Fault detection in Autonomous Underwater Vehicles (AUVs) is crucial for ensuring their safe and efficient operation, especially in challenging underwater environments. In this study, we investigate traditional machine learning models to detect common AUV conditions, Add Weight, Pressure Gain Constant, PropellerDamageBad, and PropellerDamageSlight, using a comprehensive dataset of sensor readings and control signals. First, the data were segmented into four time windows (20, 50, 100, and 150 s) to address dimensionality and optimize model performance. To complement these time-series features, we then extracted basic descriptive statistical features (mean, standard deviation, min/max, 25th/50th/75th percentiles, skewness, and kurtosis) for each window and retrained our classifiers on this enriched feature set. Among all models, the Cubic SVM achieved the highest test accuracy of 96.7%. Finally, we applied SHapley Additive exPlanations (SHAP) to interpret the Cubic SVM’s predictions and identify the top-10 features driving correct classification for each class. Our results demonstrate that the Cubic SVM not only delivers a balanced trade-off between accuracy and computational efficiency, suitable for real-time, resource-constrained deployment, but also, through SHAP, yields actionable insights into the most discriminative sensor and control-signal statistics for each AUV condition. Future work will explore online adaptation and further model compression to enhance deployment in fully autonomous missions.
GertlerJ.Fault detection and diagnosis in engineering systems. CRC Press, 2017.
2.
BandaraRNGaspeS.Fuzzy logic controller design for an unmanned aerial vehicle. In: 2016 IEEE international conference on information and automation for sustainability (ICIAfS), 2016, pp.1–5.
3.
HamiltonKLaneDMBrownKE, et al. An integrated diagnostic architecture for autonomous underwater vehicles. J Field Robot2007; 24(6): 497–526.
4.
RatnayakeRDe SilvaTRodrigoC. A comparison of fuzzy logic controller and pid controller for differential drive wall-following mobile robot. In: 2019 14th conference on industrial and information systems (ICIIS), 2019, pp.523–528.
5.
JiDYaoXLiS, et al. Model-free fault diagnosis for autonomous underwater vehicles using sequence convolutional neural network. Ocean Eng2021; 232: 108874.
6.
MakumburaRKMampitiyaLRathnayakeN, et al. Advancing water quality assessment and prediction using machine learning models, coupled with explainable artificial intelligence (XAI) techniques like shapley additive explanations (shap) for interpreting the black-box nature. Results Eng2024; 23: 102831.
7.
RathnayakeNDangTLHoshinoY. Performance comparison of the anfis based quad-copter controller algorithms. In: 2021 IEEE international conference on fuzzy systems (FUZZ-IEEE), 2021, pp.1–8.
8.
ShumskyAZhirabokAHajiyevC.Observer based fault diagnosis in thrusters of autonomous underwater vehicle. In: 2010 conference on control and fault-tolerant systems (SysTol), 2010, pp.11–16.
9.
KempM.Underwater thruster fault detection and isolation. In: AIAA Scitech 2019 forum, 2019, p. 1959.
10.
WangYChenYGaoJ, et al. A fault diagnosis method for AUVs based on meta-self-attentive variable-scale CNN. In: International conference on autonomous unmanned systems, 2023, pp.293–303.
11.
TsaiC-MWangC-SChungY-J, et al. Multi-sensor fault diagnosis of underwater thruster propeller based on deep learning. Sensors2021; 21(21): 7187.
12.
RuedenLMayerSSifaR, et al. Combining machine learning and simulation to a hybrid modelling approach: current and future directions. In: Advances in intelligent data analysis XVIII: 18th international symposium on intelligent data analysis, proceedings 18, 2020, pp.548–560.
13.
QaidTSMazaarHAl-ShamriMYH, et al. Hybrid deep-learning and machine-learning models for predicting covid-19. Comput Intell Neurosci2021; 2021(1): 9996737.
14.
KamatPSugandhiRKumarS.Data-driven bearing fault detection using hybrid autoencoder-LSTM deep learning approach. Int J Model Identification Control2021; 38(1): 88.
15.
PicautJCanAFortinN, et al. Low-cost sensors for urban noise monitoring networks-a literature review. Sensors2020; 20(8): 2256.
16.
GungorVCLuBHanckeGP.Opportunities and challenges of wireless sensor networks in smart grid. IEEE Trans Ind Electron2010; 57(10): 3557–3564.
17.
ChenMShaoHDouH, et al. Data augmentation and intelligent fault diagnosis of planetary gearbox using ilofgan under extremely limited samples. IEEE Trans Reliab2023; 72(3): 1029–1037.
18.
GoodfellowIPouget-AbadieJMirzaM, et al. Generative adversarial networks. Commun ACM2020; 63(11): 139–144.
19.
AbukmeilMFerrariSGenoveseA, et al. A survey of unsupervised generative models for exploratory data analysis and representation learning. ACM Comput Surv2022; 54(5): 1–40.
20.
FuWJiangXTanC, et al. Rolling bearing fault diagnosis in limited data scenarios using feature enhanced generative adversarial networks. IEEE Sens J2022; 22(9): 8749–8759.
21.
GuoQLiYLiuY, et al. Data augmentation for intelligent mechanical fault diagnosis based on local shared multiple-generator GAN. IEEE Sens J2022; 22(10): 9598–9609.
22.
WangWYangRGuoC, et al. CNN-based hybrid optimization for anomaly detection of rudder system. IEEE Access2021; 9: 121845–121858.
23.
RathnayakeNDangTLHoshinoY. A novel optimization algorithm: cascaded adaptive neuro-fuzzy inference system. Int J Fuzzy Syst2021; 23(7): 1955–1971.
24.
RathnayakeNRathnayakeUDangTL, et al. A cascaded adaptive network-based fuzzy inference system for hydropower forecasting. Sensors2022; 22(8): 2905.
25.
Al-QuranM.Efficient and effective anomaly detection in autonomous vehicles: a combination of gradient boosting and anfis algorithms. Int J Fuzzy Syst2025; 27: 1421–1437.
26.
de MiguelLJBlázquezLF.Fuzzy logic-based decision-making for fault diagnosis in a dc motor. Eng Appl Artif Intell2005; 18(4): 423–450.
27.
HuangKLiWFangH, et al. IPORF: a combined improved parrot optimizer algorithm and random forest for fault diagnosis in AUV. Ocean Eng2024; 313: 119665.
28.
HuangKLiWCaoS, et al. Fault diagnosis in autonomous underwater vehicle propulsion system: a systematic review. Ships Offshore Struct2025; 25: 1–29.
29.
ZhaoHLiuCDangX, et al. Few-shot cross-domain fault diagnosis of transportation motor bearings using MAML-GA. IEEE Trans Transp Electrification2026; 12: 1165–1174.
30.
ZhaoHGuMQiuS, et al. Dynamic path planning for space-time optimization cooperative tasks of multiple unmanned aerial vehicles in uncertain environment. IEEE Trans Consum Electron2025; 71: 7673–7682.
31.
LiJDengWDingJ, et al. IBN-mixstyle network with dynamic weighted invariant risk minimization for domain-generalized bearing fault diagnosis. IEEE Trans Consum Electron2025; 71: 9929–9939.
32.
DengWGuanHZhaoH.Parameterized iterative time–frequency-multisqueezing transform for bearing fault diagnosis. IEEE Trans Instrum Meas2025; 74: 1–11.
33.
DengWLiHZhaoH.Antinoise bearing fault diagnosis using time-reassigned multisynchrosqueezing transform and complex sparse learning dictionary. IEEE Trans Instrum Meas2025; 74: 1–10.
34.
DengWLiXSunY, et al. Privacy protection-enhanced vertical-horizontal federated learning secure sharing for multisource heterogeneous data. IEEE Trans Ind Inform2026; 22(4): 1–10.
35.
BarandasMFolgadoDFernandesL, et al. Tsfel. Time series feature extraction library. SoftwareX2020; 11: 100456.
36.
PedregosaFVaroquauxGGramfortA, et al. Scikit-learn: machine learning in python. J Mach Learn Res2011; 12: 2825–2830.
37.
SnoekJLarochelleHAdamsRP.Practical bayesian optimization of machine learning algorithms. Adv Neural Inf Process Syst2012; 25: 2951–2959.
38.
ChangC-CLinC-J.Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol2011; 2(3): 1–27.
39.
LundbergSMErionGChenH, et al. From local explanations to global understanding with explainable AI for trees. Nat Mach Intell2020; 2: 56–67.
