基于粒子群优化神经网络的水下链式机器人直航阻力预报

doi:10.3901/JME.2019.21.029

机械工程学报 ›› 2019, Vol. 55 ›› Issue (21): 29-39.doi: 10.3901/JME.2019.21.029

扫码分享

基于粒子群优化神经网络的水下链式机器人直航阻力预报

康帅^1,2,3, 俞建成^1,2, 张进^1,2, 金乾隆^1,2,3, 胡峰^1,2

1. 中国科学院沈阳自动化研究所机器人学国家重点实验室沈阳 110016;
2. 中国科学院机器人与智能制造创新研究院沈阳 110016;
3. 中国科学院大学北京 100049

收稿日期:2019-01-02 修回日期:2019-04-01 出版日期:2019-11-05 发布日期:2020-01-08
通讯作者: 张进(通信作者),男,1987年出生,博士,助理研究员。主要研究方向为多体机器人建模与控制、移动机器人路径规划、最优化调度。E-mail:zhangjin1@sia.cn
作者简介:康帅,男,1993年出生,博士研究生。主要研究方向为水下链式机器人技术。E-mail:kangshuai@sia.cn;俞建成,男,1976年出生,博士,研究员,博士研究生导师。主要研究方向为新概念海洋机器人技术、移动自主海洋环境观测理论与技术、海洋机器人智能控制方法与技术;金乾隆,男,1994年出生,博士研究生。主要研究方向为海洋机器人控制与规划;胡峰,男,1991年出生,硕士,研究实习员。主要研究方向为海洋机器人水动力学。
基金资助:
国家自然科学基金（U1709202）和机器人学国家重点实验室自主课题（2019-Z13）资助项目。

Direct Route Drag Prediction of Chain-structured Underwater Vehicle Based on Neural Network Optimized by Particle Swarm Optimization

KANG Shuai^1,2,3, YU Jiancheng^1,2, ZHANG Jin^1,2, JIN Qianlong^1,2,3, HU Feng^1,2

1. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016;
2. Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016;
3. China University of Chinese Academy of Sciences, Beijing 100049

Received:2019-01-02 Revised:2019-04-01 Online:2019-11-05 Published:2020-01-08

摘要/Abstract

摘要： 多单体水下机器人串联组成的水下链式机器人具有航行效率高、稳定性能好、搭载能力强等优势，对其直航阻力的精确预报可实现更有效的运动控制和更合理的动力编组。针对由于水下链式机器人各单体间耦合关系复杂及使用计算流体力学分析阻力耗时较长导致无法快速准确进行阻力预报问题，开展了水下链式机器人直航阻力预报研究。利用计算流体力学分析获得大量输入量（单体数量、航速和单体间间距）与输出量（直航阻力）样本数据，使用BP神经网络建立输入量与输出量模型关系，并通过粒子群算法优化神经网络的初始权值和偏差以改善BP神经网络易陷入局部极值点和过拟合等问题。由大量测试样本的预报结果可知：基于粒子群优化的BP神经网络算法比传统BP神经网络算法预报结果更准确，在给定不同速度和间距测试中均方误差分别降低了2.04×10^-5和7.40×10^-6；在5单体水下链式机器人以0.25 m/s²的加速度做匀加速运动过程中，基于粒子群优化的BP神经网络模型预报结果的平均相对误差为0.42%，精度较高。试验结果说明所提方法是可行且有效的。

关键词: 水下链式机器人, 神经网络, 粒子群算法, 阻力预报

Abstract: The chain-structured underwater vehicle is composed of several autonomous underwater vehicles in series. It has advantages in terms of navigation efficiency, stability, and carrying capacity. The motion can be better controlled and the power can be better organized if its direct route drag can be predicted accurately. Aiming at the problem that the drag prediction of chain-structured underwater vehicle cannot be carried out quickly and accurately because of the complex coupling relationship among the units and the long time-consuming of computational fluid dynamics (CFD) analysis, the research on the direct route drag prediction carried out. A large number of input (number of units, velocity and spacing between units) and output (direct route drag) sample data are obtained by using CFD. BP neural network is used to establish the relationship between input and output. Particle swarm optimization is used to optimize the initial weights and biases of the neural network to improve the problem that BP neural network is easy to fall into local extreme points and over-fitting. The prediction results of a large number of test samples show that the BP neural network algorithm based on particle swarm optimization is more accurate than the traditional BP neural network algorithm, and the mean square error is reduced by 2.04×10^-5 and 7.4×10^-6 respectively in the tests of given different velocities and spacing. The average relative error of BP neural network model optimized by particle swarm optimization is 0.42% during the uniform acceleration of the 5-unit chain-structured underwater vehicle with an acceleration of 0.25 m/s². The accuracy of prediction results is high. The experimental results show that the proposed method is feasible and effective.

Key words: chain-structured underwater vehicle, neural network, particle swarm optimization, drag prediction

中图分类号:

TP242

康帅, 俞建成, 张进, 金乾隆, 胡峰. 基于粒子群优化神经网络的水下链式机器人直航阻力预报[J]. 机械工程学报, 2019, 55(21): 29-39.

KANG Shuai, YU Jiancheng, ZHANG Jin, JIN Qianlong, HU Feng. Direct Route Drag Prediction of Chain-structured Underwater Vehicle Based on Neural Network Optimized by Particle Swarm Optimization[J]. Journal of Mechanical Engineering, 2019, 55(21): 29-39.

参考文献

[1] 李一平,李硕,张艾群. 自主/遥控水下机器人研究现状[J]. 工程研究,2016,8(2):217-222. LI Yiping,LI Shuo,ZHANG Aiqun. Research status of autonomous-remotely operated vehicle[J]. Journal of Engineering Studies,2016,8(2):217-222.
[2] EDWARDS D B,BEAN T A,ODELL D L,et al. A leader-follower algorithm for multiple AUV formations[C]//Autonomous Underwater Vehicles,2004 IEEE/OES. IEEE,2004:40-46.
[3] 陶广红,房立金,徐鑫霖,等. 多节链式移动机器人单元模块研究与设计[J]. 机器人,2018,40(6):887-894. TAO Guohong,FANG Lijin,XU Xinlin,et al. Research and design of the unit module of the multi-link mobile robot[J]. Robot,2018,40(6):887-894.
[4] BLOCKEN B,TOPARLAR Y,ANDRIANNE T. Aerodynamic benefit for a cyclist by a following motorcycle[J]. Journal of Wind Engineering and Industrial Aerodynamics,2016,155:1-10.
[5] TIAN W,MAO Z,ZHAO F,et al. Layout optimization of two autonomous underwater vehicles for drag reduction with a combined CFD and neural network method[J]. Complexity,2017,1:1-15.
[6] BALLABIO D,VASIGHI M. A MATLAB toolbox for self organizing maps and supervised neural network learning strategies[J]. Chemometrics and Intelligent Laboratory Systems,2012,18:24.
[7] 倪春波,孔一斐,杨月全,等. 粒子群优化及其在多机器人系统中的应用展望[J]. 中南大学学报,2013(s2):126-132. NI Chunbo,KONG Yifei,YANG Yuequan,et al. Particle swarm optimization and its application in multi-robot systems[J]. Journal of Central South University,2013(s2):126-132.
[8] 谢延敏,孙新强,田银,等. 基于改进粒子群算法和小波神经网络的高强钢扭曲回弹工艺参数优化[J]. 机械工程学报,2016,52(19):162-167. XIE Yanmin,SUN Xinqiang,TIAN Yin,at al. Optimization of parameters in twist springback process for high-strength sheets based on improved particle swarm optimization algorithm and wavelet neural network[J]. Journal of Mechanical Engineering,2016,52(19):162-167.
[9] 孟令帅,林扬,郑荣,等. 模块化自主水下机器人的机械设计与实现[J]. 机器人,2016,38(4):395-401. MENG Lingshuai,LIN Yang,ZHENG Rong,et al. Mechanical design and implementation of a modular autonomous underwater vehicle[J]. Robot,2016,38(4):395-401.
[10] MENG L S,LIN Y,XU H L,et al. Effects of front shapes of mini revolving AUV on sailing resistance characteristics[C]//IEEE International Conference on Information and Automation. Piscataway,USA:IEEE,2015:1795-1799.
[11] 王亚兴. AUV的水动力优化及近水面运动性能研究[D]. 哈尔滨:哈尔滨工程大学,2015. WANG Yaxing. Study on AUV hydrodynamic optimization and motion performance near free surface[D]. Harbin:Harbin Engineering University,2015.
[12] 庞永杰,王亚兴,杨卓懿,等. Myring型回转体直航阻力计算及艇型优化[J]. 哈尔滨工程大学学报,2014,35(9):1093-1098. PANG Yongjie,WANG Yaxing,YANG Zhuoyi,et al. Direct route drag calculation and shape optimization of Myring shape axisymmetric revolution body[J]. Journal of Harbin Engineering University,2014,35(9):1093-1098.
[13] MYRING D. A theoretical study of body drag in subcritical axisymmetric flow[J]. Aeronautical Quartely,1976,27(3):186-194.
[14] HOU Y H,LIANG X,MU X Y. AUV hull lines optimization with uncertainty parameters based on six sigma reliability design[J]. International Journal of Naval Architecture and Ocean Engineering,2018,10(4):499-507.
[15] GAO T,WANG Y,PANG Y,et al. Hull shape optimization for autonomous underwater vehicles using CFD[J]. Engineering Applications of Computational Fluid Mechanics,2016,10(1):599-607.
[16] WU N,WU C,GE T,et al. Pitch channel control of a REMUS AUV with input saturation and coupling disturbances[J]. Applied Sciences,2018,8(2):10.3390/app8020253.
[17] MADHAN R,DESA E S,PRABHUDESAI S,et al. Mechanical design and development aspects of a small AUV-Maya[C]//2006,7th IFAC Conference in MCMC, 20-22 Sept.,2006,Lisbon. IFAC,2006:1-6.
[18] 李明,刘楠. STAR-CCM+11.0与流场计算[M]. 北京:机械工业出版社,2017. LI Ming,LIU Nan. STAR-CCM+11.0 and flow field calculation[M]. Beijing:China Machnie Press,2017.
[19] 张亮,张继业,李田,等. 超高速列车流线型头型多目标优化设计[J]. 机械工程学报,2017,53(2):106-114. ZHANG Liang,ZHANG Yeji,LI Tian,et al. Multi-objective optimization design of the streamlined head shape of super high-speed trains[J]. Journal of Mechanical Engineering,2017,53(2):106-114.
[20] 蒋新松,封锡盛,王棣堂. 水下机器人[M]. 沈阳:辽宁科学技术出版社,2000. JIANG Xinsong,FENG Xisheng,WANG Ditang. Unmanned underwater vehicles[M]. Shenyang:Liaoning Science and Technology Press,2000.
[21] 丛爽. 智能控制系统及其应用[M]. 合肥:中国科学技术大学出版社,2013. CONG Shuang. Intelligent control system and its application[M]. Hefei:University of Science and Technology of China Press,2013.
[22] WANG Y,ZHANG F,CUI T,et al. Fault diagnosis for manifold absolute pressure sensor(MAP) of diesel engine based on Elman neural network observer[J]. Chinese Journal of Mechanical Engineering,2016,29(2):386-395.
[23] 周品. MATLAB神经网络设计与应用[M]. 北京:清华大学出版社,2013. ZHOU Pin. Design and application of MATLAB neural network[M]. Beijing:Tsinghua University Press,2013.
[24] PEI J,WANG W,YUAN S,et al. Optimization on the impeller of a low-specific-speed centrifugal pump for hydraulic performance improvement[J]. Chinese Journal of Mechanical Engineering,2016,29(5):992-1002.
[25] 李镇,樊炳辉,王鑫,等. 基于BP神经网络的仿生眼定位追踪算法[J]. 机器人,2017,39(1):63-69. LI Zhen,FANG Binghui,WANG Xin,et al. Locating and tracking algorithm of biomimetic eye based on backpropagation neural network[J]. Robot,2017,39(1):63-69.
[26] 牛江川,韩利涛,李素娟,等. 基于PSO-BP神经网络的盾构刀具配置研究[J]. 机械工程学报,2018,54(10):167-172. NIU Jiangchuan,HAN Litao,LI Sujuan,et al. Research on shield cutting tool configuration based on PSO-BP neural network[J]. Journal of Mechanical Engineering,2018,54(10):167-172.

基于粒子群优化神经网络的水下链式机器人直航阻力预报

Direct Route Drag Prediction of Chain-structured Underwater Vehicle Based on Neural Network Optimized by Particle Swarm Optimization

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郑杰, 权伟, 刘洋, 卢学民, 刘晓红, 岳雅楠, 周腾, 蔡振兵. Cr/Zr涂层环向压缩表面裂纹识别研究[J]. 机械工程学报, 2024, 60(8): 1-10.
[2]	刘占广, 张云, 刘晴雨. 基于差分融合长短期记忆神经网络数控机床热误差建模[J]. 机械工程学报, 2024, 60(7): 249-257.
[3]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[4]	王俊玖, 刘金玉, 侯秀娟, 齐振国, 李志敏, 刘涛. 列车车体柔性装配精度预测的力学-数据混合建模方法[J]. 机械工程学报, 2024, 60(6): 177-186.
[5]	李春凯, 王嘉昕, 石玗, 代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究[J]. 机械工程学报, 2024, 60(6): 236-244.
[6]	周宁, 姚建勇, 邓文翔. 基于神经网络的比例伺服阀阀芯液动力补偿鲁棒智能控制[J]. 机械工程学报, 2024, 60(4): 126-133.
[7]	王丹丹, 黄伟迪, 张军辉, 赵守军, 于斌, 刘施镐, 吕飞, 苏琦, 徐兵. 基于边缘计算的轴向柱塞泵磨损状态辨识方法研究[J]. 机械工程学报, 2024, 60(4): 189-199.
[8]	张昊, 魏超, 胡纪滨, 陈泳丹. 基于转向模式切换的三轴独立转向车辆路径跟踪控制研究[J]. 机械工程学报, 2024, 60(2): 243-251.
[9]	段书用, 杨建华, 韩旭, 刘桂荣. 高维数据自适应降维方法[J]. 机械工程学报, 2024, 60(17): 283-296.
[10]	刘建琴, 胡桂菘, 乔金丽, 郭晓. 基于双路神经网络的TBM实时性能预测研究[J]. 机械工程学报, 2024, 60(16): 43-53.
[11]	胡伟飞, 廖家乐, 郭云飞, 鄢继铨, 李光, 岳海峰, 谭建荣. 基于物理信息神经网络的时变可靠性分析方法[J]. 机械工程学报, 2024, 60(13): 141-153.
[12]	张德权, 李星奥, 张宁, 宁国松, 韩旭. 工业机器人全域误差场精细化建模方法及其误差补偿策略[J]. 机械工程学报, 2024, 60(13): 316-329.
[13]	王俊, 杨轶青, 刘金朝, 沈长青, 黄伟国, 朱忠奎. 小波核编码的脉冲卷积神经网络在可解释性智能诊断中的应用研究[J]. 机械工程学报, 2024, 60(12): 41-50.
[14]	袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.
[15]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.