基于IDE-FLANN方法的六维力传感器动态建模研究

Dynamic Modeling of Six Axis Force Sensor Based on IDE-FLANN Method

针对六维力传感器动态建模问题,提出了一种改进差分进化算法结合函数连接型神经网络(IDE-FLANN)的动态建模方法,该方法在继承了函数连接型神经网络(FLANN)特殊结构的基础上,进一步发展了差分进化算法(DE)的寻优建模能力,具有结构巧妙、建模能力强的特点。实验结果表明:该方法可以有效克服FLANN方法易于陷入局部最优值的缺陷,与常用建模方法相比,该方法具有建模速度快、精度高、鲁棒性强的优点。

Aiming at the dynamic modeling problem of six axis force sensor,an improved differential evolution algorithm combined with functional link artificial neural network(IDE-FLANN)is proposed,on the basis of inheriting the special structure of functional link artificial neural network(FLANN),this method further develops the modeling ability of differential evolution algorithm(DE),which has the characteristics of smart structure and strong modeling ability. The experimental results show that the method can overcome the defect that FLANN is easy to fall into the local optimum,and it has the advantages of fast modeling speed,high precision and strong robustness compared with common modeling methods.