Vibration signals have been widely used in engine fault diagnosis due to their excellent ability to characterize faults. However, they suffer from disadvantages such as susceptibility to noise interference and difficulty in extracting weak fault features. To address this, this article introduces acoustic emission (AE) signals to complement vibration signals with complementary high- and low-frequency characteristics, thereby enabling effective diagnosis of subtle engine faults. Nevertheless, traditional single-level fusion models still face significant challenges in comprehensively extracting faint fault features and deeply exploiting information complementarity. To overcome these limitations, this article innovatively proposes a multisource multilevel information fusion model based on graph convolutional networks (GCNs). The framework utilizes GCNs to compensate for traditional deep learning algorithms’ inability to capture spatial relationships among nodes; introduces an attention-based multiscale feature cross-fusion module to achieve cross-fusion of multisource features across different scales; and integrates a multilevel fusion strategy with Dempster–Shafer evidence theory to accomplish decision-level fusion, enabling multisource information integration at multiple scales and deep levels. The effectiveness of the proposed method in diagnosing aircraft engine faults is verified through the establishment of experiments, and excellent performance is achieved in the remaining working conditions, which prove that the method has a certain degree of universality.
NingLDuanQWeiY, et al. Effects of injection timing and compression ratio on the combustion performance and emissions of a two-stroke DISI engine fuelled with aviation kerosene. Appl Thermal Eng2019; 161: 114–124.
2.
KrishnaASMallikarjunaJMKumarD.Effect of engine parameters on in-cylinder flows in a two-stroke gasoline direct injection engine. Appl Energy2016; 176: 282–294.
3.
XuZJiFDingS, et al. High-altitude performance and improvement methods of poppet valves 2-stroke aircraft diesel engine. Appl Energy2020; 276: 115471.
4.
WangRJingHKarimiHR, et al. Robust fault-tolerant H∞ control of active suspension systems with finite-frequency constraint. Mech Syst Signal Process2015; 62–63: 341–355.
5.
LiZJiangYDuanZ, et al. A new swarm intelligence optimized multiclass multi-kernel relevant vector machine: an experimental analysis in failure diagnostics of diesel engines. Struct Health Monit2018; 17: 1503–1519.
6.
LiuYKangJBaiY, et al. A novel adaptive fault diagnosis algorithm for multi-machine equipment: application in bearing and diesel engine. Struct Health Monit2023; 22: 1677–1707.
7.
LinLHeWFuS, et al. Novel aeroengine fault diagnosis method based on feature amplification. Eng Appl Artif Intell2023; 122: 106093.
8.
MathewSKZhangY.Acoustic-based engine fault diagnosis using WPT, PCA and Bayesian optimization. Appl Sci2020; 10: 6890.
9.
ShaoHXiaMHanG, et al. Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images. IEEE Trans Ind Inf2021; 17: 3488–3496.
10.
LiuYZhangJMaL.A fault diagnosis approach for diesel engines based on self-adaptive WVD, improved FCBF and PECOC-RVM. Neurocomputing2016; 177: 600–611.
11.
LiuXLuJLiZ.Multiscale fusion attention convolutional neural network for fault diagnosis of aero-engine rolling bearing. IEEE Sens J2023; 23: 19918–19934.
12.
ZhaoNZhangJMaoZ, et al. Variational time–frequency adaptive decomposition of machine multi-impact vibration signals. Mech Syst Signal Process2023; 189: 110084.
13.
ZhouXWangXWangH, et al. Method for denoising the vibration signal of rotating machinery through VMD and MODWPT. Sensors2023; 23: 6904.
14.
WangCPengZLiuR, et al. Research on multi-fault diagnosis method based on time domain features of vibration signals. Sensors2022; 22: 8164.
15.
HuJYuYYangJ, et al. Research on the generalisation method of diesel engine exhaust valve leakage fault diagnosis based on acoustic emission. Measurement2023; 210: 112560.
16.
HanCLiuTJinY, et al. Acoustic emission intelligent identification for initial damage of the engine based on single sensor. Mech Syst Signal Process2022; 169: 108789.
17.
ZhangZWuXTanJ.In-situ monitoring of stress corrosion cracking of 304 stainless steel in high-temperature water by analyzing acoustic emission waveform. Corros Sci2019; 146: 90–98.
18.
HeDWuJJinZ, et al. AGFCN: a bearing fault diagnosis method for high-speed train bogie under complex working conditions. Reliab Eng Syst Safe2025; 258: 110907.
19.
HeDXuYJinZ, et al. A zero-shot model for diagnosing unknown composite faults in train bearings based on label feature vector generated fault features. Appl Acoust2025; 232: 110563.
20.
HouDQiHLuoH, et al. Comparative study on the use of acoustic emission and vibration analyses for the bearing fault diagnosis of high-speed trains. Struct Health Monit2022; 21: 1518–1540.
21.
YeZYuJ.Deep morphological convolutional network for feature learning of vibration signals and its applications to gearbox fault diagnosis. Mech Syst Signal Process2021; 161: 107984.
22.
ZhangXZhangXLiuJ, et al. Graph features dynamic fusion learning driven by multi-head attention for large rotating machinery fault diagnosis with multi-sensor data. Eng Appl Artif Intell2023; 125: 106601.
23.
WuZPanSChenF, et al. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learning Syst2021; 32: 4–24.
24.
WeiYWuDTerpennyJ.Bearing remaining useful life prediction using self-adaptive graph convolutional networks with self-attention mechanism. Mech Syst Signal Process2023; 188: 110010.
25.
ZhaoXZhuXLiuJ, et al. Model-assisted multi-source fusion hypergraph convolutional neural networks for intelligent few-shot fault diagnosis to electro-hydrostatic actuator. Inform Fusion2024; 104: 102186.
26.
XiaoYLiuDCuiL, et al. Heterogeneous graph representation-driven multiplex aggregation graph neural network for remaining useful life prediction of bearings. Mech Syst Signal Process2024; 220: 111679.
27.
LiuZPengZ.Few-shot bearing fault diagnosis by semi-supervised meta-learning with graph convolutional neural network under variable working conditions. Measurement2025; 240: 115402.
28.
YangCLiuJZhouK, et al. A node-level pathgraph-based bearing remaining useful life prediction method. IEEE Trans Instrum Meas2022; 71: 1–10.
29.
ZhangKLiHCaoS, et al. Trusted multi-source information fusion for fault diagnosis of electromechanical system with modified graph convolution network. Adv Eng Inform2023; 57: 102088.
30.
LiXHuHZhangS, et al. A fault diagnosis method for rotating machinery with semi-supervised graph convolutional network and images converted from vibration signals. IEEE Sens J2023; 23: 11946–11955.
31.
LuCWangSWangX.A multi-source information fusion fault diagnosis for aviation hydraulic pump based on the new evidence similarity distance. Aerosp Sci Technol2017; 71: 392–401.
32.
ShaoSYanRLuY, et al. DCNN-based multi-signal induction motor fault diagnosis. IEEE Trans Instrum Meas2020; 69: 2658–2669.
33.
ChenHHuNChengZ, et al. A deep convolutional neural network based fusion method of two-direction vibration signal data for health state identification of planetary gearboxes. Measurement2019; 146: 268–278.
34.
ZhangYLiCWangR, et al. A novel fault diagnosis method based on multi-level information fusion and hierarchical adaptive convolutional neural networks for centrifugal blowers. Measurement2021; 185: 109970.
35.
ZhouKLuNJiangB.Information fusion-based fault diagnosis method using synthetic indicator. IEEE Sens J2023; 23: 5124–5133.
36.
SunDLiYJiaS, et al. Non-contact diagnosis for gearbox based on the fusion of multi-sensor heterogeneous data. Inform Fusion2023; 94: 112–125.
37.
LiWLiuXWangD, et al. MITDCNN: A multi-modal input Transformer-based deep convolutional neural network for misfire signal detection in high-noise diesel engines. Expert Syst Appl2024; 238: 121797.
38.
YeZYuJ.Multi-level features fusion network-based feature learning for machinery fault diagnosis. Appl Soft Comput2022; 122: 108900.
39.
XuXZhaoZXuX, et al. Machine learning-based wear fault diagnosis for marine diesel engine by fusing multiple data-driven models. Knowl Based Syst2020; 190: 105324.
40.
GaoXXiaoF.A generalized χ2 divergence for multisource information fusion and its application in fault diagnosis. Int J Intell Syst2022; 37: 5–29.
41.
SeitiHHafezalkotobAMartinezL.R-sets, comprehensive fuzzy sets risk modeling for risk-based information fusion and decision-making. IEEE Trans Fuzzy Syst2021; 29: 385–399.
42.
WangYLiuY.Bayesian entropy network for fusion of different types of information. Reliab Eng Syst Safe2020; 195: 106747.
43.
GhoshMDeyAKahaliS.Type-2 fuzzy blended improved D-S evidence theory based decision fusion for face recognition. Appl Soft Comput2022; 125: 109179.
44.
LinZXieJ.Research on improved evidence theory based on multi-sensor information fusion. Sci Rep2021; 11: 9267.
45.
WangQZhangKLinS.Fault diagnosis method of disconnector based on CNN and D-S evidence theory. IEEE Trans Ind Appl2023; 59: 5691–5704.
46.
XuXBaoSShaoH, et al. A multi-sensor fused incremental broad learning with D-S theory for online fault diagnosis of rotating machinery. Adv Eng Inform2024; 60: 102419.
47.
WuZPanSLongG, et al. Graph WaveNet for deep spatial-temporal graph modeling. arXiv preprint arXiv:1906.00121. 2019.
48.
AhmedNKRossiRAZhouR, et al. Inductive representation learning in large attributed graphs. arXiv preprint arXiv:1710.09471. 2017.
49.
XuKHuWLeskovecJ, et al. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826. 2019.
50.
YeYJiS.Sparse graph attention networks. IEEE Trans Knowl Data Eng2021; 35(1): 905–916.
51.
DefferrardMBressonXVandergheynstP.Convolutional neural networks on graphs with fast localized spectral filtering. arXiv preprint arXiv:1606.09375. 2017.
52.
FuSLiuWZhangK, et al. Example-feature graph convolutional networks for semi-supervised classification. Neurocomputing2021; 461: 63–76.
53.
HuaYSunYXuG, et al. A fault diagnostic method for oil-immersed transformer based on multiple probabilistic output algorithms and improved DS evidence theory. Int J Electr Power Energy Syst2022; 137: 107828.
HouQZhouDFengJ.Coordinate attention for efficient mobile network design. arXiv preprint arXiv:2103.02907. 2021.
56.
HuJShenLAlbanieS, et al. Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell2020; 42: 2011–2023.
57.
NiQJiJCHalkonB, et al. Physics-Informed Residual Network (PIResNet) for rolling element bearing fault diagnostics. Mech Syst Signal Process2023; 200: 110544.
