IETM centered intelligent maintenance system integrating fuzzy semantic inference and data fusion

This paper presents a novel interactive electronic technical manual (IETM) centered intelligent maintenance system, which integrates diagnosis strategies of experience-based manual interpretation, rule-based fuzzy semantic inference and condition-based data fusion. Firstly, initial judgment is tried by onsite maintainer; otherwise rule-based fuzzy semantic inference is proposed on the designed IETM platform for rapid diagnosis using portable maintenance aid (PMA). For condition monitoring subsystems, signals can be collected and download to ground station via PMA for enhanced diagnosis using advanced classifiers and data fusion techniques. The combined diagnostic strategies are employed to trigger maintenance guidance and relevant works such as spare parts management etc. The proposed scheme was evaluated by two experiments of fault diagnosis for electric multiple units (EMU) trains. Experiment results show that intelligent, convenient, accurate and flexible diagnosis advantages can be obtained, which are benefit to maintenance reality.