Data-driven Optimization Study Of A Distribution Warehouse Operation

With the arrival of information technology,intelligence and digital era,the use of big data technology means to analyze and process the massive amount of data,mining the massive amount of data contains value of data-driven business model gradually mature,more and more companies began to use data-driven data analysis to deal with the warehouse operation process generated by high picking costs,low operational efficiency and other issues.At the same time,along with the rapid development of the economy,the flow of goods in the logistics industry is increasing day by day,the traditional warehouse has gradually failed to meet the needs of the turnover of goods operation,the flow of warehouse needs to be born.How to maximize the use of space in the circulation warehouse,the maximum to meet the turnover requirements,reduce the labor intensity of workers,improve the efficiency of warehouse operations,reduce operational logistics costs is the circulation warehouse requirements and the pursuit of.This paper takes a flow-through warehouse as the research object,analyzes the data generated in the operation process of the warehouse driven by data,uses data analysis methods combined with mathematical models,uses intelligent algorithms to solve,and uses simulation software to optimize the analysis of goods storage,sorting and outbound and verify the effectiveness of the optimization scheme.The research is an important tool for the effective use of warehouse data in distribution warehouses,improving warehouse operations and reducing operational logistics costs,and has high practical application significance.The main research elements of the thesis are as follows.(1)The first part mainly analyzes the operation mode and existing problems of the circulation warehouse,combined with the data analysis method,and at the same time analyzes the data of warehouse order data,uses EIQ-ABC analysis method to determine the preliminary type of order and picking mode,and uses correlation analysis to determine the order type and picking mode of key research.(2)The second part is aimed at the key research orders combined with Canopy+K-means clustering to classify orders,use IQ analysis theory to optimize inbound storage strategy,use factor analysis combined with clustering to optimize picking resource scheduling on the basis of optimizing storage locations,and finally use Flexsim to simulate inbound optimization to verify the effectiveness of the improvement scheme.(3)In the third part,for the types of orders that require order batching,considering the picking path optimization model of order batching,taking the minimum picking distance as the goal and combining the load-bearing constraints of the picking truck,the firefly algorithm is used to find the optimal picking path,and the effectiveness of the sorting out improvement scheme is verified by simulation.(4)The fourth part establishes a three-stage model of order outbound with maximum warehouse operation efficiency,obtains the warehouse resource allocation of the optimization model through parameter discussion,and finally verifies the effectiveness of the optimization configuration model through simulation.At the same time,the impact of shelf size and order difference on warehouse operation efficiency is discussed through parameter discussion and simulation model.