Information Environment for Neural-Network Adaptive Control System

The computer architecture for the neural-network control system with a synchronous peripheral subsystem allows transmitting information about the state of the control object and its environment with maximum accuracy. Synchronization between executive resources eliminates restrictions on the interaction between the components of complex control objects. This problem used to be able to be solved only by breaking the problem into slightly dependent smaller tasks. The proposed model is a coherent information environment for neural-network control system, with simultaneous record mode of the object state parameters. This mode is important for the control systems objects with unidentified degrees of freedom – typical field of applications of neural systems. The proposed model of the synchronous information environment is necessary even the control system is implemented with a fixed algorithm.