Bayesian optimization genetic algorithm based on automated stereo warehouse space optimization

Automated three-dimensional warehouse is one of the important development directions of modern logistics industry, which can achieve efficient, accurate and safe logistics operation and improve the competitiveness of logistics enterprises. In order to fully exploit the advantages of automated three-dimensional warehouses, the storage of goods in automated three-dimensional warehouses must be reasonably designed and optimized to improve space utilization and logistics efficiency. In this paper, a hybrid algorithm based on a combination of Bayesian optimization algorithm and genetic algorithm is proposed to solve the problem of cargo space layout and cargo storage strategy in an automated three-dimensional warehouse. The method uses the Bayesian optimization algorithm to adaptively adjust the parameters of the genetic algorithm to improve the search capability and convergence speed of the genetic algorithm, while preventing the genetic algorithm from falling into local optimum solutions. Through experimental and simulation analysis, this paper demonstrates the effectiveness of the method in improving the cargo space utilization rate and warehouse operation efficiency, and outperforms the method using genetic algorithm alone in terms of performance and stability, providing a new way of thinking and method for the design and management of automated three-dimensional warehouses, with certain theoretical significance and practical value.