Proportional Integral Synchronization Control for Coupled Neural Networks: A Coding‐Decoding Scheme

ABSTRACT The synchronization control problem of coupled neural networks based on a proportional‐integral observer is addressed in this paper. Since the state vector of each node may not be measured directly, a proportional‐integral observer is established to estimate the state information of the plant, thus improving the design method of the observer. In addition, considering the limited communication bandwidth, the coding‐decoding scheme is adopted to relieve the bandwidth pressure and improve transmission efficiency effectively. The decoding state obtained by the coding‐decoding scheme is used as the basis for the designed controller, and it is deduced how the upper bounds of the coding‐decoding scheme parameters relate to the exponential ultimate boundedness of the synchronization error system. Finally, an example is offered to demonstrate the validity of the proposed method.