Malfunction diagnosis in industrial process systems using data mining for knowledge discovery

The determination of abnormal behavior at process industries gains increasing interest as strict regulations and highly competitive operation conditions are regularly applied at the process systems. A synergetic approach in exploring the behavior of industrial processes is proposed, targeting at the discovery of patterns and implement fault detection (malfunction) diagnosis. The patterns are based on highly correlated time series. The concept is based on the fact that if independent time series are combined based on rules, we can extract scenarios of functional and non-functional situations so as to monitor hazardous procedures occurring in workplaces. The selected methods combine and apply actions on historically stored, experimental data from a chemical pilot plant, located at CERTH/CPERI. The implementation of the clustering and classification methods showed promising results of determining with great accuracy (97%) the potential abnormal situations.