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

Study of Threshing Function of Combine harvester with Artificial Neural Network

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

Citation:  Paper number  033012,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.14048) @2003
Authors:   Munenori Miyamoto, Haruhiko Murase
Keywords:   combine harvester, quality engineering, Taguchi method, artificial neural network, back propagation method, robustness

Taguchi Method, one of methods of robust engineering, has been a leading tool in the quality because S/N ratio as in this method represents factorial effect of control variables to outputs considering noise factors. According to the standard procedure of Taguchi, it is needed to have experiments depending on Lattice matrix such as L18 matrix. On the other hand, artificial neural network (ANN) has been utilized to describe a lot of systems because it is capable of describing nonlinear system. In this paper, threshing function of combine harvester was modeled by ANN. Training of ANN was done with the experimental results not depending on Lattice matrix. After training, ANN model was used as an additional tool to Taguchi Method in design of threshing function of combine harvester in order to calculate the factorial effect of control variables. It was proved that proposed method combining Taguchi Method and ANN is effective.

(Download PDF)    (Export to EndNotes)