SYSTEM AND METHOD FOR MACHINE LEARNING PROGNOSTICS AND HEALTH MANAGEMENTPHM BASED ON FEATURE VECTOR DATA OF ROLLING STOCK PARTS

摘要

Disclosed are a machine learning failure diagnosis system and method based on parts and operating environment feature vector information of a railway vehicle. According to the present invention, a failure diagnosis method of a vehicle comprises the steps of: generating part feature vector information by using state sensor information received from parts of a vehicle or state sensors installed on a track; generating operational feature vector information using environmental sensor information received from an environmental sensor installed in an operating section of the vehicle including the track and operating performance information of the vehicle; determining a priority for failure diagnosis of the part feature vector information and the operational feature vector information using a verification algorithm; setting a failure diagnosis environment of the parts of the vehicle by using the priority for failure diagnosis of the part feature vector information, the operational feature vector information, the part feature vector information, and the operational feature vector information; generating a training information set and a test information set using the part feature vector information and the operational feature vector information; and applying the training information set and the test information set to a machine learning model for failure diagnosis, and outputting a result of the diagnosis.