|本期目录/Table of Contents|

[1]王振洋,徐春晖,郭 烁.基于AC-BiLSTM的自主水下机器人早期故障诊断研究[J].工业仪表与自动化装置,2023,(03):63-69.[doi:10.19950/j.cnki.cn61-1121/th.2023.03.013]
　WANG Zhenyang,XU Chunhui,GUO Shuo.Research on early fault diagnosis of autonomous underwater vehicle based on AC-BiLSTM[J].Industrial Instrumentation & Automation,2023,(03):63-69.[doi:10.19950/j.cnki.cn61-1121/th.2023.03.013]
点击复制

基于AC-BiLSTM的自主水下机器人早期故障诊断研究

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2023年03期
页码:
63-69
栏目:
出版日期:
2023-06-15

文章信息/Info

Title:
Research on early fault diagnosis of autonomous underwater vehicle based on AC-BiLSTM
文章编号:
1000-0682（2023）02-0063-07
作者:
王振洋1; 2; 3; 4; 徐春晖2; 3; 4; 郭 烁1
1.沈阳化工大学 信息工程学院，辽宁 沈阳 110142；
2.中国科学院沈阳自动化研究所机器人学国家重点实验室，辽宁 沈阳 110016；
3.中国科学院机器人与智能制造创新研究院，辽宁 沈阳 110169；
4.辽宁省水下机器人重点实验室，辽宁 沈阳 110169
Author(s):
WANG Zhenyang1; 2; 3; 4; XU Chunhui2; 3; 4;  GUO Shuo1
1.Department of Information Engineering，Shenyang University of Chemical Technology，Liaoning Shenyang 110142，China；
2.State Key Laboratory of Robotics, Shenyang Institute of Automation，Liaoning Shenyang 110016，China；
3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences，Liaoning Shenyang 110169，China；
4.Key Laboratory of Marine Robotics, Liaoning Province，Liaoning Shenyang 110169，China
关键词:
自主水下机器人; 早期故障诊断; 特征融合; 时间注意力机制
Keywords:
AUV; early fault diagnosis; feature fusion; temporal attention
分类号:
TP183
DOI:
10.19950/j.cnki.cn61-1121/th.2023.03.013
文献标志码:
A
摘要:
针对自主水下机器人（AUV）在航行中产生的早期微小故障及缓变风险，对大量时序数据进行挖掘分析，提出了一种基于混合模型和时间注意力机制的端到端AUV早期故障诊断方法（AC-BiLSTM）。该方法首先通过包含局部特征提取模块的混合模型结构对AUV故障类型与多维监测数据之间的非线性关系进行学习，然后嵌入时间注意力机制提取早期故障的关键时间特征。为了验证算法的有效性，以“潜龙二号”AUV实航数据进行试验，试验分析结果证明该方法在不均衡数据集下识别AUV早期微弱故障的可行性和优越性。
Abstract:
Aiming at the early minor faults and slow change risks of autonomous underwater vehicle (AUV) during navigation, a large amount of time series data is mined and analyzed, and an end-to-end AUV early fault diagnosis method based on hybrid model and time attention mechanism (AC-BiLSTM) is proposed. This method first studies the nonlinear relationship between AUV fault types and multi-dimensional monitoring data through the hybrid model structure including local feature extraction module, and then embeds the time attention mechanism to extract the key time features of early faults. In order to verify the effectiveness of the algorithm, the actual flight data of the QianLong-2 AUV are tested. The test analysis results show that the method is feasible and superior in identifying the early weak faults of the AUV under the unbalanced data set.

参考文献/References:

[1] 封锡盛,李一平,徐会希,等.深海自主水下机器人发展及其在资源调查中的应用[J].中国有色金属学报,2021,31(10):2746-2756.

[2] 黄琰,李岩,俞建成,等.AUV智能化现状与发展趋势[J].机器人,2020,42(02):215-231.
[3] BIAN X J,MOU C,YAN Z,et al. Reliability analysis of AUV based on fuzzy fault tree.[C]//Proceedings of the 2009 IEEE International Conference on Mechatronics and Automation August 9 - 12, Changchun, China.2009:438-442.?/div>
[4] ZHENG Y ,WANG G,CHEN Z, et al. A finite state machine based diagnostic expert system of large-scale autonomous unmanned submarine[C]//2018 IEEE 8th International Conference on Underwater System Technology: Theory and Applications (USYS).1-6.
[5] 褚振忠,朱大奇,张铭钧.基于终端滑模观测器的水下机器人推进器故障重构[J].上海交通大学学报,2015,49(06):837-841.
[6] SHUMSKY A ,ZHIRABOK A ,HAJIYEV C . Observer based fault diagnosis in thrusters of autonomous underwater vehicle[C]//Control & Fault-tolerant Systems. IEEE, 2010:11-16.
[7] NASCIMENTO S,VALDENEGRO-TORO M.Modeling and Soft-fault Diagnosis of Underwater Thrusters with Recurrent Neural Networks[C]//11th IFAC Conference on Control Applications in Marine Systems, Robotics, and Vehicles CAMS,2018,51(29), 80-85.
[8] 段杰,李辉,陈自立,等.基于RBF与OS-ELM神经网络的AUV传感器在线故障诊断[J].水下无人系统学报,2018,26(02):157-165+184.
[9] XIA S S,ZHOU X F,SHI H B,et al.A fault diagnosis method based on attention mechanism with application in Qianlong-2 autonomous underwater vehicle[J]. Ocean Engineering, 2021, 233(12):109049.
[10] 刘全,翟建伟,章宗长,等.深度强化学习综述[J].计算机学报,2018,41(01):1-27.[11] GRAVES A,SCHMIDHUBER J.Frame wise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005,18( 5-6):602-610.
[12] POVEY D,HADIAN H,GHAHREMANI P, et al. A Time-Restricted Self-Attention Layer for ASR[C]//International Conference on Acoustics, Speech and Signal Processing (ICASSP),IEEE ,2018:5874-5878.
[13] VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[C]//Advances in Neural Information Processing Systems,2017:6000-6010.
[14] MEDHAT W,HASSAN A,KORASHY H.Sentiment analysis algorithms and applications: A survey[J].A in Shams Engineering Journal,2014, 5(4):1093-1113.
[15] 刘建伟,王园方,罗雄麟.深度记忆网络研究进展[J].计算机学报,2021,44(08):1549-1589.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：2023-02-23
基金项目:
国家重点研发计划(No. 2018YFC0308205)?/div>

第一作者：
王振洋（1998—），男，河北邯郸人，硕士研究生，研究方向为AUV故障诊断，深度学习。

通信作者：
徐春晖（1982—），男，辽宁沈阳人，硕士，副研究员，从事水下机器人软件控制的研究。
更新日期/Last Update: 1900-01-01