Non-Vibrational Fault Analysis of Turbojet Engine Bearings by using Deep Neural Networks
Keywords:
Bearings, Turbojet Engines, Fault Analysis, Deep Neural NetworksAbstract
This paper depicts the implementation of deep neural networks in predicting common faults of the turbojet engine bearings by training the model with images and processing them by designing proper Deep Neural Network model apart from conventional vibration analysis methods, for faster detection of bearing health and reusability. The turbojet engines have higher main-shaft speeds operating at elevated temperature conditions, reducing the bearing estimated life and thus the need of schedule maintenance. This system can identify some of the bearing damages like cracks, dents, fatigue, fretting and smearing conditions prevailing due to thermal effects, high axial and radial loads over the main-shaft, propeller shank and auxiliary systems bearings. It finally assists the aircraft maintenance engineers and technicians to reach to the conclusions of bearing conditions by taking pictures of bearings from any device and fetching them to the system for better results of bearing conditions.
Downloads
References
H. Shen, S. Li, D. Gu, H. Chang, Bearing defect inspection based on machine vision, Measurement. 45 (2012)719-733.
https://doi.org/10.1016/j.measurement.2011.12.018.B. L. Averbach, E.N. Bamberger, Analysis of Bearing Incidents in Aircraft Gas Turbine Mainshaft Bearings, Tribology Transactions. 34 (1991) 241-247. https://doi.org/10.1080/1040200910808982032.
B. Samanta, K.R. Al-Balushi, S.A. Al-Araimi, Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection, Engineering Applications of Artificial Intelligence. 16 (2003)657- 665.https://doi.org/10.1016/j.engappai.2003.09.006.
For New Technology Network, CAT. No. 8102 – III/E, NTN Aerospace Bearings. https:// www.ntnamericas.com/en/website/documents/brochur es-and
literature/catalogs/aerospace_bearings_8102_III_lowr es.pdf
H. Heshmat, M.J. Tomaszewski, J.F. Walton II, Small Gas Turbine Engine operating with High-Temperature Foil Bearings, in: Volume 5: Marine; Microturbine and Small Turbomachinery; oil and Gas Applications; Structures and Dynamics, Parts A and B, ASMEDC, 2006. https://doi.org/10.1115/gt2006-90791.
Bearing Failure: Causes and Cures, 2001. Barden Precision Bearings.
J.R. Nygaard, M. Rawson, P. Danson, H.K.D.H. Bhadeshia, Bearing steel microstructures after aircraft gas turbine engine service, Materials Science and Technology.30(2014)1911-1918.https://doi.org/10.1179/1743284714y.000000054 8.
Bearing faults that can be detected with vibration monitoring. March 2011, Wilcoxon Research Inc., Meggitt.
K. Deák, I. Kocsis, A. Vámosi, Application of machine vision in manfacturing of bearings using ANN and SVM, in: Proceedings of the 9th International Conference on Applied Informatics, Volume 1, Eszterházy Károly College, 2015. https://doi.org/10.14794/icai.9.2014.1.295.
Rolling Bearing Damage, recognition of damage and bearing inspection.2001, Publ. No. WL 82 102/3 EA, FAG – Schaeffler Group Industrial.
V. Sze, Y.H. Chen, T.J. Yang, J.S. Emer, Efficient Processing of Deep neural Networks: A Tutorial and Survey, Proceedings of the IEEE. 105 (2017) 2295- 2329.https://doi.org/10.1109/jproc.2017.2761740.
[dataset] Juvith Ghosh, 2020. Turbojet-Bearing, GitHubRepository.https://github.com/Juvith/Turbojet Bearing.git
Nikhil B., Nicholas L., 2017. Fundamentals of Deep Learning, first ed. United States of America, O.Reilly. [13]Batch normalization in Neural Networks: https://towardsdatascience.com/batch-normalization in-neural-networks-1ac91516821c.
Batch Normalization – Speed up Neural Network Training, Ilango R – Medium: https://medium.com/@ilango100/batch-normalization speed-up-neural-network-training-245e39a62f85.
Mark Hudson B., Martin T.H., Howard B.D., Deep Learning Toolbox – User’s Guide, MATLAB 2018b. https://www.mathworks.com/products/deep
learning.html
Oliver. W.L., Neural Networks, lecture – 11, Colby College.http://cs.colby.edu/courses/F19/cs343/lectures /lecture11/Lecture11Slides.pdf
What are Max Pooling, Chris – MACHINECURVE: https://www.machinecurve.com/index.php/2020/01/30 /what-are-pooling-average-pooling-global-max pooling-and-global-average-pooling/
Fully Connected Layer: The brute force layer of a Machine Learning model, Surya Pratap Singh, OpenGenusIQ: https://iq.opengenus.org/fully connected-layer/
Softmax Layer by DeepAI: https://deepai.org/machine-learning-glossary-and terms/softmax-layer
Phil K. 2017. MATLAB Deep Learning with Machine Learning, Neural Networks and Artificial Intelligence, APress.
Vincent V., Andrew S., Mark Z.M., 2011. Improving the speed of neural networks on CPUs. Deep Learning and Unsupervised Feature Learning Workshop, NIPS, California.
A.M. HAY, The derivation of global estimates from a confusion matrix, International Journal of Remote Sensing.9(1998)1395-
https://doi.org/10.1080/01431168808954945.
Confusion Matrix in Machine Learning by GeeksforGeeks.https://www.geeksforgeeks.org/confus ion-matrix-machine-learning/
