Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


osu1190140082.pdf (2.46 MB)

ETD Abstract Container

Abstract Header

Resilient modulus prediction using neural network algorithm

Hanittinan, Wichai
http://rave.ohiolink.edu/etdc/view?acc_num=osu1190140082

Abstract Details

2007, Doctor of Philosophy, Ohio State University, Civil Engineering.
The resilient modulus (MR) of subgrade or unbound materials is a key parameter current and proposed methods for predicting the structural response of pavements (the 2002 Mechanistic-Empirical Pavement Design Guide, M-E PDG). Backpropagation neural network algorithms were adopted to construct artificial neural networks (ANNs) were then used to predict the resilient modulus of three Ohio cohesive soil types: A- A-6, and A-7-6. The key input parameters for ANN analysis and simulations are percent of soil particles passing through a #200 sieve, plasticity index, liquid limit, unconfined compressive strength, percent of optimum moisture content, percent moisture content, degree of saturation, confining stress, deviator stress, and MR. Once developed, the ANNs were embedded in a soil utility model. This soil utility model has several features to help users prepare the required input data for the MR prediction using the developed ANNs and analyze the outcome. These features included discrepancy estimator, an optimum moisture content estimator using a one point proctor data inquiry for similarly matched soil data sets, a basic sensitivity analysis tool, Histogram of each key required parameter, a summary report, unit conversions, the Ohio classification system, a California bearing ratio estimator, soil unconfined compressive strength (qu) estimator, and MR estimators using the developed ANNS, the algorithms defined by the M-E PDG, or the Ohio department transportation (ODOT). These ANN regression algorithms can be used as an advisory tool which predicts MR for the M-E PDG model. Some advantages of the ANN models as a regression analysis tool were that no pre-determined relationship is required. The ANN algorithms can learn from the data to handle non-linear problems. Disadvantages are that they provide no explanation on their outcomes. In addition, the results can be overfitted if ANNs are not trained properly. For future studies, statistical techniques, information theory, fuzzy theory, and decision tree and matrix analysis can be incorporated in the ANN algorithms. Additional soil data are also needed so that they can represent all available Ohio soils under saturated and optimum moisture conditions and that they also extend the coverage to possible minimum and maximum MR prediction.
Fabian Tan (Advisor)
309 p.
resilient modulus; Mechanistic-Empirical Pavement Design Guide; M-E PDG; Pavement design; Ohio soils; artificial neural networks

Recommended Citations

Citations

  • Hanittinan, W. (2007). Resilient modulus prediction using neural network algorithm [Doctoral dissertation, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1190140082

    APA Style (7th edition)

  • Hanittinan, Wichai. Resilient modulus prediction using neural network algorithm. 2007. Ohio State University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1190140082.

    MLA Style (8th edition)

  • Hanittinan, Wichai. "Resilient modulus prediction using neural network algorithm." Doctoral dissertation, Ohio State University, 2007. http://rave.ohiolink.edu/etdc/view?acc_num=osu1190140082

    Chicago Manual of Style (17th edition)

osu1190140082
1,892
© 2007, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.