Correlation Analysis of Manufacturing Systems

小行星9812858 该基金资助了一个项目，研究制造系统中相关性（作为时间依赖性的代理）对性能的影响。该项目将确定制造系统中具有明显相关性的随机组件;将研究它们对性能统计的影响;并将开发建模技术，以捕获任何存在明显程度的相关性。潜在的随机成分包括客户需求，订单加载时间，机器故障和停机时间的随机过程。该项目将采用一种新的建模方法，称为TES/QTES，它强调在这种随机过程中的相关性的显式建模。TES过程是一类通用的连续空间、离散时间随机过程，旨在同时捕获经验分布和自校正，而QTES本质上是TES的离散化变体，适用于分析建模。该方法将应用于制药、食品加工和微电子等各个行业，以获得性能指标的分析和/或数值解决方案。 它将进一步被用来探索各种制造绩效指标和最佳经营策略的相关性的影响。 如果成功的话，这项研究将产生一个新的相关导向的范式。相关性分析，旨在影响制造业的研究和实践。研究TES/QTES模型有望产生更准确的分析或仿真模型的制造系统和相关的性能预测制造系统。改进的预测将使更有效的生产计划、调度和库存控制变得更容易。相关性分析研究的实践方面将与工业伙伴合作进行。从教育的角度来看，相关性分析将被纳入本科和研究生课程的制造相关的理论和应用，包括模拟，生产控制，库存理论和性能分析。

9812858Altiok This grant fluids a project to study tile performance effects of correlations (as proxies of temporal dependence) in manufacturing systems. The project will identify random components of manufacturing systems with appreciable correlations; will study their impact on performance statistics; and will develop modeling technologies to capture correlations whenever present in appreciable magnitudes. Potential random components include stochastic processes of customer demands, order load times, machine failures and down times The project will employ a novel modeling methodology, called TES/QTES, which emphasizes explicit modeling of correlations in such stochastic processes. TES processes constittute a versatile class of continuous-space, discrete-time stochastic processes designed to capture empirical distributions and autocorreclations, simultaneously, while QTES is essentially a discretized variant of TES, suitable for analytical modeling. The methodology will be applied to various industries including pharmaceutical, food processing and microelectronics, to obtain analytical and/or numerical solutions for performance metrics. It will farther be used ti explore the impact of correlations on various manufacturing performance measures and optimal operating policies. If successful, this research will produce a new correlation-oriented paradigm. correlation analysis, designed to impact both manufacturing research and practices. The research TES/QTES models promise to yield significantly more accurate analytical or simulation models of manufacturing systems and associated performance predictions in manufacturing systems. Improved predictions will faxcilitate more effective production planning, scheduling and inventory control. The practical aspects of the researched correlation analysis will be exercised in collaboration with industrial partners. From The educational viewpoint, correlation analysis will be incorporated into undergraduate and graduate courses on manufacturing-related theory and applications, including simulation, production control, inventory theory and performance analysis.