Abstract: A technique involves outputting not only the condition of hydraulic oil but also information on failure prediction of equipment by processing in real time. Such a technique utilizes an oil condition sensor attached to the equipment, a parameter calculator that calculates the values of a plurality of parameters indicating the state of the hydraulic oil based on the sensor output of the oil condition sensor and correlation information between the sensor output and the values of a plurality of parameters indicating the state of the hydraulic oil, and failure prediction determiner that predicts equipment failures based on parameter values and identifies and outputs parameters that are inferred as the cause of the failure prediction, and outputs not only the condition of hydraulic oil but also information on failure prediction of the equipment by processing in real time.

Abstract: The present invention improves accuracy in machine learning and reduce running costs by updating to a new learning model generated by selecting data, etc. The data collector collects data to perform machine learning. The data storage stores the collected data. The data selector selects data for updating existing learning models used for machine learning from the data stored in the data storage. The learning model generator generates a new learning model by machine learning based on the selected data, and the updater updates at least the existing learning model to the new learning model generated in the learning model generator.