Due to the sensitivity and complexity of the composition-process-microstructure-performance relationship, the research and development of high-performance titanium-based materials have long been constrained by the dual challenges of high-dimensional nonlinear optimization and high trial-and-error costs. As a highly pervasive disruptive technology, artificial intelligence (AI) is introducing a new research and development paradigm for the strategic field of high-performance titanium-based materials, shifting from experience-driven modes to dual-driven approaches supported by models and data. This review summarizes the latest research advances in artificial intelligence-enabled high-performance titanium-based material technology (AI+Ti), focusing on how AI provides innovative solutions targeting the inherent characteristics of high-performance titanium-based materials, including complex compositions, diverse phase transitions, narrow thermal processing windows, and strong path dependence of microstructure evolution. The main contents include breakthroughs achieved by AI in constructing high-precision phase diagram and performance prediction models, as well as realizing the inverse design from performance objectives to microstructures and further to composition and processing parameters; the intelligent upgrading from forming control to active regulation of microstructures and properties in key processes such as additive manufacturing and heat treatment; and the establishment of an in-service behavior prediction framework based on digital twins. On this basis, this paper further analyzes the core challenges in the AI+Ti field regarding data, models, verification and integration, and prospects future development directions such as physics-informed machine learning and autonomous experimental platforms. Finally, it discusses controversial issues involving knowledge representation, human-machine collaboration modes and engineering trust establishment, and elaborates on the future development trends of this field: (1) material performance prediction and multi-scale coupling under complex service environments; (2) intelligent coordination of full-process processing parameters; (3) the construction and iteration of specialized physics-informed perception models for titanium alloys. Beyond simple tool application, AI+Ti has evolved into a transformative revolution that enables in-depth understanding and ultimate mastery of the cognition and research paradigm for high-performance titanium-based materials.

The ignition temperature serves as a pivotal parameter for assessing the flame retardancy of high-temperature titanium aluminum alloys（TiAl alloys）. Nevertheless, accurately predicting the ignition temperature of TiAl alloys remains a formidable challenge. Leveraging the Frank-Kamenetskii and Coulomb friction models, this paper develops a computational framework to determine the critical ignition temperature of TiAl alloy. It further investigates the influences of flow velocity, friction contact pressure, and oxygen partial pressure on this critical temperature. The findings reveal that as the flow velocity escalates from 140 m/s to 340 m/s, the critical ignition temperature incrementally rises from 1699.0 K to 1751.6 K. Intriguingly, while friction contact pressure increases from 1.0 MPa to 3.9 MPa, the critical ignition temperature stabilizes at 1710.2 K; however, the threshold ambient temperature necessary for alloy combustion decreases linearly, spanning from 1363.0 K to 537.5 K. Conversely, as the oxygen partial pressure climbs from 21.3 kPa to 96.3 kPa, the critical ignition temperature diminishes from 1719.7 K to 1665.8 K. Under specific conditions of an air flow temperature of 298 K and an air flow rate of 4.1 g/s, the finite volume method calculates a maximum flow velocity of 155.1 m/s near the specimen surface within the combustion chamber. Notably, the computed and experimental values for the critical oxygen partial pressure required for ignition are 93.8 kPa and 88.2 kPa, respectively, exhibiting a relative error of 6.3%.