本文提出一种结合联邦无迹卡尔曼滤波（Federated Unscented Kalman Filtering，FUKF）与多模型自适应估计（Multiple Model Adaptive Estimation，MMAE）的故障诊断方法。该方法首先基于多个无迹卡尔曼滤波（Unscented Kalman Filter，UKF）子滤波器分别构建正常状态和不同故障模式下的状态估计模型，并利用MMAE框架计算各模型的概率权重，从而实现对故障类型的自适应识别。在此基础上，FUKF通过加权融合所有UKF的估计值，以提高状态估计的精度和鲁棒性。与传统方法相比，该方法不仅能够适应非线性系统的复杂动态特性，还能在线实时监测故障并精确估计其严重程度。实验结果表明，该方法在响应速度和诊断精度方面显著优于联邦扩展卡尔曼滤波（Federated Extended Kalman Filtering，FEKF），有效提升了推进器故障诊断的可靠性和安全性。
In this paper, a fault diagnosis method combining FEDERAL untraceable Kalman filtering (FUKF) and Multi-model Adaptive Estimation (MMAE) is proposed. The method is based on multiple Unscented Kalman Filter (UKF) sub-filters to construct state estimation models under normal and different fault modes respectively, and calculates the probability weights of each model using the MMAE framework so as to realize the adaptive identification of fault types. On this basis, the FUKF fuses all the UKF estimates by weighting in order to improve the accuracy and robustness of state estimation. Compared with the traditional method, this method can not only adapt to the complex dynamic characteristics of nonlinear systems, but also monitor the faults in real time and accurately estimate their severity. The experimental results show that the method significantly outperforms the federated extended Kalman filter (FEKF) in terms of response speed and diagnostic accuracy, which effectively improves the reliability and safety of propeller fault diagnosis.
2025,47(21): 73-80 收稿日期：2025-2-21
DOI：10.3404/j.issn.1672-7649.2025.21.013
分类号：U672.7
基金项目：国家自然科学基金资助项目（52001235）；湖北省自然科学基金资助项目（2022CFB313）
作者简介：李昌隆(2000-),男,硕士研究生,研究方向为智能传感与无人艇故障诊断
参考文献：
[1] 王志光, 李彬, 刘峰, 等. 国内外无人艇布放与回收系统发展综述[J]. 船舶工程, 2024, 46(11): 1-11.
WANG Z G, LI B, LIU F, et al. Overview and analysis of domestic and foreign unmanned surface vessel launch and recovery system[J]. Ship Engineering, 2024, 46(11): 1-11.
[2] FOSSEN T I, FJELLSTAD O E. Nonlinear modelling of marine vehicles in 6 degrees of freedom[J]. Mathematical Modelling of Systems, 1995, 1(1): 17-27.
[3] 王石, 张建强, 杨舒卉, 等. 国内外无人艇发展现状及典型作战应用研究[J]. 火力与指挥控制, 2019, 44(2): 11-15.
WANG S, ZHANG J Q, YANG S H, et al. Research on development status and combat applications of USVs in worldwide[J]. Fire Control & Command Control, 2019, 44(2): 11-15.
[4] ER M J, MA C, LIU T, et al. Intelligent motion control of unmanned surface vehicles: A critical review[J]. Ocean Engineering, 2023, 280: 114562.
[5] YANG T, JIANG Z, SUN R, et al. Maritime search and rescue based on group mobile computing for unmanned aerial vehicles and unmanned surface vehicles[J]. IEEE transactions on industrial informatics, 2020, 16(12): 7700-7708.
[6] SAITEJA G, PRAMOD S. Design and simulation of an autonomous surface vehicle for trash collection using ros[C]//2021 IEEE 9th Region 10 Humanitarian Technology Conference (R10-HTC). IEEE, 2021.
[7] MA Y, NIE Z, HU S, et al. Fault detection filter and controller co-design for unmanned surface vehicles under DoS attacks[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(3): 1422-1434.
[8] 郑海山, 杨奕飞. 基于改进VIT神经网络的无人艇电力系统故障诊断[J]. 舰船科学技术, 2024, 46(18): 154-158.
ZHENG H S, YANG Y F. Fault diagnosis of unmanned surface vessel power system based on improved VIT neural network[J]. Ship Science and Technology, 2024, 46(18): 154-158.
[9] CHOO K B, CHO H, PARK J H, et al. A research on fault diagnosis of a USV thruster based on PCA and entropy[J]. Applied Sciences, 2023, 13(5): 3344.
[10] CHO H, PARK J H, CHOO K B, et al. Unmanned surface vehicle thruster fault diagnosis via vibration signal wavelet transform and vision transformer under varying rotational speed conditions[J]. Sensors, 2024, 24(5): 1697.
[11] KO N Y, SONG G, CHOI H T, et al. Fault detection and diagnosis of sensors and actuators for unmanned surface vehicles[C]//2021 21st International Conference on Control, Automation and Systems (ICCAS). IEEE, 2021.
[12] ZHANG Q. Adaptive Kalman filter for actuator fault diagnosis[J]. Automatica, 2018, 93: 333-342.
[13] SKRIVER M, HELCK J, HASAN A. Adaptive extended kalman filter for actuator fault diagnosis[C]//2019 4th International Conference on System Reliability and Safety (ICSRS). IEEE, 2019: 339-344.
[14] ZHOU Z, ZHONG M, WANG Y. Fault diagnosis observer and fault-tolerant control design for unmanned surface vehicles in network environments[J]. IEEE Access, 2019(7): 173694-173702.
[15] FEI Z, WANG X, WANG Z. Event-based fault detection for unmanned surface vehicles subject to denial-of-service attacks[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 52(5): 3326-3336.
[16] BHAGAVATHI R, KUFOALOR D K M, HASAN A. Digital twin-driven fault diagnosis for autonomous surface vehicles[J]. IEEE Access, 2023, 11: 41096-41104
[17] HASAN A, ASFIHANI T, OSEN O, et al. Leveraging digital twins for fault diagnosis in autonomous ships[J]. Ocean Engineering, 2024, 292: 116546.
[18] FOSSEN T I. Handbook of marine craft hydrodynamics and motion control[M]. John Wiley & Sons, 2011.
