The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Due to the difficulty in describing the nonlinear characteristic of Francis turbine, this paper takes advantage of the powerful nonlinear approximate ability of the feed forward neural network to put up the Francis turbine neural network model (FTNNM) and the neural network identification model (NNIM) for the nonlinear Francis hydroturbine generator set (TGS) including FTNNM. The neural network model...
A direct adaptive control design method is proposed for a class of uncertain single-input single-output (SISO) nonaffine system. It is a difficult problem to be dealt with in the control literature, mainly because that the virtual controls and the final control law of uncertain nonaffine system is not easy to resolve. To overcome this difficulty, the fuzzy-neural approximator cancels the unknown part...
In order to solve the increasingly serious network congestion, a node closed loop PID control mechanism is proposed, which is based on BP neural network (abbr. BPNN). This mechanism works with active queue management (abbr. AQM) scheme with probability drop strategy, which forms a closed loop by controlling node buffer average queue size. The method tries to avoid the disadvantages of the traditional...
A neural adaptive inverse compensator design method was proposed for a class of nonlinear systems with input unmodeled dynamics based on RBF neural networks. The compensator was designed using two neural networks, one to estimate the input unmodeled dynamics and another to provide adaptive inverse compensation to the input unmodeled dynamics. The method relaxes some rigorous demands to unmodeled dynamics...
Generalized PID neural network (GPIDNN) has recently received more attention in industry application. To investigate the control of long time-delay systems with GPIDNN control system, both the structure and the algorithm were presented in this paper, the real-time simulation to a main steam temperature control system was also carried out. The results show that GPIDNN is less sensitive to variation...
For nonlinear friction force in hydraulic position tracking system, partition compensation is employed to solve the problem of large approximation error caused by non-smooth characteristic of friction when the friction is compensated globally by fuzzy neural network (FNN). The experimental results show that the partition compensation algorithm is effective in compensating the nonlinearity, and the...
A neural network control algorithm based on predictive control is proposed to control time-delay chaotic systems. When the time-delay chaotic model is unknown, the control system stabilizes a chaotic orbit onto an unstable fixed point without using the knowledge of the location of the unstable fixed point and the local linearized dynamics at the point. The control system includes a watcher, an online...
An adaptive neural network control strategy based on fuzzy self-tuning is presented. The strategy is applied to the control system for drum water level of coal-fired power plant. Fuzzy inference engine (FIE) is used to train neural network online. The control strategy possesses feedforward compensation ability for steam flow disturbance by introducing the steam flow signal to neural network controller...
A novel approach of nonlinear model predictive control (NMPC) is proposed using radial basis function neural network (RBFNN) and particle swarm optimization (PSO). A multi-step predictive model of the controlled process based on RBFNN is studied. The fuzzy c-mean (FCM) clustering algorithm was used to determine the position of centers of the hidden layer of RBFNN. A modified PSO with simulated annealing...
In this paper, a systematic guideline is introduced to design a stable adaptive fuzzy wavelet controller with sliding mode for a class of uncertain nonlinear systems. Based on the Lyapunov synthesis approach, we construct the fuzzy wavelet controller such that it can basically control and guarantee the stability of the whole control system. On the other hand, a robust controller is designed to restrain...
A robust adaptive neural network (NN) control scheme is proposed for a class of nonlinear systems with unknown control gain functions and unmodeled dynamics. The proposed design method expands the class of nonlinear systems for which adaptive neural network control approaches have been studied. By a special design scheme, the controller singularity problem is avoided. The developed NN control scheme...
The paper investigates the adaptive neural network control design for a class of nonlinear systems with input nonlinearity using Lyapunov's stability theory. Based on the principle of sliding mode control and the approximation capability of multilayer neural networks (MNNs), a novel sliding mode neural network control strategy with supervisory controller is developed. With the help of a supervisory...
This paper presents the compliance control of a robot manipulator under a constrained environment. The controller design proposed herein is based on the intelligence adaptive control scheme. In this design, the DFNNs (dynamic fuzzy neural networks) and PD feedback controllers control the position and the contact force of robot end-effector. The DFNNs controller is employed to compensate for environmental...
This paper presents the design, development of dynamic load simulator based on dynamic fuzzy neural networks (D-FNNs) controller. Dynamic load simulator (DLS) can reproduce desired load torque acting on loaded object to test its performance and stability. In DLS, the redundancy torque caused by the motion of loaded object has a very poor effect on the loading accuracy. So a simplified dynamic model...
The diagonal recurrent neural networks (DRNN) is a powerful computational tools that have been used extensively in the areas of pattern recognition, systems modeling and identification. This paper proposes a self-tuning PID decoupling control based on DRNN neural networks for solving the time-varying coupling nonlinear control problems. The approach can on-line identify the controlled plant using...
Using a batch learning scheme and a hybrid learning rule, i.e. BP algorithm is applied to the learning of premise parameters, while least square algorithm to the learning of consequent parameters, an ANFIS system for ship autopilot with two inputs and one output, three fuzzy zones, nine fuzzy rules is trained. Training data come from a PD course control system, then the trained ANFIS autopilot controls...
Classical methods for designing a controller depend on the accuracy of system model. However, plant's models and other parts in a physical system can not accurately represent all possible dynamics. Thus the controller designed is usually not the optimal one. In this article, a new, simple adaptive control method, which combines the classical frequency domain method with the neural network theory,...
The paper designs a new AQM algorithm called ANPID, which applies the theory of adaptive linear neuron to AQM controller in congestion control. ANPID can adjust the queue length to the desired value, revise its weights online by LMS learning rule, and tune the coefficients of PID controller. The weighted factors are regulated continuously according to the system errors, as well as eliminate the sensitivity...
Radial basis function (RBF) neural network (NN) is powerful computational tools, which have been used extensively in the areas of pattern recognition, systems modeling and identification due to the advantages of simple construction, adaptability and robustness. This paper presents a novel approach of single neuron PID model reference adaptive control (MRAC) control based on RBF neural network on-line...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.