Artificial neural-net based dynamic security assessment for electric power systems

An adaptive pattern recognition approach based on highly parallel information processing using artificial neural networks is discussed. The high adaptability of these networks allows them to synthesize the complex mappings that carry the input attributes and features into the single-valued space of the critical fault clearing times. Appropriate input feature selection makes this approach a candidate for handling a topologically independent dynamic security assessment process.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>