Abstract: A method for generating an abnormal state detection model, that includes: receiving first and second normal state signals detected, for a predetermined time by first and second sensors, respectively; generating a normal state data set based on the first and the second normal state signals; recognizing first and second variable values; generating a first abnormal state signal by applying the first variable value to an impulse function and a second abnormal state signal by applying the second variable value to a Gaussian distribution function; generating an abnormal state data set based on the first and second abnormal state signals; generating a detection model learning set for generating an abnormal state detection model by combining the normal state data set and the abnormal state data set; and generating an abnormal state detection model based on the detection model learning set.

Abstract: Disclosed are a facility failure prediction system and method using an acoustic signal of the ultrasonic band. The facility failure prediction system using an ultrasonic band according to the present disclosure includes a detection sensor located adjacent to a facility, and a server configured to determine whether sampling data extracted from an acoustic signal is a normal signal or an abnormal signal to generate a plurality of labeling information, to analyze sampling data corresponding to abnormal signal labeling information determined as an abnormal signal to generate abnormal signal analysis information, and to analyze a pattern of normal signal labeling information determined as the normal signal among the plurality of labeling information and the abnormal signal analysis information to provide failure prediction information for the facility.