Multiple factors collaborative optimisation of intelligent storage system

For improving the storage efficiency of intelligent warehousing systems and avoiding local optimum problem, this paper studies the mutually coordinated strategy for inbound and outbound, which is realised by collaboratively analysing the influence of multiple factors such as order, location and path. Firstly, the correlation between stock keeping units (SKU) in historical orders is analysed by the cosine similarity algorithm, and a storage location optimisation model is established. Then, an improved grey wolf optimiser (IGWO) algorithm integrating genetic algorithm (GA) is proposed, which overcomes the disadvantage of insufficient global search ability from GWO algorithm. Moreover, according to the characteristics of the goods placement, an outbound strategy based on item clustering is put forward. The items in multiple orders are clustered and redistributed based on K-means clustering algorithm, and the improved ant colony optimisation (IACO) is given to solve the path optimisation problem. Finally, the effectiveness of the proposed algorithms is proved by analysing the delivery efficiency under different strategies. It demonstrated that the proposed IGWO is stable in solving the storage space optimisation problems with different SKU numbers, and it improves the algorithm solution speed by 50.2% on average than simulated annealing genetic algorithm (SAGA).