بهینه‌سازی یکپارچه موجودی قطعات یدکی با استفاده از پیش‌بینی تقاضا مبتنی بر یادگیری ماشین با در نظر گرفتن موجودی اطمینان و تأمین با دو زمان تحویل

ویسی, امید

doi:10.22034/sep.2026.2074035.1409

بهینه‌سازی یکپارچه موجودی قطعات یدکی با استفاده از پیش‌بینی تقاضا مبتنی بر یادگیری ماشین با در نظر گرفتن موجودی اطمینان و تأمین با دو زمان تحویل

مقالات آماده انتشار

نوع مقاله : پژوهشی

نویسنده

امید ویسی

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

10.22034/sep.2026.2074035.1409

چکیده

یکی از چالش‌های همیشگی در صنعت، برقراری تعادل میان تداوم تولید و کاهش هزینه‌های انبارداری است؛ هدفی که روش‌های سنتی مدیریت موجودی، به دلیل ضعف در پیش‌بینی تقاضاهای نامنظم و نادیده‌گرفتن محدودیت‌های اجرایی، اغلب در تحقق آن ناموفق‌اند. در این پژوهش، سعی شده با تلفیق پیش‌بینی دقیق تقاضا و مدل‌سازی ریاضی، راهکاری یکپارچه برای این مسئله ارائه شود. نقطه قوت این مدل، انعطاف‌پذیری آن در انتخاب شیوه تأمین است؛ یعنی سیستم می‌تواند بسته به شرایط، بین خرید عادی و خرید اضطراری بهترین گزینه را انتخاب کند. در طراحی این مدل، محدودیت‌های واقعی نظیر سقف بودجه (برای اقلام حیاتی و غیرحیاتی) و ظرفیت انبار دقیقاً در نظر گرفته شده‌اند و سطح موجودی اطمینان نیز متناسب با نوسانات تقاضا تغییر می‌کند. نتایج پیاده‌سازی مدل روی داده‌های ۶۰ قلم کالا نشان داد که فاصله‌گرفتن از سیاست‌های تک‌بعدی و استفاده از یک راهبرد ترکیبی، حتی در شرایط محدودیت مالی و فضا، منجر به کاهش هزینه‌ها و حفظ پایداری سیستم می‌شود.

تازه های تحقیق

توسعه یک چارچوب یکپارچه که پیش‌بینی دقیق تقاضا توسط یادگیری ماشین را با مدل بهینه‌سازی ریاضی، تأمین با دو زمان تحویل و محدودیت‌های بودجه ترکیب می‌کند.
جایگزینی سیاست‌های سنتی با راهبرد تأمین ترکیبی و مدیریت هوشمندانه موجودی اطمینان و سفارش‌های فوری که منجر به دستیابی به کاهش 19/3 درصدی در هزینه‌های کل سیستم شد.

کلیدواژه‌ها

مدیریت موجودی قطعات یدکی

پیش‌بینی تقاضا

یادگیری ماشین

بهینه‌سازی موجودی

زمان تحویل دوگانه

موضوعات

مهندسی صنایع

عنوان مقاله English

An Integrated Optimization of Spare Parts Inventory Using Machine-learning–based Demand Forecasting, Taking into Account Safety Stock and Dual Lead-time Supply

نویسنده English

Omid Veisi

Assistant Professor, Department of Industrial Engineering, Faculty of Engineering and Flight, Imam Ali University (AS), Tehran, Iran

چکیده English

One of the persistent challenges in industry is achieving a balance between uninterrupted production and minimizing inventory-holding costs—an objective that traditional inventory management methods often fail to meet due to their weaknesses in forecasting irregular demand and overlooking operational constraints. In this study, we attempt to provide an integrated solution to this problem by combining accurate demand forecasting with mathematical modeling. A key strength of the proposed model is its flexibility in selecting the procurement method; that is, the system can choose the optimal option between regular purchasing and emergency purchasing based on prevailing conditions. In designing the model, real-world constraints—such as budget limits (for both critical and non-critical items) and warehouse capacity—are precisely incorporated, and the safety stock level dynamically adjusts according to demand fluctuations. The results obtained from implementing the model on data from 60 items indicate that moving away from one-dimensional policies and adopting a hybrid strategy leads to cost reduction and improved system stability, even under financial and space limitations.

کلیدواژه‌ها English

Spare Parts Inventory Management

Demand Forecasting

Machine Learning

Inventory Optimization

Dual Delivery Lead Time

Copyright © Omid Veisi

License

This article is released under the Creative Commons Attribution (CC BY 4.0) license. Anyone is free to copy, share, translate, and adapt this article for any purpose, whether commercial or non-commercial, as long as proper citation is given to the authors and original publication.

Abbaspour, M., Shakhsi-Niaei, M., Vahdat Zad, M. A., & Ghazanfari, M. (2020). Predicting spare parts demand using machine learning. In Proceedings of the Eighth National Conference on Management and Humanities Research in Iran, Tehran, Iran (In Persian). https://civilica.com/doc/1114362/

Ameri, E., Ebadi, S. T., & Teimoury, E. (2021). Presenting an inventory management model for critical spare parts considering supplier disruption conditions under uncertainty. Proceedings of the 18th International Conference on Industrial Engineering, Iran (In Persian). https://civilica.com/doc/1354248/

Andersson, J., & Siminos, E. (2023). Spare parts demand prediction by using a random forest approach. In Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures (pp. 795–811). Springer. https://doi.org/10.1007/978-3-031-43670-3_55

ArunKumar, K. E., Kalaga, D. V., Kumar, C. M. S., Chilkoor, G., Kawaji, M., & Brenza, T. M. (2021). Forecasting the dynamics of cumulative COVID-19 cases (confirmed, recovered and deaths) for top-16 countries using statistical machine learning models: Auto-Regressive Integrated Moving Average (ARIMA) and Seasonal Auto-Regressive Integrated Moving Average (SARIMA). Applied Soft Computing, 103, 107161. https://doi.org/10.1016/j.asoc.2021.107161

Bhattacharyya, S. S., Kulkarni, O., & Mishra, A. (2023). Study of emerging avenues in supply chain resilience; the case of integration of additive manufacturing with spare parts procurement. Benchmarking: An International Journal, 30(10), 4100–4118. https://doi.org/10.1108/BIJ-03-2022-0163

Croston, J. D. (1972). Forecasting and stock control for intermittent demands. Journal of the Operational Research Society, 23(3), 289-303. https://doi.org/10.1057/jors.1972.50

Damayanti, M. L., & Sukmono, T. (2024). Analysis of spare part inventory control using economic order quantity (EOQ) and continuous review methods. Journal for Technology and Science, 1(3), 147–159. https://doi.org/10.61796/ipteks.v1i3.213

Demke, T. M., Kämpfer, T., Lucht, T., Wachsmann, J., & Nyhuis, P. (2023). Forecast-Based Dimensioning of Spare Parts Inventory Levels in the MRO Industry. In Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures (pp. 95–109). Springer. https://doi.org/10.1007/978-3-031-43666-6_7

Dereci, U., & Tuzkaya, G. (2024). An explainable artificial intelligence model for predictive maintenance and spare parts optimization. Supply Chain Analytics, 8, 100078. https://doi.org/10.1016/j.sca.2024.100078

Elhadaf, H., Marzoug, N., & Jraifi, A. (2024). Optimizing spare parts inventory management using genetic algorithm. In 2024 10th International Conference on Optimization and Applications (ICOA) (pp. 1–6). IEEE. https://doi.org/10.1109/ICOA62581.2024.10754264

Emadi, S. H., Sadeghian, A., Rabbani, M., & Dehghan Dehnavi, H. (2024). Application of optimal control approach in the optimization of production inventory systems in supply chain. Systems Engineering and Productivity, 4(1), 85-98 (In Persian). https://doi.org/10.22034/msb.2024.2026595.1203

Fattah, J., Ezzine, L., Aman, Z., El Moussami, H., & Lachhab, A. (2018). Forecasting of demand using ARIMA model. International Journal of Engineering Business Management, 10, 1847979018808673. https://doi.org/10.1177/1847979018808673

Fesharaki, M. M., & Landran Esfahani, S. (2024). Predicting spare parts demand based on machine learning using linear regression and artificial neural network methods. Quarterly Journal of New Interdisciplinary Research in Basic Sciences and Technical and Engineering, 4(1), 1-14 (In Persian). https://civilica.com/doc/1944243/

Gupta, C., Kumar, V., & Kumar, K. (2024). An efficient technique for arranging various commodities in a warehouse. Communications on Applied Nonlinear Analysis, 31(3s), 265–276. https://doi.org/10.52783/cana.v31.764

Hassanzadeh, F., Tavakkoli-Moghaddam, R., & Taleizadeh, A. (2013). Integrated pricing and inventory control model for perishable goods considering backorder shortage and vendor-managed inventory policy. Proceedings of the second National Conference on Industrial Engineering and Systems, Tehran, Iran (In Persian). https://en.civilica.com/doc/251219/

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

Hyndman, R. J. (2004). The interaction between trend and seasonality. International Journal of Forecasting, 20(4), 561–563. https://doi.org/10.1016/j.ijforecast.2004.03.005

Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice. OTexts.

Kang, Z. (2023). Robust spare parts inventory management. SSRN Electronic Journal.

Kenaka, S. P., Cakravastia, A., Ma’ruf, A., & Cahyono, R. T. (2025). Enhancing intermittent spare part demand forecasting: A novel ensemble approach with focal loss and SMOTE. Logistics, 9(1), 25. https://doi.org/10.3390/logistics9010025

Kim, J.-D., Hwang, J.-H., & Doh, H.-H. (2023). A predictive model with data scaling methodologies for forecasting spare parts demand in military logistics. Defence Science Journal, 73(6), 647–654. https://doi.org/10.14429/dsj.73.19129

Kim, J.-D., Kim, T.-H., & Han, S. W. (2023). Demand forecasting of spare parts using artificial intelligence: A case study of KX tanks. Mathematics, 11(3), 501. https://doi.org/10.3390/math11030501

Krishnan, M., & Khastgir, A. (2024). Enhancing supply chain efficiency to build next-gen artificial intelligence (AI)/machine learning network through Al-driven forecasting. International Journal of Supply Chain Management, 13(3), 28–41. https://doi.org/10.59160/ijscm.v13i3.6244

Kurawarwala, A. A., & Matsuo, H. (1998). Product growth models for medium-term forecasting of short life cycle products. Technological Forecasting and Social Change, 57(3), 169–196. https://doi.org/10.1016/S0040-1625(97)00102-9

Liu, X., Xu, Z., & Zheng, M. (2024). Optimal inventory decisions of infrequently needed spare parts for maintenance with inaccurate demand forecasts and limited storage space. Journal of Physics: Conference Series, 2853, 012063. https://doi.org/10.1088/1742-6596/2853/1/012063

Malekpour Kalbadi Nejad, S., & Bagheri Nejad, J. (2023). Presenting a dual-objective location-inventory model for designing an integrated forward/reverse logistics network. Systems Engineering and Productivity, 3(1), 1-40 (In Persian). https://doi.org/10.22034/sep.2023.706141

Miller, D. M., & Williams, D. (2003). Shrinkage estimators of time series seasonal factors and their effect on forecasting accuracy. International Journal of Forecasting, 19(4), 669–684. https://doi.org/10.1016/S0169-2070(02)00077-8

Mongkolkittaveepol, P., Phongthiya, T., & Yuangyai, C. (2023). Improvement of spare parts warehouse management in selected garage. In 2023 8th International Conference on Business and Industrial Research (ICBIR) (pp. 436–441). IEEE. https://doi.org/10.1109/ICBIR57571.2023.10147442

Moshiri, S., & Rashidi Komijan, A. (2023). Integrated supply-production-distribution model with the aim of profit maximization (case study: Zimaband Ariafer Factory). Systems Engineering and Productivity, 3(1), 157-184 (In Persian). https://doi.org/10.22034/sep.2023.706146

Mouschoutzi, M., & Ponis, S. T. (2022). A comprehensive literature review on spare parts logistics management in the maritime industry. The Asian Journal of Shipping and Logistics, 38(2), 71–83. https://doi.org/10.1016/j.ajsl.2021.12.003

Mudunuri, L. N. R. (2024). Maximizing every square foot: AI creates the perfect warehouse flow. FMDB Transactions on Sustainable Computing Systems, 2(2), 64–73. https://doi.org/10.69888/FTSCS.2024.000198

Ostertagová, E., & Ostertag, O. (2011). The simple exponential smoothing model. In The 4th International Conference on Modelling of Mechanical and Mechatronic Systems, Technical University of Košice, Slovak Republic, Proceedings of Conference (pp. 380–384).

Pham, D. T., & Kiesmüller, G. P. (2024). Hybrid value function approximation for solving the technician routing problem with stochastic repair requests. Transportation Science, 58(2), 499–519. https://doi.org/10.1287/trsc.2022.0434

Ramírez, X. S., Solorio, X. G., Paredes, M. P., & Sifuentes, C. T. (2024). Proposal for an improvement model to reduce aircraft spare parts overstock based on ABC methodology and neural network forecasting in an air service company in Peru. In 2024 Congreso Internacional de Innovación y Tendencias en Ingeniería (CONIITI) (pp. 1–6). IEEE. https://doi.org/10.1109/CONIITI64189.2024.10854866

Ravuri, V., & Vasundra, S. (2023). An effective weather forecasting method using a deep long–short-term memory network based on time-series data with sparse fuzzy c-means clustering. Engineering Optimization, 55(9), 1437–1455. https://doi.org/10.1080/0305215X.2022.2088741

Riskianto, W., Vanany, I., & Arvitrida, N. I. (2021). Consumable material spare part management control in electricity transmission system. IPTEK Journal of Proceedings Series, (7), 66–70. http://dx.doi.org/10.12962%2Fj23546026.y2020i7.9539

Rizki, M. I., & Dora, Y. M. (2024). Management inventory control kaizen of using continuous review policy in a PT XYZ commercial vehicle at Jakarta City, Indonesia. International Student Conference on Business, Education, Economics, Accounting, and Management (ISC-BEAM). https://doi.org/10.21009/ISC-BEAM.012.09

Tapia-Ubeda, F. J., Miranda, P. A., Roda, I., Macchi, M., & Durán, O. (2020). Modelling and solving spare parts supply chain network design problems. International Journal of Production Research, 58(17), 5299–5319. https://doi.org/10.1080/00207543.2020.1720924

Teimoury, E., & Farahani, M. M. E. (2009). A Model for spare parts' demand forecasting based on reliability, operational environment and failure interaction of parts. International Journal of Industrial Engineering & Production Management, 20(1), 55-64 (In Persian). https://ijiepm.iust.ac.ir/article-1-61-fa.html

Teixeira, C., Lopes, I., & Figueiredo, M. (2024). Spare parts stock management: Classification and policy assignment. FME Transactions, 52(2), 257–270. https://doi.org/10.5937/fme2402257T

Veisy, O., Heydari, J., Razmi, J., & Sangari, M. (2019). Optimization of distribution and support model in logistics system supply chain under dynamic and uncertainty conditions. Military Management Quarterly, 19(74), 81-116 (In Persian). https://jmm.iranjournals.ir/article_38054_en.html

Wang, Y., Shi, Q., Li, L., Li, F., & Xia, W. (2021). Spare parts supply network optimization with uncertain distributed lead times and demands. Métodos Numéricos para Cálculo y Diseño en Ingeniería: Revista Internacional, 37(1), 1–16. https://doi.org/10.23967/j.rimni.2020.11.002

Yu, C., Zhou, Y., & Zhang, Z. (2020). Multi-agent reinforcement learning for dynamic spare parts inventory control. In 2020 Global Reliability and Prognostics and Health Management (PHM-Shanghai) (pp. 1–7). IEEE. https://doi.org/10.1109/PHM-Shanghai49105.2020.9280935

Zhang, S., Huang, K., & Yuan, Y. (2021). Spare parts inventory management: A literature review. Sustainability, 13(5), 2460. https://doi.org/10.3390/su13052460

Zhu, Q., Yang, L., & Liu, Y. (2023). Research on vehicle spare parts demand forecast based on XGBoost-LightGBM. In Proceedings of the 2023 5th International Conference on Pattern Recognition and Intelligent Systems (pp. 130–134). ACM. https://doi.org/10.1145/3609703.3609721