Adaptive Local Mean Decomposition and Multiscale-Fuzzy Entropy-Based Algorithms for the Detection of DC Series Arc Faults in PV Systems

DC series arc fault detection is essential for improving the productivity of photovoltaic (PV) stations. The also poses severe fire hazards to solar equipment and surrounding building. faults must be detected early provide reliable safe power delivery while preventing hazards. However, it challenging detect using conventional overcurrent current differential methods because these produce only minor variations. Furthermore, hard define their characteristics due randomness other arc-like transients. This paper focuses on investigating a novel method extract reliably detecting in PV systems. methodology first uses an adaptive local mean decomposition (ALMD) algorithm decompose samples into production functions (PFs) representing information from different frequency bands, then selects PFs that best characterize fault, calculates its multiscale fuzzy entropies (MFEs). Eventually, MFE values are inputted trained SVM identify accurately. proposed technique compared logistic regression naive Bayes terms several metrics assessing algorithms’ validity Arc data acquired arc-generating experiment platform utilized authenticate effectiveness feasibility method. experimental results indicated could efficiently classify normal less than 1 ms with accuracy rate 98.75%.