Statistical Process Control of Processes Generating Time Dependent Data

9732831英语本赠款提供资金，用于开发一个有效和高效的框架，对流程工业(即化学流程)产生通用的依赖时间的数据的流程进行质量监测和控制。首先，对经验协变图进行分析，并对其性能潜力进行评估。第二，统计过程控制(SPC)和自动过程控制之间的接口将被进一步开发，而不是文献中所发现的。第三，其他新的和现有的统计过程控制方法将在时间相关数据独有的新的过程扰动范例的背景下进行评估。第四，对递归离散时间卡尔曼滤波(RDTKF)进行了改进，并对其在该场景中的应用进行了评估。如果成功，该项目将为流程工业提供一个统一的质量监测和控制工具设计。由此产生的框架应该适合于在许多制造过程中应用，并将根据分析和模拟结果进行良好的测试。具体情况的优势和劣势将被记录在研究议程的任务中。这项研究的影响将通过在学术期刊和不同行业的应用中传播研究成果来实现。

9732831 English This grant provides funding for the development of an effective and efficient framework for the quality monitoring and control of processes generating time dependent data common to the process industries (i.e., chemical processes). First, the empirical covariation chart will be analytically developed, and its performance potential will be evaluated. Second, the interface between statistical process control (SPC) and automatic process control will be further exploited beyond what is found in the literature. Third, other new and existing SPC approaches will be evaluated in the context of a new process disturbance paradigm unique to time dependent data. Fourth, the recursive discrete time Kalman filter (RDTKF) will be modified and evaluated for application in this scenario. If successful, this project will provide a cohesive design of tools for quality monitoring and control for the process industries. The resulting framework should be suitable for application in many manufacturing processes and will be well tested based upon analytical and simulation results. Scenario specific strengths and weaknesses will be documented within the tasks of the research agenda. The impact of the research will be realized through the dissemination of findings in scholarly journals and applications within various industries.