Vibration diagnostic system of rotating machinery using self-organizing feature map and wavelet transform

This paper describes a signal recognition method for diagnosing the rotating machinery using the wavelet-aided Self-Organizing Feature Map(SOFM). The SOFM specialized from the neural network is a new and effective algorithm used for interpreting large and complex data sets. It converts high-dimensional data to a low dimension with simple relationships. Additionally the Learning Vector Quantization(LVQ) is used for reducing the error from SOFM. The multi-resolution and wavelet transform are used to extract salient features from the primary vibration signals. Since it decomposes raw time-waveform signals into two respective parts in the time space and frequency domain, it does not lose either information unlike Fourier transform does. This paper is focused on the development of an advanced signal classifier in order to automatize the vibration signal pattern recognition. This method is verified by the experiment and several abnormal vibrations such as due to unbalance and rubbing are classified with high flexibility and reliability by the proposed method.