基于 CSI 的单 AP 港口人员指纹定位方法

Single AP port personnel fingerprint location method based on CSI

摘要

港口是我国重要的物流和交通枢纽，高精度的港口人员定位系统在安全生产和管理过程中发挥着重要作用。该文 将径向基函数（RBF）和极限学习机（ELM）结合，提出了一种基于信道状态信息（CSI）的 RBF-ELM 港口人员定位方法，实现单个接入点（AP）进行人员定位。在离线训练阶段，首先将定位区域网格化，并测量各网格位置的 CSI 数据；将幅值差和线性重构的相位信息融合构造位置指纹，并使用主成分分析（PCA）进行降维处理。最后，将模拟退火（SA）嵌入量子粒子群优化（QPSO）算法中，提高全局搜索能力，寻找模型最优参数，进而提升定位模型的精度和泛化能力。在在线预测阶段，通过 WKNN 匹配算法将模型的预测结果与位置库中的标签和坐标进行匹配，以获得更为精确的定位坐标。同时，采用动态遗忘因子的权值更新方式，只需采集部分校准数据即可完成对定位模型权值的更新，有效缓解随时间和环境变化引起的定位精度衰退问题。在模拟港口的场景下进行实验验证，该定位系统在视距（LOS）环境下达到 1 m 定位精度的概率在 92% 以上，静态平均误差为 0.58 m，动态平均误差为 0.86 m；在非视距（NLOS）环境下也可获得 0.67 m 的静态平均定位误差。所提算法相比其他定位方法在定位精度、时效性和稳定性上均有所提升。

Abstract

The port is an important logistics and transportation hub in our country, the high-precision port personnel positioning system plays an important role in the process of safety production and management. By combining radial basis function (RBF) and extreme learning machine (ELM), an RBF-ELM port personnel location method based on channel state information (CSI) is proposed to realize personnel location by a single access point (AP). In the offline training stage, the positioning area is first gridded and the CSI data of each grid position is measured; position fingerprints are constructed by fusing the amplitude difference and linearly reconstructed phase information, and dimensionality reduction was performed by principal component analysis (PCA); subsequently, simulated annealing (SA) is embedded into quantum particle swarm optimization (QPSO) to improve the global search ability, find the optimal parameters of the model, and thereby improve the accuracy and generalization ability of positioning model. In the online prediction stage, the prediction results of the model are matched with labels and coordinates in the location library by weighted K-nearest neighbors (WKNN) matching algorithm to obtain more accurate positioning coordinates. At the same time, the weight update method of dynamic forgetting factor is adopted, and only part of calibration data can be collected to complete the update of positioning model weight, which effectively alleviates the problem of positioning accuracy decline caused by changes in time and environment. In the simulated port scenario, the probability of the positioning accuracy of the system reaching 1m in line-of-sight (LOS) environment is more than 92%, the static average error is 0.58 m, and the dynamic average error is 0.86 m. The static average positioning error of 0.67 m can also be obtained in non-line-of-sight (NLOS) environment. Compared with other positioning methods, the proposed algorithm has improved positioning accuracy, timeliness and stability.

关键词

港口人员定位 / 信道状态信息 / 极限学习机 / 量子粒子群 / 动态权值更新

Key words

port personnel location / channel state information / extreme learning machine / quantum particle swarm / dynamic weight update

参考文献

[1] 施晓冬, 姜昊舟 . 港口智能水平运输设备感知和定位系统[J]. 港口装卸, 2023(4): 46-49.

[2] SHI X D , JIANG H Z . Perception and positioning system for intelligent horizontal transportation equipment in ports[J]. Port Handling, 2023(4): 46-49.

[3] 黄庭 . 基于北斗高精度定位的智慧港口创新应用[J]. 中国港口, 2023(9): 58-61.

[4] HUANG T . Innovative applications of smart ports based on Beidou high—precision positioning[J]. China Ports, 2023(9): 58-61.

[5] 王鹏, 庄肃凯, 刘雷 . 基于 5G+ 的人员定位系统在港口安全管理中的应用[J]. 设备管理与维修, 2023(8): 124-125.

[6] WANG P , ZHUANG S K , LIU L . Application of 5G+ based personnel positioning system in port safety management[J]. Equipment Management and Maintenance, 2023(8): 124-125.

[7] 杨勇生, 迟景成, 姚海庆 . 基于模糊 Kalman 滤波的港口车辆组合定位方法研究[J]. 全球定位系统, 2020, 45(6): 80-85.

[8] YANG Y S , CHI J C , YAO H Q . Research on the combined positioning method of port vehicles based on fuzzy Kalman filtering[J]. Global Positioning System, 2020, 45(6): 80-85.

[9] 邵小强, 李康乐, 陈熙, 等. 基于改进卡尔曼滤波和参数拟合的矿井 TOA 定位方法[J]. 煤炭学报, 2019, 44(5): 1616-1624.

[10] SHAO X Q , LI K L , CHEN X , et al. Mine TOA positioning method based on improved Kalman filtering and parameter fitting[J]. Journal of China Coal Society, 2019, 44(5): 1616-1624.

[11] GUO X C , XIA P P . Mine personnel location system based on Internet of Things[J]. IOP Conference Series: Materials Science and Engineering, 2018, 439: 032087.

[12] 宋明智 . 矿井 WLAN 位置指纹定位中的关键问题研究[D]. 徐州: 中国矿业大学, 2020.

[13] SONG M Z . Research on key issues in mine WLAN fingerprint positioning[D]. Xuzhou: China University of Mining and Technology, 2020.

[14] 宋明智, 钱建生, 胡青松 . 基于 AKPCA 算法的井下 WLAN 位置指纹定位[J]. 煤炭科学技术, 2022, 50(3): 248-256.

[15] SONG M Z , QIAN J S , HU Q S . Underground WLAN fingerprint positioning based on AKPCA algorithm[J]. Coal Science and Technology, 2022, 50(3): 248-256.

[16] YANG Z , ZHOU Z M , LIU Y H . From RSSI to CSI[J]. ACM Computing Surveys, 2013, 46(2): 1-32.

[17] 张大庆, 张扶桑, 吴丹, 等. 基于 CSI 的通信感知一体化设计: 问题、挑战和展望[J]. 移动通信, 2022, 46(5): 9-16.

[18] ZHANG D Q , ZHANG F S , WU D , et al. Integrated design of communication sensing based on CSI: Issues, challenges, and prospects[J]. Mobile Communications, 2022, 46(5): 9-16.

[19] 王旭东, 刘帅, 吴楠 . CAEFi: 基于卷积自编码器降维的信道状态信息指纹室内定位方法[J]. 电子与信息学报, 2022, 44(8): 2757-2766.

[20] WANG X D , LIU S , WU N . CAEFi: Indoor positioning method based on convolutional autoencoder dimensionality reduction of channel state information fingerprint[J]. Journal of Electronics and Information Technology, 2022, 44(8): 2757-2766.

[21] LI Q , LIAO X W , LIU M M , et al. Indoor localization based on CSI fingerprint by Siamese convolution neural network[J]. IEEE Transactions on Vehicular Technology, 2021, 70(11): 12168-12173.

[22] 王博远, 刘学林, 蔚保国, 等. WiFi 指纹定位中改进的加权 k 近邻算法[J]. 西安电子科技大学学报（自然科学版）, 2019, 46(5): 41-47.

[23] WANG B Y , LIU X L , WEI B G , et al. Improved weighted k—nearest neighbor algorithm in WiFi fingerprint positioning[J]. Journal of Xi’an University of Electronic Science and Technology (Natural Science Edition), 2019, 46(5): 41-47.

[24] 刘星, 王文双, 赵建印, 等. 自适应在线增量 ELM 的故障诊断模型研究[J]. 系统工程与电子技术, 2021, 43(9): 2678-2687.

[25] LIU X , WANG W S , ZHAO J Y , et al. Research on fault diagnosis model based on adaptive online incremental ELM[J]. System Engineering and Electronics, 2021, 43(9): 2678-2687.

[26] 张兆娟, 王万良, 唐继军 . 适应度二次选择的 QPSO 和 SA 协同搜索大规模离散优化算法[J]. 通信学报, 2020, 41(8): 22-31.

[27] ZHANG Z J , WANG W L , TANG J J . Collaborative search large—scale discrete optimization algorithm based on QPSO and SA with fitness secondary selection[J]. Journal on Communications, 2020, 41(8): 22-31.

[28] CAO W P , MING Z , XU Z W , et al. Online sequential extreme learning machine with dynamic forgetting factor[J]. IEEE Access, 2019, 7: 179746-179757.

[29] 张雷 . 基于 CSI 的煤矿井下定位方法研究[D]. 徐州: 中国矿业大学, 2019.

[30] ZHANG L . Research on CSI—based underground positioning method for coal mines[D]. Xuzhou: China University of Mining and Technology, 2019.

[31] ZHANG L , HU Y J , LIU Y F , et al. WiCLoc: A novel CSI—based fingerprint localization system[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2020, 34(4): 2058003

[32] LIU W , WANG X , DENG Z L . CSI amplitude fingerprinting for indoor localization with dictionary learning[J]. Entropy, 2021, 23(9): 1164.

[33] LI H H , ZENG X S , LI Y Z , et al. Convolutional neural networks based indoor Wi—Fi localization with a novel kind of CSI images[J]. China Communications, 2019, 16(9): 250-260.

基金资助

国家自然科学基金(52272318)