Comparison of proportional hazards models and neural networks for reliability estimation

Because of increased manufacturing competitiveness, new methods for reliability estimation are being developed. Intelligent manufacturing relies upon accurate component and product reliability estimates for determining warranty costs, as well as optimal maintenance, inspection, and replacement schedules. Accelerated life testing is one approach that is used for shortening the life of products or components or hastening their performance degradation with the purpose of obtaining data that may be used to predict device life or performance under normal operating conditions. The proportional hazards (PH) model is a non-parametric multiple regression approach for reliability estimation, in which a baseline hazard function is modified multiplicatively by covariates (i.e. applied stresses). While the PH model is a distribution-free approach, specific assumptions need to be made about the time behavior of the hazard rates. A neural network (NN) is particularly useful in pattern recognition problems that involve capturing and learning complex underlying (but consistent) trends in the data. Neural networks are highly non-linear, and in some cases are capable of producing better approximations than multiple regression. This paper reports on the comparison of PH and MN models for the analysis of time-dependent dielectric breakdown data for a metal-oxide-semiconductor integrated circuit. In this case, the NN model results in a better fit to the data based upon minimizing the mean square error of the predictions when using failure data from an elevated temperature and voltage to predict reliability at a lower temperature and voltage.