Advanced Materials Research Vols. 1070-1072

Abstract: An improved tracking method based on trajectory prediction is proposed and studied. The moving target tracking system is given and described. In order to fast and efficient tracking, a mathematical model of trajectory prediction of moving target is established. A large of experiments are carried by MALTAB. The results show that the improved method is better, improves the tracking speed and tracking precision.

Abstract: Nowadays, multi-relational classification has become a hotspot for research and application in the field of data mining. Compared to the single table with simple structure, multi-relational tables is more complicated. However, not all of the information in the tables has good effects on classification. It may decrease the classification accuracy of the algorithm when irrelevant relations are added. In this article, we optimized the multi-relational tables using the usefulness of the backgrounds to remove those relations which have little effect on the classification. The results show that, this method is effective.

Abstract: It is difficult to estimate the parameters of Weibull distribution model using maximum likelihood estimation based on particle swarm optimization (PSO) theory for which is easy to fall into premature and needs more variables, ant colony algorithm theory was introduced into maximum likelihood method, and a parameter estimation method based on ant colony algorithm theory was proposed, an example was simulated to verify the feasibility and effectiveness of this method by comparing with ant colony algorithm and PSO.This template explains and demonstrates how to prepare your camera-ready paper for Trans Tech Publications. The best is to read these instructions and follow the outline of this text.

Abstract: To reveal the fault occurrence regularity during actual operation of transport vehicle, based on reliability, maintainability and optimization theory and method, and by the the technical means such as large sample testing, mathematical modeling and multivariate data analysis, after several years of follow-up research, we found that the occurrence of vehicle failts obey Weibull distribution, and given specific failt rate functions. Accordingly, we established a corresponding optimal mathematical model of vehicle maintenance cycle, and got the optimal solution of the model. The results of special organized verify test shows that the model solution is accurate and reliable. If transport vehicles perform the optimal vehicle maintenance cycle, the lowest unit mileage cost of vehicle detection, diagnosis and maintenance would be got.

Abstract: The rolling bearing is widely used in rail vehicles. The detection and diagnosis of the bearing is of great theoretical value and practical significance. The fault diagnosis method of support vector machine (SVM) based on kernel fuzzy C-means (KFCM) membership degrees can have very good results. Support vector machine based on statistical learning theory do well in terms of classification .This method clusters according to the sample membership degrees and puts data into nuclear space. It can highlight samples of differences in features. The training sample size has been greatly reduced, while training speed and the rate of correct classification is improved. The experiment results show that this method is feasible.

Abstract: as everyone knows, conditioning F²N² (Feed Forward Neural Network) in many ways, but ways, but has so far failed to completely solve the "convergence not quickly" and "convergence is not robust"of these two problems, thus affecting the application of F²N². Aiming at this problem, pro this paper puts forward a new method of processing and application of F²N², the method of flexible BPNN (Back Propagation Neural Network) algorithm and hierarchical optimization algo-rithm as a whole, each layeris independent rights attached to the conditioning process, carefully con-structed F²N² objective function is non linear series based on the description, not only can the optimization of each layer of the weight problem is simplified to a linear problem, but also can effec-tively controlthe linearity error. This paper provides several examples of application of F²N² automa-tic detection, the results of application show that, this method is superior to other methods.

Abstract: Removed at authors request.

Abstract: The existing sample selection methods are inadequate in the determination of defect sample set, and lacking necessary metrics or evaluation methods of the defect sample set. This paper determines the typical defect sample set according to the selecting principles and proposes a metrics method of defect sample set to measure whether the defect sample set is representative of the defect library. At present, defect sample selection mainly depends on brainstorming and expert experiences in the electric system. However, for those organizations which have no experiences orfor large databases, there are significant difficulties on sample selection. The proposed defect sample selection framework and measurement criteria can effectively improve the situation and ensure that the selected sample set can well represent the defect library.