Machine fault diagnosis with small sample based on variational information constrained generative adversarial network

In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches.     

Study on the non-uniform contact during ELID groove grinding

This paper introduces the potential feasibility that ELID (electrolytic in-process dressing) grinding replaces superfinishing in bearing manufacturing, but ELID grinding will bring new challenges. Different regions present distinguish surface profile due to the non-uniform contact in ELID groove grinding. However, few reports explaining the non-uniform contact are available. This article explores the mechanisms of the non-uniform contact during ELID groove grinding. Experiments on the non-uniform contact between bearing raceway and grinding wheel have been carried out under different conditions. The results show that non-uniform contact exists in ELID groove grinding process and it exerts influence on the profile of the raceway surface. Non-uniform contact influences the Rsk and Rku value all the time, but it influences the Ra value occasionally. Improvement strategies of eliminating the non-uniform contact are also discussed based on the experimental study.     

烧结机卸料装置耐磨性改善

烧结机导料箱、单辊破碎机和卸料漏斗承载着烧结热矿的导料、破碎与输送,是烧结生产的重要组成部分。高温、重载的工况环境决定着机尾卸料装置必须具有抗磨损、耐高温的特性。针对邯钢1^#435m^2烧结机机尾关键部件耐磨工作面寿命短,更换不方便等问题,分析磨损机理与失效原因,提出改进抗磨工作面结构,升级耐磨材料,优化焊接工艺等措施。通过技术方案的实施,使烧结机导料箱、单辊破碎机和卸料漏斗等卸料装置维持了较高的抗磨损性能,达到了预期的改造效果。     

强化研磨加工中喷射角度对GCr15轴承钢板塑性变形的影响

利用ABAQUS有限元仿真软件研究不同喷射角度强化研磨加工GCr15轴承钢板过程的塑性变形,得到不同喷射角度与等效塑性应变沿真实路径距离的关系,并通过拉伸试验进行验证。喷射角度为90°的强化研磨加工伸长率为1.4%,相比未经过强化研磨加工的伸长率数值缩减了2.0%。断口收缩率由空白组的4.9%降低到喷射角为90°的2.2%。结合仿真和试验可知,强化研磨加工中喷射角度越大,塑性变形能力越低,材料加工越难。     

狭缝节流空气静压轴承局部气膜流场的直接数值模拟

采用3阶精度的迎风格式及2阶精度的中心差分格式,直接求解二维非定常N-S方程组,研究狭缝节流空气静压轴承压降恢复之后区域的流场特性。使用雷诺方程计算相同位置气膜中心处的流场状态,并与直接数值模拟方法的计算结果进行对比。结果表明:雷诺方程与N-S方程在计算域内计算结果基本一致,两者压力偏差为0.173%,速度偏差为1.217%;流场压力、密度沿气流方向逐渐减小,但在气膜方向几乎不变;流场速度、压力梯度沿气流方向逐渐增加,速度在流场出口处达到最大值;直接数值模拟方法得到了流场的温度变化,即整个流场的温度变化很小,温度整体呈上下高、中心低的分布,而雷诺方程无法计算得出整个流场的温度变化情况;采用雷诺方程计算轴承压降恢复之后区域的流场是合理的。     

测井资料在优选压裂层位中的应用

压裂是低孔、低渗油层改造的主要增产措施。根据常规测井资料、岩石物理实验分析数据及试油成果。研究储层四性关系，确定区块的低孔、低渗储层评价标准。进一步对油层进行分类，有针对性地为油层压裂提供施工层位和准确的储层参数。通过商543区块实例，阐述了选择压裂层位的方法。     

大同市水资源开发利用状况与承载能力的思考

文中分析了大同市水资源开发利用的状况，并对水资源承载能力的有关问题进行了讨论。     

水资源承载力及其研究

文章简要介绍了我国水资源情况,分析了我国水资源承载力与可持续发展的关系,并阐述了水资源承载力 研究的特点和方法。     

万家寨引黄工程北干1号隧洞Ⅳ标155-274型TBM主轴承总成组装概要

文中对万家寨引黄工程北干线1号隧洞Ⅳ标使用的155—274型TBM主轴承总成各部件组装过程及其相应的技术要求进行了概要的描述，目的是进一步熟悉155—274型TBM主轴承总成的各个部件并加深对主轴承工作原理的理解。     

压型钢板组合楼板承载力的有限元分析

压型钢板组合楼板是 2 0世纪发展起来的一种新型结构形式。它具有显著的优势 ,如轻质、高强 ,施工快捷等 ,将在未来的建筑领域中大有作为。组合楼板的承载力主要取决于钢板 -混凝土界面处的抗剪强度。建立了一个二维有限元模型来研究单向组合板的性能。并将计算结果与试验数据进行对比 ,验证了模型的有效性