Position prediction of underground moving targets in mines based on IPSO-LSTM
-
摘要:
提升井下人员定位精度能够加强矿山安全监测,最大程度保障井下人员的生命安全。针对现有测距类算法受现场环境影响致使定位精度不足的问题,提出一种基于IPSO-LSTM的定位模型,应用于井下动目标的位置预测。采用LSTM构建指纹定位模型,通过UWB无线模块采集距离信息以构建距离-位置指纹关系数据库,利用数据库对PSO-LSTM模型进行训练,最后将训练好的模型进行目标轨迹预测。为比较不同改进策略对PSO的提升效果,对比了混沌映射随机初始化种群位置、非线性惯性权重递减、非对称优化学习因子和适应度函数优化4种改进策略,实验证明改进的PSO优化算法收敛速度快、鲁棒性好。为验证IPSO-LSTM的定位效果,以平均定位误差作为评价指标,将IPSO-LSTM模型与Chan算法、PSO-LSTM模型、LSTM神经网络、SSA-LSTM模型和GWO-LSTM进行对比,结果显示,IPSO-LSTM定位模型的平均定位误差为30 mm,相对传统Chan算法、LSTM、PSO-LSTM模型分别提升了76%、49%、24%。为降低局部误差偏大的现象,采用中值滤波对输入信息处理,进一步提升了定位精度。研究对进一步提高现有井下动目标定位系统的精度和稳定性具有重要意义和参考价值。
-
关键词:
- 井下动目标 /
- 改进的粒子群优化算法 /
- IPSO-LSTM模型 /
- 平均定位误差
Abstract:Improving the positioning accuracy of underground personnel can not only strengthen mine safety monitoring, but also increase the speed of rescue, thus ensuring the life safety of underground personnel to the maximum extent.This paper proposes a positioning model based on IPSO-LSTM for position prediction of underground moving targets in response to the problem of existing ranging algorithms which are affected by the on-site environment, resulting in insufficient positioning accuracy.This article uses LSTM to build a fingerprint positioning model.It collects distance information through the UWB wireless module to build a distance-position fingerprint relationship database, which is used to train the PSO-LSTM model.Then we use the trained model to predict target trajectories.We compared four improvement strategies on PSO including random initialization of population position by chaotic mapping, nonlinear inertia weight reduction and fitness function optimization.Experiments show that the improved PSO optimization algorithm in this paper exhibit fast convergence speed and good robustness.In order to verify the positioning effect of IPSO-LSTM, we compared the IPSO-LSTM model with the Chan algorithm, PSO-LSTM model, LSTM neural network, SSA-LSTM model and GWO-LSTM.The average positioning error is used as the evaluation index.The results show that the average positioning error of the IPSO-LSTM positioning model proposed in this study is 30mm, which is 76% higher than the traditional Chan algorithm, 49% higher than the LSTM, and 24% higher than the PSO-LSTM model.In order to reduce large local errors, we used median filtering to process input information, further improving positioning accuracy.This study offers references for improving the accuracy and stability of the existing underground moving target positioning system.
-
表 1 改进PSO优化LSTM模型的平均误差
Table 1. The average error of the three algorithmic models
算法 平均误差/mm a-PSO-LSTM模型 39.5 b-PSO-LSTM模型 38.3 c-PSO-LSTM模型 37.9 d-PSO-LSTM模型 32.9 PSO-LSTM模型 39.7 表 2 6种算法模型的平均误差
Table 2. The average error of six algorithmic models
定位算法 平均误差/mm 初始学习率 隐含单元个数 Chan算法 127 — — LSTM 58.7 0.1 70 SSA-LSTM 42.8 0.032 25 GWO-LSTM 46.5 0.15 113 PSO-LSTM 39.7 0.018 95 IPSO-LSTM 30.1 0.022 241 -
[1] 李锋. 煤矿井下精确定位技术现状及应用[J]. 工矿自动化, 2023, 49(S1): 44-46. https://www.cnki.com.cn/Article/CJFDTOTAL-MKZD2023S1013.htmLI Feng. Present situation and application of accurate positioning technology in coal mine[J]. Industry and Mine Automation, 2023, 49(S1): 44-46. https://www.cnki.com.cn/Article/CJFDTOTAL-MKZD2023S1013.htm [2] SUN M X, GAO Y L, JIAO Z Q, et al. R-T-S assisted Kalman filtering for robot localization using UWB measurement[J]. Mobile Networks and Applications, 2022: 1-10. [3] CHENG J H, YU P P, HUANG Y R. Application of improved Kalman filter in under-ground positioning system of coal mine[J]. IEEE Transactions on Applied Superconductivity, 2021, 31(8): 0603904. [4] 程雪聪, 刘福才, 黄茹楠. 基于卡尔曼滤波和粒子滤波融合的UWB室内定位算法[J]. 计量学报, 2022, 43(10): 1335-1340. https://www.cnki.com.cn/Article/CJFDTOTAL-JLXB202210014.htmCHENG Xuecong, LIU Fucai, HUANG Runan. UWB indoor positioning algorithm based on Kalman filter and particle filter fusion[J]. Acta Metrologica Sinica, 2022, 43(10): 1335-1340. https://www.cnki.com.cn/Article/CJFDTOTAL-JLXB202210014.htm [5] TONG Z X, XUE J H, KANG Z Q. A novel indoor positioning algorithm based on UWB[J]. International Journal of Sensor Networks, 2022, 40(4): 238-249. doi: 10.1504/IJSNET.2022.127843 [6] 李新春, 阳士宇, 张玉琛, 等. 削减NLOS误差的UWB室内定位算法[J]. 重庆邮电大学学报: 自然科学版, 2022, 34(5): 758-765. https://www.cnki.com.cn/Article/CJFDTOTAL-CASH202205004.htmLI Xinchun, YANG Shiyu, ZHANG Yuchen, et al. UWB interior positioning algorithm for NLOS error reduction[J]. Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, 2022, 34(5): 758-765. https://www.cnki.com.cn/Article/CJFDTOTAL-CASH202205004.htm [7] 田子建, 阳康, 吴佳奇等. 基于LMIENet图像增强的矿井下低光环境目标检测方法[J]. 煤炭科学技术, 2023, 12(4): 1-14.TIAN Zijian, YANG Kang, WU Jiaqi et al. Target detection method in low-light environment in mines based on LMIENet image enhancement[J]. Coal Science and Technology, 2023, 12(4): 1-14. [8] 亿吉, 张楠. 基于RSSI的矿井移动目标加权质心定位算法[J]. 山西煤炭, 2022, 42(3): 102-108. doi: 10.3969/j.issn.1672-5050.2022.03.015YI Ji, ZHANG Nan. RSSI-based weighted centroid localization algorithm for moving targets in mines[J]. Shanxi Coal, 2022, 42(3): 102-108. doi: 10.3969/j.issn.1672-5050.2022.03.015 [9] POULOSE A, EYOBU O S, KIM M, et al. Localization error analysis of indoor positioning system based on UWB measurements[C]//. 2019 Eleventh International Conference on Ubiquitous and Future Networks(ICUFN). Zagreb, Croatia. IEEE, 2019: 84-88. [10] DJOSIC S, STOJANOVIC I, JOVANOVIC M, et al. Fingerprinting-assisted UWB-based localization technique for complex indoor environments[J]. Expert Systems with Applications, 2021, 167: 114188. doi: 10.1016/j.eswa.2020.114188 [11] 沈天盛, 陈文莹, 朱彬斌, 等. 基于改进WKNN的蓝牙室内定位方法[J]. 现代电子技术, 2023, 46(10): 11-16. https://www.cnki.com.cn/Article/CJFDTOTAL-XDDJ202310003.htmSHEN Tiansheng, CHEN Wenying, ZHU Binbin, et al. Method of Bluetooth indoor positioning based on improved WKNN[J]. Modern Electronics Technique, 2023, 46(10): 11-16. https://www.cnki.com.cn/Article/CJFDTOTAL-XDDJ202310003.htm [12] 刘晓阳, 刘金强, 郑昊琳. 基于双流神经网络的煤矿井下人员步态识别方法[J]. 矿业科学学报, 2021, 6(2): 218-227. doi: 10.19606/j.cnki.jmst.2021.02.010LIU Xiaoyang, LIU Jinqiang, ZHENG Haolin. Gait recognition method of coal mine personnel based on Two-Stream neural network[J]. Journal of Mining Science and Technology, 2021, 6(2): 218-227. doi: 10.19606/j.cnki.jmst.2021.02.010 [13] 杨家强, 别昊泽, 张更新, 等. 机器学习辅助的WiFi位置指纹算法研究[J]. 黑龙江大学自然科学学报, 2023, 40(1): 92-97. https://www.cnki.com.cn/Article/CJFDTOTAL-HLDZ202301012.htmYANG Jiaqiang, BIE Haoze, ZHANG Gengxin, et al. Research on WiFi location fingerprinting algorithm assisted by machine learning[J]. Journal of Natural Science of Heilongjiang University, 2023, 40(1): 92-97. https://www.cnki.com.cn/Article/CJFDTOTAL-HLDZ202301012.htm [14] 陈禹, 渠吉庆, 唐文静, 等. 基于LSTM的室内定位系统设计与实现[J]. 电子测量技术, 2021, 44(19): 161-166. https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL202119026.htmCHEN Yu, QU Jiqing, TANG Wenjing, et al. Design and implementation on indoor positioning system based on LSTM[J]. Electronic Measurement Technology, 2021, 44(19): 161-166. https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL202119026.htm [15] 王红尧, 郑鸿林, 田劼, 等. 面向矿井动目标的PSO-SVR模型与UWB Chan优化距离指纹融合定位方法[J]. 电子测量与仪器学报, 2022, 36(7): 106-114. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202207013.htmWANG Hongyao, ZHENG Honglin, TIAN Jie, et al. Fusion location method of PSO-SVR model and UWB Chanoptimal fingerprint matching for mine moving target[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(7): 106-114. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202207013.htm [16] CHEN X H, FU M S, LIU Z Y, et al. Harris Hawks optimization algorithm and BP neural network for ultra-wideband indoor positioning[J]. Mathematical Biosciences and Engineering, 2022, 19(9): 9098-9124. doi: 10.3934/mbe.2022423 [17] 黄先龙, 黄良璜, 谢佳俊, 等. 一种基于PSO-BPNN的CSI指纹定位方法[J]. 江西师范大学学报: 自然科学版, 2023, 47(4): 393-399. https://www.cnki.com.cn/Article/CJFDTOTAL-CAPE202304009.htmHUANG Xianlong, HUANG Lianghuang, XIE Jiajun, et al. The CSI fingerprint location method based on PSO-BPNN[J]. Journal of Jiangxi Normal University: Natural Science Edition, 2023, 47(4): 393-399. https://www.cnki.com.cn/Article/CJFDTOTAL-CAPE202304009.htm [18] 尹春杰, 赵钦, 王光旭, 等. 基于改进粒子群优化BP神经网络的火灾预警方法[J]. 电子设计工程, 2023, 31(22): 6-10. https://www.cnki.com.cn/Article/CJFDTOTAL-GWDZ202322002.htmYIN Chunjie, ZHAO Qin, WANG Guangxu, et al. Fire warning method based on improved particle swarm optimization BP neural network[J]. Electronic Design Engineering, 2023, 31(22): 6-10. https://www.cnki.com.cn/Article/CJFDTOTAL-GWDZ202322002.htm [19] 祝钊, 曹鹏. 基于改进PSO-PNN的大螺旋钻机故障诊断系统研究[J]. 煤炭工程, 2022, 54(11): 193-198. https://www.cnki.com.cn/Article/CJFDTOTAL-MKSJ202211034.htmZHU Zhao, CAO Peng. Fault diagnosis system of large auger based on improved PSO-PNN[J]. Coal Engineering, 2022, 54(11): 193-198. https://www.cnki.com.cn/Article/CJFDTOTAL-MKSJ202211034.htm [20] 刘丹, 王瑞虎, 吕伟, 等. 基于IPSO-LSTM的新能源汽车锂电池健康状态监测[J]. 中国安全科学学报, 2023, 33(9): 94-102. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK202309013.htmLIU Dan, WANG Ruihu, LÜ Wei, et al. SOH monitoring of new energy vehicle lithium batteries based on IPSO-LSTM[J]. China Safety Science Journal, 2023, 33(9): 94-102. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK202309013.htm [21] 吕诗为, 朱迎谷, 卢倪斌, 等. 基于改进粒子群算法的水下机器人路径规划研究[J]. 控制与信息技术, 2023(6): 58-64. https://www.cnki.com.cn/Article/CJFDTOTAL-BLJS202306009.htmLÜ Shiwei, ZHU Yinggu, LU Nibin, et al. An investigation into path planning of underwater vehicle based on improved particle swarm optimization algorithm[J]. Control and Information Technology, 2023(6): 58-64. https://www.cnki.com.cn/Article/CJFDTOTAL-BLJS202306009.htm [22] 谭章禄, 王美君. 智能化煤矿数据治理概念模型及技术架构研究[J]. 矿业科学学报, 2023, 8(2): 242-255. doi: 10.19606/j.cnki.jmst.2023.02.011TAN Zhanglu, WANG Meijun. Research on the conceptual model and technical architecture of data governance for intelligent coal mine[J]. Journal of Mining Science and Technology, 2023, 8(2): 242-255. doi: 10.19606/j.cnki.jmst.2023.02.011 [23] 田祥瑞, 罗欣, 贾茚钧, 等. 基于UWB的无人机自主导航系统设计[J]. 电子技术应用, 2023, 49(5): 129-134. https://www.cnki.com.cn/Article/CJFDTOTAL-DZJY202305024.htmTIAN Xiangrui, LUO Xin, JIA Yinjun, et al. Autonomous navigation system design for UAV based on UWB[J]. Application of Electronic Technique, 2023, 49(5): 129-134. https://www.cnki.com.cn/Article/CJFDTOTAL-DZJY202305024.htm [24] 张春翔, 唐烨锈, 邹冠贵, 等. 深度卷积神经网络目标检测算法在煤矿断层检测上的应用[J]. 矿业科学学报, 2023, 8(6): 733-743. doi: 10.19606/j.cnki.jmst.2023.06.001ZHANG Chunxiang, TANG Yexiu, ZOU Guangui, et al. Deep convolutional neural network target detection algorithm for coal mine fault detection[J]. Journal of Mining Science and Technology, 2023, 8(6): 733-743. doi: 10.19606/j.cnki.jmst.2023.06.001 [25] 时子皓, 高常青, 张瑞年, 等. 基于ZigBee的室内指纹定位算法应用[J]. 物联网技术, 2023, 13(10): 23-25. https://www.cnki.com.cn/Article/CJFDTOTAL-WLWJ202310008.htmSHI Zihao, GAO Changqing, ZHANG Ruinian, et al. Application of indoor fingerprint location algorithm based on ZigBee[J]. Internet of Things Technologies, 2023, 13(10): 23-25. https://www.cnki.com.cn/Article/CJFDTOTAL-WLWJ202310008.htm [26] 闫孟婷, 陶湘明, 王胜军, 等. 基于SSA-LSTM模型的水电站能效综合评价方法[J]. 水电能源科学, 2024, 42(2): 177-182. https://www.cnki.com.cn/Article/CJFDTOTAL-SDNY202402040.htmYAN Mengting, TAO Xiangming, WANG Shengjun, et al. Comprehensive evaluation method of energy efficiency of hydropower station based on SSA-LSTM model[J]. Water Resources and Power, 2024, 42(2): 177-182. https://www.cnki.com.cn/Article/CJFDTOTAL-SDNY202402040.htm [27] POULOSE A, HAN D S. Feature-based deep LSTM network for indoor localization using UWB measurements[C]//. 2021 International Conference on Artificial Intelligence in Information and Communication(ICAⅡC). Jeju Island, Korea(South). IEEE, 2021: 298-301. [28] 唐晓灵, 刘嘉敏. 基于PSO-LSTM网络模型的建筑碳排放峰值预测[J]. 科技管理研究, 2023, 43(1): 191-198. https://www.cnki.com.cn/Article/CJFDTOTAL-KJGL202301024.htmTANG Xiaoling, LIU Jiamin. Forecast of peak carbon emissions of buildings based on PSO-LSTM model[J]. Science and Technology Management Research, 2023, 43(1): 191-198. https://www.cnki.com.cn/Article/CJFDTOTAL-KJGL202301024.htm [29] 张大桂, 周志峰, 张怡, 等. 基于粒子群优化的TDOA声源定位方法[J]. 电子科技, 2023, 36(9): 21-28. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKK202309004.htmZHANG Dagui, ZHOU Zhifeng, ZHANG Yi, et al. TDOA sound source localization method based on particle swarm optimization algorithm[J]. Electronic Science and Technology, 2023, 36(9): 21-28. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKK202309004.htm [30] 马宽, 何国锋, 董燕飞, 等. 基于多策略改进PSO算法的微电网优化调度研究[J]. 智慧电力, 2023, 51(8): 23-29, 45. https://www.cnki.com.cn/Article/CJFDTOTAL-XBDJ202308004.htmMA Kuan, HE Guofeng, DONG Yanfei, et al. Microgrid optimal scheduling based on multi-strategy improved PSO algorithm[J]. Smart Power, 2023, 51(8): 23-29, 45. https://www.cnki.com.cn/Article/CJFDTOTAL-XBDJ202308004.htm [31] 谢金燕, 刘丽星, 杨欣, 等. 改进粒子群优化算法的果园割草机作业路径规划[J]. 中国农业大学学报, 2023, 28(11): 182-191. https://www.cnki.com.cn/Article/CJFDTOTAL-NYDX202311016.htmXIE Jinyan, LIU Lixing, YANG Xin, et al. Orchard lawn mower operation path planning based on improved particle swarm optimization algorithm[J]. Journal of China Agricultural University, 2023, 28(11): 182-191. https://www.cnki.com.cn/Article/CJFDTOTAL-NYDX202311016.htm [32] 李虎, 刘泓滨. 基于改进PSO算法的时间最优机械臂轨迹规划[J]. 组合机床与自动化加工技术, 2023(1): 29-33. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHJC202301007.htmLI Hu, LIU Hongbin. Time optimal manipulator trajectory planning based on improved particle swarm optimization algorithm[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2023(1): 29-33. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHJC202301007.htm [33] 谭光兴, 王雨辰, 符丹丹, 等. 基于中值滤波的SBW信号处理及控制策略[J]. 计算机仿真, 2021, 38(7): 134-138. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJZ202107032.htmTAN Guangxing, WANG Yuchen, FU Dandan, et al. Steer-by-wire system signal processing and control strategy based on Median filter[J]. Computer Simulation, 2021, 38(7): 134-138. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJZ202107032.htm -