A Smart Deep Convolutional Neural Network for Real-Time Surface Inspection

A proper detection and classification of defects in steel sheets in real time have become a requirement for manufacturing these products, largely used in many industrial sectors. However, computers used in the production line of small to medium size companies, in general, lack performance to attend real-time inspection with high processing demands. In this paper, a smart deep convolutional neural network for using in real-time surface inspection of steel rolling sheets is proposed. The architecture is based on the state-of-the-art SqueezeNet approach, which was originally developed for usage with autonomous vehicles. The main features of the proposed model are: small size and low computational burden. The model is 10 to 20 times smaller when compared to other networks designed for the same task, and more than 700 times smaller than general networks. Also, the number of floating-point operations for a prediction is about 50 times lower than the ones used for similar tasks. Despite its small size, the proposed model achieved near-perfect accuracy on a public dataset of 1800 images of six types of steel rolling defects.     

对大中型钢结构企业生产管理体系的研究分析

以某大型钢结构制造企业为例,通过对产量分布、质量控制、劳动效率等基本数据的分析,研判外协生产管理体系方面存在的问题,从组织形态、管理模式、职能管理等多个维度提出了可行性建议,可为同类型钢结构制造企业提供经验借鉴。     

Corrosion mechanism of cement-bonded Al2O3–MgAl2O4 pre-cast castables in contact with molten steel and slag

In this work, a cement-bonded corundum-spinel (Al₂O₃–MgAl₂O₄) pre-cast refractory brick with two typical Al₂O₃ aggregates was designed as the refractory lining. Corroded microstructure of the used corundum-spinel bricks after industrial trials in a commercial RH refining ladle was analyzed. Degradation processes of two types of alumina aggregates in the same corroded interface also were discussed. Typical corroded microstructure revealed that needle-like calcium hexaaluminate (CA₆) was observed in the matrix of the original layer. The formation of CA₆ was attributed to the reactions with pure calcium aluminate cement and matrix components under a high-temperature gradient during refining. Furthermore, the corrosion process of the used Al₂O₃–MgAl₂O₄ bricks would be discussed based on a post-mortem microstructural characterization, and the corrosion mechanism of the two types of aggregates was also elucidated.     

热轧圆钢热顶锻裂纹原因分析

热顶锻合格率是反映热轧圆钢实物质量的一个重要指标。在对国内外热轧圆钢热顶锻质量控制研究成果综述的基础上，对热轧圆钢的热顶锻质量进行了全面的调查、统计和试验研究，归纳了引起热轧圆钢热顶锻裂纹的常见原因，介绍了热顶锻裂纹分析步骤。通过对热顶锻裂纹的形貌和金相组织进行分析，阐述了引起热顶锻裂纹的冶炼因素和轧制因素，并进行了举例说明。     

中国抗中子辐照钢的抗辐照设计与验证

聚变堆等未来先进核能系统要求材料在强流高能中子辐照下长期保持良好的结构稳定性和机械性能。为适应未来先进核能技术发展的需要，中国科学院核能安全技术研究所•凤麟团队牵头研发了具有我国自主知识产权的中国抗中子辐照钢--CLAM钢。CLAM钢的设计考虑了未来核能清洁性的要求，以及苛刻服役环境中材料抗辐照、耐高温、耐腐蚀等性能要求。通过中子学计算分析设计了低活化成分范围，基于选择性纳米相析出进行了抗辐照、耐高温性能优化设计。针对材料的抗辐照性能，利用国内外中子、离子、电子及等离子体辐照设施开展了系列辐照考验研究，通过多角度表征辐照前后材料的微观结构和宏观性能，综合评估了材料的辐照性能，并与国际上同类材料在相近或相同条件下的辐照性能进行了对比分析，结果表明CLAM钢具有良好的抗辐照性能。     

0Cr17Ni4Cu4Nb传感器断裂原因分析

某力学传感器在出厂检验流程中发生断裂失效,为了确定失效原因,防止此类失效事件再次发生,实验对该传感器的力学性能、金相组织和断口形貌进行了分析,确定了断裂原因。结果表明,传感器的失效模式为氢致延迟开裂,材料中氢含量偏高和开裂位置机加工质量较差是导致传感器发生氢致开裂的主要原因。结合失效原因,提出了改进措施。     

中国钢铁产品全生命周期评价理论与实践

阐述了全生命周期评价的基本原理和内涵，分析了全生命周期评价在国内外钢铁行业的应用现状、差距及研究进展情况，论述了钢铁企业开展全生命周期评价的重要意义，研究了中国政府、行业协会、钢铁企业、咨询机构等在推进绿色设计产品评价技术规范系列标准等方面开展的相关工作。提出钢铁行业全生命周期评价推广与应用的具体建议，探讨了发展方向，对钢铁企业开展生命周期评价具有一定的指导意义。     

Methane bi-reforming over boron-doped Ni/SBA-15 catalyst: Longevity evaluation

A highly active and stable boron-promoted catalyst was successfully prepared by using the sequential incipient wetness impregnation technique and examined for methane bi-reforming reaction. The initial investigation found that the NiO and B₂O₃ particles were dispersed on the outer surface of the high surface area SBA-15 support. In addition, the catalytic activity was increased linearly with the tested reaction temperature due to the endothermic nature of the reaction. In fact, the catalyst achieved the CH₄ conversion and H₂/CO molar ratio of approximately 67.3% and 2.7, respectively at 1073 K. The resulting product ratio is highly suitable for downstream Fischer-Tropsch (FT) synthesis. The B-promoted catalyst showed the lowest degree of catalyst deactivation (4%) at 1023 K. Additionally, the XPS measurements unveiled that the boron facilitates the adsorption of CO₂ by donating electrons to the neighbouring Ni cluster and thus improved its catalytic performance. Furthermore, Raman and XRD analysis revealed that the boron promotion on 10%Ni/SBA-15 could prevent the reoxidation and deposition of carbonaceous species.