What the study found
The paper proposes a framework for adaptive facility layout in remanufacturing that combines Bayesian inferential, data-driven methods with genetic algorithms and discrete modeling. The authors present it as a way to help manufacturing systems respond to uncertainty in market demand and supply.
Why the authors say this matters
The authors say the framework is motivated by the need for manufacturing systems that can accommodate uncertainty while supporting more sustainable practice through remanufacturing. They conclude that this approach is intended to help mitigate compromise in stakeholder requirements while extending product service life.
What the researchers tested
The researchers proposed a production model that uses Bayesian inference to account for uncertainty, genetic algorithms as a heuristic method for adaptability, and discrete-event modeling to simulate shop floor behavior through sample paths. The abstract describes this as a framework and modeling approach rather than reporting a specific experimental comparison.
What worked and what didn't
The abstract states that the model is designed to account for uncertainty, adapt to system deliverables, and simulate shop floor behavior. It does not report numerical results, comparative performance, or which parts of the framework worked best.
What to keep in mind
The available summary does not describe limitations, dataset details, or validation results. The abstract presents a proposed framework, so the scope and effectiveness beyond the described modeling approach are not stated.
Key points
- The paper proposes a framework for adaptive facility layout in remanufacturing.
- It combines Bayesian inferential data-driven methods, genetic algorithms, and discrete modeling.
- The framework is intended to help manufacturing systems respond to uncertainty in market demand and supply.
- The authors link the work to remanufacturing and more sustainable practice.
- The abstract does not report numerical results or comparative testing.
Disclosure
- Research title:
- Framework combines Bayesian learning and discrete-event modeling for remanufacturing
- Authors:
- Toluwalase Olajoyegbe, Fatemeh Mozaffar, Xiaoou Yang, Beshoy Morkos
- Institutions:
- University of Georgia, Santa Clara University
- Publication date:
- 2026-03-07
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.