基于BP神经网络的铀尾矿砂氡射气系数预测
|
摘要
以中国南方某铀尾矿砂为研究对象,在实测150组不同环境温度、湿度和尾矿砂粒径下的射气系数数据的基础上,基于BP神经网络预测理论,将环境温度、湿度和尾矿砂粒径作为BP神经网络的输入元,射气系数作为输出元,建立了颗粒堆积型介质射气系数的BP神经网络预测模型。将130组实测数据作为预测模型的训练样本,经过7 974次训练后精度满足要求,训练后的预测模型所得射气系数预测值与实测值的最大相对误差为2.68%,利用颗粒堆积型介质射气系数的BP神经网络预测模型得到的预测值与实测值吻合较好,预测模型可用于分析环境温度、湿度和介质粒径对颗粒堆积型介质射气系数的影响规律。
Taking a uranium tailings sand in southern China as the research object, under the measurement of 150 sets of emanation coefficient data with different environmental temperatures, humidity, and particle sizes of tailings and based on the BP neural network prediction theory, the environmental temperature, humidity, and particle size of the tailings sand are taken as the input elements of the BP neural network and the emanation coefficient is taken as the output element, the BP neural network prediction model of particle-packing media emanation coefficient is established. The 130 sets of measured data were used as training samples for the prediction model, the accuracy meets the requirement after 7 974 trainings. The maximum relative error between the predictive value and the measured value of the emanation coefficient obtained after training is 2.68%. The predicted values obtained by the BP neural network prediction model for the emanation coefficient of the particle-packing media were found to be in good agreement with the measured values, and the values can be used to analyze the influence rule of environmental temperature, humidity and media particle size on the emanation coefficient of particle-packing media.
Taking a uranium tailings sand in southern China as the research object, under the measurement of 150 sets of emanation coefficient data with different environmental temperatures, humidity, and particle sizes of tailings and based on the BP neural network prediction theory, the environmental temperature, humidity, and particle size of the tailings sand are taken as the input elements of the BP neural network and the emanation coefficient is taken as the output element, the BP neural network prediction model of particle-packing media emanation coefficient is established. The 130 sets of measured data were used as training samples for the prediction model, the accuracy meets the requirement after 7 974 trainings. The maximum relative error between the predictive value and the measured value of the emanation coefficient obtained after training is 2.68%. The predicted values obtained by the BP neural network prediction model for the emanation coefficient of the particle-packing media were found to be in good agreement with the measured values, and the values can be used to analyze the influence rule of environmental temperature, humidity and media particle size on the emanation coefficient of particle-packing media.
引文
[1] SAHU P,MISHRA D P,PANIGRAHI D C,et al.Radon emanation from backfilled mill tailings in underground uranium mine[J].Journal of Environmental Radioactivity,2014,130(4):15-21.
[2] THOMPSON R E,NELSON D F,POPKIN J H,et al.Case-control study of lung cancer risk from residential radon exposure in Worcester county,Massachusetts[J].Health Physics,2008,94(3):228.
[3] AL-ZOUGHOOL M,KREWSKI D.Health effects of radon:a review of the literature[J].International Journal of Radiation Biology,2009,85(1):57.
[4] 蒋经乾,劳玉军,王理,等.铀矿山尾矿库区浅层尾砂中核素的垂直分布特征[J].环境化学,2015,34(8):1561-1563.
[5] 张彪,张晓文,李密,等.铀尾矿污染特征及综合治理技术研究进展[J].中国矿业,2015(4):58-62.
[6] BARBOSA S M,LOPES F,CORREIA A D,et al.Temporal variability of radon in a remediated tailing of uranium ore processing - the case of Urgeirica (central Portugal)[J].Journal of Environmental Radioactivity,2015(142):14-23.
[7] 童建.吸烟与氡暴露致肺癌的流行病学和生物学差异[J].环境与职业医学,2007,24(5):542-545.
[8] CHARLES M.UNSCEAR report 2000:sources and effects of ionizing radiation[J].Journal of Radiological Protection Official Journal of the Society for Radiological Protection,2001,21(1):83.
[9] 张哲,朱民安,张永祥.地下工程与人居环境氡防护技术[M].北京:原子能出版社,2010:13-15.
[10] 付锦,韩耀照.氡射气系数与铀尾矿含水率关系探讨[J].南华大学学报(理工版),2003,17(3):29-32.
[11] BASKARAN M.Radon:a tracer for geological,geophysical and geochemical studies[M].Berlin:Springer International Publishing,2016.
[12] 杜洋.721矿尾矿库中核素(铀、钍)迁移特征及其对库区水环境影响[D].南昌:东华理工大学,2014.
[13] BASSOT S,STAMMOSE D,BENITAH S.Radium behavior during ferric oxi-hydroxides ageing[J].Radioprotection,2005,40(S1):277-283.
[14] LOTTERMOSER B G,ASHLEY P M.Tailings dam seepage at the rehabilitated Mary Kathleen uranium mine,Australia[J].Journal of Geochemical Exploration,2005,85(3):119-137.
[15] SEMKOW T M,PAREKH P P.The role of radium distribution and porosity in radon emanation from solids[J].Geophysical Research Letters,1990,17(6):837-840.
[16] 居治豪,周青芝,徐乐昌,等.铀矿样氡射气系数γ能谱法的应用及可靠性分析[J].铀矿冶,2016,35(3):224-228.
[17] 曾晔,陈凌,赵桂芝,等.原煤、粉煤灰及锅炉渣222Rn射气系数测量与研究[J].核电子学与探测技术,2014(11):1297-1300.
[18] ISHIMORI Y,LANGE K,MARTIN P,et al.Measurement and calculation of radon releases from NORM residues:technical reports series No.474[M].Vienna:International Atomic Energy Agency,2013.
[19] 雷浩东,孟耀勇,廖昱博,等.BP人工神经网络在光谱定量预测中的应用[J].激光生物学报,2007,16(4):490-494.
[20] 丛爽.面向MATLAB工具箱的神经网络理论与应用[M].合肥:中国科学技术大学出版社,2009.
[21] 肖云华.双峰隧道围岩稳定性非线性系统研究[D].长春:吉林大学,2009.
[2] THOMPSON R E,NELSON D F,POPKIN J H,et al.Case-control study of lung cancer risk from residential radon exposure in Worcester county,Massachusetts[J].Health Physics,2008,94(3):228.
[3] AL-ZOUGHOOL M,KREWSKI D.Health effects of radon:a review of the literature[J].International Journal of Radiation Biology,2009,85(1):57.
[4] 蒋经乾,劳玉军,王理,等.铀矿山尾矿库区浅层尾砂中核素的垂直分布特征[J].环境化学,2015,34(8):1561-1563.
[5] 张彪,张晓文,李密,等.铀尾矿污染特征及综合治理技术研究进展[J].中国矿业,2015(4):58-62.
[6] BARBOSA S M,LOPES F,CORREIA A D,et al.Temporal variability of radon in a remediated tailing of uranium ore processing - the case of Urgeirica (central Portugal)[J].Journal of Environmental Radioactivity,2015(142):14-23.
[7] 童建.吸烟与氡暴露致肺癌的流行病学和生物学差异[J].环境与职业医学,2007,24(5):542-545.
[8] CHARLES M.UNSCEAR report 2000:sources and effects of ionizing radiation[J].Journal of Radiological Protection Official Journal of the Society for Radiological Protection,2001,21(1):83.
[9] 张哲,朱民安,张永祥.地下工程与人居环境氡防护技术[M].北京:原子能出版社,2010:13-15.
[10] 付锦,韩耀照.氡射气系数与铀尾矿含水率关系探讨[J].南华大学学报(理工版),2003,17(3):29-32.
[11] BASKARAN M.Radon:a tracer for geological,geophysical and geochemical studies[M].Berlin:Springer International Publishing,2016.
[12] 杜洋.721矿尾矿库中核素(铀、钍)迁移特征及其对库区水环境影响[D].南昌:东华理工大学,2014.
[13] BASSOT S,STAMMOSE D,BENITAH S.Radium behavior during ferric oxi-hydroxides ageing[J].Radioprotection,2005,40(S1):277-283.
[14] LOTTERMOSER B G,ASHLEY P M.Tailings dam seepage at the rehabilitated Mary Kathleen uranium mine,Australia[J].Journal of Geochemical Exploration,2005,85(3):119-137.
[15] SEMKOW T M,PAREKH P P.The role of radium distribution and porosity in radon emanation from solids[J].Geophysical Research Letters,1990,17(6):837-840.
[16] 居治豪,周青芝,徐乐昌,等.铀矿样氡射气系数γ能谱法的应用及可靠性分析[J].铀矿冶,2016,35(3):224-228.
[17] 曾晔,陈凌,赵桂芝,等.原煤、粉煤灰及锅炉渣222Rn射气系数测量与研究[J].核电子学与探测技术,2014(11):1297-1300.
[18] ISHIMORI Y,LANGE K,MARTIN P,et al.Measurement and calculation of radon releases from NORM residues:technical reports series No.474[M].Vienna:International Atomic Energy Agency,2013.
[19] 雷浩东,孟耀勇,廖昱博,等.BP人工神经网络在光谱定量预测中的应用[J].激光生物学报,2007,16(4):490-494.
[20] 丛爽.面向MATLAB工具箱的神经网络理论与应用[M].合肥:中国科学技术大学出版社,2009.
[21] 肖云华.双峰隧道围岩稳定性非线性系统研究[D].长春:吉林大学,2009.