An interoperable adaptive scheduling strategy for knowledgeable manufacturing based on SMGWQ-learning

To address the uncertainty of production environment in knowledgeable manufacturing system, an interoperable knowledgeable dynamic-scheduling system based on multi-agent is designed, wherein an adaptive scheduling mechanism based on the state membership grade weighted Q-learning (known as SMGWQ-learning) is proposed for guiding the equipment agent to select proper scheduling strategy in a dynamic environment. To avoid the side effect of large state space and minimize errors between the clustering and real states, the state membership grade, defined as weight coefficients, is incorporated into the weighted Q-value update so that several Q-values can be updated simultaneously in an iteration. Results from our convergence analysis and simulation experiments show the effectiveness of the proposed strategy that endows the scheduling system with higher intelligence, interoperability and adaptability to environmental changes by self-learning.