基于GD-FNN的药物注射系统辨识

针对手动控制调节药物注射量缺乏正确性和低效的特点,将广义动态模糊神经网络（GD-FNN）应于药物注射系统辨识。学习算法在动态模糊神经网络算法基础上进行改进,以模糊完备性作为高斯函数宽度的确定准则,避免初始化选择的随机性。同时,该算法能对模糊规则而且能对输入变量的重要性做出评价,从而使每条规则的输入变量的宽度可以根据它对系统性能贡献的大小实施在线自适应调整。通过对药物注射系统的辨识和控制仿真实验表明改进后的广义动态模糊神经网络与动态模糊神经网络相比,可取得更好学习效率和辨识精度。

Identification of Drug Infusing System Based on generalized dynamic fuzzy neural network

Manual control adjusting drug infusion lacks of accuracy and inefficient. For this characteristic, a generalized dynamic fuzzy neural network was used in identification of drug infusing system. Learning algorithm was improved based on fuzzy neural network algorithm. The breadth of Gaussian function was determined in this algorithm based on fuzzy completeness, which avoided random initialization choice. At the same time, this algorithm can not only make the evaluation on the importance of the fuzzy rules, thus enables each regular input variable the width to be possible to act according to the system performance contribution size implementation online auto-adapted adjustment. Through the simulation of identification and control on the drug infusing systems show that the improved generalized dynamic fuzzy neural network can achieve better learning efficiency and estimation accuracy.