Composition optimization of radiation resistance ODS alloy with high strength and ductility for advanced reactor based on machine learning

ABSTRACT

Oxide dispersion strengthened (ODS) alloy is a candidate material for cladding in the fast reactor and the first wall in fusion reactor. Its radiation resistance is still a key problem restricting its application in the field of fast reactor and fusion reactor. By collecting, cleaning and screening the data which includes the composition, process, irradiation conditions, test conditions and yield strength of ODS alloy, the correlation between key components and irradiation hardening of ODS alloy were established by use of deep neural network, and the irradiation hardening prediction of ODS alloy was obtained. The results show that the irradiation hardening decreases significantly when the amount of Y₂O₃ is about 0.2%. In addition, it is found that when the addition of Y₂O₃ is greater than 0.3 wt%, the addition of Ti and Al has little effect on the irradiation hardening, while when the addition of Y₂O₃ is less than 0.2 wt%, the addition of a certain amount of Ti or Al will effectively inhibit the irradiation hardening of ODS alloy. According to the above results, combined with the high strength and ductility ODS alloy design obtained in the previous work, the composition optimization of ODS alloy with both strengthening and toughening and irradiation hardening resistance is further obtained.

KEYWORDS:

• ODS alloy
• irradiation hardening resistance
• machine learning
• material design

Acknowledgement

This work is supported by the R&D project of CNNC, National Natural Science Foundation of China No. 52001330 and No.U1867217, and Innovation Centre of Nuclear Materials for National Defense Industry.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [52001330,U1867217]; Innovation Centre of Nuclear Materials for National Defense Industry [ICNM-2020-ZH-06]; R&D project of CNNC [FA18000120].