The engine health monitoring system has been generally applied to the aircraft system to improve reliability and durability of the aircraft propulsion system and to minimize its operational cost. The helicopter flies at low altitude level flight mode in its own operational range comparing to other aircraft categories. The low level flight means that the engine operates at variable atmospheric condition such as hot and cold temperature, snow, heavy rain, etc. Furthermore, it may increase the possibility of foreign object ingestion, such as sand, dust, etc., i.e. this operating condition gives rise to damages of engine gas path components. Because types and severities of most helicopter engine faults are very complicate, the conventional model based fault diagnostic approach like the GPA (Gas Path Analysis) method is not adequate to monitor such a complex engine fault condition. An on-line diagnostic program was developed by using SIMULINK, where measurement signals were simulated by an input module. This study proposes a neural network algorithm for calculating variation of mass flow and efficiency in each engine component from measuring data. The neural network was trained by damages at each component such as compressor, compressor turbine or power turbine. The used database for training the neural network was obtained from simulation under various flight conditions. Reliability and capability of the developed on-line diagnostics program were evaluated through application to a helicopter engine health monitoring.

This content is only available via PDF.
You do not currently have access to this content.