Fault diagnosis model research based on support vector regression and principal components analysis

To overcome the deficiencies of low accuracy and high false alarm rate in fault diagnosis system, a new optimization method for f the fault diagnosis model is proposed based on support vector regression (SVR) and principal components analysis. Utilizing the character that principal components analysis algorithm can keep the discernability of original dataset after reduction, the reduces of the original dataset are calculated and used to train individual SVR classifier for ensemble, which increase the diversity between individual classifiers, and consequently, increase the detection accuracy. To validate the effectiveness of the proposed method, simulation experiments are performed based on the electronic circuit dataset. The results show that the proposed method is a promised ensemble method owning to its high diversity, high detection accuracy and faster speed in fault diagnosis.