AUTONOMOUS NEURAL CONTROL IN FLEXIBLE SPACE STRUCTURES

The present paper proposes the use of a hybrid connectionist system as a learning controller with reconfiguration capability. Embedded with adjustable time-delays, an adaptive radial basis function network offe rs an effective modeling technique to capture most of the spatiotempor al interactions among the structure members. A fuzzy-based fault diagn osis system is applied for health monitoring to provide the neural con troller with various failure scenarios. Associative memory is incorpor ated to compensate for catastrophic changes of structural parameters b y providing a continuous solution space of acceptable controller confi gurations. This paper addresses the theoretical foundation of architec ture and demonstrates its applicability via specific examples.