Research on Solving the Excavation Pose of Shield Machine based on Neural Network-Newton Hybrid Algorithm

Qiang Zhang; Dongchen Qin; Qiang Zhu; Jiangyi Chen

doi:10.16578/j.issn.1004.2539.2021.07.004

您当前的位置：

首页 >

文章列表页 >

Research on Solving the Excavation Pose of Shield Machine based on Neural Network-Newton Hybrid Algorithm

Theory·Reserach | 更新时间：2022-11-10

- Research on Solving the Excavation Pose of Shield Machine based on Neural Network-Newton Hybrid Algorithm
- Journal of Mechanical Transmission Vol. 45, Issue 7, Pages: 24-29(2021)
- 作者机构：
  
  1.郑州大学机械与动力工程学院，河南郑州 450001
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2021.07.004
  CLC：
扫描看全文
张强,秦东晨,朱强等.基于神经网络-牛顿混合算法的盾构机掘进位姿求解研究[J].机械传动,2021,45(07):24-29.

Zhang Qiang,Qin Dongchen,Zhu Qiang,et al.Research on Solving the Excavation Pose of Shield Machine based on Neural Network-Newton Hybrid Algorithm[J].Journal of Mechanical Transmission,2021,45(07):24-29.
张强,秦东晨,朱强等.基于神经网络-牛顿混合算法的盾构机掘进位姿求解研究[J].机械传动,2021,45(07):24-29. DOI： 10.16578/j.issn.1004.2539.2021.07.004.

Zhang Qiang,Qin Dongchen,Zhu Qiang,et al.Research on Solving the Excavation Pose of Shield Machine based on Neural Network-Newton Hybrid Algorithm[J].Journal of Mechanical Transmission,2021,45(07):24-29. DOI： 10.16578/j.issn.1004.2539.2021.07.004.

摘要

为了解决盾构机推进系统运动学建模及正解求解困难等问题，采用简化等效模型法，构建了盾构机推进系统简化模型，将n-SPS的盾构并联推进系统简化为4-SPS的等效并联推进机构，并构建其运动学模型。根据建立的等效机构运动学模型，采用神经网络-牛顿混合算法求解盾构掘进位姿；利用神经网络的解域搜索功能，对初值进行预测并把预测结果代入牛顿迭代法进行计算求解，分析比较了单一神经网络预测值与BP神经网络-牛顿迭代混合算法计算结果的优劣性。研究发现，盾构机推进系统等效模型的建立可以大大简化运动学建模复杂度，而且利用混合算法求解运动学正解的求解精度更高，可以提高盾构机掘进位姿控制精度，从而提高掘进隧洞质量。

Abstract

In order to solve the problems such as the kinematics modeling of the shield machine propulsion system and the difficulty of forward solution， the simplified equivalent model method is adopted to construct a simplified model of the shield machine propulsion system， and the parallel shield propulsion system of n-SPS is simplified to 4-SPS equivalent parallel propulsion mechanism and construct its kinematics model. According to the established equivalent mechanism kinematics model， a neural network-Newton hybrid algorithm is used to solve the shield tunneling pose， and the solution domain search function of the neural network is used to predict the initial value and substitute the prediction result into the Newton iteration method for calculation and solution. The pros and cons of the single neural network predicted value and the calculated results of the BP neural network-Newton iterative hybrid algorithm are analyzed and compared. The study found that the establishment of the equivalent model of the shield machine propulsion system can greatly simplify the complexity of kinematics modeling， and the use of hybrid algorithms to solve the kinematics positive solution has higher accuracy， which can improve the control accuracy of the shield machine excavation attitude， thereby improving the tunneling tunnel quality.

关键词

盾构机运动学正解牛顿迭代法BP神经网络等效模型

Keywords

Shield machinePositive kinematics solutionNewton iteration methodBP neural networkEquivalent model

references

王林涛.盾构掘进姿态控制关键技术研究［D］.杭州：浙江大学，2014：63-65.

WANG Lintao.Research on key technologies for attitude control of shield tunneling machine［D］.Hangzhou：Zhejiang University，2014：63-65.

郑冰冰.先导式双护盾TBM推进系统开发与性能仿真分析［D］.西安：西安理工大学，2018：4-7.

ZHENG Bingbing. Development and performance simulation analysis of pilot dual shield TBM propulsion system［D］.Xi'an：Xi'an University of Technology，2018：4-7.

刘志斌.盾构推进电液系统动力学特性及轨迹实时精确控制研究［D］.杭州：浙江大学，2015：1-5.

LIU Zhibin.Research on dynamic characteristics and trajectory tracking control of electro-hydraulic thrust svstem on shield tunneling machine［D］.Hangzhou：Zhejiang University，2015：1-5.

胡国良，龚国芳，杨华勇.基于压力流量复合控制的盾构推进液压系统［J］.机械工程学报，2006，42（6）：124-127.

HU Guoliang，GONG Guofang，YANG Huayong. Thrust hydraulic system of shield tunnel boring machine with pressure and flow compound control［J］.Chinese Journal of Mechanical Engineering，2006，42（6）：124-127.

庄欠伟，龚国芳，杨华勇，等.盾构液压推进系统结构设计［J］.工程机械，2005，36（3）：47-50.

ZHUANG Qianwei，GONG Guofang，YANG Huayong，et al.Structural design of hydraulic propelling system of shield［J］.Construction Machinery and Equipment，2005，36（3）：47-50.

邓颖聪，郭为忠，高峰.盾构推进系统分区性能分析的等效机构建模［J］.机械工程学报，2010，46（13）：122-127.

DENG Yingcong，GUO Weizhong，GAO Feng.Equivalent mechanism-based modeling for grouping performance analysis of the thrustsystem of shield machines［J］.Chinese Journal of Mechanical Engineering，2010，46（13）：122-127.

郭文韬.盾构推进系统的机构-环境一体化建模与推进分区研究［D］.上海：上海交通大学，2017：3-10.

GUO Wentao.Mechanism-environment integrated modeling of thrust system and grouping method of shield machine［D］.Shanghai：Shanghai Jiaotong University，2017：3-10.

ZHOU H，CAO Y，ZHANG Q J.The research on direct kinematic problem of a special class of the Stewart-Gough manipulators［C］//Proceedings of 2008 IEEE International Conference on Mechatronics and Automation，August 5-8，2008，Takamatsu，Japan.New York：IEEE，2008：971-976.

陈长忆，车林仙.应用粒子群算法的3-RPS并联机器人机构位置正解［J］.现代制造工程，2006（5）：77-79.

CHEN Changyi，CHE Linxian. Forward position analysis of 3-RPS in-parallel manipulators based on particle swarm optimiza-tion［J］.Modern Manufacturing Engineering，2006（5）：77-79.

荆学东，张英驰，王梓腾，等.神经网络-牛顿改进算法求解stewart平台正解［J］.机械设计与制造，2019（12）：251-254.

JING Xuedong，ZHANG Yingchi，WANG Ziteng，et al.Solution to steward platform forward kinematics based on neural network and newton iterative hybrid algorithm［J］.Machinery Design & Manufacture，2019（12）：251-254.

李晶.六自由度Stewart平台运动学遗传神经网络正解［J］.舰船科学技术，2017，39（4）：112-114.

LI Jing.Genetic neural network positive solution of Stewart platform kinematics with six degree of freedom［J］.Ship Science and Technology，2017，39（4）：112-114.

肖帆，李光，游雨龙.空间3R机械手逆向运动学的多模块神经网络求解［J］.中国机械工程，2019，30（10）：1233-1237.

XIAO Fan，LI Guang，YOU Yulong. Multiple module neural network solving for inverse kinematicsof space 3R manipulators［J］.China Mechanical Engineering，2019，30（10）：1233-1237.

刘玉梅，曹晓宁，王秀刚，等.基于齐次变换矩阵数值解的6自由度并联机构位姿正解解算［J］.哈尔滨工程大学学报，2013，34（7）：894-898.

LIU Yumei，CAO Xiaoning，WANG Xiugang，et al.Forward kinematics of the 6-DOF parallel mechanism based on homogeneous transformation matrix numerical solution［J］.Journal of Harbin Engineering University，2013，34（7）：894-898.

李阁强，牛彦杰，陈馈，等.基于BP-PID控制器的盾构液压推进控制系统研究［J］.隧道建设，2017，37（7）：885-880.

LI Geqiang，NIU Yanjie，CHEN Kui，et al.Research on hydraulic thrusting control system of shield machine based on BP-PID controller［J］.Tunnel Construction，2017，37（7）：885-880.

张宗之，秦俊奇，陈海龙，等.基于BP神经网络的Stewart平台位姿正解算法研究［J］.机械传动，2015，39（6）：54-57.

ZHANG Zongzhi，QIN Junqi，CHEN Hailong，et al.Research of the pose forward solution algorithm of stewart platform based on BP neural network［J］.Mechanical Transmission，2015，39（6）：54-57.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design and Motion Analysis of an Automatic Retractable Manipulator for a Vehicle-mounted Wheelchair

A Self-adaptive CS Algorithm and Its Application in Fault Diagnosis of Wind Turbine Gearboxes

Fault Diagnosis Method of Planetary Gearboxes Based on LMD Permutation Entropy and BP Neural Network

Transmission Error Prediction of RV Reducer based on SSA-BP

Application of GA-ACO Optimized BP Neural Network in Fault Diagnosis of Planetary Gearbox

Related Author

No data

Related Institution

College of Mechanical and Vehicle Engineering, Hunan University

Tianjin Key Laboratory of Modern Electromechanical Equipment Technology

School of Mechanical Engineering, Tiangong University

Engineering College, Honghe University, Mengzi

College of Mechanical and Control Engineering, Guilin University of Technology

⁰