-6832-2298 (2023) Multimodal continual learning for process monitoring: a novel weighted canonical correlation analysis with attention mechanism. IEEE Transactions on Neural Networks and Learning Systems. ISSN 2162-237X

[img]
Preview
Text - Accepted Version
· Please see our End User Agreement before downloading.

4MB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.1109/TNNLS.2023.3331732

Abstract/Summary

Aimed at sequential dynamic modes, a novel multimodal weighted canonical correlation analysis using attention mechanism (MWCCA-A) is introduced to derive a single model for process monitoring, by integrating two ideas of replay and regularization in continual learning. Under the assumption that data are received sequentially, subsets of data from past modes with dynamic features are selected and stored as replay data, which are utilized together with the current mode data for continual model parameter estimation. The weighted canonical correlation analysis is introduced to achieve appropriate weightings of past modes’ replay data, so that the latent variables are extracted by maximizing the weighted correlation with its prediction via the attention mechanism. Specifically, replay data weightings are obtained via the probability density estimation from each mode. This is also beneficial in overcoming data imbalance amongst multiple modes and consolidating the significant features of past modes further. Alternatively, the proposed model also regularizes parameters based on its previous modes’ importance, which is measured by synaptic intelligence. Meanwhile, the objective is decoupled into a regularization-related part and a replay-related part, to overcome the potentially unstable optimization trajectory of synaptic intelligence-based continual learning. In comparison with several multimode monitoring methods, the effectiveness of the proposed MWCCA-A approach is demonstrated by a continuous stirred tank heater, Tennessee Eastman process and a practical coal pulverizing system.

Item Type:Article
Refereed:Yes
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:114030
Publisher:IEEE Computational Intelligence Society

Downloads

Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation