Due to the complexity of neural networks the problem of large computation requirements on computational devices where the network is trained or evaluated and slow network evaluation/training response can appear. The p...
详细信息
Due to the complexity of neural networks the problem of large computation requirements on computational devices where the network is trained or evaluated and slow network evaluation/training response can appear. The problem is more evident when networks are compared to the conventional algorithms that run with low response time. In general this problem is being solved using by more powerful computational device or parallel systems. This paper deals with a neural network optimized for run on the real time control system to obtain real time responses comparable to the conventional algorithms. Special effort is made for solving of the problem of optimal network structure with reflection to preserve or aproove original network qualities (approximation and generalization capability).
The paper proposes an original frequency domain approach to decentralized controller design for performance applied within a robust design strategy. The novelty of the proposed approach consists in assessing the influ...
详细信息
New developments in computer networks and communications provide new possibilities for control purposes. controlsystems for highly complex plants are themselves very complex and heterogeneous. A new software infrastr...
详细信息
Two novel linear matrix inequality (LMI) - based procedures to receive stabilizing robust output feedback gain are presented, one of them being modification of previous results of (Oliveira et al., 1999). The proposed...
详细信息
Two novel linear matrix inequality (LMI) - based procedures to receive stabilizing robust output feedback gain are presented, one of them being modification of previous results of (Oliveira et al., 1999). The proposed robust control law stabilizes the respective uncertain discrete-time system described by polytopic model with guaranteed cost. The obtained results are compared with other LMI results from literature and illustrated on the example.
The paper addresses the problem of robust output feedback controller design with a guaranteed cost and quadratic, and parameter dependent Lyapunov function quadratic stability for linear continuous time affine systems...
详细信息
The paper addresses the problem of robust output feedback controller design with a guaranteed cost and quadratic, and parameter dependent Lyapunov function quadratic stability for linear continuous time affine systems. The proposed design methods lead to a non-iterative LMI based algorithm. Numerical examples are given to illustrate the design procedure.
This paper focuses upon the diagnosis of an assembling/dissembling robot, using analytical methods based on observers. The paper presents a modality of detecting incidents, using the mathematical model of the robot, w...
详细信息
This paper focuses upon the diagnosis of an assembling/dissembling robot, using analytical methods based on observers. The paper presents a modality of detecting incidents, using the mathematical model of the robot, which is based upon the analytical evaluation of the residue with adaptive limits.
GO-CAD brings some novel functions and features to the intelligent building design and virtual reality simulation. This paper presents a novel methodology simulation during lighting simulation of a building to acquire...
详细信息
GO-CAD brings some novel functions and features to the intelligent building design and virtual reality simulation. This paper presents a novel methodology simulation during lighting simulation of a building to acquire data about the mutual interaction between a human - a virtual reality visitor represented by the so-called “avatar”, and a 3D building model and distance designing via Internet performed by a distributed multi-professional team. To demonstrate possibilities of the GO-CAD based modelling in the virtual reality, a lighting model has been chosen.
This paper presents an attractive artificial neural network (ANN) architecture with novel type of activation functions based on orthonormal function for modelling and control of non-linear processes. Theoretical metho...
详细信息
This paper presents an attractive artificial neural network (ANN) architecture with novel type of activation functions based on orthonormal function for modelling and control of non-linear processes. Theoretical methodology and design of algorithm for modelling and self-tuning control of uncertain non-linear complex processes is proposed. Several types of orthonormal functions (Fourier, Legendre, Laguerre and Chebychev) for non-linear process modelling and control are analysed and compared. Simulation results are provided to illustrate high performance of artificial neural networks with the orthonormal activation functions (OAFN) in practical problem solutions . The obtained results are compared and potential shortcomings of the proposed methods for real time industry control are discussed and analysed.
The paper addresses the problem of robust output feedback controller design with a guaranteed cost and parameter dependent Lyapunov function quadratic stability for linear continuous time polytopic systems. The propos...
详细信息
The paper addresses the problem of robust output feedback controller design with a guaranteed cost and parameter dependent Lyapunov function quadratic stability for linear continuous time polytopic systems. The proposed design methods lead to a non-iterative LMI based algorithm. Numerical example is given to illustrate the design procedure.
This paper dealt with modelling and control of non-linear dynamic processes by artifiacal neural network with orthogonal and wavelet activation functions. Wavelet decomposition is employed to explore the characteristi...
详细信息
This paper dealt with modelling and control of non-linear dynamic processes by artifiacal neural network with orthogonal and wavelet activation functions. Wavelet decomposition is employed to explore the characteristics of demand time series to extract more patterns from the series, and therefore enhance the forecast capability of neural network based models. Several types of orthogonal functions (Fourier, Legendre, Laguerre and Chebychev) for non-linear process modelling and control are analysed and compared. Simulation results are provided to illustrate high performance of artificial neural networks with the orthogonal activation functions in practical industrial problems. The obtained results are compared and potential shortcomings of the proposed methods for real time industry control are discussed and analysed.
暂无评论