基于多新息理论的PID神经网络改进算法

Improvement of PID Neural Network Based on Multi-innovation Algorithm

为了提高非线性动态系统辨识精度,提出一种基于多新息理论的PID神经网络改进算法。对具有时间延迟非线性动态系统,由于采用多新息,充分利用了系统的当前数据和历史数据,较传统的BP算法,本文所提算法在辨识精度和收敛速度方面具有更好的效果。仿真结果表明该算法的有效性。

In order to improve the identification accuracy of dynamic system, a improvement algorithm of PID neural network is proposed based on multi-innovation learning algorithm. For dynamic systems with time delay, the proposed method is very useful because the utilization of the current and past date of the system at the same time makes the presented multi-innovation theory more effective than the BP algorithm in view of accuracy and convergence rate. Simulation results showed that the algorithm is effect.