Abstract
Project management for large-scale industrial operations may be challenged by rigid plans that are susceptible to disruptions from real-world events, potentially leading to schedule and cost overruns. A system for automated workflow optimization can process unstructured data by using an agentic framework to ingest heterogeneous data, such as technical manuals and three-dimensional models, to extract project tasks and their dependencies. A bilevel optimization engine, which could be coupled with Monte Carlo risk simulation, may then process this task list to generate a risk-adjusted and optimized schedule based on variables including, for example, cost and time. This approach can facilitate a more dynamic, data-driven methodology for managing complex projects by transforming raw operational data into actionable execution plans that may account for operational uncertainties.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Goodman, Mike; Foreman, Gary; Agrawal, Sumit; Anderson, Matt; and Mishra, Ashwin, "Automated Risk-Based Schedule Optimization from Unstructured Project Data", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12384