基于DEM的磨粉机皮磨研磨仿真及参数优化

目的 探究辊式磨粉机皮磨系统工作参数对工艺效果的影响,并进行1B磨制粉过程磨辊工作参数优化。方法 通过Dem离散元软件对磨辊研磨过程进行模拟分析,以齿角、前角、轧距、落料点间距4个因素为变量对取粉率和功耗的影响进行分析,并采用正交试验和矩阵分析法对数值模拟结果进行综合评定。结果 得出1B磨制粉工序中最优参数组合方案为齿角γ=85°,前角α=25°,轧距d=1.5 mm,落料点间距b=0 mm。结论 本文对磨辊研磨过程的仿真分析提供了参考方法,并对辊式磨粉机工作参数的优化设置具有一定的指导意义。     

考虑资源需求差异的印包设备网络协同制造资源匹配方法

目的 包装印刷装备行业存在制造资源分散、产业协同不足和效率低等问题,针对网络协同制造中的制造资源匹配问题提出一种有效方法。方法 从不同子任务资源需求差异视角出发,构建基于TQCS制造资源评价指标体系及制造任务约束体系,通过层次分析法计算不同子任务的权重,以资源与任务的匹配度最大为目标函数,提出基于莱维飞行–遗传算法的网络协同制造资源匹配方法。结果 改进的资源匹配方法相较于传统方法,能够得到成本更低、时间更短的方案,并且改进的遗传算法的寻优能力更高。结论 相较于传统方法,改进的制造资源匹配方法的目标函数更合理、权重取值更客观、寻优能力更好,能够得到更为合理的制造资源匹配方案。     

考虑绿色制造和外协方式的多周期订单安排模型研究

针对多品种小批量企业的多周期订单安排问题,提出一种以绿色制造和外协方式为研究视角的优化方法模型。综合考虑企业的设备操作成本、人工成本、库存成本、外协成本等竞争性指标以及设备能耗、噪声等绿色性指标,构建考虑绿色制造和外协方式的多周期订单安排模型,并基于遗传算法设计了模型的求解方法;最后以一个机加工企业的四周期订单需求为例,应用该方法给出了各阶段订单的安排结果以及企业制造资源的分配方案,既验证了模型和算法的有效性,又在绿色制造和外协方式的研究视角上为多周期订单的安排方式提供理论方法支持。     

差分拉曼光谱对眼药水塑料瓶的分类研究

目的 建立一种便捷精准无损检验眼药水塑料瓶的方法。方法 使用便携式差分拉曼光谱仪检测33个塑料眼药水瓶，根据获得的各样品数据，包括差分拉曼光谱图的峰位、峰数等对样品进行成分分析，并通过统计分析软件“统计产品与服务解决方案”(SPSS 26.0)对样品进行K均值聚类，利用轮廓系数优选K值。对分类结果中样品数目较多的一类样品进行填料分析，利用皮尔逊相关系数验证分析结果的准确性。结果 样品主要成分为聚乙烯和聚对苯二甲酸乙二醇酯，利用轮廓系数优选K值为2，K均值聚类算法对样品的分类结果与成分分析结果能够相互印证。以聚乙烯类样品为例，根据填料不同可将其分为7组。皮尔逊相关系数计算结果能够证明上述分类分组结果可靠。结论 利用该方法能够准确无损地检测眼药水塑料瓶，并对其进行分类研究。     

云制造环境下板材余料资源的服务匹配方法

在云制造环境下,针对中小型企业加工后的板材余料造成极大资源浪费的问题,提出了一种基于语义相似度算法同时融入QoS(quality of service,服务质量)信息的分层次资源描述模型.首先,建立板材余料和板材加工设备资源的本体模型;然后,基于语义相似度算法对板材余料和板材加工设备的各个属性参数进行匹配,得到初选服务...     

基于改进遗传算法的导向辊生产调度方法研究

目的 研究导向辊生产车间中的调度优化问题,有利于缩短工件的完工时间,提高产线生产效率。方法 以某导向辊生产车间为研究对象,以最小化最大完工时间为目标建立数学模型。针对该导向辊生产车间的实际工况,提出一种改进的遗传算法进行求解。通过对10种不同尺寸的导向辊进行生产调度,分别采用改进的遗传算法和传统遗传算法进行试验分析。结果 改进的遗传算法相比传统遗传算法寻优能力更高,工件的完工时间从139 min缩短为113 min,缩短了18.7%左右,生成了完工时间为113 min的生产调度甘特图。结论 与传统遗传算法相比,改进的遗传算法在导向辊生产调度优化中具有更高的全局优化能力和寻优精度。     

基于混合型模糊指标的云制造资源选择决策方法研究

针对云资源优选决策过程中存在定性指标模糊性,以及定量指标以区间性度量为代表的决策难点问题,提出了一种不确定性环境下基于OWA算子的混合型多指标云制造资源优势度决策方法。该方法首先运用标度法将不可量化的模糊性定性指标转化为区间数定量指标;其次利用基于相对优势度的区间数排序,结合OWA算子对云服务的优势度进行集结,得到云制造资源的综合优势度,给出云制造资源集合的优先排序,从而为用户选择出最需要的制造服务资源。通过在数控机床设备优选过程中的应用,验证了该方法的可行性和实用性。     

基于多色蚁群的柔性测试系统测试资源匹配

柔性测试系统是测试需求导向的客户化定制系统,其组建和运行的前提是如何根据具体的测试任务需求匹配出能够完成测试任务的最优测试资源集合.本文首先在面向信号描述测试任务需求和测试资源能力的基础上,求得测试任务的信号完整特征集合,然后对匹配问题的传统二分图模型进行扩展,给出测试资源匹配的多色加权二分图描述模型.结合蚁群算法,提出了柔性测试系统资源匹配的多色蚁群算法,最后通过实际的资源匹配实例说明了模型的有效性和算法的优越性.     

包装机械手轨迹规划和控制系统设计

目的 针对常见分区域图像修复算法中,对于待修复目标的分离效果不佳而导致的修复效果较差等问题,提出一种基于改进K均值聚类的图像修复方案。方法 首先将待分割图像转换到CIELab颜色空间,对a,b分量进行聚类运算,得到K个聚类中心,通过改变聚类迭代次数,得到粗分割结果;然后采用数学形态学对分割结果进行细化处理,精确分离得到目标对象和背景;最后,采用Reinhard算法对目标和背景分别进行色彩迁移,得到图像修复结果。结果 所提模型中的区域分割算法,其分离效果均优于经典的分水岭算法、最大类间方差法和基于Lab通道的最大类间方差算法,采用Reinhard色彩迁移算法图像修复结果比较接近理想修复效果。结论 由最终结果可知,提出修复法的整体效果较为理想,且优于传统的分区域图像修复算法,可为生产实践提供必要的理论依据。     

柔性电子卷到卷制造中导向辊牵引特性的研究进展

目的 探索柔性电子卷到卷制造过程中薄膜经过导向辊时发生皱褶、划伤和滑移等问题的原因,以期提高柔性电子薄膜的制造精度和效率。方法 总结近年来导向辊与薄膜之间夹带气体流场特性和薄膜对导向辊牵引特性的研究进展,提出进一步需要研究的要点。结果 薄膜与导向辊之间夹带气体的流场特性和薄膜对导向辊的牵引特性是柔性电子薄膜稳定传输的主要影响因素,其对提高柔性电子产品加工精度具有重要作用。结论 有效控制导向辊与薄膜之间的夹带气体流场特性和薄膜对导向辊的牵引特性有助于提高薄膜传输的精度,从而保障卷到卷制造柔性电子产品的生产质量。     

Prediction of manufacturing resource requirements from customer demands in mass-customisation production

Mass-customisation production is a new manufacturing approach to produce customised products based on requirements of individual customers while maintaining the quality and efficiency of mass production. Due to the large variations of customised products, the traditional methods for planning manufacturing resources based on volumes of mass produced products are not effective for mass-customization production. In this research, a new manufacturing resource planning method is developed by studying the relations between customer demands and manufacturing resource requirements based on the true data from a mass-customisation production company—Gienow Windows and Doors. In this research, first the relations between the customer demands, modeled by sales data at levels of whole company, sales branches, and markets in sales branches, and the manufacturing resource requirements, modeled by labour requirements of different production lines are studied. Fuzzy pattern clustering method is employed for classifying the resource requirements into patterns to further understand the relations. Based on this study, linear regression and neural network are used to model the linear and non-linear relations between customer demands and manufacturing resource requirements, and to predict the manufacturing resource requirements from available customer demands. A manufacturing resource planning system was developed to demonstrate the effectiveness of this introduced approach.     

Cloud manufacturing resources fuzzy classification based on genetic simulated annealing algorithm

To solve the problem of fuzzy classification of manufacturing resources in a cloud manufacturing environment, a hybrid algorithm based on genetic algorithm (GA), simulated annealing (SA) and fuzzy C-means clustering algorithm (FCM) is proposed. In this hybrid algorithm, classification is based on the processing feature and attributes of the manufacturing resource; the inner and outer layers of the nested loops are solving it, GA obtains the best classification number in the outer layer; the fitness function is constructed by fuzzy clustering algorithm (FCM), carrying out the selection, crossover and mutation operation and SA cooling operation. The final classification results are obtained in the inner layer. Using the hybrid algorithm to solve 45 kinds of manufacturing resources, the optimal classification number is 9 and the corresponding classification results are obtained, proving that the algorithm is effective.     

Collaboration of large equipment complete service under cloud manufacturing mode

This paper focuses on the need of the large equipment manufacturing industry to adapt collaborative operation to transform the industry to cloud manufacturing services and to solve the new problem of federal resources coordination in complete service operation. We systematically study federal resources cooperation under cloud manufacturing mode to complete a large complex project. The primary research contents are divided into four points. First, a system structure of cloud manufacturing service mode is presented. Second, a synergy logic framework from the global system perspective is designed based on generalised partial global planning. Third, a multi-level system coordination mechanism is established by integrating various methods, including the bidding game mechanism for enterprise external resources, the planning control mechanisms for enterprise internal resource and the global collaborative optimisation mechanism for enterprise global federal resources. Finally, a cloud manufacturing service platform for a typical enterprise is developed by combining theory with practice. The results can realise collaborative management in resource selection and configuration, service process planning control and service information feedback in cloud manufacturing service, as well as achieve overall synergy effect for the system.     

Cloud manufacturing service composition based on QoS with geo-perspective transportation using an improved Artificial Bee Colony optimisation algorithm

Cloud Manufacturing (CMfg) ambitions to create dedicated manufacturing clouds (i.e. virtual enterprises) for complex manufacturing demands through the association of various service providers’ resources and capabilities. In order to insure a dedicated manufacturing cloud to match the level of customer’s requirements, the cloud service selection and composition appear to be a decisive process. This study takes common aspects of cloud services into consideration such as quality of service (QoS) parameters but extend the scope to the physical location of the manufacturing resources. Unlike the classic service composition, manufacturing brings additional constraints. Consequently, we propose a method based on QoS evaluation along with the geo-perspective correlation from one cloud service to another for transportation impact analysis. We also insure the veracity of the manufacturing time evaluation by resource availability overtime. Since the composition is an exhaustive process in terms of computational time consumption, the proposed method is optimised through an adapted Artificial Bee Colony (ABC) algorithm based on initialisation enhancement. Finally, the efficiency and precision of our method are discussed furthermore in the experiments chapter.     

云制造中产品个性化定制研究综述

消费者对个性化产品购买需求的增加,对制造企业的定制生产能力提出了越来越高的要求。而现有制造企业存在的信息化水平不高、制造资源不足等问题,严重影响了制造企业向个性化生产转型的进程。针对上述情况,结合云制造概念及技术提出了云制造中产品个性化定制生产模式。为了更加深入地研究云制造中产品个性化定制的运行模式及阐述云制造平台在定制生产过程中的主要作用,从体系架构、服务流程、关键技术等方面对相关研究进行了回顾和介绍,然后列举了个性化定制生产模式在汽车、软件和服装行业的应用,最后对研究趋势进行了展望。分析表明,云制造平台汇聚全球的制造资源为个性化定制服务,能够有效解决单一制造企业实施个性化定制过程中面临的一系列困难,做到以较低的成本快速高效地满足消费者日益多样化、个性化的需求。     

Incorporating production concerns in conceptual product design

This paper presents a set of analytical tools that can be used to alter a product's design, manufacturing processes and assembly techniques to increase production rate. The analytical tools obtain these improvements by simultaneously considering each part's geometric attributes and complexity, vendor selection, material and process selection, and capacity planning at the conceptual stage of the product realization process. The method detects and then avoids heavily used resources by indicating which combination of one or more of its components' geometric attributes, manufacturing processes, material and assembly methods should be altered. The method is illustrated with the analysis of an overhead projector. It is shown that production rate can be doubled by either making small changes to a component's geometric attributes or by selecting different manufacturing processes. Neither of these changes affects the functionality of the product.     

Dynamic Intelligent Supply-Demand Adaptation Model Towards Intelligent Cloud Manufacturing

As a new mode and means of smart manufacturing, smart cloud manufacturing (SCM) faces great challenges in massive supply and demand, dynamic resource collaboration and intelligent adaptation. To address the problem, this paper proposes an SCM-oriented dynamic supply-demand (S-D) intelligent adaptation model for massive manufacturing services. In this model, a collaborative network model is established based on the properties of both the supply-demand and their relationships; in addition, an algorithm based on deep graph clustering (DGC) and aligned sampling (AS) is used to divide and conquer the large adaptation domain to solve the problem of the slow computational speed caused by the high complexity of spatiotemporal search in the collaborative network model. At the same time, an intelligent supply-demand adaptation method driven by the quality of service (QoS) is established, in which the experiences of adaptation are shared among adaptation subdomains through deep reinforcement learning (DRL) powered by a transfer mechanism to improve the poor adaptation results caused by dynamic uncertainty. The results show that the model and the solution proposed in this paper can perform collaborative and intelligent supply-demand adaptation for the massive and dynamic resources in SCM through autonomous learning and can effectively perform global supply-demand matching and optimal resource allocation.