Dynamic evolutionary model based on a multi-sampling inherited HAPFNN for an aluminium electrolysis manufacturing system

Open Webpage

Wei Ding, Lizhong Yao, Yanyan Li, Wei Long, Jun Yi, Tiantian He

Published: 2021, Last Modified: 10 Sept 2025Appl. Soft Comput. 2021EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A multi-sampling inherited hybrid annealed particle filter neural network (MSI-HAPFNN) algorithm is proposed.•A multi-sampling technique in MSI-HAPFNN is employed to reduce the interference of abnormal industrial data.•The concept of inheritance is introduced to improve the capacity of data transmission at the latest time.•The proposed algorithm is applied to nonlinear and non-Gaussian systems.•MSI-HAPFNN obtains best results than previous models in the actual industrial manufacturing systems.