Application of artificial neural network for prediction ionitriding of thickness and hardness test in Ti-6Al-4V alloy
ZHU Shuo1, WANG Zhe2, HE Rui-jun1, WANG Yun1, ZHANG Yun-sheng3, ZHOU Ge3
1. AECC Beijing Institute of Aeronautical Materials, Beijing 100095, China; 2. AECC Shenyang Liming Aero ENGINE Co., Ltd., Shenyang 110043, Liaoning, China; 3. School of Materials, Shenyang University of Technology, Shenyang 110870, Liaoning, China
Abstract：Associations between Ti-6Al-4V alloy ionic nitridation layer thickness or hardness and thermal treatment parameters were studied using the artificial neural network technology. Based on experiments of Ti alloy ionic nitridation process, a three-layer back-propagation(BP) neural network model was established, which took ionic nitridation temperature, heat preservation time and pressure as input parameters and the thickness and hardness of ionic nitridation layer as output variables. Then the optimization algorithm and neuron number during the model learning and training were investigated, and the ionic nitridation layer thickness and hardness of the alloy were predicted. The prediction results show that the comprehensive multi-correlation coefficient of the model is 0.978 45, and the model predicted values are highly similar to the sample values. The optimal ranges of the ionic nitridation process are determined to be temperature at 850-880 ℃, heat preservation time of 16 h, pressure of 200-300 Pa, nitridation layer thickness greater than 85 μm, and hardness greater than 1 000HV. Thus, it can provide new methods and ideas for the research of ionic nitridation process, microstructure and performance control of Ti alloy complex parts.
朱硕, 王哲, 贺瑞军, 王赟, 张允胜, 周舸. 基于人工神经网络模型的Ti-6Al-4V合金离子氮化层厚度、硬度预测[J]. 中国冶金, 2022, 32(10): 89-96.
ZHU Shuo, WANG Zhe, HE Rui-jun, WANG Yun, ZHANG Yun-sheng, ZHOU Ge. Application of artificial neural network for prediction ionitriding of thickness and hardness test in Ti-6Al-4V alloy[J]. China Metallurgy, 2022, 32(10): 89-96.
SHE D,WEN Y,FU Z,et al. Effects of nitriding temperature on microstructures and vacuum tribological properties of plasma-nitrided titanium[J]. Surface and Coatings Technology,2015,264:32.
[13]
Ali M M,Raman S G S,Pathak S D,et al. Influence of plasma nitriding on fretting wear behaviour of Ti-6Al-4V[J]. Tribology International,2010,43(1/2):152.
[14]
Ali M M,Raman S G S. Effect of plasma nitriding environment and time on plain fatigue and fretting fatigue behavior of Ti-6Al-4V[J]. Tribology Letters,2010,38(3):291.
LIN Yi,ZHENG Zi-qiao,HAN Ye. Effect of heat treatment process on tensile properties of 2A97 Al-Li alloy:experiment and BP neural network simulation[J]. Transactions of Nonferrous Metals Society of China,2013,23:1728.
[21]
GUO La-feng,LI Bao-cheng,ZHANG Zhi-min. Constitutive relationship model of TC21 alloy based on artificial neural network[J]. Transactions of Nonferrous Metals Society of China,2013,23:1761.
2022, Vol. 32 
