✍ Scribed by L. Monostori; B. Kádár; A. Pfeiffer; D. Karnok
No coin nor oath required. For personal study only.
The paper summarises the main challenges and problems related to customised mass production. In the elaborated solution the reference for real-time production control is generated by a novel scheduling system. Detection of changes and disturbances emerging during the daily production is based on the integration of information coming from the process, quality and production monitoring subsystems. All the information forms the basis of rescheduling policies. In the proposed framework both the more traditional discrete event simulation (in different settings) and the agent-based approach plays key role. The effectiveness of the proposed solutions is shown by experimental results on industrial data.
📜 SIMILAR VOLUMES
We present a strategy for learning optimal control. The approach uses functional-link neural network implementations which have several beneficial properties giving advantages over the more common generalized delta rule implementations. The learning task is decomposed onto three parts: identificatio