Abstract: The gate is one of the most important parts in injection mold, which has the direct influence on the quality of the injection products. The design of the gate schemes depends on prior experience and knowledge. Due to the vagueness and uncertainty in the scheme design of the gate, the classical rough set theory is not effective. A fuzzy rough set model is proposed, which is not based on equivalent relation but on fuzzy similarity relation. Then an inductive learning algorithm based on fuzzy rough set model (FRILA) is presented. Compared to the decision tree algorithms, the proposed algorithm can generate less fuzzy rules and the generated rules are more concise. Finally, an intelligent gate scheme design prototype system based on the gate scheme design knowledge base is developed, which can improve the efficiency of the gate design.

Key words: Injection mold, Knowledge acquirement, Fuzzy rough set, Gating design