基于QPSO优化ELM算法的井下快速定位方法研究

Research on underground fast location method based on ELM method optimized via QPSO

近年来,基于WiFi的井下人员定位算法受到了广泛关注,为进一步提高定位算法的速度和精度,提出了一种基于量子粒子群(QPSO)优化极限学习机(ELM)算法的井下人员快速定位方法。首先将优化的K均值聚类算法(K-means)引入定位流程,通过对位置指纹库进行聚类划分,降低单次识别需要的时间;其次利用QPSO算法优越的优化能力,提高ELM算法的定位精度,最终实现对井下人员的高效、准确定位。仿真实验结果表明,提出的基于量子粒子群优化极限学习机的井下快速定位方法,能够提高定位的精度和效率,具有较高的实用价值和工程意义。

In recent years,the underground personnel positioning algorithm based on WiFi has received widespread attention.In order to further improve the speed and accuracy of the positioning algorithm,this paper proposes a fast underground personnel positioning method based on quantum particle swarm optimization(QPSO)extreme learning machine(ELM)algorithm.Firstly,the optimized K-means clustering algorithm is introduced into the localization process,which reduces the time required for single recognition by clustering and partitioning the location fingerprint database;Secondly,the superior optimization ability of QPSO algorithm is used to improve the positioning accuracy of ELM algorithm,ultimately achieving efficient and accurate positioning of underground personnel.The simulation experimental results show that the proposed underground fast positioning method based on quantum particle swarm optimization limit learning machine can improve the accuracy and efficiency of positioning,and has high practical value and engineering significance.