Study On Profile Monitoring In Complex Products Manufacturing

Profile monitoring is the utilization of control charts for checking the stability of the quality of a product over time when the quality of a process or a product is characterized by a function (namely the profile) at each time point. Currently profile monitoring is a hot research point in statistical quality control. This study presents some profile monitoring approaches to monitor nonlinear profiles with varied argument values, linear profiles with within-profile correlations, linear circular profiles, and to detect directed shape changes of linear profiles, respectively.This study firstly proposed a novel nonparametric control scheme based on profile error for monitoring nonlinear profiles with varied argument values. The proposed scheme uses the metrics of profile error as the statistics to construct the control charts. More details about the design of this nonparametric scheme are also discussed. The monitoring performance of the combined control scheme is compared with that of alternative nonparametric methods via simulation. Simulation studies show that the combined scheme is effective in detecting parameter error and is sensitive to small shifts in the process. In addition, due to the properties of the charting statistics, the out-of-control signal can provide diagnostic information for the users. Also the implementation steps of the proposed monitoring scheme are given and applied for monitoring the blade manufacturing process. With the application in blade manufacturing of aircraft engines, the proposed nonparametric control scheme is effective, interpretable, and easy to apply.This study also focuses on monitoring linear profiles with within-profile correlation which is described by a Gaussian process model. Two Shewhart-type multivariate control charts are proposed to monitor the linear trend term and the within-profile correlation separately in Phase II. The proposed approaches are compared with alternative methods through numerical simulations in which different in-control within-profile correlations are considered. Simulation studies show that the proposed control charts are sensitive to changes in the linear trend term when the correlation is strong and effective in detecting large shifts in the within-profile correlation. Furthermore, an example is given to illustrate the implementation of our proposed control charts Next, in order to quickly detect the shape changes from a straight line to a second-order polynomial curve, three control charts based on the hypothesis testing on the quadratic term are proposed as the directed process monitoring approaches. Comparsion simulation studies show that the proposed charts are robust when the out-of-control second-order profile moves along Y-axis, and are effective in detecting shape changes when the out-of-control profiles are around or near the in-control profile. When the out-of-control profiles are far away from the in-control profile, the larger the number of the observed points on each profile, the more effective the proposed methods perform.Finally, this study focuses on monitoring the ordinary linear circular regression. A control chart is proposed for monitoring the parameters of the linear circular-circular profile simultaneously in Phase II, and a control scheme is developed for Phase I. Simulation study illustrates that our proposed control chart performs well.