Open Access
A survey of design methods for failure detection in dynamic systems
Alan S. Willsky
- Vol. 76, pp 11347
Reads0
Chats0
TLDR
A number of methods for detecting abrupt changes (such as failures) in stochastic dynamical systems are surveyed in this paper, where tradeoffs in complexity versus performance are discussed, ranging from the design of specific failure-sensitive filters, to the use of statistical tests on filter innovations, and the development of jump process formulations.Abstract:
A number of methods for detecting abrupt changes (such as failures) in stochastic dynamical systems are surveyed. The class of linear systems is concentrated on but the basic concepts, if not the detailed analyses, carry over to other classes of systems. The methods surveyed range from the design of specific failure-sensitive filters, to the use of statistical tests on filter innovations, to the development of jump process formulations. Tradeoffs in complexity versus performance are discussed.read more
Citations
More filters
Journal ArticleDOI
Adaptive Forgetting in Recursive Identification through Multiple Models
TL;DR: A new recursive identification method, Adaptive forgetting through Multiple Models — AFMM, is presented and evaluated using computer simulations, indicating that AFMM is able to track rapidly changing parameters well, and that the method is robust in several respects.
Journal ArticleDOI
System identification for adaptive and reconfigurable control
TL;DR: In this article, an efficient static system identification method was developed that incorporates prior information, which enhances the performance of the identification algorithm, yielding more accurate parameter estimates, making it suitable for adaptive and reconfigurable control.
Journal ArticleDOI
Neural Network Approach to Detection of Changes in Structural Parameters
TL;DR: In this article, a neural network-based approach is presented for the detection of changes in the characteristics of structure-unknown systems, which relies on the use of vibration measurements from a "healthy" system to train a CNN for identification purposes.
Journal ArticleDOI
A generalized change detection problem
TL;DR: It is shown that the proposed algorithm is asymptotically optimal in this class of sequential change detection/isolation algorithms and the theoretical results are applied to the case of additive changes in linear stochastic models.
Journal ArticleDOI
A recursive multiple model approach to noise identification
X.R. Li,Yaakov Bar-Shalom +1 more
TL;DR: An approach is presented that is valid for nonstationary noise with rapidly or slowly varying statistics as well as stationary noise and the application of the proposed approach to failure detection is illustrated.