基于神经网络的卷烟共线分拣系统自适应控制

针对目前方法自适应控制卷烟共线系统时，由于未能依据Lyapunov函数确定系统的控制规律，导致在实施系统自适应控制时，存在控制效果差、控制误差高和控制性能低的问题，提出基于神经网络的卷烟共线分拣系统自适应控制方法。首先依据Lyapunov函数确定系统的控制规律，建立对象控制模型并使用前馈神经网络训练模型，优化控制器参数，完成控制器的设计；再利用控制器的参数建立线性和非线性2种自适应控制方法；最后通过制定的切换规则，完成自适应算法的平滑转换，实现系统的自适应控制。实验结果表明，运用该方法控制系统时，控制效果好、控制误差低以及控制性能高。

Adaptive Control of Cigarette Collinear Sorting System Based on Neural Network

When the current method adaptively controls the cigarette collinear system , the control law of the system cannot be determined because of no access to the Lyapunov function.Hence , the method has the problems of poor control effect , high control error and low control performance when implementing the system adaptive control.An adaptive control method of cigarette collinear sorting system based on neural network is proposed in response to the above problems.The method firstly determines the control law of the system according to the Lyapunov function , establishes the object control model , uses the feedforward neural network to train the model , optimizes the controller parameters , and completes the design of the controller.Then it uses the parameters of the controller to establish linear and nonlinear self-adaptive control methods.Finally , the smooth transition of the self-adaptive algorithm is completed through the formulated switching rules , and the self-adaptive control of the system is achieved.The experimental results show that when the method is used to control the system , the control effect is good , the control error is low , and the control performance is high.