Yazar "Sel, Cagri" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    A Multi-Agent Reinforcement Learning Approach to the Dynamic Job Shop Scheduling Problem
    (Mdpi, 2023) Inal, Ali Firat; Sel, Cagri; Aktepe, Adnan; Turker, Ahmet Kursad; Ersoz, Suleyman
    In a production environment, scheduling decides job and machine allocations and the operation sequence. In a job shop production system, the wide variety of jobs, complex routes, and real-life events becomes challenging for scheduling activities. New, unexpected events disrupt the production schedule and require dynamic scheduling updates to the production schedule on an event-based basis. To solve the dynamic scheduling problem, we propose a multi-agent system with reinforcement learning aimed at the minimization of tardiness and flow time to improve the dynamic scheduling techniques. The performance of the proposed multi-agent system is compared with the first-in-first-out, shortest processing time, and earliest due date dispatching rules in terms of the minimization of tardy jobs, mean tardiness, maximum tardiness, mean earliness, maximum earliness, mean flow time, maximum flow time, work in process, and makespan. Five scenarios are generated with different arrival intervals of the jobs to the job shop production system. The results of the experiments, performed for the 3 x 3, 5 x 5, and 10 x 10 problem sizes, show that our multi-agent system overperforms compared to the dispatching rules as the workload of the job shop increases. Under a heavy workload, the proposed multi-agent system gives the best results for five performance criteria, which are the proportion of tardy jobs, mean tardiness, maximum tardiness, mean flow time, and maximum flow time.
  • [ X ]
    Öğe
    A hybrit approach on single server parallel machines scheduling problem with sequence dependent setup times
    (Gazi Univ, Fac Engineering Architecture, 2011) Türker, A. Kürşad; Sel, Cagri
    In this paper, a scheduling problem on two identical parallel machines with sequence-dependent setup times and setup operations that performed by a single server is considered. The main objective is to minimize the makespan of the schedule. For solution procedure, an algorithm combining genetic algorithm and tabu search methodology is proposed. Firstly, the algorithm finds an initial solution using genetic algorithm module. Then, tabu search module is applied to the solution of genetic algorithm in order to find better solution. The performance of the algorithm is analyzed by comparing the results with the random search results. It has been seen that the proposed algorithm is effective to solve P2,S vertical bar STsd vertical bar Cmax scheduling problem in reasonable time, and the results are close to optimum solution values.
  • Küçük Resim
    Öğe
    Integrated definition modeling and Taguchi analysis of flexible manufacturing systems: aircraft industry application
    (Springer London Ltd, 2013) Pinarbasi, Mehmet; Sel, Cagri; Alagas, Haci Mehmet; Yuzukirmizi, Mustafa
    In this paper, flexible manufacturing systems (FMS) are studied. Firstly, an FMS design approach is proposed using integrated definition for function methodology. A systematic layout design and performance evaluation scheme is presented and detailed using this modeling framework. Then, the proposed approach is carried out with a case study from an aircraft industry to convert an existing traditional production system to FMS. To improve the system performance, a simulation-based method with Taguchi approach consisting of multiproducts is utilized. The objective is to find the machine and the product mix that achieves the maximum utilization while minimizing the cycle time. FMS system performance has been greatly improved by determining the most advantageous level of system components. It has also shown that FMS is a practicable production system in aircraft industry.
  • [ X ]
    Öğe
    Scheduling Two Parallel Machines with Sequence-dependent Setups and A Single Server
    (Gazi Univ, 2011) Turker, A. Kursad; Sel, Cagri
    This paper presents a scheduling problem on parallel machines with sequence-dependent setup times and setup operations that performed by a single server. The main purpose is to get minimum makespan of the schedule. The system is formulated as genetic algorithm with problem sizes consisting of two machines and 10, 20 and 30 jobs. A genetic algorithm is developed using random data sets. The optimum results are obtained using a string based permutation algorithm which scans all alternatives. As a result, proposed algorithm is effective to solve P2,S|STsd|Cmax scheduling problem on reasonable runtime and the results of the algorithm which are close to optimum solution values. Effectiveness of the solution is presented considering approximation rates of the genetic algorithm solutions to the optimum results obtained for P2,S|STsd|Cmax problem.