Diagnostic inference algorithm for radio engineering devices based on a semantic knowledge base

A reproducible diagnostic inference algorithm for radio engineering devices based on a semantic knowledge base is proposed. Heterogeneous measurements are converted to a common scale based on the distance from the normative value to the explicitly defined critical boundary; all normalization scales and the complete sign matrix of "symptom – fault" relationships have been published for the computational scenario. The basic assessment takes into account confirming and refuting indicators, and a separate criticality rule prevents the suppression of a single physically significant symptom by the sum of less important relationships. In the amplification path scenario, a frequency deviation of 14 kHz with a norm of no more than 5 kHz activated the priority check of the generator node; this is followed by the amplification stage, filter or matching circuits, antenna-feeder path and power supply circuits. The proposed approach provides an interpretable ranking of diagnostic hypotheses and prioritization of engineering checks. Sensitivity analysis with a factor of refuting signs from 0.2 to 0.6 preserved the basic order of non-priority hypotheses, and a change in the control context changed the activation and the final order. The calculations are compared with the unweighted direct correspondence rule. The obtained results confirm the reproducibility of the computational procedure, but they do not replace bench or operational validation.

1. Isermann R. Model-based fault-detection and diagnosis – status and applications. Annual Reviews in Control. 2005;29(1):71–85. https://doi.org/10.1016/j.arcontrol.2004.12.002

2. Gao Zh., Cecati C., Ding S.X. A survey of fault diagnosis and fault-tolerant techniques – Part I: fault diagnosis with model-based and signal-based approaches. IEEE Transactions on Industrial Electronics. 2015;62(6):3757–3767. https://doi.org/10.1109/TIE.2015.2417501

3. Venkatasubramanian V., Rengaswamy R., Yin K., Kavuri S.N. A review of process fault detection and diagnosis. Part I: quantitative model-based methods. Computers & Chemical Engineering. 2003;27(3):293–311. https://doi.org/10.1016/S0098-1354(02)00160-6

4. Venkatasubramanian V., Rengaswamy R., Kavuri S.N. A review of process fault detection and diagnosis. Part II: qualitative models and search strategies. Computers & Chemical Engineering. 2003;27(3):313–326. https://doi.org/10.1016/S0098-1354(02)00161-8

5. Giarratano J.C., Riley G.D. Expert Systems: Principles and Programming. Boston: Course Technology; 2005. 842 p.

6. Buchanan B.G., Shortliffe E.H. Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project. Reading: Addison-Wesley; 1984. 748 p.

7. Reiter R. A theory of diagnosis from first principles. Artificial Intelligence. 1987;32(1):57–95. https://doi.org/10.1016/0004-3702(87)90062-2

8. De Kleer J., Mackworth A.K., Reiter R. Characterizing diagnoses and systems. Artificial Intelligence. 1992;56(2–3):197–222. https://doi.org/10.1016/0004-3702(92)90027-U

9. Blanke M., Kinnaert M., Lunze J., Staroswiecki M. Diagnosis and Fault-Tolerant Control. Berlin: Springer; 2016. 695 p.

10. Isermann R. Fault-Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance. Berlin: Springer; 2006. 475 p.

11. Hogan A., Blomqvist E., Cochez M., et al. Knowledge Graphs. ACM Computing Surveys. 2021;54(4):71. https://doi.org/10.1145/3447772

12. Ji Sh., Pan Sh., Cambria E., Marttinen P., Yu Ph.S. A survey on knowledge graphs: representation, acquisition, and applications. IEEE Transactions on Neural Networks and Learning Systems. 2022;33(2):494–514. https://doi.org/10.1109/TNNLS.2021.3070843

13. Huang X., Yang Ch., Zhang Y., Lou S., Kong L., Zhou H. Ontology guided multi-level knowledge graph construction and its applications in blast furnace ironmaking process. Advanced Engineering Informatics. 2024;62:102927. https://doi.org/10.1016/j.aei.2024.102927

14. Brahmbhatt P., Patel R., Maheshwari A., Gudi R.D. Improved fault detection and diagnosis using graph auto encoder and attention-based graph convolution networks. Digital Chemical Engineering. 2024;11(4):100158. https://doi.org/10.1016/j.dche.2024.100158

15. Ding Y., Li H., Zhu F., Wang Zh., Peng W., Xie M. A semi-supervised failure knowledge graph construction method for decision support in operations and maintenance. IEEE Transactions on Industrial Informatics. 2024;20(3):3104–3114. https://doi.org/10.1109/TII.2023.3299078

16. Liu P., Qian L., Zhao X., Tao B. Joint knowledge graph and large language model for fault diagnosis and its application in aviation assembly. IEEE Transactions on Industrial Informatics. 2024;20(6):8160–8169. https://doi.org/10.1109/TII.2024.3366977

17. Klein P., Malburg L., Bergmann R. Combining informed data-driven anomaly detection with knowledge graphs for root cause analysis in predictive maintenance. Engineering Applications of Artificial Intelligence. 2025;145(1):110152. https://doi.org/10.1016/j.engappai.2025.110152