基于SE-CNN的服务机器人运动系统云端故障诊断方法

doi:10.13973/j.cnki.robot.200295

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (672 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
缪昭明, 袁宪锋, 张晖, 颜亮, 周风余, 郭仁和, 汪佳宇. 基于SE-CNN的服务机器人运动系统云端故障诊断方法[J]. 机器人, 2021, 43(3): 321-330.DOI: 10.13973/j.cnki.robot.200295. MIAO Zhaoming, YUAN Xianfeng, ZHANG Hui, YAN Liang, ZHOU Fengyu, GUO Renhe, WANG Jiayu. Cloud Fault Diagnosis Method of a Service Robot Motion System Based on SE-CNN. ROBOT, 2021, 43(3): 321-330. DOI: 10.13973/j.cnki.robot.200295.

摘要研究并设计了一种基于服务机器人云平台的故障诊断系统．传统算法只关注服务机器人某一时刻的状态数据，所提取的特征信息有限，因而难以较好地完成故障诊断任务．在这种背景下，提出了基于时间序列关联特征的故障诊断方法．首先，对采集的服务机器人数据进行归一化和后向差分预处理，消除数据量纲并获取数据变化特征；其次，利用滑动窗口来生成时间序列样本，保证每个样本包含足够的特征信息；然后，应用卷积神经网络（CNN）挖掘时间序列的关联特征，并在网络中引入通道注意力网络（squeeze-and-excitation network，SENet），构建了一种SE-CNN模型．该模型能够自适应调整特征通道的重要程度，聚焦于更有效的特征通道，从而提高了诊断精度．对比实验与实际场景下的综合测试证明了本文提出的故障自诊断方法的可行性和有效性．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	缪昭明
	袁宪锋
	张晖
	颜亮
	周风余
	郭仁和
	汪佳宇

关键词 ：服务机器人, 故障诊断, 云服务, 关联特征

Abstract：A fault diagnosis system based on a service robot cloud platform is studied and designed. Since the traditional algorithms only focus on the state data of the service robot at a particular time, the extracted feature information is limited. Therefore, it is difficult for the traditional algorithms to complete the fault diagnosis task well. In this context, a fault diagnosis method based on the correlation features of the time series is proposed. Firstly, the collected service robot data are pre-processed by normalization and backward difference to eliminate the data dimension and obtain the data change characteristics. Secondly, the sliding window is employed to generate time series samples to ensure that each sample contains sufficient feature information. Then, convolutional neural network (CNN) is applied to extracting correlation features of time series, and channel attention networks (squeeze-and-excitation network, SENet) are introduced to construct an SE-CNN model, which can adaptively adjust the importance of feature channels and focus on more effective feature channels, thereby improving diagnosis accuracy. Comparative experiments and comprehensive test in the actual scene prove the feasibility and effectiveness of the fault self-diagnosis method proposed.

Key words： service robot fault diagnosis cloud service correlation feature

收稿日期: 2020-08-07 【基金专刊】 录用日期: 2020-10-08

TP242.6

基金资助:国家重点研发计划（2017YFB1302400）；国家自然科学基金（61773242，61803227）；山东省农业重大应用技术创新项目（SD2019NJ014）；山东省自然科学基金（ZR2019MF064）．

通讯作者: 周风余，zhoufengyu@sdu.edu.cn E-mail: zhoufengyu@sdu.edu.cn

作者简介: 缪昭明（1997–），男，硕士生．研究领域：故障诊断与预测，云服务机器人
袁宪锋（1989–），男，博士，讲师．研究领域：服务机器人，故障诊断与预测．

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.200295 或 https://robot.sia.cn/CN/Y2021/V43/I3/321

[1] 王天然. 机器人技术的发展[J].机器人， 2017， 39(4)： 385-386. Wang T R. Development of the robotics[J]. Robot, 2017, 39(4): 385-386.
[2] 杨中欣. 轮式服务机器人控制系统可靠性设计与安全性研究[D].济南：山东大学， 2018. Yang Z X. Research on reliability design and security of wheeled service robot control system[D]. Jinan: Shandong University, 2018.
[3] An Z H, Li S M, Wang J R, et al. Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method[J]. Neurocomputing, 2019, 352: 42-53.
[4] Zhao Y, Li T T, Zhang X J, et al. Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future[J]. Renewable and Sustainable Energy Reviews, 2019, 109: 85-101.
[5] Guo L, Lei Y G, Xing S B, et al. Deep convolutional transfer learning network: A new method for intelligent fault diagnosis of machines with unlabeled data[J]. IEEE Transactions on Industrial Electronics, 2019, 66(9): 7316-7325.
[6] Li L L, Ding S X, Yang Y, et al. A fault detection approach for nonlinear systems based on data-driven realizations of fuzzy kernel representations[J]. IEEE Transactions on Fuzzy Systems, 2018, 26(4): 1800-1812.
[7] Yin S, Ding S X, Zhou D H. Diagnosis and prognosis for complicated industrial systems – Part II[J]. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3201-3204.
[8] Wang K, Chen J H, Song Z H. Performance analysis of dynamic PCA for closed-loop process monitoring and its improvement by output oversampling scheme[J]. IEEE Transactions on Control Systems Technology, 2019, 27(1): 378-385.
[9] Xia L L, Zhang S F, Shen R, et al. Data association-based fault diagnosis of IMUs: Optimized DBN design and wheeled robot evaluation[J]. IEEE Access, 2020, 8: 59618-59636.
[10] Zhu Y H, Fu Z Y, Fu Z, et al. Multi-features fusion for fault diagnosis of pedal robot using time-speed signals[J]. Sensors, 2019, 19(1). DOI: 10.3390/s19010163.
[11] Hoang N B, Kang H J. A model-based fault diagnosis scheme for wheeled mobile robots[J]. International Journal of Control, Automation and Systems, 2014, 12(3): 637-651.
[12] 王秀青，侯增广，曾慧，等. 基于多传感器信息融合的机器人故障诊断[J].上海交通大学学报， 2015， 49(6)： 793- 798. Wang X Q, Hou Z G, Zeng H, et al. Fault diagnosis of robots based on multi-sensor information fusion[J]. Journal of Shanghai Jiao Tong University, 2015, 49(6): 793-798.
[13] Khaldi B, Harrou F, Cherif F, et al. Monitoring a robot swarm using a data-driven fault detection approach[J]. Robotics and Autonomous Systems, 2017, 97: 193-203.
[14] Duan Z H, Cai Z X, Min H Q. Robust dead reckoning system for mobile robots based on particle filter and raw range scan[J]. Sensors, 2014, 14(9): 16532-16562.
[15] Yuan X F, Song M M, Zhou F Y, et al. Design of a software simulation platform for fault diagnosis of service robot[C]//IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems. Piscataway, USA: IEEE, 2017: 376-381.
[16] Baghernezhad F, Khorasani K. Computationally intelligent strategies for robust fault detection, isolation, and identification of mobile robots[J]. Neurocomputing, 2016, 171: 335-346.
[17] Khalastchi E, Kalech M. On fault detection and diagnosis in robotic systems[J]. ACM Computing Surveys, 2018, 51(1). DOI: 10.1145/3146389.
[18] Stavrou D, Eliades D G, Panayiotou C G, et al. Fault detection for service mobile robots using model-based method[J]. Autonomous Robots, 2016, 40(2): 383-394.
[19] Zhou B, Qian K, Ma X D, et al. Ellipsoidal bounding setmembership identification approach for robust fault diagnosis with application to mobile robots[J]. Journal of Systems Engineering and Electronics, 2017, 28(5): 986-995.
[20] 刘景泰，张森，孙月. 面向智能家居/智慧生活的服务机器人技术与系统[J].集成技术， 2016， 5(3)： 38-46. Liu J T, Zhang S, Sun Y. Technology and system of service robots for smart home and intelligent life[J]. Journal of Integration Technology, 2016, 5(3): 38-46.
[21] Kehoe B, Matsukawa A, Candido S, et al. Cloud-based robot grasping with the Google object recognition engine[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2013: 4263-4270.
[22] Tenorth M, Perzylo A C, Lafrenz R, et al. Representation and exchange of knowledge about actions, objects, and environments in the RoboEarth framework[J]. IEEE Transactions on Automation Science and Engineering, 2013, 10(3): 643-651.
[23] Kehoe B, Warrier D, Patil S, et al. Cloud-based grasp analysis and planning for toleranced parts using parallelized Monte Carlo sampling[J]. IEEE Transactions on Automation Science and Engineering, 2015, 12(2): 455-470.
[24] Liu J, Zhou F Y, Yin L, et al. A novel cloud platform for service robots[J]. IEEE Access, 2019, 7: 182951-182961.
[25] Yin S, Ding S X, Zhou D H. Diagnosis and prognosis for complicated industrial systems – Part I[J]. IEEE Transactions on Industrial Electronics, 2016, 63(4): 2501-2505.
[26] 郭仁和. 基于机器学习的服务机器人云端故障诊断方法研究[D].济南：山东大学， 2019. Guo R H. Research of service robot cloud fault diagnosis based on machine learning[D]. Jinan: Shandong University, 2019.