OUT-OF-STEP DETECTION BASED ON PATTERN-RECOGNITION

This paper presents a new approach for out-of-step detection of synchr onous generators with the ability to initiate early tripping for non-r ecoverable swings while avoiding tripping on recoverable swings. The a pproach is based on the K-means clustering pattern recognition techniq ue. The capabilities of the developed algorithm are tested through com puter simulation for a typical case study. While being feasible for on -line implementation, the introduced algorithm shows high classificati on performance.