In this chapter, a new and effective quaternion based machine condition monitoring system using log-polar mapper, quaternion based thermal image correlator and max-product fuzzy neural network classifier is discussed. Two classification characteristics namely: peak to sidelobe ratio (PSR) and real to complex ratio of the discrete quaternion correlation output (?-value) are applied in the quaternion based machine condition monitoring system. Large PSR and ?-value are observed in case of a good match among correlation of the input thermal image with a particular reference image, while small PSR and ?-value are observed in case of a bad/not match among correlation of the input thermal image with a particular reference image. Some simulation results show that log-polar mapping actually help solving rotation and scaling invariant problems in quaternion based thermal image correlation. Log-polar mapping can help in smoothing the output correlation plane, and hence it provides a better way for measuring PSR and ?-values. Results also show that quaternion based machine condition monitoring system is an efficient machine condition monitoring system with accuracy more than 98%.
Condition Monitoring of Railway Tracks from Car-Body Vibration Using a Machine Learning Technique