AN INTEGRATED AI-DRIVEN FRAMEWORK FOR SMART WAREHOUSE OPTIMIZATION AND AUTOMATED DEFECT DETECTION IN INDUSTRIAL SYSTEMS
Keywords:
Smart Warehouse, Defect Detection, Artificial Intelligence, CNN, Inventory Optimization, Predictive Maintenance, SPC, Industrial Automation, MATLAB.Abstract
More and more, Industrial Systems are being equipped with intelligent technologies to make them more efficient, better and better-performing in warehouses. Conventional warehouse optimization and defect detection systems are isolated, causing increased operating costs, inventory issues, equipment breakdowns, and defective inspection procedures. In this paper, an integrated framework based on Artificial Intelligence (AI) for inventory optimization, dynamic slotting, predictive maintenance, and automated defect detection in an integrated industrial system is presented. The proposed framework combines the concepts of Economic Order Quantity (EOQ), safety stock models, condition based maintenance, convolutional neural networks (CNN), support vector machines (SVM), and statistical process control (SPC). The implementation in MATLAB proves the efficiency of warehouses, the reduction of operational failures, and more accurate detection of defects. The research confirms the efficiency of the optimization and intelligent inspection methods for Industry 4.0 smart industrial systems.