Research on Improved Deep Convolutional Generative Adversarial Networks for Insufficient Samples of Gas Turbine Rotor System Fault Diagnosis
Source abstract
Abstract
In gas turbine rotor systems, an intelligent data-driven fault diagnosis method is an important means to monitor the health status of the gas turbine, and it is necessary to obtain sufficient fault data to train the intelligent diagnosis model. In the actual operation of a gas turbine, the collected gas turbine fault data are limited, and the small and imbalanced fault samples seriously affect the accuracy of the fault diagnosis method. Focusing on the imbalance of gas turbine fault data, an Improved Deep Convolutional Generative Adversarial Network (Improved DCGAN) suitable for gas turbine signals is proposed here, and a structural optimization of the generator and a gradient penalty improvement in the loss function are introduced to generate effective fault data and improve the classification accuracy. The experimental results of the gas turbine test bench demonstrate that the proposed method can generate effective fault samples as a supplementary set of fault samples to balance the dataset, effectively improve the fault classification and diagnosis performance of gas turbine rotors in the case of small samples, and provide an effective method for gas turbine fault diagnosis.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Engineering Diagnostics and Reliability · Machine Fault Diagnosis Techniques · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical and Electrical Engineering, Beijing Information Science and Technology University, Beijing 100192, China
College of Mechanical Engineering and Applied Electronics Technology, Beijing University of Technology, Beijing 100124, China
Key Laboratory of Modern Measurement and Control Technology of Ministry of Education, Beijing Information Science and Technology University, Beijing 100192, China
Funding
National Natural Science Foundation of China
References (51)
Show source-provided references
1. Prognostics of gas turbine engine: An integrated approach10.1016/j.eswa.2015.07.003 ↗
2. Ahmadi, P., Saidi, M.H., and Dincer, I. (2014). Performance Assessment of a Hybrid Solid Oxide Fuel Cell-Gas Turbine Combined Heat and Power System. Progress in Exergy, Energy, and the Environment, Springer International Publishing.10.1007/978-3-319-04681-5_20 ↗
3. Gas turbine sensor validation through classification with artificial neural networks10.1016/j.apenergy.2011.03.047 ↗
4. Xia, F., Zhang, H., Peng, D., Li, H., and Su, Y. (2009). Turbine fault diagnosis based on fuzzy theory and SVM. Artificial Intelligence and Computational Intelligence, Springer International Publishing.10.1007/978-3-642-05253-8_73 ↗
5. Probabilistic failure analysis of hot gas path in a heavy-duty gas turbine using Bayesian networks10.1007/s13198-019-00848-z ↗
6. Application of integrated fuzzy logic and neural networks to the performance prediction of axial compressors10.1177/0957650915596877 ↗
7. Chen, J., Xu, C., Ying, Y., Li, J., Jin, Y., Zhou, H., Lin, Y., and Zhang, B. (2019, January 25–27). Gas-path Component Fault Diagnosis for Gas Turbine Engine: A Review. Proceedings of the 2019 Prognostics and System Health Management Conference (PHM-Qingdao), Qingdao, China.10.1109/PHM-Qingdao46334.2019.8942819 ↗
8. Comprehensive analysis of energy, exergy and exergo-economic of cogeneration of heat and power in a combined gas turbine and organic Rankine cycle10.1016/j.enconman.2015.02.067 ↗
9. An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines10.1016/j.neunet.2016.01.003 ↗
10. Hybrid solid oxide fuel cells-gas turbine systems for combined heat and power: A review10.1016/j.apenergy.2015.06.027 ↗
11. Fault diagnosis approach for rotating machinery based on dynamic model and computational intelligence10.1016/j.measurement.2014.09.045 ↗
12. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis10.1016/j.ymssp.2017.03.034 ↗
13. Multiwavelet transform and its applications in mechanical fault diagnosis—A review10.1016/j.ymssp.2013.09.015 ↗
14. Reconfigurable monitoring system for time-frequency analysis on industrial equipment through STFT and DWT10.1109/TII.2012.2221131 ↗
15. A fuzzy-based gas turbine fault detection and identification system for full and part-load performance deterioration10.1016/j.ast.2015.07.002 ↗
16. Performance-Based Gas Turbine Health Monitoring, Diagnostics, and Prognostics: A Survey10.1109/TR.2018.2822702 ↗
17. Failure and Metallurgical Defects Analysis of IN-738LC Gas Turbine Blades10.1016/j.engfailanal.2021.105213 ↗
18. A multi-nets ANN model for real-time performance-based automatic fault diagnosis of industrial gas turbine engines10.1007/s40430-017-0742-8 ↗
19. Application of higher order spectral features and support vector machines for bearing faults classification10.1016/j.isatra.2014.08.007 ↗
20. Gayme, D., Menon, S., Ball, C., Mukavetz, D., and Nwadiogbu, E. (2003, January 8). Fault diagnosis in gas turbine engines using fuzzy logic. Proceedings of the 2003 IEEE International Conference on Systems, Man and Cybernetics, Conference Theme—System Security and Assurance (Cat. No.03CH37483), Washington, DC, USA.
21. A new K-means singular value decomposition method based on self-adaptive matching pursuit and its application in fault diagnosis of rolling bearing weak fault10.1177/1550147720920781 ↗
22. Gas turbine monitoring using neural network dynamic nonlinear autoregressive with external exogenous input modelling10.1016/j.matcom.2020.07.017 ↗
23. Rao, A., Satish, T.N., Nambiar, A.S., Jana, S., Naidu, V.P.S., Uma, G., and Umapathy, M. (2020). Challenges in Engine Health Monitoring Instrumentation during Developmental Testing of Gas Turbine Engines. Proceedings of the National Aerospace Propulsion Conference, Springer.
24. Gas path fault diagnosis for gas turbine group based on deep transfer learning10.1016/j.measurement.2021.109631 ↗
25. Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration10.1364/BOE.8.000579 ↗
26. Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis10.1177/0954406219840381 ↗
27. Method for fault diagnosis of bearing based on transfer learning with VGG16 model
28. Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis10.1016/j.ymssp.2021.108139 ↗
29. Bharti, V., Biswas, B., and Shukla, K.K. (2021). EMOCGAN: A novel evolutionary multiobjective cyclic generative adversarial network and its application to unpaired image translation. Neural Comput. Appl., 1–15.10.1007/s00521-021-05975-y ↗
30. A case study of conditional deep convolutional generative adversarial networks in machine fault diagnosis10.1007/s10845-020-01579-w ↗
31. Enhanced generative adversarial network for extremely imbalanced fault diagnosis of rotating machine10.1016/j.measurement.2021.109467 ↗
32. FaultFace: Deep Convolutional Generative Adversarial Network (DCGAN) based Ball-Bearing Failure Detection Method10.1016/j.ins.2020.06.060 ↗
33. Enhanced generative adversarial networks for fault diagnosis of rotating machinery with imbalanced data10.1088/1361-6501/ab3072 ↗
34. DCGAN Based Data Augmentation for Tomato Leaf Disease Identification10.1109/ACCESS.2020.2997001 ↗
35. An adaptive deep convolutional neural network for rolling bearing fault diagnosis10.1088/1361-6501/aa6e22 ↗
36. Dewi, C., Chen, R.C., Liu, Y.T., and Tai, S.-K. (2021). Synthetic Data generation using DCGAN for improved traffic sign recognition. Neural Comput. App., 1–16.10.1007/s00521-021-05982-z ↗
37. Li, J., Zhao, B., Wu, K., Dong, Z., Zhang, X., and Zheng, Z. (2021). A Representation Generation Approach of Transmission Gear Based on Conditional Generative Adversarial Network. Actuators, 10.10.3390/act10050086 ↗
38. Imputation of Missing Data with Class Imbalance using Conditional Generative Adversarial Networks10.1016/j.neucom.2021.04.010 ↗
39. Generative Adversarial Networks with Comprehensive Wavelet Feature for Fault Diagnosis of Analog Circuits10.1109/TIM.2020.2969008 ↗
40. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv.
41. Remaining useful life prediction of planet bearings based on conditional deep recurrent generative adversarial network and action discovery10.1007/s12206-020-1202-4 ↗
42. Data Augmentation Using DCGAN for Improved Fault Detection of High Voltage Shunt Reactor10.1088/1742-6596/1944/1/012012 ↗
43. Highly accurate machine fault diagnosis using deep transfer learning10.1109/TII.2018.2864759 ↗
44. Gearbox fault identification and classification with convolutional neural networks
45. Assessment of Data Suitability for Machine Prognosis Using Maximum Mean Discrepancy10.1109/TIE.2017.2777383 ↗
46. Construction of Health Indicators for Rotating Machinery Using Deep Transfer Learning with Multiscale Feature Representation10.1109/TIM.2021.3057498 ↗
47. (2020). Imbalanced Fault Classification of Bearing via Wasserstein Generative Adversarial Networks with Gradient Penalty. Shock Vib., 2020, 8836477.10.1155/2020/8836477 ↗
48. Simultaneous multi-slice image reconstruction using regularized image domain split slice-GRAPPA for diffusion MRI10.1016/j.media.2021.102000 ↗
49. Rolling bearing fault diagnosis using an optimization deep belief network10.1088/0957-0233/26/11/115002 ↗
50. Gearbox Fault Diagnosis based on Multi-Scale Deep Residual Learning and Stacked LSTM Model10.1016/j.measurement.2021.110099 ↗
51. A novel transfer learning fault diagnosis method based on Manifold Embedded Distribution Alignment with a little labeled data10.1007/s10845-020-01657-z ↗