@article{XU2026, 
author = {Songzhe XU and Zhifan TANG and Jing DAI and Baojun WANG and Chaoyue CHEN and Yumeng WU and Yunsong ZHAO and Weidong XUAN and Zhongming REN},
title = {Research progress on application of artificial intelligence in precision casting and casting inspection},
year = {2026},
journal = {Journal of Aeronautical Materials},
volume = {46},
number = {9},
pages = {17-33},
keywords = {artificial intelligence, turbine blade, precision casting, shape and property control, casting inspection},
url = {https://www.sciopen.com/article/10.11868/j.issn.1005-5053.2025.000241},
doi = {10.11868/j.issn.1005-5053.2025.000241},
abstract = {Precision casting is the primary manufacturing process for core components of high-end critical equipment such as turbine blades for aero-engines and gas turbines, which directly determines the quality and performance of components and affects the efficiency and reliability of high-end equipment. Nevertheless, the precision casting process still faces challenges including casting defect control, dimensional accuracy and deformation control, and casting quality inspection. The rapid advancement of artificial intelligence technology offers new technical approaches for investment-casting process optimization and casting inspection. This paper systematically reviews the research progress of artificial intelligence in the field of investment casting. It mainly covers the applications of artificial intelligence in the preparation of key intermediate products including ceramic cores, wax patterns, and ceramic shells; the advances of artificial intelligence in assisting defect-performance control and dimensional control during casting solidification; as well as its applications in casting inspection, involving surface and internal defect detection, metallographic microstructure analysis, and other aspects. Finally, the advantages and challenges of applying artificial intelligence to precision casting processes and casting inspection are summarized, and future research directions are prospected:  (1) promote the evolution of artificial intelligence from empirical prediction for individual process links toward unified full-process and multi-scale modelling;  (2) drive the transformation of investment casting from independent shape control or performance control toward coordinated shape-performance regulation;  (3) develop physics-informed neural networks tailored for the investment-casting process;  (4) realize the transition of investment-casting processes from offline optimization to autonomous closed-loop control;  (5) large-language models provide new technical pathways for the intelligent development of precision casting.}
}