Adaptive neural predictive control strategies for general nonlinear systems are proposed. The network weight update rule with discrete-time learning procedures which executes the minimal error between the feedforward ...
详细信息
Adaptive neural predictive control strategies for general nonlinear systems are proposed. The network weight update rule with discrete-time learning procedures which executes the minimal error between the feedforward neural network (FNN) model output and plant output is obtained. The one-step-ahead neural predictive control combined with the 'dual' optimization algorithm serves as a rapid, reliable adaptation mechanism and guarantees the stable output regulation of a class of uncertain nonlinear systems. In principle, the off-line training algorithm on neural networks is reduced, and the state/parameter estimation design is obviated. Through closed-loop simulation demonstrations, the proposed control schemes have been successfully applied to two reactor system examples.
In this paper, an adaptive cerebellar-model articulation computer (CMAC) neural network (NN) control system is developed for a linear piezoelectric ceramic motor (LPCM) that is driven by an LLCC-resonant inverter. The...
详细信息
In this paper, an adaptive cerebellar-model articulation computer (CMAC) neural network (NN) control system is developed for a linear piezoelectric ceramic motor (LPCM) that is driven by an LLCC-resonant inverter. The motor structure and LLCC-resonant driving circuit of an LPCM are introduced initially. The LLCC-resonant driving circuit is designed to operate at an optimal switching frequency such that the output voltage will not be influenced by the variation of quality factor. Since the dynamic characteristics and, motor parameters of the LPCM are highly nonlinear and time varying, an adaptive CMAC NN control system is designed without mathematical dynamic model to control the position of the moving table of the LPCM drive system to achieve high-precision position control with robustness. In the proposed control scheme, the dynamic backpropagation algorithm is adopted to train the CMAC NN online. Moreover, to guarantee the convergence of output tracking error for periodic commands tracking, analytical methods based on a discrete-type Lyapunov function are utilized to determine the optimal learning-rate parameters of the CMAC NN. The effectiveness of the proposed driving circuit and control system is verified by experimental results in the presence of uncertainties, and the advantages of the proposed control system are indicated in comparison with a traditional integral-proportional position control system. Accurate tracking response and superior dynamic performance can be obtained due to the powerful online learning capability of the CMAC NN with optimal learning-rate parameters.
Whilst the necessity of finding an intelligent-based controlling method for a two-leg walking robot increases, the balance of the under-actuated leg consisting of two links is emphasized in this study. This is not onl...
详细信息
Whilst the necessity of finding an intelligent-based controlling method for a two-leg walking robot increases, the balance of the under-actuated leg consisting of two links is emphasized in this study. This is not only a nonlinear structure, but also a single-input double-output system. However, the problem becomes concrete through the proposed diagonal recurrent neural networks (DRNN) method. In this paper, two kinds of DRNN are introduced into the control system. The diagonal recurrent neuroidentifier (DRNI) is selected as an identifier, and the diagonal recurrent neurocontroller (DRNC) is determined as a controller. Additionally, a generalized dynamic backpropagation algorithm (DBP) is also applied to train both DRNC and DRNI. With the simulated results, it is shown that the under-actuated leg is balanced and stabilized by DRNN. This study definitely contributes the intelligent-based as well as the real-time controlled method for a two-leg walking robot with profound insight.
In this paper, adaptive neural-network predictive control strategies for general nonlinear systems are presented. The system is described by an unknown NARMAX model and neuro model is used to on-line learn the system....
详细信息
In this paper, adaptive neural-network predictive control strategies for general nonlinear systems are presented. The system is described by an unknown NARMAX model and neuro model is used to on-line learn the system. Despite state/parameter estimation, the neural predictive control scheme associated with the constrained optimization framework is implemented in a straightforward manner. Through the Lyapunov stability analysis, the network weight adaptation rule is derived, and guarantees the minimum error between the neuro output and plant output. An unstable reactor system is given to demonstrate the effectiveness of the proposed control schemes.
By using neural networks and multivariable decoupling control theory, the idea of model reference inverse dynamic control was applied in the boiler-turbine system. Four neural networks are used as an approximating mod...
详细信息
By using neural networks and multivariable decoupling control theory, the idea of model reference inverse dynamic control was applied in the boiler-turbine system. Four neural networks are used as an approximating model of the unknown nonlinear dynamic behavior of the boiler-turbine while another neural networks are decoupling and controller. Neural network controllers are trained by using dynamic backpropagation algorithm. Simulation shows the developed design method for the boiler-turbine control system can simultaneously control load megawatt and throttle pressure and has good adaptive ability
A new type of recurrent neural network is discussed, which provides the potential for modelling unknown nonlinear systems. The proposed network is a generalization of the network described by Elman, which has three la...
详细信息
A new type of recurrent neural network is discussed, which provides the potential for modelling unknown nonlinear systems. The proposed network is a generalization of the network described by Elman, which has three layers including the input layer, the hidden layer and the output layer. The input layer is composed of two different groups of neurons, the group of external input neurons and the group of the internal context neurons. Since arbitrary connections can be allowed from the hidden layer to the context layer, the modified Elman network has more memory space to represent dynamic systems than the Elman network. In addition, it is proved that the proposed network with appropriate neurons in the context layer can approximate the trajectory of a given dynamical system for any fixed finite length of time. The dynamic backpropagation algorithm is used to estimate the weights of both the feedforward and feedback connections. The methods have been successfully applied to the modelling of nonlinear plants.
Robust control of a permanent magnet (PM) linear synchronous motor (LSM) servodrive is achieved by using a disturbance observer and a recurrent neural network (RNN) compensator. An integral-proportional (TP) controlle...
详细信息
Robust control of a permanent magnet (PM) linear synchronous motor (LSM) servodrive is achieved by using a disturbance observer and a recurrent neural network (RNN) compensator. An integral-proportional (TP) controller is introduced to control the mover position of the LSM. The IP position controller is designed according to the estimated mover parameters to match the time-domain command tracking specifications. A disturbance observer is implemented and the observed disturbance force is fed forward to increase the robustness of the LSM servodrive. Moreover, to increase the control performance of the LSM servodrive under the occurrence of large disturbance, a RNN compensator is proposed to reduce the influence of parameter variations and external disturbances of the LSM servodrive system as a force controller. In addition, a dynamic backpropagation algorithm is developed to train the RNN online using the delta adaptation law. The effectiveness of the proposed control schemes is demonstrated by some simulated and experimental results.
The conventional dynamicbackpropagation (DBP) algorithm proposed by Pineda does not necessarily imply the stability of the dynamic neural model in the sense of Lyapunov during a dynamic weight learning process. A dif...
详细信息
The conventional dynamicbackpropagation (DBP) algorithm proposed by Pineda does not necessarily imply the stability of the dynamic neural model in the sense of Lyapunov during a dynamic weight learning process. A difficulty with the DBP learning process is thus associated with the stability of the equilibrium points which have to be checked by simulating the set of dynamic equations, or else by verifying the stability conditions, after the learning has been completed. To avoid unstable phenomenon during the learning process, two new learning schemes, called the multiplier and constrained learning rate algorithms, are proposed in this paper to provide stable adaptive updating processes for both the synaptic and somatic parameters of the network. Based on the explicit stability conditions, in the multiplier method these conditions are introduced into the iterative error index, and the new updating formulations contain a set of inequality constraints. In the constrained learning rate algorithm, the learning rate is updated at each iterative instant by an equation derived using the stability conditions, With these stable DBP algorithms, any analog target pattern may be implemented by a steady output vector which is a nonlinear vector function of the stable equilibrium point. The applicability of the approaches presented is illustrated through both analog and binary pattern storage examples.
暂无评论