EUVIMEDEUVIMED entdecken
Crossref

AI-Driven Cyber-Physical Warehouse Digital Twin for Uncertainty-Aware Inventory Prediction and Adaptive Demand-Based Material Replenishment

Gautam Kumar

International Journal of Engineering & Extended Technologies Research · 22.01.2025 · 7 (1)

DOI: 10.15662/ijeetr.2025.0701012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 22.01.2025. Verfasst von Gautam Kumar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Warehouse replenishment depends on accurate stock records, reliable demand estimates, and decisions that respond to shifting operating conditions. This manuscript examines an uncertainty-aware cyber-physical framework integrating Bayesian inventory-state estimation, calibrated quantile demand forecasting, and scenario-based stochastic model predictive control. The supplied analysis covers 1,000 stock-keeping units across two warehouses, with 546,000 historical SKU-day observations and a separately described 12-week operational comparison. Reported summary values favor UACWRF: inventory-state mean absolute error is 3.90 rather than 6.20 units; weighted quantile loss is 7.60 rather than 8.50; and historical replenishment cost is ₹16,200 rather than ₹18,100 per 1,000 requested units against the probabilistic WMS-only comparator. Under the combined WMS-delay and demand-shift condition, additional cost deterioration is reported as 51.9% smaller. All four hypotheses are listed as supported in the supplied summary. Because the source explicitly attributes these numbers to an earlier constructed scenario without accompanying observations or fitted analysis outputs, quantitative claims are retained as source-reported values whose empirical provenance is not independently established.

Zitieren

APA

Kumar, G. (2025). AI-Driven Cyber-Physical Warehouse Digital Twin for Uncertainty-Aware Inventory Prediction and Adaptive Demand-Based Material Replenishment. International Journal of Engineering & Extended Technologies Research, 7(1). https://doi.org/10.15662/ijeetr.2025.0701012

Vancouver

Kumar G. AI-Driven Cyber-Physical Warehouse Digital Twin for Uncertainty-Aware Inventory Prediction and Adaptive Demand-Based Material Replenishment. International Journal of Engineering & Extended Technologies Research. 2025;7(1). doi:10.15662/ijeetr.2025.0701012

BibTeX
@article{Kumar2025,
  author = {Kumar, Gautam},
  title = {AI-Driven Cyber-Physical Warehouse Digital Twin for Uncertainty-Aware Inventory Prediction and Adaptive Demand-Based Material Replenishment},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2025},
  volume = {7},
  number = {1},
  doi = {10.15662/ijeetr.2025.0701012}
}
Kostenlos starten →