The objective of this study is to develop an efficient and practical real-time fault detection and prognostic system framework which is providing consistent useful information from sensed operating condition information. This system framework uses ideas combining expert knowledge that supplied by expert or experienced worker, resultant expert system database, real-time sensor information and fuzzy inference as the way to improve the performance of prognostic ability of proposed RFDPS system. The RFDPS model consists of four parts; embedded devide hardware part related to sensor, fuzzy inference/experts system part for describing uncertain status by fuzzying sensor signal, software part and database part for prognosis of quality condition monitoring on injection molding machines.