Michael Edili Ogbaje, Gregory Onwodi, Felix Ale, Oludolapo Olanrewaju, Kazeem Aderemi Bello, Rendani Wilson Maladzhi, Lanre Daniyan and Ilesanmi Daniyan
Adv. Artif. Intell. Mach. Learn., XX (XX):-
1. Michael Edili Ogbaje: Department of Computer Science National Open University of Nigeria, Abuja, Nigeria
2. Gregory Onwodi: Department of Computer Science, National Open University of Nigeria, Abuja, Nigeria.
3. Felix Ale: National Space Research and Development Agency, Institute of Space Science and Engineering, Obasanjo Space Centre, Umaru Musa Yar’adua Express Way, P. M. B 437, Garki, Abuja 900108, Nigeria.
4. Oludolapo Olanrewaju: Institute of Systems Science, Durban University of Technology, Durban South Africa.
5. Kazeem Aderemi Bello: Department of Mechanical Engineering Durban University of Technology, Durban, South Africa
6. Rendani Wilson Maladzhi: Department of Mechanical Engineering Durban University of Technology Durban, South Africa
7. Lanre Daniyan: Centre for Space Earth Station and Observatory (CSESO), National Space Research and Development Agency, Eruwa, Oyo State, Nigeria
8. Ilesanmi Daniyan: Department of Mechatronics Engineering Bells University of Technology P. M. B. 1015, Ota, Nigeria.
DOI: 10.54364/AAIML.2026.63303
Article History: Received on: 14-Nov-25, Accepted on: 06-May-26, Published on: 13-May-26
Corresponding Author: Michael Edili Ogbaje
Email: edilimike@gmail.com
Citation: Michael Edili Ogbaje, et al. An Artificial Intelligence Driven Digital Twins Framework for Reconfigurable Manufacturing Systems: Towards Integration, Adaptability and Productivity. Advances in Artificial Intelligence and Machine Learning.2026. (Ahead of Print) https://dx.doi.org/10.54364/AAIML.2026.63303
Reconfigurable Manufacturing Systems (RMS) are
being utilised in smart manufacturing due to its ability to rapidly adjust its
functionality and production in line with changes or fluctuations in market
demands. The integration of Artificial Intelligence (AI) with Digital Twin (DT)
offers a robust capability for real-time system’s configuration, predictive
analytics, process optimisation and decision-making in RMS. This study proposed
an AI-DT framework for RMS to enable intelligent reconfiguration, adaptive
control, continuous monitoring and machine learning (ML)-based predictive
analytics. First, systematic literature review was employed to synthesis
existing literature on the applications of AI and DT to identify research gaps
and foster their integration within the RMS environment. Secondly, a framework that
leverages AI, Internet of Things (IoT) and cloud computing was proposed to
process high-volume sensor data to enable effective system’s reconfiguration in
real time. The validation
of the proposed AI-DT model conducted in the Python environment indicated that
the model can achieved up to 35% increase throughput and 55% reduction in
downtime compared to the baseline model. Furthermore, the proposed intelligent
model achieved 48% improvement in response time compared to the baseline. The findings obtained
in this study suggest that integrated AI-DT model can significantly promote the
agility and resilience of RMS in smart manufacturing. The findings of this
study are useful in the exploration of AI-DT models for enhancing the
capabilities of the RMS.