Self-Learning Automatic Tiered Warehouse Scheduling Based on the Expert Database

The materials storage time is the key factor to the access efficiency of the automatic tiered warehouse. To improve the access efficiency, a new scheduling policy was proposed. The model is based on storage time after in-depth study on the scheduling tactics. By using the self-learning and the improved genetic algorithms, the storage time generate from the trained example data and the expert database knowledge of the storage cargo space, the conflict between the massive data analysis and rapid real-time scheduling is solved. Thus the tiered warehouse scheduling based on the expert database self-learning and genetic algorithms optimal solution is achieved. In addition, the results have been applied in the automatic tiered warehouse in a cigarette factory, its access ability is effectively improved, and the example verifies that the research is feasible and effective. © 2012 American Scientific Publishers All rights reserved.