نگهداری و تعمیرات پیش‌بینانه خودرو با استفاده از الگوریتم‌های یادگیری ماشین و الگوریتم‌های ترکیبی

ویسی, امید

doi:10.66224/jii.4.2.70

نگهداری و تعمیرات پیش‌بینانه خودرو با استفاده از الگوریتم‌های یادگیری ماشین و الگوریتم‌های ترکیبی

نوع مقاله : مقاله پژوهشی

نویسنده

امید ویسی

گروه مهندسی صنایع، دانشکده مهندسی و پرواز، دانشگاه امام علی (ع)، تهران، ایران.

10.66224/jii.4.2.70

چکیده

در سال‌های اخیر، بهره‌گیری از روش‌های یادگیری ماشین در حوزه‌ی نگهداری و تعمیرات پیش‌بینانه خودرو به یکی از راهکارهای کارآمد برای کاهش خرابی‌های ناگهانی، افزایش ایمنی و بهینه‌سازی هزینه‌های تعمیر تبدیل شده است. هدف این پژوهش، توسعه و ارزیابی مدل‌های مختلف یادگیری ماشین برای پیش‌بینی نیاز به تعمیر خودرو بر اساس داده‌های عملکردی سیستم‌های خودرو است. داده‌های گردآوری‌ شده پس از پیش‌پردازش و تقسیم به مجموعه‌های آموزش 80 درصد و آزمون 20 درصد، توسط دوازده الگوریتم شامل SVM، LR، NB، KNN، RF، DT، AdaBoost، Bagging، Stacking، XGBoost، CatBoost و LightGBM مدل‌سازی شدند. عملکرد مدل‌ها با معیارهای دقت، صحت، بازخوانی، F1-score و ROC- AUC ارزیابی شد. نتایج نشان داد مدل‌های مبتنی بر درخت و روش‌های ترکیبی، عملکرد برتری دارند و در میان آن‌ها، LightGBM با مقدار AUC برابر با 9475/0 و F1-score برابر با 9613/0 بهترین عملکرد را ارائه داده است. یافته‌ها بیانگر آن است که الگوریتم‌های یادگیری ماشین، به‌ویژه مدل‌های ترکیبی، می‌توانند در پیش‌بینی خرابی و طراحی سامانه‌های نگهداری هوشمند خودرو نقشی کلیدی ایفا کنند.

کلیدواژه‌ها

یادگیری ماشین

نگهداری و تعمیرات پیش‌بینانه خودرو

پیش‌بینی خرابی

مدل‌های ترکیبی

تحلیل داده‌های خودرو

عنوان مقاله English

Predictive Maintenance of Vehicles Using Machine Learning and Ensemble Algorithms

نویسنده English

Omid Veisi

Department of Industrial Engineering, Faculty of Engineering and Aviation, Imam Ali University (AS), Tehran, Iran.

چکیده English

In recent years, the use of machine learning methods in the field of predictive vehicle maintenance has become an effective approach for reducing unexpected failures, increasing safety, and optimizing repair costs. The aim of this study is to develop and evaluate various machine learning models to predict vehicle maintenance needs based on operational data from vehicle systems. After preprocessing, the collected data were split into 80% training and 20% testing sets and modeled using twelve algorithms, including SVM, LR, NB, KNN, RF, DT, AdaBoost, Bagging, Stacking, XGBoost, CatBoost, and LightGBM. The performance of the models was assessed using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The results indicated that tree-based models and ensemble methods performed superiorly, among which LightGBM achieved the best performance with an AUC of 0.9475 and an F1-score of 0.9613. The findings highlight that machine learning algorithms particularly ensemble models can play a key role in failure prediction and the design of intelligent vehicle maintenance systems.

کلیدواژه‌ها English

Machine Learning

Predictive Vehicle Maintenance

Failure Prediction

Ensemble Models

Vehicle Data Analysis

[1] Laxmi MM, Varshini KVS, Sandhya B, Prasmitha B, Sruthi B, Tanisha A. Hybrid Ensemble Learning for Real-Time Predictive Maintenance in Vehicular Engine Health Monitoring Systems. Frontiers in Collaborative Research. 2025;3(2):1-11.
[2] Hossain M, Rahman M, Ramasamy D. Artificial intelligence-driven vehicle fault diagnosis to revolutionize automotive maintenance: A review. Computer Modeling in Engineering & Sciences. 2024;141(2):951.
[3] Samrat B, Thomas P, Kumar S, Benila A, Bhardwaj R, Vigenesh M, editors. Industrial informatics in optimizing software-defined vehicles for logistics. 2024 IEEE 2nd International Conference on Innovations in High Speed Communication and Signal Processing (IHCSP); 2024: IEEE.
[4] Li H, Shaukat H, Zhu R, Bin Kaleem M, Wu Y. Fault Detection of Li–Ion Batteries in Electric Vehicles: A Comprehensive Review. Sustainability. 2025;17(14):6322.
[5] Jegadeeshwaran R, Sugumaran V. Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines. Mechanical systems and signal processing. 2015;52:436-46.
[6] Dunn BD. Materials and processes: for spacecraft and high reliability applications: Springer; 2016.
[7] Moubray J. Reliability-centered maintenance: Industrial Press Inc.; 2001.
[8] Zhang W, Yang D, Wang H. Data-driven methods for predictive maintenance of industrial equipment: A survey. IEEE systems journal. 2019;13(3):2213-27.
[9] Lee J, Bagheri B, Kao H-A. A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing letters. 2015;3:18-23.
[10] Zhao R, Yan R, Chen Z, Mao K, Wang P, Gao RX. Deep learning and its applications to machine health monitoring. Mechanical systems and signal processing. 2019;115:213-37.
[11] Mosallam A, Medjaher K, Zerhouni N. Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction. Journal of Intelligent Manufacturing. 2016;27(5):1037-48.
[12] Mobley RK. An introduction to predictive maintenance: Elsevier; 2002.
[13] Selcuk S. Predictive maintenance, its implementation and latest trends. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture. 2017;231(9):1670-9.
[14] Lee J, Bagheri B, Kao H-A, editors. Recent advances and trends of cyber-physical systems and big data analytics in industrial informatics. International proceeding of int conference on industrial informatics (INDIN); 2014.
[15] Tao F, Qi Q, Liu A, Kusiak A. Data-driven smart manufacturing. Journal of manufacturing systems. 2018;48:157-69.
[16] Yurdagül HH, Zaim U, Seller A, Özdemir H, Uyğur G, Akay MF, editors. Fault Prediction in Energy Systems: Telemetric Data and Machine Learning Approaches. 2025 9th International Symposium on Innovative Approaches in Smart Technologies (ISAS); 2025: IEEE.
[17] Reddy TV, Rao KM. Recent Trends in VLSI and Semiconductor Packaging: CRC Press; 2025.
[18] Baviskar¹ PV, Nayak C, editors. A Review on Equipment Health Monitoring Using Machine Learning Techniques. Proceedings of the International Conference on Applications of Machine Intelligence and Data Analytics (ICAMIDA 2022); 2023: Springer Nature.
[19] Radhakrishnan P, Ramaiyan K, Vinayagam A, Veerasamy V. A stacking ensemble classification model for detection and classification of power quality disturbances in PV integrated power network. Measurement. 2021;175:109025.
[20] Soresini F, Barri D, Cazzaniga I, Ballo F, Mastinu G, Gobbi M. Artificial Intelligence for Fault Detection of Automotive Electric Motors. Machines 2025; 13: 457.
[21] Patel K, Kolla D, Yadav G, Waghmode U, Mannava SK, Narayanan A, editors. IoT-Enabled Predictive Maintenance System for Smart Manufacturing Plants. 2025 10th International Conference on Communication and Electronics Systems (ICCES); 2025: IEEE.
[22] Benkaihoul S, Khadar S, Özüpak Y, Aslan E, Almalki MM, Mossa MA. Advanced fault classification in induction motors for electric vehicles using a stacking ensemble learning approach. World Electric Vehicle Journal. 2025;16(11):614.
[23] Dettinger F, Jazdi N, Weyrich M, Brandl L, Reuss H-C, Pecha U, et al., editors. Machine-Learning-Based Fault Detection in Electric Vehicle Powertrains Using a Digital Twin. 23rd Stuttgart International Symposium; 2023: SAE Technical Paper.
[24] Dui H, Dong X, Chen L, Wang Y. IoT-enabled fault prediction and maintenance for smart charging piles. IEEE Internet of Things Journal. 2023;10(23):21061-75.
[25] Guo B, Ding Y, Yao L, Liang Y, Yu Z. The future of false information detection on social media: New perspectives and trends. ACM Computing Surveys (CSUR). 2020;53(4):1-36.
[26] Afroz S, Brennan M, Greenstadt R, editors. Detecting hoaxes, frauds, and deception in writing style online. 2012 IEEE symposium on security and privacy; 2012: IEEE.
[27] Cantarella M, Fraccaroli N, Volpe R. Does fake news affect voting behaviour? Research Policy. 2023;52(1):104628.
[28] Goutte C, Gaussier E, editors. A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. European conference on information retrieval; 2005: Springer.
[29] Hosmer Jr DW, Lemeshow S, Sturdivant RX. Applied logistic regression: John Wiley & Sons; 2013.
[30] Cortes C, Vapnik V. Support-vector networks. Machine learning. 1995;20(3):273-97.
[31] Cover T, Hart P. Nearest neighbor pattern classification. IEEE transactions on information theory. 1967;13(1):21-7.
[32] John GH, Langley P. Estimating continuous distributions in Bayesian classifiers. arXiv preprint arXiv:13024964. 2013.
[33] Breiman L. Random forests. Machine learning. 2001;45(1):5-32.
[34] Breiman L. Bagging predictors. Machine learning. 1996;24(2):123-40.
[35] Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences. 1997;55(1):119-39.
[36] Chen T, Guestrin C, editors. Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016.
[37] Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems. 2017;30.
[38] Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems. 2018;31.
[39] Wolpert DH. Stacked generalization. Neural networks. 1992;5(2):241-59.