Jia Ruisheng

Research on P2P-Based Application Layer Multicast Technology for Streaming Media

The application layer multicast for streaming media is one of the hot and difficult problems in the field of network video broadcast. At first, the paper analyzed the principles and performances of classical application layer multicast models suitable for streaming media. Then we pointed out the application occasion of every model and the advantages and disadvantages. At last, a cluster splitting algorithm based on NICE is proposed. Simulation experiments show that the algorithm is simple and efficient, and able to adapt well to real-time streaming media applications.

Research and development of intelligent diagnosis based on neural network

The intelligent diagnosis technology has got a rapid development in the past few decades. Some new theories and methods have been applied to practice successfully, and obtained fruitful achievements. The artificial neural network leads to a new way for the research on fault diagnosis. It also provides a new scientific theory and thinking way for fault diagnosis. The intelligent fault diagnosis technology based on neural network has a great application potential and practical value. At present, it plays an irreplaceable role in monitoring, prediction, diagnosis and control of mechanical equipment condition, especially in the study of nonlinear and non-stationary signal processing. It shows that the intelligent fault diagnosis technology based on neural network is worthy of serious study. However, each diagnosis method has both advantages and disadvantages. Because of the inherent mechanism of the artificial neural network, this method also has some weaknesses inevitably. It is difficult to find an almost perfect way for the fault diagnosis. Only the intersection of a variety of methods, theories and technologies, and the introduction of new technologies and thoughts, could get a more accurate result of the fault diagnosis. The fault diagnosis based on neural network mainly includes two processes, training and diagnosis matching. The research focuses on three aspects: considering the neural network as a classifier from the angle of pattern recognition, considering the neural network as a dynamic forecasting model from the point of fault prediction, and establishing an expert system based on the neural network from the perspective of knowledge processing. This paper introduces the two processes of fault diagnosis, analyzes the present research situation from the three different angles above, put forward their advantages and disadvantages respectively, and discusses the development trends in the future.

Intelligent fault diagnosis based on support vector machine

Rolling bearing is one of the most important parts of a mechanical device. It has a higher failure rate, while the quality of the rolling bearing operating conditions affecting the operation of the entire device or even the entire production line. Therefore, the study of rolling bearing fault diagnosis is very important realistic significance and necessity. In this paper, we collect the bearing vibration signals by the sensor, and use wavelet threshold method to reduce the noise of the rolling bearing vibration signal wavelet and to remove the interference signal of signals. Then we use the wavelet packet technology to extract the energy band of noise signals. The energy spectrum feature vectors are extracted from the individual frequency bands, and they are set as the input vectors of SVM. Finally, the running condition of the rolling bearing is diagnosed intelligently by the analysis method of SVM.

Research on IETM authoring platform architecture based on S1000D specification

In order to solve the problems of traditional paper-based technology data storages difficulty and maintenances low efficiency, adapt to the modern information development needs, in the system studied the design of Interactive Electronic Technical Manual (IETM) based on S1000D specification, given the overall architecture model of IETM authoring platform. Firstly introduces S1000D specification, mainly introduces the two core contents that Common Source Data Base (CSDB) and Data Module (DM) of creation IETM based on S1000D, studies the design and implementation of DM. Describes the application of Extensible Markup Language (XML) and relational database in the IETM creation, established the mapping relationship of XML and relational database conforms to the S1000D specification, and gives the method of conversion between XML document and relational database. In order to enhance the easy operation of human-computer interaction, studies the application of speech recognition in the creation of IETM platform and system introduces the process of IETM creation.

Web Engineering Process and Its Application

Introduced the process framework of Web engineering, discussed the task requirements of web analysis and design. Pointed out that under the basis of using the base theory of traditional software engineering method, web engineering method should consider the specific features of the web application on analysis and design mechanism, and practiced an online course selecting system case of web engineering development, with the combining of web engineering and object-oriented UML(Unified Modeling Language) modeling technology, analyzed the system development environment and functional requirements, established the function model in UML use case diagram, the dynamic behavior model in UML Sequence diagram and the activity diagram that describe cases realization process, and the static model in UML class diagram, designed the system structure, navigation, and interface. As a new discipline, Web engineering still need carry out farther in-depth research.