A multi-scale bottleneck attention and mixup-based domain adaptation misfire diagnostic method for diesel engines under different conditions
Source abstract
Abstract
Diesel engines are critical power sources widely used in marine, transportation, and industrial applications, where reliable operation is essential for safety and economic efficiency. However, traditional signal processing and many machine learning methods face challenges in extracting generalized fault features and accurately diagnosing misfires under complex, noisy operating conditions. To address these challenges, this paper proposes a novel multi-scale bottleneck attention and mixup- based domain adaptation network (MBA-MDAN) for reliable misfire detection across varying noise levels and working conditions. The approach integrates a denoising convolutional neural network (DnCNN) to suppress noise unrelated to fault characteristics, enabling clearer fault signal extraction. A parallel multi-scale convolution module captures fault features at different time scales, while a bottleneck attention module (BAM) selectively emphasizes critical features for deep fault representation. To preserve important information, time-domain statistical features are also incorporated. During training, metric learning minimizes feature discrepancies between source and target domains, and adversarial training between a domain discriminator and the fault classifier enhances domain adaptation. Additionally, domain mixup is applied to augment discriminator samples, further improving diagnostic performance. On the real-world datasets, compared to several state-of-the-art methods—including ShuffleNetV2, DenseNet, ANMCNN, MCBACNN, DANN, and WDAN—MBA-MDAN improves average diagnostic accuracy by 30.372%,16.407%,15.410%,16.483%,5.200%, and 4.725%, respectively. These results confirm the effectiveness of MBA-MDAN and indicate its strong potential for integration into intelligent operation and maintenance (O&M) systems for diesel engines, facilitating early fault detection and maintenance decision-making in complex industrial environments.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Fire Detection and Safety Systems · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (56)
Show source-provided references
1. Rao X, Sheng C, Guo Z, et al. A review of online condition monitoring and maintenance strategy for cylinder liner-piston rings of diesel engines. Mech Syst Signal Pr, 2022, 165: 10838510.1016/j.ymssp.2021.108385 ↗
2. Li O, Lei J B, Qin C J, et al. A novel multi-channel CNN-LSTM and transformer-based network for diesel engine misfire diagnosis under different noise conditions. Sci China Tech Sci, 2024, 67: 2965–296710.1007/s11431-023-2698-2 ↗
3. Siegel J, Kumar S, Ehrenberg I, et al. Engine misfire detection with pervasive mobile audio. In: Berlingerio M, Bonchi F, Gärtner T, et al., eds. Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2016, Part III. Berlin: Springer, 2016. 226–241
4. Zheng T, Zhang Y, Li Y, et al. Real-time combustion torque estimation and dynamic misfire fault diagnosis in gasoline engine. Mech Syst Signal Pr, 2019, 126: 521–53510.1016/j.ymssp.2019.02.048 ↗
5. Delvecchio S, Bonfiglio P, Pompoli F. Vibro-acoustic condition monitoring of Internal Combustion Engines: A critical review of existing techniques. Mech Syst Signal Pr, 2018, 99: 661–68310.1016/j.ymssp.2017.06.033 ↗
6. Tao J, Qin C, Li W, et al. Intelligent fault diagnosis of diesel engines via extreme gradient boosting and high-accuracy time-frequency information of vibration signals. Sensors, 2019, 19: 328010.3390/s19153280 ↗
7. Mohammadpour J, Franchek M, Grigoriadis K. A survey on diagnostic methods for automotive engines. Int J Engine Res, 2012, 13: 41–6410.1177/1468087411422851 ↗
8. Xu C, Li S, Cao F, et al. Misfire detection based on generalized force identification at the engine centre of gravity. IEEE Access, 2019, 7: 165039–16504710.1109/ACCESS.2019.2947621 ↗
9. Shen P F, Tang C, Bi F R, et al. Cross-domain diagnosis of mechanical system typical faults based on pretrain-finetune machine learning model. In: Proceedings of the 2024 7th International Conference on Advanced Algorithms and Control Engineering (ICAACE). New York: IEEE, 2024. 806–81010.1109/ICAACE61206.2024.10548078 ↗
10. Stringer D B, Sheth P N, Allaire P E. Physics-based modeling strategies for diagnostic and prognostic application in aerospace systems. J Intell Manuf, 2012, 23: 155–16210.1007/s10845-009-0340-4 ↗
11. Qiang W, Peilin Z, Chen M, et al. Multi-task Bayesian compressive sensing for vibration signals in diesel engine health monitoring. Measurement, 2019, 136: 625–63510.1016/j.measurement.2018.07.074 ↗
12. Vong C M, Wong P K. Engine ignition signal diagnosis with wavelet packet transform and multi-class least squares support vector machines. Expert Syst Appl, 2011, 38: 8563–857010.1016/j.eswa.2011.01.058 ↗
13. Devasenapati S B, Sugumaran V, Ramachandran K I. Misfire identification in a four-stroke four-cylinder petrol engine using decision tree. Expert Syst Appl, 2010, 37: 2150–216010.1016/j.eswa.2009.07.061 ↗
14. Wang Y, Chu F. Real-time misfire detection via sliding mode observer. Mech Syst Signal Pr, 2005, 19: 900–91210.1016/j.ymssp.2004.07.004 ↗
15. Tinaut F V, Melgar A, Laget H, et al. Misfire and compression fault detection through the energy model. Mech Syst Signal Pr, 2007, 21: 1521–153510.1016/j.ymssp.2006.05.006 ↗
16. Gao Z, Cecati C, Ding S X. A survey of fault diagnosis and fault- tolerant techniques—Part I: Fault diagnosis with model-based and signal-based approaches. IEEE Trans Ind Electron, 2015, 62: 3757–376710.1109/TIE.2015.2417501 ↗
17. Helm S, Kozek M, Jakubek S. Combustion torque estimation and misfire detection for calibration of combustion engines by parametric Kalman filtering. IEEE Trans Ind Electron, 2012, 59: 4326–433710.1109/TIE.2012.2193855 ↗
18. Liu Z, Wu K, Ding Q, et al. Engine misfire diagnosis based on the torsional vibration of the flexible coupling in a diesel generator set: Simulation and experiment. J Vib Eng Technol, 2020, 8: 163–17810.1007/s42417-019-00097-1 ↗
19. Song Q, Gao W, Zhang P, et al. Detection of engine misfire using characteristic harmonics of angular acceleration. Proc Inst Mech Eng D, 2019, 233: 3816–382310.1177/0954407019834104 ↗
20. Tamura M, Saito H, Murata Y, et al. Misfire detection on internal combustion engines using exhaust gas temperature with low sampling rate. Appl Therm Eng, 2011, 31: 4125–413110.1016/j.applthermaleng.2011.08.026 ↗
21. Wong P K, Zhong J, Yang Z, et al. Sparse Bayesian extreme learning committee machine for engine simultaneous fault diagnosis. Neurocomputing, 2016, 174: 331–34310.1016/j.neucom.2015.02.097 ↗
22. Zhong J H, Wong P K, Yang Z X. Fault diagnosis of rotating machinery based on multiple probabilistic classifiers. Mech Syst Signal Pr, 2018, 108: 99–11410.1016/j.ymssp.2018.02.009 ↗
23. Wang W, Li Y, Song Y. Fault diagnosis method of vehicle engine via HOSVD—HOALS hybrid algorithm-based multi-dimensional feature extraction. Appl Soft Comput, 2022, 116: 10829310.1016/j.asoc.2021.108293 ↗
24. Sharma A, Sugumaran V, Babu Devasenapati S. Misfire detection in an IC engine using vibration signal and decision tree algorithms. Measurement, 2014, 50: 370–38010.1016/j.measurement.2014.01.018 ↗
25. Wang X, Liu C, Bi F, et al. Fault diagnosis of diesel engine based on adaptive wavelet packets and EEMD-fractal dimension. Mech Syst Signal Pr, 2013, 41: 581–59710.1016/j.ymssp.2013.07.009 ↗
26. Liu B, Zhao C, Zhang F, et al. Misfire detection of a turbocharged diesel engine by using artificial neural networks. Appl Therm Eng, 2013, 55: 26–3210.1016/j.applthermaleng.2013.02.032 ↗
27. Qin C J, Wu R H, Huang G Q, et al. A novel LSTM-autoencoder and enhanced transformer-based detection method for shield machine cutterhead clogging. Sci China Tech Sci, 2023, 66: 512–52710.1007/s11431-022-2218-9 ↗
28. Qin C, Huang G, Yu H, et al. Adaptive VMD and multi-stage stabilized transformer-based long-distance forecasting for multiple shield machine tunneling parameters. Autom Constr, 2024, 165: 10556310.1016/j.autcon.2024.105563 ↗
29. Wang H, Qin C, Yu H, et al. A real-time multi-head mixed attention mechanism-based prediction method for tunnel boring machine disc cutter wear. Sci China Tech Sci, 2025, 68: 112030210.1007/s11431-024-2794-6 ↗
30. Zhang P, Gao W, Li Y, et al. Misfire detection of diesel engine based on convolutional neural networks. Proc Inst Mech Eng D, 2021, 235: 2148–216510.1177/0954407020987077 ↗
31. Shahid S M, Ko S, Kwon S. Real-time abnormality detection and classification in diesel engine operations with convolutional neural network. Expert Syst Appl, 2022, 192: 11623310.1016/j.eswa.2021.116233 ↗
32. Qin C, Jin Y, Tao J, et al. DTCNNMI: A deep twin convolutional neural networks with multi-domain inputs for strongly noisy diesel engine misfire detection. Measurement, 2021, 180: 10954810.1016/j.measurement.2021.109548 ↗
33. Qin C, Jin Y, Zhang Z, et al. Anti-noise diesel engine misfire diagnosis using a multi-scale CNN-LSTM neural network with denoising module. CAAI Trans Intel Tech, 2023, 8: 963–98610.1049/cit2.12170 ↗
34. Song L K, Tao F, Li X Q, et al. Physics-embedding multi-response regressor for time-variant system reliability assessment. Reliability Eng Syst Saf, 2025, 263: 11126210.1016/j.ress.2025.111262 ↗
35. Feng K, Xiao H, Zhang J, et al. A digital twin methodology for vibration-based monitoring and prediction of gear wear. Wear, 2025, 571: 20580610.1016/j.wear.2025.205806 ↗
36. Jin Y, Qin C, Tao J, et al. An accurate and adaptative cutterhead torque prediction method for shield tunneling machines via adaptative residual long-short term memory network. Mech Syst Signal Pr, 2022, 165: 10831210.1016/j.ymssp.2021.108312 ↗
37. Huang G, Qin C, Wang H, et al. TBM rock fragmentation classification using an adaptive spot denoising and contour-texture decomposition attention-based method. Tunn Undergr Space Tech, 2025, 161: 10649810.1016/j.tust.2025.106498 ↗
38. Qin C, Shi G, Tao J, et al. RCLSTMNet: A residual-convolutional- LSTM neural network for forecasting cutterhead torque in shield machine. Int J Control Autom Syst, 2024, 22: 705–72110.1007/s12555-022-0104-x ↗
39. Xiao Y, Shao H, Yan S, et al. Domain generalization for rotating machinery fault diagnosis: A survey. Adv Eng Inf, 2025, 64: 10306310.1016/j.aei.2024.103063 ↗
40. Xia P, Huang Y, Tao Z, et al. A digital twin-enhanced semi-supervised framework for motor fault diagnosis based on phase-contrastive current dot pattern. Reliability Eng Syst Saf, 2023, 235: 10925610.1016/j.ress.2023.109256 ↗
41. Xu S H, Lei J B, Qin C J, et al. A domain-adversarial wide-kernel convolutional neural network for noisy domain adaptive diesel engine misfire diagnosis. IEEE Trans Instrum Meas, 2024, 73: 1–19
42. Shen P, Bi F, Bi X, et al. Measuring domain shift in vibration signals to improve cross-domain diagnosis of piston aero engine faults. Processes, 2024, 12: 190210.3390/pr12091902 ↗
43. Shao H, Lai Y, Liu H, et al. LSFConvformer: A lightweight method for mechanical fault diagnosis under small samples and variable speeds with time-frequency fusion. Mech Syst Signal Pr, 2025, 236: 11301610.1016/j.ymssp.2025.113016 ↗
44. Shang Q, Jin T, Chen M. A new cross-domain motor fault diagnosis method based on bimodal inputs. JMSE, 2024, 12: 130410.3390/jmse12081304 ↗
45. Zhang M, Gunturk B K. Multiresolution bilateral filtering for image denoising. IEEE Trans Image Process, 2008, 17: 2324–233310.1109/TIP.2008.2006658 ↗
46. Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE Trans Signal Process, 2013, 62: 531–54410.1109/TSP.2013.2288675 ↗
47. Zhang K, Zuo W, Chen Y, et al. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Trans Image Process, 2017, 26: 3142–315510.1109/TIP.2017.2662206 ↗
48. Jiang G, He H, Yan J, et al. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox. IEEE Trans Ind Electron, 2018, 66: 3196–320710.1109/TIE.2018.2844805 ↗
49. Liu R, Wang F, Yang B, et al. Multiscale kernel based residual convolutional neural network for motor fault diagnosis under nonstationary conditions. IEEE Trans Ind Inf, 2019, 16: 3797–380610.1109/TII.2019.2941868 ↗
50. Niu Z, Zhong G, Yu H. A review on the attention mechanism of deep learning. Neurocomputing, 2021, 452: 48–6210.1016/j.neucom.2021.03.091 ↗
51. Park J, Woo S, Lee J Y. Bottleneck attention module. arXiv: 1807.06514
52. Ganin Y, Ustinova E, Ajakan H, et al. Domain-adversarial training of neural networks. J Mach Learn Res, 2016, 17: 1–35
53. Zhang H Y, Cisse M, Dauphin Y N. Mixup: Beyond empirical risk minimization. arXiv: 1710.09412
54. Huang G, Liu Z, Maaten L, et al. Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017. 4700–4708
55. Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018. 3–19
56. Zhong T, Qin C J, Shi G, et al. A residual denoising and multiscale attention-based weighted domain adaptation network for tunnel boring machine main bearing fault diagnosis. Sci China Tech Sci, 2024, 67: 2594–261810.1007/s11431-024-2734-x ↗