A fault diagnosis method based on attention mechanism with application in Qianlong-2 autonomous underwater vehicle

Abstract This study proposed a fault diagnosis method based on deep learning and attention mechanism for autonomous underwater vehicle (AUV). Firstly, a data attention mechanism is proposed to introduce dynamic weighting coefficients of monitoring variables to realize dynamic decorrelation. Then, the automatic feature engineering is realized by a bi-directional gated recurrent unit (GRU) network to acquire the time dynamic characteristics of monitoring variables. Finally, fault detection is implemented via multi-layer perceptron (MLP). With respect to fault identification, this study embeds a spatial attention mechanism in the fault detection network to capture the semantic relationship between monitoring variables and faults, and fault identification result can be obtained by parsing this semantic relationship. We present a new loss function and training strategy for cooperation between the fault detection and identification tasks. The proposed method is validated on the monitoring data of Qianlong-2 AUV obtained during the mission in the South China Sea, which shows the effectiveness and superiority of the method.

[1]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[2]  Hanumant Singh,et al.  Detection of unanticipated faults for autonomous underwater vehicles using online topic models , 2018, J. Field Robotics.

[3]  Gwyn Griffiths,et al.  Risk Analysis for Autonomous Underwater Vehicle Operations in Extreme Environments , 2010, Risk analysis : an official publication of the Society for Risk Analysis.

[4]  Dahai Zhang,et al.  A Data-Driven Design for Fault Detection of Wind Turbines Using Random Forests and XGboost , 2018, IEEE Access.

[5]  Gerasimos Theotokatos,et al.  A novel data condition and performance hybrid imputation method for energy efficient operations of marine systems , 2019, Ocean Engineering.

[6]  Been Kim,et al.  Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[7]  Mei Liu,et al.  Deep forest based intelligent fault diagnosis of hydraulic turbine , 2019, Journal of Mechanical Science and Technology.

[8]  Jian Liu,et al.  A novel self-adapting filter based navigation algorithm for autonomous underwater vehicles , 2019, Ocean Engineering.

[9]  Javad Askari,et al.  Fault diagnosis of autonomous underwater vehicle using neural network , 2014, 2014 22nd Iranian Conference on Electrical Engineering (ICEE).

[10]  Kristin Y. Pettersen,et al.  Learning an AUV docking maneuver with a convolutional neural network , 2017, OCEANS 2017 – Anchorage.

[11]  Gunnar Rätsch,et al.  Leveraging Sequence Classification by Taxonomy-Based Multitask Learning , 2010, RECOMB.

[12]  Zhao Chen,et al.  GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks , 2017, ICML.

[13]  Mingjun Zhang,et al.  Thruster fault identification based on fractal feature and multiresolution wavelet decomposition for autonomous underwater vehicle , 2017 .

[14]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[15]  Daqi Zhu,et al.  Observer-based fault detection for magnetic coupling underwater thrusters with applications in jiaolong HOV , 2020 .

[16]  Jun Lu,et al.  Sensor Fault Diagnosis of Autonomous Underwater Vehicle Based on LSTM , 2018, 2018 37th Chinese Control Conference (CCC).

[17]  Bo-Suk Yang,et al.  VIBEX: an expert system for vibration fault diagnosis of rotating machinery using decision tree and decision table , 2005, Expert Syst. Appl..

[18]  Dan Yu,et al.  An improved recurrent neural network for unmanned underwater vehicle online obstacle avoidance , 2019 .

[19]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[20]  Yanchao Sun,et al.  Distributed finite-time fault-tolerant containment control for multiple ocean Bottom Flying node systems with error constraints , 2019, Ocean Engineering.

[21]  Venugopalan Pallayil,et al.  Design of an adaptive noise canceller for improving performance of an autonomous underwater vehicle-towed linear array , 2020 .

[22]  Weidong Zhang,et al.  Adaptive non‐singular integral terminal sliding mode tracking control for autonomous underwater vehicles , 2017, IET Control Theory & Applications.

[23]  Mingjun Zhang,et al.  Multi-fault diagnosis for autonomous underwater vehicle based on fuzzy weighted support vector domain description , 2014 .

[24]  Vlad Niculae,et al.  A Regularized Framework for Sparse and Structured Neural Attention , 2017, NIPS.

[25]  Benedetto Allotta,et al.  Redundant and reconfigurable propulsion systems to improve motion capability of underwater vehicles , 2018 .

[26]  Chaomin Luo,et al.  Fault reconstruction using a terminal sliding mode observer for a class of second-order MIMO uncertain nonlinear systems. , 2020, ISA transactions.

[27]  Abbas Karamodin,et al.  A novel anomaly detection method based on adaptive Mahalanobis-squared distance and one-class kNN rule for structural health monitoring under environmental effects , 2020 .

[28]  Mingjun Zhang,et al.  Thruster fault diagnosis in autonomous underwater vehicle based on grey qualitative simulation , 2015 .

[29]  Qin Zhang,et al.  On intelligent risk analysis and critical decision of underwater robotic vehicle , 2017 .