METHOD AND APPARATUS FOR DIAGNOSING FAULT BASED ON PROBABILISTIC DENSITY

摘要

The present invention relates to a method and an apparatus for diagnosing a fault based on a probability density. According to an embodiment of the present invention, the method for diagnosing a fault based on a probability density comprises the steps of: generating a learning feature vector by extracting learning features dividing each defect from a previously obtained learning signal for each defect; learning the generated learning feature vectors in a probability density-based classifier; generating input feature vectors by extracting input features dividing each defect from an input signal which is a classification target; inputting the generated input feature vectors to the learned probability density-based classifier, and calculating a classification probability on the input feature vectors and a distance probability density function of each class on the learning feature vectors so as to calculate a defect classification resu and diagnosing a fault state through the calculated defect classification result.