implementation and evaluation of a fuzzy logic controller for the automatic settings of a combine harvester

many factors affect yield loss in wheat harvesting with a grain combine harvester and there is no mathematical model to describe the behavior of this complex system. thus in this study, a fuzzy logic controller (flc) was designed, implemented and tested for the automatic settings of cylinder speed, concave clearance, fan speed and forward speed of a model 955 john deere combine. first, the mechanical systems of these units were converted into hydraulic systems to implement the flc. then, seven sensors were installed to measure combine parameters (four sensors) and yield losses (three sensors). the yield loss sensors were very accurate and reliable. a fuzzy logic algorithm was proposed to control these units, with two inputs (straw walker and sieve loss) and four outputs (cylinder speed, concave clearance, fan speed and forward speed). trapezoidal membership functions were selected as fuzzy linguistic input variables and fuzzy singletons were selected as output variables. six rules having logical and operators and mamdani implications were employed. the fuzzy algorithm was implemented using a cj1m model plc. laboratory and field experiments were carried out in the summer of 2006 to evaluate the performance of the proposed fuzzy inference system. statistical analysis (t-tests) of the present investigation indicated a significant difference (p<1%) between loss mean in the combine with flc installed and the combine without a controller.