.png){kind=icon}
.png){kind=icon}
Return
Explainable scheduling in vehicle-as-a-conveyor matrix manufacturing systems via deep reinforcement learning
.png){kind=icon}
OA
AI
C
W
S
S
DOI：10.1093/jcde/qwag058.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A matrix manufacturing system (MMS) is a highly flexible production system designed to adapt to uncertainties in product demand and shop floor operations, with a focus on maximizing production efficiency and adaptability. Recently, the emergence of the vehicle-as-a-conveyor (VaaC) concept presents an opportunity to fully leverage the flexibility and parallel processing capabilities of MMS. VaaC is a concept in which a vehicle autonomously navigates among workstations and undergoes various processes during production. To ensure efficient operation of an MMS integrated with VaaC (VaaC-MMS), it is crucial to develop an optimization methodology. This paper proposes a methodology for explainable optimization via deep reinforcement learning to enhance dynamic scheduling and resource utilization of the VaaC-MMS. The learning processes and learned policies are interpreted using frequency-map analysis, action-occlusion sensitivity analysis, and SHapley Additive exPlanations (SHAP) based feature attribution. The proposed methodology applies deep Q-network, proximal policy optimization, and asynchronous advantage actor-critic algorithms. To validate the proposed methodology, a case study was conducted focusing on the trim part assembly process in the automotive industry. This paper contributes to the realization of VaaC-MMS and provides a valuable reference for envisioning the factory of the future in the automotive industry.
Journal
IF:
6.1
Papers:
392
Citations:
3.2K
Organization
Cited Papers