The marine diesel engine is an important guarantee for the safe operation of the ship. It is of great significance to predict the running trend of the diesel engine and infer whether the diesel engine is in an abnormal working state in advance to ensure the safe operation of the ship. In this paper, combining the feature extraction ability of the attention mechanism (Attention) and the time-series memory ability of the long short-term neural network (LSTM), a prediction model of the exhaust gas temperature of the marine diesel engine is constructed. Meanwhile, in order to improve the prediction accuracy of the model, the improved particle swarm algorithm is used to optimize the structural parameters of the model, and a model with higher prediction performance is obtained. Then, according to the residual value distribution between the predicted value and the actual value of the model, the process control method is used to set the fault threshold, and the experimental data of normal and abnormal conditions are used for verification. The results show that the proposed model can accurately predict developing failures and provide a new method for ship condition maintenance.
LiTHuaMYinQ. The temperature forecast of ship propulsion devices from sensor data. Information2019; 10:316.
2.
CheliotisMLazakisITheotokatosG. Machine learning and data-driven fault detection for ship systems operations. Ocean Eng2020; 216:107968.
3.
KeYSongEYaoC, et al. A review: ship diesel engine prognostics and health management technology. J Harbin Eng Univ2020; 41:125–131.
4.
ZengYXieQ. Fault prediction method based on improved RNN and VAR for ship equipment. Comput Sci2021; 48:184–189.
5.
DikisKLazakisI. Dynamic predictive reliability assessment of ship systems. Int J Nav Archit Ocean Eng. Epub ahead of print 13March2019. DOI: 10.1016/j.ijnaoe.2019.01.002
6.
JianMTanLLaiFT, et al. Design of prognostics and health management for marine main propulsion system. J Nanjing Univ Aeronaut Astronaut2011; 43:119–124.
7.
QianL. Current situation and development of fault diagnosis technology for ship power plant. Mar Technol2006; 28(4): 44–47.
8.
ChenTWangNWangR. One-stage CNN detector-based benthonic organisms detection with limited training dataset. Neural Netw2021; 144:247–259.
9.
WangNWangYErMJ. Review on deep learning techniques for marine object recognition: architectures and algorithms. Control Eng Pract2022; 118:104458.
10.
JiangJRLeeJEZengYM. Time series multiple channel convolutional neural network with attention-based long short-term memory for predicting bearing remaining useful life. Sensors2020; 20:19.
11.
XuHMaRYanL, et al. Two-stage prediction of machinery fault trend based on deep learning for time series analysis. Digit Signal Process2021; 117:12.
12.
CheCWangHFuQ, et al. Combining multiple deep learning algorithms for prognostic and health management of aircraft. Aerosp Sci Technol2019; 94:9.
13.
ZraibiBOkarCChaouiH, et al. Remaining useful life assessment for lithium-ion batteries using CNN-LSTM-DNN hybrid method. IEEE Trans Vehicular Technol2021; 70:4252–4261.
14.
ChuiKTGuptaBBVasantP. A genetic algorithm optimized RNN-LSTM model for remaining useful life prediction of turbofan engine. Electronics2021; 10:285.
15.
WangLZhangZLongH, et al. Wind turbine gearbox failure identification with deep neural networks. IEEE Trans Ind Inform2017; 13:1360–1368.
16.
HuALianJXiangL. Early fault identification of wind turbine based on ACNN and bi-LSTM. Acta Energiae Solaris Sinica2021; 42(12): 143–149.
17.
JiaCKangKGaoW, et al. Fault prediction of electrohydraulic servo valve based on CNN + LSTM neural network. Chin Hydraul Pneum2020; 44(12): 173–181.
18.
HeQYinFWuX, et al. Fault prediction of wind turbine gearbox based on long short-term memory network. Acta Meteorologica Sin2020; 41(10): 1284–1290.
19.
LiWZhouBJiangD, et al. Fault prediction of power supply vehicle based on multi-state time series prediction learning. J Jilin Univ (Eng Technolo Ed)2020; 50:1532–1544.
20.
GeYChenWHuS, et al. Model based simulation and prediction of some key parameters of surge fault in engine. J Ordnance Equip Eng2021; 2021:194–200.
21.
ChenTChenWLiX, et al. Transformer fault prediction based on analysis of dissolved gas in oil. Electron Meas Technol2021; 44(22): 25–31.
22.
SunYLiuK. Failure rate of avionics system forecasting based on PSO-LSTM network. Aeronaut Sci Technol2021; 32(5): 17–22.
23.
ShiHShangYBaiX, et al. Early fault prediction method combining SWDAE and LSTM for rolling bearings based on Bayesian optimization. J Vibr Shock2021; 40(18): 286–297.
24.
HeimesFO. Recurrent neural networks for remaining useful life estimation. In: 2008 International conference on prognostics and health management, Denver, CO, 6–9 October 2008, pp.1–6.
25.
ManieniyanVVinodhiniGSenthilkumarR, et al. Wear element analysis using neural networks of a DI diesel engine using biodiesel with exhaust gas recirculation. Energy2016; 114:603–612.
26.
HanPEllefsenALLiG, et al. Fault prognostics using LSTM networks: application to marine diesel engine. IEEE Sens J2021; 21:25986–25994.
27.
MoosavianANajafiGGhobadianB, et al. Piston scuffing fault and its identification in an IC engine by vibration analysis. Appl Acoust2016; 102:40–48.
28.
DesbazeilleMRandallRBGuilletF, et al. Model-based diagnosis of large diesel engines based on angular speed variations of the crankshaft. Mech Syst Signal Process2010; 24:1529–1541.
29.
TongSYanqiaoCYuanZ. Fault prediction of marine diesel engine based on time series and support vector machine. In: 2020 International Conference on Intelligent Design (ICID), Xi’an, China, 11–13 December 2020, pp.75–81.
30.
SbarufattiCCorbettaMManesA, et al. Sequential Monte-Carlo sampling based on a committee of artificial neural networks for posterior state estimation and residual lifetime prediction. Int J Fatigue2016; 83:10–23.
31.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9:1735–1780.
32.
YangZYangDDyerC, et al. Hierarchical attention networks for document classification. In: Proceedings of the 2016 Conference of the North American chapter of the association for computational linguistics: human language technologies, San Diego, CA, Jun 2016, pp.1480–1489. Association for Computational Linguistics.
33.
PengWJinruiWShanqingY. Short-term load forecasting model based on attention-LSTM in electricity market. Power Syst Technol2019; 43(5): 1745–1751.
34.
KennedyJEberhartR. Particle swarm optimization. In: Proceedings of ICNN’95 - international conference on neural networks, Perth, WA, 27 November–1 December 1995, pp.1942–1948, vol.1944.
35.
ZhangYLiuTLiK, et al. Improved visual correlation analysis for multidimensional data. J Vis Lang Comput2017; 41:121–132.
36.
HuangZTianLXiangD, et al. Prediction of oil temperature variations in a wind turbine gearbox based on PCA and an SPC-dynamic neural network hybrid. J Tsinghua Univ (Sci Technol)2018; 58:539–546.
37.
CuiJXieL. Auto-correlated charts based on dynamic Bayesian model. J Beijing Univ Aeronaut Astronaut2007; 375–378.
38.
ZhaoHHuQLiZ. Failure prediction of wind turbine gearbox based on statistical process control. Power Syst Prot Control2012; 40:67–73.
