(1. 吉林大学 材料科学与工程学院，长春 130025;
2. 吉林大学 汽车材料教育 部重点实验室，长春 130025)
摘 要: 研究了不同成分的Ti-Fe-Mo-Mn-Nb-Zr合金的压缩强度、 硬度及其在Hank's人工体液中的耐腐蚀性能，得到了高压缩强度、硬度与牙本质相近的钛合金。在综合考虑钛合金成本、力学性能及耐腐蚀性能的基础上，采用BP神经网络建立了钛合金中的元素质量分数与硬度之间的关系，并通过实验进行了验证，预测结果与实验测定结果的对比是令人满意的。在保证性能的基础上，利用训练好的BP网络结构对材料的成分进行优化，以减少贵重元素的加入量。
关键字: 钛合金；BP算法；硬度；成分优化
Ti-Fe-Mo-Mn-Nb-Zr alloys based on
BP algorithm
（1. College of Materials Science and Engineering, Jilin University,
Changchun 130025, China;
2. The Key Laboratory for Automobile Materials of the Ministry of
Education, Jilin University, Changchun 130025, China）
Abstract:Corrosion resistivity in Hank's artificial body fluid, compression strength and hardness for heterogeneity Ti-Fe-Mo-Mn-Nb-Zr alloys were investigated. The alloys whose compression strength and hardness of approximate to that of dentin were obtained. Considering cost, mechanical performances and corrosion resistivity of alloy, the relationship between component and hardness of titanium alloys was found by BP algorithm. The the oretical analysis agree well with experiment result. The element contents of alloys were optimized by the BP arithmetic in order to save valued elements with appropriate me chanical performances.
Key words: titanium alloy；BP arithmetic；hardness；composition optimization
