SPC procedures for process inspection by attributes are usually designed under the assumption of directly observed quality data. However, in many practical cases this direct observations are very costly or even hardly possible. For example, in the production of pharmaceuticals costly and time consuming chemical analyses are required for the determination of product's quality even in the simplest case when we have to decide whether the inspected product conforms to quality requirements. The situation is evenmore difficultwhen quality tests are destructive and long-lasting, as it is in the case of reliability testing. In such situations we try to predict the actual quality of inspected items using the values of predictors whose values are easily measured. In the paper we consider a situation when traditional prediction models based on the assumption of the multivariate normal distribution cannot be applied. Instead, for prediction purposes we propose to use some techniques known from data mining. In this study, which has an introductory character, and is mainly based on the results of computer simulations, we show how the usage of popular data mining techniques, such as binary regression, linear discrimination analysis, and decision trees may influence the results of process inspection.
CITATION STYLE
Hryniewicz, O. (2015). Process inspection by attributes using predicted data. In Challenges in Computational Statistics and Data Mining (Vol. 605, pp. 113–134). Springer International Publishing. https://doi.org/10.1007/978-3-319-18781-5_7
Mendeley helps you to discover research relevant for your work.