Root cause fault diagnostic reasoning is critical for ensuring the safety and reliability of airborne systems, where timely and accurate fault isolation can significantly reduce downtime and maintenance costs. However, the inherent complexity of fault propagation within airborne systems makes root cause fault diagnostic reasoning difficult. To address this challenge, an integrated framework that systematically combines a formal ontology model with rule-based reasoning is proposed in this paper. The ontology model is established to represent structural and functional knowledge of the system. Furthermore, explicit causal semantics are introduced into the ontology model to encode fault-related knowledge. Building upon the ontology model, a set of semantic web rule language (SWRL) rules is established to perform causal deduction from fault symptoms to root cause faults. The effectiveness of the proposed framework is validated through case studies on a communication receiver subsystem. Comparative analysis against a baseline ontology model, which is constructed via a direct and structural mapping of the failure mode and effects analysis (FMEA) table, demonstrates the superior diagnostic reasoning precision of the proposed framework. This advantage is most evident in complex scenarios involving multiple potential fault propagation paths, where the baseline ontology model can only generate a list of fault candidates due to its lack of explicit causal reasoning. By enabling more accurate and interpretable localization of root cause faults, this ontology-driven diagnostic reasoning framework not only enhances diagnostic reasoning accuracy but also contributes to the development of more intelligent and maintainable airborne systems.
She et al. (Tue,) studied this question.