关于机械设计专家系统求解策略的探讨

文章着重讨论机械设计专家系统求解策略.从分析专家任务特征入手,讨论了专家求解问题的全过程.提出一种机械设计专家系统的求解策略.该策略突出反映了设计过程中,专家决策和有效地利用支持资源的求解方法.最后,用一个标准滚子链传动设计专家系统(CDDES),说明这种控制策略的可行性.     

机械设计和评估专家系统的设计与实现

本文阐述了专家系统技术在机械设计和评估中的应用研究情况，主要内容包括如何针对机械设计的特点构造其专家系统的体系结构，如何利用人工智能领域中开发知识表示方法表达机械设计和知识和建立相应的知识库，以及设计推理机。     

《机械设计手册（软件版）》V3．0

《机械设计手册（软件版）》V3．0是一套大型机械设计专业技术工具软件，主要由机械设计数据资源、机械设计计算和查询程序、机械工程常用公式计算、机械标准件2D和3D图库、机械工程常用英汉词汇等分系统组成。     

面向机械设计的知识获取环境

在开发机械设计专家系统时，需要有效的知识获取环境，本文介绍了一个针对机械设计知识的特点所研制的面向机械设计领域的知识获取环境ＭＤＫＡＳ，其内容包括：知识表示和获取，知识库的组织，维护，管理及各种辅助模块，该系统在微机上用ＧＣＬＩＳＰ实现，经过运行使用，效果良好。     

甘蔗收获机械可视化虚拟设计平台的研究开发

介绍了甘蔗收获机械可视化虚拟集成设计平台研究开发的基本思路。该平台的构建通过STEP标准建立产品开发的全局共享信息模型，利用PDM软件集成和封装CAD／CAE及其它产品设计过程中用到的应用软件；平台也集成了甘蔗收获机械设计、分析和评价专家系统，专家系统采用模糊评价的方法对开发过程设计和仿真分析的结果进行评价和决策。集成平台支持甘蔗收获机械可视化虚拟产品集成化的团队设计及收获机械系列化产品开发。     

用ToolBook开发多媒体电子手册

本文介绍了作者在开发多媒体辅助教学系统过程中，用多媒体著作工具ＴｏｏｌＢｏｏｋ设计制作多媒体机械设计电子手册的方法，该手册以机械设计数据为为后台，以多媒体窗口为用户界面，形式新颖别致。可以预见，这种具有多媒体功能的“电子教材”将会得到广泛的应用。     

浅谈机械设计中材料的选择和应用

随着国民经济的快速发展,人类社会对机械设计的要求越来越高,尤其是对机械设计中的材料的选择和应用,社会各界及本行业都予以一定的关注,如何做好机械设计中材料的选择和应用,成为广大机械设计技术人员和所有从业人员必须面对并加以认真解决的问题.节能减排与环境保护以及机械设计的适用性和经济性成为机械设计中材料选择和应用的必然选择.本文立足于机械设计中材料选择和应用的实际情况,简要叙述了机械设计中材料选择和应用的重要意义,提出了机械设计中的材料的选择和应用的适用性和经济性、机械设计中的材料的选择和应用应当重视绿色环保、机械设计中的材料的选择和应用中要坚决贯彻可持续发展观等观点.     

机械设计制造环节自动化技术的实际应用

在机械设计制造环节中,对各部件的尺寸规格具有较高的精度要求.自动化技术在机械设计制造环节中具有显著的应用优势,能实现对机械设计制造精度要求的有效保障.因此,为提高机械设计制造的质量,必须加强自动化技术在机械设计制造环节的应用.本文浅析了机械设计制造环节自动化技术的应用优势,探讨了机械设计制造环节自动化技术的实际应用.     

提高设计水平的基础工程

提高设计水平的基础工程中国机械工程学会机械设计分会张志远一项历时６载的系统基础工程，已经通过评审。这项名为“提高机电产品设计水平的研究与信息服务”的软课题，是由机械部科技信息研究院机电产品设计信息中心与中国机械工程学会机械设计分会承担的，经机械工业部...     

基于Web的机械设计基础课程教学素材库

以知识点为基础构建的机械设计基础多媒体素材库，能够给教师提供机械设计基础类多门课程的教学内容，本文分析了该系统数据库的结构以及文本、图形、声音、视频等素材的存储方式，并讨论了B／S结构模式下系统构建的关键技术，最后对系统应用的工作流程作了介绍。     

Information structuring for use and reuse of mechanical analysis models in engineering design

Nowadays, in an industrial context, cost and delay reduction, as well as quality improvement are of major interest in engineering design. Therefore, in order to make a decision as early as possible and according to the product specifications, mechanical analysis is used more and more, and earlier and earlier in the engineering process. Then, a multitude of mechanical models are elaborated during engineering design, and management difficulties appear with engineering changes or evolution of specifications. Moreover, when the designer is faced with design or modelling options, previous analysis could answer the choice of options for decision making. Then, the reuse of a previous analysis must be envisaged. The paper presented deals with the aim and the different use of mechanical analysis in embodiment design. Afterwards, different levels of models handled by the designer during the engineering process are proposed. A particular type of analysis, namely instructional' is identif ied in a further step and its interest in a reuse context is emphasized. Finally, information structuring is proposed in order to allow mechanical analysis reuse during engineering design.     

基于知识融合技术的产品设计知识模型研究*

为解决机械产品设计中知识融合的问题,建立了一种基于本体的产品设计知识模型。基于此,提出了一种基于模糊证据理论的融合推理方法,这种方法将模糊集引入证据识别空间中,利用证据合成与决策规则得出知识融合的结果,这种方法弥补了本体建模时的不足并解决了不确定性知识的推理。最后,将该知识模型应用于制造行业产品设计中,帮助制造企业缩短产品设计周期和提高开发质量,同时也有利于产品设计知识的共享和重用。     

Factors that affect planning in a knowledge-based system for mechanical engineering design optimization with application to the design of mechanical power transmissions

Intelligent computer-aided design (CAD) emulates the human activity of design so that production planning, decision making, and inventive design can be performed by computers.Based on the history of human experience in engineering design, a formalized and systematic approach to design should include procedures from (1) conceptual design, (2) layout design, and (3) numerical optimization. The highest level within such a system should be responsible for specifying and symbolically optimizing skeleton structures of generic (nonspecific) elements within the design process that are eventually to be specified uniquely (pinned down) and ultimately optimized numerically. Planning plays a key role in such a system.Planning has been utilized as a tool for process organization within the knowledge domains of chemical engineering, electrical engineering, manufacturing, as well as for general problem formulation and solution. State estimation, subtask scheduling, and constraint propagation have been found to be factors of prime importance in this type of problem.Problems associated with the implementation of a planning strategy within a knowledge-based system for mechanical engineering design optimization are discussed. A hypothesis for planning is put forth and examined within the context of a model of the mechanical design optimization process. An example that demonstrates the applicability of this approach to mechanical power transmission design is considered.     

基于神经网络的机械传动方案决策系统的建模与仿真

针对机械传动方案决策系统难以建立准确数学模型的特点,提出了利用BP及BP改进神经网络的非线性映射能力,进行机械传动方案决策系统模型辨识建模的新方法.介于网络的输入输出数据难以精确描述的特点,运用模糊理论对其进行了处理.通过仿真实验验证了利用BP及BP改进网络建立其决策模型的可行性,表明了BP改进算法收敛速度更快,模型更准确,从而为机械系统传动方案的决策提供了一种更为有效的推理模型.     

Structural optimization system based on trabecular bone surface adaptation

In the paper the structural optimization system based on trabecular bone surface adaptation is presented. The basis of the algorithm formulation was the phenomenon of bone adaptation to mechanical stimulation. This process, called remodeling, leads to the optimization of the trabecular network in the bone. The simulation system, as well as the finite element mesh generation, decision criteria for structural adaptation, and the finite element analysis in a parallel environment are described. The possibility of applying the system in mechanical design is discussed. Some computation results using the developed system are presented, including the comparison to the topology optimization method.     

Prediction of product design decision Making: An investigation of eye movements and EEG features

Design decision making is happened in every design node and iteration, and the expert decision-making bias and personal preference will ultimately affect the success or failure of the product reaching the market. In this paper, we try to predict the design decision making by investigating the relations between design decision making and subjects’ eye movements and Electroencephalogram(EEG) response. Four different methods were applied and compared to classify the different EEG features and two methods were used for EEG feature selection to correspond the design decision making results. In this study, the authors applied a multimodal fusion strategy for design decision making recognition where the authors used eye tracking and EEG response data as input dataset. According to the experiment results, the performance of the fusion strategy combined with EEG signals and eye movement characteristics is well in fitting the expert decision making results. The multimodal fusion combining eye tracking data and EEG has a strong potential to be a new design decision method to guide the design practice and provide supportive and objective data to reduce the effects of subjectivity, one-sidedness and superficiality in decision making. These results show that it is possible to create a classifier based on features extracted from eye movements and EEG response for the design decision making behaviour.     

Design of an Early Minicomputer

In this article, I describe the design of an early 1950s attempt to build a relatively low-cost computer, using a mechanical desktop calculator to perform the arithmetic operations. The resulting computer-one of the earliest attempts at building a "minicomputer"-could perform stored-program addition, subtraction, multiplication, and division, as well as carry out a simple decision operation based on a number comparison. To solve a problem, the operator would type in a program sequence based on the use of nine basic instructions. Total memory capacity was 400 words.     

A model of design decision making based on empirical results of interviews with software designers

Despite the impact of design decisions on software design, we have little understanding about how design decisions are made. This hinders our ability to provide design metrics, processes and training that support inherent design work. By interviewing 25 software designers and using content analysis and explanation building as our analysis technique, we provide qualitative and quantitative results that highlight aspects of rational and naturalistic decision making in software design. Our qualitative multi-case study results in a model of design decision making to answer the question: how do software designers make design decisions? We find the structure of the design problem determines the aspects of rational and naturalistic decision making used. The more structured the design decision, the less a designer considers options.     

网络化设计评价群决策支持系统研究*

为了改进产品设计评价的方法,将决策支持系统机制引入产品设计评价领域。改进了部分个体评价及群决策方法,构建了适用产品设计的评价问题生成库和评价问题解决方法库。结合产品设计评价的特点,采用群体决策的思想,构建出包括对话、数据、模型三个模块的群决策支持系统框架。建立基于网络的产品设计评价群决策支持系统。它将对辅助决策、改进设计质量具有较高的实用价值。     

Template-based configuration and execution of decision workflows in design of complex engineered systems

The research reported in the paper is from a decision-based design perspective wherein the principal role (but not only) role of a designer is to make decisions. Decision workflows are the processes by which the solutions pertaining to the design of complex systems are generated. Decision workflows are core to design processes, in which a set of decisions are connected (or interconnected) to generate shared and desired design outputs. Careful configuration of decision workflows is very important to ensure the generation of designs using available resources. Configuration of decision workflows is a process that requires a designer to use the basic elements to compose feasible workflows and then select an appropriate one for implementation in designing a product or a system. In this paper, we propose a template-based method for the design and execution of decision workflows associated with designing engineered systems. The value of the method is anchored in that it facilitates designers rapidly planning the processes, namely, the decision workflows, for designing products or systems. Moreover, due to the fact that these decision workflows are modeled in a computational manner, designers are able to execute decision workflows to explore the solution space and identify satisficing design solutions in early design stages. A gearbox with connected gears and shafts is a typical complex engineered system that can be partitioned into multiple levels of interacting subsystems. We illustrate the method and the decision workflows using a gear and shaft (within a gearbox) design example.