摘要
井下人员行为识别是保障煤矿安全生产的重要措施。针对现有井下人员行为识别研究缺少对感知机理的研究与分析且特征提取手段单一的问题,提出一种基于融合网络的井下人员行为识别方法。该方法主要包括数据预处理、特征构建和判识网络构造3个部分。数据预处理:通过信道状态信息(CSI)商模型、子载波去直流和离散小波去噪对采集的CSI数据进行处理,以降低环境噪声、设备噪声等的影响。特征构建:将处理后的数据利用格拉姆和/差角场(GASF/GADF)转换成图像,从而保留数据的空间和时间特性。判识网络构造:根据人员动作的特点,提出一种由基于门控循环单元(GRU)的编解码网络和多尺度卷积神经网络(CNN)组成的融合网络,利用GRU保留前后数据之间的关联性,同时利用注意力机制的权重分配策略有效提取关键特征,以提高行为识别的准确率。实验结果表明:该方法对行走、摘帽子、扔东西、坐、抽烟、挥手、跑动、睡觉8种动作的平均识别准确率为97.37%,对睡觉和坐的识别准确率最高,最容易发生误判的动作是行走和跑动;使用准确率、精确率、召回率和F1分数作为评价指标,得出融合网络的性能优于CNN和GRU,人员行为识别准确率高于HAR系统、WiWave系统和Wi−Sense系统;正常速度下行走和摘帽子2种动作的平均识别精度为95.6%,高于快速动作情况下的93.6%和慢速动作情况下的92.7%;收发设备之间的距离为2 m和2.5 m时,识别准确率较高。
Underground personnel behavior recognition is an important measure to ensure safe production in coal mines.The existing research on behavior recognition of underground personnel lacks research and analysis on the perception mechanism,and the feature extraction method is simple.In order to solve the above problems,a behavior recognition method for underground personnel based on fusion networks is proposed.The method mainly includes three parts: data preprocessing, feature construction, and recognition network construction. Data preprocessing: the collected channel status information (CSI) data is processed through CSI quotient models, subcarrier denoising, and discrete wavelet denoising to reduce the impact of environmental noise and equipment noise. Feature construction: the processed data is transformed into images using the Gramian angular summation/difference fields (GASF/GADF) to preserve the spatial and temporal features of the data. Recognition network construction: according to the features of personnel actions, a fusion network composed of a gate recurrent unit (GRU) based encoding and decoding network and a multiscale convolutional neural network (CNN) is proposed. GRU is used to preserve the correlation between pre and post data. The weight allocation strategy of the attention mechanism is used to effectively extract key features to improve the accuracy of behavior recognition. The experimental results show that the average recognition accuracy of this method for eight movements, namely walking, taking off a hat, throwing things, sitting, smoking, waving, running, and sleeping, is 97.37%. The recognition accuracy for sleeping and sitting is the highest, and the most prone to misjudgment are walking and running. Using accuracy, precision, recall, and F1 score as evaluation indicators, it is concluded that the performance of the fusion network is superior to CNN and GRU. The accuracy of personnel behavior recognition is higher than the HAR system, WiWave system and Wi-Sense system. The average recognition
作者
张雷
冉凌鎛
代婉婉
朱永红
史新国
ZHANG Lei;RAN Lingbo;DAI Wanwan;ZHU Yonghong;SHI Xinguo(School of Information Engineering(School of Big Data),Xuzhou University of Technology,Xuzhou 221018,China;IoT Perception Mine Research Center,China University of Mining and Technology,Xuzhou 221008,China;National Mobile Communications Research Laboratory,Southeast University,Nanjing 210096,China;Information Center,Shandong Energy Zibo Mining Group Co.,Ltd.,Zibo 225100,China)
出处
《工矿自动化》
CSCD
北大核心
2023年第3期45-52,共8页
Journal Of Mine Automation
基金
江苏省高等学校基础科学(自然科学)研究项目(21KJB510025)
国家重点研发计划项目(2017YFC0804401)
国家自然科学基金项目(52074273)
教育部产学合作协同育人项目(BY2021160202102356012)
徐州市科技计划项目(KC19208)
淄矿集团智慧矿山关键技术研发开放基金项目(2019LH05)。
关键词
智能矿山
行为识别
无线感知
深度学习
信道状态信息
多尺度卷积神经网络
门控循环单元
intelligent mine
behavior recognition
wireless perception
deep learning
channel status information
multi scale convolutional neural network
gate recurrent unit
