Fault diagnosis analysis with support vector regression and particle swarm optimization algorithm

The fault diagnosis model with support vector regression (SVR) and particle swarm optimization algorithm (POSA) for is proposed. The novel structure model has higher accuracy and faster convergence speed. We construct the network structure, and give the algorithm flow. The impact factor of fault behaviors is discussed. With the ability of strong self-learning and faster convergence, this fault detection method can detect various fault behaviors rapidly and effectively by learning the typical fault characteristic information. Utilizing the character that principal components analysis algorithm can keep the discern ability of original dataset after reduction, the reduces of the original dataset are calculated and used to train individual SVR for ensemble, 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 method owning to its high diversity, high detection accuracy and faster speed in fault diagnosis.