智能选材系统的研究实现

发布时间：2018-12-13 01:14

【摘要】：现代设计理论认为,产品的结构、功能和成本的70%在设计阶段就被决定了。材料的选择又是机械产品设计工作中一个极其重要的组成部分。很多机械的重大失效并不是在于它的运动设计和动力设计,而在于材料的种类和牌号选择不当。近年来,越来越多的新材料被使用,以减轻产品的重量,提高产品的质量,降低产品的成本。另外,创新设计也需要材料选用方面的创新给予支持。因此如何在数量巨大的材料库中选择最优的材料就成了国内外学者研究的热点。本文研究和初步实现了一个智能材料选择系统,建立了材料数据库和知识库,着重研究了BP神经网络和专家系统在材料选择方面的应用。本文的工作包括以下几个方面：一、论述了传统材料选择过程中存在的问题,分析了国内外关于选材方法和专家系统的研究现状。分析了神经网络与专家系统各自的优缺点后,本文提出以BP神经网络和专家系统相结合的方式设计选材系统,为设计人员推荐材料。二、确定了材料数据来源,研究了材料的标准存储格式后,建立了包含大多数工程材料信息的材料数据库,并开发了系统的材料查询模块。建立知识库,系统通过学习样本和总结归纳两种方式,获取专家的选材知识并保存在知识库中。三、根据知识库中的知识建立系统的选材模块,包含一个BP神经网络和一个决策树,通过提问的方式为设计人员推荐材料,并且能够对选材结果做出合理的解释。四、建立知识管理模块、用户反馈模块、帮助模块、用户管理模块等辅助模块,完善系统功能。系统采用B/S结构,所有服务都在服务器上实现,减少客户端载荷,使用户能够更加简单方便的使用。五、文章最后通过一个应用实例,验证了系统的有效性。本系统不仅可以给设计人员推荐合适的材料,也可以为经验不足的用户积累选材知识,具有广泛的应用价值。
[Abstract]:According to modern design theory, 70% of the product's structure, function and cost are determined in the design stage. The selection of materials is also an extremely important part in the design of mechanical products. The major failure of many machines lies not in their motion design and dynamic design, but in the improper selection of materials and grades. In recent years, more and more new materials have been used to reduce product weight, improve product quality and reduce product cost. In addition, the innovative design also needs the material choice aspect innovation to give the support. Therefore, how to select the best materials in a large number of materials has become a hot topic for scholars at home and abroad. In this paper, an intelligent material selection system is studied and implemented, and the material database and knowledge base are established. The application of BP neural network and expert system in material selection is emphatically studied. The work of this paper includes the following aspects: firstly, the problems existing in the selection of traditional materials are discussed, and the present situation of research on material selection methods and expert systems at home and abroad is analyzed. After analyzing the advantages and disadvantages of the neural network and the expert system, this paper proposes to design the material selection system by combining the BP neural network with the expert system, and recommends the material for the designer. Secondly, the source of material data is determined, the standard storage format of material is studied, the material database containing most engineering materials information is established, and the material query module of the system is developed. The knowledge base is established. The system acquires the experts' knowledge of selecting materials and stores it in the knowledge base by learning samples and summarizing. Thirdly, according to the knowledge in the knowledge base, the system material selection module is set up, which includes a BP neural network and a decision tree. The material is recommended to the designer by asking questions, and the material selection results can be explained reasonably. Fourth, establish knowledge management module, user feedback module, help module, user management module and other auxiliary modules to improve the system functions. The system adopts the structure of B / S, all services are implemented on the server, which reduces the load of the client and makes the user more simple and convenient to use. Finally, an application example is given to verify the effectiveness of the system. This system can not only recommend suitable materials to designers, but also accumulate knowledge of material selection for inexperienced users.
【学位授予单位】：北京交通大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：TH186;TP311.13

【相似文献】