INTELLIGENT CONTROL OF THE GEAR-SHAVING PROCESS

The objective of this paper is to describe how AI (artificial intellig ence) and fuzzy logic techniques can be combined to implement an on-li ne computer control of an axial gear-shaving process in order to impro ve the quality of workpiece gears. The basic principle of correcting t he geometric errors of workpiece gears is introduced. The final knowle dge base is obtained by the iterative procedure of trying the expert c ontroller, observing the results and then modifying the control rules accordingly. Inference is provided by a fuzzy logic engine. Experiment al results showed that accuracy of the shaved gears was greatly enhanc ed. The total cumulative pitch error and the individual pitch error we re reduced by approximately two times. In particular, the flank groove s, which commonly occur in the middle of tooth profiles, were removed.