Automated function generation of symptom parameters and application to fault diagnosis of machinery under variable operating conditions

Dimensional or nondimensional symptom parameters are usually used for condition monitoring of plant machinery. However, it is difficult to extract most important symptom parameters and functions of those parameters by which faults of machinery can be sensitively detected and fault types can be precisely distinguished. In order to overcome this difficulty and ensure highly accurate fault diagnosis, a new method called "automated function generation of symptom parameters" using genetic algorithms (GA) is presented here. By applying the method to real machinery diagnoses problems, it has been shown that the key symptom parameter function can be quickly generated. In this paper, we give a diagnosis example of rolling bearing of which operating conditions are variable in rotating speed and load.