Current transformer saturation detection with genetically optimized neural networks

Application of the genetic algorithm (GA) for optimization of artificial neural network (ANN) based CT saturation detector is presented. To determine the most suitable ANN topology for the CT state classifier the rules of evolutionary improvement of the characteristics of individuals by concurrence and heredity are used. The proposed genetic optimization principles were implemented in MATLAB programming code. The initial as well as further consecutive network populations were created, trained and graded in a closed loop until the selection criterion was fulfilled. Various aspects of genetic optimization have been studied, including ANN quality assessment, versions of genetic operations etc. The developed optimized neural CT saturation detector has been tested with EMTP-ATP generated signals, proving better performance than traditionally used algorithms and methods.