STATISTICAL PROCESS-CONTROL SCHEME DESIGN

A simple but effective method to aid in the design of (X) over bar control schemes is presented. Subgroup size, sampling frequency, and control limit selection is combined via a methodology that determines the optimum control scheme. Average production length (APL) is introduced as the criterion for measuring control scheme performance. APL is the total amount of production between a shift in the process mean and signal of the shift, a measure of the effectiveness of a control scheme in maintaining process characteristics as close to target as possible. The methodology recognizes that statistical process control (SPC) involves resource constraints which limit the rate at which a process can be sampled. A model is developed with a sampling rate and maximum false alarm rate as inputs to determine the optimum subgroup size, sampling frequency, and control limits as measured by APL. The methodology includes key elements of control scheme design without the complexity of economic models. The performance of our design method is compared to routine application of classical (X) over bar chart guidelines.