Reducing Air Pressure System Repair Costs in Scania Trucks through Deep Learning

Taghandiki, Kazem; Dallakehnejad, Morteza; Rahimi Asiabaraki, Hossein

doi:10.48301/jear.2024.447671.1022

Reducing Air Pressure System Repair Costs in Scania Trucks through Deep Learning

Document Type : Original Article

Authors

Kazem Taghandiki ¹

Morteza Dallakehnejad ²

Hossein Rahimi Asiabaraki ³

¹ Department of Computer Engineering, Technical and Vocational University (TVU), Tehran, Iran

² Assistant Professor, Department of Mechanical Engineering, Technical and Vocational University (TVU),

³ Department of Mechanical Engineering, Technical and Vocational University (TVU), Tehran, Iran

10.48301/jear.2024.447671.1022

Abstract

Air pressure systems play a fundamental role in Scania trucks because the proper functioning of the brake and gear shifting systems of these vehicles relies on the health of the air pressure system. The presence of sensors in the air pressure system gathers various information about its status, which can be stored and analyzed in the form of datasets. Using machine learning algorithms to detect faults in the air pressure system prevents manual inspection at different time intervals, thus preventing material and time costs. Many efforts have been made to detect faults in the air pressure system through the collected datasets from sensors of the various components of Scania trucks using traditional machine learning algorithms such as decision trees, KNN, Random Forest and SVM, but they still lack sufficient accuracy and speed in data processing. However, since the number of records collected at different intervals by the Electronic Control Unit (ECU) is very high, novel machine learning algorithms like deep learning can be used to increase accuracy and speed in detecting faults in Scania truck air pressure systems. In this article, feature selection and deep learning algorithms have been used to detect and predict faults in the air pressure system of heavy trucks. The results and observations showed that the output of the evaluation parameters of the deep learning algorithm has an accuracy rate of 98.66%, a recall rate of 63.47%, and a f-measure rate of 68.99%.

Keywords

Deep Learning

Air Pressure System

Preprocessing

Feature Selection

Dataset

Subjects

Computer Engineering

[1] Selvi, K. T., Praveena, N., Pratheksha, K., Ragunanthan, S., & Thamilselvan, R. (2022, February 23-25). Air Pressure System Failure Prediction and Classification in Scania Trucks using Machine Learning [Conference session]. Second International Conference on Artificial Intelligence and Smart Energy. Coimbatore, India. https://doi.org/ 10.1109/ICAIS53314.2022.9742716

[2] Cerqueira, V., Pinto, F., Sá, C., & Soares, C. (2016). Combining Boosted Trees with Metafeature Engineering for Predictive Maintenance. In H. Boström, A. Knobbe, C. Soares, & P. Papapetrou (Eds.), Advances in Intelligent Data Analysis XV (pp. 393-397). Springer International Publishing. https://doi.org/10.1007/978-3-319-46349-0_35

[3] Rawat, S. (2022). Predict component failure related with air pressure system at scania trucks using various machine learning methods. 1-10. https://doi.org/10.1314 0/RG.2.2.29587.20003

[4] Yazdinejad, A., Bohlooli, A., & Jamshidi, K. (2018). Efficient design and hardware implementation of the OpenFlow v1.3 Switch on the Virtex-6 FPGA ML605. The Journal of Supercomputing, 74(3), 1299-1320. https://doi.org/10.1007/s1122 7-017-2175-7

[5] Akarte, M. M., & Hemachandra, N. (2018, December 16-19). Predictive maintenance of air pressure system using boosting trees: A machine learning approach [Conference session]. 51st Annual Convention of Operational Research Society of India & International Conference, Mumbai, India. https://mrugankakarte.github.io/fil es/ORSI2018.pdf

[6] Costa, C. F., & Nascimento, M. A. (2016). IDA 2016 Industrial Challenge: Using Machine Learning for Predicting Failures. In H. Boström, A. Knobbe, C. Soares, & P. Papapetrou (Eds.), Advances in Intelligent Data Analysis XV (pp. 381-386). Springer International Publishing. https://doi.org/10.1007/978-3-319-46349-0_33

[7] Costa, L. M. D. (2019). Voting Nearest Neighbors: SVM Constraints Selection Algorithm Based on K-Nearest Neighbors [Doctor, University of Rhode Island]. South Kingstown, Rhode Island. https://www.proquest.com/openview/5c27a7f79ad0ddae70e 709d9236e0d07/1.pdf?pq-origsite=gscholar&cbl=18750&diss=y#page=133

[8] Gondek, C., Hafner, D., & Sampson, O. R. (2016). Prediction of Failures in the Air Pressure System of Scania Trucks Using a Random Forest and Feature Engineering. In H. Boström, A. Knobbe, C. Soares, & P. Papapetrou (Eds.), Advances in Intelligent Data Analysis XV (pp. 398-402). Springer International Publishing. https://doi.org/1 0.1007/978-3-319-46349-0_36

[9] Lokesh, Y., Nikhil, K. S. S., Kumar, E. V., & Mohan, B. G. K. (2020, May 13-15). Truck APS Failure Detection using Machine Learning [Conference session]. 4th International Conference on Intelligent Computing and Control Systems, Madurai, India. http s://doi.org/10.1109/ICICCS48265.2020.9121019

[10] Ozan, E. C., Riabchenko, E., Kiranyaz, S., & Gabbouj, M. (2016). An Optimized k-NN Approach for Classification on Imbalanced Datasets with Missing Data. In H. Boström, A. Knobbe, C. Soares, & P. Papapetrou (Eds.), Advances in Intelligent Data Analysis XV (pp. 387-392). Springer International Publishing. https://doi.org/10.1007/ 978-3-319-46349-0_34

[11] Rafsunjani, S., Safa, R. S., Al Imran, A., Rahim, M. S., & Nandi, D. (2019). An empirical comparison of missing value imputation techniques on APS failure prediction. International Journal of Information Technology and Computer Science, 11(2), 21-29. https://doi.org/10.5815/ijitcs.2019.02.0

[12] Syed, M. N., Hassan, M. R., Ahmad, I., Hassan, M. M., & Albuquerque, V. H. C. D. (2021). A Novel Linear Classifier for Class Imbalance Data Arising in Failure-Prone Air Pressure Systems. Institute of Electrical and Electronics Engineers Access, 9, 4211-4222. https://doi.org/10.1109/ACCESS.2020.3047790

[13] Nakhodchi, S., Zolfaghari, B., Yazdinejad, A., & Dehghantanha, A. (2021, December 13-15). SteelEye: An Application-Layer Attack Detection and Attribution Model in Industrial Control Systems using Semi-Deep Learning [Conference session]. 18th International Conference on Privacy, Security and Trust, Auckland, New Zealand. https://doi.org/10.1109/PST52912.2021.9647777

[14] Rabieinejad, E., Yazdinejad, A., Parizi, R. M., & Dehghantanha, A. (2023). Generative adversarial networks for cyber threat hunting in ethereum blockchain. Distributed Ledger Technologies: Research and Practice, 2(2), 1-19. https://doi.org/10.114 5/3584666

[15] Yazdinejad, A., Parizi, R. M., Srivastava, G., & Dehghantanha, A. (2020, December 7-11). Making Sense of Blockchain for AI Deepfakes Technology [Conference session]. 2020 Institute of Electrical and Electronics Engineers Globecom Workshops, Taipei, Taiwan. https://doi.org/10.1109/GCWkshps50303.2020.9367545

[16] Yazdinejad, A., Dehghantanha, A., Parizi, R. M., & Epiphaniou, G. (2023). An optimized fuzzy deep learning model for data classification based on NSGA-II. Neurocomputing, 522(4), 116-128. https://doi.org/10.1016/j.neucom.2022.12.027

[17] Sisk, M., Majlis, M., Page, C., & Yazdinejad, A. (2023). Analyzing xai metrics: Summary of the literature review. Authorea Preprints, 1-6. https://doi.org/10.36227/tec hrxiv.21262041.v1

[18] Yazdinejad, A., Dehghantanha, A., Parizi, R. M., Hammoudeh, M., Karimipour, H., & Srivastava, G. (2022). Block Hunter: Federated Learning for Cyber Threat Hunting in Blockchain-Based IIoT Networks. Institute of Electrical and Electronics Engineers Transactions on Industrial Informatics, 18(11), 8356-8366. https://doi.org/10. 1109/TII.2022.3168011

[19] Yazdinejad, A., Parizi, R. M., Dehghantanha, A., Srivastava, G., Mohan, S., & Rababah, A. M. (2020). Cost optimization of secure routing with untrusted devices in software defined networking. Journal of Parallel and Distributed Computing, 143, 36-46. https://doi.org/10.1016/j.jpdc.2020.03.021

[20] Scania. (2017). APS Failure at Scania Trucks [Data set]. University of California Irvine Machine Learning Repository. https://doi.org/10.24432/C51S51

[21] Uska, M. Z., Wirasasmita, R. H., Usuluddin, U., & Arianti, B. D. D. (2020). Evaluation of rapidminer-aplication in data mining learning using persiva model. Edumatic: Jurnal Pendidikan Informatika, 4(2), 164-171. https://doi.org/10.29408/edumatic.v 4i2.2688

[22] Yazdinejad, A., Parizi, R. M., Dehghantanha, A., Zhang, Q., & Choo, K. K. R. (2020). An Energy-Efficient SDN Controller Architecture for IoT Networks With Blockchain-Based Security. Institute of Electrical and Electronics Engineers Transactions on Services Computing, 13(4), 625-638. https://doi.org/10.1109/TSC.2020.2966970

[23] Yazdinejad, A., Dehghantanha, A., Parizi, R. M., Srivastava, G., & Karimipour, H. (2023). Secure Intelligent Fuzzy Blockchain Framework: Effective Threat Detection in IoT Networks. Computers in Industry, 144(4), 103801. https://doi.org/10.1016/j.c ompind.2022.103801

[24] Caelen, O. (2017). A Bayesian interpretation of the confusion matrix. Annals of Mathematics and Artificial Intelligence, 81(3), 429-450. https://doi.org/10.1007/s10472-017-9564-8