Part of #A PracticalWork for Fault Classification of Electromotor of SAR-2 Hydraulic Pump by an Intelligent Combined Method Based on Data Mining and Fuzzy Logic# :
Publishing year : 2010
Conference : Sixth National Conference on Maintenance and Repair
Number of pages : 15
Abstract: Vibration techniques in a machine-state monitoring program provides useful, reliable information, bringing significant cost benefits to industry. The main purpose of this research is to explore the intelligent way to classify three common faults versus healthy state of electromotor. Vibration signal by FFT technique went to frequency domain. Then the features are extracted by using the statistical features that reduced the data. The improved distance assessment (IDE) technique was used to select the significant features from the entire feature set. The J48 algorithm as a decision tree generated fuzzy rules. The structure of the FIS classifier was then defined based on crisp sets. Results showed that total classification accuracy was about 88%. This work demonstrates that the combined J48-FIS model has the potential for fault diagnosis of an electromotor.