Data mining is used to select relevant data from a large amount of data. Here the connections and dependencies between different process values are recognized and used for further classification. When classifying the selected data, results are linked and states are automatically recognized and named by the user. Statistical models are generated from this analysed data. These models can then be used for optimization in the plantThis can be done both with historical data and with real-time data.
In addition to the existing KPI, data mining and classification functions, SmartSCADA also provides a generic interface to "R", which allows data from the SCADA system to be processed directly using statistical methods. "R" is a free programming language for statistical data analysis.