Method of predicting plant data and apparatus using the same

An apparatus for predicting plant data, the apparatus comprising:

• a plant comprising an array of sensors and at least one of a power generation plant and a chemical manufacturing plant, each of the sensors generating measurement data of multiple tags obtained from measurements performed in the plant over time;
• and
• a processor configured to perform functions of:
• generating a plant prediction model based on k-nearest neighbors (k-NN) by modeling the plant based on the measurement data, the plant prediction model containing multiple data sets, each data set having a value for each tag of the multiple tags;
• and
• generating prediction data by measuring a similarity between the plant prediction model and the measurement data, determining a parameter k value based on the similarity, and generating plant normal state prediction data based on the determined parameter k value and the measured similarity,
• wherein the generating prediction data includes:
• determining similarity for each data set by measuring a similarity between each data set of the plant prediction model and the measurement data;
• determining a parameter k to be used in generating the prediction data, based on the determined similarity for each data set;
• and
• selecting k data sets in order of decreasing similarity based on the similarity for each data set and the determined parameter k, so that the prediction data is generated based on the selected k data sets.