Gated recurrent unit autoencoder for fault detection in penicillin fermentation process.

Petrovski, Andrei; Arifeen, Murshedul; Petrovski, Sergei

Abstract

The penicillin fermentation process is a fed-batch system to generate industrial-scale penicillin for antibiotic production. Any fault in the fermentation tank can lead to low-quality penicillin products, which may cause a severe impact on final antibiotic production. In this paper, we have developed a Gated Recurrent Unit-based Autoencoder deep learning model to detect faults in the batch data of the penicillin fermentation process. In particular, we have used the data shuffling strategy to minimize distribution discrepancy from different batches generated under various controlling conditions for training the deep learning model. We have also compared the model with the Feedforward Autoencoder and Long short-term memory Autoencoder model for fault detection. Experimental results show that our model trained on shuffled data from different batches outperformed the Feedforward and Long short-term memory Autoencoder model with an avergae fault detection rate of 94.74%.

Citation

PETROVSKI, A., ARIFEEN, M. and PETROVSKI, S. 2023. Gated recurrent unit autoencoder for fault detection in penicillin fermentation process. In Kovalev, S., Kotenko, I. and Sukhanov, A. (eds.) Proceedings of the 7th Intelligent information technologies for industry international scientific conference 2023 (IITI'23), 20-25 September 2023, St. Petersburg, Russia, volume 1. Lecture notes in networks and systems (LNNS), 776. Cham: Springer [online], pages 86-95. Available from: https://doi.org/10.1007/978-3-031-43789-2_8

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 7th Intelligent information technologies for industry international scientific conference 2023 (IITI'23)
• Start Date: Sep 25, 2023
• End Date: Sep 30, 2023
• Acceptance Date: May 29, 2023
• Online Publication Date: Sep 21, 2023
• Publication Date: Dec 31, 2023
• Deposit Date: Oct 12, 2023
• Publicly Available Date: Sep 22, 2024
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 86-95
• Series Title: Lecture notes in networks and systems (LNNS)
• Series Number: 776
• Series ISSN: 2367-3370; 2367-3389
• Book Title: Proceedings of the seventh international scientific conference Intelligent information technologies for industry (ITTI'23)
• ISBN: 9783031437885
• DOI: https://doi.org/10.1007/978-3-031-43789-2_8
• Keywords: Fault detection; Autoencoder; Gated recurrent unit; Penicillin fermentation
• Public URL: https://rgu-repository.worktribe.com/output/2107579