Microstructures and mechanical properties of B4C-TiB2-SiC composites fabricated by ball milling and hot pressing

B₄C-TiB₂-SiC composites were fabricated via hot pressing using ball milled B₄C, TiB₂, and SiC powder mixtures as the starting materials. The impact of ball milling on the densification behaviors, mechanical properties, and microstructures of the ceramic composites were investigated. The results showed that the refinement of the powder mixtures and the removal of the oxide impurities played an important role in the improvement of densification and properties. Moreover, the formation of the liquid phases during the sintering was deemed beneficial for densification. The typical values of relative density, hardness, bending strength, and fracture toughness of the composites reached 99.20%, 32.84?GPa, 858?MPa and 8.21?MPa?m^1/2, respectively. Crack deflection, crack bridging, crack branching, and microcracking were considered to be the potential toughening mechanisms in the composites. Furthermore, numerous nano-sized intergranular/intragranular phases and twin structures were observed in the B₄C-TiB₂-SiC composite.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

Ni,Cr, and Fe surfaces corroded by molten ZnCl2

Understanding the corrosion of molten ZnCl₂ on metal surfaces is significant for the corrosion protection of metals, sustainable use of molten salts, preparation of ZnO coatings, and so on. In this paper, surfaces of pure Ni, Cr, and Fe corroded by molten ZnCl₂ were investigated. The results show that Ni suffered very slight corrosion, while Cr experienced more serious corrosion than Ni, but lighter corrosion than Fe. The morphology of the corrosion of Cr and Fe, respectively, presented pitting and intergranular corrosion characteristics. Furthermore, nanostructured ZnO coatings were obtained on the surfaces of Ni and Fe, but not on the surface of Cr. The ZnO coating on the Ni surface was doped with a small amount of Zn₅(OH)₈Cl₂, and the ZnO coating on the Fe surface was doped with ZnFe₂O₄ and Zn₂OCl₂. The coatings on the Ni and Fe surfaces had an average thickness of 1.5 and 50 μm, respectively.     

Corrosion resistance of Al–Cr-slag containing chromium–corundum refractories to slags with different basicity

Al–Cr slag is the solid waste generated by the smelting of Cr metal. It presents a range of environmental hazards. This study addressed the corrosion resistance of Al–Cr slag containing chromium–corundum refractories to slags with different basicity. Herein, we provide suggestions for the use of Cr–corundum of different basicity in kilns. Al–Cr slag, brown fused Al₂O₃, and chrome green were used as the raw materials, with pure calcium aluminate cement being used as a binder. The brick samples, prepared using different blends of chrome green and corundum, were fired at 1600?°C, and subsequently subjected to a slag corrosion test. After corrosion by slag of different basicity, the phase composition and microstructure of the sample were analyzed by X-ray diffraction, energy dispersive spectrometer and scanning electron microscopy. There were two major findings. First, Cr–corundum brick made from Al–Cr slag has a better slag corrosion resistance than that made from Cr₂O₃ and brown fused Al₂O₃. Second, Cr–corundum brick made from Al–Cr slag has superior corrosion resistance to slag with a CaO:SiO₂ ratio of 2:1.