Prediction of Marshall test results for polypropylene modified dense bituminous mixtures using neural networks

This study presents an application of neural networks (NN) for the prediction of Marshall test results for polypropylene (PP) modified asphalt mixtures. PP fibers are used to modify the bituminous binder in order to improve the physical and mechanical properties of the resulting asphaltic mixture. Marshall stability and flow tests were carried out on specimens fabricated with different type of PP fibers and also waste PP at optimum bitumen content. It has been shown that the addition of polypropylene fibers results in the improved Marshall stabilities and Marshall Quotient values, which is a kind of pseudo stiffness. The proposed NN model uses the physical properties of standard Marshall specimens such as PP type, PP percentage, bitumen percentage, specimen height, unit weight, voids in mineral aggregate, voids filled with asphalt and air voids in order to predict the Marshall stability, flow and Marshall Quotient values obtained at the end of mechanical tests. The explicit formulation of stability, flow and Marshall Quotient based on the proposed NN model is also obtained and presented for further use by researchers. Moreover parametric analyses have been carried out. The results of parametric analyses were used to evaluate mechanical properties of the Marshall specimens in a quite well manner.

[1]  Mohamed S Kaseko,et al.  A neural network-based methodology for pavement crack detection and classification , 1993 .

[2]  Sam Owusu-Ababio.  Effect of Neural Network Topology on Flexible Pavement Cracking Prediction , 1998 .

[3]  Abdullah M. Alsugair,et al.  Artificial neural network approach for pavement maintenance , 1998 .

[4]  Ahmed Senouci,et al.  A pavement condition-rating model using backpropagation neural networks , 1995 .

[5]  Erol Tutumluer,et al.  Backcalculation of full-depth asphalt pavement layer moduli considering nonlinear stress-dependent subgrade behavior , 2005 .

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  Ibrahim H. Guzelbey,et al.  Neural network modeling of strength enhancement for CFRP confined concrete cylinders , 2008 .

[8]  A R Shekharan.  EFFECT OF NOISY DATA ON PAVEMENT PERFORMANCE PREDICTION BY ARTIFICIAL NEURAL NETWORKS , 1998 .

[9]  Stephen G. Ritchie,et al.  DEVELOPMENT OF AN INTELLIGENT SYSTEM FOR AUTOMATED PAVEMENT EVALUATION , 1991 .

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

[11]  Gerald J. Malasheskie,et al.  FIELD PERFORMANCE OF FABRICS AND FIBERS TO RETARD REFLECTIVE CRACKING , 1989 .

[12]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[13]  M. Aren Cleven,et al.  INVESTIGATION OF THE PROPERTIES OF CARBON FIBER MODIFIED ASPHALT MIXTURES , 2000 .

[14]  S F Brown,et al.  ASPHALT MODIFICATION. THE UNITED STATES STRATEGIC HIGHWAY RESEARCH PROGRAM. SHARING THE BENEFITS. CONFERENCE ORGANIZED BY THE INSTITUTION OF CIVIL ENGINEERS IN COOPERATION WITH U.S. STRATEGIC HIGHWAY RESEARCH PROGRAM, 29TH-31ST OCTOBER 1990, TARA HOTEL, KENSINGTON, LONDON , 1990 .

[15]  Yeou-Shang Jenq,et al.  ANALYSIS OF CRACK RESISTANCE OF ASPHALT CONCRETE OVERLAYS--A FRACTURE MECHANICS APPROACH , 1993 .

[16]  Byoung Jik Lee,et al.  Position‐Invariant Neural Network for Digital Pavement Crack Analysis , 2004 .

[17]  刘刚,et al.  Effect of fiber types on relevant properties of porous asphalt , 2006 .

[18]  Ahmet Tuncan,et al.  Repeated Creep Behavior of Polypropylene Fiber-Reinforced Bituminous Mixtures , 2009 .

[19]  Pedro Albrecht,et al.  Computing truck attributes with artificial neural networks , 1994 .

[20]  Yudong Cal,et al.  Soil classification by neural network , 1995 .

[21]  S. Tapkın.  IMPROVED ASPHALT AGGREGATE MIX PROPERTIES BY PORTLAND CEMENT MODIFICATION , 2000 .

[22]  G. Bosurgi,et al.  A model based on artificial neural networks and genetic algorithms for pavement maintenance management , 2005 .

[23]  Wu Shaopeng,et al.  Effect of fiber types on relevant properties of porous asphalt , 2006 .

[24]  Ke‐long Huang,et al.  Synthesis and electrochemical properties of SnO2-CuO nanocomposite powders , 2006 .

[25]  Manjriker Gunaratne,et al.  Neural Network for Rapid Depth Evaluation of Shallow Cracks in Asphalt Pavements , 2004 .

[26]  Serkan Tapkın,et al.  The effect of polypropylene fibers on asphalt performance , 2008 .

[27]  Nii O. Attoh-Okine,et al.  A Comparative Analysis of Two Artificial Neural Networks Using Pavement Performance Prediction , 1998 .

[28]  Amy L. Simpson,et al.  Case Study of Modified Bituminous Mixtures: Somerset, Kentucky , 1994 .

[29]  Erol Tutumluer,et al.  Neural Network Modeling of Anisotropic Aggregate Behavior from Repeated Load Triaxial Tests , 1998 .

[30]  Nii O. Attoh-Okine.  Grouping Pavement Condition Variables for Performance Modeling Using Self-Organizing Maps , 2001 .

[31]  A. G. Razaqpur,et al.  Bridge management by dynamic programming and neural networks , 1996 .

[32]  Nii O Attoh-Okine,et al.  Modeling incremental pavement roughness using functional network , 2005 .

[33]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .