KNOWLEDGE REPRESENTATION IN A GRAIN DRIER FUZZY-LOGIC CONTROLLER

This paper describes a method of using governing rules associated with fuzzy membership matrices to represent drier control knowledge in a fuzzy logic controller. The objectives of the controller were to obtain (1) outlet maize moisture content between 15.0 and 16.0% and (2) outlet maize breakage susceptibility as low as possible with a certain required drying rate. The governing rules contained information for control decision-making including predicted moisture and breakage levels of dried maize which were derived from some measurable drying process variables, current dryer operating conditions, and process disturbances. Fuzzy membership matrices consisted of state matrices and action matrices. State matrices contained likelihoods of the process achieving control objectives at the current process state. Action matrices contained degrees of confidence of control actions in achieving control objectives. All matrices were kept in five knowledge sub-bases along with their governing rules to represent drier control knowledge for different process states. A computer simulation showed that of 918 test cases, 793 control actions designated by the fuzzy logic controller matched preferred ones, that is, actions which matched human operators' preferred actions, indicating that this method of knowledge representation in a fuzzy logic controller was effective.