HIDDEN MARKOV-MODELS FOR FAULT-DETECTION IN DYNAMIC-SYSTEMS

PATTERN RECOGNITION

卷:27

Article

关键词: FAULT DIAGNOSIS;    CLASSIFICATION;    NEURAL NETWORKS;    HIDDEN MARKOV MODELS;    DYNAMIC SYSTEMS;    MONITORING;    RELIABILITY;    NOVEL CLASSES;   

DOI  :  10.1016/0031-3203(94)90024-8

来源: Elsevier

【 摘 要 】

Continuous monitoring of complex dynamic systems is an increasingly important issue in diverse areas such as nuclear plant safety, production line reliability, and medical health monitoring systems. Recent advances in both sensor technology and computational capabilities have made on-line permanent monitoring much more feasible than it was in the past. In this paper it is shown that a pattern recognition system combined with a finite-state hidden Markov model provides a particularly useful method for modelling temporal context in continuous monitoring. The parameters of the Markov model are derived from gross failure statistics such as the mean time between failures. The model is validated on a real-world fault diagnosis problem and it is shown that Markov modelling in this context offers significant practical benefits.

【 授权许可】

Free