Translate 
Abstract
The paper reviews, represents and captures knowledge about industrial water treatment processes and predicative models, in order to facilitate management of relevant knowledge. The proposed approach is based on a Knowledge Graph (KG), which integrates process knowledge and predictive models, adding context to their application and usage; improves problem and data understanding by facilitating communication between data analysts and process engineers, providing clear, human-readable explanations; and facilitates answering process-related knowledge questions and provides answers that include relevant data elements, models, and key performance indicators (KPIs).Further, the paper includes examples of how the KG can be used in practice. Directions and recommendations are provided, as well as research guidelines of how the KG can augment generative AI approaches, paving the way for the development of retrieval-augmented knowledge management models and systems.
Published Version
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
