Artificial Neural Network estimation of wheel rolling resistance in clay loam soil

H. Taghavifar, A. Mardani, H. Karim-Maslak, H. Kalbkhani

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Despite of complex and nonlinear relationships imparting soil–wheel interactions, however, logical, non-randomized, and manifold relations tackle to express and model the interactions which are valid for variety of conditions and are likely to be established whereas mathematical equations are restricted to present. A 3-10-1 feed-forward Artificial Neural Network (ANN) with back propagation (BP) learning algorithm was utilized to estimate the rolling resistance of wheel as affected by velocity, tire inflation pressure, and normal load acting on wheel inside the soil bin facility creating controlled condition for test run. The model represented mean squared error MSE of 0.0257 and predicted relative error values with less than 10% and high coefficient of determination (R2) equal to 0.9322 utilizing experimental output data obtained from single-wheel tester of soil bin facility. These rewarding outcomes signify the fitting exploit of ANN for prediction of rolling resistance as a practical model with high accuracy in clay loam soil. Derived data revealed rolling resistance is less affected by applicable velocities of tractors in farmlands nevertheless is much influenced by inflation pressure and vertical load. An approximate constant relationship existed between velocity and rolling resistance implying that rolling resistance is not function of velocity chiefly in lower ones. Increase of inflation pressure results in decrease of rolling resistance while increase of vertical load brings about increase of rolling resistance which was measured to be function of vertical load by polynomial with order of two model validated by conventional models such as Wismer and Luth model.

Graphical abstract
Original languageEnglish
Pages (from-to)3544-3551
Number of pages8
JournalApplied Soft Computing Journal
Volume13
Issue number8
Early online date24 Apr 2013
DOIs
Publication statusPublished - Aug 2013
Externally publishedYes

Fingerprint

Rolling resistance
Wheels
Clay
Neural networks
Soils
Bins
Backpropagation
Tires
Learning algorithms
Polynomials

Keywords

  • Artificial Neural Networks
  • Rolling resistance
  • Soil bin
  • Velocity
  • Tire inflation pressure
  • Vertical load

Cite this

Artificial Neural Network estimation of wheel rolling resistance in clay loam soil. / Taghavifar, H.; Mardani, A.; Karim-Maslak, H.; Kalbkhani, H.

In: Applied Soft Computing Journal, Vol. 13, No. 8, 08.2013, p. 3544-3551.

Research output: Contribution to journalArticle

Taghavifar, H. ; Mardani, A. ; Karim-Maslak, H. ; Kalbkhani, H. / Artificial Neural Network estimation of wheel rolling resistance in clay loam soil. In: Applied Soft Computing Journal. 2013 ; Vol. 13, No. 8. pp. 3544-3551.
@article{5f8aca38c8ca4823bad231552e041222,
title = "Artificial Neural Network estimation of wheel rolling resistance in clay loam soil",
abstract = "Despite of complex and nonlinear relationships imparting soil–wheel interactions, however, logical, non-randomized, and manifold relations tackle to express and model the interactions which are valid for variety of conditions and are likely to be established whereas mathematical equations are restricted to present. A 3-10-1 feed-forward Artificial Neural Network (ANN) with back propagation (BP) learning algorithm was utilized to estimate the rolling resistance of wheel as affected by velocity, tire inflation pressure, and normal load acting on wheel inside the soil bin facility creating controlled condition for test run. The model represented mean squared error MSE of 0.0257 and predicted relative error values with less than 10{\%} and high coefficient of determination (R2) equal to 0.9322 utilizing experimental output data obtained from single-wheel tester of soil bin facility. These rewarding outcomes signify the fitting exploit of ANN for prediction of rolling resistance as a practical model with high accuracy in clay loam soil. Derived data revealed rolling resistance is less affected by applicable velocities of tractors in farmlands nevertheless is much influenced by inflation pressure and vertical load. An approximate constant relationship existed between velocity and rolling resistance implying that rolling resistance is not function of velocity chiefly in lower ones. Increase of inflation pressure results in decrease of rolling resistance while increase of vertical load brings about increase of rolling resistance which was measured to be function of vertical load by polynomial with order of two model validated by conventional models such as Wismer and Luth model.Graphical abstract",
keywords = "Artificial Neural Networks, Rolling resistance, Soil bin, Velocity, Tire inflation pressure, Vertical load",
author = "H. Taghavifar and A. Mardani and H. Karim-Maslak and H. Kalbkhani",
year = "2013",
month = "8",
doi = "10.1016/j.asoc.2013.03.017",
language = "English",
volume = "13",
pages = "3544--3551",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier",
number = "8",

}

TY - JOUR

T1 - Artificial Neural Network estimation of wheel rolling resistance in clay loam soil

AU - Taghavifar, H.

AU - Mardani, A.

AU - Karim-Maslak, H.

AU - Kalbkhani, H.

PY - 2013/8

Y1 - 2013/8

N2 - Despite of complex and nonlinear relationships imparting soil–wheel interactions, however, logical, non-randomized, and manifold relations tackle to express and model the interactions which are valid for variety of conditions and are likely to be established whereas mathematical equations are restricted to present. A 3-10-1 feed-forward Artificial Neural Network (ANN) with back propagation (BP) learning algorithm was utilized to estimate the rolling resistance of wheel as affected by velocity, tire inflation pressure, and normal load acting on wheel inside the soil bin facility creating controlled condition for test run. The model represented mean squared error MSE of 0.0257 and predicted relative error values with less than 10% and high coefficient of determination (R2) equal to 0.9322 utilizing experimental output data obtained from single-wheel tester of soil bin facility. These rewarding outcomes signify the fitting exploit of ANN for prediction of rolling resistance as a practical model with high accuracy in clay loam soil. Derived data revealed rolling resistance is less affected by applicable velocities of tractors in farmlands nevertheless is much influenced by inflation pressure and vertical load. An approximate constant relationship existed between velocity and rolling resistance implying that rolling resistance is not function of velocity chiefly in lower ones. Increase of inflation pressure results in decrease of rolling resistance while increase of vertical load brings about increase of rolling resistance which was measured to be function of vertical load by polynomial with order of two model validated by conventional models such as Wismer and Luth model.Graphical abstract

AB - Despite of complex and nonlinear relationships imparting soil–wheel interactions, however, logical, non-randomized, and manifold relations tackle to express and model the interactions which are valid for variety of conditions and are likely to be established whereas mathematical equations are restricted to present. A 3-10-1 feed-forward Artificial Neural Network (ANN) with back propagation (BP) learning algorithm was utilized to estimate the rolling resistance of wheel as affected by velocity, tire inflation pressure, and normal load acting on wheel inside the soil bin facility creating controlled condition for test run. The model represented mean squared error MSE of 0.0257 and predicted relative error values with less than 10% and high coefficient of determination (R2) equal to 0.9322 utilizing experimental output data obtained from single-wheel tester of soil bin facility. These rewarding outcomes signify the fitting exploit of ANN for prediction of rolling resistance as a practical model with high accuracy in clay loam soil. Derived data revealed rolling resistance is less affected by applicable velocities of tractors in farmlands nevertheless is much influenced by inflation pressure and vertical load. An approximate constant relationship existed between velocity and rolling resistance implying that rolling resistance is not function of velocity chiefly in lower ones. Increase of inflation pressure results in decrease of rolling resistance while increase of vertical load brings about increase of rolling resistance which was measured to be function of vertical load by polynomial with order of two model validated by conventional models such as Wismer and Luth model.Graphical abstract

KW - Artificial Neural Networks

KW - Rolling resistance

KW - Soil bin

KW - Velocity

KW - Tire inflation pressure

KW - Vertical load

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-84878360006&partnerID=MN8TOARS

U2 - 10.1016/j.asoc.2013.03.017

DO - 10.1016/j.asoc.2013.03.017

M3 - Article

VL - 13

SP - 3544

EP - 3551

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

IS - 8

ER -