simultaneous monitoring of multivariate-attribute process mean and variability using artificial neural networks

In some statistical process control applications, the quality of the product is characterized by the combination of both correlated variable and attributes quality characteristics. in this paper, we propose a novel control scheme based on the combination of two multi-layer perceptron neural networks for simultaneous monitoring of mean vector as well as the covariance matrix in multivariate-attribute processes whose quality characteristics are correlated. the proposed neural network-based methodology not only detects separate mean and variance shifts, but also can efficiently detect simultaneous changes in mean vector and covariance matrix of multivariate-attribute processes. the performance of the proposed neural network-based methodology in detecting separate as well as simultaneous changes in the process is evaluated thorough a numerical example based on simulation in terms of average run length criterion and the results are compared with a statistical method based on the combination of two control charts that are developed for monitoring the mean vector and covariance matrix of multivariate-attribute processes, respectively. the results of model implementation on numerical example show the superior detection performance of the proposed nn-based methodology rather than the developed combined statistical control charts.