The aviation industry is a key market that promote additive manufacturing (AM) technology since there are huge demands for precision manufacture of high-value complex structural parts and repair of local defects. Extensive research has been conducted on AM process

characterization

and fatigue evaluation of titanium alloy

but there are rare comprehensive reviews on fatigue evaluation methods used for AM aero-engine blades. Rigorous tests

evaluation

and certification are necessary before AM technology is applied in aero-engine blade repair

although it has shown great advantages in different engineering fields. This paper introduces the application of AM technology in the manufacturing and repair of aero-engine titanium alloy blades

summarizes the key factors affecting the fatigue performance of AM titanium alloys

thoroughly discusses the fatigue mechanism

research methods

and process optimizations of AM parts

and compares the differences among several prediction models in fatigue evaluation of AM titanium alloys.

Abbreviations:

FOD: foreign object damage; LCF: low cycle fatigue; HCF: high cycle fatigue; LSP: laser shock pe

ening; SP: shot peening; LP: low-pressure; HAZ: heat affected zone; AM: additive manufacturing; LAM: laser additive manufacturing; DED: directed energy deposition; PBF: powder bed fusion; LPBF: laser powder bed fusion; EPBF: electron beam powder bed fusion; LMD: laser metal deposition; LCD: laser cladding deposition; LENS: laser engineered net shaping; SLM: selective laser melting; EBM: electron beam melting; SEBM: selective electron beam melting; SLS: selective laser sintering; DMLS: direct Metal Laser Sintering; DMD-L: direct metal deposition by laser; DMD-P: direct metal deposition by plasma arc; LS: laser sintering; AB: as-built; LOF: lack of fusion; EVS: extreme value statistics; LEVD: largest extreme value distribution; VED: volumetric energy density; PD: probabilistic distribution; MRO: maintenance

repair operations; STA: solution treatment aging; BUS: broken-up structure; HIP: hot isostatic pressing; MP: machining and polishing; SR: stress relief; AN: annealing; DAN: double annealing; PBG: prior β grain; TCT: thermochemical treatment; AC: air cooling; SMAT: surface mechanical attrition treatment; CT: computer tomography; SEM: scanning electron microscope; FCG: fatigue crack propagation; FCGR: fatigue crack propagation rate; SIF: stress intensity factor; EIFS: equivalent initial defect size; LEFM: linear elastic fracture mechanics; ML: machine learning; ANN: artificial neural network; FNN: feed forward neural network; CNN: convolutional neural network; PINN: physics-informed neural network; PPgNN: probabilistic physics-guided neural network; ANFS: adaptive network-based fuzzy system; SVM: support vector machine; SVR: support vector regression; RF: random forest; CDM: continuum damage mechanics.IMPACT STATEMENT The fatigue performance of additively manufactured titanium alloys is influenced by a combination of microstructure

defects

surface roughness

and residual stresses. In the context of fatigue assessment

the role of defects is typically prioritized.