Diagnosing faults in electrical power systems of spacecraft and aircraft

Authors:
Ole J. Mengshoel;Adnan Darwiche;Keith Cascio;Mark Chavira;Scott Poll;Serdar Uckun
Affiliations:
USRA, RIACS, NASA Ames Research Center, Moffett Field, CA;Computer Science Department, University of California, Los Angeles, CA;Computer Science Department, University of California, Los Angeles, CA;Google and Computer Science Department, University of California, Los Angeles, CA;Intelligent Systems Division, NASA Ames Research Center, Moffett Field, CA;Intelligent Systems Division, NASA Ames Research Center, Moffett Field, CA
Venue:
IAAI'08 Proceedings of the 20th national conference on Innovative applications of artificial intelligence - Volume 3
Year:
2008

Citing 11
Cited 9

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
The computational complexity of probabilistic inference using Bayesian belief networks (research note)

Artificial Intelligence
Finding MAPs for belief networks is NP-hard

Artificial Intelligence
Bucket elimination: a unifying framework for reasoning

Artificial Intelligence
The Challenges of Real-Time AI

Computer
A differential approach to inference in Bayesian networks

Journal of the ACM (JACM)
Controlled generation of hard and easy Bayesian networks: Impact on maximal clique size in tree clustering

Artificial Intelligence
Macroscopic models of clique tree growth for Bayesian networks

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Complexity results and approximation strategies for MAP explanations

Journal of Artificial Intelligence Research
Exploiting causal independence in Bayesian network inference

Journal of Artificial Intelligence Research
Compiling Bayesian networks using variable elimination

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence

Estimation of faults in DC electrical power system

ACC'09 Proceedings of the 2009 conference on American Control Conference
Understanding the scalability of Bayesian network inference using clique tree growth curves

Artificial Intelligence
Bayesian networks

Communications of the ACM
Probabilistic model-based diagnosis: an electrical power system case study

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on model-based diagnostics
A comprehensive diagnosis methodology for complex hybrid systems

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on model-based diagnostics
Towards software health management with bayesian networks

Proceedings of the FSE/SDP workshop on Future of software engineering research
Portfolios in Stochastic Local Search: Efficiently Computing Most Probable Explanations in Bayesian Networks

Journal of Automated Reasoning
Who guards the guardians?: toward v&v of health management software

RV'10 Proceedings of the First international conference on Runtime verification
An aircraft electric power testbed for validating automatically synthesized reactive control protocols

Proceedings of the 16th international conference on Hybrid systems: computation and control

Quantified Score

Hi-index	0.02

Visualization

Abstract

Electrical power systems play a critical role in spacecraft and aircraft. This paper discusses our development of a diagnostic capability for an electrical power system testbed, ADAPT, using prohabilistic techniques. In the context of ADAPT, we present two challenges, regarding modelling and real-time performance, often encountered in real-world diagnostic applications. To meet the modelling challenge, we discuss our novel high-level specification language which supports autogeneration of Bayesian networks. To meet the real-time challenge, we compile Bayesian networks into arithmetic circuits. Arithmetic circuits typically have small footprints and are optimized for the real-time avionics systems found in spacecraft and aircraft. Using our approach, we present how Bayesian networks with over 400 nodes are auto-generated and then compiled into arithmetic circuits. Using real-world data from ADAPT as well as simulated data, we obtain average inference times smaller than one millisecond when computing diagnostic queries using arithmetic circuits that model our real-world electrical power system.