Yang Guo-wei

Approximate Solution Research of State Equation for Controlled Nonlinear Systems

Based on the solution of the linear state equation, by making of the Taylor expansion, the nonlinear state equation of controlled systems under ideal state is transformed to a set of ordinary differential equations with infinite series expression. Based on the solution of this set of linear state equation, the integral equation of the nonlinear state equation is also obtained by utilizing constant variation method. Finally, any order approximate solution of the nonlinear state equation is given by utilizing successive approximation method.

An associative memory fault-tolerance control for model signal of intelligent control system

Because artificial brain associative memory neural networks have property of nonlinear mapping, fault-tolerance power and learning capability, they have especial advantages for fault-tolerance control. This paper proposes an associative memory neural network of artificial brains controllable fault-tolerant field, which can be used as fault-tolerance apparatus for model signals of intelligent control system. The model signal fault-tolerance apparatus differs from other ones and can design proper fault-tolerant fields for signals based on the fault-tolerance request of intelligent control system. The fault-tolerance of the control system can be heightened when the fault-tolerance apparatus is embedded in a right control system.

Current Status of SoftMan Research and Its Application in Publishing and Printing Industry

In this paper, first of all, the concept of SoftMan and its features are introduced, then the current status of SoftMan research is discussed, especially the applications of SoftMan in digital gas field, intelligent enterprise resource planning (ERP), information security, intelligent games are discussed. Finally, the applications of SoftMan in publishing and printing industry are discussed.

Lossless data compression methods based on neural network

No lossless data compression method based on neural network has been found before. A lossless compression method based on BP network for the long character-string of 0 and 1 is given by establishing specific mapping Y and specific integer function and with the non-linear approximation capability of concrete three-layer BP network in this paper. The compression and decompression algorithms of the lossless compression method are provided. Experiments show that the compression ratio of the lossless compression method is usually around 16/11 and the method can effectively compress the data which have been compressed by Huffman coding, arithmetic coding or dictionary coding.