摘要Rolling Dynamic Compaction (RDC)，which is a ground improvement technique involving non-circular modules drawn behind a tractor，has provided the construction industry with an improved ground compaction capability，especially with respect to a greater influence depth and a higher speed of compaction，resulting in increased productivity. However，to date，there is no reliable method to predict the effectiveness of RDC in a range of ground conditions. This paper presents a new and unique predictive tool developed by means of artificial neural networks (ANNs) that permits a priori prediction of density improvement resulting from a range of ground improvement projects that employed 4-sided RDC modules；commercially known as“impact rollers”. The strong coefficient of correlation (i.e. R＞0.86) and the parametric behavior achieved in this study indicate that the model is successful in providing reliable predictions of the effectiveness of RDC in various ground conditions.
Abstract：Rolling Dynamic Compaction (RDC)，which is a ground improvement technique involving non-circular modules drawn behind a tractor，has provided the construction industry with an improved ground compaction capability，especially with respect to a greater influence depth and a higher speed of compaction，resulting in increased productivity. However，to date，there is no reliable method to predict the effectiveness of RDC in a range of ground conditions. This paper presents a new and unique predictive tool developed by means of artificial neural networks (ANNs) that permits a priori prediction of density improvement resulting from a range of ground improvement projects that employed 4-sided RDC modules；commercially known as“impact rollers”. The strong coefficient of correlation (i.e. R＞0.86) and the parametric behavior achieved in this study indicate that the model is successful in providing reliable predictions of the effectiveness of RDC in various ground conditions.
R. A. T. M. Ranasinghe，M. B. Jaksa，F. Pooya Nejad，Y. L. Kuo. Prediction of the effectiveness of rolling dynamic compaction using artificial neural networks and cone penetration test data[J]. 岩石力学与工程学报, 2019, 38(1): 153-170.
R. A. T. M. Ranasinghe，M. B. Jaksa，F. Pooya Nejad，Y. L. Kuo. Prediction of the effectiveness of rolling dynamic compaction using artificial neural networks and cone penetration test data. , 2019, 38(1): 153-170.
[1] HAUSMANN M R. Engineering principles of ground modification[J]. New York：McGraw-Hill，1990.
[2] PINARD M I. Innovative developments in compaction technology using high energy impact compactors[C]// 8th Australia New Zealand Conference on Geomechanics：Consolidating Knowledge. Hobart，Australia：Australian Geomechanics Society，1999.
[3] AVALLE D L. Use of the impact roller to reduce agricultural water loss[C]// 9th ANZ Conference on Geomechanics. Auckland，New Zealand：Citeseer，2004.
[4] PINARD M I，OOKEDITSE S. Evaluation of high energy impact compaction techniques for minimising construction water requirements in semi arid regions[C]// 14th Australian Road Research Board (ARRB) Conference. Canberra，Australia：ARRB Group Limited，1988.
[5] AVALLE D L，CARTER J P. Evaluating the improvement from impact rolling on sand[C]// 6th International Conference on Ground Improvement Techniques. Coimbra，Portugal：[s. n.]，2005.
[6] CLEGG B，BERRANGÉ A R. The development and testing of an impact roller[J]. The Civil Engineer in South Africa，1971，13(3)： 65–73.
[7] CLIFFORD J M. Impact rolling and construction techniques[C]// Australian Road Research Board Conference. Perth，Australia：[s. n.]，1976，8：21–29.
[8] CLIFFORD J M. The impact roller-problem solved[J]. The Civil Engineer in South Africa，1978，20(12)：321–324.
[9] AVALLE D L. Reducing haul road maintenance costs and improving Tyre wear through the use of impact rollers[C]// Mining for Tyres Conference. Perth，Australia：[s. n.]， 2006.
[10] AVALLE D L，YOUNG G. Trial programme and recent use of the impact roller in Sydney[C]// Earthworks Seminar，Australian Geomechanics Society. Adelaide，Australia：[s. n.]，2004.
[11] SCOTT B T，JAKSA M B. Mining applications and case studies of rolling dynamic compaction[C]// 11th Australia-New Zealand (ANZ) Conference on Geomechanics. Melbourne，Australia：[s. n.]，2012.
[12] ROBERTSON P K. Soil classification using the cone penetration test[J]. Canadian Geotechnical Journal，1990，27(1)：151–158.
[13] ASTM D5778–95 Standard test method for performing electronic friction cone and piezocone penetration testing of soils[S]. West Conshohocken：ASTM International，2000.
[14] LUNNE T，ROBERTSON P K，POWELL J J M. Cone penetration testing in geotechnical engineering practice[M]. New York，USA：Blackie Academic and Professional，1997.
[15] KELLY D B. Deep in-situ ground improvement using high energy impact compaction (Heic)[C]// Technology International Conference on Geological and Geotechnical Engineering. Melbourne，Australia：International Society for Rock Mechanics，2000.
[16] SCOTT B T，JAKSA M B. Evaluating rolling dynamic compaction of fill using CPT[C]// 3rd International Symposium on Cone Penetration Testing. Las Vegas，Nevada，USA：Omni Press，2014.
[17] JAKSA M B，SCOTT B T，MENTHA N L，et al. Quantifying the zone of influence of the impact roller[C]// International Symposium on Ground Improvement Brussels. Belgium：[s. n.]，2012， II：41–52.
[18] LACHTERMACHER G，FULLER J D. Backpropagation in hydrological time series forecasting[J]. Stochastic and Statistical Methods in Hydrology and Environmental Engineering，1994，10(3)：229–242.
[19] SHAHIN M A. Intelligent computing for modeling axial capacity of pile foundations[J]. Canadian Geotechnical Journal，2010，47(2)：230–243.
[20] MAIER H R，DANDY G C. The use of arti?cial neural networks for the prediction of water quality parameters[J]. Water Resources Research，1996，32(4)：1 013–1 022.
[21] SHAHIN M A，MAIER H R，JAKSA M B. Predicting the settlement of shallow foundations on cohesionless soils using back-propagation neural networks[M]. Adelaide，Australia：Department of Civil and Environmental Engineering，University of Adelaide，2000.
[22] MAIER H R，DANDY G C. Neural networks for the prediction and forecasting of water resources variables：a review of modelling issues and applications[J]. Environmental Modelling and Software，2000，15(1)：101–124.
[23] NAJJAR Y M，BASHEER I A，NAOUSS W A. On the identification of compaction characteristics by neuronets[J]. Computers and Geotechnics，1996，18(3)：167–187.
[24] GÜNAYDIN O. Estimation of soil compaction parameters by using statistical analyses and artificial neural networks[J]. Environmental Geology，2009，57(1)：203–215.
[25] POOYA NEJAD F，JAKSA M B，KAKHI M，et al. Prediction of pile settlement using artificial neural networks based on standard penetration test data[J]. Computers and Geotechnics，2009，36(7)： 1 125–1 133.
[26] SULEWSKA M J. Neural modelling of compactibility characteristics of cohesionless soil[J]. Computer Assisted Mechanics and Engineering Sciences，2010，17(1)：27–40.
[27] CHOK Y H，JAKSA M B，KAGGWA W S，et al. Neural network prediction of the reliability of heterogeneous cohesive slopes[J]. International Journal for Numerical and Analytical Methods in Geomechanics，2016，40(11)：1 556–1 569.
[28] POOYA NEJAD F，JAKSA M B. Load-settlement behavior modeling of single piles using artificial neural networks and CPT data[J]. Computers and Geotechnics，2017，89：9–21.
[29] Neusciences. Neuframe version 4.0[M]. Southampton，Hampshire：Neusciences Corp.，2000.
[30] MAIER H R，JAIN A，DANDY G C，et al. Methods used for the development of neural networks for the prediction of water resource variables in river systems： current status and future directions[J]. Environmental Modelling and Software，2010，25(8)：891–909.
[31] STONE M. Cross-validatory choice and assessment of statistical predictions[J]. Journal of the Royal Statistical Society Series B-Statistical Methodology，1974，36(2)：111–147.
[32] TOKAR A S，JOHNSON P A. Rainfall-runoff modeling using artificial neural networks[J]. Journal of Hydrologic Engineering，1999，4(3)：232–239.
[33] SHAHIN M A，MAIER H R，JAKSA M B. Data division for developing neural networks applied to geotechnical engineering[J]. Journal of Computing in Civil Engineering，2004，18(2)：105–114.
[34] BOWDEN G J，MAIER H R，DANDY G C. Optimal division of data for neural network models in water resources applications[J]. Water Resources Research，2002，38(2)：2–11.
[35] FLOOD I，KARTAM N. Neural networks in civil engineering. I：principles and understanding[J]. Journal of Computing in Civil Engineering，1994，8(2)：131–148.
[36] MINNS A W，Hall M J. Artificial neural networks as rainfall-runoff models[J]. Hydrological Sciences Journal，1996，41(3)：399–417.
[37] RUMELHART D E，HINTON G E，WILLIAMS R J. Learning representations by backpropagating errors. cognitive modeling[M]. POLK T A，SEIFERT C M. London，UK：The MIT Press，1986：213–221.
[38] FAUSETT L V. Fundamentals of neural networks：architectures，algorithms，and applications[M]. New Jersey，USA：Prentice-Hall，Inc.，1994.
[39] CYBENKO，G. Approximation by superpositions of a sigmoidal function[J]. Mathematics of Control，Signals and Systems，1989，2(4)：303–314.
[40] HORNIK K，STINCHCOMBE M，WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural Networks，1989，2(5)：359–366.
[41] CAUDILL M. Neural networks primer，part III[J]. AI Expert，1988，3(6)：53–59.
[42] SMITH M Neural networks for statistical modeling[M]. New York，USA：Thomson Learning，1993.
[43] SHAHIN M A，JAKSA，M B，MAIER H R. Neural network based stochastic design charts for settlement prediction[J]. Canadian Geotechnical Journal，2005，42(1)：110–120.
[44] DAS S K，SAMUI P，SABAT A. K. Application of artificial intelligence to maximum dry density and unconfined compressive strength of cement stabilized soil[J]. Geotechnical and Geological Engineering，2011，29(3)：329–342.
2019, Vol. 38 
