Improving the wire bonding process quality using statistically designed experiments

Statistically Designed Experiments (SDE) are used for identifying the critical variables associated with a process and thereby determining the optimal levels for these variables for enhanced performance. These methods are well known among the statisticians but few industrial engineers have any exposure to these powerful problem solving methods because of limited statistical skills and expertise. This paper presents the potential benefits of SDE for product and process quality improvement in a manufacturing environment. The paper also describes the application of SDE to a wire bonding process in order to identify the key variables which affect the pull strength. Both analytical and graphical methods are used for better and rapid understanding of the results to the engineering community. The results of this study will encourage the engineering community to apply methods such as a chronic problem solving tool in their own organisation.