This paper presents a modification to the Kandadai and Tien’s learning algorithm for tuning a fuzzy-neural controller that is able to automatically generate a knowledge base. Tuning is based on reinforcements from a ...
详细信息
This paper presents a modification to the Kandadai and Tien’s learning algorithm for tuning a fuzzy-neural controller that is able to automatically generate a knowledge base. Tuning is based on reinforcements from a dynamical system, thus giving a pseudosupervised learning scheme using error backpropagation. Originally, a weak reinforcement in the form of a binary failure signal was assumed which proved to be insufficient in terms of steady-state error. Therefore, a continuous reinforcement signal is applied enabling the system to correct the error as well as decreasing the overall control effort in the learning phase.
The majority of nonlinear models based on neural networks are of the black-box structure. A nonlinear system can be nonlinear in many different ways, thus the nonlinear black-box model structure must be very flexible....
详细信息
The majority of nonlinear models based on neural networks are of the black-box structure. A nonlinear system can be nonlinear in many different ways, thus the nonlinear black-box model structure must be very flexible. This means that it must have many parameters. A model offering many parameters usually creates problems, and the variance contribution to the error might be high. For a particular identification problem, only a subset of the parameters may be necessary, and the main topic in nonlinear system identification is how to select a model structure that describes the system dynamics with the minimum number of parameters. This paper discusses nonlinear input-output models that are suitable for implementation of feedforward neural networks. The proposed model structures were tested and compared using the identification procedure of a pH process. The results indicated that a simplest model structure can satisfactorily represent the investigated process.
Modeling of nonlinear systems is implemented using a partial linear modeling (PLM) technique, which separates the linear and nonlinear part of the model. The linear part of the model is in the form of an ARX model, wh...
详细信息
Modeling of nonlinear systems is implemented using a partial linear modeling (PLM) technique, which separates the linear and nonlinear part of the model. The linear part of the model is in the form of an ARX model, while the nonlinear part is in the form of NNARX model using an RBF neural network. For the RBF neural network, the centers of the network are chosen using an orthogonal least squares (OLS) method. The linear part of the model is constructed to fit and absorb as much as possible the dynamic of the system, while its residuals are fitted using the nonlinear part of the model. The model is tested on experimental data of a MIMO spark ignition (SI) engine system. The plant (SI engine) is handled as a two-inputs, two-outputs process, the two inputs are the ignition timing and the throttle angle, the two outputs are the engine speed and manifold pressure. Different order and nonlinear terms of model are tested on the input-output data to obtain a valid model. Finally, second order with three nonlinear terms of model is found as a fairly accurate model. Model validation is treated using different sets of input-output data which indicates that the resulting model is fairly valid. A feedback linearization method is used for controlling the nonlinear system where the model is constructed using the PLM technique. The smooth transition of the controller output shows that the combination of the modeling and control technique has real potential for real-time implementation.
The article concerns with AC induction motor closed loop direct vector control design. It includes design and program realisation of PI controllers for currents, flux, torque and speed. The system consists of two-pole...
详细信息
The article concerns with AC induction motor closed loop direct vector control design. It includes design and program realisation of PI controllers for currents, flux, torque and speed. The system consists of two-pole 1.1 kW motor, IGBT inverter. DSP processor ADSP2101 on ADSP2101 EZ-LAB board and coprocessor ADMC201 on ADMC200-EVAL board. The switching frequency of the inverter is 3 kHz. The both the rotor position for the vector Park-Clark transformations and the rotor speed for the speed control are obtained from an optical encoder of 1024 pulses per evolve.
Present trends in education are dominated by the shift from the traditional teacher-centred to the learner-centred approaches. Needs of new target groups, together with the development of the multimedia and ICT lead t...
详细信息
Present trends in education are dominated by the shift from the traditional teacher-centred to the learner-centred approaches. Needs of new target groups, together with the development of the multimedia and ICT lead to radical changes in the learning environment and to necessity of the new learning organization. This paper is reporting about experience in developing such a new environment at the Department of automation and control, FEI STU in Bratislava, in cooperation with the Local Centre of Distance Education.
Fuzzy control belongs towards recently often-used control algorithms. The fuzzy controller can work like a classical feedback controller or like a superior control system that can choose some control algorithm in depe...
详细信息
Fuzzy control belongs towards recently often-used control algorithms. The fuzzy controller can work like a classical feedback controller or like a superior control system that can choose some control algorithm in dependence on the working point of the controlled system. The combination of these two possibilities was chosen in our case because our main aim was design of the fuzzy controller for an inverted pendulum. This paper describes the fuzzy control foundations, control structure tuning with a Takagi-Sugeno fuzzy controller and a case study - an inverted pendulum control.
The paper deals with the parameter identification of Wiener systems having two-segment polynomial nonlinearities. Application of a simple decomposition technique provides a special form of Wiener model that is linear-...
详细信息
The paper deals with the parameter identification of Wiener systems having two-segment polynomial nonlinearities. Application of a simple decomposition technique provides a special form of Wiener model that is linear-in-parameters. This allows simultaneous estimation of all the model parameters. To demonstrate the feasibility of the identification method, more illustrative examples are included and analyzed.
The contribution is oriented to the area of automatic control of the amorph bands reeling. The bands are produced by the technology of fast cooling. The process of bands production runs at velocities approx. 30 m/s. I...
详细信息
The contribution is oriented to the area of automatic control of the amorph bands reeling. The bands are produced by the technology of fast cooling. The process of bands production runs at velocities approx. 30 m/s. In the article there is presented the original method to capture the band beginning into the special reeling device that is automatically controlled. This method is patented by the author. The problem is in extremely difficult control of the abducting forces in the variable structure system with variable parameters.
In this paper, we present the theoretical development to stabilize a class of uncertain time-delay system and its application to model-following systems. The system under consideration is described in state space mode...
详细信息
ISBN:
(纸本)078039805X
In this paper, we present the theoretical development to stabilize a class of uncertain time-delay system and its application to model-following systems. The system under consideration is described in state space model containing state delay, uncertain parameters and disturbance. The main idea is to reduce the state of system into an equivalent one, by employing generalized transformation, which is easier to analyze its behavior and stability. Then, the min-max approach is employed to find the stabilizing control law. After that, a class of model-following system is introduced for controlling the error between the model and process. With the extended theorem, the suitable control law that guarantees model tracking is derived. Finally, two numerical simulations are illustrated to show the algorithm for applying the proposed theorems and the effectiveness of the designed control law in stabilizing the controlled systems.
Sufficient and necessary conditions for nonlinear impulsive systems considering linear constraints with bounded additive disturbances are obtained from a characterization of positive invariance properties for these sy...
详细信息
Sufficient and necessary conditions for nonlinear impulsive systems considering linear constraints with bounded additive disturbances are obtained from a characterization of positive invariance properties for these systems. As the application of results obtained, the sufficient conditions for discrete state feedback control and for asymptotic stabilization of the linear uncertain systems with the state positively asymmetrical invariant set are presented. Finally, a numerical example is given.
暂无评论