Data Fusion for Quality Improvements in Complex Solar Cell Manufacturing Processes


The wide deployment and applications of automatic sensing devices and computer systems have resulted in both temporally and spatially dense data-rich environments, which bring new challenges in quality engineering. Data fusion, through integration of engineering domain knowledge with data analysis techniques from advanced statistics, signal processing, decision making and control, represents one of the frontiers in quality improvement research for complex systems. In this presentation, an overview of ongoing research activities along this emerging area will be presented. Examples of methodological developments and their applications will be discussed to demonstrate the characteristics of data fusion research and the need of multidisciplinary efforts. Detail discussions will be given on a model free multiscale process monitoring method for autocorrelated processes, which is demonstrated in solar cell manufacturing processes.

The wide deployment and applications of automatic sensing devices and computer systems have resulted in both temporally and spatially dense data-rich environments, which bring new challenges in quality engineering. Data fusion, through integration of engineering domain knowledge with data analysis techniques from advanced statistics, signal processing, decision making and control, represents one of the frontiers in quality improvement research for complex systems. In this presentation, an overview of ongoing research activities along this emerging area will be presented. Examples of methodological developments and their applications will be discussed to demonstrate the characteristics of data fusion research and the need of multidisciplinary efforts. Detail discussions will be given on a model free multiscale process monitoring method for autocorrelated processes, which is demonstrated in solar cell manufacturing processes