جستجوی مقالات مرتبط با کلیدواژه "real-time scheduling" در نشریات گروه "صنایع"

In this paper, the problem of real-time scheduling of multi-factury production network in the smart manufacturing system with job shop environment is studied. In this smart manufacturing system, a number of independently owned factories are joined together to form a multi-agent production network, which is also called a virtual production network. In such a network, each factory focuses on its interests and communicates with each other by sharing information such as machine breakdowns and job transfers. Therefore, it can be stated that studying the problem of distributed scheduling in the environment of smart factories is important and will have a significant effect on obtaining desirable and ideal results. At first, a bi-objective mixed integer linear programming model is presented; then an approach to solve the dynamic real-time scheduling problem is proposed. Considering the successful applications of the Lagrangian relaxation algorithm in solving scheduling problems, in this research, the improved Lagrangian relaxation algorithm is used to solve the problem. To examine the performance of the proposed algorithm, its results were compared with solving the original model that was solved by the augmented epsilon constraint method. The obtained results showed that the proposed Lagrangian relaxation algorithm has a better performance than the augmented epsilon constraint method

This paper proposes several innovative approaches to model evaluation after obtaining the reinforcement learning model of scheduling with predictive maintenance. To train this model, its reward and loss function must be determined according to the conditions of the workshop environment. One of the innovations of this paper is to provide a definition of the reward function for the issue. This learning model is examined in different modes of work entry into the workshop and the results obtained from other scheduling methods show better outputs. The predictive maintenance model is evaluated by four learning methods and the quality of these models is examined. By selecting and adding the best machine failure model to the scheduling reinforcement learning model, the instant tasks entered into the workshop are assigned to the machines. By comparing the proposed method with the previous ones, the best performance is found and shown.