Knowledge augmented broad learning system for computer vision based mixed-type defect detection in semiconductor manufacturing

Defect detection is a critical measurement process for intelligent manufacturing systems to provide insights for product quality improvement. For complex products such as integrated circuit wafers, several types of defects are usually coupled in a piece of wafer to form a mixed-type defect, which poses a challenge to current defect detection methods. This paper proposed a knowledge augmented broad learning system with a knowledge module and broad selective sampling module, which provides a multichannel selective sampling network to decouple the mixed-type defects. In this model, each channel is equipped with a pre-trained deformable convolution model to extract the feature of a fixed single-type defect. The knowledge module is designed to activate the candidate network channel by pre-detection of wafer maps. The experiment results indicated that the proposed model outperforms conventional models and other deep learning models, which demonstrated that the knowledge augmented broad selective sampling mechanism is effective for mixed-type defect detection.     

基于同步挤压提取变换的滚动轴承故障诊断研究

滚动轴承是大型机械设备的重要部件,起着非常重要的作用。当轴承发生故障时,如不及时修复或更换,将严重影响设备的寿命。时频分析方法是一种非常有效的故障特征提取工具,已得到广泛的应用;同时,时频分布的能量聚集性影响故障特征提取效果,因此,一种能量更加集中的时频分析方法对机械信号处理与故障诊断起着至关重要的作用。提出了一种全新的时频域特征提取方法——同步挤压提取变换。该方法主要包含两个步骤:首先,使用同步挤压变换将信号大部分能量聚集到多个小频带范围内,实现信号能量的初步聚集;然后,在同步挤压变换结果中引入一个频率提取算子,该算子可以提取出每个小频带内与信号时变特征最相关的信息并将其保留,从而实现信号能量的再次聚集。仿真信号的分析验证了该方法的可行性。通过对实际轴承信号的分析发现,与先前的时频分析方法相比,该方法效果更佳。     

选区激光熔化中飞溅行为的研究进展

选区激光熔化技术(SLM)被认为是极有前途的增材制造技术之一,但不可逆的溅射行为严重限制了SLM技术的应用。从粉末熔池演变、加工工艺优化和飞溅颗粒动态特征监测等方面,总结了SLM过程中飞溅行为的研究现状,分析了飞溅行为的产生机制,探讨了激光–粉末–熔池相互作用下的熔池演变情况,表明金属蒸气、Marangoni效应和伯努利效应是诱发飞溅的主要因素;讨论了加工工艺与飞溅行为的相互关系,表明通过优化工艺参数和改善打印环境以抑制飞溅是行之有效的方法;阐述了飞溅诱导缺陷的机理,并讨论了SLM过程的监测方法,表明单一信号的局限性会导致监测结果失准,多信号融合监测是提升精准性的重要方法之一。最后,针对飞溅行为存在的关键科学问题和技术难题,展望了SLM加工中飞溅行为的研究方向。     

离合器摩擦副摩滑过程轴向振动特性研究

通过对摩擦副表面结构特征和接触力学等理论的应用,建立了热变形微观法向单元接触数学模型。采用数理统计和归一化方法,将微观模型转换成宏观数学模型,分析了摩擦副法向弹性接触特性,并引入Kelvin-Voigt(KV)模型,增加黏弹性接触微分算子,构建了包含有应力和应变关系的黏弹性接触属性的数学模型,得到了摩擦副轴向振动数学模型。经仿真分析,获得了摩擦副摩滑过程的振动特性,同时对不同转速条件下的摩擦副摩滑过程轴向振动特性进行了实验测试。经对比分析,结果表明,仿真模型精度达到87%,仿真结果准确。这为进一步深入研究振动特性对摩擦副使用性能和寿命,具有理论研究和工程设计指导意义。     

直齿轮轮齿双侧裂纹对其刚度影响的研究

齿轮副的时变啮合刚度(Time-varying meshing stiffness,TVMS)是机械动力学分析中一个极为重要的参数,其准确程度直接影响着动力学分析结果的准确性。首先,从理论角度推导了剪切刚度的计算公式,并在案例分析中应用,将求得结果与有限元分析结果进行对比,结果显示相差较小;然后,建立了一种新的裂纹故障模型——轮齿双侧非对称裂纹模型;在基于精确全齿廓的能量法基础上,推导了轮齿双侧裂纹模型的时变啮合刚度计算公式,分析了裂纹形状参数对时变刚度的影响;最后,通过有限元法(Finite element method,FEM)进行了分析验证。结果表明,有限元法和能量法计算的结果基本一致。     

基于选区激光熔化316L不锈钢晶粒生长的仿真分析

目的 针对选区激光熔化成形316L不锈钢的晶粒生长行为难以被观测且观测成本高的问题,预测不同激光功率(P)、扫描间距(h)下选区激光熔化成形316L不锈钢的晶粒类型、尺寸大小及生长角度,探究不同P–h组合对晶粒生长行为的影响规律。方法 基于元胞自动机模型,采用全因子法设计16种P–h组合,从微观尺度模拟不同成形面316L不锈钢的晶粒生长变化情况,并对模拟结果进行数据统计分析。结果 在平行于激光扫描方向的xy平面上,分布着大量晶粒直径小于60 μm的等轴晶;而在垂直于激光扫描方向的xz、yz平面上,晶粒直径大于120 μm的柱状晶分布得更多。随着扫描间距的增大,xz、yz两平面上的平均晶粒尺寸不断减小,而xy平面上的平均晶粒尺寸呈现先增大后减小的趋势。当P=150 W、h=0.18 mm时,xy平面上的平均晶粒尺寸最小,绝大部分晶粒直径小于20 μm,晶粒生长角度均匀分布在0°~90°,没有出现晶粒生长向大角度偏移聚集的现象。结论 不同P–h组合能够通过改变熔池凝固时的冷却速率对选区激光熔化成形316L不锈钢的晶粒生长行为产生显著影响,在较低的激光功率下,适当提高扫描间距能够有效细化晶粒,减少晶粒生长向大角度偏移聚集的现象。     

Meta-inventory

In an Industry 4.0 Factory, physical entities such as humans, machines and materials are digitized into digital twins (DT) with smart IoT (Internet of Things) devices resulting in Cyber-Physical Production Systems (CPPS). Real-time data analytics builds up traceability and visibility, not only in the physical domain but also cyber space. This paper adds a new concept of cyber-physical inventory or simply meta-inventory to Industry 4.0 CPPS. In addition to physical items, their digital twins are considered as part of production inventory. Traceability and visibility enabled by digital twin can significantly reduce complexity and uncertainties (e.g. lead times and variability) while achieving resilience in case of major disturbances. The CPPS factory hedges the risks through meta-inventory without incurring cost for holding inventory digitally. After reflecting upon the developments of production inventory management corresponding to the evolutionary history of manufacturing systems to Industry 4.0, the paper presents the meta-inventory paradigm within a simple Industry 4.0 compliant supply chain. The factory, the supplier, and the transport implement a VMI (vendor-managed inventory) strategy. Two well-known basic EOQ (Economic Order Quantity) and EPQ (Economic Production Quantity or production Lot Sizing) problems are extended to demonstrate and quantify the impacts of using meta-inventory on the supply chain and the member enterprise. The analyses allow us to unfold key perspectives in more complex production and supply chain systems for further research.     

基于考试过程和知识结构的数据挖掘算法研究

为了研究学生在不同阶段对知识点的掌握情况,基于对数据挖掘的理论研究,把知识结构与考试成绩相结合来进行数据研究。以教育测量学为基础,结合数据挖掘的决策树算法,针对原有的C4.5算法提出改进算法,应用试卷中涉及到的知识点的难易程度与知识点种类进行知识结构细化,以便确定单个学生或群体学生对知识点的掌握程度和试卷中各知识点之间的关系。结果显示,改进后算法的计算公式比原计算公式简单实用;根据决策树模型,使用剩余数据对计算公式进行验证,能够更快地得出对程序设计这个知识点的掌握是 影响成绩相对重要的因素。使用测试数据对已创建的决策树进行验证,准确率为90%。最后对决策树进行可视化展示,为学生的学习安排、教师的教学方案及安排等提供有效的参考。     

基于Vinnicombe距离的电力系统低频振荡预警精度研究

随着我国智能电网技术的发展,低频振荡预警已成为电力系统稳定性研究的重要问题.提出一种基于关键特征广域降维数据Vinnicombe距离的电力系统低频振荡幅值预警指标识别方法,该方法首先对PMU采集的原始大数据进行筛选与降维预处理,生成低频振荡幅值预警指标所需的初始特征量矩阵,然后通过对电力系统监控终端节点和各节点之间的区...     

A hybrid genetic algorithm with multiple decoding methods for energy-aware remanufacturing system scheduling problem

Remanufacturing system scheduling is an essential and effective approach to realize the digitization and greening of the remanufacturing industry. However, previous researches on the remanufacturing system scheduling problem mainly consider a single or two production stages and economic objectives. In this paper, by integrating the three core production stages, i.e., disassembly, reprocessing and reassembly together, we study the energy-aware remanufacturing system scheduling problem in which the well-accepted Turn Off and On strategy is also considered. First, a mathematical model aiming at minimizing the total energy consumption (TEC) of the remanufacturing system is established. Then, a hybrid genetic algorithm based on variable neighborhood search (GAVNS) solution method is proposed, given the NP-hard nature of the problem. In GAVNS, each chromosome is encoded by a job sequence and three different decoding methods are specially designed according to the formation of optimization objective TEC. To enhance the algorithm's local search capability, the variable neighborhood search technique is introduced. The feasibility and effectiveness of GAVNS in addressing the energy-aware remanufacturing system scheduling problem is verified through simulation experiments on a set of designed test instances. Experimental results also demonstrate that: (1) the Turn Off and On strategy can effectively reduce TEC of the remanufacturing system, which can reach an energy saving rate of 6.68%; (2) the performance of those decoding methods varies with respect to the problem size; (3) the decoding method based on minimizing the energy consumption of the remanufacturing system (namely DM3) has the best performance among the three decoding methods in most cases; (4) GAVNS is more effective than its four peers, i.e., a variant GAVNS_R, iterated greedy algorithm (IG), extended artificial bee colony algorithm (EABC), discrete invasive weed optimization algorithm (DIWO) in seeking the optimal schedule.