Identification of transient overvoltage using discrete wavelet transform with minimised border distortion effect and support vector machine

The existing border distortion effect at signal edges can produce inaccurate detection of transient signals when deploying signal processing method. Therefore, there is a need to develop a technique to minimise this border distortion effect through the use of Discrete Wavelet Transform (DWT). In this study, the extension mode has been proposed to minimise border distortion effect. DWT based on one-cycle window technique is used to extract the features of transient disturbances signal. The disturbances contain imprecision of data and provide insuffi-cient information, thereby leading to the failure of the conventional method to identify any power quality (PQ) problems. Thus, the detection and classification method using Support Vector Machine (SVM) is deployed to acquire reliable and accurate classification technique. The novel approached of one-cycle sliding window with the association of extension mode are validated through the SVM classification. From the results obtained, the performance of absolute reconstructed signal after threshold technique shows that smooth padding is the most effective extension mode to reduce the border distortion effect using one-cycle sliding window. Overall, the SVM classification performance based on one-versus-one (OVO) coding design can detect transient and non-transient events subsequent to undergoing all subsequent processes.