Author ORCID Identifier

https://orcid.org/0009-0007-3109-5865

https://orcid.org/0000-0003-0633-9411

Document Type

Article

Disciplines

1.1 MATHEMATICS, Applied mathematics, Statistics, Chemical engineering (plants, products), Chemical process engineering

Publication Details

https://link.springer.com/chapter/10.1007/978-3-031-45608-4_2

doi:10.1007/978-3-031-45608-4_2

Abstract

Intoday’s rapidly evolving industrial landscape, control room operators must grapple with an ever-growing array of tasks and respon sibilities. One major challenge facing these operators is the potential for task overload, which can lead to decision fatigue and increased reliance on cognitive biases. To address this issue, we propose the use of dynamic influence diagrams (DID) as the core of our decision support system. By monitoring the process over time and identifying anomalies, DIDs can recommend the most effective course of action based on a probabilistic assessment of future outcomes. Instead of letting the operator choose or search for the right procedure, we display automatically the optimal pro cedure according to the model. The procedure is streamlined compared to the traditional approach, focusing on essential steps and adapting to the system’s current state. Our research tests the effectiveness of this approach using a simulated formaldehyde production environment. Preliminary results demonstrate the ability of DIDs to effectively support control room operators in making informed decisions during times of high stress or uncertainty. This work represents an important step forward in the development of intelligent decision support systems for the process industries.

DOI

https://doi.org/10.1007/978-3-031-45608-4_2

Funder

European Union

Creative Commons License

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.

Download
Contact the Author


Share

COinS