论文部分内容阅读
针对多变量的生物发酵系统,为提高神经网络逆解耦控制性能,提出一种基于神经网络逆解耦的自适应补偿控制方法。首先,基于逆系统理论构造神经网络近似被控系统的逆系统,并将神经网络逆系统与被控系统串联构成伪线性复合系统;然后,对解耦后的伪线性复合系统设计自适应补偿控制器,实现系统的跟踪控制;最后,基于Lyapunov稳定性理论设计控制器参数的自适应律,保证了控制系统的稳定性。将提出的控制方法应用于生物发酵过程的菌丝浓度、基质浓度的解耦控制,数值仿真结果表明,所提出的控制方法较能有效提高普通的神经网络逆系统解耦控制性能。
In order to improve the inverse decoupling control performance of neural networks for multivariable biological fermentation system, an adaptive compensation control method based on inverse decoupling of neural networks is proposed. First, the inverse system based on inverse system theory is constructed to approximate the inverse system of the controlled system, and the inverse system of the neural network and the controlled system are connected in series to form the pseudo-linear system. Then, the adaptive compensation control is designed for the decoupled pseudo-linear system Finally, based on the Lyapunov stability theory, the adaptive law of controller parameters is designed to ensure the stability of the control system. The proposed control method is applied to the decay control of mycelial concentration and matrix concentration in biological fermentation process. The numerical simulation results show that the proposed control method can effectively improve the performance of the conventional inverse neural network inverse system.