As one of the important friction components of internal combustion engine, the main bearing is exposed to complex dynamic loads and is prone to wear during long-term operation. It is of great significance to study the wear condition monitoring of main bearing. Time domain analysis and wavelet packet decomposition (WPD) are carried out to analyze the block vibration signals under different working conditions. The influence of engine speed, torque, oil temperature and main bearing clearance on the block vibration is analyzed. On this basis, the characteristic parameters reflecting the main bearing state are extracted to form the input vector and the support vector machine (SVM) model is established. Then the key parameters of the SVM, including penalty factor and kernel function parameter are optimized by grid search method and gray wolf optimizer (GWO). The optimized diagnosis model is used to identify the wear state of main bearing. The result indicates that the recognition accuracy and the running time of the model optimized by GWO is 97.22% and 9.13 s respectively. So GWO-SVM diagnosis model can effectively recognize the main bearing wear state, mitigating the risks of unplanned downtime and secondary damage caused by main bearing failure.
TianJWangLXiongY, et al. Enhancing combustion efficiency and reducing nitrogen oxide emissions from ammonia combustion: a comprehensive review. Process Saf Environ Prot2024; 183: 514–543.
2.
JiSLanXLianJ, et al. Combustion parameter estimation for ICE from surface vibration using frequency spectrum analysis. Measurement2018; 128: 485–494.
3.
DuCLiWRongYLiFYuFZengX.Research on the application of artificial intelligence method in automobile engine fault diagnosis. Eng Res Express2021; 3(2): 026002.
4.
CaiBSunXWangJ, et al. Fault detection and diagnostic method of diesel engine by combining rule-based algorithm and BNs/BPNNs. J Manuf Syst2020; 57: 148–157.
5.
ChenRZhaoBHeT, et al. Study on coupling transient mixed lubrication and time-varying wear of main bearing in actual operation of low-speed diesel engine. Tribol Int2024; 191: 109159.
6.
ZhaoXShiJWuLMaFZhangZShengB.Research of coordinated deformation characteristics for diesel engine main bearing based on bearing clearance margin. Int J Engine Res2024; 25(12): 2215–2229.
7.
JiSLiYTianG, et al. Study on the relationship between combustion parameters and cylinder head vibration signal in time domain. Energies2021; 14(19): 6421.
8.
ZhuJYangJG.Development trends of research on monitoring wear of sliding main bearing for diesel engine. Adv Mater Res2012; 472–475: 1702–1706.
9.
JiaJRenG.An improved adaptive VMD method and its application in wear condition monitoring of main bearing. Vibroeng Proc2021; 38: 26–31.
10.
YuYYangJ.Vibration diagnosis of main journal bearings for diesel engines. Int J Veh Noise Vib2005; 1(3–4): 265–286.
11.
OkhionkpamwonyiSOtuyemiFShiD, et al. Experimental Investigation of vibration signals from an on-rotor sensing for diesel engine crankshaft lubrication monitoring. In: ZhangHJiYLiuTSunXBallAD (eds) Proceedings of TEPEN 2022. TEPEN 2022. Mechanisms and machine science. 2023, pp.138–150, Vol. 129. Cham: Springer.
12.
LiMShiPHanD, et al. Lubrication state monitoring of journal bearings based on vibration features. In: LiuTZhangFHuangSWangJGuF (eds) Proceedings of the TEPEN International Workshop on Fault Diagnostic and prognostic. TEPEN 2024. Mechanisms and Machine Science. 2024, pp.522–531, Vol. 169. Cham: Springer.
13.
MachadoTHAlvesDSCavalcaKL.Investigation about journal bearing wear effect on rotating system dynamic response in time domain. Tribol Int2019; 129: 124–136.
14.
ZhouYWangZZuoXZhaoH.Identification of wear mechanisms of main bearings of marine diesel engine using recurrence plot based on CNN model. Wear2023; 520-521: 204656.
15.
DaiJTianLChangH.An intelligent diagnostic method for wear depth of sliding bearings based on MGCNN. Machines2024; 12(4): 266.
16.
MoosavianAAhmadiHTabatabaeefarA.Fault diagnosis of main engine journal bearing based on vibration analysis using Fisher linear discriminant, K-nearest neighbor and support vector machine. J Vibroengineering2012; 14(2): 894–906.
17.
ZhangYCuiJ.Crankshaft bearing fault diagnosis based on SVDD and D-S theory. J Chongqing Univ Technol2019; 33(11): 89–94.
18.
MoosavianAAhmadiHTabatabaeefarA.Condition monitoring of engine journal-bearing using power spectral density and support vector machine. Elixir Mech Engg2012; 43: 6631–6635.
19.
WuJDLiuCH.An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network. Expert Syst Appl2009; 36(3): 4278–4286.
20.
ZhangXZhuJWuYZhenDZhangM.Feature extraction for bearing fault detection using wavelet packet energy and fast Kurtogram analysis. Appl Sci2020; 10(21): 7715.
21.
HeQ.Vibration signal classification by wavelet packet energy flow manifold learning. J Sound Vib2013; 332(7): 1881–1894.
22.
LiuXHanJXuH, et al. An indirect method for rail corrugation measurement based on numerical models and wavelet packet decomposition. Measurement2022; 191: 110726.
23.
XiaSXiaYXiangJ.Piston wear detection and feature selection based on vibration signals using the improved spare support vector machine for axial piston pumps. Materials2022; 15(23): 8504.
JiWLiuDMengYXueY.A review of genetic-based evolutionary algorithms in SVM parameters optimization. Evol Intell2021; 14: 1389–1414.
26.
BhavsarHPanchalMH. A review on support vector machine for data classification. Int J Adv Res Comput Eng Technol2012; 1: 185–189.
27.
SunYDingSZhangZJiaW.An improved grid search algorithm to optimize SVR for prediction. Soft Comput2021; 25: 5633–5644.
28.
MirjaliliSMirjaliliSMLewisA.Grey wolf optimizer. Adv Eng Softw2014; 69: 46–61.
29.
LiJLuoWBaiMSongM.Fault diagnosis of high-speed rolling bearing in the whole life cycle based on improved grey wolf optimizer-least squares support vector machines. Digit Signal Process2024; 145: 104345.
30.
XieSTanHLiYFengZCaoZ.Locally generalized preserving projection and flexible grey wolf optimizer-based ELM for fault diagnosis of rolling bearing. Measurement2022; 202: 111828.
