On the base of the Fourier neural networks, this paper adopted dichotomy to search the neural networks' optimization structure and optimization learning rate. Given the variational ranges of the Fourier neural net...
详细信息
On the base of the Fourier neural networks, this paper adopted dichotomy to search the neural networks' optimization structure and optimization learning rate. Given the variational ranges of the Fourier neural networks' structure and learning rate, on the condition of arbitrary nonlinear mapping relationship, arbitrary error request and arbitrary training sample number, this algorithm can adjust the fourier neural networks' structure and learning rate automatically to the optimization structure and the optimization learning rate. The simulation results showed that the convergence speed of the fourier neural networks can be greatly improved if the fourier neural networks adopt the optimization structure and the optimization learning rate.
The model-free PID control method with fuzzy neuron gain scheduling is proposed for turning processes in this paper. In order to enhance the control system stability and adaptability to the plants with nonlinearities ...
详细信息
ISBN:
(纸本)0780379527
The model-free PID control method with fuzzy neuron gain scheduling is proposed for turning processes in this paper. In order to enhance the control system stability and adaptability to the plants with nonlinearities and uncertainties, the model-free PID controller is designed to keep the cutting force to be constant by changing the controller gain on-line when a cutting tool cuts at various cutting depth or the spindle operates in different speeds. In this control system, the PID controller is used to control the turning process, the neuron is applied to tune the PID controller gain, and a fuzzy scheme is set up to change the neuron gain. With the two examples of different turning processes, the experiments of using the proposed control method are made. The simulation results show the good performance of the model-free PID controller.
The neuron PID double-layer control system is set up and the double-layer control method is proposed for control system with uncertainties in this paper. In this control system, a conventional PID controller is used i...
详细信息
ISBN:
(纸本)0780378652
The neuron PID double-layer control system is set up and the double-layer control method is proposed for control system with uncertainties in this paper. In this control system, a conventional PID controller is used in the insider layer control loop, and the neuron model-free controller is used in the outsider layer control loop. As a result of utilizing the double layer control structure, the PID control parameters can be selected imprecisely and the control system dynamics can be improved efficiently. The application of the proposed control method to the liquid level control of a tower of the fluid catalytic cracking unit (FCCU) is described. The excellent performance obtained in practice shows that the new control method has powerful vitality in industrialcontrol.
According to the neuron model and its learning strategy in [Wang Ning et al., 1991], the intelligent control method based on two neurons is presented in this paper. In this control system, the two neurons are used to ...
详细信息
ISBN:
(纸本)0780378652
According to the neuron model and its learning strategy in [Wang Ning et al., 1991], the intelligent control method based on two neurons is presented in this paper. In this control system, the two neurons are used to structure the compound controller. One neuron acts as a feed-forward and PD controller, the other neuron acts as a PI controller. With an example of basis weight control, the simulation tests are made to demonstrate the effectiveness of the proposed controller in handing plants with uncertainties.
The nonlinear neuron control method is proposed for a direct drive robot in this paper. In this control system, the neuron controller and the relay controller are designed in parallel connection to form the model-free...
详细信息
ISBN:
(纸本)0780379527
The nonlinear neuron control method is proposed for a direct drive robot in this paper. In this control system, the neuron controller and the relay controller are designed in parallel connection to form the model-free controller to control a direct drive robot with uncertainties. A fuzzy scheme is used to tune the relay controller gain on line. With an example of a direct drive robot manipulator, the experiments are made. The simulation results demonstrate that the proposed method can efficiently control the independent joint of the direct drive robot. This model-free controller has excellent performance, strong robustness and adaptability.
This paper proposed a new state feedback controller synthesis method for solving forbidden states avoidance problems. The method can be used when all influentially uncontrollable subnets have normalized cascade struct...
详细信息
ISBN:
(纸本)0780379241
This paper proposed a new state feedback controller synthesis method for solving forbidden states avoidance problems. The method can be used when all influentially uncontrollable subnets have normalized cascade structures, which differ from marked graph, state machine as well as forward and backward conflict-free structure. Two advantages of the method are shown as follows: 1) It is suitable for a class of controlled discrete event plants modeled by generalized Petri nets; 2) The online computation of maximally permissive control law can be carried out within polynomial times.
This paper proposes a new control synthesis method for a class of discrete event systems modeled by controlled ordinary Petri nets with linear marking constraint. Monitor is constructed to track the system state resul...
详细信息
This paper presents a sliding mode (SM) based identifier to deal with the parameter identification problem for a class of parameter uncertain nonlinear dynamic systems with input nonlinearity. A sliding mode controlle...
详细信息
This paper presents a sliding mode (SM) based identifier to deal with the parameter identification problem for a class of parameter uncertain nonlinear dynamic systems with input nonlinearity. A sliding mode controller (SMC) is used to ensure the global reaching condition of the sliding mode for the nonlinear system; an identifier is designed to identify the uncertain parameter of the nonlinear system. A numerical example is studied to show the feasibility of the SM controller and the asymptotical convergence of the identifier.
A model-free control method for nonlinear plants is proposed. According to the neuron model and learning strategy in Wang et al. (1991), the neural network model is structured and the learning algorithm is also presen...
详细信息
ISBN:
(纸本)0780375084
A model-free control method for nonlinear plants is proposed. According to the neuron model and learning strategy in Wang et al. (1991), the neural network model is structured and the learning algorithm is also presented. Based on the neural network, the model-free controller is designed. In an example of control of a pH process, the simulation results show that the proposed control method can control a nonlinear plant efficiently.
This paper proposes a new control synthesis method for a class of discrete event systems modeled by controlled ordinary Petri nets with linear marking constraint. Monitor is constructed to track the system state resul...
详细信息
This paper proposes a new control synthesis method for a class of discrete event systems modeled by controlled ordinary Petri nets with linear marking constraint. Monitor is constructed to track the system state resulted from the uncontrollable firing sequences. The maximally permissive feedback control policy then can be obtained based on the making of the monitor. No non-convex constraint transformation is introduced in the design procedure. The method is capable of synthesizing a class of net that cannot be treated using previous methods due to some necessary restrictions.
暂无评论