Research on Fault Diagnosis of Rotor based on Improved V-detector Algorithm

A rotor fault diagnosis method based on improved V-detector algorithm is proposed in this paper for improving the rotor fault diagnosis accuracy. Firstly, the V-detector algorithm is advanced to improve the detection accuracy of the algorithm by changing conditions of the rejecting and accepting hypothesis testing to reduce the generation of the invalid detectors, and it optimizes the generated detector set referring to the regulatory mechanism of immune system on immune cells; secondly, the entropy value of the signal is used as a feature vector and divided into different self-sample sets according to fault types, several detector sets are generated by using the improved V-detector algorithm; then classifier for identifying rotor fault is finally designed based on such sets. Simulation results show that the improved V-detector algorithm can produce fewer detectors, and the number of detectors will not be obviously increased when the estimated coverage is increased from 95% to 99%. This approach improves the fault identification accuracy compared with the traditional V-detector algorithm.