Automatic classification and diagnostics of power system disturbance recordings

The aim is to automatic classification of the underlining causes of power system disturbances from a large amount of measurement data. This includes analysing and characterizing power system disturbances, searching for common phenomena behind each type of underlying causes, and give recommendations. With increasing usage of wind, solar and hydro power in smart grids, analysis the causes of disturbances become an essential task for improving
the power system. The project is collaboration with industries and power engineering experts.


The methods:
 
- Event segmentation in disturbance data;
 
- Analysis and characterization of disturbances: finding common features for each type of causes;
 
- Classification and diagnosis of underlying causes (e.g. using machine learning methods such as SVMs, expert Systems, and AdaBoost) 

- Allocation of disturbances, and giving recommendations.
 
Some examples are given as follows:

a) Finding common features/profiles of disturbances according to their underlying causes. 
 
b) Analyzing disturbance data by applying signal processing methods, e.g. time-frequency analysis, wavelets, STFT, sinusoidal model-based ESPRIT.
 
c) Classification of underlying causes of disturbances, using machine learning methods.


Main references:

1.M.H.J.Bollen, I.Y.H. Gu, Signal Processing of Power Quality Disturbances, John Wiley & Sons – IEEE Press, ISBN: 0-471-73168-4, 862 pages, August 2006.
 
2. Math H. J. Bollen, Irene Y. H. Gu, Surya Santoso, Mark F. McGranaghan, Peter A. Crossley, Mois´es V. Ribeiro, Paulo F. Ribeiro, ”BRIDGING THE GAP BETWEEN SIGNAL AND POWER: Assessing power system quality using signal processing techniques”, IEEE Signal Processing Magazine, pp.12-31, Vol. 26, No.4, July 2009.
 
Contact person: Prof. Irene YH Gu, irenegu@chalmers.se



Publicerad: må 11 nov 2019.