Application of Signal Processing Tools and Artificial Neural Network in Diagnosis of Power System Faults

Download or read book Application of Signal Processing Tools and Artificial Neural Network in Diagnosis of Power System Faults written by Nabamita Banerjee Roy and published by . This book was released on 2021-07-21 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Accurate, fast, and reliable fault classification techniques are an important operational requirement in modern-day power transmission systems. Application of Signal Processing Tools and Neural Network in Diagnosis of Power System Faults examines power system faults and conventional techniques of fault analysis. The authors provide insight into artificial neural networks and their applications, with illustrations, for identifying power system faults. Wavelet transform and its application are discussed as well as an elaborate method of Stockwell transform. The authors also employ probabilistic neural networks (PNN) and back propagation neural networks (BPNN) to identify the different types of faults and determine their corresponding locations, respectively. Both PNN and BPNN are presented in detail, and their applications are illustrated through simple programming in MATLAB®. Furthermore, their applications in fault diagnosis are discussed through multiple case studies. FEATURES Explores methods of fault identification through programming and simulation in MATLAB® Examines signal processing tools and their applications with examples Provides knowledge of artificial neural networks and their application with illustrations Uses PNN and BPNN to identify the different types of faults and obtain their corresponding locations Discusses the programming of signal processing using wavelet transform and Stockwell transform This book is designed for engineering students and for practitioners. Readers will find methods of programming and simulation of any network in MATLAB® as well as ways to extract features from a signal waveform by using a suitable signal processing toolbox and by application of artificial neural networks.