Detection and classification of faults from helicopter vibration data using recently developed signal processing and neural network techniques

The feasibility of using nontraditional methods of helicopter transmission fault classification is studied. Various signal processing and classifier techniques are investigated. All algorithms successfully classified the fault samples from a tail rotor transmission dataset. A hardware neural network system was designed and implemented. The relatively low resolution of the neural network circuitry required extensive preprocessing and scaling of the large dynamic range input signal. Results from the hardware system were similar to those achieved in simulation. It is pointed out that a true test of the techniques presented may require a dataset that is statistically richer