Machine learning for multi-criteria inventory classification applied to intermittent demand

Multi-criteria inventory classification groups inventory items into classes, each of which is managed by a specific re-order policy according to its priority. However, the tasks of inventory classification and control are not carried out jointly if the classification criteria and the classification approach are not robustly established from an inventory-cost perspective. Exhaustive simulations at the single item level of the inventory system would directly solve this issue by searching for the best re-order policy per item, thus achieving the subsequent optimal classification without resorting to any multi-criteria classification method. However, this would be very time-consuming in real settings, where a large number of items need to be managed simultaneously.

In this article, a reduction in simulation effort is achieved by extracting from the population of items a sample on which to perform an exhaustive search of best re-order policies per item; the lowest cost classification of in-sample items is, therefore, achieved. Then, in line with the increasing need for ICT tools in the production management of Industry 4.0 systems, supervised classifiers from the machine learning research field (i.e. support vector machines with a Gaussian kernel and deep neural networks) are trained on these in-sample items to learn to classify the out-of-sample items solely based on the values they show on the features (i.e. classification criteria). The inventory system adopted here is suitable for intermittent demands, but it may also suit non-intermittent demands, thus providing great flexibility. The experimental analysis of two large datasets showed an excellent accuracy, which suggests that machine learning classifiers could be implemented in advanced inventory classification systems.     

Understanding the emergence of redistributed manufacturing: an ambidexterity perspective

Abstract

This paper extends operations strategy theory on efficiency and flexibility trade-offs to the emergent phenomenon of redistributed manufacturing (RDM). The study adopts a multiple-case design including five small and five large pharmaceutical firms. We propose that organizations can gain the efficiency benefits of centralized manufacturing and the flexibility advantages of RDM by building an ambidexterity capability. To build such a capability, large firms can structurally partition their manufacturing and supply management functions, with one sub-unit managing centralized production and the other RDM. Smaller enterprises can build an ambidexterity capability by creating the right organizational context, where multi-skilled workers switch between efficient and flexible tasks. This paper contributes to theory by explaining the emergence of RDM using an organizational ambidexterity lens, laying the groundwork for new theory development in the field. We provide managers with a practical example of how to build an ambidexterity capability to realize flexibility and efficiency advantages.     

Machine gaming in Sydney clubs: characteristics of the supporting resident populations

This research provided background for surveys and interviews in later stages of a 3 part project. It aimed to identify, from secondary research, sociodemographic characteristics which tend to support registered clubs and their machine gaming activities in the Sydney Statistical Division. Using multiple methods including Pearson's Product Moment correlation, Principal Components factor analysis, and stepwise regression, the study profiled Sydney populations which spend highly on gaming machines. The most important sociodemographic predictors of Sydney statistical local areas where per capita gaming machine expenditure is high are large proportions of the adult resident population who were born in Malta, Greece, Lebanon, China, Italy, Vietnam, Yugoslavia, India or the Philippines; have no vocational or tertiary qualifications; or are unemployed.     

车灯反射镜充液拉深液压机的设计

在对车灯反射镜充液拉深工艺数值模拟优化及实验的基础上,研究设计车灯反射镜充液拉深液压机.利用液压提供凸模拉深力、压边力以及凹模容腔压力;通过PLC(可编程控制器)来控制凸模运动、压边力和凹模容腔压力按照规定的曲线实时的变化.结果表明,充液拉深液压机具有体积小、易操作、高精度和高效率等优点.     

中国雕版印刷术向日本传播的途径

印刷术是我国历史上著名的“四大发明”之一，它对人类文明的发展作出了杰出的贡献。本文从商船的往来与汉籍的输入，两国间的文化往来，中国刻工到日本亲传身授，讨论了中国雕版印刷术向日本传播的途径     

基于浊度检测的洗衣机废水自动回收装置的设计

为回收再利用洗衣机在洗涤过程中所排的废水，设计了洗衣机废水自动回收装置，装置由浊度传感器、液位开关、水用电磁阀、潜水泵、水箱等构成。该装置可自动识别废水污浊程度，从而决定是否回收储存起来。经简易处理的回收废水类似于q-水，可用于马桶及地面的冲洗，这对于水资源的节约利用、绿色住宅建筑设施设计具有一定的参考意义，同时也具有一定的经济效益。     

论清代武英殿聚珍版印书之鉴定

武英殿聚珍版书的出版，是清代官方参与的历史上规模最大的一次木活字印书工程，当时曾引起朝野震动。无论其所印书的资料价值，还是活字印刷本身的意义，影响都是深远的。本文论述了清代武英殿聚珍版印书的来历、刊刻情况、版刻特点及相关问题，并从版本鉴定角度提出了考证武英殿木活字印书的理论和实践依据。     

再生核支持向量机在非线性系统中的应用

为了提高非线性系统辨识的精度,提出用Walsh函数作为空间V0的尺度函数,构造出L2(R)空间的正交规范序列。结合小波多分辨分析,将Hilbert空间分为一系列子空间,并由可分Hilbert空间与L2(R)的等价性,利用内积同构的线性算子,可以把V0子空间的尺度函数折算为Hilbert空间的子空间V0的尺度函数,构造出新的Walsh序列再生核。通过仿真实验,与传统的RBF核函数、高斯核函数等比较,该尺度再生核函数具有更高的辨识精度,较少支持向量数目,充分体现了支持向量机较好的推广性能。     

浅谈机械制造工艺学之教学

机械制造工艺学课是机械类专业的专业基础课,具有较强的实践性。教师应根据这门课的特点和要求,钻研教材内容,合理安排教学,激发学生的学习积极性,提高教学质量。     

QA95—630型钢坯剪切机焊接机身的有限元分析

建立了ＱＡ９５－６３０型钢坯剪切机焊接机身的力学模型，利用有限元分析软件Ｓｕｐｅｒ－ＳＡＰ对机身进行网格划分和有限元分析，输出应力数表、位移数表、等应力线图和等位移线图等结果，以帮助设计人员对机身进行校核、改进或重新设计。