Artificial Neural Networks approach for prediction and modeling the coefficient of motion resistance

Hamid Taghavifar


Artificial neural networks are appearing as useful alternatives to traditional statistical modeling techniques in many scientific disciplines. In this paper, we strived to utilize a supervised feed-forward artificial neural network (ANN) trained by back propagation algorithms to predict coefficient of motion resistance (CMR) from readily available data obtained from experiments conducted in soil bin environment using a single wheel-tester. The inputs were speed, tire inflation pressure, and wheel load. A total of 45 samples were used for training, validating and testing the neural networks. Evaluating a three layered architecture (i.e. one hidden layer) with a four layered one (i.e. two hidden layers), the optimal topology to yield better performance on the criteria of lower mean squared error (MSE) and coefficient of determination (R2) was a four-layer topology. Then among 2 hidden layers, each of layers was increased from 0 to 50 to discover the best number of neurons by the best performance. It was divulged that a 3-47-41-1 provided the best performance with MSE of 2×10-6 and R2 of 0.9982 and also that a proper trained ANN could model and predict output variable wherein mathematical and statistical methods may fail to have the equal efficiency owing to unidentified behavior of soil due to its unknown nature. 

Full Text:



Wulfsohn D. (1987). Tractive characteristics of radial ply and bias ply tires in a California soil. M.S. thesis, Dept. of Agr. Eng., University of California, Davis.

Taghavifar H, Mardani A. Contact Area Determination of Agricultural Tractor Wheel with Soil. Cercetări Agronomice în Moldova. 2012, 150(2): 15-20.

Kurjenluomar J, Alakukku L, Ahokas, J. Rolling resistance and rut formation by implement tires on tilled clay soil. J of Terramechanics. 2009, 46: 267-275.

Elwaleed A K, Yahya A, Zohadie M, Ahmad D, Kheiralla A F.. Effect of inflation pressure on motion resistance ratio of a high-lug agricultural tyre. J of Terramechanics, 2006, 43(2): 69-84.

Shoop S A, Richmond P W, Lacombe J. Overview of cold regions mobility modeling at CRREL. J of Terramechanics. 2006, 43: 1-26.

Way T R, Kishimoto T. Interface pressures of a tractor drive tyre on structured and loose soils. Biosyst Eng. 2004, 87(3): 375-386.

Coutermarsh B. Velocity effect of vehicle rolling resistance in sand. J of Terramechanics. 2007, 44(4): 275-291.

Haykin, S S (1999). Neural networks: A comprehensive Foundation. Prentice-Hall, Upper Saddle River, NJ, USA.

Mardani A, Shahidi K, Rahmani A, Mashoofi B, Karimmaslak H. Studies on a long soil bin for soil-tool interaction. Cercetări Agronomice în Moldova. 2010, 142(2): 5-10.

Jaiswal S, Benson E R, Bernard J C, Van Wicklen G L. Neural network modelling and sensitivity analysis of a mechanical poultry catching system. Biosyst Eng. 2005, 92(1), 59-68.

Roul A K, Raheman H, Pansare M.S, Machavaram R. Predicting the draught requirement of tillage implements in sandy clay loam soil using an artificial neural network, Biosyst Eng. 2009, 104(4): 476-485.

Zhang Z X, Kushwaha R L. Application of neural networks to simulate soil tool interaction and soil behaviour. Canadian Agricultural Engineering. 1999, 41(2), 119-125.


  • There are currently no refbacks.