科研之友
微信
新浪微博
Facebook
分享链接
摘要
A new type of ceramic tool material is usually developed with the "trial-and-error" method which wastes a lot of time and effort. With the advancement of computers and ceramic material science, ceramic material design can be carried out based on known knowledge and experience of the fabricated materials, with the aid of the computer. The compositions and contents of the ceramic tool materials to be developed may be designed and simulated in accordance with the requirement for the mechanical properties. The development process of a new ceramic tool material can be carried out based on the simulated information of the material composition and content. In this paper, the characteristics of the artificial neural network (ANN) and it's applications in the design of ceramic tool materials are introduced. The non-linear mapping relationship between the component, the composition content of raw material, the flexural strength, and the fracture toughness of the composite ceramic tool is investigated. The model for predicting the mechanical properties of the alumina matrix ceramic tool is established by means of an ANN. On the basis of the neural network toolbox in MATLAB (MATrix LABoratoryMA software), the neural network model for predicting the mechanical properties of the ceramic tool is trained to be reliable and the required programs are compiled. The mechanical properties of two-phase and three-phase composite ceramic tools such as Al2O3-(W, Ti)C and Al2O3-TiC-ZrO2 are predicted to verify the proposed model. It is found from the research results that the established model based on the ANN are available and effective in simulating the composition content and predicting the mechanical properties of the ceramic tool.
- 出版日期2002-10-11
- 单位山东大学
