本文提出了用于SCARA 機器人運動控制的自組織模糊聚類神經網絡控制器。該控制器基于模糊聚類方法在學習模糊規則之前先優化訓練數據，去除冗余數據并解決數據沖突問題，不但減少了神經網絡的計算負擔，而且生成的規則更加適合機器人運動控制。控制器主要特點是能夠動態地自組織結構，學習速度快，魯棒性強。仿真結果表明控制效果很好。
關鍵詞：自組織模糊控制; 聚類分析; 模糊系統; 神經網絡
Abstract：This paper presents a self-organizing fuzzy clustering neural network (SOFCNN)
controller suitable for motion control of SCARA robotic manipulators. The SOFCNN is based on the fuzzy clustering method optimizing training data before learning fuzzy rules, in order to
remove redundant data and resolve conflicts in data. The method reduced computation of neural network and made the control rules more reasonable for the robotic manipulators. The feature of the SOFCNN controller has dynamic self-organizing structure, fast learning speed and flexibility in learning. The simulation results show that is very fine.
Key Word: Self-Organizing Fuzzy Control; Clustering Analysis; Fuzzy System; Neural
Networks