Knowledge discovery and data mining in pavement inverse analysis

Abstract This paper describes the use of data mining tools for predicting the non-linear layer moduli of asphalt road pavement structures based on the deflection profiles obtained from non-destructive deflection testing. The deflected shape of the pavement under vehicular loading is predominantly a function of the thickness of the pavement layers, the moduli of individual layers, and the magnitude of the load. The process of inverse analysis, more commonly referred to as ‘backcalculation’, is used to estimate the elastic (Young's) moduli of individual pavement layers based upon surface deflections. A comprehensive synthetic database of pavement response solutions was generated using an advanced non-linear pavement finite-element program. To overcome the limitations associated with conventional pavement moduli backcalculation, data mining tools such as support vector machines, neural networks, decision trees, and meta-algorithms like bagging were used to conduct asphalt pavement inverse analysis. The resul...

[1]  Y. Richard Kim,et al.  Prediction of Layer Moduli from Falling Weight Deflectometer and Surface Wave Measurements Using Artificial Neural Network , 1998 .

[2]  Yong Wang.  A New Approach to Fitting Linear Models in High Dimensional Spaces , 2000 .

[3]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[4]  C L Monismith,et al.  FACTORS INFLUENCING THE RESILIENT RESPONSE OF GRANULAR MATERIALS , 1971 .

[5]  Robert L. Lytton.  Backcalculation of Pavement Layer Properties , 1989 .

[6]  Jerzy Jackowski,et al.  Use of Artificial Neural Networks in Geomechanical and Pavement Systems , 2000 .

[7]  S. Emerson,et al.  AASHTO (American Association of State Highway and Transportation Officials). 2001. A Policy on Geometric Design of Highways and Streets. Fourth Edition. Washington, D.C. , 2007 .

[8]  Ghassan R. Chehab,et al.  New England Verification of National Cooperative Highway Research Program (NCHRP) 1-37A Mechanistic-Empirical Pavement Design Guide , 2012 .

[9]  Peter Dalgaard,et al.  R Development Core Team (2010): R: A language and environment for statistical computing , 2010 .

[10]  Gonzalo R. Rada,et al.  COMPREHENSIVE EVALUATION OF LABORATORY RESILIENT MODULI RESULTS FOR GRANULAR MATERIAL , 1981 .

[11]  M R Thompson,et al.  Mechanistic interpretation of nondestructive pavement testing deflections , 1981 .

[12]  Anastasios M. Ioannides.  DIMENSIONAL ANALYSIS IN NDT RIGID PAVEMENT EVALUATION , 1990 .

[13]  Victor Cervantes,et al.  Performance of concrete pavements , 2009 .

[14]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[15]  Kurt D Smith,et al.  PERFORMANCE OF CONCRETE PAVEMENTS. VOLUME II: EVALUATION OF INSERVICE CONCRETE PAVEMENTS , 1998 .

[16]  M I Darter,et al.  LTPP data analysis - phase 1: validation of guidelines for k-Value selection and concrete pavement performance prediction , 1997 .

[17]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[18]  J P Christory.  EVALUATION OF CONCRETE PAVEMENTS , 1988 .

[19]  E J Barenberg,et al.  EVALUATION OF CONCRETE PAVEMENTS USING NDT RESULTS. FINAL SUMMARY REPORT , 1991 .

[20]  Erna Weher.  Edwards, Allen, L.: An introduction to linear regression and correlation. (A series of books in psychology.) W. H. Freeman and Comp., San Francisco 1976. 213 S., Tafelanh., s 7.00 , 1977 .

[21]  Sunil Sharma,et al.  Backcalculation of pavement layer moduli from falling weight deflectometer data using an artificial neural network , 2008 .

[22]  Norbert J. Delatte,et al.  Mechanistic-Empirical Pavement Design Guide , 2014 .

[23]  Yong Wang,et al.  Modeling for Optimal Probability Prediction , 2002, ICML.

[24]  Halil Ceylan.  Analysis and Design of Concrete Pavement Systems Using Artificial Neural Networks , 2002 .

[25]  L H Irwin.  Backcalculation: an overview and perspective , 2002 .

[26]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Pt Foxworthy,et al.  ILLI-SLAB and FWD Deflection Basins for Characterization of Rigid Pavements , 1989 .

[28]  J. Friedman.  Stochastic gradient boosting , 2002 .

[29]  A. L. Edwards,et al.  An introduction to linear regression and correlation. , 1985 .

[30]  阿部 頼政.  国際会議"The Bearing Capacity of Roads and Airfields"に参加して , 1982 .

[31]  W O Hadley,et al.  PACIFIC RIM TRANSTECH CONFERENCE PROCEEDINGS. VOLUME II. CHANGES TO THE AASHTO GUIDE FOR DESIGN OF PAVEMENT STRUCTURES , 1993 .

[32]  Lutfi Raad,et al.  LOAD RESPONSE OF TRANSPORTATION SUPPORT SYSTEMS , 1980 .

[33]  G Y Baladi,et al.  Nondestructive Testing of Pavements and Backcalculation of Moduli , 1989 .

[34]  D E Newcomb.  COMPARISONS OF FIELD AND LABORATORY ESTIMATED RESILIENT MODULI OF PAVEMENT MATERIALS (WITH DISCUSSION) , 1987 .

[35]  Sirous Alavi,et al.  Falling Weight Deflectometer Usage , 2008 .

[36]  Ron Kohavi,et al.  The Power of Decision Tables , 1995, ECML.

[37]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[38]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[39]  Halil Ceylan,et al.  Advanced Approaches to Characterizing Nonlinear Pavement System Responses , 2007 .

[40]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[41]  Thomas D. White,et al.  MULTILAYER ELASTIC PROGRAM FOR BACKCALCULATING LAYER MODULI IN PAVEMENT EVALUATION , 1989 .

[42]  Nenad Gucunski,et al.  Backcalculation of Pavement Profiles from Spectral-Analysis-of-Surface-Waves Test by Neural Networks Using Individual Receiver Spacing Approach , 1996 .

[43]  Kasthurirangan Gopalakrishnan,et al.  Performance Analysis of Airport Flexible Pavements Subjected to New Generation Aircraft , 2004 .

[44]  渡辺 亨,et al.  コンクリ-ト製中央分離帯防護柵に関する衝突実験と事故分析(Transportation Research Circular,No.341,1988) , 1990 .

[45]  J. Wielinski,et al.  Annual Meeting of the Transportation Research Board , 2010 .

[46]  Marshall R Thompson,et al.  ILLI-PAVE-BASED RESPONSE ALGORITHMS FOR DESIGN OF CONVENTIONAL FLEXIBLE PAVEMENTS , 1985 .

[47]  William W. Cohen.  Fast Effective Rule Induction , 1995, ICML.

[48]  Maryam Miradi,et al.  Knowledge Discovery and Pavement Performance: Intelligent Data Mining , 2009 .

[49]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[50]  Richard D. Woods,et al.  Comparison of Field and Laboratory Shear Moduli , 1975 .

[51]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[52]  H WittenIan,et al.  The WEKA data mining software , 2009 .

[53]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[54]  E J Barenberg,et al.  INTERPRETATION OF FALLING WEIGHT DEFLECTOMETER RESULTS USING PRINCIPLES OF DIMENSIONAL ANALYSIS. PROCEEDINGS, 4TH INTERNATIONAL CONFERENCE ON CONCRETE PAVEMENT DESIGN AND REHABILITATION, PURDUE UNIVERSITY, APRIL 18-20, 1989 , 1989 .

[55]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[56]  Q. L. Robnett,et al.  Resilient Properties of Subgrade Soils , 1973 .

[57]  Jeffery Raphael Roesler,et al.  DIPLOBACK: Neural-Network-Based Backcalculation Program for Composite Pavements , 1997 .

[58]  Roger W. Meier,et al.  BACKCALCULATION OF FLEXIBLE PAVEMENT MODULI USING ARTIFICIAL NEURAL NETWORKS , 1994 .

[59]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1993 .

[60]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[61]  Nii O. Attoh-Okine,et al.  Intelligent and Soft Computing in Infrastructure Systems Engineering: Recent Advances , 2009, Intelligent and Soft Computing in Infrastructure Systems Engineering.