摘要 |
As a result of being provided with the following, this abnormality predictor diagnosis system makes it possible to diagnose whether an abnormality predictor is present in mechanical equipment: a sensor data acquisition means that acquires sensor data; a learning means that identifies a value detected by the sensor at a time at which a predetermined length of time had elapsed after an operation process began, that uses a predetermined function for chronologically outputting values differing from each other over time in order to identify the value at the time at which the predetermined length of time had elapsed after the operation process began, and that learns a normal model for a waveform on the basis of the identified value detected by the sensor and the values of the function; and a diagnosis means that diagnoses whether an abnormality predictor is present in mechanical equipment on the basis of comparison of the normal model with the value detected by the sensor at the time at which the predetermined length of time had elapsed after the operation process began and the values of the function in a chronological waveform of sensor data to be diagnosed. |