Wavelet scattering and multiclass support vector machine (WS_MSVM) for effective fault classification in transformers: a real-time experimental approach

Abstract

Abstract The dependable operation of the protective system is affected by residual magnetism and magnetic bias during the activation of the transformer. Challenges arise in distinguishing between inrush current and fault current when the transformer circuit breaker switching angle and remnant flux attain specific values. This situation can lead to a lack of sensitivity or failure in the operation of the transformer protection system. Thus, this paper proposes an effective approach for classifying different faults in transformers (internal and non-internal faults) using wavelet scattering and multiclass support vector machine (MSVM) technique (WS_MSVM). The wavelet scattering method begins by transmitting the data through a sequence of wavelet transforms, nonlinear operations, and averaging processes. This series of operations aims to generate low-variance representations of time series data. Wavelet time scattering produces signal representations that remain unaffected by shifts in the input signal, while still preserving the ability to distinguish between internal and non-internal faults. Internal faults are those occurring within the zones of the current transformer (CT) connected on both sides of the transformer. On the other hand, non-internal faults consist of magnetizing inrush current, sympathetic inrush current, and external faults (faults occurring outside the CT zones). The efficacy of the proposed WS_SVM is evaluated on the real-time experimental results obtained from the differential path of a laboratory transformer. The experimental data generated over one power frequency cycle under diverse operating conditions is employed in MATLAB to assess the effectiveness of the proposed WS_SVM algorithm.