Adaptive Optimal Control of Baker's Yeast Fermentation Process with Extreme Learning Machine and Recursive Least Square Technique

Alli, K; Zhang, J

doi:10.1016/B978-0-323-88506-5.50191-1

Adaptive Optimal Control of Baker's Yeast Fermentation Process with Extreme Learning Machine and Recursive Least Square Technique

Lookup NU author(s): Kazeem Alli ORCiD, Dr Jie Zhang ORCiD

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

© 2021 Elsevier B.V.This paper presents combining extreme learning machine (ELM) and recursive least square (RLS) technique in modelling and optimisation of a fed-batch fermentation process. ELM has some characteristic features of fast training together with better generalisation capability. In order to cope with batch-to-batch variations due to unknown disturbances such as unknown process condition drift, the RLS algorithm is integrated with the ELM to update the output layer weights recursively from batch to batch. The offline trained output layer weights of the ELM are used as the initial parameter estimation in RLS. After updating the ELM model, optimisation is carried out to update the feeding policy for the next batch. The proposed method is applied to a simulated baker's yeast fermentation process and the results obtained shows that the proposed method can cope with unknown disturbance and improve process operation from batch to batch.