The present work deals with intelligent vehicle fleet maintenance and
prediction. We propose an approach based primarily on the history of failures
data and on the geographical data system. The objective here is to predict the
date of failures for a fleet of vehicles in order to allow the maintenance
department to efficiently deploy the proper resources; we further provide
specific details regarding the origins of failures, and finally, give
recommendations. This study used the Société de transport de Montréal (STM)’s
historical bus failure data as well as weather data from Environment Canada. We
thank Facebook’s Prophet, Simple Feed-forward, and Beats algorithms (Uber), we
proposed a set of computer codes that allow us to identify the 20% of buses
that are responsible for the 80% of failures by mean of the failure history.
Then, we deepened our study on the unreliable equipments identified during the
diffusion of our computer codeThis allowed us to propose probable predictions of the dates of future
failures. To ensure the validity of the proposed algorithm, we carried out
simulations with more than 250,000
data. The results obtained are similar to the predicted theoretical values.
References
[1]
Cachada, A., Barbosa, J., Leitão, P., et al. (2018) Maintenance 4.0: Intelligent and Predictive Maintenance System Architecture. IEEE 23rd International Conference on Emerging Technologies and Factory Automation (ETFA), Turin, 4-7 September 2018, 139-146. https://doi.org/10.1109/ETFA.2018.8502489
[2]
Chen, C., Liu, Y., Sun, X.F., et al. (2020) Automobile Maintenance Modelling Using gcForest. 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), Hong Kong, 20-21 August 2020, 600-605. https://doi.org/10.1109/CASE48305.2020.9216745
[3]
Mobley, R.K. (2002) An Introduction to Predictive Maintenance. 2nd Edition, Butterworth-Heinemann, Oxford. https://doi.org/10.1016/B978-075067531-4/50006-3
[4]
Mou, L.T., Mao, S.S., Xie, H.T. and Chen, Y.Y. (2019) Structured Behaviour Prediction of On-Road Vehicles via Deep Forest. Electronics Letters, 55, 452-455. https://doi.org/10.1049/el.2019.0472
[5]
Liu, X.L., et al. (2019) Deep Forest Based Intelligent Fault Diagnosis of Hydraulic Turbine. Journal of Mechanical Science and Technology, 33, 2049-2058. https://doi.org/10.1007/s12206-019-0408-9
[6]
Hu, G.Z., Li, H.F., Xia, Y.Q. and Luo, L.X. (2018) A Deep Boltzmann Machine and Multi-Grained Scanning Forest Ensemble Collaborative Method and Its Application to Industrial Fault Diagnosis. Elsevier, Amsterdam. https://doi.org/10.1016/j.compind.2018.04.002
[7]
Liu, Q., Gao, H.L., You, Z.C., et al. (2018) Gcforest-Based Fault Diagnosis Method For Rolling Bearing. 2018 Prognostics and System Health Management Conference, Chongqing, 26-28 October 2018, 572-577. https://doi.org/10.1109/PHM-Chongqing.2018.00103
[8]
Taylor, S.J. and Letham, B. (2017) Prophet: Forecasting at Ccale. Computer Science. https://doi.org/10.7287/peerj.preprints.3190v2
[9]
Žunić, E., Korjenić, K., et al. (2020) Application of Facebook’s Prophet Algorithm for Successful Sales Forecasting Based on Real-World Data. International Journal of Computer Science & Information Technology, 12, 23-36. https://doi.org/10.5121/ijcsit.2020.12203
[10]
Zhoul, L., Chenl, M. and Ni, Q.J. (2020) A Hybrid Pophet—LSTM Model for Prediction of Air Quality Index. 2020 IEEE Symposium Series on Computational Intelligence (SSCI), Canberra, 1-4 December 2020, 595-601. https://doi.org/10.1109/SSCI47803.2020.9308543
[11]
Panicker, V. (2021) AOD Forecasting Using Prophet Model across Four Major Urban Areas in India. 2021 6th International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, 25-27 March 2021, 400-405. https://doi.org/10.1109/WiSPNET51692.2021.9419423
[12]
Gong, F.X., Han, N.H., Li, D.Z. and Tian, S.M. (2020) Trend Analysis of Building Power Consumption Based on Prophet Algorithm. 2020 Asia Energy and Electrical Engineering Symposium (AEEES), Chengdu, 29-31 May 2020, 1002-1006. https://doi.org/10.1109/AEEES48850.2020.9121548
[13]
Septiani, R., et al. (2021) Applied of Feed-Forward Neural Network and Facebook Prophet Model for Train Passengers Forecasting. Journal of Physics: Conference Series, 1776, Article ID: 012057. https://doi.org/10.1088/1742-6596/1776/1/012057
[14]
Melnychuk, M.C., Murphy, P.R., Robertson, I.H., et al. (2020) Prediction of Attentional Focus from Respiration with Simple Feed Forward and Time Delay Neural Networks. Springer Science and Business Media, Berlin. https://doi.org/10.1007/s00521-020-04841-7
[15]
Cohen, D., Foley, J., Zamani, H., et al. (2018) Universal Approximation Functions for Fast Learning to Rank: Replacing Expensive Regression Forest with Simple Feed-Forward Networks. Association for Computing Machinery, New York. https://doi.org/10.1145/3209978.3210137
[16]
Jat, G.L., Mahajan, A., Singh, K. and Shimi, S.L. (2016) A Simple Feed Forward Fuzzy Direct Torque Control of DSP Induction Motor Drive. 2016 International Conference on Electrical Power and Energy Systems (ICEPES), Bhopal, 14-16 December 2016, 284-289. https://doi.org/10.1109/ICEPES.2016.7915944
[17]
Lin, Z.N., Chen, M.Y., Zhan, J. and Yao, W. (2020) Prediction Algorithm for Micro-Loudspeaker Diaphragm Displacement Based on PG-LSTM with 44% MSE Reduction. 2020 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA), Nanjing, 23-25 November 2020, 104-105. https://doi.org/10.1109/ICTA50426.2020.9332102
