Diagnosis and Reconfiguration using Bayesian Networks: An Electrical Power System Case Study

摘要: Automated diagnosis and reconfiguration are important computational techniques that aim to minimize human intervention in autonomous systems. In this paper, we develop novel models the context of reasoning using causal Bayesian networks (BNs). We take as starting point a successful diagnostic approach, static BN developed for real-world electrical power system. discuss paper extension approach along two dimensions, namely: (i) from dynamic BN; (ii) task task. More specifically, auto-generation network network. addition, subtle, but important, differences between when used versus reconfiguration. agent, which system causally, including effects actions through time, Though general, demonstrate them systems (EPSs) aircraft spacecraft. EPSs vital subsystems on-board spacecraft, many incidents accidents these vehicles have been attributed EPS failures. case study provides initial promising results our setting