The status of the electric rudder servo system status directly affects the whole controlled system. We develop an innovative intelligent test platform for the electric rudder servo system and propose a new end-to-end method called K-clusters Synthetic Minority Over-sampling Technique-Multiscale Convolution Neural Attention Network for fault detection and diagnosis. Among them, the new method called K-clusters Synthetic Minority Over-sampling Technique is applied to address imbalances between and within classes by supplementing samples for the electric rudder servo system. Furthermore, to prevent the loss of sensor information due to the initial position, we propose a 2D-Multiscale Convolution Neural Attention Network to extract the 1D-Multisensor information. Compared to other models, the K-clusters Synthetic Minority Over-sampling Technique-Multiscale Convolution Neural Attention Network approach achieves state-of-the-art results, with an average Gmean of 0.99,646 and an average F2 Score of 0.99,375 in 10-fold validation. Finally, the total program execution time for all experimental models is calculated, which demonstrates the high efficiency of the 2D K-clusters Synthetic Minority Over-sampling Technique-Multiscale Convolution Neural Attention Network approach.
QinHYangRGuoC, et al.Fault diagnosis of electric rudder system using psofoa-bp neural network. Measurement2021; 186: 110058.
2.
TanXQiuJLiuG, et al.A novel approach of testability modeling and analysis for phm systems based on failure evolution mechanism. Chin J Aeronaut2013; 26(3): 766–776.
3.
DengYDi BucchianicoAPechenizkiyM. Controlling the accuracy and uncertainty trade-off in rul prediction with a surrogate wiener propagation model. Reliab Eng Syst Saf2020; 196: 106727.
4.
HeZChengWWenWA similarity comparison method of homologous fault response fragments under variable rotational speed. Shock Vib2020; 2020(1):8973678.
5.
XuQZhouHYuF, et al.Effective model based fault detection scheme for rudder servo system. J Cent South Univ2014; 21(11): 4172–4183.
6.
KemmetmullerWMullerSKugiA. Mathematical modeling and nonlinear controller design for a novel electrohydraulic power-steering system. IEEE ASME Trans Mechatron2007; 12(1): 85–97.
7.
ShiZGuFLennoxB, et al.The development of an adaptive threshold for model-based fault detection of a nonlinear electro-hydraulic system. Control Eng Pract2005; 13(11): 1357–1367.
8.
DongMLiuCLiG. Robust fault diagnosis based on nonlinear model of hydraulic gauge control system on rolling mill. IEEE Trans Control Syst Technol2009; 18(2): 510–515.
9.
ChiYDongYWangZJ, et al.Knowledge-based fault diagnosis in industrial internet of things: a survey. IEEE Internet Things J2022; 9(15): 12886–12900.
10.
MohamedSZFetouhTShaabanSM, et al.A novel analytical approach using rough set and genetic algorithm of a stable sensorless induction motor drives in the regenerating mode. IEEE Access2020; 8: 157748–157761.
11.
GhimireRZhangCPattipatiKR. A rough set-theory-based fault-diagnosis method for an electric power-steering system. IEEE ASME Trans Mechatron2018; 23(5): 2042–2053.
12.
LiLYangRGuoC, et al.The data learning and anomaly detection based on the rudder system testing facility. Measurement2020; 152: 107324.
13.
LiLYangRGuoC, et al.A novel application of intelligent algorithms in fault detection of rudder system. IEEE Access2019; 7: 170658–170667.
14.
ChangBYangRGuoC, et al.A new application of optimized random forest algorithms in intelligent fault location of rudders. IEEE Access2019; 7: 94276–94283.
15.
ChangBYangRGuoC, et al.Performance evaluation and prediction of rudders based on machine learning technology. Proc Inst Mech Eng G J Aerosp Eng2019; 233(15): 5746–5757.
16.
MingT-taoZhangY-xiangZhangX-yong. Fault detection for electro-hydraulic valve-controlled single rod cylinder servo system using linear robust observer. In 2009 International Conference on Measuring Technology and Mechatronics Automation2009; 1: 639–642.
17.
LiuJJiangBZhangK. Fault diagnosis for linear discrete systems based on an adaptive observer. Math Probl Eng2013; 2013(1): 343524–343525.
18.
YangZLiuPWangZ, et al.Fault and defect diagnosis of battery for electric vehicles based on big data analysis methods. Appl Energy2017; 207: 354–362.
19.
CadiniFSbarufattiCCancelliereF, et al.State-of-life prognosis and diagnosis of lithium-ion batteries by data-driven particle filters. Appl Energy2019; 235: 661–672.
20.
JiangLDengZTangX, et al.Data-driven fault diagnosis and thermal runaway warning for battery packs using real-world vehicle data. Energy2021; 234: 121266.
21.
WenLLiXGaoL, et al.A new convolutional neural network-based data-driven fault diagnosis method. IEEE Trans Ind Electron2017; 65(7): 5990–5998.
22.
JiaLChowTWSWangY, et al.Multiscale residual attention convolutional neural network for bearing fault diagnosis. IEEE Trans Instrum Meas2022; 71: 1–13.
23.
PhamMTKimJ-MKimCH. Rolling bearing fault diagnosis based on improved gan and 2-d representation of acoustic emission signals. IEEE Access2022; 10: 78056–78069.
24.
ZhangBWangPLiuG, et al.Diagnosis of single and multiple-source faults of chiller sensors using eweemd-icknn by time sequence denoising and non-Gaussian distribution feature extraction. Energy Build2023; 298: 113572.
25.
ZhaoMKangMTangB, et al.Deep residual networks with dynamically weighted wavelet coefficients for fault diagnosis of planetary gearboxes. IEEE Trans Ind Electron2017; 65(5): 4290–4300.
26.
SunWWangHXuJ, et al.Effective convolutional transformer for highly accurate planetary gearbox fault diagnosis. IEEE Open J Instrum Meas2022; 1: 1–9.
27.
GhimireRSankavaramCGhahariA, et al.Integrated model-based and data-driven fault detection and diagnosis approach for an automotive electric power steering system. In: 2011 Ieee Autotestcon. Piscataway: IEEE, 2011, pp. 70–77.
28.
RenHGuoCYangR, et al.Fault diagnosis of electric rudder based on self-organizing differential hybrid biogeography algorithm optimized neural network. Measurement2023; 208: 112355.
29.
YixiangXChunningY. Fault recognition of electric servo steering gear based on long and short-term memory neural network. In: 2020 International Conference on Unmanned Aircraft Systems (ICUAS). Piscataway: IEEE, 2020, pp. 1605–1613.
HanHWangW-YMaoB-H. Borderline-smote: a new over-sampling method in imbalanced data sets learning. In: International conference on intelligent computing. Berlin: Springer, 2005, pp. 878–887.
32.
HeHYangBGarciaEA, et al.Adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks. Piscataway: IEEE World Congress on Computational Intelligence, 2008, pp. 1322–1328.
33.
KumarAIngleYPandeA, et al.Canopy clustering: a review on pre-clustering approach to k-means clustering. Int. J. Innov. Adv. Comput. Sci.(IJIACS)2014; 3(5): 22–29.
34.
HuoYCaoYWangZ, et al.Traffic anomaly detection method based on improved gru and efms-kmeans clustering. Comput Model Eng Sci2021; 126(3): 1053–1091.
35.
ZhangJYiSGuoL, et al.A new bearing fault diagnosis method based on modified convolutional neural networks. Chin J Aeronaut2020; 33(2): 439–447.
36.
Sergey Ioffe and Christian Szegedy. Batch normalization: accelerating deep network training by reducing internal covariate shift. arxiv 2015. arXiv preprint arXiv:1502.031672015.
37.
HuJShenLSunG. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Piscataway: IEEE, 2018, pp. 7132–7141.
