考虑扰动的制造供应链配置优化方法研究

发布时间：2018-05-12 05:22

本文选题：制造供应链 + 配置优化　；参考：《大连理工大学》2014年硕士论文

【摘要】：随着科学技术的不断进步与生产力的飞速发展,供应链管理越来越受重视。在制造供应链中,核心企业把供应链中所有企业看作一个整体,做任何决定均从整体利益角度出发。当核心企业选定供应链上的其他供应商时,就已经决定了该制造供应链的质量。因此,为了提高供应链管理的绩效,就需要优化供应链的配置,为供应链选取最适合的合作伙伴——供应商。在选取供应商时,需要考虑供应链上的企业为追求利润,以期将生产加工时间安排在集中的时间段内。当其具有较短的提前期时,企业可以在剩余的时间安排其他产品生产,创造更多的利润,同时从供应链角度,此时供应链整体对市场的响应速度较快,具有竞争优势。因此,本文将提前期作为衡量供应商的一个重要指标。然而快速响应市场的供应商成本较高,反之,成本低的供应商响应市场速度慢,故选取供应商本质上是对供应商的成本与响应市场速度的权衡。同时,考虑到经济、政治、自然环境的不断变化可能造成供应商中断生产的情况发生,为了防止供应商无法按时供货造成供应链断裂,本文在选取供应商时,供应链的每一阶段均选取两家供应商进行供货。基于以上两点,本文以一家笔记本电脑生产企业的供应链为研究对象,建立关于“成本-提前期”的供应链配置优化模型。在算法求解方面,考虑到以往的动态规划算法无法求解多目标优化问题,本文引入融合微粒群优化与局部邻域搜索思想的新混合算法进行求解。PSO算法求解全局问题具有较高的效率,局部邻域搜索则在局部搜索时具有较好的搜索精度,结合二者优势,设计两种混合PSO算法求解。数据验证结果表明,基于swap邻域结构的混合PSO算法比基于three_swap邻域结构的混合PSO算法更为有效。通过基于swap邻域结构的混合PSO算法获得两种供应链的配置优化方案。随后,为了验证选取两家供应商的供应链具有可靠性,对供应链配置优化方案得到的两种供应链进行比较,建立出现扰动的供应链模型,比较选取一家供应商与选取两家供应商的供应链出现扰动后的利润变化情况。数据验证结果表明,选取两家供应商的供应链更具有可靠性。考虑成本与提前期的供应链配置优化模型通过权衡供应商的成本、提前期和可靠性因素,明确了供应链中合作伙伴的选择标准,为面向订单装配的供应链选择合作伙伴提供了数据信息支持。
[Abstract]:With the continuous progress of science and technology and the rapid development of productivity, supply chain management has been paid more and more attention. In manufacturing supply chain, core enterprises regard all enterprises in supply chain as a whole, and make any decision from the angle of overall benefit. When the core enterprise selects other suppliers in the supply chain, it already determines the quality of the manufacturing supply chain. Therefore, in order to improve the performance of supply chain management, it is necessary to optimize the configuration of supply chain and select the most suitable partner-supplier for supply chain. In the selection of suppliers, enterprises in the supply chain should be considered in pursuit of profit, in order to arrange the production and processing time in a centralized time period. When it has a short lead time, the enterprise can arrange the production of other products in the remaining time to create more profits. At the same time, from the supply chain point of view, the supply chain as a whole has a faster response to the market and has a competitive advantage. Therefore, this paper regards lead time as an important index to measure suppliers. However, the suppliers who respond to the market quickly have a higher cost, whereas the suppliers with low cost respond to the market slowly, so the selection of suppliers is essentially a trade-off between the cost of suppliers and the speed of responding to the market. At the same time, considering that the changing economy, politics and natural environment may lead to the interruption of the supplier's production, in order to prevent the supplier from not supplying on time, the supply chain is broken. Two suppliers are selected for each stage of the supply chain. Based on the above two points, this paper takes the supply chain of a notebook computer manufacturing enterprise as the research object, and sets up a supply chain configuration optimization model about "cost-lead time". In the aspect of algorithm solving, considering that the previous dynamic programming algorithm can not solve the multi-objective optimization problem, In this paper, a new hybrid algorithm combining particle swarm optimization and local neighborhood search is introduced to solve the global problem. PSO has a high efficiency in solving the global problem, and the local neighborhood search has a better search accuracy in local search, which combines the advantages of both. Two hybrid PSO algorithms are designed to solve the problem. The data validation results show that the hybrid PSO algorithm based on the swap neighborhood structure is more effective than the hybrid PSO algorithm based on the three_swap neighborhood structure. Two supply chain configuration optimization schemes are obtained by hybrid PSO algorithm based on swap neighborhood structure. Then, in order to verify the reliability of the supply chain selected from two suppliers, the supply chain model with disturbance is established by comparing the two supply chain configuration optimization schemes. The profit changes of the supply chain with one supplier and two suppliers were compared. The results show that the supply chain with two suppliers is more reliable. The optimization model of supply chain configuration considering cost and lead time defines the selection criteria of partners in the supply chain by weighing the cost, lead time and reliability factors of suppliers. It provides data information support for supply chain selection partners for order-oriented assembly.
【学位授予单位】：大连理工大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：F274

【参考文献】