Geometrical inspection point reduction for rigid and non-rigid parts using cluster analysis – an industrial verification
Paper i proceeding, 2007
Since the model program in automotive industry gets more and more extensive, the costs related to inspection increase. Therefore, there are needs for more effective inspection preparation. In many situations, a large number of inspection points are inspected, despite the fact that only a small subset of points is needed. In this paper a method for reducing the number of inspection point using cluster analysis is tested on production data. The method finds clusters, where the points in a cluster are highly correlated. From each cluster only one representing point is selected for inspection. This leads to reductions with up to 90 percent in the case studies considered. Further, the problem about sample size is considered. The sample must be large enough to reflect the different phenomena occurring in the process. The choice of sample size is also affecting the statistical confidence of the estimated correlation coefficient between points or clusters. The theory supports rigid parts as well as non-rigid parts.