• 품질경영학회지
• /
• 제43권1호
• /
• pp.31-42
• /
• 2015

Purpose: System consists of a lot of units with coherent function. In design phase, various units could be considered with the same function. In this study, we consider the alternative units with the same function and redundancy allocation to maximize system reliability in multi level system. Methods: The redundancy allocation problem with the alternative units in multi level system is formulated. Memetic algorithm(MA) is proposed to optimize the redundancy allocation problem. In addition, the performance of the proposed algorithm is explained by a numerical experiment. Results: MA showed better results than genetic algorithm(GA) and the convergence of the solutions in MA was also faster than GA. In addition, we could know from experiment that system reliability is increased and the chosen unit for redundancy allocation is changed if cost limit is increased. Conclusion: The chose unit for redundancy allocation is changed as resource constraints. It means we need to consider the alternative units in system design. In the future, we need to consider various problem related to redundancy allocation in multi level system and develop the better method to enhance search performance.

• Journal of Advanced Marine Engineering and Technology
• /
• 제38권8호
• /
• pp.1004-1009
• /
• 2014

The redundancy allocation problem has usually considered only the component redundancy at the lowest-level for the enhancement of system reliability. A system can be functionally decomposed into system, module, and component levels. Modular redundancy can be more effective than component redundancy at the lowest-level because in modular systems, duplicating a module composed of several components can be easier, and requires less time and skill. We consider a multi-level redundancy allocation problem in which all cases of redundancy for system, module, and component levels are considered. A tabu search of memory-based mechanisms that balances intensification with diversification via the short-term and long-term memory is proposed for its solution. To the best of our knowledge, this is the first attempt to use a tabu search for this problem. Our tabu search algorithm is compared with the previous genetic algorithm for the problem on the new composed test problems as well as the benchmark problems from the literature. Computational results show that the proposed method outstandingly outperforms the genetic algorithm for almost all test problems.

• 대한산업공학회지
• /
• 제43권2호
• /
• pp.135-146
• /
• 2017

This paper considers redundancy optimization problems of multi-level systems and reviews existing papers which proposed various optimization models and used different algorithms in this research area. Three different mathematical models are studied: Multi-level redundancy allocation (MRAP), multiple multi-level redundancy allocation, and availability-based MRAP models. Many meta-heuristics are applied to find optimal solutions in the several optimization problems. We summarized key idea of meta-heuristics applied to the existing MARP problems. Two extended models (MRAP with interval reliability of units and an integrated optimization problem of MRAP and preventive maintenance) are studied and further research ideas are discussed.

• 품질경영학회지
• /
• 제47권4호
• /
• pp.701-711
• /
• 2019

Purpose: The problem of optimizing redundancy allocation in multi-level systems is considered when each item in a multi-level system has alternative items with the same function. The number of redundancy of multi-level system is allocated to maximize the reliability of the system under path set and cost limitation constraints. Methods: Based on cost limitation and path set constraints, a mathematical model is established to maximize system reliability. Particle swarm optimization is employed for redundant allocation and verified by numerical experiments. Results: Comparing the particle swarm optimization method and the memetic algorithm for the 3 and 4 level systems, the particle swarm optimization method showed better performance for solution quality and search time. Particularly, the particle swarm optimization showed much less than the memetic algorithm for variation of results. Conclusion: The proposed particle swarm optimization considerably shortens the time to search for a feasible solution in MRAP with path set constraints. PS optimization is expected to reduce search time and propose the better solution for various problems related to MRAP.