Bispectral and trispectral features for machine condition diagnosis

The application of bispectral and trispectral analysis in condition monitor ing is discussed. Higher-order spectral analysis of machine vibrations for the provision of diagnostic features is investigated. Experimental work is based on vibration data collected from a small test rig subjected to bearin g faults. The direct use of the entire bispectrum or trispectrum to provide diagnostic features is investigated using a variety of classification algo rithms including neural networks, and this is compared with simpler power s pectral and statistical feature extraction algorithms. A more detailed inve stigation of the higher-order spectral structure of the signals is then und ertaken. This provides features which can be estimated more easily in pract ice and could provide diagnostic information about the machines.