Identifying Change Point in a Bivariate Normal Process Mean Vector with Monotonic Changes

When a control chart shows an out-of-control condition, a search begins to identify and eliminate the root cause(s) of the process disturbance. The time when the disturbance has manifested itself to the process is referred to as change point. Identification of the change point is considered as an essential step in analyzing and eliminating the disturbance source(s) effectively. When a process control is based on a quality characteristic vector, identification of the change point alone would not help practitioners to an effective elimination of the source(s) contributing to the out-of-control condition. This paper provides a control scheme based on artificial neural networks to identify the change point in a mean vector when the change type is monotonic and at the same time allows one to perform effective diagnostic analysis to identify the variable(s) responsible for the change in a bivariate process. To the best of our knowledge, this the first time that an artificial neural networks scheme is presented to identify the change point and simultaneously perform diagnostic analysis in a multivariate environment when a monotonic change appears in the mean vector. Average run length criterion is used as a vehicle to investigate the performance of the proposed scheme numerically under different correlation structure. Simulation results indicate effective performance for the proposed scheme.