Agent-based intelligent manufacturing control systems are capable to efficiently respond and adapt to environmental changes. Manufacturing system adaptation and evolution can be addressed with learning mechanisms that increase the intelligence of agents. In this paper a manufacturing scheduling method is presented based on Timed Colored Petri Nets (CTPNs) and reinforcement learning (RL). CTPNs model the manufacturing system and implement the scheduling. In the search for an optimal solution a scheduling agent uses RL and in particular the Q-learning algorithm. A warehouse order-picking scheduling is presented as a case study to illustrate the method. The proposed scheduling method is compared to existing methods. Simulation and state space results are used to evaluate performance and identify system properties.

Purpose: Information distortion results in demand variance amplification in upstream supply chain members, known as the bullwhip effect, and inventory inaccuracy in the inventory records. As inventory inaccuracy contributes to the bullwhip effect, the purpose of this paper is to investigate the impact of inventory inaccuracy on the bullwhip effect in radio-frequency identification (RFID)-enabled supply chains and, in this context, to evaluate supply chain performance because of the RFID technology.Design/methodology/approach: A simulation modeling method based on hierarchical timed colored petri nets is presented to model inventory management in multi-stage serial supply chains subject to inventory inaccuracy for various traditional and information sharing configurations in the presence and absence of RFID. Validation of the method is done by comparing results obtained for the bullwhip effect with published literature results.Findings: The bullwhip effect is increased in RFID-enabled multi-stage serial supply chains subject to inventory inaccuracy. The information sharing supply chain is more sensitive to the impact of inventory inaccuracy.Research limitations/implications: Information sharing involves collaboration in market demand and inventory inaccuracy, whereas RFID is implemented by all echelons. To obtain the full benefits of RFID adoption and collaboration, different collaboration strategies should be investigated.Originality/value: Colored petri nets simulation modeling of the inventory management process is a novel approach to study supply chain dynamics. In the context of inventory errors, information on RFID impact on the dynamic behavior of multi-stage serial supply chains is provided.