Online Model-Based Condition Monitoring for Brushless Wound-Field Synchronous Generator to Detect and Diagnose Stator Windings Turn-to-Turn Shorts Using Extended Kalman Filter


In this paper, a model-primarily based approach is proposed to detect and diagnose stator winding fault in the Brushless wound-field synchronous generator (BWFSG). The extended Kalman filter is employed as a state and parameter estimation technique for the proposed model-primarily based approach. The mathematical model of the BWFSG with stator winding fault is developed and simplified for on-line implementation. An experimental check-rig is used to acquire the required inputs for the developed state estimation technique. The estimated rotor currents and fault parameter are analyzed to spot key signatures for condition monitoring (CM). The harmonic elements such as the second harmonic elements of the estimated field and damper currents, and the rms price of the estimated fault parameters are identified as appropriate signatures for winding fault and diagnose. Based mostly on the identified signatures, a model-based CM algorithm is proposed and validated in real time. The validation results confirmed that the proposed algorithm is in a position to detect and diagnose winding inter-flip short-circuit faults in real-time reliably.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Classification of Online Toxic Comments Using Machine Learning Algorithms ABSTRACT: Toxic comments are online remarks that are insulting, abusive, or inappropriate, and frequently cause other users to quit a
PROJECT TITLE : Reviewer Credibility and Sentiment Analysis Based User Profile Modelling for Online Product Recommendation ABSTRACT: Even for humans, deciphering user buying preferences, likes and dislikes is a difficult undertaking,
PROJECT TITLE : Active Learning From Imbalanced Data A Solution of Online Weighted Extreme Learning Machine ABSTRACT: Active learning is well known for its ability to improve the quality of a classification model while also reducing
PROJECT TITLE : Online ADMM-based Extreme Learning Machine for Sparse Supervised Learning ABSTRACT: In the field of machine learning, sparse learning is a useful strategy for selecting features and avoiding overfitting. An online
PROJECT TITLE : Online Subspace Learning from Gradient Orientations for Robust Image Alignment ABSTRACT: Robust and effective picture alignment remains a difficult task due to the size and complexity of images as well as fluctuations

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry