"Interval Type-2 Fuzzy Logic Rule based Data mining for Steam Turbine Fault Analysis of a Power System Rotatory Machine Component"
Neelam Sahu, Manoj Kumar Jha, Mohammad Farukh Qureshi · 2014
Fuzzy decision tree or Soft Decision Tree (SDT) classifier using interval type-2 fuzzy logic rule based data mining for steam turbine fault analysis of a power system rotatory machine component is used not only for database analyses, but also for machine learning. The classification rules are based on standardized vibration frequency data for steam turbines and field experts’ analyses of turbine vibration problems. The system can identify twenty types of standard steam turbine faults. The system was developed using 1500 simulated data sets. The data mining methods were then used to identify 20 explicit rules for the turbine faults. The results indicate that the fuzzy decision tree classifier using interval type-2 fuzzy logic rule based data mining can be effectively applied to diagnosis of rotating machinery by giving useful rules to interpret the data. The data mining and analysis was implemented between the fault information dimensions table and the relationship rule dimensions table. We made sure the causes of the fault and chose the priority solution for troubleshooting by generating candidates sets and filtering the candidate set and matching the fault. Fuzzy decision trees called soft decision trees (SDT) combines tree growing and pruning, to determine the structure of the soft decision tree, with refitting and back fitting, to improve its generalization capabilities. Moreover, a global model variance study shows a much lower variance for soft decision trees than for standard trees as a direct cause of the improved accuracy.