Sensor selected fusion considering process condition in grinding system

Grinding process is frequently used to produce a smooth surface in the manufacturing system. In this process, sensor fusion methods for inferring the surface roughness from on-line sensing values have received much attention, because it takes a long time to measure the surface roughness during process. We also have proposed a sensor selected fusion system using reliability based on possibility measure because there are sensors with ambiguity and conflicts between sensor values. However, this system cannot infer states from sensor values under various process conditions because the selection rule does not change according to the process condition. In this paper, we propose a sensor selected fusion system with knowledge database which stores the selection rules for each process condition generated by the genetic algorithm. This system can fuse sensor values according to process conditions and the reliability based on possibility measure.