Location
Online
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2023 12:00 AM
End Date
7-1-2023 12:00 AM
Description
Power outages and fluctuations represent serious crisis situations in energy-intensive process industry like glass and paper production, where substances such as oil, gas, wood fibers or chemicals are processed. Power disruptions can interrupt chemical reactions and produce tons of waste as well as damage of machine parts. But, despite of the obvious criticality, handling of outages in manufacturing focuses on commissioning of expensive proprietary power plants to protect against power outages and implicit gut feeling in anticipating potential disruptions. With AISOP, we introduce a model for AI-based scenario planning for predicting crisis situations. AISOP uses conceptual, well-defined scenario patterns to capture entities of crisis situations. Data streams are mapped onto these patterns for determining historic crisis scenarios and predicting future crisis scenarios by using inductive knowledge and machine learning. The model was exemplified within a proof of concept for energy-driven disruption prediction. We were able to evaluate the proposed approach by means of a set of data streams on weather and outages in Germany in terms of performance in predicting potential outages for manufacturers of paper industry with promising results.
Recommended Citation
Janzen, Sabine; Gdanitz, Natalie; Abdel Khaliq, Lotfy; Munir, Talha; Franzius, Christoph; and Maass, Wolfgang, "Anticipating Energy-driven Crises in Process Industry by AI-based Scenario Planning" (2023). Hawaii International Conference on System Sciences 2023 (HICSS-56). 5.
https://aisel.aisnet.org/hicss-56/in/data_spaces/5
Anticipating Energy-driven Crises in Process Industry by AI-based Scenario Planning
Online
Power outages and fluctuations represent serious crisis situations in energy-intensive process industry like glass and paper production, where substances such as oil, gas, wood fibers or chemicals are processed. Power disruptions can interrupt chemical reactions and produce tons of waste as well as damage of machine parts. But, despite of the obvious criticality, handling of outages in manufacturing focuses on commissioning of expensive proprietary power plants to protect against power outages and implicit gut feeling in anticipating potential disruptions. With AISOP, we introduce a model for AI-based scenario planning for predicting crisis situations. AISOP uses conceptual, well-defined scenario patterns to capture entities of crisis situations. Data streams are mapped onto these patterns for determining historic crisis scenarios and predicting future crisis scenarios by using inductive knowledge and machine learning. The model was exemplified within a proof of concept for energy-driven disruption prediction. We were able to evaluate the proposed approach by means of a set of data streams on weather and outages in Germany in terms of performance in predicting potential outages for manufacturers of paper industry with promising results.
https://aisel.aisnet.org/hicss-56/in/data_spaces/5