Date of Award


Publication Type


Degree Name



Industrial and Manufacturing Systems Engineering


Computer Aided Process Planning;Flexible Job Shop Scheduling;Rescheduling;Setup Planning;Supervised Classification Learning


Ahmed Azab



Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.


In the era of digitalization, manufacturing industries are transitioning to Smart Manufacturing (SM) to meet customized customer demands. However, the integration of CAPP and scheduling (ICAPPS) remains a challenge due to conflicting objectives. Most of the literature in existence does not consider the IPPS problem in real-world or dynamic multi-part and multi-machine scenarios and cannot address the sequencing objectives. In this research we propose a machine learning-optimization model to assign and sequence setups in a dynamic flexible job shop environment, considering real-time disruptions like machine breakdowns. The research aims to bridge the gap between process planning and scheduling by treating setups as dispatching units, minimizing makespan, and enhancing manufacturing flexibility. The Dynamic Flexible Job Shop Problem (DFJSP) is solved through a comprehensive methodology that encompasses solving with mathematical programming, heuristics, and creation of a robust dataset for data mining by extracting attributes reflecting priority relationships among setups. The empirical findings demonstrate the effectiveness of the proposed methodology, with the mining model outperforming classical dispatching rules. Furthermore, the model exhibits robust generalization capabilities. This research contributes valuable insights into addressing the complex CAPP and scheduling problems for smart manufacturing environments.

Available for download on Friday, October 04, 2024