An application research of virtual meter on gear fault detection

The signal analysis and processing module, signal features extraction module and the fault diagnosis module were developed with graphic program language LABVIEW. The signal feature extraction was realized by the wavelet packet decomposition. The fault diagnosis was completed by the neural network. The features of frequency segment energy of the gear vibration signal picked up by the wavelet packet decomposition were used as the input vector of the neural network. The neural network was trained with the gear typical faults vibration signal acquired by imitation fault testing platform. Following that, the neural network trained was used to diagnose gear fault. The result indicates the effectiveness of the intelligent diagnosis system for gear faults. Virtual technology was effectively used on fault diagnosis.