Structural and Multidisciplinary Optimization

, Volume 59, Issue 4, pp 1335–1353 | Cite as

Principal component analysis-based predictive modeling and optimization of permanent deformation in asphalt pavement: elimination of correlated inputs and extrapolation in modeling

  • Parnian GhasemiEmail author
  • Mohamad Aslani
  • Derrick K. Rollins
  • R. C. Williams
Research Paper


Permanent deformation in asphalt pavement is a function of material properties, loading, environmental conditions, and structural design (e.g., thickness of pavement layers). Because of the large number of effective variables and their nonlinear interrelationships, it is not easy to develop a predictive model for permanent deformation. In this study, a laboratory database containing accumulated strain values (output) and material properties (inputs) from several asphalt pavements has been used to develop a predictive model for permanent deformation. We first show that the inputs are highly correlated, then principal component analysis (PCA) is used to compute a set of orthogonal pseudo-inputs. Two predictive models based on the pseudo-inputs were developed using linear regression analysis and artificial neural networks (ANN) and are compared using statistical analysis. Extrapolation using empirical predictive models is highly risky and discouraged by experienced practitioners, so to guard against extrapolation, a method is developed to determine an input hyper-space. The above-developed model, along with an n-dimensional hyper-space, provides sufficient information for supporting an optimization algorithm for finding the minimum accumulated strain. An asphalt pavement design with accumulated strain value of 1772 micro-strain (0.02 in. in a 10-in.-thick asphalt pavement layer) is obtained by solving the optimization problem and the design parameters meet flexible pavement design specifications. The proposed framework is able to generate accurate predictive models when the original inputs are highly correlated and able to map to an optimal point in the fitted input space.


Permanent deformation Asphalt pavement Principal component analysis Linear regression modeling Artificial neural networks Optimization 



  1. AASHTOTP 79-13 (2013) AASHTO TP 79-13 Determining the dynamic modulus and flow number for asphalt mixtures using the Asphalt Mixtures Performance Tester. American Association of State Highway and Transportation Officials, pp 1–19Google Scholar
  2. Apeagyei AK (2011) Rutting as a function of dynamic modulus and gradation. Amer Soc Civ Eng 23 (9):1302–1310Google Scholar
  3. ARA Inc. ECD (2004) Guide for mechanistic–empirical design of new and rehabilitated pavement structures. Final Rep. NCHRP Project 1-37AGoogle Scholar
  4. Arabali P, Sakhaeifar MS, Freeman TJ, Wilson BT, Borowiec JD (2017) Decision-making guideline for preservation of flexible pavements in general aviation airport management. Journal of Transportation Engineering. Part B: Pavements 143(2):04017,006Google Scholar
  5. Aslani M, Asla RN, Oftadehb R, Panahic MS (2010) A novel hybrid simplex-genetic algorithm for the optimum design of truss structures. In: Proceedings of the world congress on engineering, vol. 2Google Scholar
  6. Aslani M, Ghasemi P, Gandomi AH (2018) Constrained mean-variance mapping optimization for truss optimization problems. Struct Des Tall Special Build 27(6):e1449Google Scholar
  7. Bashin A, Masad E, Kutay ME, Buttlar W, Kim YR, Marasteanu M, Kim YR, Schwartz CW, Carvalho RL (2012) Applications of advanced models to understand behavior and performance of asphalt mixtures. Transportation Research E-Circular (E-C161)Google Scholar
  8. Birgisson B, Roque R, Kim J, Pham LV (2004) The Use of Complex Modulus To Characterize Performance of Asphalt Mixtures and Pavements in Florida. Tech. Rep. September 2004, florida department of transportation florida department of transportationGoogle Scholar
  9. Carpenter W, Barthelemy JF (1993) A comparison of polynomial approximations and artificial neural nets as response surfaces. Struct Multidiscip Optim 5(3):166–174Google Scholar
  10. Cheng B, Titterington D (1994) Neural networks: a review from a statistical perspectiveGoogle Scholar
  11. Cominsky RJ, Huber GA, Kennedy TW, Anderson M (1994) The superpave mix design manual for new construction and overlays. SHRP-a-407. Strategic Highway Research Program, Washington, DCGoogle Scholar
  12. Devore JL (2011) Probability and Statistics for Engineering and the. Sciences Cengage learningGoogle Scholar
  13. Ebrahimi M, ShafieiBavani E, Wong RK, Fong S, Fiaidhi J (2017) An adaptive meta-heuristic search for the internet of things. Futur Gener Comput Syst 76:486–494Google Scholar
  14. Erlich I, Venayagamoorthy GK, Worawat N (2010) A mean-variance optimization algorithm. IEEE Congress on Evolutionary Computation, pp 1–6.
  15. Fodor IK (2002) A Survey of Dimension Reduction Techniques. Tech. rep., U.S Department of Energy, U.S. Department of EnergyGoogle Scholar
  16. García-Segura T, Yepes V, Frangopol DM (2017) Multi-objective design of post-tensioned concrete road bridges using artificial neural networks. Struct Multidiscip Optim 56(1):139–150MathSciNetGoogle Scholar
  17. Ghasemi P, Aslani M, Rollins DK, Williams R, Schaefer VR (2018) Modeling rutting susceptibility of asphalt pavement using principal component pseudo inputs in regression and neural networks. International Journal of Pavement Research and TechnologyGoogle Scholar
  18. Granato D, Santos JS, Escher GB, Ferreira BL, Maggio RM (2017) Use of principal component analysis (PCA) and hierarchical cluster analysis (HCA) for multivariate association between bioactive compounds and functional properties in foods: a critical perspective. Trends in Food Science & TechnologyGoogle Scholar
  19. Happ C, Greven S (2018) Multivariate functional principal component analysis for data observed on different (dimensional) domains. J Am Stat Assoc 113(522):649–659. MathSciNetzbMATHGoogle Scholar
  20. Johnson RA, Wichern DW, et al. (2014) Applied multivariate statistical analysis, vol 4. Prentice-Hall, New JerseyGoogle Scholar
  21. Jolliffe IT (2002) Principal component analysis, Second Edition. Encycl Stat Behav Sci 30(3):487zbMATHGoogle Scholar
  22. Juang CH, Chen CJ (1999) CPT-based liquefaction evaluation using artificial neural networks. Comput-Aided Civ Infrastruct Eng 14(3):221–229Google Scholar
  23. Kaloush K, Witczak M, Sullivan BW (2003) Simple performance test for permanent deformation evaluation of asphalt mixtures. Sixth International RILEM Symposium on Performance Testing and Evaluation of Bituminous Materials, pp 498–505Google Scholar
  24. Kartam N (1994) Neural netwroks in civil engineering: systems and application. J Comput Civ Eng 8(2):149–162Google Scholar
  25. Kutner MH, Nachtsheim C, Neter J (2004) Applied linear regression models. McGraw-Hill/Irwin, New YorkGoogle Scholar
  26. Kvasnak A, Robinette C, Williams R (2007) A statistical development of a flow number predictive equation for the Mechanistic-Empirical Pavement Design Guide.CD-ROM. In: Transportation Research Board. D. Transportation Research Board, Washington (ed), vol 3. Washington, DC, pp 1–18Google Scholar
  27. Lever J, Krzywinski M, Altman N (2017) Points of significance: principal component analysisGoogle Scholar
  28. Liew K, Tan H, Ray T, Tan M (2004) Optimal process design of sheet metal forming for minimum springback via an integrated neural network evolutionary algorithm. Struct Multidiscip Optim 26(3):284–294Google Scholar
  29. Lim J, Jang YS, Chang HS, Park JC, Lee J (2018) Role of multi-response principal component analysis in reliability-based robust design optimization: an application to commercial vehicle design. Struct Multidiscip Optim 58(2):785–796. Google Scholar
  30. Lombardero AC, Piqueras VY, Vidosa FG (2012) Automatic design of concrete vaults using iterated local search and extreme value estimation, vol 9. Argentinean Association of Computational Mechanics, Brazilian Association of Computational Mechanics, Mexican Association of Numerical Methods in Engineering and Applied SciencesGoogle Scholar
  31. Malik MR, Isaac BJ, Coussement A, Smith PJ, Parente A (2018) Principal component analysis coupled with nonlinear regression for chemistry reduction. Combust Flame 187:30–41Google Scholar
  32. Marti-Vargas JR, Ferri FJ, Yepes V (2013) Prediction of the transfer length of prestressing strands with neural networks. Comput Concr 12(2):187–209Google Scholar
  33. MATLAB (2012) Matheworks, T., 2012. Matlab 2012bGoogle Scholar
  34. May R, Dandy G, Maier H (2011) Review of input variable selection methods for artificial neural networks. In: Artificial neural networks-methodological advances and biomedical applications. intechGoogle Scholar
  35. Nicholas PE, Padmanaban K, Vasudevan D, Ramachandran T (2015) Stacking sequence optimization of horizontal axis wind turbine blade using fea, ann and ga. Struct Multidiscip Optim 52(4):791–801MathSciNetGoogle Scholar
  36. Noh Y, Choi K, Du L (2009) Reliability-based design optimization of problems with correlated input variables using a gaussian copula. Struct Multidiscip Optim 38(1):1–16Google Scholar
  37. Paya-Zaforteza I, Yepes V, González-Vidosa F, Hospitaler A (2010) On the weibull cost estimation of building frames designed by simulated annealing. Meccanica 45(5):693–704zbMATHGoogle Scholar
  38. Pellinen T, Witczak M (2002) Use of stiffness of Hot-Mix asphalt as a simple performance test. Transp Res Rec J Transp Res Board 1789(02):80–90Google Scholar
  39. Rahami H, Kaveh A, Aslani M, Najian Asl R (2011) A hybrid modified genetic-nelder mead simplex algorithm for large-scale truss optimization. Iran Univ Sci Technol 1(1):29–46Google Scholar
  40. Refaeilzadeh P, Tang L, Liu H (2009) Cross-validation. In: Encyclopedia of database systems. Springer, pp 532–538Google Scholar
  41. Rodezno M, Kaloush K, Corrigan M (2010) Development of a Flow Number Predictive Model. Transp Res Rec J Transp Res Board 2181(2181):79–87Google Scholar
  42. Rollins KD Sr (2015) A One-dimensional PCA approach for classifying imbalanced data. J Comput Sci Syst Biol 8(1):5–11Google Scholar
  43. Rollins DK, Zhai D, Joe AL, Guidarelli JW, Murarka A, Gonzalez R (2006) A novel data mining method to identify assay-specific signatures in functional genomic studies. BMC Bioinforma 7:377Google Scholar
  44. Rueda JL, Erlich I (2015) Testing MVMO on learning-based real-parameter single objective benchmark optimization problems. 2015 IEEE Congress on Evolutionary Computation, CEC 2015 - Proceedings, pp 1025–1032Google Scholar
  45. Su CT, Tong LI (1997) Multi-response robust design by principal component analysis. Total Qual Manag 8(6):409–416Google Scholar
  46. Talatahari S, Gandomi AH, Yang XS, Deb S (2015) Optimum design of frame structures using the eagle strategy with differential evolution. Eng Struct 91:16–25Google Scholar
  47. Timm D, West R, Priest A, Powell B, Selvaraj I, Zhang J, Brown R (2006) Phase ii ncat test track results. NCAT Report 6(05)Google Scholar
  48. Todd MJ, Yıldırım EA (2007) On khachiyan’s algorithm for the computation of minimum-volume enclosing ellipsoids. Discret Appl Math 155(13):1731–1744MathSciNetzbMATHGoogle Scholar
  49. Witzcak MW (2002) Simple performance test for superpave mix design. Transportation Research Board, vol 465Google Scholar
  50. Xiong F, Wang D, Zhang S, Cai K, Wang S, Lu F (2017) Lightweight optimization of the side structure of automobile body using combined grey relational and principal component analysis. Struct Multidiscip Optim 57:441–461Google Scholar
  51. Xiong F, Wang D, Zhang S, Cai K, Wang S, Lu F (2018) Lightweight optimization of the side structure of automobile body using combined grey relational and principal component analysis. Struct Multidiscip Optim 57(1):441–461Google Scholar
  52. Yi S, Lai Z, He Z, Cheung YM, Liu Y (2017) Joint sparse principal component analysis. Pattern Recogn 61:524–536Google Scholar
  53. Zhang J, Yang J, Kim YR (2015) Characterization of mechanical behavior of asphalt mixtures under partial triaxial compression test. Constr Build Mater 79:136–144Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Civil EngineeringIowa State UniversityAmesUSA
  2. 2.Department of MathematicsFlorida State UniversityTallahasseeUSA
  3. 3.Department of Chemical and Biological EngineeringIowa State UniversityAmesUSA

Personalised recommendations