基于DPBBO算法的智慧云仓UAV盘库作业优化

    Optimization of UAV Inventory Operation in Smart Cloud Warehouse Based on DPBBO Algorithm

    • 摘要: 针对智慧云仓货物信息量大、易出现账物不符等库存管理问题, 迫切需要将无人机(unmanned aerial vehicle, UAV)和工业物联网(industrial Internet of things, IIoT)集成起来, 为仓储精细化管理提供解决方案。首先, 分析盘库作业数据采集与信息交互运行机制, 以危险避障和数据采集为约束函数, 考虑了UAV在加速、减速、匀速、转角等飞行条件下的能耗差异, 并以能耗最低和时间最短为目标函数构造UAV盘库作业数学模型; 然后, 设计了差分迁移-分段变异生物地理学优化(differential migration-piecewise mutation-biogeography-based optimization, DPBBO)算法对上述模型进行优化解算; 最后, 进行了仿真实验验证。结果表明: DPBBO算法对解决该盘库作业问题的效果较优, 可以提升库存抽检任务的时效性和库存管理的准确性。

       

      Abstract: It is essential to integrate unmanned aerial vehicle (UAV) and industrial Internet of things (IIoT) to provide solutions for the refined warehouse management in response to inventory management issues such as the large amount of cargo information in smart cloud warehouses and the risk of discrepancies between accounts and goods.First, the operation mechanism of data collection and information interaction was analyzed, and the mathematical model of UAV inventory operation was constructed with the lowest energy consumption and the shortest time as the objective functions. At the same time, the energy consumption difference of UAV under the flight conditions of acceleration, deceleration, uniform speed and cornering was considered, and hazard avoidance and data acquisition were taken as the constraint functions. Afterwards, the differential migration-piecewise mutation-biogeography-based optimization (DPBBO) algorithm was designed to solve the above model. Finally, the simulation was verified. Results show that the DPBBO algorithm is more effective in solving this inventory operation problem and can improve the timeliness of inventory sampling tasks and the accuracy of inventory management.

       

    /

    返回文章
    返回