A genetic algorithm for construction of recognizers of anomalies in behaviour of dynamical systems

In this paper, the problem of automatic construction of recognizers of anomalies in behaviour of complicated dynamical systems is considered. Information about system behaviour is available in a form of multidimensional trajectories (time-series) obtained from sensors surrounding the system. A specific feature of the problem consists in the fact that, depending on the individual properties of the system and conditions of its operation, trajectories that contain anomalies may significantly differ from each other in amplitude and length. The genetic algorithm described here allows to construct recognizers of abnormal behaviour of complicated dynamical systems.