ANFIS-optimized control for resilient and efficient supply chain performance in smart manufacturing
Due to the dramatic revolution in global trade, competition, and the epidemic of COVID-19, the Small and Medium Enterprises (SME's) production paradigm has been evolving and gaining traction to meet its dynamic demands and challenges for industrial process adaptability and standards. As a resul...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025003470 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Due to the dramatic revolution in global trade, competition, and the epidemic of COVID-19, the Small and Medium Enterprises (SME's) production paradigm has been evolving and gaining traction to meet its dynamic demands and challenges for industrial process adaptability and standards. As a result, they develop Cyber-Physical Production Systems (CPPS) by integrating CPS modules into their manufacturing processes. This integration is founded on the belief that value-added services result from technological advancements. Better tools would be needed in the future to provide process management, monitoring, and maintenance. Our main goal is to support existing SMEs with an economically adaptable solution for technological improvement. So, to make the proposed solution sustainable, the whole process must be analyzed, from the input of raw materials to the output of finished products. This paper evaluates the supply chain (SC) using the adaptive neuro-fuzzy inference system (ANFIS) classification control algorithm to improve the SC performance, maximize the system quality, and minimize the cost. Also, the butterfly optimization algorithm (BOA) is proposed for obtaining optimal parameters for the ANFIS controller algorithm. The performance of the SC is evaluated on the real-time production system, and the results are analyzed to prove the effectiveness of the proposed algorithm. The proposed algorithm can be applied to CPS components in the current SME environment to improve the performance of manufacturing processes. |
|---|---|
| ISSN: | 2590-1230 |