Details

Autor(en) / Beteiligte

• Shafi'i, M A
• Hamzah, N

Titel

Internal fault classification using Artificial Neural Network

Ist Teil von

• 2010 4th International Power Engineering and Optimization Conference (PEOCO), 2010, p.352-357

Ort / Verlag

IEEE

Erscheinungsjahr

2010

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• The main objective of this project is to create an intelligent model using image processing techniques in order to categorize the internal fault to four categories, which are low, intermediate, medium and high. Sample of internal fault location are captured using infrared thermography camera in which the RGB color image are stored and processed using Matlab. Processing involves impixelregion which includes creating a Pixel Region tool associated with the image displayed in the current figure, called the target image. This information is then being used to train a three layer Artificial Neural Network (ANN) using Levenberg Marquardt algorithm. A total of 168 samples are used as training whilst another 168 samples are used for testing. The optimized model is evaluated and validated through analysis of performance indicators frequently used in any classification model.