|
|
论文:2024,Vol:42,Issue(2):189-196 |
|
|
引用本文： |
|
|
杜晓旭, 李瀚宇, 刘鑫. 基于BP神经网络的非线性流域UUV动态回收过程预测[J]. 西北工业大学学报 |
|
|
DU Xiaoxu, LI Hanyu, LIU Xin. Predicting underwater unmanned vehicle dynamic recovery process in nonlinear watershed based on BP neural network[J]. Journal of Northwestern Polytechnical University |
|
|
|
|
|
|
|
| 基于BP神经网络的非线性流域UUV动态回收过程预测 |
|
| 杜晓旭, 李瀚宇, 刘鑫 |
|
| 西北工业大学 航海学院, 陕西 西安 710002 |
| 摘要: |
| 针对水下无人自主航行器(UUV)回收过程中流域存在非线性干扰问题,提出了一种基于BP神经网络优化UUV回收路径的闭环控制方法。采用计算流体力学(CFD)方法模拟UUV相对于潜艇以不同路径进行回收的水动力系数,将数值模拟结果作为训练BP神经网络的初始数据,利用拉丁超立方法对非线性流域的位置随机采样,采用神经网络输出UUV在采样处的水动力系数,实现非线性流域内UUV动态回收过程的水动力系数预测。结果表明:通过均方根检验神经网络预测水动力系数误差均在10％范围内。将神经网络预测结果与UUV纵向操纵性方程结合,对比回收速度和操舵间隔与理论回收轨迹的误差,优化UUV动态回收路径的闭环控制方案。 |
| 关键词:
神经网络
非线性流域
水动力系数
UUV动态回收
|
|
| Predicting underwater unmanned vehicle dynamic recovery process in nonlinear watershed based on BP neural network |
|
| DU Xiaoxu, LI Hanyu, LIU Xin |
|
| School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China |
| Abstract: |
| Because of a nonlinear watershed's interference during the recovery of an unmanned underwater vehicle (UUV), a closed-loop control method for optimizing the recovery path of the UUV based on the BP neural network is proposed. The paper uses the computational fluid dynamics(CFD) method to simulate the hydrodynamic coefficients for recovering the UUV relative to a submarine in different paths. The numerical simulation results are used as the initial data for training the BP neural network. Using the Latin super-law, the location of the nonlinear watershed is randomly sampled. Hydrodynamic coefficients of the UUV in the nonlinear watershed at sampling points are predicted based on the BP neural network. The results show that the error predicted by the neural network through root mean squares is within 10％. Through combining the prediction results of the neural network with the UUV longitudinal maneuverability equation, the error of the recovery speed and steering interval is compared with the theoretical recovery path. The closed-loop control method of UUV dynamic recovery in the nonlinear watershed is optimized. |
| Key words:
neural network
nonlinear watershed
hydrodynamic coefficient
underwater unmanned vehicle dynamic recovery
|
|
| 收稿日期: 2023-03-24
修回日期:
|
| DOI: 10.1051/jnwpu/20244220189 |
| 基金项目: 国家自然科学基金(U2341217)资助 |
| 通讯作者: 杜晓旭(1981—) e-mail:nwpudu@163.com
Email：nwpudu@163.com |
| 作者简介: 杜晓旭(1981—),教授
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 杜晓旭 在本刊中的所有文章 |
| 李瀚宇 在本刊中的所有文章 |
| 刘鑫 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 黄波, 常金达, 丁浩, 等. UUV与潜艇协同作战模式及关键技术[J]. 舰船科学技术, 2020, 42(9): 138-142 HUANG Bo, CHANG Jinda, DING Hao, et al. Research on modes and key technologies of submarine-UUV collaborative combat[J]. Ship Science and Technology, 2020, 42(9): 138-142 (in Chinese)
[2] 张鑫明, 韩明磊, 余益锐, 等. 潜艇与UUV协同作战发展现状及关键技术[J]. 水下无人系统学报,2021,29(5):497-508 ZHANG Xinming, HAN Minglei, YU Yirui, et al. Development and key technologies of submarine-UUV cooperative operation[J]. Journal of Unmanned Undersea Systems, 2021, 29(5): 497-508 (in Chinese)
[3] 廉成斌, 杨亭鹏, 李磊, 等. UUV水下回收路径规划方法研究[J]. 舰船科学技术, 2021, 43(S1): 42-47 LIAN Chengbin, YANG Tingpeng, LI Lei, et al. Research on UUV underwater recycling path planning method[J]. Ship Science and Technology, 2021, 43(S1): 42-47 (in Chinese)
[4] 王思泽. UUV水下回收动态对接方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2020 WANG Size. Research on the dynamic docking method of UUV underwater recovery[D]. Harbin: Harbin Engineering University, 2020 (in Chinese)
[5] 杨智栋. UUV水下回收非线性流体动力干扰及引导过程操纵性研究[D]. 西安: 西北工业大学, 2015 YANG Zhidong, Reseach on hydrodynaic interaction and guidance manouevtabiliy of UUV underwater recovery[D]. Xi'an: Northwestern Polytechnical University, 2015 (in Chinese)
[6] JI L, WANG X, YANG X, et al. Back-propagation network improved by conjugate gradient based on genetic algorithm in QSAR study on endocrine disrupting chemicals[J]. Chinese Science Bulletin, 2008(1): 33-39
[7] RUMELHART D, HINTION G, WILLIAMS R. Learning represtation by back-propagating errors[J]. Nature, 1985(6088): 533-536
[8] 叶年辉, 龙腾, 史人赫, 等. 基于神经网络的跨介质飞行器水动力系数快速预示方法[J]. 无人系统技术, 2022, 5(3): 12-19 YE Nianhui, LONG Teng, SHI Renhe, et al. Efficient prediction method for hydrodynamic coefficient of trans-media flight vehicle based on neural network[J]. Unmanned Systems Technology, 2022, 5(3): 12-19 (in Chinese)
[9] KAZEMI H, DOUSTDAR M, NAJAFI A, et al. Hydrodynamic performance prediction of stepped planing craft using CFD and ANNs[J]. Journal of Marine Science and Application, 2021, 20(1): 67-84
[10] 郭可建, 林晓波, 郝程鹏, 等. 基于神经网络状态估计器的高速AUV强化学习控制[J]. 水下无人系统学报, 2022, 30(2): 147-156 GUO Kejian, LIN Xiaobo, HAO Chengpeng, et al. Reinforcement-learning control for the high-speed AUV based on the neural-network state estimator[J]. Journal of Unmanned Undersea Systems, 2022, 30(2): 147-156 (in Chinese)
[11] 潘光, 杜晓旭, 宋保维, 等. 鱼雷力学[M]. 西安: 陕西师范大学出版总社有限公司, 2013: 149-151, 220-227 PAN Guang, DU Xiaoxu, SONG Baowei, et al. Torpdo mechanics[M], Xi'an: Shaanxi Normal University Press Co., Ltd, 2013: 149-151, 220-227 (in Chinese)
[12] 章梓雄, 董曾南. 粘性流体力学[M]. 北京:清华大学出版社, 2011: 40-42 ZHANG Zixiong, DONG Zengnan. Viscous fluid mechnics[M] Beijing: Tsinghua University Press, 2011: 40-42 (in Chinese) |
|
|
|
|
|
|
|
