A multiobjective prediction model with incremental learning ability by developing a multi-source filter neural network for the electrolytic aluminium process

• Main Authors: Yao, Lizhong, Ding, Wei, He, Tiantian, Liu, Shouxin, Nie, Ling
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Multi-Source Filter; Unscented Kalman Filter
• Online Access: https://hdl.handle.net/10356/163863
• Institution: Nanyang Technological University

Improving current efficiency and reducing energy consumption are two important technical goals of the electrolytic aluminum process (EAP). However, because the process involves complex noise characteristics (i.e., unknown types, redundant distributions and variable forms), it is very difficult to ac...