JIN Kanhui,YANG Tao,HUO Shuyi,et al.Research on Prediction Methods of Shear Strength of Rolled Clay Based on Different PSO-ELM Models[J].Research of Soil and Water Conservation,2022,29(03):213-219+227.
基于不同PSO-ELM模型的碾压黏土抗剪强度预测方法研究
- Title:
- Research on Prediction Methods of Shear Strength of Rolled Clay Based on Different PSO-ELM Models
- 文章编号:
- 1005-3409(2022)03-0213-07
- Keywords:
- rolled clay; shear strength; particle swarm optimization; extreme learning machine; activation function
- 分类号:
- TU411.7
- 文献标志码:
- A
- 摘要:
- 碾压黏土的抗剪强度直接影响碾压土石坝的质量和使用寿命。为得出碾压黏土抗剪强度的最优预测模型,通过粒子群算法优化极限学习机模型(PSO-ELM),分别以Sine函数、radbas函数和hardlim函数3种激活函数为基础,构建PSO-ELMsin,PSO-ELMrad和PSO-ELMhard3种模型,并将模型结果与ELM模型、广义回归神经网络模型(GRNN)、随机森林模型(RF)和BP神经网络模型进行了对比。结果表明:在黏聚力和内摩擦角的拟合结果中,PSO-ELMsin模型精度最高,其拟合方程斜率分别为1.005,1.032; 在月值模拟中,PSO-ELMsin模型与实测值的拟合度最高,相对误差仅在6.0%～9.3%; PSO-ELMsin模型在黏聚力模拟中RMSE,RRMSE,MAE,Ens和R2分别为0.776 kPa,1.80%,0.641 kPa,0.993和0.997,该模型在内摩擦角模拟中RMSE,RRMSE,MAE,Ens和R2分别为1.635°,6.98%,1.616°,0.983和0.998,模型精度均排名第一。因此,PSO-ELMsin模型在所有模型中精度最高,可作为碾压黏土抗剪强度预测的标准模型使用。
- Abstract:
- The shear strength of rolled clay directly affects the quality and service life of roller compacted earth-rock dams. In order to obtain the optimal prediction model for the shear strength of rolled clay, we used particle swarm optimization to optimize the extreme learning machine model(PSO-ELM), which is based on the three activation functions of Sine function, radbas function and hardlim function to construct PSO-ELMsin, PSO-ELMrad and PSO-ELMhard. We compared the accuracy with ELM model, generalized regression neural network model(GRNN), random forest model(RF)and BP neural network model. The results show that: in the fitting results of cohesion and internal friction angle, the PSO-ELMsin model has the highest accuracy, and the slopes of the fitting equations are 1.005 and 1.032, respectively, which are closer to the standard value ‘1'; in the monthly simulation, the PSO-ELMsin model has the relative error of between 6.0% and 9.3%; RMSE, RRMSE and MAE of the PSO-ELMsin model in the conhesion simulation of the PSO-ELMsin model, the RMSE, RRMSE, MAE, Ens and R2 are 0.776 kPa, 1.80%, 0.641 kPa, 0.993 and 0.997, respectively. In the internal friction angle simulation, the RMSE, RRMSE, MAE, Ens and R2 are 1.635°, 6.98%, 1.616°, 0.983 and 0.998, respectively. The accuracy of PSO-ELMsin model ranks first. respectively. Therefore, the PSO-ELMsin model has the highest accuracy among all models and can be used as a precise model for predicting the shear strength of rolled clay.
参考文献/References:
[1] 胡赛潇,张云发,刘超,等.基于坝坡稳定复核的土石坝整体填筑质量评价[J].人民黄河,2018,40(5):133-138.
[2] 刘东海,王光烽.实时监控下土石坝碾压质量全仓面评估[J].水利学报,2010,41(6):720-726.
[3] Lai J, Wu S, Chiang C H. Evaluating the compaction quality of backfills by stress wave velocities[J]. Journal of Testing and Evaluation, 2011,39(5):785-791.
[4] 国家能源局.碾压式土石坝施工规范:DL/T 5129-2013[S].北京:中国电力出版社,2014:20-25.
[5] 赵惠新,吴志琴,李兆宇,等.基于BP神经网络冻融作用下细粒土抗剪强度的研究[J].水电能源科学,2012,30(4):32-33,78.
[6] 蒋佳莉,张卫兵,王红雨.干湿循环作用下银川地区重塑粉质黏土强度劣化试验研究[J].公路交通科技,2020,37(5):33-42.
[7] 陈佳雨,刘之葵.含水率及干密度对桂林红黏土抗剪强度的影响[J].中国岩溶,2019,38(6):930-936.
[8] 尚松浩,毛晓敏.基于BP神经网络的土壤冻结温度及未冻水含量预测模型[J].冰川冻土,2001,23(4):414-418.
[9] 王志会,吴爱祥,王洪江.基于PSO-BPNN的充填体围岩界面抗剪强度预测[J].矿业研究与开发,2020,40(3):130-134.
[10] 谢文强,蔡国军,王睿,等.基于CPTu数据的黏性土不排水抗剪强度神经网络预测[J].土木工程学报,2019,52(S2):35-41.
[11] 许健,冯灿,王掌权.基于BP神经网络的重塑黄土冻融过程抗剪强度劣化特性研究[J].水利与建筑工程学报,2016,14(6):13-17.
[12] Wang Y M, Traore S, Kerh T. Neural network approach for estimating reference evapotranspiration from limited climatic data in Burkina Faso[J]. Wseas Transactions on Computers, 2008,7(6):704-713.
[13] Traorea S, Wang Y M, Kerh T. Artificial neural network for modeling reference evapotranspiration complex process in Sudano-Sahelian zone[J]. Agricultural Water Management, 2010,97(5):707-714.
[14] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006,70:489-501.
[15] Zhu B, Feng Y, Gong D Z, et al. Hybrid particle swarm optimization with extreme learning machine for daily reference evapotranspiration prediction from limited climatic data[J]. Computers and Electronics in Agriculture, 2020,173:1-13.
[16] 冉梽乂,肖璐,崔宁博,等.基于广义回归神经网络模型模拟夏玉米蒸发蒸腾量[J].中国农村水利水电,2020(2):93-99.
[17] 张智韬,劳聪聪,王海峰,等.基于FOD和SVMDA-RF的土壤有机质含量高光谱预测[J].农业机械学报,2020,51(1):156-167.
[18] 展超.基于BP神经网络的富水砂层渣土改良试验效果预测[J].隧道建设(中英文),2020,40(7):988-996.
[19] 王杰,毕浩洋.一种基于粒子群优化的极限学习机[J].郑州大学学报:理学版,2013,45(1):100-104.
[20] 张念,崔宁博,赵璐,等.基于PSO-ELM的温室梨枣树液流量模拟[J].灌溉排水学报,2019,38(8):1-8.
[21] 张颖,李梅.基于粒子群优化极限学习机的水质评价新模型[J].环境科学与技术,2016,39(5):135-139.
[22] 王新民,万孝衡,朱阳亚,等.基于PSO-ELM的建筑物爆破震动速度预测[J].科技导报,2014,32(19):15-20.
[23] 陆业奇.含水率对黏土与混凝土接触面抗剪强度影响研究[J].水力发电,2018,44(12):126-129.
相似文献/References:
[1]潘天辉,杜 峰,王 月.陕北黄土区护坡植物根系分布和抗剪增强分析[J].水土保持研究,2020,27(03):357.
PAN Tianhui,DU Feng,WANG Yue.Analysis of Root Distributions and Shear Strengths of Slope Protection Plants in the Loess Region of Northern Shaanxi[J].Research of Soil and Water Conservation,2020,27(03):357.
[2]宋鹏帅,王 健,陈 琳,等.模拟干湿交替对夯实土壤抗剪强度的影响[J].水土保持研究,2021,28(02):74.
SONG Pengshuai,WANG Jian,CHEN Lin,et al.Effect of Wet-Dry Cycle on Shear Strength of Compacted Soil[J].Research of Soil and Water Conservation,2021,28(03):74.
[3]杨 路,杜 峰,秦晶晶,等.黄土区3种优势灌木根土复合体的抗剪强度研究[J].水土保持研究,2022,29(01):295.
YANG Lu,DU Feng,QIN Jingjing,et al.Research on Shear Strengths of Root-Soil Complexes of Three Dominant Shrubs in Loess Region[J].Research of Soil and Water Conservation,2022,29(03):295.
[4]李叶鑫,吕 刚,宁宝宽,等.排土场土体裂缝区植被根系及抗剪强度分布特征[J].水土保持研究,2022,29(04):108.
LI Yexin,L Gang,NING Baokuan,et al.Distribution Characteristics of Vegetation Root System and Shear Strength with Ground Fissure in a Dump[J].Research of Soil and Water Conservation,2022,29(03):108.
[5]何伟鹏,胡夏嵩,刘昌义,等.不同植物对黄土边坡产流产沙与抗剪强度的影响[J].水土保持研究,2023,30(04):18.[doi:10.13869/j.cnki.rswc.2023.04.046.]
HE Weipeng,HU Xiasong,LIU Changyi,et al.Effects of Different Plants on Runoff and Sediment Yield and Shear Strength of Loess Slope[J].Research of Soil and Water Conservation,2023,30(03):18.[doi:10.13869/j.cnki.rswc.2023.04.046.]
[6]展 鹏,张超波,张 强,等.干湿交替下苜蓿根系对黄土抗剪力学性能影响[J].水土保持研究,2023,30(06):222.[doi:10.13869/j.cnki.rswc.2023.06.006]
Zhan Peng,Zhang Chaobo,Zhang Qiang,et al.Effects of Alfalfa Roots on the Shear Properties of Loess Under Alternate Drying-Wetting Conditions[J].Research of Soil and Water Conservation,2023,30(03):222.[doi:10.13869/j.cnki.rswc.2023.06.006]
备注/Memo
收稿日期:2021-01-06 修回日期:2021-02-21
资助项目:河北省高等学校科学技术研究项目(Z2019031); 道路与铁道工程安全保障省部共建教育部重点实验室(石家庄铁道大学)开放课题(STKF201902); 河北省属高等学校基本科研业务费科技重点科研培育项目(SYKY2101)
第一作者:金坎辉(1986—),男,河北沧州人,硕士,讲师,研究方向:土木工程施工及工程结构。E-mail:kingkh0001@163.com
通信作者:杨涛(1986—),男,河北沧洲人,硕士,工程师,研究方向:建筑工程技术。E-mail:cangzhouyt@163.com