In this paper we propose a neurocontroller (NC) for suppression of load swing with disturbance in a crane system rotating around the vertical axis. As in a nonholonomic system, the classical control method using a static continuous state feedback law cannot stabilize the load swing. It is necessary to design a time-varying feedback controller or a discontinuous feedback controller. Previous research had been successful in constructing the suppression controller of the load swing with a single initial rotation angle when disturbance occurred. In this paper, the performance of the NC optimized by genetic algorithm will be examined with three initial rotation angles.