---

Abstract- This paper uses data fusion based on fuzzy measure and fuzzy integral theory for stator winding inter-turn short circuit fault diagnosis in induction motors. Data fusion be considered in two level: feature level and decision level. Three-phase current signals of induction motor are used for fault diagnosis. Time-domain features are extracted from current signals, and a technique based on fuzzy density is proposed to choose appropriate features. The fuzzy c-mean analysis method is employed to classify different modes. It is used to choose the membership values of each feature for each fault mode. Finally, different features are fused at feature-level using Sugeno fuzzy integral data fusion and at decision-level using Choquet fuzzy integral data fusion to produce diagnostic results. Results show that fuzzy data fusion method performs very well for fault diagnosis in a 4hp laboratory induction motor.

Key words: Fuzzy integral; Data fusion; Fault diagnosis; Induction motor; Stator three-phase current.

---

Signal processing has a key role in signal based fault diagnosis in rotating machinery for finding beneficial discriminating features. Task of Signal processing is conversion of the raw data into beneficial features to facilitate the diagnostic operations. the features should be robust regarding noise and working condition of the machine and simultaneously sensitive to the machine defects. Therefore, assignment of more efficient analyzing techniques in order to achieve more beneficial features of the signal and faster and more accurate fault detection is taken into consideration by researchers. In order to finding such features, the current research applies at first wavelet packet denoising and then applies wavelet packet based Hilbert transform as well as improved Hilbert-Huang transform separately to decompose vibration signal into narrow frequency bands in order to extracting instantaneous frequencies. The findings show that the wavelet packet based Hilbert transform generates better results in comparison to the improved Hilbert-Huang transform in detecting frequencies of the broken rotor bar fault.

---

Fault propagation analysis is a method based on graph theory used to study the propagation of the effects of faults and disturbances in the system parts. The inclusion of fault propagation and interference of fault and disturbance effects in the design of fault detection algorithms increases reliability and reduces false alarms in critical equipment. In this paper the failure mode and effects analysis (FMEA) method was used to prepare a list of the possible faults and disturbances of each part of a system including of an induction motor and a centrifugal pump. Then a logical model is obtained through the fault propagation analysis to explain the connection between different parts of this system and the propagation of the electrical, vibrational and process effects. This model can be used to consider the propagation of the effects of faults and disturbances in system parts, and the interference of these effects and to select the appropriate effects or sensor configurations required for robust fault detection. The concept of this method is illustrated in this paper by applying this technique to an experimental system.