Draft Prediction of a Vertical Narrow Tillage Tool by Artificial Neural Networks

Draft of different tillage tools is an important parameter for performance measurement, evaluation of tillage tools and also for determining the amount of required energy. Prediction of this parameter could be beneficial in many farm management practices, prediction of energy requirements and selecting appropriate tractor. In this study, field experiments were carried out at two soil types, namely, clay loam and loam clay, for predicting draft of a vertical narrow tillage tool, using artificial neural network and also, for comparison of developed model accuracy with that of regression models. Some parameters such as soil types, soil conditions, tools parameters and operational parameters were selected as inputs to artificial neural network. Within each type of soil, experiments were conducted in the form of factorial experiment based on randomized complete block design (RCDB) with three replications. Different levels of soil moisture content (factor A) 5-16 percent for dry soil and 17-38 percent for wet soil, tractor speed (factor B) at four levels of 1, 1.5, 1.8 and 3 km/hr, working depth (factor C) at four levels of 10, 20, 30 and 40cm and blade width (factor D) in four levels of 2.5, 3, 3.5 and 4cm were selected. Back propagation neural networks with three different training algorithms (gradient descending algorithm with momentum, descending scaled gradient and Levenberg-Marquardt) were adopted to predict the draft. Back propagation neural networks with Levenberg-Marquardt training algorithm presented better accuracy in simulation (95.05%) and correlation coefficient (R2 ) of 0.9935 as compared to others. The obtained data from neural network model were compared to ASAE and Ashrafizadeh (2006) models; the result showed that the predicted data by artificial neural network were very close to real data obtained from field experiments and the regression models did not have much proficiency for predicting draft at the studied area.