Genetic Integration of Different Diagnosis Methods and/or Fault Features for Improvement of Diagnosis Accuracy

Abstract

Genetic integration of different diagnosis methods and/or fault features is proposed in this paper for improvement of diagnosis accuracy, and a weighted matrix is established by integrating neural network and artificial immune diagnoses, wavelet packet energy, and bispectrum features using genetic algorithm for the diagnosis of a rotating machinery to prove the validity of this approach. Experimental results indicate that both diagnosis accuracy and robustness of diagnosis system can be improved by integrating different diagnosis methods and/or fault features. It is therefore concluded that integration of different diagnosis methods and/or fault features is one of the ways to achieve more accurate diagnosis of machinery.