A Design Method with Knowledge Modeling for Complex Product Based on Ontology

Innovation design for complex products is a difficult issue in the military manufacturing industry. Ontology may provide a feasible way to rebuild the design process for complex products via sharing and reusing of design knowledge. In this paper, a design method used in the innovation design process of the complex products with knowledge modeling is proposed. Knowledge modeling is realized through ontology construction by combining the cycling evolutional theory of constructing ontology and OWL (Ontology Web Language)-based knowledge representation. As a case study, the satellite is selected as one of the complex products. The application domain of the satellite ontology is analyzed. According to the analysis result, the knowledge structure of satellite ontology is put forward based on OWL. The application of satellite product design shows that the method can effectively organize and reuse the knowledge resources in the innovation design of complex product and help companies to create more competitive products based on the existing knowledge and experience.

Predicting Model for Complex Production Process Based on Dynamic Neural Network

Based on the comparison of several methods of time series predicting, this paper points out that it is necessary to use dynamic neural network in modeling of complex production process. Because self feedback and mutual feedback are adopted among nodes at the same layer in Elman network, it has stronger ability of dynamic approximation, and can describe any non linear dynamic system. After the structure and mathematical description being given, dynamic back propagation (BP) algorithm of training weights of Elman neural network is deduced. At last, the network is used to predict ash content of black amber in jigging production process. The results show that this neural network is powerful in predicting and suitable for modeling, predicting, and controling of complex production process.

A method of manufacturing process modeling based on activity network for large-sized and complex products

Simulation technique is an efficient approach to realize the planning and scheduling of manufacturing process of products. An appropriate and efficient manufacturing process model is the basis and key of manufacturing process simulation. By analyzing the features of large-sized and complex products, a method of manufacturing process modeling based on activity network is presented and a mapping algorithm of translating BOM/BOP into the manufacturing process model is designed in detail.

Product Data Model for Performance-driven Design

When designing large-sized complex machinery products, the design focus is always on the overall per- formance; however, there exist no design theory and method based on performance driven. In view of the defi- ciency of the existing design theory, according to the performance features of complex mechanical products, the performance indices are introduced into the traditional design theory of ＂Requirement-Function-Structure＂ to construct a new five-domain design theory of ＂Client Requirement-Function-Performance-Structure-Design Parameter＂. To support design practice based on this new theory, a product data model is established by using per- formance indices and the mapping relationship between them and the other four domains. When the product data model is applied to high-speed train design and combining the existing research result and relevant standards, the corresponding data model and its structure involving five domains of high-speed trains are established, which can provide technical support for studying the relationships between typical performance indices and design parame- ters and the fast achievement of a high-speed train scheme design. The five domains provide a reference for the design specification and evaluation criteria of high speed train and a new idea for the train＇s parameter design.

The Reconstruction Technique of Multi-Product Production and MINLP Mathematical Modelling

Low efficiency, negative impacts on the environment and non-profitable operations are the main shortcomings of out-dated industrial processes. Such systems can be reconstructed and improved in the direction of multi-product operations. The study of this article focuses on the development of a method for multi-product operations by reconstructing out-dated industrial processes. This article contains the theory of a developed method that enables the updating of existing process units and integrated systems on the basis of reconstruction scenarios and pathways. The goals of the set out method are: 1) to maintain the existing process units and chemical plants to a greater extent, 2) to enable the potential for finding new process alternatives and technological solutions, 3) to provide a streamlined operation for all subsystems and total systems, 4) to promote environmental and social responsibilities, and 5) to apply the concept of the presented reconstruction method to non-profitable industrial processes. In regard to multi-product operations, a conceptual model is a suitable tool for the reconstruction of industrial processes. It connects several software tools and so enables quick decision-making between process alternatives. A reconstruction method provides foresight into the possible improvements to existing industrial processes. In comparison with the indirect synthesis of DME (simple reconstruction pathway), the lower operating costs from the direct synthesis of DME (complex reconstruction pathway) were confirmed.

重复压裂裂缝系统产能对比与分析

单井重复压裂的裂缝生成模式可以分为两种形式,包括在井筒处形成新的转向裂缝以及在原有裂缝的基础上形成扩充缝。如何评价重复压裂后不同形式裂缝系统下油气井的产能,对优化重复压裂施工方案至关重要。以重复压裂产生的两种不同复杂裂缝系统为研究对象,利用嵌入式离散裂缝方法建立数值模型,开展重复压裂后转向型和扩充型裂缝系统的生产规律研究,明确不同裂缝系统对井产能的影响。研究发现:储层及裂缝参数会在不同程度上影响重复压裂后井的产能,且对扩充型裂缝系统的影响程度始终大于转向型裂缝系统。考虑储层基质渗透率各向异性,正交于初始裂缝延伸方向的基质渗透率越大,重复压裂后增产效果越好,并且扩充型裂缝系统累计产量升高更显著。重复压裂裂缝与初始裂缝越趋向于正交,重复压裂后增产效果越明显,扩充型裂缝系统的增产率高于转向型裂缝系统。重复压裂裂缝渗透率和重复压裂裂缝长度均与重复压裂井产能提升呈现正相关,且扩充型裂缝系统的累计产量增大趋势更显著。结果表明,扩充型裂缝系统能更加有效地提高重复压裂井产能,为重复压裂增产机理与矿场应用结合提供理论指导。

基于复杂网络的产品族造型意象耦合网络模型构建方法

目的拓展产品族多意象设计相关知识的获取途径,提升产品族造型创新设计的能效。方法基于产品族造型意象耦合特性,引入复杂网络中的多层网络概念,利用造型特征间的多意象表达关系,构建了产品族造型意象耦合网络模型。利用节点敏感性与中心性分析产品族造型意象耦合网络,识别各造型特征节点属性类型以作为模型析出知识。结合产品族设计的特点,总结归纳适用于产品族设计的各造型特征节点类型并制定其类型运用规则,以辅助设计师进行产品族造型创新设计。结果以马自达汽车前脸造型设计为例,构建了马自达汽车前脸造型意象耦合网络模型,析出了产品族相关设计知识并运用于汽车前脸设计。结论产品族造型意象耦合网络模型丰富了产品族多意象设计相关知识的获取途径,可用于辅助产品族设计,提升设计能效。

基于知识的复杂产品装配工艺快速编制方法

针对复杂产品装配工艺设计过程中存在的编制效率低、质量波动大、自动化和智能化程度低等问题,提出一种面向语义的知识实例检索和复用的装配工艺快速编制方法。分析复杂产品装配工艺业务流程,建立基于知识检索层和知识实例层的双层装配工艺知识模型,从内容、类型、功能及应用方向对知识进行分类。在此基础上,针对已有的知识实例,提出基于Sentence-BERT句向量模型的工艺文档语义分析方法,结合余弦相似度算法给出了工艺知识的语义检索方法,实现知识在装配工艺设计流程中的快速复用。以某航天产品为例,开发航天产品装配工艺快速设计管理系统,构建装配工艺知识库,并在某制造企业上线运行,验证所提方法的可行性,使工艺编制效率大幅提升。

内部价值链视角下复杂产品变更成本预测模型

在持续进步的制造技术环境和复杂多变的市场环境下,以渐进创新为目标的复杂产品设计变更活动高频多发。为有效预测受变更传播影响的生产制造成本,提高设计变更决策的效益性和准确性,从企业内部价值链视角出发,提出基于复杂网络方法的变更成本预测模型。基于负载容量模型对变更传播进行表达,构建设计特征变更传播分析模型;采用改进的灰色关联度、关联分析方法对全局权重进行计算;基于变更传播影响下的量化设计特征值,建立基于特征映射的变更成本预测模型。最后,以G公司某型永磁同步变频冷水机组为案例,验证了所提方法的可行性和有效性。

Top-level modeling theory of multi-discipline virtual prototype

Multi-disciplinary virtual prototypes of complex products are increasingly and widely used in modern advanced manufactur- ing. How to effectively address the problems of unified modeling, composition and reuse based on the multi-disciplinary heteroge- neous models has brought great challenges to the modeling and simulation （M＆S） science and technology. This paper presents a top-level modeling theory based on the meta modeling framework （M2F） of the COllaborative SIMulation （COSlM） theory of virtual prototyping to solve the problems. Firstly the fundamental prin- ciples of the top-level modeling theory are decribed to expound the premise, assumptions, basic conventions and special require- ments in the description of complex heterogeneous systems. Next the formalized definitions for each factor in top level modeling are proposed and the hierarchical nature of them is illustrated. After demonstrating that they are self-closing, this paper divides the top- level modeling into two views, static structural graph and dynamic behavioral graph. Finally, a case study is discussed to demon- strate the feasibility of the theory.

A Collaborative Platform for Complex Product Development Based on Multi-Domain Unified Modeling and Simulation

In order to intensify market competition, manufacturing enterprises must improve their product innovation capability. It is difficult to integrate the system modeling, simulation and collaborative process management in complex product development. A collaborative platform for complex product development based on multi-domain unified modeling and simulation is proposed in this paper. The architecture of the platform is firstly stated. The idea and realization of three key technologies, i.e. multi-domain modeling and simulation for complex product, knowledge management for product design and simulation, multi-domain collaborative mechanism, are emphasized. Finally, an industry case is given. The demonstration of the system shows that integration architecture is the effective infrastructure for multi-domain collaborative product development.

Research on Software Production Support Structure

Firstly, it is found that process design is necessary for software process improvement after analyzing its complexity. Then, research methods and concepts framework are put forward, and the research content is also provided. The find-ings of research, including propositions of complexity of software process, the work program of complexity of software process improvement, software enterprise model and software production support structure are clarified. Finally, the demonstration, including mindbugs (cognitive barriers) in software process and the knowledge integration support structure of quality software production, is illustrated with case study. It is concluded that the research is useful for both software production and knowledge economy in the future.

考虑情绪的混流装配系统产品质量研究

针对操作者情绪状态影响生产系统产品质量的问题,以最大化装配系统流通合格率(RTY)为目标,考虑选择复杂度与操作者情绪建立了混流装配系统产品质量优化模型,并使用改进量子遗传算法进行求解。采用分段式编码有效应对连续变量和离散变量,并使用基于禁忌搜索的染色体变异加强了算法的全局搜索能力。通过算例证明了模型的有效性和算法的改进效果,结果表明操作者情绪状态对装配系统的流通合格率有着较大影响。考虑情绪因素,能够通过优化操作者的情绪类型与唤醒度来提高装配系统流通合格率,在复杂度优化的基础上进一步改善装配系统的产品质量。

基于实例推理的复杂产品设计协同研究

高效、高质量确定复杂产品初步设计模型是缩短产品研发周期的关键,本文提出了一种基于改进皮尔森相似度实例推理的复杂产品设计协同方法。基于复杂产品多学科知识及产品单体库,构建了复杂产品多领域模型。根据复杂产品需求模型的性能指标,采用基于改进皮尔森相似度的实例推理,从多领域模型实例库中筛选复杂产品初步设计模型。为减少产品试样的“盲目性”,引入仿真推演与协同评价以获得初步设计决策。以平尾控制模拟系统为例,验证了所提方法的有效性,有助于缩短复杂产品研发周期。

MBSE应用于系统研发的效能分析

基于模型的系统工程(MBSE)是当前系统工程发展的热点方向。然而,将MBSE应用于系统研发的实际效果有时不及预期,文中针对该问题展开分析。首先,建立了一种MBSE的效能分析模型。基于该模型,在得益方面辨析了应用MBSE的期望得益与实际得益的概念和区别,分析了影响实际得益的系统复杂度和瓶颈问题等因素;在代价方面分析了应用MBSE的建模成本、学习成本、试错成本、过度应用成本。随后,基于效能分析模型解释了应用MBSE未达到预期效能的几种典型情况。最后,基于得益最大化和代价最小化原则,提出了MBSE应用于系统研发的优化建议,并对MBSE的试点和推广提供参考意见。

复杂人工裂缝产状页岩气藏多段压裂水平井产能评价

基于页岩气多重运移机制理论,针对页岩储层压裂裂缝呈现复杂形状和非均匀分布的实际情况,建立耦合了两类孔隙表观渗透率的页岩表观渗透率统一模型,另外,运用实空间源汇函数理论和压降叠加原理,建立了气藏—裂缝—井筒耦合渗流模型。模拟分析了页岩气微观渗流、裂缝形状和裂缝非均匀分布对产能的影响,结果表明:微观渗流对页岩气井产量的影响不可忽视,在生产初期考虑微观渗流的日产气量比不考虑微观渗流的日产气量高了20.3%;复杂形状裂缝的产能比理想矩形裂缝的产能要低,其中星形裂缝的产能最低;裂缝的非均匀分布会影响水平井的产能,需选择最优布缝方式。研究模型综合考虑了页岩气的微观渗流机理和实际压裂裂缝情况,为页岩气藏压裂水平井产能研究提供了参考。

基于模型和数据驱动的复杂重型装备管理系统设计

复杂重型装备的体量大、质量大、结构复杂等特点导致其设计、制造、交付、运维等环节具有跨组织、跨学科、跨行业、知识/技术密集的特点,为设计与管理带来很大的困难。本文在复杂重型装备行业制造现状与发展趋势的基础上,针对复杂重型装备的订单式定制生产,完成了基于数据驱动的复杂重型装备管理系统构建。该系统为分析双重驱动下的复杂重型装备制造企业的战略管控综合分析奠定了良好的基础。

基于数字孪生的复杂机电产品线缆装配工艺模型动态构建方法

针对目前以理想数据制定出的线缆装配工艺文件不能很好地满足实际装配需要以及制定好的装配路径与实际装配路径存在一定偏差等问题,提出一种基于数字孪生的复杂机电产品线缆装配工艺模型动态构建方法。采用同步定位与地图构建方法对线缆装配过程中的零部件特征进行地图构建和线缆空间定位,引入随机有限集描述同步定位和地图构建问题,并采用高斯混合概率假设密度进行地图零部件特征信息的预测与更新;同时采用平方根转换无味卡尔曼滤波器和单特征策略对线缆装配路径进行位姿估计,以完成线缆装配工艺模型的动态构建。最后将所提方法应用于实例分析,验证了方法的可行性。

复杂生产过程工况分类及预测模型研究——以青霉素生产过程为例

为实现青霉素生产过程的有效控制和管理,针对生产过程中青霉素浓度无法实时监测的问题,提出了基于机器学习算法的两种工况分类方法及其相应的预测模型。首先,以青霉素生产过程中影响青霉素浓度的因素作为参数指标,分别采用K-Means、ISODATA聚类算法实现青霉素生产工况的分类;然后,在两种分类结果的基础上采用支持向量机线性回归(SVR)建模,得到对应的SVR预测模型;最后,对青霉素发酵过程产生的数据进行仿真实验,仿真结果表明,基于两种聚类算法的SVR预测模型的预测准确性都较高,而基于K-Means聚类算法的SVR预测模型的可靠性更优。

嵌套结构的生产:城乡融合新机制——以广清经济特别合作区为例

采用ASID模型比较广清经济特别合作区2个阶段的空间生产过程发现,空间生产是在高尺度话语的动员下,行动者以各种策略性行动形成新的制度,以便突破现有社会空间结构约束并巩固该成果的过程;在空间生产过程中,所处的空间生产阶段决定行动者的目的,进而影响其所属类型和空间生产策略选择。行动者类型的实质是实现其目的的策略工具,嵌套结构可视为高政治责任感官员避责偏好的结果。对城乡融合过程中嵌套结构的研究,一方面深化了中国行政区划理论,另一方面也说明,要鼓励多种形式的城际合作,以便发挥如嵌套结构等柔性空间区划调整手段的灵活性,促进核心城市政府管理的跨界延伸,实现城市资本的再领域化。同时要积极行使行政区划调整等刚性手段,锁定嵌套结构的制度改革成果。