S Transform based Extreme Learning Machine for Power System Disturbances Classification

This paper presents an effective method based on extreme learning machine (ELM) for identification of power system disturbances. Learning time is an important factor while designing any computational intelligent algorithms for classifications. ELM is a single hidden layer neural network with good generalization capabilities and extremely fast learning capacity. An advanced signal-processing tool such as S transform is used to extract the distinctive features of the voltage signals. After feature extraction stage ELM is used to classify the power system disturbance waveforms and the performance of ELM is compared with the backpropagation neural network (BPN), probabilistic neural network (PNN), radial basis function neural network and support vector machines (SVM) with different kernel types. Ten types of disturbances are considered for the classification problem. The experimental results showed that the proposed algorithm is feasible and promising for real time applications.