Publicado

2023-03-03

Vehicle maintenance management based on machine learning in agricultural tractor engines

Gestión del mantenimiento de vehículos basada en el aprendizaje autónomo en motores de tractores agrícolas

DOI:

https://doi.org/10.15446/dyna.v90n225.103612

Palabras clave:

autonomous learning; classification algorithm; predictive maintenance; vibrations (en)
aprendizaje autónomo; algoritmo de clasificación; mantenimiento predictivo; vibraciones (es)

Autores/as

The objective of this work is to use the autonomous learning methodology as a tool in vehicle maintenance management. In obtaining data, faults in the fuel supply system have been simulated, causing anomalies in the combustion process that are easily detectable by vibrations obtained from a sensor in the engine of an agricultural tractor. To train the classification algorithm, 4 engine states were used: BE (optimal state), MEF1, MEF2, MEF3 (simulated failures). The applied autonomous learning is of the supervised type, where the samples were initially characterized and labeled to create a database for the execution of the training. The results show that the training carried out within the classification algorithm has an efficiency greater than 90%, which indicates that the method used is applicable in the management of vehicle maintenance to predict failures in engine operation.

El objetivo del trabajo es utilizar la metodología de aprendizaje autónomo como herramienta en la gestión del mantenimiento de vehículos. En la obtención de datos se han simulado fallos en el sistema de alimentación de combustible que provocan anomalías en el proceso de combustión que son fácilmente detectables por vibraciones obtenidas de un sensor en el motor de un tractor agrícola. Para entrenar el algoritmo de clasificación se utilizaron 4 estados del motor: BE (estado óptimo), MEF1, MEF2, MEF3 (fallas simuladas). El aprendizaje autónomo aplicado es del tipo supervisado, donde inicialmente se caracterizó y rotuló las muestras para crear una base de datos para la ejecución del entrenamiento. Los resultados muestran que el entrenamiento realizado dentro del algoritmo de clasificación tiene una eficiencia superior al 90%, lo que indica que el método utilizado es aplicable en la gestión del mantenimiento de vehículos para predecir fallas en el funcionamiento del motor.

Referencias

Zhang, Z., Tang, Q. and Chica, M., Maintenance costs and makespan minimization for assembly permutation flow shop scheduling by considering preventive and corrective maintenance, J. Manuf. Syst. 59(April), ppp. 549-564, 2021. DOI: DOI: https://doi.org/10.1016/j.jmsy.2021.03.020

Wang, J. and Miao, Y., Optimal preventive maintenance policy of the balanced system under the semi-Markov model, Reliab. Eng. Syst. Saf. 213(December2020), art. 107690, 2021. DOI: https://doi.org/10.1016/j.ress.2021.107690

Sahba, R,. Radfar, R., Ghatari, A.R., and Ebrahimi, A.P., Development of Industry 4.0 predictive maintenance architecture for broadcasting chain, Adv. Eng. Informatics, 49(August), art. 101324, 2021. DOI: https://doi.org/10.1016/j.aei.2021.101324

Kanawaday, A. and Sane, A., Machine learning for predictive maintenance of industrial machines using IoT sensor data, Proc. IEEE Int. Conf. Softw. Eng.Serv. Sci. ICSESS 2017–Novem, 2018, pp. 87-90. DOI: https://doi.org/10.1109/ICSESS.2017.8342870

Yahia, S., Said, S, and Zaied, M., Wavelet extreme learning machine and deep learning for data classification, Neurocomputing , 470(January), pp. 280-289, 2022. DOI: https://doi.org/10.1016/j.neucom.2020.04.158

He, M. and Zhang, L., Machine learning and symbolic regression investigation on stability of MXene materials, Comput. Mother. Sci. 196(August), art. 110578, 2021. DOI: https://doi.org/10.1016/j.commatsci.2021.110578

Kirschner, K. and Realff, M., A joint optimization and machine learning method for a selection and grouping problem, Chem. Eng. Res. Des., 77(4), pp. 271-280, 1999. DOI: https://doi.org/10.1205/026387699526205

Amihai, I., Gitzel, R., Kotriwala, A., Pareschi, D., Subbiah, S. and Sosale, G., An industrial case study using vibration data and machine learning to predict asset health, Proceeding - 2018 20th IEEE Int. Conf. Bus. Informatics, CBI 2018, pp. 178-185. DOI: https://doi.org/10.1109/CBI.2018.00028

Jardine, A., Lin, D. and Banjevic, D., A review on machinery diagnostics and prognostics implementing condition-based maintenance, Mech. Syst. SignalProcess. 20(7), pp. 1483-1510, 2006. DOI: https://doi.org/10.1016/j.ymsspp.2005.09.012

Mathew, V., Toby, T., Singh, V., Rao, B. and Kumar, M., Prediction of Remaining Useful Lifetime (RUL) of turbofan engine using machine learning, in: IEEE Int. Conf. Circuits Syst. ICCS 2017 2018–January, 2018, pp. 306-311. DOI: https://doi.org/10.1109/ICCS1.2017.8326010

Li, Q., Xiong, Q., Ji, S., Yu, Y., Wu, C. and Gao, M., Incremental semi-supervised extreme learning machine for mixed data stream classification, Expert Syst. Appp. 185(1), art.. 115591, 2021. DOI: https://doi.org/10.1016/j.eswa.2021.115591

Omar, F., Selim, M. and Emam, S., Time and frequency analyzes of dual-fuel engine block vibration, Fuel, 203, pp. 884-893, 2017. DOI: https://doi.org/10.1016/J.FUEL.2017.05.034

Praveenkumar, T., Saimurugan, M., Krishnakumar, P. and Ramachandran, K., Fault diagnosis of automobile gearbox based on machine learning techniques, Procedia Eng. 97, pp. 2092-2098, 2014. DOI: https://doi.org/10.1016/j.proeng.2014.12.452

Dimensions

PlumX

Visitas a la página del resumen del artículo

1364

Descargas

Los datos de descarga aún no están disponibles.

Cómo citar

[1]
“Gestión del mantenimiento de vehículos basada en el aprendizaje autónomo en motores de tractores agrícolas”, DYNA, vol. 90, no. 225, pp. 22–28, Mar. 2023, doi: 10.15446/dyna.v90n225.103612.