基于径向基函数神经网络的压电式六维力传感器解耦算法

发布时间：2018-03-02 19:48

  本文选题：六维力传感器　切入点：压电式传感器　出处：《光学精密工程》2017年05期 　论文类型：期刊论文

【摘要】：针对四点支撑结构的压电式六维力传感器线性度差,维间耦合严重的问题,提出了基于径向基函数(RBF)神经网络的解耦算法。分析了耦合产生的主要原因,建立了RBF神经网络模型。通过对六维力传感器进行标定实验获取解耦所需的实验数据,并对实验数据进行处理。然后采用RBF神经网络优化传感器输出系统的多维非线性解耦算法,解耦出传感器的输入输出映射关系,得到解耦后的传感器输出数据。对传感器解耦后的数据分析表明:采用RBF神经网络的解耦算法得到的最大Ⅰ类误差和Ⅱ类误差分别为1.29%、1.56%。结果显示:采用RBF神经网络的解耦算法,能够更加有效地减小传感器的Ⅰ类误差和Ⅱ类误差,满足了传感器两类误差指标均低于2%的要求。该算法有效地提高了传感器的测量精度,基本解决了传感器解耦困难的难题,
[Abstract]:Aiming at the problem of poor linearity and serious coupling between dimensions of piezoelectric six-axis force sensors with four-point support structure, a decoupling algorithm based on radial basis function (RBF) neural network is proposed, and the main causes of coupling are analyzed. The RBF neural network model is established, and the experimental data for decoupling are obtained by calibrating the six-axis force sensor. Then the multi-dimensional nonlinear decoupling algorithm of sensor output system is optimized by using RBF neural network to decouple the input and output mapping relationship of the sensor. The output data of the sensor after decoupling are obtained. The analysis of the data after decoupling shows that the maximum class I error and the class 鈪，

本文编号：1557951