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.     

Saliency4ASD: Challenge,dataset and tools for visual attention modeling for autism spectrum disorder

The recent studies showing that gaze features can be useful in the identification of Autism Spectrum Disorder (ASD), have opened a new domain where Visual Attention (VA) modeling could be of great help. In this sense, this paper presents a report of the Grand Challenge “Saliency4ASD: Visual attention modeling for Autism Spectrum Disorder”, organized at IEEE ICME’19, aiming at supporting the research on VA modeling towards this healthcare societal challenge. In particular, this paper describes the workflow, obtained results, and datasets and tools that were used within this activity, in order to help on the development and evaluation of two types of VA models: (1) to predict saliency maps that fit gaze behavior of people with ASD, and (2) to identify individuals with ASD from typical development.     

铌对取向硅钢冷轧组织织构的影响

采用光学显微镜(OM)、电子背散射衍射(EBSD)等研究了铌对取向硅钢冷轧过程中的组织与织构的影响。结果表明:含铌正火板和不含铌正火板经冷轧后都是条带状组织,但含铌冷轧板在宽度方向更窄。铌元素的存在对织构也具有优化作用,经过中间退火后,含铌冷轧板二次冷轧织构得到明显改善,相较于不含铌二次冷轧板拥有强度较低的旋转立方织构以及强度较高的{111}<112>织构,其取向密度最高可达12.460。     

基于烟丝特性和卷制原理的卷烟机最佳回丝量计算模型

为确定卷烟机最佳回丝量,根据烟支卷制原理,结合烟支重量、规格、密度和平准盘凹槽规格、卷烟机吸丝道导轨规格等因素建立了卷烟机最佳回丝量计算模型。通过实例验证,该模型推算出的卷烟机回丝量是合适的,不仅能提供满足烟支质量要求的烟丝量,而且能最大程度减少因回丝量过大造成的烟丝造碎,降低烟支含末率,提升产品质量。该模型确定卷烟机最佳回丝量的方法实施方便,且不受卷烟机机型、烟支规格、原辅材料等因素限制,具有一般适用性。     

基于改进奇异值分解滤波和谱峭度的滚动轴承故障诊断

针对含噪信号的有效奇异值个数难以确定的问题，提出了一种改进的奇异值分解降噪方法--奇异值累积法。该方法通过计算奇异值的实际下降值与奇异值平均下降速度累积量的差值，并取该差值最大值点的位置作为有效奇异值的分界点来确定有效奇异值的个数。在此基础上，提出了一种基于奇异值累积法与快速谱峭度的滚动轴承故障诊断方法。采用奇异值累积法对原信号进行降噪处理，然后利用快速谱峭度确定滤波器中心频率及带宽，通过分析频段包络谱中明显的频率成分来诊断故障。该方法可以有效去除信号中的噪声，使得到的峭度值所反映的故障冲击更接近实际情况。对含内圈、外圈故障的滚动轴承实验数据进行分析，实验结果表明，相比快速谱峭度的故障诊断方法，该方法具有更好的故障识别效果。     

地表移动带范围内建构筑物安全可靠性分析

地表建构筑物位于在生产矿山地表开采移动范围内，如果按照一般圈定地表移动范围原则判断建构筑物的安全可靠性，结果是不安全或者预留保安矿柱可保证安全。为分析地表移动带范围内建构筑物安全可靠性，采用FLAC3D软件建立数值模拟模型，对矿区地表移动进行分析研究，并结合建构筑物的破坏等级评判标准，可以更加合理地判断地表移动范围内建构筑物的安全可靠性，对存在相似条件的矿山具有一定的借鉴意义。     

整体壁板离散填料滚弯成形有限元模拟

具有一定曲率外形的铝合金整体壁板属于典型的多筋零部件,传统弯曲成形工艺成形困难,容易产生多种缺陷。提出了离散填料辅助滚弯成形整体2A12T4铝合金壁板滚弯工艺,并通过实验与整体填料滚变成形进行了对比,同时采用有限元模拟技术,探究了离散填料辅助整体壁板滚弯成形中的影响因素。研究结果表明:填料数量、上下垫板厚度等因素对成形性能影响较大,填料在3~6块时成形稳定,可以有效地避免筋条屈曲与失稳;随垫板厚度增加,壁板表面圆弧更加光滑、连续,但是回弹性增强;上下垫板分别在10~20 mm厚度时,综合性能较好。通过离散填料辅助滚弯技术可以成形出质量较高的整体壁板。     

采动覆岩卸荷膨胀累积效应

地下煤层开采引起的岩层运动是一系列安全和环境问题的根源,研究采动岩层运动规律是安全、高效、绿色开采的重要基础。通过对岩层运动过程的研究,揭示了采动覆岩卸荷膨胀累积效应及其对岩层运动规律的影响机制。研究表明:采动覆岩经历了卸荷膨胀与再压实的动态过程。受关键层结构控制,上覆岩层由下向上成组破断运动,关键层破断前,阻断了上覆载荷向下方岩层的传递,导致其因卸荷而产生膨胀,包括碎胀与弹性膨胀。随着关键层破断高度增加,覆岩卸荷高度同步增大,因卸荷而膨胀的岩层总厚度不断增大;同时卸荷煤岩也受到已破断关键层载荷的压实作用,从而造成覆岩卸荷膨胀总量的不断变化。将这种覆岩卸荷膨胀总量随覆岩卸荷高度动态变化的现象定义为采动覆岩卸荷膨胀累积效应,进而建立了理论模型,并通过淮北海孜煤矿巨厚火成岩下采煤覆岩裂隙实测进行了验证。结果表明,采动覆岩卸荷膨胀累积效应对采动岩层运动规律产生了重要影响,如影响覆岩关键层下离层量,影响覆岩关键层贯通破断的高度,影响不同开采条件的地表下沉系数等。采动覆岩卸荷膨胀累积效应改变了对离层存在形式的传统认识,该效应的存在导致关键层下最大离层量一般小于采高的10%,覆岩可注浆充填空间并非传统认识上的“离层区”,而主要是注浆充填压力“压实”作用下将覆岩卸荷累积膨胀所转化出的那部分空间,该发现指导了覆岩隔离注浆充填绿色开采技术的创新研发及其在建筑物压煤开采中的成功实践。     

Hydrogen storage in MgH2LaNi5 composites prepared by cold rolling under inert atmosphere

Mg-AB₅ composites are promising systems for hydrogen storage applications, due to their possibility of hydrogen cycling at relatively low temperatures. Traditionally, these composites are mainly processed by high-energy ball milling (HEBM) techniques employing longer processing times. In this study, cold rolling was applied to prepare MgH₂LaNi₅ composites and the hydrogen storage properties were investigated. The materials were processed using a vertical rolling mill under argon atmosphere, leading to a good homogeneity and no contamination at shorter processing times. The mixture of MgH₂-1.50 mol.% LaNi₅ showed the best hydrogen storage properties at 200 °C and 100 °C and the lowest desorption temperature even when compared to cold rolled MgH₂. The results indicate that the composite MgH₂LaNi₅ is transformed into a mixture of three phases MgH₂, Mg₂NiH₄ and LaH₃ upon hydrogen absorption/desorption cycles. The synergetic effect among these phases when in appropriate proportion in the sample seems to play a crucial role in the acceleration of hydrogen absorption/desorption kinetics at lower temperatures in comparison to MgH₂.     

巨厚煤层开采覆岩含水层破坏模拟——以准东大井矿区为例

本文针对准东矿区巨厚煤层典型赋存特征,以大井矿区为研究对象,通过识别覆岩关键层及含水层,采用UDEC数值模拟方法,建立大井矿区巨厚煤层开采覆岩力学模型,对不同开采方法覆岩含水层破坏进行了模拟研究。结果表明:研究区覆岩关键层分为4层、覆岩含水层共2层;开采厚度相同时,大采高开采覆岩下沉量、裂隙带发育高度及开采对含水层的扰动影响均大于放顶煤开采;采高24m,推进长度为300m时,导水裂隙已发育至含水层Ⅱ;主关键层对覆岩位移、裂隙分布及开采对含水层的扰动影响起关键作用。