System identification (2nd ed.): theory for the user
System identification (2nd ed.): theory for the user
Introduction to Stochastic Search and Optimization
Introduction to Stochastic Search and Optimization
System reliability estimation and confidence regions from subsystem and full system tests
ACC'09 Proceedings of the 2009 conference on American Control Conference
| Hi-index | 0.00 |
This paper develops a method for finding an optimum test plan, which consists of a mixture of full system and subsystem tests, to estimate the reliability of a system. An optimum test plan is developed by trading off the number of full system and subsystem tests to minimize the meansquared error (MSE) of the maximum likelihood estimate (MLE) of system reliability and testing costs. The MSE is decomposed into the variance of the MLE and a bias from incorrectly specifying the function that relates the subsystem reliabilities to the full system reliability (series, parallel, other). The variance of the MLE comes from Fisher theory. The bias is due to the modeling error. Optimum test plans involve trade offs between the MSE (estimation accuracy), the degree of modeling error, and the cost of doing system and subsystem tests. A Pareto frontier can be identified, as illustrated in the paper.