Sensing, modeling and control for laser-based additive manufacturing

Laser-Based Additive Manufacturing (LBAM) is a promising manufacturing technology that can be widely applied to part preparation, surface modification, and Solid Freeform Fabrication (SFF). A large number of parameters govern the LBAM process. These parameters are sensitive to the environmental variations, and they also influence each other. This paper introduces the research work in RCAM on improving the performance of the LBAM process. Metal powder delivery real-time sensing and control is studied to achieve a controllable powder delivery for fabrication of functionally graded material. A closed-loop control system based on infrared image sensing is built for control of the heat input and size of the molten pool in the LBAM process. The closed-loop control results show a great improvement in the geometrical accuracy of the built features. A three-dimensional finite element model is also established to explore the thermal behavior of the molten pool in the closed-loop controlled LBAM process.     

Characterisation of mortar morphology in thin sections by digital image processing

A digital imaging approach was applied to investigate mortar morphology in thin sections; in particular, the binder/aggregate ratio and the grading curve of five mortar bars were attained by digital image processing (DIP), using the Image Pro Plus 4.1 software package. The imaging procedure employed image segmentation, to extract mortar aggregate, and image filtering, to fix grain boundaries. The results show that digital image processing may be considered as an alternative method to mechanical sieving for the characterisation of mortar morphology, as it appears to be quicker and more accurate than the traditional method. However, digital image processing exhibits limits, which are discussed in the text.     

Past and future of software architectural decisions – A systematic mapping study

ContextThe software architecture of a system is the result of a set of architectural decisions. The topic of architectural decisions in software engineering has received significant attention in recent years. However, no systematic overview exists on the state of research on architectural decisions.ObjectiveThe goal of this study is to provide a systematic overview of the state of research on architectural decisions. Such an overview helps researchers reflect on previous research and plan future research. Furthermore, such an overview helps practitioners understand the state of research, and how research results can help practitioners in their architectural decision-making.MethodWe conducted a systematic mapping study, covering studies published between January 2002 and January 2012. We defined six research questions. We queried six reference databases and obtained an initial result set of 28,895 papers. We followed a search and filtering process that resulted in 144 relevant papers.ResultsAfter classifying the 144 relevant papers for each research question, we found that current research focuses on documenting architectural decisions. We found that only several studies describe architectural decisions from the industry. We identified potential future research topics: domain-specific architectural decisions (such as mobile), achieving specific quality attributes (such as reliability or scalability), uncertainty in decision-making, and group architectural decisions. Regarding empirical evaluations of the papers, around half of the papers use systematic empirical evaluation approaches (such as surveys, or case studies). Still, few papers on architectural decisions use experiments.ConclusionOur study confirms the increasing interest in the topic of architectural decisions. This study helps the community reflect on the past ten years of research on architectural decisions. Researchers are offered a number of promising future research directions, while practitioners learn what existing papers offer.     

The influence of grinding technique on the liberation of clinker minerals and cement properties

This paper describes a study of the relationship between the physical, chemical and mineralogical parameters of cement products obtained by different grinding mechanisms namely high pressure grinding rolls (HPGR) and ball milling, and their effects upon the properties of cements prepared from the ground clinker. Samples were prepared as narrow size fractions and also as distribution samples. Characterization parameters were ascertained by using XRF, laser sizing, Blaine and BET surface area and image analysis methods. HPGR grinding resulted in higher degrees of liberation of clinker phases arising from the intergranular breakage along the grain boundaries compared to ball mill grinding. As for service properties, water demand of HPGR products was higher than ball mill products resulting from high micro fissured structure. Despite high liberation of particularly alite mineral in HPGR grinding, the compressive strength of ball mill products was slightly higher than HPGR products for narrow size samples. Finally, particle size distribution effect on strength was more obvious for distribution samples; generally ball milling gave higher strength values.     

Ensemble of multiple instance classifiers for image re-ranking

Text-based image retrieval may perform poorly due to the irrelevant and/or incomplete text surrounding the images in the web pages. In such situations, visual content of the images can be leveraged to improve the image ranking performance. In this paper, we look into this problem of image re-ranking and propose a system that automatically constructs multiple candidate “multi-instance bags (MI-bags)”, which are likely to contain relevant images. These automatically constructed bags are then utilized by ensembles of Multiple Instance Learning (MIL) classifiers and the images are re-ranked according to the final classification responses. Our method is unsupervised in the sense that, the only input to the system is the text query itself, without any user feedback or annotation. The experimental results demonstrate that constructing multiple instance bags based on the retrieval order and utilizing ensembles of MIL classifiers greatly enhance the retrieval performance, achieving on par or better results compared to the state-of-the-art.     

基于最大后验概率的熔融态物料结构的层析图像提取法

以聚合物挤出过程中的熔融态物料为对象，在比较层析图像与反射式光强图像的成像特点基础上，叙述了基于最大后验概率的熔融态物料多特征结构的层析图像提取方法，并介绍了层析图像提取实验的结果，理论与实验表明，该方法能有效地分割熔融态物料，细化熔融态结构,实现对熔融态物料特征结构的提取和测量。     

自动化翻拍图像空间失真复原研究

在自动化翻拍的图像采集过程中,图像中各像素间的空间相互关系会随着采集发生变化,通过对空间失真复原算法的深入研究,利用几何极坐标、中值滤波等方法,提出自动化翻拍图像复原算法。实验结果表明,使用该算法能够消除由图像采集引起的空间畸变失真,提高图像的可识别性,是一种有效的方法。     

基于机器视觉的转辙机缺口检测方法研究

针对现有转辙机缺口检测方法所存在的问题,本文介绍了一种基于机器视觉技术的转辙机缺口检测基本方法及其原理和步骤。文章详细论述了LSD算法的工作原理,同时本文作者对该算法做出了改进。最后将改进的LSD算法应用在转辙机缺口检测当中,结果表明该检测算法具有良好的稳定性和快速性,并且能够很好的解决转辙机缺口检测的问题。