Advanced Materials Research Vol. 1014

Abstract: Air transportation network reasonable planning related to express the long-term development of the enterprise, optimized air transportation network can make the express enterprises with strong market competitiveness. Based on the induction, and summarized the domestic and foreign related research results of air transportation network, and the importance of long-term development of enterprises, this paper shows the "air transport hub" bi level programming model and algorithm. EMS is an example.

Abstract: The process of building the database of tilapia’s farming and breeding is described in this paper. It presents the conversion between the database and the extra data files. It describes several strategies to achieve the data constraints of this database and presents the information retrieval methods based on this database. It described commonly used data analysis algorithms, and comes up with some solutions to solve the problem that reading the database frequently makes the efficiency of algorithm slow. Finally, it briefly describes some measures of maintaining the security of the database.

Abstract: Existing E-Learning courses are designed to guide users acquire information or to help users undertake specific tasks. User is expected to increase proficiency about the context via the stationary computer. However, such design cannot allow multiple users to access the system simultaneously, thus leading inefficiency and lack of expandability. A framework to support M-learning in RFID system is therefore proposed. A mobile user first can use a mobile computer to communicate with home agent to acquire the related server information he may be interested in. The framework can navigate mobile agents to the mobile computer when the tag is detected within the coverage of the reader. The framework enables a mobile user to directly access his/her personalized services from the mobile computer. The experimental simulation demonstrates its efficiency.

Abstract: Knowledge reduction is one of the basic contents in rough set theory and the most challenging problem in knowledge acquisition. In this paper, an algorithm is proposed, which aims to get all the reducts based on the attributes of the formal context. Experiments show that the algorithm is sound and accurate. Finally, further work and future perspectives are discussed.

Abstract: In the research of invasion detection, Positive and Unlabeled Learning algorithms canreduce the amount of work for labeling training samples. The present data stream classificationalgorithms aim at totally labeled data stream. From the perspective of data stream, a novel invasiondetection algorithm which is based on positive and unlabeled data stream classification using staticclassifier ensemble is proposed in this chapter. The experimental results on different datasetsdemonstrate that the proposed invasion detection algorithm can achieve good detectionperformance with reduced labeled training samples.

Abstract: Material selection is an important step in the product design process. Material selection problem contains many influence factors, and thus it is actually a multi-attribute decision making problem. In some situations, measure values cannot or unsuitable to be depicted by crisp numbers. Interval number is a suitable selection in these situations, and for the material selection problem with interval numbers, a new decision making method is developed based on grey relation analysis method. The attribute weights will be determined by the coefficient of variation method. Finally, a practical example is used to illustrate the effectiveness and feasibility of the proposed method.

Abstract: The general design of virtual maintenance platform based on 3D simulation is given to solve the difficulty of maintenance training for large equipment. Firstly, primary functions of platform are defined by comparing common platform with application system. Secondly, component structure and interaction structure of platform are designed based on common thinking of subsystem-serverice. Finally, technology systems of platform including common simulation framework and training basing on 3D simulation are also presented to realize simulation software. It will provide beneficial reference for maintenance training simulation of other similar large weapon equipment.

Abstract: In order to discover the fault with roller bearing in time, a new fault diagnosis method based on Empirical mode decomposition (EMD) and BP neural network is put forward in the paper. First, we get the fault signal through experiments. Then we use EMD to decompose the vibration signal into a series of single signals. We can extract main fault information from the single signals. The kurtosis coefficient of the single signals forms a feature vector which is used as the input data of the BP neural network. The trained BP neural network can be used for fault identification. Through analyzing, BP neural network can distinguish the fault into normal state, inner race fault, outer race fault. The results show that this method can gain very stable classification performance and good computational efficiency.

Abstract: Empirical mode decomposition (EMD) can extract real time-frequency characteristics from the non-stationary and nonlinear signal. Variable prediction model based class discriminate (VPMCD) is introduced into roller bearing fault diagnosis in this paper. Therefore, a fault diagnosis method based on EMD and VPMCD is put forward in the paper. Firstly, the different feature vectors in the signal are extracted by EMD. Then, different fault models of roller bearing are distinguished by using VPMCD. Finally, an simulation example based on EMD and VPMCD is shown in this paper. The results show that this method can gain very stable classification performance and good computational efficiency.

Abstract: The time-domain energy message conveyed by vibration signals of different gear fault are different, so a method based on local mean decomposition (LMD) and variable predictive model-based class discriminate (VPMCD) is proposed to diagnose gear fault model. The vibration signal of gear which is the research object in this paper is decomposed into a series of product functions (PF) by LMD method. Then a further analysis is to select the PF components which contain main fault information of gear, the energy feature parameters of the selected PF components are used to form a fault feature vector. The variable predictive model-based class discriminate is a new multivariate classification approach for pattern recognition, through taking fully advantages of the fault feature vector. Finally, gear fault diagnosis is distinguished into normal state, inner race fault and outer race fault. The results show that LMD method can decompose a complex non-stationary signal into a number of PF components whose frequency is from high to low. And the method based on LMD and VPMCD has a high fault recognition function by analyzing the fault feature vector of PF.