Том 50, № 2 (2016)

A reservoir radial-basis function neural network, which is based on the ideas of reservoir computing and neural networks and designated for solving extrapolation tasks of nonlinear non-stationary stochastic and chaotic time series under conditions of a short learning sample, is proposed in the paper. The network is built with the help of a radial-basis function neural network with an input layer, which is organized in a special manner and a kernel membership function. The proposed system provides high approximation quality in terms of a mean squared error and a high convergence speed using the second-order learning procedure. A software product that implements the proposed neural network has been developed. A number of experiments have been held in order to research the system’s properties. Experimental results prove the fact that the developed architecture can be used in Data Mining tasks and the fact that the proposed neural network has a higher accuracy compared to traditional forecasting neural systems.

This paper deals with fuzzy dynamic fault tree analysis for the electro-mechanical actuator with common-cause failures to provide fast fault location strategy. To fully describe the level of uncertainty of basic events, triangle fuzzy set is used. Temporal operators are defined, algebraic model is used to model and analyze dynamic fault tree of the electro-mechanical actuator and is general to all kind of life distribution. An innovative common-cause gate with incomplete common-cause under consideration is raised and it can also match the algebraic model analysis method. Fuzzy probability importance is computed by level-progressive strategy, and complexity of solving entirely is avoided and calculation time is reduced. The analysis result shows that the method is flexible and effectively done with the reliability analysis of electro-mechanical actuator and can provide suggestions for faults location.

With the development of network technology, cloud computing as an emerging network technology has drawn more and more attention. At the same time, the security and efficiency of cloud computing technology has become major issues restricting the rapid development and popularization of cloud computing technology. By exploring the security of cloud computing service model, this study puts forward the architecture of a service model based on cloud computing. In order to implement the service model safely, a hybrid encryption algorithm is designed to ensure that data cannot be easily stolen during transmission and storage. Besides, this thesis also discusses different implementation mechanisms on data security storage, isolation and backup.

This paper presents a backstepping control method with speed estimation of permanent magnet synchronous motor (PMSM) based on model reference adaptive system (MRAS). First, a comprehensive dynamical model of PMSM in d–q axis and its space state equations are established. Next, using Lyapunov stability theorem, based on the backstepping control theory, the PMSM rotor speed and current backstepping controllers are designed. Furthermore, using Popov stability theory, based on MRAS, the PMSM rotor speed observer is designed. Finally, Matlab/Simulink simulation results show that the backstepping control and speed observer are effective and feasible.