Optimizing Human-Centric Warehouse Operations: A Digital Twin Approach Using Dynamic Algorithms and AI/ML

Year 2025, Issue: PRODUCTIVITY FOR LOGISTICS, 119 - 138, 03.02.2025

Erhan Arslan

https://doi.org/10.51551/verimlilik.1524701

Abstract

Purpose: This study aims to develop a versatile and adaptive system that optimizes manual warehouse operations through the integration of Digital Twin technology and AI/ML models.
Methodology: The framework combines Digital Twin technology with advanced AI/ML analytics to dynamically adjust operational strategies based on real-time data collected from warehouse activities.
Findings: A prototype implementation demonstrated significant improvements, including a 28.6% reduction in average picking time, a 20% improvement in inventory turnover, an increase in demand forecasting accuracy from 85% to 92%, and a reduction in labor costs by 15%.
Originality: This research uniquely applies Digital Twin technology to manual warehouse environments, showcasing its effectiveness in enhancing operational efficiency without the need for full automation.

Keywords

Digital Twin, Warehouse, Optimization, Artificial Intelligence, Machine Learning

İnsan Merkezli Depo Operasyonlarının Optimizasyonu: Dinamik Algoritmalar ve AI/ML Kullanarak Dijital İkiz Yaklaşımı

Abstract

Amaç: Bu çalışmada, Dijital İkiz teknolojisi ve Yapay Zekâ/Makine Öğrenmesi modellerinin entegrasyonu yoluyla manuel depo operasyonlarını optimize eden çok yönlü ve uyarlanabilir bir sistem geliştirmeyi hedeflenmiştir.
Yöntem: Çerçeve, depo faaliyetlerinden toplanan gerçek zamanlı verilere dayanarak operasyonel stratejileri dinamik olarak ayarlamak için Dijital İkiz teknolojisini gelişmiş Yapay Zekâ/Makine Öğrenimi analitiğiyle birleştiriyor.
Bulgular: Prototip uygulaması, ortalama toplama süresinde %28,6'lık bir azalma, stok devir hızında %20'lik bir iyileşme, talep tahmin doğruluğunda %85'ten %92'ye bir artış ve işçilik maliyetlerinde %15'lik bir azalma dahil olmak üzere önemli iyileştirmeler gösterdi.
Özgünlük: Bu araştırma, Dijital İkiz teknolojisini manuel depo ortamlarına benzersiz bir şekilde uygulayarak, tam otomasyona ihtiyaç duymadan operasyonel verimliliği artırmadaki etkinliğini ortaya koyuyor.

Keywords

: Dijital İkiz, Depo, Optimizasyon, Yapay Zekâ, Makine Öğrenmesi

Supporting Institution

TURKCELL TECHNOLOGY

References

• AIM Consulting. (2023). “AI for Supply Chain Optimization: Improve Demand Forecasting”, https://www.aimconsulting.com/ai-for-supply-chain-optimization, (Accessed: 20.06.2023).
• Amazon. (2021). “Optimizing Warehouse Operations with Digital Twins. Amazon Blog”, https://www.aboutamazon.com/news/operations/optimizing-warehouse-operations-with-digital-twins, (Accessed: 15.07.2023).
• Aylak, B.L., İnce, M., Oral, O., Süer, G., Almasarwah, N., Singh, M. and Salah, B. (2021). “Application of Machine Learning Methods for Pallet Loading Problem”, Applied Sciences, 11(18), 8304.
• Aylak, B.L. (2022). “Warehouse Layout Optimization Using Association Rules”, Fresenius Environmental Bulletin, 31(3A), 3828-3840.
• Boschert, S. and Rosen, R. (2016). “Digital Twin—The Simulation Aspect”, Mechatronic Futures, Springer.
• Breiman, L. (2001). “Random Forests”, Machine Learning, 45, 5-32.
• Chen, L., Cui, H. and Shi, F. (2019). “Reinforcement Learning in Predictive Control for Smart Warehouse Logistics”, Computers & Industrial Engineering, 137, 106072.
• Chicaiza, D., Loaiza, R. and Burbano, D. (2020). “Augmented Reality Applications for Warehouse Management: A Literature Review”, Procedia Manufacturing, 42, 319-325.
• Cortes, C. and Vapnik, V. (1995). “Support-Vector Networks”, Machine Learning, 20, 273-297.
• DHL. (2023). “Leveraging AI for Predictive Maintenance in Warehousing”, https://www.dhl.com/content/dam/dhl/global/core/documents/pdf/glo-core-digital-twins-in-logistics.pdf, (Accessed: 03.07.2023).
• Exotec. (2023). “Implementing Digital Twins for Enhanced Warehouse Efficiency”, https://www.exotec.com/digital-twins-for-enhanced-warehouse-efficiency, (Accessed: 12.06.2023).
• Forbes. (2023). “Digital Twins for Warehouses: Transforming Efficiency and Productivity” https://www.forbes.com/sites/forbestechcouncil/2023/06/22/digital-twins-for-warehouses/, (Accessed: 10.06.2023).
• Fuller, A., Fan, Z., Day, C. and Barlow, C. (2020). “Digital Twin: Enabling Technologies, Challenges and Open Research”, IEEE Access, 8, 108952-108971.
• Ghiassi, M. and Saidane, H. (2018). “A Dynamic Artificial Neural Network Model for Forecasting Time Series Events”, International Journal of Forecasting, 21(2), 341-362.
• Glaessgen, E. and Stargel, D. (2012). “The Digital Twin Paradigm for Future NASA and U.S. Air Force Vehicles”, AIAA SciTech Forum, https://ntrs.nasa.gov/api/citations/20120008178/downloads/20120008178.pdf.
• Graves, S.C. and Yücesan, H.C.S. (2009). “Strategic Safety Stock Placement in Supply Chains with Demand and Lead-Time Uncertainty”, Management Science, 46(5), 739-750.
• Grieves, M. (2002). “Concept of Digital Twin”, Product Lifecycle Management Conference, https://www.plm.automation.siemens.com/global/en/our-story/glossary/digital-twin/24465.
• Grieves, M. and Vickers, J. (2017). “Digital Twin: Mitigating Unpredictable, Undesirable Emergent Behavior in Complex Systems” Transdisciplinary Perspectives on Complex Systems, Springer.
• Gu, J., Goetschalckx, M. and McGinnis, L.F. (2007). “Research on Warehouse Design and Performance Evaluation: A Comprehensive Review”, European Journal of Operational Research, 203(3), 539-549.
• Ivanov, D., Dolgui, A., & Sokolov, B. (2020). Handbook of Ripple Effects in the Supply Chain. Springer International Series in Operations Research & Management Science, Switzerland. DOI: 10.1007/978-3-030-14302-2.
• Kaber, D.B. and Riley, S.M. (2017). “Task Design and Workload Management in Manual and Automated Warehouses: A Human Factors Perspective”, Applied Ergonomics, 60, 35-45.
• Kardinal. (2023). “Machine Learning and Route Optimization: Towards Flawless Deliveries”, https://www.kardinal.ai/machine-learning-and-route-optimization, (Accessed: 05.06.2023).
• Kritzinger, W., Karner, M., Traar, G., Henjes, J. and Sihn, W. (2018). “Digital Twin in Manufacturing: A Categorical Literature Review and Classification”, IFAC-PapersOnLine, 51(11), 1016-1022.
• Kumar, P., Kumar, S. and Kumar, S. (2020). “Predictive Maintenance of Industrial Equipment Using Machine Learning”, International Journal of Advanced Research in Computer Science, 11(3), 75-81.
• McKinsey & Company. (2022). “Improving Warehouse Operations Digitally”, https://www.mckinsey.com/capabilities/operations/our-insights/improving-warehouse-operations-digitally, Accessed: (18.06.2023).
• PepsiCo. (2020). “Digital Twin Technology in PepsiCo's Distribution Centers”, PepsiCo Annual Report, https://www.pepsico.com/sustainability/digital-transformation, Accessed: (22.06.2023).
• Rashid, A. and Rattenbury, S. (2018). “Scalable Machine Learning for Real-Time Inventory Optimization”, Journal of Business Research, 89, 201-213.
• Tao, F., Cheng, J., Qi, Q., Zhang, M., Zhang, H. and Sui, F. (2016). “Digital Twin-Driven Product Design, Manufacturing and Service with Big Data”, The International Journal of Advanced Manufacturing Technology, 94, 3563-3576.
• Uhlemann, T.H., Schock, C., Lehmann, C., Freiberger, S. and Steinhilper, R. (2017). “The Digital Twin: Demonstrating the Potential of Real Time Data Acquisition in Production Systems”, Procedia Manufacturing, 9, 113-120.
• WarehouseBlueprint. (2023). “Optimizing Warehouse Operations with the Power of Digital Twin, SketchUp, and Power BI”, https://www.warehouseblueprint.com/blog/optimizing-warehouse-operations-with-digital-twin, (Accessed: 30.06. 2023).