Research on Data Fusion for Diagnosing Types of Tribological Failures by Dampster-Shafer

The diesel engines model 8NVD48A 2u were monitored under running condition by spectrometric oil analysis, ferrographic monitoring, infrared spectrum analysis and oil quality testing. According to the results from the monitoring experiment, the types of worn parts and the relevant information descriptors are summarized. The worn parts are mainly subject to scoring, seizure and corrosion between piston (or piston ring) and cylinder liner; scratching, seizure, spalling and corrosion in gear; pitting, seizure and fatigue in gear. Based on the experiences and rules of some experts, the basic probability assignment for Dampster Shafer is given, and the applicability of different oil monitoring for different wear types is also discussed. The analysis and calculation show that data fusion is useful for information process in oil monitoring.