ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

Tillage Optimization Using a Neural Network and Numerical Analysis

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2015 ASABE Annual International Meeting  152184338.(doi:10.13031/aim.20152184338)
Authors:   Elizabeth Frink, Daniel Flippo
Keywords:   tillage systems, neural networks, optimization models.

Abstract. An overall trend towards conservation tillage is emerging, stemming from interest in methods to be more efficient, to increase yield, and to protect the value of the crop land. This is a daunting task due to the complex relationship between the parameters. A system is being developed to optimize a tillage implement based on the initial field conditions and the desired final conditions, eliminating the need to weigh the advantages and disadvantages of off-the-shelf tools. An exhaustive set of tests in various experimental conditions will be performed on a small-scale test system. An artificial neural network, followed by a genetic algorithm, will be used to optimize an implement for specified conditions. Additionally, the data will be analyzed using a numerical algorithm. The two approaches will be compared and contrasted to determine the most suitable technique. Future work includes a full-scale test system and implement optimization.

(Download PDF)    (Export to EndNotes)