Support vector machines for nonlinear pavement backanalysis

نویسندگان

  • Kasthurirangan Gopalakrishnan
  • Sunghwan Kim
چکیده

Backanalysis or backcalculation of in-service pavement mechanical properties (such as elastic modulus) from pavement Non-Destructive Test (NDT) deflection data is a routine practice carried out by highway engineers for pavement structural condition evaluation, remaining life calculations, and mechanistic-based analysis. Owing to the complexity of this ill-conditioned inverse modeling problem, numerous backcalculation routines have been developed and implemented over the years ranging from simple deflection-basin matching programs to intelligent and soft computing based methodologies and each has its own pros and cons. This paper presents an efficient off-line pavement backcalculation system based on support vector machines (SVM) and compares its performance with another popular machine learning technique, multi-layer perceptrons (MLP). Both systems are trained and tested using synthetic deflection basins generated using a two-dimensional axisymmetric finite element software covering a wide range of in-service pavement scenarios. The results show that the effectiveness of SVM approach in pavement backanalysis is comparable to MLP approach, in general, and better in some specific cases. © 2010 Institution of Engineers, Bangladesh. All rights reserved.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Identification and Adaptive Position and Speed Control of Permanent Magnet DC Motor with Dead Zone Characteristics Based on Support Vector Machines

In this paper a new type of neural networks known as Least Squares Support Vector Machines which gained a huge fame during the recent years for identification of nonlinear systems has been used to identify DC motor with nonlinear dead zone characteristics. The identified system after linearization in each time span, in an online manner provide the model data for Model Predictive Controller of p...

متن کامل

Knowledge discovery and data mining in pavement inverse analysis

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 th...

متن کامل

Evaluation of the Efficiency of Linear and Nonlinear Models in Predicting Monthly Rainfall (Case Study: Hamedan Province)

     In this research, we used the support vector machine (SVM), support vector machine combine with wavelet transform (W-SVM), ARMAX and ARIMA models to predict the monthly values of precipitation. The study considers monthly time series data for precipitation stations located in Hamedan province during a 25-year period (1998-2016). The 25-year simulation period was divided into 17 years for t...

متن کامل

Application of Support Vector Machine Regression for Predicting Critical Responses of Flexible Pavements

This paper aims to assess the application of Support Vector Machine (SVM) regression in order to analysis flexible pavements. To this end, 10000 Four-layer flexible pavement sections consisted of asphalt concrete layer, granular base layer, granular subbase layer, and subgrade soil were analyzed under the effect of standard axle loading using multi-layered elastic theory and pavement critical r...

متن کامل

A Comparative Study of Extreme Learning Machines and Support Vector Machines in Prediction of Sediment Transport in Open Channels

The limiting velocity in open channels to prevent long-term sedimentation is predicted in this paper using a powerful soft computing technique known as Extreme Learning Machines (ELM). The ELM is a single Layer Feed-forward Neural Network (SLFNN) with a high level of training speed. The dimensionless parameter of limiting velocity which is known as the densimetric Froude number (Fr) is predicte...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011