Approach to the knowledge base validation of intelligent systems in industrial equipment diagnostics
https://doi.org/10.46973/0201-727X_2023_3_18
Abstract
The paper considers the efficiency of decision making in industrial equipment diagnosis, an approach to the knowledge base validation (KBV) containing mixed production rules (MPRs) of intelligent equipment diagnosis systems. The classification of structural errors in the KBV with their definition and representation in the form of a directed graph, as well as recommendations for their elimination, is proposed. This approach will reduce the KBV size, which will make the search process more efficient and simplify the organization of output control. It is given the screen parts forms of the developed software system for automatic search using the structural errors in the KBV. The software system will provide to remove unnecessary rules without losing useful information.
About the Authors
A. E. Kolodenkova
Samara State Technical University
Russian Federation
Russian Federation
Anna E. Kolodenkova - Chair «Information Technology», Doctor of Engineering Sciences, Associated Professor, Head of the Chair.
S. S. Vereshchagina
Samara State Technical University
Russian Federation
Russian Federation
Svetlana S. Vereshchagina - Chair «Information Technology», Candidate of Engineering Sciences, Associate Professor.
References
1. Ogheneovo, E. E. Knowledge representation in artificial intelligence and expert systems using inference rule / E. E. Ogheneovo, P. A. Nlerum // Int. J. Sci. Eng. Res. – 2020. – Vol. 4. – P. 1886–1900.
2. Yurin, A. Y. Personal knowledge base designer: Software for expert systems prototyping / A. Y. Yurin, N. O. Dorodnykh // SoftwareX. – 2020. – Vol. 11. – P. 1–6.
3. Rybina, G. V. Verification of knowledge bases in integrated expert systems / G. V. Rybina, V. V. Smirnov // Artificial Intelligence News. – 2005. – No. 3. – P. 7–19. – ISSN 1682-8917.
4. Dolinina, O. Formal Models of the Structural Errors in the Knowledge Bases of Intellectual Decision Making Systems / O. Dolinina, N. Suchkova // Computer Science On-line Conference. – 2017. – P. 156–167.
5. QOS of data networks analyzing based on the fuzzy knowledge base / L. Globa, Z. Savchuk, O. Vasylenko, E. Siemens // International Conference Infocommunications–Present and Future. – 2020. – P. 130–149.
6. Cao, Q. Using rule quality measures for rule base refinement in knowledge-based predictive maintenance systems / Q. Cao, C. Zanni-Merk, A. Samet, F.D.B de Beuvron, C. Reich // Cybernetics and Systems. – 2020. – Vol. 2. – P. 161–176.
7. Rybina, G. V. Methods and algorithms of knowledge base verification in integrated expert systems / G. V. Rybina, V. V. Smirnov // Izvestiya RAS. Theory and control systems. – 2007. – No. 4. – P. 91–102. – ISSN 1029-3620.
8. Harmelen, F. Applying rule-base anomalies to KADS inference structures / F. Harmelen // Decision Support Systems. – 1998. – Vol. 21. – P. 41–46.
9. Pira, E Verification of confliction and unreachability in rule-based expert systems with model checking / E. Pira, M. Miralvand, F. Soltani // International Journal of Artificial Intelligence. – 2014. – Vol. 2. – P. 1–7.
10. Vanthienen, J. Experiences with Modeling and Verification of Regulations / J. Vanthienen, C. Mues, S. Goedertier // REMO2V'06. – 2006. – P. 793–799.
11. Kolodenkova, А. Е. Integrated approach to processing diagnostic data based on heterogeneous cognitive models / A. E. Kolodenkova, S. S. Vereshchagina, V. E. Vereshchagin // Moscow Workshop on Electronic and Networking Technologies. – 2020. – P. 1–5.
12. Kolodenkova, А. Е. Verification of mixed production rules correctness in intelligent systems for diagnosing industrial equipment / A. E. Kolodenkova, S. S. Vereshchagina, V. O. Tuvaeva // Smart Innovation, Systems and Technologies. – 2022. – Vol. 272. – P. 363–370.
13. Simiński, R. Circularity in rule knowledge bases detection using decision unit approach / R. Simiński, A. Wakulicz-Deja // Monitoring, Security, and Rescue Techniques in Multiagent Systems. – 2005. – P. 273–279.
14. Diagnostics of the technical condition of industrial equipment based on a system of hierarchical production rules / A. E. Kolodenkova, S. S. Vereshchagina, V. O. Tuvaeva, A. N. Guda // Lecture Notes in Networks and Systems. – 2022. – Vol. 330 LNNS. – P. 180–187.
15. Katasev, A. Neurofuzzy model of fuzzy rules formation for object condition assessment under uncertainty conditions / A. Katasev // Computer research and modeling. 2019. – Vol. 11. –No. 3. – P. 477–492. – ISSN 2077-6853.
16. Angelov, P. Evolving fuzzy-rule-based classifiers from data streams / P. Angelov, X. Zhou // IEEE Transactions on Fuzzy Systems. – 2008. – Vol. 16. – P. 1462–1475.
17. Kolodenkova, А. Е. System of mixed production rules for diagnosing the technical condition of asynchronous electric motors / A. E. Kolodenkova, S. S. Vereshchagina // Certificate of registration of a computer program No. 2023616943, 04.04.2023. – EDN HZUGDJ.
Review
For citations:
Kolodenkova A.E., Vereshchagina S.S. Approach to the knowledge base validation of intelligent systems in industrial equipment diagnostics. Vestnik Rostovskogo Gosudarstvennogo Universiteta Putej Soobshcheniya. 2023;(3):18-27. (In Russ.) https://doi.org/10.46973/0201-727X_2023_3_18
Views:
11
JATS XML
Email this article 