Applied Mechanics and Materials Vols. 44-47

Abstract: The paper introduces a new method for prediction of electromagnetic compatibility in the power system, and use the Electromagnetic simulation software ATP. By comparing the actual test results to the simulation results, it is proved that electromagnetic transient simulation is reliable and effective. It also introduces the Gray prediction theory to predict the next Electromagnetic Interference (EMI) of the substation. It is high practical to research and analyze the substation electromagnetic compatibility, and feasible to use the Gray prediction theory with multivariable for the model EMI prediction analysis.

Abstract: The order-disorder transition at antiphase domain boundary (APDB) between DO22 (Ni3V) phases is investigated using the microscopic phase-field model. After the formation of ordered APDB, the order-disorder transition at APDB is happened, and the ordered APDB transforms into a thin disordered phase layer. Accompanied with the enrichment of Ni and Al at the disordered APDB, the second phase L12 nucleates at the order-disorder interface between DO22 phases and grows along the disordered phase layer. The order-disorder transition at the ordered APDB makes the nucleation and growth of the second phase L12 much easier and faster. The disordered phase caused by the order-disorder transition at the APDB can be considered as the transient phase during the precipitation process of L12 phase.

Abstract: The sensory quality evaluation processes are widely used for many industrial products, which is evaluated according to the knowledge acquired via human senses (such as sight, taste, touch, smell). Because the evaluation information acquired by our senses is involving uncertainty, vagueness and imprecision, and the sensory quality information of products always has the panel data characteristic, so the sensory quality evaluation and certification is a multi-feature group decision-making problem based on panel linguistic information processing. This paper presents a proposed method for the development of accredited sensory evaluation methods, and shows the application of the linguistic 2-tuple representation model and its advantages. It involved several steps: gathering of sensory information from experts; computing a collective evaluation for each feature; computing collective evaluations for each object; dynamic aggregation; sensory evaluation and quality certification with global evaluation result.

Abstract: This paper presents a new smooth approach to solve support vector regression (SVR). Based on Karush-Kuhn-Tucker complementary condition in optimization theory, a smooth unconstrained optimization model for SVR is built. Since the objective function of the unconstrained SVR model is non-smooth, we apply the smooth techniques and replace the ε-insensitive loss function by CHKS function. Newton-Armijo algorithm is used to solve the smooth CHKS-SSVR model. Primary numerical results illustrate that our proposed approach improves the regression performance and the learning efficiency.

Abstract: As one of the most potential field in today’s society, E-Commerce is coruscating vigorous vitality. Development of the information and network technology provide possibility for some new technology in e-commerce application, the application of new technology will also promote e-commerce to a higher level, Agent technology is one of the new technology, it is a product with the complete development of distributed computing and artificial intelligence technology, it has the advantage of autonomy and initiative and provide structure fundament for advanced stage of e-commerce activities. The Agent technique made users on longer lost in the changing product information. Enterprise can provide personalized service vary from person to person when they faced a lot of users and fundamentally improved problems in e-commerce. It will promote the development of e-commerce.

Abstract: Clustering is an efficient and fundamental unsupervised learning algorithm for many vision-based applications. This paper aim at the problems of fast indexing high-dimensional local invariant features of images (e.g. SIFT features) and quick similarity searching of images in a scalable image database by using a hierarchical clustering algorithm. We adopt the hierarchical K-means (HKM) clustering method to build a visual vocabulary tree efficiently on given training data and represent image as a “bag of visual words” which are the leaf nodes of the visual vocabulary tree. For the application of image retrieval, we adopt an usually-used indexing structure called “inverted file” to record the mapping of each visual word to the database images containing that visual word along with the number of times it appears in each image. We propose a weighted voting strategy for the application of content-based image retrieval and achieve desirable performance through experiments.

Abstract: In order to improve the fault diagnosis result of the condenser, one new approach based on the fuzzy neural network and data fusion is proposed in this paper. Firstly, the data from the various sensors can be processed through the specific membership functions. With the fault symptoms and fault types of condenser, the fuzzy neural network is constructed for the primary fault diagnosis. Some likelihood of the neural network outputs is too close to make the correct decision of fault diagnosis. The problem can be solved by the data fusion technology. This method was successfully adopted in the application of condenser fault diagnosis. Compared with the general method of FNN, this approach can enhance the accuracy in the domain of fault diagnosis, especially for reducing the uncertainty in the fault diagnosis.

Abstract: Track geometry deformation lead to dangerous of train driving, endangering railway transport. It is the prerequisite of developing a reasonable plan of track maintenance and repair that find out the occurrence of track geometry deformation and the law of development. It is also one of the core works of railway's maintenance and repair. In this paper, we analyze detect data of railway track use time series analysis, discovery the track deformation production, make a thorough inquiry to find out the trend of deformation occurrence and forecast the status of the track geometry. The results show that there is higher accuracy of the forecasting, and it can be used to guide the conservation of railway track.

Abstract: Data platform of data sharing and service provide technical support for high-speed railway transportation organization, it provide data parameter and data support for high-speed railway operation management, and it plays an important role in promoting national economic development. In this paper, the metadata theory is used for data storage, data cataloging, data retrieval and data discovery in the management of the Beijing-Shanghai high-speed railway transportation equipment, analyze and propose key technologies of the establishment of data sharing platform based on metadata management of high-speed railway transportation equipment, correlation analysis is made and the result of analysis indicates that data platform can greatly improve the utilization and ability to obtain high-speed railway transportation equipment data. It can also improve the ability to support organizational decision-making of high-speed railway transportation.

Abstract: Urban storm intensity formula is one of the basic urban drainage design formulas. The accuracy and precision of the formula will be directly related to urban infrastructure security and economic rationality. The traditional solution method of the storm intensity formula is time-consuming and the accuracy is poor. The accuracy and precision of the current value iteration algorithm are good, but these methods require a continuous and differentiable objective function, if the function is Non-differentiable or without gradient information, these methods will fail. In response to these shortcomings, this paper uses the Genetic Algorithm to solve the storm intensity formula of the Tieling City to provide a reliable method.