FMS生产计划的柔性研究

通过对影响FMS利用率的因素进行分析,本文提出了FMS生产计划的柔性的概念,建立了柔性的指标体系,并对柔性的归一化和综合评判等问题进行了研究.需要特别指出的是,本文首次将系统可靠性理论引入FMS生产计划,并根据其不同运行阶段系统可靠性的变化情况,对制定生产计划提出了建议.     

Nanostructure evolution studies of bulk polymer materials with synchrotron radiation: progress in method development

The prospects of a modern analysis of nanostructure evolution during the processing of polymer materials by means of scattering from synchrotron radiation are demonstrated in examples. The beam sources have gained stability, shortages are located in beamline setups and in method development for the quantitative analysis of voluminous data sets.By using the proposed multidimensional chord distribution function (CDF) analysis method, nanostructure information from small-angle X-ray scattering (SAXS) data are extracted and visualised. The method can be automated if the beamline setup is able to deliver a full data set with simple constraints. In this case even a simultaneous data evaluation is possible (while one pattern is accumulated, the previous one is analysed). The advantages of the method are demonstrated in a study of the straining of a thermoplastic elastomer. The possibilities of an automated analysis are demonstrated in an investigation of the crystallisation behaviour of high-pressure injection-moulded polyethylene (HPIM-PE). The achievable results of nanostructure analysis of polymer materials are discussed. It is shown that the time-resolved SAXS of polymer materials studied during a transformation and analysed by the CDF method is not just a powerful tool to investigate the relationship between structure and properties of materials; the information that can be gained concerning the processes that control nanostructure evolution is equally important. In the future the enlightenment of such relationships may help to tailor polymer materials with respect to their properties and, beyond that, to improve assessments concerning their aging.     

Learning attention-based strategies to cooperate for multi-agent path finding

Multi-agent path finding (MAPF) is a challenging multi-agent systems problem where all agents are required to effectively reach their goals concurrently with not colliding with each other and avoiding obstacles. In MAPF, it is a challenge to effectively express the observation of agents, utilize historical information, and effectively communicate with neighbor agents. To tackle these issues, in this work, we proposed a well-designed model that utilizes the local states of nearby agents and outputs an optimal action for each agent to execute. We build the local observation encoder by using residual attention CNN to extract local observations and use the Transformer architecture to build an interaction layer to combine local observations of agents. With the purpose of overcoming the deficiency of success rate, we also designed a new evaluation index, namely extra time rate (ETR). The experimental results show that our model is superior to most previous models in terms of success rate and ETR. In addition, we also completed the ablation study on the model, and the effectiveness of each component of the model was proved.     

PRM蚁群融合算法的AGV路径规划研究

针对AGV运货时需一次性取多件货物的路径规划问题,提出一种PRM算法与蚁群算法相结合的融合算法,将问题拆分为路径的选择与TSP问题分布解决,即先利用PRM算法进行AGV路径规划,再利用蚁群算法决策出取货顺序,生成总的路径。最后采用matlab进行仿真实验,并与A*算法进行对比,结果证明了PRM蚁群融合算法比A*算法得出的路径更短、效率更高。     

空间机器人组装超大型结构的动力学分析北大核心CSCD

超大型航天结构具有超大柔性、超低固有频率的特点,空间机器人在轨组装时应尽可能避免激起超大型结构的柔性振动.空间机器人组装超大型结构模块的过程分成抓捕阶段、位姿调整与稳定阶段、安装阶段和爬行阶段.通过对安装阶段的动力学与控制研究,提出共线安装的轨迹规划方法,有效避免了柔性结构振动.首先,采用自然坐标法和绝对节点坐标法建立主结构-空间机器人-待组装结构的在轨组装系统动力学模型.然后,将共线安装的要求转化为空间机器人的轨迹规划约束,要求空间机器人质心到主结构/待组装结构的距离保持不变,实现共线安装的轨迹规划.数值仿真表明:提出的组装方法在组装过程中可有效避免超大型结构的横向运动,降低夹持力矩.最后,分析了系统参数对组装过程动力学响应的影响,为超大型航天器的在轨组装提供了参考.     

基于工艺形态学理论的工艺数据库设计

工艺形态学是一种新的工艺方法分类理论,文章阐述了工艺形态学理论的基本概念,应用工艺形态学理论对各种工艺方法进行了系统化的分析与描述,建立了相应的工艺方法分类原则和分类代码,在此基础上,建立了工艺数据库。     

并行工程计划问题的模糊网络分析方法

基于网络流模型,本文提出了确定模糊网络关键路线的参数线性规划方法,并给出了反映决策者偏好信息的模糊网络关键路线和工程模糊完工期的隶属函数形式,从而得到了模糊网络关键路线性质的更全面结果。最后,针对模糊环境下的并行工程计划问题,给出了模糊网络的分析方法。     

批量制造业模糊交货期准时化生产计划方法

通过建立批量制造业模糊交货期下的准时化生产计划模型,将隶属度函数引入到生产计划问题中,从而拓宽了准时化生产计划问题的研究范围,并为实际生产计划的编制提供了一种有效途径。     

基于实例的工艺知识获取模型

介绍了耦合神经网络的工艺设计实例推理系统的实现方法论,提出了一种基于神经网络的工艺设计实例推理索引模型．与现存大多数实例推理系统不同,该方法用神经网络实现实例的动态分类和索引．实例层次分类的三层结构和基于特征的聚类模板概念,为实现基于符号处理的实例推理求解模式向基于神经计算的模式识别求解模式映射提供了条件．提出了基于实例的工艺知识获取模型,采用新实例的入库操作实现工艺知识的隐式获取,从而使知识获取得以简化．神经网络的自适应、自学习能力将减少系统的日常维护工作．基于实例的系统可望解决知识获取的难题．     

基于任务的产品工艺设计过程管理

在分析产品工艺设计流程现状的基础上,研究了现有ＣＡＰＰ系统中工艺过程设计和过程管理,提出了任务驱动型的ＣＡＰＰ思想．认为工艺设计的过程本质上是对任务完成过程的集合,通过对任务的生成、监控、设计、提交、签审、发放,正好控制工艺设计的流程,并在ＣＡＰＰ系统开发中进行了成功的尝试,为工艺设计的管理提供了一种可行的方法．