• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus 收录
  • 全国中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

基于MEC-BP高海拔隧道供氧浓度与劳动强度规律

陈政 郭春 谌桂舟 张佳鹏 许昱旻

陈政, 郭春, 谌桂舟, 张佳鹏, 许昱旻. 基于MEC-BP高海拔隧道供氧浓度与劳动强度规律[J]. 西南交通大学学报, 2023, 58(3): 622-629. doi: 10.3969/j.issn.0258-2724.20210669
引用本文: 陈政, 郭春, 谌桂舟, 张佳鹏, 许昱旻. 基于MEC-BP高海拔隧道供氧浓度与劳动强度规律[J]. 西南交通大学学报, 2023, 58(3): 622-629. doi: 10.3969/j.issn.0258-2724.20210669
CHEN Zheng, GUO Chun, CHEN Guizhou, ZHANG Jiapeng, XU Yumin. Oxygen Supply Concentration and Labor Intensity of High Altitude Tunnel Based on MEC-BP[J]. Journal of Southwest Jiaotong University, 2023, 58(3): 622-629. doi: 10.3969/j.issn.0258-2724.20210669
Citation: CHEN Zheng, GUO Chun, CHEN Guizhou, ZHANG Jiapeng, XU Yumin. Oxygen Supply Concentration and Labor Intensity of High Altitude Tunnel Based on MEC-BP[J]. Journal of Southwest Jiaotong University, 2023, 58(3): 622-629. doi: 10.3969/j.issn.0258-2724.20210669

基于MEC-BP高海拔隧道供氧浓度与劳动强度规律

doi: 10.3969/j.issn.0258-2724.20210669
基金项目: “十三五”国家重点研发计划(2019YFC0605104);教育部科技产学合作协同育人项目(201801221005);四川省教育科研资助(2020597)
详细信息
    作者简介:

    陈政(1992—),男,博士研究生,研究方向为隧道及地下工程,E-mail:1847485788@qq.com

  • 中图分类号: U25

Oxygen Supply Concentration and Labor Intensity of High Altitude Tunnel Based on MEC-BP

  • 摘要:

    为解决高海拔隧道施工供氧关键技术,开展高海拔隧道供氧浓度及劳动功率对劳动强度的影响研究. 通过在西藏拉萨达孜区的圭嘎拉隧道进行现场实测,以平均能量代谢率作为衡量劳动强度指标,采用肺通气量仪搜集6名测试人员在不同劳动强度(50、75 W和100 W劳动功率)和供氧浓度(20.9%、25.0%和29.0%)下的肺通量数据,并转化为劳动强度指标,运用基于思维进化算法的前馈神经网络(mind evolutionary computation back-propagation, MEC-BP)对劳动强度指标进行拟合. 研究结果表明:MEC-BP神经网络拟合数据的拟合优度略高于GA-BP 和BP 神经网络的拟合优度;50 W低劳动功率下,施工人员平均能量代谢率对氧浓度的变化较小,最大约0.1 kJ/(min•m2);在100 W较高劳动功率下,25%供氧浓度可作为4 200 m高原供氧浓度参考值.

     

  • 图 1  MEC-BP神经网络框架

    Figure 1.  MEC-BP neural network framework

    图 2  现场测试及实验仪器

    Figure 2.  Field test and experimental instrument diagram

    图 3  BP神经网络结构

    Figure 3.  Structure diagram of BP neural network

    图 4  MEC-BP迭代收敛及拟合优度

    Figure 4.  MEC-BP iterative convergence and goodness of fit

    图 5  GA-BP拟合优度

    Figure 5.  GA-BP goodness of fit

    图 6  BP拟合优度

    Figure 6.  BP goodness of fit

    图 7  MEC-BP拟合平均能量代谢率变化

    Figure 7.  MEC-BP fitting average energy metabolic rate change chart

    表  1  现场测试及计算数据

    Table  1.   Field test and calculation data

    测试人员
    编号
    氧浓度/%功率/W肺通量/(L·min−1)A/m2测试环境温度/K标准肺通气量/
    (L·min−1)
    平均能量代谢率/
    (kJ·(min·m2)−1)
    1 号20.95010.521.86298.155.780.57
    25.0507.881.86286.154.510.50
    29.0507.291.86284.154.200.48
    20.97520.031.86296.1511.080.96
    25.07517.071.86288.159.710.69
    29.07517.021.86290.159.610.67
    20.910032.751.86298.1518.002.21
    25.010027.881.86292.1515.641.80
    29.010027.941.86292.1515.671.80
    2 号20.9509.751.80299.155.340.56
    25.0507.521.80292.154.220.49
    29.0506.731.80284.153.880.47
    20.97520.451.80298.1511.241.06
    25.07518.121.80298.159.960.81
    29.07516.411.80284.159.460.71
    20.910027.541.80298.1515.131.80
    25.010023.891.80290.1513.491.50
    29.010022.871.80289.1512.961.39
    3 号20.9508.641.72298.154.750.53
    25.0507.391.72291.154.160.50
    29.0506.911.72283.154.000.49
    20.97523.561.72297.1512.991.52
    25.07520.451.72298.1511.241.17
    29.07519.311.72285.1511.101.14
    20.910029.441.72298.1516.182.14
    25.010026.561.72289.1515.051.92
    29.010025.441.72285.1514.621.84
    4 号20.95010.741.85298.155.900.59
    25.0507.861.85291.154.420.49
    29.0506.661.85282.153.870.46
    20.97518.641.85295.1510.350.83
    25.07516.241.85292.159.110.59
    29.07513.521.85284.157.800.53
    20.910025.791.85298.1514.171.55
    25.010022.171.85300.1512.101.17
    29.010021.251.85283.1512.301.20
    5 号20.95010.221.99298.155.620.54
    25.0508.541.99292.154.790.49
    29.0507.471.99282.154.340.47
    20.97519.391.99298.1510.660.74
    25.07518.721.99292.1510.500.71
    29.07518.351.99283.1510.620.73
    20.910028.271.99298.1515.541.60
    25.010025.881.99299.1514.171.37
    29.010024.331.99285.1513.981.33
    6 号20.9509.991.85298.155.490.56
    25.0507.351.85291.154.140.48
    29.0506.191.85282.153.590.45
    20.97519.311.85298.1510.610.88
    25.07519.171.85294.1510.680.89
    29.07518.841.85292.1510.570.87
    20.910027.51.85300.1515.011.70
    25.010026.091.85299.1514.291.57
    29.010025.131.85289.1514.241.56
    下载: 导出CSV
  • [1] GUO C, XU J F, WANG M N, et al. Study on oxygen supply standard for physical health of construction personnel of high-altitude tunnels[J]. International Journal of Environmental Research and Public Health, 2016, 13(1): 64.
    [2] 郭春,陈小峰,郑鑫,等. 西藏S5线拉萨至泽当快速路圭嘎拉隧道施工供氧方案研究[J]. 现代隧道技术,2018,55(增2): 331-336.

    GUO Chun, CHEN Xiaofeng, ZHENG Xin, et al. Oxygen supply scheme for the construction of Guigala tunnel from Tibet S5 line Lhasa to Zedang expressway[J]. Modern Tunnelling Technology, 2018, 55(S2): 331-336.
    [3] 孙志涛. 基于肺泡氧分压的高海拔隧道施工供氧技术研究[D]. 成都: 西南交通大学, 2016.
    [4] 王明年,李琦,于丽,等. 高海拔隧道通风、供氧、防灾与节能技术的发展[J]. 隧道建设,2017,37(10): 1209-1216.

    WANG Mingnian, LI Qi, YU Li, et al. Development of new technologies for ventilation, oxygen supply, disaster prevention and energy saving for high-altitude tunnels[J]. Tunnel Construction, 2017, 37(10): 1209-1216.
    [5] WANG M N, YAN G F, YU L, et al. Effects of different artificial oxygen-supply systems on migrants’ physical and psychological reactions in high-altitude tunnel construction[J]. Building and Environment, 2019, 149: 458-467. doi: 10.1016/j.buildenv.2018.12.032
    [6] 谢文强. 巴朗山高海拔隧道施工期供氧标准及设计方法研究[D]. 成都: 西南交通大学, 2015.
    [7] 严涛, 王明年, 郭春, 等. 高海拔特长公路隧道弥散式供氧关键技术研究[J]. 现代隧道技术, 2015, 52(2): 180-185, 204.

    YAN Tao, WANG Mingnian, GUO Chun, et al. Key techniques for the diffused oxygen supply of an extra-long highway tunnel in a high-altitude area[J]. Modern Tunnelling Technology, 2015, 52(2): 180-185, 204.
    [8] 刘亚丽,李英娜,李川. 基于遗传算法优化BP神经网络的线损计算研究[J]. 计算机应用与软件,2019,36(3): 72-75.

    LIU Yali, LI Yingna, LI Chuan. Line loss calculation of optimized BP neural network based on genetic algorithm[J]. Computer Applications and Software, 2019, 36(3): 72-75.
    [9] 任谢楠. 基于遗传算法的BP神经网络的优化研究及MATLAB仿真[D]. 天津: 天津师范大学, 2014.
    [10] 刘春艳,凌建春,寇林元,等. GA-BP神经网络与BP神经网络性能比较[J]. 中国卫生统计,2013,30(2): 173-176,181.

    LIU Chunyan, LING Jianchun, KOU Linyuan, et al. Performance comparison between GA-BP neural network and BP neural network[J]. Chinese Journal of Health Statistics, 2013, 30(2): 173-176,181.
    [11] WANG X D, MIAO C Q, WANG X M. Prediction analysis of deflection in the construction of composite box-girder bridge with corrugated steel webs based on MEC-BP neural networks[J]. Structures, 2021, 32: 691-700. doi: 10.1016/j.istruc.2021.03.011
    [12] 李步遥,司马军. 基于MEC-BP神经网络的基坑水平位移反演分析[J]. 铁道科学与工程学报,2021,18(7): 1764-1772.

    LI Buyao, SIMA Jun. Horizontal displacement back-analysis for deep excavation using MEC-BP neural network[J]. Journal of Railway Science and Engineering, 2021, 18(7): 1764-1772.
    [13] 王春晓,陈志坚. 基于MEC-BP神经网络的群桩轴力预测[J]. 中国煤炭地质,2017,29(3): 53-57. doi: 10.3969/j.issn.1674-1803.2017.03.11

    WANG Chunxiao, CHEN Zhijian. Pile group axial force prediction based on MEC-BP neural network[J]. Coal Geology of China, 2017, 29(3): 53-57. doi: 10.3969/j.issn.1674-1803.2017.03.11
    [14] 刘应书, 祝显强, 杨雄, 等. 高原低气压环境富氧防火安全研究[C]//青藏铁路运营十周年学术研讨会论文集. 北京: 中国铁道出版社, 2016: 140-146.
    [15] 王万梁. 单项体力劳动强度分级研究[D]. 济南: 山东大学, 2007.
    [16] 中华人民共和国卫生部. 工作场所物理因素测量 第10部分: 体力劳动强度分级: GBZ/T 189.10—2007[S]. 北京: 人民出版社, 2007.
  • 加载中
图(7) / 表(1)
计量
  • 文章访问数:  237
  • HTML全文浏览量:  75
  • PDF下载量:  27
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-08-16
  • 修回日期:  2021-12-16
  • 网络出版日期:  2023-04-13
  • 刊出日期:  2022-12-01

目录

    /

    返回文章
    返回