基于支持向量分类的姿态仪升沉误差修正方法

全永贵; 肖体兵; 刘建群; 阳曼

doi:10.12052/gdutxb.240164

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于支持向量分类的姿态仪升沉误差修正方法

机械工程 | 更新时间：2026-05-27

- 基于支持向量分类的姿态仪升沉误差修正方法
- A Method for Correcting Heave Measurement Errors of Attitude Sensors Based on Support Vector Classification
- 广东工业大学学报 2025年42卷第3期页码：80-85
- 作者机构：
  
  1. 广东工业大学机电工程学院,广东,广州,510006
  2. 广东省海洋能源装备先进制造技术重点实验室,广东,广州,510006
- 作者简介：
  
  全永贵(1999–) ，男，硕士研究生，主要研究方向为机电液一体化控制，E-mail: 794904429@qq.com
  肖体兵(1975–) ，男，副教授，博士，主要研究方向为机电液一体化控制，E-mail: xiaotb75@gdut.edu.cn
- 基金信息：
  
  广东省基础与应用基础研究基金资助项目(2022A1515240015)
- DOI：10.12052/gdutxb.240164
  中图分类号： TH137
- 纸质出版：2025
- 稿件说明：
移动端阅览
全永贵, 肖体兵, 刘建群, 等. 基于支持向量分类的姿态仪升沉误差修正方法[J]. 广东工业大学学报, 2025, 42(3): 80–85.

Quan Yonggui, Xiao Tibing, Liu Jianqun, et al. A Method for Correcting Heave Measurement Errors of Attitude Sensors Based on Support Vector Classification[J]. 2025, 42(3): 80-85.
全永贵, 肖体兵, 刘建群, 等. 基于支持向量分类的姿态仪升沉误差修正方法[J]. 广东工业大学学报, 2025, 42(3): 80–85. DOI： 10.12052/gdutxb.240164

Quan Yonggui, Xiao Tibing, Liu Jianqun, et al. A Method for Correcting Heave Measurement Errors of Attitude Sensors Based on Support Vector Classification[J]. 2025, 42(3): 80-85. DOI： 10.12052/gdutxb.240164.

摘要

在浮式作业的升沉补偿系统中，检测单元姿态仪的精度直接影响补偿精度。目前主流姿态仪的升沉检测精度为5cm或5%，导致升沉补偿系统难以实现95%的补偿率。为提高补偿精度，本文提出一种基于支持向量分类(Support Vector Classification，SVC)的误差修正方法。姿态仪安装在六自由度平台上，利用动态捕捉系统测得的平台升沉位移作为参考真值，以此获得姿态仪的测量误差。通过误差与姿态仪输出信号之间的显著性分析，筛选出加速度、速度和位移3个参数作为SVC模型的输入。在MATLAB中建立SVC模型后，运用采集的数据完成模型训练并进行参数优化，参数优化采用贝叶斯优化和

-折交叉验证技术。然后将训练好的SVC模型导入数据采集软件，并编写代码实现分类功能。最终，通过SVC模型识别姿态仪3个输出参数对应的误差范围，并为每类误差修正一个特定值。实验结果表明，修正时间平均仅需1.4 ms，修正后的升沉位移均方根误差从

0.4567

cm降至

0.2622

cm或幅值的2.622%，绝对平均误差从

0.3668

cm降至

0.1989

cm，表明该方法能有效减小升沉测量误差。该方法也适用于修正姿态仪其他自由度输出的误差。

Abstract

The precision of attitude sensors in heave compensation systems for floating operations directly affects the compensation accuracy. Mainstream attitude sensors typically achieve a heave measurement accuracy of 5 cm or 5%

which limits the system's ability to r

each a 95% compensation rate. To address this issue

a method based on Support Vector Classification (SVC) was developed to correct measurement errors. The attitude sensor was mounted on a six-degree-of-freedom platform

and the platform's heave displacement

measured by a dynamic capture system

was used as the reference ground truth to determine the sensor's measurement errors. Through significance analysis of the relationship between the errors and the sensor's output signals

three parameters—acceleration

velocity and displacement—were selected as inputs for the SVC model. An SVC model was constructed in MATLAB

and data collected from the system were used for model training and parameter optimization

employing Bayesian optimization and

-fold cross-validation techniques. The trained SVC model was then integrated into data acquisition software

with custom code developed to implement classification functions.The results demonstrate that the SVC model effectively identified the error ranges corresponding to the three output parameters of the attitude sensor

enabling specific correction values for each error category. The correction process required an average time of only 1.4 ms. After correction

the root mean square error of the heave displacement decreased from

0.4567

cm to

0.2622

cm (or 2.622% of the amplitude)

while the absolute mean error was reduced from

0.3668

cm to

0.1989

cm. These findings indicate that the proposed method significantly reduces heave measurement errors. Furthermore

the method is applicable for correcting errors in other degrees of freedom outputs of the attitude sensor.

关键词

Keywords

references

XIONG Y F, CHEN Z L. Domestic research status and development emphases of drill string heave compensation system[J]. Ship Science and Technology, 2018, 40(12): 78-83.

ZHANG Q, ZHANG Z Z, LIU D K, et al . Ship active heave compensation strategy based on incremental model switching and backstepping control method[J ] . Ship Science and Technology, 2022, 44(18): 111-115.

WU W Y, LIU X S, GUO Z F, et al . Real time-delay control of active heave compensation system for marine crane[J ] . Chinese Hydraulics Pneumatics, 2021, 45(4): 167-174.

ZHANG Z W, ZHENG X S, JIA S J. Research on heave compensation system of trawler based on fuzzy PID[J]. Fishery Modrnization, 2022, 46(1): 106-112.

邸瑛琳. 基于惯性导航的升沉测量系统研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.

ZHANG Y, XU J N, BIAN H W. Analysis for capability of INS error-correction based on GPS attitude determination system[J]. Information Command Control System Simulation Technology, 2005, 27(5): 96-100.

DUAN Y, YANG Z, FU Y Z. Improved SINS/ADS based on error correction method[J]. Aerospace Control, 2023, 41(3): 3-10.

ZHANG M, CHEN A S, CHEN S, et al . An improved SINS_ODO_ZUPT integrated navigation algorithm[J ] . Aerospace Control, 2021, 39(1): 15-19.

WANG X, ZUO Q Y, CHEN L, et al . A SINS/single land-based station navigation correction scheme based on extrapolation information[J ] . Navigation Positioning Timing, 2018, 5(6): 25-35.

MIAO L J, GONG F, SHAO H J, et al . Horizontal attitude error correction method for single-axis rotational inertial navigation system[J ] . Journal of Chinese Inertial Technology, 2019, 27(1): 8-14.

熊必凤. 低成本MEMS陀螺仪随机漂移误差的建模及修正[D]. 重庆: 西南大学, 2017.

LI N, HE H Y, JING M, et al . IMU dynamic error suppression based on improved EKF[J ] . Journal of Nanjing University of Aeronautics Astronautics, 2023, 55(4): 718-724.

VAPNIK V N. Statistical learning theory[M]. New York: A Wiley-Interscience Publication, 1998.

ZHANG X G. Introduction to statistical learning theory and support vector machines[J]. Acta Automatica Sinica, 2000, 26(1): 32-42.

LI Y R, ZHANG Y L, WANG J C. Survey on Bayesian optimization methods for hyper-parameter tuning[J]. Computer Science, 2022, 49(6): 86-92.

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

灰色预测模型在高速公路车流预测中的应用

SCA-YOLO: 基于可变形卷积与上下文感知注意力的实时目标检测

基于AAGV-YOLOX模型的输电线路异物检测研究

基于PSI技术的福州市地面形变监测与影响因素分析

融合沟道倾斜角的3D NAND存储单元建模及编程策略优化