Hybrid feature adaptive fusion network for multivariate time series classification with application in AUV fault detection

References

• Alshamrani M. 2021. Remote intelligent healthcare system based on the rocket technique. Arab J Sci Eng. 46:9263–9277. doi:10.1007/s13369-021-05805-2.
   Web of Science ®Google Scholar
• Bagnall A, Lines J, Bostrom A, Large J, Keogh E. 2017. The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Discov. 31:606–660. doi:10.1007/s10618-016-0483-9.
   PubMed Web of Science ®Google Scholar
• Chen G, Lu Y, Su R. 2022. Interpretable fault diagnosis with shapelet temporal logic: theory and application. Automatica. 142. doi:10.1016/j.automatica.2022.110350.
   Web of Science ®Google Scholar
• Cheng C, Jia R. 2019. A classification method of cnn for numerical data based on radar chart representation. Inf Control. 48:429–436. doi:10.13976/j.cnki.xk.2019.8525.
   Google Scholar
• Cheng MY, Guan QS, Ji F, Cheng JL, Chen WQ. 2022. Mobile relaying-based reliable data collection in underwater acoustic sensor networks. IEEE Wirel Commun Lett. 11:1795–1799. doi:10.1109/lwc.2022.3181239.
   Web of Science ®Google Scholar
• Cheng X, Han P, Li G, Chen S, Zhang H. 2020. A novel channel and temporal-wise attention in convolutional networks for multivariate time series classification. IEEE Access. 8:212247–212257. doi:10.1109/access.2020.3040515.
   Google Scholar
• Davari N, Aguiar AP. 2021. Real-time outlier detection applied to a doppler velocity log sensor based on hybrid autoencoder and recurrent neural network. IEEE J Ocean Eng. 46:1288–1301. doi:10.1109/joe.2021.3057909.
   Web of Science ®Google Scholar
• Dempster A, Petitjean F, Webb GI. 2020. Rocket: exceptionally fast and accurate time series classification using random convolutional kernels. Data Min Knowl Discov. 34:1454–1495. doi:10.1007/s10618-020-00701-z.
   Web of Science ®Google Scholar
• Gao S, He B, Yu F, Zhang X, Yan TH, Feng C. 2021. An abnormal motion condition monitoring method based on the dynamic model and complex network for AUV. Ocean Eng. 237. doi:10.1016/j.oceaneng.2021.109472.
   Web of Science ®Google Scholar
• Grinsztajn L, Oyallon E, Varoquaux G. 2022. Why do tree-based models still outperform deep learning on tabular data? https://hal.archives-ouvertes.fr/hal-03723551.
   Google Scholar
• Hodges BA, Fratantoni DM. 2014. Auv observations of the diurnal surface layer in the North Atlantic salinity maximum. J Phys Oceanogr. 44:1595–1604. doi:10.1175/jpo-d-13-0140.1.
   Web of Science ®Google Scholar
• Huang Y, Li Y, Yu J. Li s. Feng X. 2020. State-of-the-art and development trends of AUV intelligence. Robot. 42:215–231. doi:10.13973/j.cnki.robot.190392.
   Google Scholar
• Ji D, Wang R, Zhai Y, Gu H. 2021. Dynamic modeling of quadrotor AUV using a novel cfd simulation. Ocean Eng. 237:109651. doi:10.1016/j.oceaneng.2021.109651.
   Web of Science ®Google Scholar
• Ji D, Yao X, Li S, Tang Y, Tian Y. 2021. Autonomous underwater vehicle fault diagnosis dataset. Data Brief. 39:107477–107477. doi:10.1016/j.dib.2021.107477.
   PubMed Web of Science ®Google Scholar
• Kang X, Li Y. 2022. Motion parameters estimation of underwater moving target based on iterative optimization algorithm for an AUV. Robot. 44:203–211. doi:10.13973/j.cnki.robot.200473.
   Google Scholar
• Karatug C, Arslanoglu Y. 2022. Importance of early fault diagnosis for marine diesel engines: a case study on efficiency management and environment. Ships Offshore Struct. 17:472–480. doi:10.1080/17445302.2020.1835077.
   Web of Science ®Google Scholar
• Khan M, Wang H, Ngueilbaye A, Elfatyany A. 2020. End-to-end multivariate time series classification via hybrid deep learning architectures. Pers Ubiquitous Comput. doi:10.1007/s00779-020-01447-7.
   Web of Science ®Google Scholar
• Lazakis I, Gkerekos C, Theotokatos G. 2019. Investigating an SVM-driven, one-class approach to estimating ship systems condition. Ships Offshore Struct. 14:432–441. doi:10.1080/17445302.2018.1500189.
   Web of Science ®Google Scholar
• Li W, Luo Z, Xi X. 2020. Movement trajectory recognition of sign language based on optimized dynamic time warping. Electronics. 9. doi:10.3390/electronics9091400.
   PubMed Web of Science ®Google Scholar
• Lin C, Liu K, Li Y, Zhang Y, Chen Y. 2020. Bearing-only target pursuing strategy for AUV based on short-term planning. Robot. 42:309–315. doi:10.13973/j.cnki.robot.190227.
   Google Scholar
• Miao Z, Yuan X, Zhang H, Yan L, Zhou F, Guo R, Wang J. 2021. Cloud fault diagnosis method of a service robot motion system based on se-cnn. Robot. 43:321–330. doi:10.13973/j.cnki.robot.200295.
   Google Scholar
• Miller A, Miller B, Miller G. 2019. On AUV control with the aid of position estimation algorithms based on acoustic seabed sensing and doa measurements. Sensors. 19. doi:10.3390/s19245520.
   Web of Science ®Google Scholar
• Miller AB, Miller BM. 2018. On AUV navigation based on acoustic sensing of the seabed profile. J Commun Technol Electron. 63:1502–1505. doi:10.1134/s106422691812015x.
   Web of Science ®Google Scholar
• Mohammadzade H, Hosseini S, Rezaei-Dastjerdehei MR, Tabejamaat M. 2021. Dynamic time warping-based features with class-specific joint importance maps for action recognition using kinect depth sensor. IEEE Sens J. 21:9300–9313. doi:10.1109/jsen.2021.3051497.
   Web of Science ®Google Scholar
• Ngatini, Apriliani E, Nurhadi H. 2017. Ensemble and fuzzy Kalman filter for position estimation of an autonomous underwater vehicle based on dynamical system of AUV motion. Expert Syst Appl. 68:29–35. doi:10.1016/j.eswa.2016.10.003.
   Web of Science ®Google Scholar
• Qian B, Xiao Y, Zheng Z, Zhou M, Zhuang W, Li S, Ma Q. 2020. Dynamic multi-scale convolutional neural network for time series classification. IEEE Access. 8:109732–109746. doi:10.1109/access.2020.3002095.
   Google Scholar
• Ren RZ, Zhang LCA, Liu L, Wu DW, Pan G, Huang QG, Zhu YC, Liu YZ, Zhu ZX. 2022. Multi-AUV cooperative navigation algorithm based on temporal difference method. J Mar Sci Eng. 10. doi:10.3390/jmse10070955.
   PubMed Web of Science ®Google Scholar
• Ruiz AP, Flynn M, Large J, Middlehurst M, Bagnall A. 2021. The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Min Knowl Discov. 35:401–449. doi:10.1007/s10618-020-00727-3.
   PubMed Web of Science ®Google Scholar
• Shi LL, Zheng RH, Zhang SL, Liu MQ. 2022. Cooperative flow field estimation via relative and absolute motion-integration errors of multiple AUVs. Automatica. 141: 110306. doi:10.1016/j.automatica.2022.110306.
   Web of Science ®Google Scholar
• Shokoohi-Yekta M, Hu B, Jin H, Wang J, Keogh E. 2017. Generalizing DTW to the multi-dimensional case requires an adaptive approach. Data Min Knowl Discov. 31:1–31. doi:10.1007/s10618-016-0455-0.
   PubMed Web of Science ®Google Scholar
• Sun YS, Ran XR, Li YM, Zhang GC, Zhang YH. 2016. Thruster fault diagnosis method based on Gaussian particle filter for autonomous underwater vehicles. Int J Nav Archit Ocean Eng. 8:243–251. doi:10.1016/j.ijnaoe.2016.03.003.
   Web of Science ®Google Scholar
• Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G. 2018. Understanding convolution for semantic segmentation. In: 2018 IEEE winter conference on applications of computer vision (WACV); p. 1451–1460. doi:10.1109/WACV.2018.00163.
   Google Scholar
• Wang ZG, Yan WZ, Oates T. 2017. Time series classification from scratch with deep neural networks: a strong baseline. In: International joint conference on neural networks (IJCNN); p. 1578–1585.
   Google Scholar
• Wolbrecht E, Gill B, Borth R, Canning J, Anderson M, Edwards D. 2015. Hybrid baseline localization for autonomous underwater vehicles. J Intell Robot Syst. 78:593–611. doi:10.1007/s10846-014-0070-5.
   Web of Science ®Google Scholar
• Wu H, Liu H. 2021. Non-intrusive load transient identification based on multivariate LSTM neural network and time series data augmentation. Sustain Energy Grids Netw. 27: doi:10.1016/j.segan.2021.100490.
   Web of Science ®Google Scholar
• Xia S, Zhou X, Shi H, Li S, Xu C. 2021. A fault diagnosis method based on attention mechanism with application in Qianlong-2 autonomous underwater vehicle. Ocean Eng. 233. doi:10.1016/j.oceaneng.2021.109049.
   Web of Science ®Google Scholar
• Yan D, Wang C, Zhou NE, You XR. 2018. Construction and application of ocean big data platform based on UAV system. In: Conference on ocean optics and information technology / international symposium on optoelectronic technology and application (OTA). doi:10.1117/12.2501845.
   Google Scholar
• Yu D, Deng K, Gong W, Zhang M, Chu Z. 2020. Thruster fault feature extraction method for underwater vehicle. In: 32nd Chinese control and decision conference (CCDC); p. 2751–2757. doi:10.26914/c.cnkihy.2020.047594.
   Google Scholar
• Yu J, Zhou Z, Liu J. 2021. Research progress and analysis on multiple autonomous underwater vehicle systems. Inf Control. 50:129–140. doi:10.13976/j.cnki.xk.2021.0572.
   Google Scholar
• Yu Y, Si X, Hu C, Zhang J. 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 31:1235–1270. doi:10.1162/neco_a_01199.
   PubMed Web of Science ®Google Scholar
• Zhang J, Zhang Y, Xu X, Fu X, He Y. 2022. Unsupervised and supervised learning combined power load curve classification based on sequential trajectory feature extraction algorithm. IEEE Access. 10:90312–90320. doi:10.1109/access.2022.3201552.
   Web of Science ®Google Scholar
• Zhou S, Xu X, Xiao Y, Chang W, Qian S, Pan X. 2019. Remaining useful life prediction with similarity fusion of multi-parameter and multi-sample based on the vibration signals of diesel generator gearbox. Entropy. 21. doi:10.3390/e21090861.
   Web of Science ®Google Scholar
• Zhu H, Zhang J, Cui H, Wang K, Tang Q. 2022. Tcran: multivariate time series classification using residual channel attention networks with time correction. Appl Soft Comput. 114. doi:10.1016/j.asoc.2021.108117.
   PubMed Web of Science ®Google Scholar