采用长短期记忆神经网络的压电式六维力/力矩传感器解耦算法

亓振广; 王桂从; 褚宏博; 张帅; 李映君

doi:10.7652/xjtuxb202504015

您当前的位置：

首页 >

文章列表页 >

采用长短期记忆神经网络的压电式六维力/力矩传感器解耦算法

—————————————————————— | 更新时间：2026-01-06

- 采用长短期记忆神经网络的压电式六维力/力矩传感器解耦算法
- Decoupling Algorithm of Piezoelectric Six-Dimensional Force/Torque Sensor Using Long Short-Term Memory Neural Network
- 西安交通大学学报 2025年59卷第4期页码：158-170
- 作者机构：
  
  1.济南大学机械工程学院， 250022，济南
  2.山东省传感技术与高精度衡器重点实验室， 250022，济南
- 作者简介：
  
  亓振广（1999—），男，硕士生；
  李映君（通信作者），男，教授，硕士生导师。
- 基金信息：
  
  山东省自然科学基金资助项目(ZR2023ME109);济南市“新高校20条”科研带头人工作室资助项目(202228116)
- DOI：10.7652/xjtuxb202504015
  中图分类号： TP212.9;TN384
- 收稿：2024-09-08，
  
  网络首发：2024-11-20，
  
  纸质出版：2025-04-10
- 稿件说明：
移动端阅览
亓振广, 王桂从, 褚宏博, 等. 采用长短期记忆神经网络的压电式六维力/力矩传感器解耦算法[J]. 西安交通大学学报, 2025,59(4):158-170.

QI Zhenguang, WANG Guicong, CHU Hongbo, et al. Decoupling Algorithm of Piezoelectric Six-Dimensional Force/Torque Sensor Using Long Short-Term Memory Neural Network[J]. Journal of Xi’an Jiaotong University, 2025, 59(4): 158-170.
亓振广, 王桂从, 褚宏博, 等. 采用长短期记忆神经网络的压电式六维力/力矩传感器解耦算法[J]. 西安交通大学学报, 2025,59(4):158-170. DOI： 10.7652/xjtuxb202504015.

QI Zhenguang, WANG Guicong, CHU Hongbo, et al. Decoupling Algorithm of Piezoelectric Six-Dimensional Force/Torque Sensor Using Long Short-Term Memory Neural Network[J]. Journal of Xi’an Jiaotong University, 2025, 59(4): 158-170. DOI： 10.7652/xjtuxb202504015.

摘要

针对压电式六维力/力矩传感器存在的维间耦合导致传感器测力性能下降问题，提出了一种基于长短期记忆神经网络（LSTM）的压电式六维力/力矩传感器解耦算法。首先，通过六维力传感器静态标定实验，获取解耦算法所需的实验数据，并对其进行处理；然后，通过分析传感器维间耦合产生的原因及LSTM神经网络解耦原理，构建LSTM神经网络解耦模型；最后，采用基于LSTM神经网络的解耦算法，对传感器输出的多维非线性特性开展优化，解耦后得到传感器输入、输出之间的映射关系和对应的输出数据，并与径向基函数（RBF）及最小二乘（LS）解耦算法进行对比分析。研究结果表明：所使用四点支撑式压电六维力传感器的最大重复性误差为1.55%；采用基于LSTM的神经网络算法解耦后，传感器输出结果的最大非线性误差、交叉耦合误差分别为0.55%和0.28%，均小于RBF和LS算法。LSTM神经网络解耦算法能有效减少六维力/力矩传感器的维间耦合，提高传感器的测量精度，对航空航天领域的发展具有参考意义。

Abstract

To address the issue of decreased force measurement performance in piezoelectric six-dimensional force/torque sensors due to inter-dimensional coupling

a decoupling algorithm for piezoelectric six-dimensional force/torque sensors based on long short-term memory neural network (LSTM) is proposed. Firstly

experimental data needed for the decoupling algorithm is obtained through static calibration experiments of the six-dimensional force sensor and processed accordingly. Then

by analyzing the causes of inter-dimensional coupling in sensors and the decoupling principle of the LSTM neural network

an LSTM neural network decoupling model is constructed. Finally

the decoupling algorithm based on the LSTM neural network is used to optimize the multi-dimensional nonlinear characteristics of the sensor output

obtaining the mapping relationship between sensor inputs and outputs after decoupling

and corresponding output data. A comparative analysis is conducted with radial basis function (RBF) and least squares (LS) decoupling algorithms. The research results show that the maximum repeatability error of the four-point supported piezoelectric six-dimensional force sensor is 1.55%. After utilizing the LSTM-based neural network algorithm for decoupling

the maximum nonlinear error and cross-coupling error of the sensor output results are 0.55% and 0.28% respectively

both lower than those of the RBF and LS algorithms. The LSTM neural network decoupling algorithm effectively reduces inter-dimensional coupling in the six-dimensional force/torque sensor

improving measurement accuracy and holding important implications for the development of the aerospace industry.

关键词

Keywords

references

唐志共 , 袁先旭 , 钱炜祺 , 等 . 高速空气动力学三大手段数据融合研究进展 [J ] . 空气动力学学报 , 2023 , 41 ( 8 ): 44 - 58 .

TANG Zhigong , YUAN Xianxu , QIAN Weiqi , et al . Research progress on the fusion of data obtained by high-speed wind tunnels, CFD and model flight [J ] . Acta Aerodynamica Sinica , 2023 , 41 ( 8 ): 44 - 58 .

周学文 , 闫华东 , 吕水燕 , 等 . 高超声速火箭橇气动特性优化与风洞试验 [J ] . 西安交通大学学报 , 2024 , 58 ( 5 ): 156 - 166 .

ZHOU Xuewen , YAN Huadong , LÜ Shuiyan , et al . Optimization of hypersonic rocket Sled aerodynamic characteristics and wind tunnel tests [J ] . Journal of Xi'an Jiaotong University , 2024 , 58 ( 5 ): 156 - 166 .

焦林虎 , 任宗金 , 张军 , 等 . 六维压电风洞盒式天平研究 [J ] . 传感器与微系统 , 2024 , 43 ( 10 ): 31 - 34 .

JIAO Linhu , REN Zongjin , ZHANG Jun , et al . Research on six dimensional piezoelectric wind tunnel box balance [J ] . Transducer and Microsystem Technologies , 2024 , 43 ( 10 ): 31 - 34 .

李荟霖 , 康雨 , 赵保华 , 等 . 基于最小二乘的多维力/力矩传感器线性解耦算法研究 [J ] . 应用物理 , 2024 , 14 ( 6 ): 452 - 461 .

LI Huilin , KANG Yu , ZHAO Baohua , et al . Study of linear decomposition algorithms for multidimensional force/torque sensors based on least squares [J ] . Applied Physics , 2024 , 14 ( 6 ): 452 - 461 .

彭小武 , 马国鹭 , 赵涌 , 等 . 三维力传感器的设计和静态解耦算法研究 [J ] . 传感技术学报 , 2021 , 34 ( 11 ): 1518 - 1522 .

PENG Xiaowu , MA Guolu , ZHAO Yong , et al . Design of three-dimensional force sensor and research on the static decoupling algorithm [J ] . Chinese Journal of Sensors and Actuators , 2021 , 34 ( 11 ): 1518 - 1522 .

LI Yingjun , WANG Guicong , YANG Xue , et al . Research on static decoupling algorithm for piezoelectric six axis force/torque sensor based on LSSVR fusion algorithm [J ] . Mechanical Systems and Signal Processing , 2018 , 110 : 509 - 520 .

王志军 , 张小涛 , 李梦祥 . 基于多项式拟合的六维力传感器解耦算法研究 [J ] . 工程设计学报 , 2023 , 30 ( 5 ): 571 - 578 .

WANG Zhijun , ZHANG Xiaotao , LI Mengxiang . Research on decoupling algorithm of six-dimensional force sensor based on polynomial fitting [J ] . Chinese Journal of Engineering Design , 2023 , 30 ( 5 ): 571 - 578 .

石中盘 , 赵铁石 , 厉敏 , 等 . 大量程柔性铰六维力传感器静态解耦的研究 [J ] . 仪器仪表学报 , 2012 , 33 ( 5 ): 1062 - 1069 .

SHI Zhongpan , ZHAO Tieshi , LI Min , et al . Research on static decoupling of large range flexible joint six-axis force sensor [J ] . Chinese Journal of Scientific Instrument , 2012 , 33 ( 5 ): 1062 - 1069 .

查浩 , 费少华 , 傅云 , 等 . 基于EtherCAT总线的六维力传感器在线解耦技术 [J ] . 浙江大学学报(工学版) , 2023 , 57 ( 10 ): 2042 - 2050 .

ZHA Hao , FEI Shaohua , FU Yun , et al . Online decoupling technology of six-dimensional force sensor based on EtherCAT bus [J ] . Journal of Zhejiang University (Engineering Science) , 2023 , 57 ( 10 ): 2042 - 2050 .

徐志成 , 关佳希 , 周兴林 . 基于ReLU函数的胎路接触三向力传感器解耦方法 [J ] . 仪表技术与传感器 , 2023 ( 4 ): 77 - 82 .

XU Zhicheng , GUAN Jiaxi , ZHOU Xinglin . ReLU function-based decoupling method for tyre path contact three-way force sensors [J ] . Instrument Technique and Sensor , 2023 ( 4 ): 77 - 82 .

张家敏 , 许德章 . 基于蚁群BP神经网络算法的六维力传感器解耦研究 [J ] . 轻工机械 , 2016 , 34 ( 1 ): 1 - 4, 13 .

ZHANG Jiamin , XU Dezhang . Study on decoupling algorithms for six-axis force sensor based on ant algorithm and BP neural network [J ] . Light Industry Machinery , 2016 , 34 ( 1 ): 1 - 4, 13 .

张军 , 王康 , 钱敏 , 等 . 压电矢量力传感器力分量解耦与实验研究 [J ] . 仪表技术与传感器 , 2016 ( 1 ): 1 - 3 .

ZHANG Jun , WANG Kang , QIAN Min , et al . Component decoupling of piezoelectric vector force sensor and experiment research [J ] . Instrument Technique and Sensor , 2016 ( 1 ): 1 - 3 .

LI Yingjun , YANG Cong , WANG Guicong , et al . Research on the parallel load sharing principle of a novel self-decoupled piezoelectric six-dimensional force sensor [J ] . ISA Transactions , 2017 , 70 : 447 - 457 .

李映君 , 韩彬彬 , 王桂从 , 等 . 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 [J ] . 光学精密工程 , 2017 , 25 ( 5 ): 1266 - 1271 .

LI Yingjun , HAN Binbin , WANG Guicong , et al . Decoupling algorithms for piezoelectric six-dimensional force sensor based on RBF neural network [J ] . Optics and Precision Engineering , 2017 , 25 ( 5 ): 1266 - 1271 .

孙世政 , 庞珂 , 于竞童 , 等 . 基于白鲨优化极限学习机的三维力传感器非线性解耦 [J ] . 光学精密工程 , 2023 , 31 ( 18 ): 2664 - 2674 .

SUN Shizheng , PANG Ke , YU Jingtong , et al . Nonlinear decoupling of 3D force sensors based on WSO-ELM [J ] . Optics and Precision Engineering , 2023 , 31 ( 18 ): 2664 - 2674 .

陈伟 , 张晓 , 袁栋 , 等 . 农田耕整载荷六维力传感器结构优化与解耦研究 [J ] . 农业机械学报 , 2024 , 55 ( 2 ): 28 - 35, 89 .

CHEN Wei , ZHANG Xiao , YUAN Dong , et al . Structural optimization and decoupling of six dimensional force sensor for farmland tillage load [J ] . Transactions of the Chinese Society for Agricultural Machinery , 2024 , 55 ( 2 ): 28 - 35, 89 .

董翔 , 许子健 , 曹会彬 , 等 . 基于IFWA-ELM的六维力传感器解耦算法 [J ] . 传感技术学报 , 2023 , 36 ( 12 ): 1943 - 1951 .

DONG Xiang , XU Zijian , CAO Huibin , et al . Decoupling algorithm of Six-Axis force sensor based on IFWA-ELM [J ] . Chinese Journal of Sensors and Actuators , 2023 , 36 ( 12 ): 1943 - 1951 .

张军 , 蔡佳乐 , 王郁赫 , 等 . 基于HSA-SVR的压电式车削测力仪多维力解耦 [J ] . 仪表技术与传感器 , 2024 ( 6 ): 26 - 29 .

ZHANG Jun , CAI Jiale , WANG Yuhe , et al . Decoupling for multidimensional force of piezoelectric turning dynamometer based on HSA-SVR [J ] . Instrument Technique and Sensor , 2024 ( 6 ): 26 - 29 .

LI Yingjun , WANG Guicong , ZHANG Shuai , et al . Design and calibration of spoke piezoelectric six-dimensional force/torque sensor for space manipulator [J ] . Chinese Journal of Aeronautics , 2024 , 37 ( 1 ): 218 - 235 .

曹会彬 , 孙玉香 , 刘利民 , 等 . 多维力传感器耦合分析及解耦方法的研究 [J ] . 传感技术学报 , 2011 , 24 ( 8 ): 1136 - 1140 .

CAO Huibin , SUN Yuxiang , LIU Limin , et al . Coupling analysis of multi-axis force sensor and research of decoupling method [J ] . Chinese Journal of Sensors and Actuators , 2011 , 24 ( 8 ): 1136 - 1140 .

赵鹏 , 王桂从 , 李映君 , 等 . 组合式自解耦压电薄膜三维力传感器研制 [J ] . 西安交通大学学报 , 2023 , 57 ( 3 ): 139 - 149 .

ZHAO Peng , WANG Guicong , LI Yingjun , et al . Development of combined self-decoupling piezoelectric thin film three-dimensional force sensor [J ] . Journal of Xi'an Jiaotong University , 2023 , 57 ( 3 ): 139 - 149 .

马俊青 , 宋爱国 , 吴涓 . 三维力传感器静态解耦算法的研究与应用 [J ] . 计量学报 , 2011 , 32 ( 6 ): 517 - 521 .

MA Junqing , SONG Aiguo , WU Juan . Research and application of static decoupling for 3-axis wrist force sensor [J ] . Acta Metrologica Sinica , 2011 , 32 ( 6 ): 517 - 521 .

陈保家 , 陈学力 , 沈保明 , 等 . CNN-LSTM深度神经网络在滚动轴承故障诊断中的应用 [J ] . 西安交通大学学报 , 2021 , 55 ( 6 ): 28 - 36 .

CHEN Baojia , CHEN Xueli , SHEN Baoming , et al . An application of convolution neural network and long short-term memory in rolling bearing fault diagnosis [J ] . Journal of Xi'an Jiaotong University , 2021 , 55 ( 6 ): 28 - 36 .

ZHANG Dongxiao , CHEN Yuntian , MENG Jin . Synthetic well logs generation via recurrent neural networks [J ] . Petroleum Exploration and Development , 2018 , 45 ( 4 ): 629 - 639 .

吴全玉 , 刘美君 , 范家琪 , 等 . 遗传算法与修正的自适应矩估计优化循环神经网络的心音分类方法 [J ] . 南京理工大学学报 , 2024 , 48 ( 2 ): 202 - 208, 226 .

WU Quanyu , LIU Meijun , FAN Jiaqi , et al . Heart sound classification method combining GA with rectified Adam for RNN optimization [J ] . Journal of Nanjing University of Science and Technology , 2024 , 48 ( 2 ): 202 - 208, 226 .

刘颖 , 杨鹏飞 , 张立军 , 等 . 前馈神经网络和循环神经网络的鲁棒性验证综述 [J ] . 软件学报 , 2023 , 34 ( 7 ): 3134 - 3166 .

LIU Ying , YANG Pengfei , ZHANG Lijun , et al . Survey on robustness verification of feedforward neural networks and recurrent neural networks [J ] . Journal of Software , 2023 , 34 ( 7 ): 3134 - 3166 .

LIN Chenxiao , TAN Yidong , WANG Qingxuan . Machine learning-based prediction approach for ranging resolution enhancement of FMCW LiDAR system with LSTM networks [J ] . Optics & Laser Technology , 2024 , 179 : 111299 .

张译文 , 王志恒 , 邱睿贤 , 等 . 利用长短期记忆神经网络的改进POD-Galerkin降阶模型及其在流场预测中的应用 [J ] . 西安交通大学学报 , 2024 , 58 ( 2 ): 12 - 21 .

ZHANG Yiwen , WANG Zhiheng , QIU Ruixian , et al . Improved POD-Galerkin reduced order model with long short-term memory neural network and its application in flow field prediction [J ] . Journal of Xi'an Jiaotong University , 2024 , 58 ( 2 ): 12 - 21 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

离子液体改性燃料的电流体动力学效应研究

融合物理信息与深度算子网络的变压器绕组热-流场快速计算方法

隧道内燃料电池汽车氢气泄漏扩散特性及影响因素

EBSILON软件在热电联产系统优化中的应用综述

混合电解槽阵列协同的风光耦合制氢系统双层多目标优化