PREDICTION AND ANALYSIS OF SULFURED NBR AGING IN GLYCOL BASED ON ARTIFICIAL NEURAL NETWORKS
High temperature accelerated aging was adopted to investigate mechanical properties changes of sulfured nitrile-butadiene rubber (NBR) in glycol at 70℃, 90℃, 110℃. Based on the experimental data, a BP neural network model for predicting the aging of NBR was developed by using time and temperature as the input variables and the properties as output variables. The predicted data, which is in good agreement with the test one, is used for creating 3D surface plots and contour plots. This paper discussed the change rules of the properties through analyzing these plots. By compared with the change of the cross-section microstructure, it was found that the rules were well in accordance with the actual situation.
Zhu Liqun Gu An Huang Huijie
School of Materials Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100083, China
国际会议
第九届工程结构完整性国际会议(The Ninth International Conference on Engineering Structural Integrity Assessment)
北京
英文
2007-10-15(万方平台首次上网日期,不代表论文的发表时间)