Fractal image compression for classification of PD sources

The fractal image compression technique has a unique feature due to which physical position of blocks/regions in the input image can be extracted directly from the compressed data. Applying this technique, φ-q-n partial discharge (PD) patterns (treated as an image) are compressed and stored as affine transformations. These transformations then are used directly to extract the embedded pattern features, which are classified by a neural network. The novel route to PD pattern classification described in this paper thus addresses both the tasks of compression and feature extraction in a single step. The task of compression is essential to store and handle large quantities of pattern data acquired, especially during on-line monitoring of PD in power apparatus. Results presented illustrate that this approach can address satisfactorily the tasks of compression and classification of PD patterns