A Reward Functional to Solve the Replacement Problem

• 作者: Antonio Oswaldo Ortega Reyes Eva Selene Hernández Gress José Ramón Corona Armenta Oscar Monta?o Arango
• 来源期刊: 智能控制与自动化(英文)
• 学科: 医学
• 关键词: MARKOV CHAINS Dynamic PROGRAMMING REPLACEMENT PROBLEM
• 年，卷（期）: 2012,（4）
• 页码范围: 413-418
• 页数: 6页
• 分类号: R73

摘要

The replacement problem can be modeled as a finite, irreducible, homogeneous Markov Chain. In our proposal the problem was modeled using a Markov decision process and then, the instance was optimized using dynamic programming. We proposed a new functional that includes a reward functional, that can be more helpful in processing industries because it considerate instances like incomes, maintenance costs, fixed costs to replace equipment, purchase price and salvage values;and this functional can be solved with dynamic programming and used to make effective decisions. Two theorems are proved related with this new functional. A numerical example is presented in order to demonstrate the utility of this proposal.