Transient Analysis to Distinguish Mechanically Switched Capacitors Using Discrete Wavelet Transform and Artificial Intelligence

Capacitor banks are widely used in modern power systems for reactive power compensation and voltage regulation. However, switching operations of mechanically switched capacitors (MSCs) can generate transient phenomena, such as inrush currents, which may resemble fault currents and lead to misoperation of protection systems. Therefore, accurate detection and classification of transient events are essential for reliable system operation. This study proposes a hybrid approach for transient signal analysis and classification by integrating the discrete wavelet transform (DWT) with artificial intelligence (AI) techniques, including probabilistic neural networks and fuzzy inference systems (FIS). The DWT performs time–frequency analysis to extract multi-scale wavelet features from three-phase current signals. The proposed method enables both discrimination between inrush and fault currents and multi-class classification of transient events among six capacitor switching conditions, namely base case, pre-insertion resistor, pre-insertion inductor, current limiting reactor, 6% reactor, and synchronous closing. The methodology is validated using PSCAD/EMTDC simulations under isolated and back-to-back capacitor switching scenarios. The results demonstrate that the proposed DWT–AI approach achieves high classification accuracy exceeding 95%, outperforming conventional methods based on DWT alone and DWT combined with FIS. Furthermore, the proposed method improves protection system performance by reducing false tripping caused by transient inrush currents, while maintaining reliable fault detection capability. The findings confirm that integrating time–frequency signal processing with AI-based classification provides an effective and practical solution for transient event discrimination in MSC capacitor bank systems.