Monitoring declining quality of ammunition stockpile under step stress

Most ammunition is produced long before its ultimate consumption and stored in a series of different depots for a considerably long period of time. During storage, the quality of the ammunition stockpile deteriorates proportionally to the condition of the depots. We view different conditions associated with a series of depots as step stress. A random effects logistic regression model is employed to predict the quality of ammunition stockpile in terms of the routing information such as a series of locations and duration of storage of ammunition lots. The resultant prediction model can be used to determine the appropriate time for reorder or renovation of ammunition before the quality becomes substandard. An example is given to illustrate the implementation procedure of the prediction model suggested in this article. © 1994 John Wiley & Sons, Inc.