Papers by Keyword: Fusion

Abstract: In order to predict the effect of the Marangoni convection and the morphology of melted stainless steel powder, during the selective laser melting (SLM) process, a transient three-dimensional numerical model is developed at the mesoscale. The evolution of the temperature and velocity fields’ is then studied. The initial powder bed distribution is obtained by the discrete element method (DEM) calculation, and the temperature distribution and the molten pool shape deformation are calculated and analyzed by the Ansys-Fluent commercial code. The molten pool shape is obtained by considering the influence of Marangoni convection on the internal flow behavior. The recoil force was not considered in our calculation. As main results, a slight deviation between the position of the maximum temperature of the molten pool and the center of the laser spot is observed. The direction of the heat diffusion is more likely to be horizontal and the flow centrifugal, which causes the melt track to be wide. Finally, the Marangoni convection is the main driver of the flow.

Abstract: This paper investigates the effect of the laser cutting parameters on the heat-affected zone, and on the boundary layer of stainless steel processing. A new analytical resolution based on the boundary layer theory is used to deduce the interaction effects of the cutting parameters on the above zones. The results revealed that, the laminar nitrogen assist gas has a negligible effect on the HAZ depth but it has a remarkable effect on the molten boundary layer. It is also noticed that the pressure gradient remains very small compared to the interface shearing and the conductive heat losses from the cutting zone towards the substrate is dominant compared to the convective heat losses towards the gas.

Abstract: The composite material tungsten fiber-reinforced tungsten (W_f/W) addresses the brittleness of tungsten by extrinsic toughening through introduction of energy dissipation mechanisms. These mechanisms allow the release of stress peaks and thus improve the materials resistance against crack growth. W_f/W samples produced via chemical vapor infiltration (CVI) indeed show higher toughness in mechanical tests than pure tungsten. By utilizing powder metallurgy (PM) one could benefit from available industrialized approaches for composite production and alloying routes. In this contribution the PM method of hot isostatic pressing (HIP) is used to produce W_f/W samples. A variety of measurements were conducted to verify the operation of the expected toughening mechanisms in HIP W_f/W composites. The interface debonding behavior was investigated in push-out tests. In addition, the mechanical properties of the matrix were investigated, in order to deepen the understanding of the complex interaction between the sample preparation and the resulting mechanical properties of the composite material. First HIP W_f/W single-fiber samples feature a compact matrix with densities of more than 99% of the theoretical density of tungsten. Scanning electron microscopy (SEM) analysis further demonstrates an intact interface with indentations of powder particles at the interface-matrix boundary. First push-out tests indicate that the interface was damaged by HIPing.

Abstract: This paper was proposed a new algorithm for Facial Expression Recognition (FER) which was based on fusion of gabor texture features and Centre Binary Pattern (CBP). Firstly, gabor texture feature were extracted from every expression image. Five scales and eight orientations of gabor wavelet filters were used to extract gabor texture features. Then the CBP features were extracted from gabor feature images and adaboost algorithm was used to select final features from CBP feature images. Finally, we obtain expression recognition results on the final expression features by Sparse Representation-based Classification (SRC) method. The experiment results on Japanese Female Facial Expression (JAFFE) database demonstrated that the new algorithm had a much higher recognition rate than the traditional algorithms.

Abstract: In order to solve the hearing-impaired students in class only rely on sign language, amount of classroom information received less, This paper studies video and audio dual mode fusion algorithm combined with lip reading、speech recognition technology and information fusion technology.First ,speech feature extraction, processing of speech signal, the speech synchronization output text. At the same time, extraction of video features, voice and video signal fusion, Make voice information into visual information that the hearing-impaired students can receive. Make the students receive text messages as receive visual information, improve speech recognition rate, so meet the need of the classroom teaching for hearing-impaired students.

Abstract: The purpose of multiple biometric fusion is to improve the recognition performance by utilizing their complementary. In this paper, the feature fusion recognition method of multi-view face and gait in video is studied, and a adaptive decision fusion method is proposed. The results showed that the adaptive fusion features carry the most discriminating power compared to any individual biometric and other static fusion rules like Max and Sum.

Abstract: A novel interacting multiple model based on BLUE filter (IMM-BLUE) for tracking a maneuvering target using radar/ESM heterogeneous sensors is presented in this paper. Under the architecture of the proposed algorithm, the interacting multiple model (IMM) deals with the model switching, while the BLUE filter accounts for non-linearity in the dynamic system models. The simulation results show that the presented IMM-BLUE has higher tracking precision than the IMM-DCM, and IMM-EKF.

Abstract: Rough set theory and grey theory have the same advantage of processing inaccuracy data, so one fusion algorithm based on them is proposed. The attribute reduction algorithm of rough set theory can reduce the decision table of fault diagnosis, and grey theory can predict the fault based on the new reduced decision table. Then it is verified in some aero radio equipment, and the results indicate that the accuracy of fault prediction is quite higher, which provides the foundation to improve the equipment reliability and maintainability.

Abstract: Zeolite A has been synthesized by a modified alkali fusion followed hydrothermal process. Hydrothermal was performed at a temperature of 90 °C for 4 h in a stainless steel reactor. Characterization of the synthesized zeolite was conducted using various techniques, i.e. X-ray Diffraction (XRD), Scanning Electron Microscopy (SEM), Fourier Transform Infrared Spectroscopy (FTIR), Brunauer-Emmett-Teller (BET) and measurement of cation exchange capacity (CEC). The characterization results showed that zeolite A was selectively obtained by this method. The diffract gram, SEM image, and IR spectra of the synthesized zeolite A showed a similarity with the commercially available zeolit A.

Abstract: In order to solve the problem of the information loss on the feature extraction process in the traditional pattern recognition, a new method based on probability boxes theory was proposed. Firstly, the skewness of the fault signal data were used as the information source to construct the tow p-boxes about X and direction. Then, to take advantage of the complementation of the information source, the tow p-boxes from different directions were fused. Finally, the SVM features database was established by extracting different types of cumulative uncertainty measures from p-boxes. The analysis result shows that the combination of p-box and SVM can achieve a high recognition rate, which makes a new way for pattern recognition.