With the advantages of noncontact detection, acoustic sensor has been widely applied to turbine for structural health monitoring and blade crack detection under harsh environment. However, it is difficult and time-consuming to obtain high-quality and sufficient monitoring sound signals, which lead to poor performance in crack detection based on limited sensor data. To obtain a large number of high-quality signals of turbine blade crack detection, the sound signal synthesis method is proposed based on vibration-acoustic coupling simulation (VACS) and actual signals confrontation. First, the VACS model is built for turbine from two aspects of vibration and acoustics, which can obtain high-quality and sufficient simulation sound signals. Besides, the conditional generative adversarial network (CGAN)-based signal quality improvement method is proposed to obtain generated signals based on actual signals confrontation with limited sensor data, which can bridge the gap between simulation and measured signals. Further, the CGAN model integration method is presented to synthetize sound signal by transferring generated signals from measured points to all simulation points, which are employed for turbine blade crack detection. To verify the proposed method, two case studies are implemented based on two types of turbines. It can obtain synthetic sound signals with over 0.68 cosine similarity, and the accuracy of blade crack detection can reach about 93% under different conditions. Comparing with other methods, the superiority and reliability of the proposed method is validated, which is significant for turbine acoustic data acquisition and blade crack detection.
YooSKimMParkG, et al. Hybrid explainable anomaly detection framework of gas turbines for feature selection and fault localization. Struct Health Monit2025; 24(5): 2689–2714.
2.
MårtenssonHBillsonM. Aeroacoustic effects on the forcing of fan and compressor blades due to distortion. J Eng Gas Turbines Power2024; 146: 061013.
3.
HuangXZhangXXiongY, et al. Highly imbalanced fault diagnosis of turbine blade cracks via deep focal dynamically weighted conditional variational auto-encoder network. Adv Eng Inform2024; 62: 102612.
4.
QuqaSLasriODeloG, et al. Regional-scale bridge health monitoring: survey of current methods and roadmap for future opportunities under changing climate. Struct Health Monit2025; 24(4): 2309–2337.
5.
TimilsinaSShresthaSand FuX. Quantized radio map estimation using tensor and deep generative models. IEEE Trans Signal Process2024; 72: 173–189.
6.
QinYLiuHand MaoY. Faulty rolling bearing digital twin model and its application in fault diagnosis with imbalanced samples. Adv Eng Inform2024; 61: 102513.
7.
CaoJYangZSunR, et al. OPR-free single probe blade tip timing for monitoring rotating blade. Int J Mech Sci2023; 247: 108174.
8.
YangXFangHYuX, et al. Study on the mechanism of vibration signal generation in water supply pipeline leaks. Measurement2024; 229: 114415.
9.
WangCTianJZhangF, et al. Simulation method and spectrum modulation characteristic analysis of typical fault signals of inter-shaft bearing. Mech Syst Sig Process2024; 209: 111145.
10.
LiXLiSWeiD, et al. Dynamics simulation-driven fault diagnosis of rolling bearings using security transfer support matrix machine. Reliab Eng Syst Saf2024; 243: 109882.
11.
ChenZZhaoPYanR, et al. Quantitative finite element analysis of microscopic surface formation for TC4 aeroengine blade polishing using single-grain method. Int J Adv Manuf Tech2024; 132: 2941–2955.
12.
SeoHand HanJ. Deep learning approach for predicting crack initiation position and size in a steam turbine blade using frequency response and model order reduction. J Mech Sci Technol2024; 38(4): 1971–1984.
13.
GuanHMaHQuX, et al. Dynamic stress analysis of cracked rectangular blade: simulation and experiment. Int J Mech Sci2024; 267: 109015.
14.
LuJZhengYZhangH, et al. Bayesian approach of Elliptical Loci and RAPID for damage localization in wind turbine blade. Smart Mater Struct2024; 33(4): 045008.
15.
YangXWangFFangH, et al. Numerical and experimental research on vibration signal characteristics of water pipeline leakage. Measurement2024; 226: 114118.
16.
WangAZhangKZhaoZ, et al. Modeling strategy and dynamic analysis of a dual-rotor-bearing-casing system in aero-engine. Appl Math Model2023; 123: 105–135.
17.
XiangCFangPLiH, et al. Nonlinear dynamics of a drillstring system with PDC bit in curved wells based on the finite element method. Energy Sci Eng2023; 230: 212240.
18.
SongDShenJMaT, et al. Acoustic sensor placement optimization for compressor based on adversarial transfer learning and vibro-acoustic simulation. IEEE Sens J2023; 23(15): 13539–13547.
19.
LiR. Analysis of vibration response characteristics of composite pipeline based on finite element method. Vibroeng Procedia2024; 54: 66–71.
20.
AliMAliMHussainM, et al. Generative adversarial networks (GANs) for medical image processing: recent advancements. Arch Comput Method Eng2025; 32: 1185–1198.
21.
BoroujeniSand RaziA. Ic-gan: an improved conditional generative adversarial network for rgb-to-ir image translation with applications to forest fire monitoring. Expert Syst Appl2024; 238: 121962.
22.
HanBJiangXWangJ, et al. A novel domain adaptive fault diagnosis method for bearings based on unbalance data generation. IEEE Trans Instrum Meas2023; 72: 3519911.
23.
WangGYangZSunH, et al. AC-SNGAN: multi-class data augmentation for damage detection of conveyor belt surface using improved ACGAN. Measurement2024; 224: 113814.
24.
YangJZhangGChenB, et al. Vibration signal augmentation method for fault diagnosis of low-voltage circuit breaker based on W-CGAN. IEEE Trans Instrum Meas2023; 72: 3506611.
25.
GaoYLiuXXiangJ. FEM simulation-based generative adversarial networks to detect bearing faults. IEEE Trans Ind Electron2020; 16(7): 4961–4971.
26.
MengZLiQSunD, et al. An intelligent fault diagnosis method of small sample bearing based on improved auxiliary classification generative adversarial network. IEEE Sens J2022; 22: 19543–19555.
27.
GaoYLiuXHuangH, et al. A hybrid of FEM simulations and generative adversarial networks to classify faults in rotor-bearing systems. ISA Trans2023; 108: 356–366.
28.
TulasiramJBanothuBNickolasS. Monkeypox data enhancement and diagnosis using improved DCGA. Soft Comput2025; 29: 2497–2513.
29.
YangPLiSQinS, et al. Smart grid enterprise decision-making and economic benefit analysis based on LSTM-GAN and edge computing algorithm. Alexandria Eng J2024; 104: 314–327.
30.
JiaZYuB. A fault diagnosis method for rolling bearings of wind turbine generators based on MCGAN data enhancement. SN Appl Sci2023; 5(10): 259.
31.
ViolaJChenYWangJ. FaultFace: deep convolutional generative adversarial network (DCGAN) based ball-bearing failure detection method. Inf Sci2021; 542: 195–211.
32.
XiaXPanXLiN, et al. GAN-based anomaly detection: a review. Neurocomputing2022; 493: 497–535.
33.
YanXJiangDXiangL, et al. CDTFAFN: a novel coarse-to-fine dual-scale time-frequency attention fusion network for machinery vibro-acoustic fault diagnosis. Inform Fusion2024; 112: 102554.
34.
BrophyEWangZSheQ, et al. Generative adversarial networks in time series: a systematic literature review. ACM Comput Surv2023; 55(10): 199.
35.
PengYWangYShaoY. A novel bearing imbalance Fault-diagnosis method based on a Wasserstein conditional generative adversarial network. Measurement2022; 192: 110924.
36.
QinYWuXLuoJ. Data-model combined driven digital twin of life-cycle rolling bearing. IEEE T Ind Inform2022; 18(3): 1530–1540.
37.
RibaldoneCDesmaraisJ. Spherical to Cartesian coordinates transformation for solid harmonics revisited: construction of the Hartree potential. J Chem Phys2025; 163: 074102.
38.
AhangMJalayerMShojaeinasabA, et al. Synthesizing rolling bearing fault samples in new conditions: a framework based on a modified CGAN. Sensors2022; 22(14): 5413.
39.
WeiXWangXGaoJ, et al. Faulty feeder detection for single-phase-to-ground fault in distribution networks based on transient energy and cosine similarity. IEEE Trans Power Deliv2022; 37(5): 3968–3979.
40.
GuXYuYGuoL, et al. CSWGAN-GP: a new method for bearing fault diagnosis under imbalanced condition. Measurement2023; 217: 113014.
41.
CaoYZhangWMingP, et al. Numerical and experimental investigations of centrifugal compressor BPF noise. Appl Acoust2019; 150: 290–301.
42.
WangZMaHYangY, et al. Information transfer between tip leakage vortex and blade aerodynamic force of a compressor cascade. Aerosp Sci Technol2024; 153: 109400.
43.
LouYKumarAXiangJ. Machinery fault diagnosis based on domain adaptation to bridge the gap between simulation and measured signals. IEEE Trans Instrum Meas2022; 71: 3514709.
44.
XiangGTianK. Spacecraft intelligent fault diagnosis under variable working conditions via Wasserstein distance-based deep adversarial transfer learning. Int J Aerosp2021; 2021: 6099818.
45.
LuleciFCatbasFAvciO. A literature review: generative adversarial networks for civil structural health monitoring. Front Built Environ2022; 8: 1027379.
