Comining Quantitative and Qualitative Models with Active Observtions to Improve Diagnosis of Complex Systems
Quantitative and qualitative models and reasoning methods for diagnosis are able to cover a wide range of different properties of a system. Both groups of methods have advantages and drawbacks in respect to fault diagnosis. In this chapter we propose a framework which combines methods of both groups to a combined diagnosis engine in order to improve the overall quality of diagnosis. Moreover, we present the different methods based on a running example of an autonomous mobile robot. Furthermore, we discuss the problems and research topics which arise from such a fusion of diverse methods. Finally, we explain how actively gathered observation are able to further improve the quality of diagnosis of complex systems.
KeywordsModel-based diagnosis Robustness Fault-tolerance Embedded systems
Unable to display preview. Download preview PDF.
- Steinbauer G. and Wotawa F., Detecting and locating faults in the control software of autonomous mobile robots. In 19th International Joint Conference on Artificial Intelligence (IJCAI-05), pp. 1742–1743 (2005).Google Scholar
- Köb D. and Wotawa F., Introducing alias information into model-based debugging. In Ramon Lopez de Mantaras and Lorenza Saitta, editors, Proceedings of the 16th Eureopean Conference on Artificial Intelligence, ECAI’2004, pp. 833–837 (2004). IOS Press.Google Scholar
- 5.Struss P. and Price C., Model-based systems in the automotive industry. AI Magazine, 24(4):17–34 (2004).Google Scholar
- Hamscher W., Console L., and de Kleer J., Readings in Model-Based Diagnosis. Morgan Kaufmann, San Mate. (1992).Google Scholar
- 9.Kalman R., A new approach to linear filtering and prediction problems. ASME Transactions, Journal of Basic Engineering, 82:35–50 (1960).Google Scholar
- Anderson B. and Moore J., Optimal Filtering. Information and System Sciences Series. Prentice Hall, Englewood Cliffs (1979).Google Scholar
- Chen J. and Patton R., Robust Model-Based Fault Diagnosis for Dynamic Systems. Kluwer, Dordrecht (1999).Google Scholar
- Dearden R. and Clancy D., Particle filters for real-time fault detection in planetary rovers. In Proceedings of the 13th International Workshop on Principles of Diagnosis, pages 1 – 6 (2002).Google Scholar
- Roos N., ten Teije A., Bos A., and Witteveen C., Multi-agent diagnosis with spatially distributed knowledge. In Proceedings of the Belgium-Netherlands Artificial Intelligence Conference (BNAIC), pp 275–282 (2002).Google Scholar
- de Kleer J., Getting the probabilities right for measurement selection. In 17th InternationalWorkshop on Principles of Diagnosis (DX-06), pp 141–146 (2006).Google Scholar
- 17.Hofbaur M., Hybrid Estimation of Complex Systems, volume 319 of Lecture Notes in Control and Information Sciences. Springer Verlag, New York (2005).Google Scholar
- 18.Drolet L., Michaud F., and Cote J., Adaptable sensor fusion using multiple kalman filters. In Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (2000).Google Scholar