基于白鲨优化极限学习机的三维力传感器非线性解耦  

Nonlinear decoupling of 3d force sensors based on WSO-ELM

作　　者：孙世政[1] 庞珂 于竞童 陈仁祥 SUN Shizheng;PANG Ke;YU Jingtong;CHEN Renxian(School of Mechatronics and Vehicle Engineering,Chongqing Jiaotong University,Chongqing 400074,China)

机构地区：[1]重庆交通大学机电与车辆工程学院,重庆400074

出　　处：《光学精密工程》2023年第18期2664-2674,共11页Optics and Precision Engineering

基　　金：国家自然科学基金青年科学基金资助项目(No.52105542);“成渝地区双城经济圈建设”科技创新项目资助(No.KJCX2020032);重庆市教委科学技术研究项目资助(No.KJZD-K202200705);重庆市研究生联合培养基地资助项目(No.JDLHPYJD2021007)。

摘　　要：针对三维力传感器维间耦合干扰问题,以基于光纤布拉格光栅(Fiber Bragg Grating,FBG)的一体式三维力传感器为研究对象,提出了一种基于白鲨优化算法的优化极限学习机(White Shark Optimizer-Extreme Learning Machine,WSO-ELM)的非线性解耦算法。首先,设计了基于FBG的一体式三维力传感器,阐明该传感器波长漂移量与三维力的映射关系;然后,搭建静态标定实验系统,分析三维力耦合特征,并建立WSO-ELM算法三维力传感器解耦模型,利用白鲨优化算法(White Shark Optimizer,WSO)稳定、高效特点优化模型,寻找ELM神经网络隐含层神经元数与解耦时间的最佳参数组合,开展基于WSO-ELM的三维力传感器非线性解耦研究;最后,该传感器解耦后最大平均I类误差达到0.51%,最大平均II类误差达到0.65%,实现了基于WSO-ELM的三维力非线性解耦。为验证解耦效果,将WSO-ELM算法与极限学习机神经网络模型、反向传播神经网络、最小二乘法解耦效果进行对比实验。实验结果表明:WSO-ELM算法具有较好的解耦效果,能有效构建三维力维间耦合关系,同时降低传感器耦合干扰,提高传感器的测量精度,具有良好的非线性解耦能力。A nonlinear decoupling algorithm based on the white shark optimization algorithm optimized ex⁃treme learning machine(WSO-ELM)is proposed to address the issue of inter dimensional coupling inter⁃ference in three-dimensional force sensors,with an integrated three-dimensional force sensor based on fiber Bragg grating(FBG)as the research object.Firstly,an integrated three-dimensional force sensor based on FBG was designed to reveal the mapping relationship between the wavelength drift of the sensor and the three-dimensional force;Then,a static calibration experimental system is established to analyze the three-dimensional force coupling characteristics,and a WSO-ELM algorithm three-dimensional force sen⁃sor decoupling model is established.The model is optimized using the stable and efficient characteristics of the white shark optimization algorithm(WSO)to find the optimal parameter combination of the number of neurons in the hidden layer of the ELM neural network and the decoupling time.Research on nonlinear de⁃coupling of three-dimensional force sensors based on WSO-ELM is carried out;Finally,after decoupling,the maximum average type I error of the sensor reaches 0.51%,and the maximum average type II error reaches 0.65%,achieving three-dimensional force nonlinear decoupling based on WSO-ELM.To verify the decoupling effect,a comparative experiment was conducted between the WSO-ELM algorithm and the extreme learning machine neural network model,backpropagation neural network,and least squares meth⁃od for decoupling effect.The experimental results show that the WSO-ELM algorithm has good decou⁃pling effect,can effectively construct the coupling relationship between three-dimensional force dimen⁃sions,reduce sensor coupling interference,improve sensor measurement accuracy,and has good nonlinear decoupling ability.

关 键 词：白鲨优化算法 非线性解耦 三维力传感器 光纤布拉格光栅 极限学习机算法 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置] TH823[自动化与计算机技术—控制科学与工程]