深圳大学学报理工版

为提高机场土面区安全动态预测及保障能力,结合某机场为期6 a的土面区安全评估数据,建立基于人工神经网络(artificial neural network, ANN)的压实度预测模型.选取天然密度(natural density, ND)、实测含水率(actual water content, AW)、最优含水率(optimal water content, OW)、降水状况(rainfall condition, RC)和压实状况(compaction condition, CC)作为输入向量,以双曲正切S型传输函数作为传递函数,利用400组实测数据完成模型训练后,用随机抽取的100组测试数据对模型进行精确校验,通过纳什效率系数(Nash-Sutcliffe efficiency coefficient, NSE)分析ANN模型的预测能力,并进行工程应用验证.结果表明,充分训练后ANN模型的均方差为0.98,NSE计算值为0.89,可有效预测土面区压实度.机场对比试验结果表明,大部分测区预测误差在±5%之内,仅有1个样本误差为15%,NSE计算值为0.86,达到了工程应用精度.采用影响因素分析法优化ANN模型发现,ND和AW是影响压实度最重要的因素,管理部门可通过严格控制回填土级配和加强排水措施有效改善土面区安全性.

In order to improve the dynamic prediction and management capabilities of soil field safety in airfield, a new artificial neural network(ANN)model was established based on the evaluation data of six years in an airport.By factors analysis of the actual soil field of the airport, natural density(ND), actual water content(AW), optimal water content(OW), rainfall condition(RC)and compaction condition(CC)were chosen as the input data, and hyperbolic tangent sigmoid function was set as the transfer function.The network was trained by 400 sets of data and validated for its accuracy by 100 sets of data selected randomly from the database.The prediction capability of achieved ANN model was analyzed by Nash-Sutcliffe efficiency coefficient(NSE)method.And engineering application had been done in another airport.The results show that soil field compactness can be effectively predicted by well-trained ANN model with R-Squared of 0.98 and NSE of 0.89.The outcomes of validation test in another airport prove that the errors of most sample zones are between -5% and 5%, with only one exception of 15%, with calculated NSE of 0.86, which satisfies the requirements of engineering application.By optimization of ANN model with factor analysis method, it indicates that ND and AW are the controlling factors of model compactness prediction, and the best ways of improving the safety of soil field in airport are soil gradation and drainage control strictly.

引言
1 压实度预测模型
2 机场应用验证
3 基于ANN的压实度影响因素分析
4 结论

图1 压实度预测流程图<br/>Fig.1 Flow chart of compactness prediction

图1 压实度预测流程图
Fig.1 Flow chart of compactness prediction

图2 某机场压实度测试方案<br/>Fig.2 Compactness test plan in the airport

图2 某机场压实度测试方案
Fig.2 Compactness test plan in the airport

图3 实测压实度与预测压实度的对比<br/>Fig.3 Comparisons of compactness between the predicted results and in-situ test results

图3 实测压实度与预测压实度的对比
Fig.3 Comparisons of compactness between the predicted results and in-situ test results

图4 对比机场验证试验<br/>Fig.4 Verification test in contrast airport

图4 对比机场验证试验
Fig.4 Verification test in contrast airport

表1 对比机场测区土样天然密度及含水率测试结果<br/>Table 1 Natural density and mass water content test results for soil samples of text zones in contrast airport

表1 对比机场测区土样天然密度及含水率测试结果
Table 1 Natural density and mass water content test results for soil samples of text zones in contrast airport

图5 对比机场压实度相对误差<br/>Fig.5 Compactness relative errors in contrast airport

图5 对比机场压实度相对误差
Fig.5 Compactness relative errors in contrast airport

图6 剔除单个影响因素后的平均误差及误差区间<br/>Fig.6 Average error and error range after removing one factor

图6 剔除单个影响因素后的平均误差及误差区间
Fig.6 Average error and error range after removing one factor

图7 剔除两个影响因素后的平均误差及误差区间<br/>Fig.7 Average error and error range after removing two factors

图7 剔除两个影响因素后的平均误差及误差区间
Fig.7 Average error and error range after removing two factors

[1] 霍志勤.中国民航运输航空器偏/冲出跑道统计分析[J].中国安全生产科学技术,2012,8(7):127-132.
[2] 刘国光,杨跃敏,牛富俊,等.春融作用对寒区机场土面区工作性能的影响[J].深圳大学学报理工版,2019,36(6):621- 627.
[3] CCAR—140—R1 民用机场运行安全管理规定[S].
[4] CANILLAS E C,SALOKHE V M.Regression analysis of some factors influencing soil compaction[J].Soil & Tillage Research,2001,61(3/4):167-178.
[5] PENG X H,HORN R,ZHANG B,et al.Mechanisms of soil vulnerability to compaction of homogenized and recompacted Ultisols[J].Soil & Tillage Research,2003,76(2):125-137.
[6] BARIK K,AKSAKAL E L,Islam K R,et al.Spatial variability in soil compaction properties associated with field traffic operations[J].Catena,2014,120:122-133.
[7] KOIKE M,KAJI T,USABORISUT P,et al.Several contributions to soil compactibility induced by cyclic loading test[J].Journal of Terramechanics,2002,39(3):127-141.
[8] AL-BADRAN Y,SCHANZ T.Modelling the compaction curve of fine-grained soils[J].Soils and Foundations,2014,54(3):426- 438.
[9] ALAOUI A,DISERENS E.Mapping soil compaction: a review[J].Current Opinion in Environmental Science & Health,2018,5:60- 66.
[10] SILVA R P,ROLIM M M,GOMES I F,et al.Numerical modeling of soil compaction in a sugarcane crop using the finite element method[J].Soil & Tillage Research,2018,181:1-10.
[11] SHAMAL S A M,ALHWAIMEL S A,MOUAZEN A M.Application of an online sensor to map soil packing density for site specific cultivation[J].Soil & Tillage Research,2016,162:78-86.
[12] KOWALCZYK S,MAAS'U1LAKOWSKI M,TUCHOLKA P.Determination of the correlation between the electrical resistivity of non-cohesive soils and the degree of compaction[J].Journal of Applied Geophysics,2014,110:43-50.
[13] NADERI-BOLDAJI M,SHARIFI A,ALIMARDANI R,et al.Use of a triple-sensor fusion system for on-the-go measurement of soil compaction[J].Soil & Tillage Research,2013,128:44-53.
[14] TROLDBORG M,AALDERS I,TOWERS W,et al.Application of Bayesian Belief Networks to quantify and map areas at risk to soil threats: using soil compaction as an example[J].Soil & Tillage Research,2013,132:56- 68.
[15] BOIVIN P, SCHAFFER B, TEMGOUA E, et al. Assessment of soil compaction using soil shrinkage modelling:experimental data and perspectives[J].Soil & Tillage Research,2006,88:65-79.
[16] TOBIAS S,TIETJE O.Modelling experts' judgments on soil compaction to derive decision rules for soil protection: a case study from Switzerland[J].Soil & Tillage Research,2007,92(1):129-143.
[17] PASDARPOUR M,GHAZAVI M,TESHNEHLAB M,et al.Optimal design of soil dynamic compaction using genetic algorithm and fuzzy system[J].Soil Dynamics and Earthquake Engineering,2009,29:1103-1112.
[18] TAGHAVIFAR H,MARDANI A,TAGHAVIFAR L.A hybridized artificial neural network and imperialist competitive algorithm optimization approach for prediction of soil compaction in soil bin facility[J].Measurement,2013,46(8):2288-2299.
[19] 林鲁生,冯夏庭,白世伟,等.人工神经网络在边坡滑移预测中的应用[J].岩土力学,2002,23(4):508-510.
[20] 史笑凡,杨春风,王可意.基于支持向量机和改进BP神经网络的路基边坡稳定性研究[J].公路交通科技,2019,36(1):31-37.
[21] ZARE A H,BAYAT V M,GOLMOHAMMADI G,et al.Soil temperature estimation using an artificial neural network and co-active neuro-fuzzy inference system in two different climates[J].Arabian Journal of Geosciences,2016,9(5):377.
[22] SARKAR T,MISHRA M.Soil erosion susceptibility mapping with the application of logistic regression and artificial neural network[J].Journal of Geovisualization and Spatial Analysis,2018,2(1):1-17.
[23] SHAHABI M,JAFARZADEH A A,NEYSHABOURI M R,et al.Spatial modeling of soil salinity using multiple linear regression,ordinary kriging and artificial neural network methods[J].Archives of Agronomy and Soil Science,2016,63(2):151-160.
[24] 杨学超,何彩平.基于BP人工神经网络的路基压实度预测模型研究[J].甘肃科学学报,2011,23(3):132-135.
[25] 李细荣.基于神经网络的土密实度检测[J].甘肃农业大学学报,2015,50(4):175-180.
[26] RANASINGHE R A T M,JAKSA M B,KUO Y L,et al.Application of artificial neural networks for predicting the impact of rolling dynamic compaction using dynamic cone penetrometer test results[J].Journal of Rock Mechanics and Geotechnical Engineering,2017,9(2):340-349.
[27] 刘国光,武志玮,牛富俊,等.基于BP神经网络的场道脱空检测方法及实验[J].深圳大学学报理工版,2016,33(3):309-316.
[28] 何秉顺,刘建坤,房建宏.使用人工神经网络预测冻土区公路路基沉降[J].公路交通科技,2005(11):46- 48.

备注

引言

1 压实度预测模型

2 机场应用验证

3 基于ANN的压实度影响因素分析

4 结论

期刊信息

备注

引言

1 压实度预测模型

2 机场应用验证

3 基于ANN的压实度影响因素分析

4 结 论

期刊信息

4 结论