SEAL QUALITY EVALUATION USING MULTIVARIATE STATISTICAL CONTROL CHARTS BASED ON ACCELERATION DATA

A good seal quality is highly wanted to ensure an acceptable shelf-life of the packaged product. A multivariate control charting procedure is applied to on-line seal quality evaluation of the packaging process by means of an accelerometer. A principal component analysis (PCA) based processing of the multivariate accelerometer data allows for correct modeling of the observations and the related Hotelling's T2 and Q test statistics are calculated. In a next step, proper control charts based on these statistics are used as a process monitoring tool for on-line distinction between good and bad seals.