面向柔性制造车间的多目标RFID网络规划方法

Multi-objective RFID network planning approach for flexible manufacturing workshop

针对具有多种覆盖需求的柔性制造车间RFID网络规划问题,以部署成本、阅读器干扰与阅读器效能为多优化目标,提出一种分层聚类、冗余消减与梯度下降方法集成的RFID网络规划方法,采用分层聚类算法确定RFID初始数量与部署位置,采用冗余阅读器消减算法优化RFID数量,采用梯度下降算法优化RFID部署位置从而实现网络规划多目标优化。实验研究表明,提出的方法在多目标综合性能方面优于传统基于分层聚类方法、遗传算法、粒子群与冗余消减混合方法的RFID网络规划方法,验证了该方法的有效性。

To solve the RFID network planning problem of flexible manufacturing workshops with multiple coverage requirements,this paper proposed an RFID network planning approach integrating hierarchical clustering,redundancy reduction,and gradient descent,where the deployment cost,reader interference,and reader efficiency were taken as multi-optimization objectives.Firstly,it designed a hierarchical clustering algorithm to determine the initial number and deployment location of RFID.Then,it constructed a redundancy reader reduction algorithm to optimize the number of RFID.Finally,it built a gradient descent algorithm to adjust the RFID deployment location,so as to achieve multi-objective optimization of the RFID network planning.Experimental results show that the proposed approach has better multi-objective comprehensive performance than the traditional RFID network planning methods,including the hierarchical clustering method,genetic algorithm,particle swarm optimization,and redundancy subtraction method.It means the proposed approach is effective.