Gray fault diagnosis method based on LSA and SVM

In order to solve the application problems of gray relation theory and support vector machine in fault diagnosis, the paper introduces a new method, which combines latent semantic analysis with support vector machine. With latent semantic analysis realizing sample data feature extraction and dimensionality reduction to solve the training and diagnosing speed problem resulted from a number of high-dimensional sample data. And with principle of gray relation analysis to solve the classification problems which support vector machine can not achieve. Applying the method to fault diagnosis for a certain type of aircraft, the accuracy could reach to more than 94%,and the experimental results demonstrates the superiority of the presented method and its applied value.