Data sorting device and method, and monitoring and diagnosis device

A non-transitory computer readable storage medium that stores instructions for

• training a learning network to diagnose anomalies in plant equipment, the instructions when executed by a processor cause the processor to execute a method, the method comprising:
• receiving operating data from sensors that monitor the plant equipment
• storing the operating data and a time when the operating data was collected by the sensors in a first database;
• forming filtered data by excluding abnormal values from the operating data;
• training an electric characteristics learning unit using a first subset of the filtered data to generate first weighting factors;
• training a vibratory characteristics learning unit using a second subset of the filtered data to generate second weighting factors;
• training a thermal characteristics learning unit using a third subset of the filtered data to generate third weighting factors;
• storing the first weighting factors, the second weighting factors and the third weighting factors in a second database;
• creating a model for nominal operation using the first weighting factors, the second weighting factors and the third weighting factors that are stored in the second database;
• receiving additional data from the sensors that monitor the plant equipment;
• and
• diagnosing the anomalies in the plant equipment by inputting the additional data into the model for nominal operated created.

A system for

• training a learning network to diagnose anomalies in plant equipment, comprising:
• sensors that monitor the plant equipment;
• an operating data database that stores operating data collected by the sensors and a time when the operating data was collected by the sensors
• a normal-value data database;
• and
• a computer that is communicatively coupled to the sensors, the operating data database and the normal-value data database, wherein the computer is configured to:
• retrieve the operating data from the operating data database,
• form filtered data by excluding abnormal values from the operating data,
• trains an electric characteristics learning unit using a first subset of the filtered data to generate first weighting factors,
• trains a vibratory characteristics learning unit using a second subset of the filtered data to generate second weighting factors,
• trains a thermal characteristics learning unit using a third subset of the filtered data to generate third weighting factors,
• stores the first weighting factors, the second weighting factors and the third weighting factors in the normal-value data database,
• creates a model for nominal operation using the first weighting factors, the second weighting factors and the third weighting factors that are stored in the normal-value data database;
• receives additional data from the sensors that monitor the plant equipment;
• and
• diagnose the anomalies in the plant equipment by inputting the additional data into the model for nominal operated created.