Using multivariate control chart instead of univariate control chart for all variables in processes provides more time and labor advantages that are of signi cance in the relations among variables. However, the statistical calculation of the measured values for all variables is regarded as a single value in the control chart. Therefore, it is necessary to determine which variable(s) are the cause of the out-of-control signal. E ective corrective measures can only be developed when the causes of the fault(s) are correctly determined. The present study was aimed at determining the machine learning techniques that could accurately estimate the fault types. Through the Hotelling T 2 chart, out-ofcontrol signals were identi ed and the types of faults a ected by the variables were speci ed. Various machine learning techniques were used to compare classi cation performances. The developed model was employed in the evaluation of paint quality in a painting process. Arti cial Neural Networks (ANNs) was determined as the most successful technique in terms of the performance criteria. The novelty of this study lies in its classi cation of the faults according to their types instead of those of the variables. De ning the faults based on their types facilitates taking e ective and corrective measures when needed.

Control charts that are used for monitoring the process and detecting the out-of-control signals are important tools for statistical process control. It is simple to estimate source(s) for out-of-control signals in the univariate process, whereas it is difficult to identify the source(s) in the multivariate processes. The reason is that these kinds of processes require monitoring and controlling of more than one quality characteristics simultaneously. In this study, the proposed model is expected to detect the source(s) for out-of-control signals without help of an expert in the process, by using a multilayer neural network. This model was implemented in furniture fasteners manufacturing. Time gain was obtained while detecting source(s) for out-of-control signals.

No abstract

No abstract

No abstract