An intelligent self-learning method for dimensional error pre-compensation in CNC grinding

Abstract

The problem of error compensation in manufacturing industry becomes important since the product quality is the manufactures' competition. This paper presents an intelligent self-learning method for dimensional error pre-compensation in CNC grinding. Measurements of the system output obtained from the previous runs are used to compute the correction for the current run without inprocess sensing and measurement, which is attractive for applications lacking in situ measurements. A modified NC program is fed to the machine tool to push the system output towards target. The simulation results and the real system input and output responses show the feasibility and effectiveness of this intelligent self-learning method.

Model-based adaptive process control for surface finish improvement in traverse grinding

“…Among these techniques, two big families are identified consisting in desktop systems to assist tool and parameter selection and self-optimizing systems integrated within the machine controller. As stated by Chen and Tian [3], however, only few optimization algorithms in literature include an explicit term related to chatter instability in the optimization process, while dimensional accuracy is often the paramount objective. In fact, Choi and Lee [4] have developed an active control system for thermal error compensation in cylindrical grinding of long slender rolls.…”