Affiliation:
1. University of California at Los Angeles
Abstract
Conventional Shiryayev Multiple Hypothesis Sequential Probability Test (MHSPT) can be applied only to an independent measurement sequence. We extend Shiryayev MHSPT to applications where the measurements are a correlated sequence generated by known dynamics, and is called here the MHSPTC. This test, which serves as a decision rule, is derived from a dynamic programming approach, and can be applied to announce system failure with probability from residuals generated from analytical redundancy methods. The decision policy is determined by considering cost of measurement, false alarm, and miss detection. This test announces failure disruption in minimum time when false alarm and miss detection rates are specified. The MHSPTC is implemented and verified in the health monitoring system of an automated vehicle.
Reference12 articles.
1. Malladi
D. P.
, and SpeyerJ. L., 1999. “A generalized shiryayev sequential probability ratio test for change detection and isolation.” IEEE Transactions on Automatic Control, AC-44(8), Aug., pp. 1522–1534.
2. Speyer
J. L.
, and WhiteJ. E., 1984. “Shiryayev sequential probability ratio test for redundancy management.” AIAA Journal of Guidance, Control, and Dynamics, 7(5), Sep-Oct, pp. 588–595.
3. Shiryayev, A. N., 1977. Optimal Stopping Rules. Springer-Verlag.
4. Bertsekas, D. P., 2000. Dynamic Programming and Optimal Control, Vol. 1. Athena Scientific.
5. Beard, R. V., 1971. “Failure accomodation in linear systems through self-reorganization.” PhD thesis, Massachusetts Institute of Technology.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. An Aggregate Sector Flow Model for Air Traffic Demand Forecasting;9th AIAA Aviation Technology, Integration, and Operations Conference (ATIO);2009-06-14