Rotating Machinery Fault Diagnosis Based on Fuzzy Data Fusion Techniques

Various diagnostics methods have been applied to machinery condition monitoring and fault diagnosis, with far from satisfactory levels of accuracy. With the development of modern multi-sensor based data acquisition technology often used in advanced signal processing, more and more information is becoming available for the purposes of fault diagnostics and prognostics of machinery integrity. It is recognized that multi-parameter data fusion approach to diagnostics can produce more accurate results. Fuzzy measures have the ability to represent the importance and interactions among different criteria. This paper presents an effective fuzzy measure and fuzzy integral data fusion approach for machinery fault diagnosis. Feature level and decision level data fusion models were developed for machinery fault diagnosis. Rolling element bearing and electrical motor experiments were conducted to validate the models. Different features were obtained from recorded signals and then fused at both feature and decision levels using fuzzy measure and fuzzy integral data fusion methods to produce the diagnostics results. The results show that the proposed approach performs very well for bearing and motor fault diagnosis.