Data analysis techniques for the visualization and classification of historical vehicle engines’ health status using data-driven solutions

Stefano Carrino; Luca  Meyer; Jonathan Dreyer; Brice Chalançon; Alejandro Roda-Buch; Laura Brambilla

doi:10.14568/cp30818

Authors

Stefano Carrino HES-SO // University of Applied Sciences and Arts Western Switzerland, Haute Ecole Arc Ingénierie, Espace de l’Europe 11, 2000 Neuchatel, Switzerland https://orcid.org/0000-0001-5171-6541
Luca Meyer HES-SO // University of Applied Sciences and Arts Western Switzerland, Haute Ecole Arc Ingénierie, Espace de l’Europe 11, 2000 Neuchatel, Switzerland
Jonathan Dreyer HES-SO // University of Applied Sciences and Arts Western Switzerland, Haute Ecole Arc Ingénierie, Espace de l’Europe 11, 2000 Neuchatel, Switzerland
Brice Chalançon Association de Gestion du Musée National de l’Automobile, 188 Av. de Colmar, 68100 Mulhouse, France
Alejandro Roda-Buch HES-SO // University of Applied Sciences and Arts Western Switzerland, Haute Ecole Arc Conservation-restauration, Espace de l’Europe 11, 2000 Neuchatel, Switzerland; Ecole Polytechnique Fédérale de Lausanne, EPFL CH-1015, Lausanne, Switzerland https://orcid.org/0000-0002-4036-1017
Laura Brambilla Haute Ecole Arc Conservation-resturation - HES-SO University of Applied Sciences and Arts of Western Switzerland https://orcid.org/0000-0002-7197-6524

DOI:

https://doi.org/10.14568/cp30818

Keywords:

Machine learning, Cultural heritage, Non-invasive monitoring, Acoustic emission

Abstract

In the field of cultural heritage, the use of non-destructive techniques to determine the state
of conservation of an artifact is of the utmost importance, to avoid damage to the object itself.
In this paper, we present a data pipeline and several machine learning techniques for the visualization, analysis and characterization of engines in historical vehicles. The paper investigates the use of vibro-acoustic signals acquired from the engines in different states of conservation and working conditions to train machine learning solutions. Data are classified according to their state of health and the presence of anomalies. The t-SNE algorithm is used for dimensionality reduction for data visualization. The machine learning algorithms tested
showed encouraging performance in associating acoustic emission data with the engine signature, the type of anomaly and the working conditions. Nevertheless, a larger dataset would allow us to improve and strengthen the results.

Downloads

Download data is not yet available.

References

Ashton, J.; Hallam, D., ‘The conservation of functional objects – An ethical dilemma’, AICCM Bulletin 16(3) (1990) 19-26, https://doi.org/10.1179/bac.1990.16.3.003.

Lemos, M.; Tissot, I., ‘Reflections on the conservation challenges of scientific and technological objects’, Conservar Património 33 (2020) 24-31, https://doi.org/10.14568/cp2018044.

Wain, A., ‘The importance of movement and operation as preventive conservation strategies for heritage machinery’, Journal of the American Institute for Conservation 56(2) (2017) 81-95, https://doi.org/10.1080/01971360.2017.1326238.

Newey, H., ‘Conservation and the preservation of scientific and industrial collections’, Studuies in Conservation 45(sup1) (2000) 137-139, https://doi.org/10.1179/sic.2000.45.Supplement-1.137.

Pye, E., ‘Challenges of conservation: working objects’, Science Museum Group Journal 6 (2016), https://dx.doi.org/10.15180/160608/001.

Scruby, C. B., ‘An introduction to acoustic emission’, Journal of Physics E Scientific Instruments 20(8) (1987) 946-953, https//doi.org/10.1088/0022-3735/20/8/001.

Delvecchio, S.; Bonfiglio, P.; Pompoli, F., ‘Vibro-acoustic condition monitoring of internal combustion engines: a critical review of existing techniques’, Mechanical Systems and Signal Processing 99 (2018) 661-683, https://doi.org/10.1016/j.ymssp.2017.06.033.

Kaul, B. C.; Lawler, B.; Zahdeh, A., ‘Engine diagnostics using acoustic emissions sensors’, SAE International Journal of Engines 9(2) (2016) 684-692, https://doi.org/10.4271/2016-01-0639.

Douglas, R. M.; Steel, J. A.; Reuben, R. L., ‘A study of the tribological behaviour of piston ring/cylinder liner interaction in diesel engines using acoustic emission’, Tribology International 39(12) (2006) 1634-1642, https://doi.org/10.1016/j.triboint.2006.01.005.

Nivesrangsan, P.; Steel, J. A.; Reuben, R. L., ‘Source location of acoustic emission in diesel engines’, Mechanical Systems and Signal Processing 21(2) (2007) 1103-1114, https://doi.org/10.1016/j.ymssp.2005.12.010.

Wu, J.-D.; Liu, C.-H., ‘An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network’, Expert Systems with Applications 36(3) (2009) 4278-4286, https://doi.org/10.1016/j.eswa.2008.03.008.

Johansson, S.; Nilsson, P. H.; Ohlsson, R.; Rosén, B.-G., ‘Experimental friction evaluation of cylinder liner/piston ring contact’, Wear 271(3-4) (2011) 625-633, https://doi.org/10.1016/j.wear.2010.08.028.

Wei, N.; Gu, J. X.; Gu, F.; Chen, Z.; Li, G.; Wang, T.; Ball, A. D., ‘An Investigation into the acoustic emissions of internal combustion engines with modelling and wavelet package analysis for monitoring lubrication conditions’, Energies 12(4) (2019) 640-659, https://doi.org/10.3390/en12040640.

Łukomski, M.; Bratasz, Ł; Hagan, E.; Strojecki, M.; Laudato Beltran, V., ‘Acoustic emission monitoring for cultural heritage’, Getty Conservation Institute, Los Angeles (2020).

Thickett, D.; Cheung, C. S.; Liang, H.; Twydle, J.; Maev, R. G.; Gavrilov, D., ‘Using non-invasive nondestructive techniques to monitor cultural heritage objects’, Insight - Non-destructive testing and Condition Monitoring 59(5) (2017) 230-234, https://doi.org/10.1784/insi.2017.59.5.230.

Le Conte, S.; Vaiedelich, S.; Thomas, J. H.; Muliava, V.; de Reyer, D.; Maurin, E., ‘Acoustic emission to detect xylophagous insects in wooden musical instrument’, Journal of Cultural Heritage 16(3) (2015) 338-343, https://doi.org/10.1016/j.culher.2014.07.001.

Chalançon, B., Les mesures d’émission acoustique appliquées aux moteurs d’automobiles de collection patrimoniale comme outil de diagnostic avant la remise en fonctionnement, Master dissertation, Haute Ecole Arc Conservation-restauration (HES-SO), Neuchâtel (2019) https://doc.rero.ch/record/327368 (accessed 2023-03-30).

Roda Buch, A.; Cornet, E.; Rapp, G.; Chalançon, B.; Mischler, S.; Brambilla, L., ‘Development of a diagnostic tool based on acoustic emission techniques’, in 500 ans de tribologie, Presses des Mines, Paris (2021) 147-152.

Roda Buch, A.; Cornet, E.; Rapp, G.; Chalançon, B.; Mischler, S.; Brambilla, L., ‘Fault detection and diagnosis of historical vehicle engines using acoustic emission techniques’, Acta Imeko 10(1) (2021) 77-83, https://doi.org/10.21014/acta_imeko.v10i1.853.

Brambilla, L.; Chalançon, B.; Roda Buch, A.; Cornet, E.; Rapp, G.; Mischler, S., ‘Acoustic emission techniques for the detection of simulated failures in historical vehicles engines’, The European Physical Journal Plus 136(6) (2021) 641, https://doi.org/10.1140/epjp/s13360-021-01611-9.

Chalançon, B.; Roda Buch, A.; Cornet, E.; Rapp, G.; Weisser, T.; Brambilla, L., ‘Acoustic emission monitoring as a non-invasive tool to assist the conservator in the reactivation and maintenance of historical vehicle engines’, Studies in Conservation (2023), https://doi.org/10.1080/00393630.2023.2183808.

Carrino, S.; Guerne, J.; Dreyer, J.; Ghorbel, H.; Schorderet, A.; Montavon, R., ‘Machining quality prediction using acoustic sensors and machine learning’, Proceedings 63(1) (2020) 31, https://doi.org/10.3390/proceedings2020063031.

Li, Z.; Li, J.; Wang, Y.; Wang, K., ‘A deep learning approach for anomaly detection based on SAE and LSTM in mechanical equipment’, The International Journal of Advanced Manufacturing Technology 103 (2019) 499-510, https://doi.org/10.1007/s00170-019-03557-w.

Malhotra, P.; Vig, L.; Shroff, G.; Agarwal, P., ‘Long short term memory networks for anomaly detection in time series’, in Proceedings of European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN, i6doc.com publ., Bruges (2015) 89-94, https://www.esann.org/proceedings/2015 (accessed 2023-07-03).

Kim, D.; Antariksa, G.; Handayani, M. P.; Lee, S.; Lee, J., ‘Explainable anomaly detection framework for maritime main engine sensor data’, Sensors 21(15) (2021) 5200, https://doi.org/10.3390/s21155200.

Kim, J-M.; Baik, J., ‘Anomaly detection in sensor data’, Journal of Applied Reliability 18(1) (2018) 20-32, https://koreascience.kr/article/JAKO201815565837435.pdf (accessed 2023-07-03).

Gokhale, M. Y.; Khanduja, D. K., ‘Time domain signal analysis using wavelet packet decomposition approach’, International Journal of Communications, Network and System Sciences 3(3) (2010) 321-329, https://doi.org/10.4236/ijcns.2010.33041.

Yu, Y.; Si, X.; Hu, C.; Zhang, J., ‘A review of recurrent neural networks: LSTM cells and network architectures’, Neural computation 31(7) (2019) 1235-1270, https://doi.org/10.1162/neco_a_01199.

Shensa, M. J., ‘The discrete wavelet transform: wedding the a trous and Mallat algorithms’, IEEE Transactions on Signal Processing 40(10) (1992) 2464-2482, https://doi.org/10.1109/78.157290.

Van der Maaten, L.; Hinton, G., ‘Visualizing data using t-SNE’, Journal of Machine Learning Research 9(11) (2008) 2579-2605, https://www.jmlr.org/papers/volume9/vandermaaten08a/vandermaaten08a.pdf (accessed 2023-07-05).

‘Shankarpandala - lazypredict’, in Github, https://github.com/shankarpandala/lazypredict (accessed 2023-07-03).