In order to address the challenges associated with diagnosing weak faults in high-pressure common rail systems, this study proposes a weak fault diagnosis method that is based on the Pied Kingfisher Optimizer (PKO), Variational Mode Decomposition (VMD), and Long Short-Term Memory (LSTM) networks. A fitness function is constructed by combining the cross-correlation coefficient with the cross-entropy loss function to optimize the parameters of VMD and LSTM. A fault diagnosis model for high-pressure common rail systems is established. The efficiency of the proposed model is substantiated through the implementation of an experimental platform designed for high-pressure common rail fault diagnosis. The experimental results demonstrate the efficiency of the proposed method in diagnosing plunger cracks and leaks in high-pressure common rail systems, with an accuracy rate exceeding 95%. This indicates the method's high performance in identifying and diagnosing weak faults in high-pressure common rail systems.
ShiQHuY. Review on intelligent diagnosis technology of electronically controlled fuel injection system of ME diesel engine. Acad J Sci Technol2022; 1: 69–75.
2.
LiuYWangYZhaoH, et al. An early weak fault assessment method for rolling bearings based on adaptive frequency focusing and multi-level activation quantum-inspired neural network. Measurement2025; 255: 118039.
3.
PlaBDe la MorenaJBaresP, et al. A supervised machine learning technique for combustion diagnosis using a vibration sensor signal. Fuel2023; 343: 127869.
4.
YanHBaiHZhanX, et al. Combination of VMD mapping MFCC and LSTM: a new acoustic fault diagnosis method of diesel engine. Sensors2022; 22: 8325.
5.
ShiQHuYYanG. Fault diagnosis of ME marine diesel engine fuel injector with novel IRCMDE method. Polish Maritime Res2023; 30: 96–110.
6.
YunKChongYEnzheS, et al. A weak fault diagnosis scheme for common rail injector based on MGOA-MOMEDA and improved hierarchical dispersion entropy. Meas Sci Technol2021; 32: 025012.
7.
LiZJiangWZhangS, et al. A hydraulic pump fault diagnosis method based on the modified ensemble empirical mode decomposition and Wavelet Kernel extreme learning machine methods. Sensors2021; 21: 2599.
8.
ZhuYLiGWangR, et al. Intelligent fault diagnosis of hydraulic piston pump based on wavelet analysis and improved AlexNet. Sensors2021; 21: 549.
9.
DragomiretskiyKZossoD. Variational mode decomposition. IEEE Trans Signal Process2014; 62: 531–544.
10.
DaiXYiKWangF, et al. Bearing fault diagnosis based on POA-VMD with GADF-swin transformer transfer learning network. Measurement2024; 238: 115328.
11.
SunYCaoYLiP, et al. Vibration-based fault diagnosis for railway point machines using VMD and multiscale fluctuation-based dispersion entropy. Chin J Electron2024; 33: 803–813.
12.
BiXLinJTangD, et al. VMD-KFCM algorithm for the fault diagnosis of diesel engine vibration signals. Energies2020; 13: 228.
13.
WuYDaiJYangX, et al. The fault diagnosis of rolling bearings based on FFT-SE-TCN-SVM. Actuators14(3): 152.
14.
RaveendranRDevikaKSubramanianSC. Learning-based fault diagnosis of air brake system using wheel speed data. Proc Inst Mech Eng Part D: J Autom Eng2022; 236: 2598–2609.
15.
DuanHYinXKouH, et al. Regression prediction of hydrogen enriched compressed natural gas (HCNG) engine performance based on improved particle swarm optimization back propagation neural network method (IMPSO-BPNN). Fuel2023; 331: 125872.
16.
MaSShiSZhangY, et al. A high-precision method for detecting rolling bearing fault is in unmanned aerial vehicle based on improved 1DCNN-informer model. Measurement2025; 256: 118200.
17.
MaSZhouXJiangH, et al. A novel intelligent fault diagnosis method for commercial vehicle pneumatic braking system. Proc Inst Mech Eng Part D: J Autom Eng2025; 239: 3370–3381.
18.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9: 1735–1780.
19.
GuanJWangXLvX, et al. Multidimensional analysis and performance prediction of heavy-duty gas turbine based on actual operational data. Appl Therm Eng2023; 234: 121280.
20.
JiangPWangYWuS, et al. Fault diagnosis of wind turbine pitch bearings via transfer learning and an improved residual network. Measurement2025; 254: 117985.
21.
NeerajMathew JBeheraRK. EMD-att-LSTM: a data-driven strategy combined with deep learning for short-term load forecasting. J Mod Power Syst Clean Energy2022; 10: 1229–1240.
22.
BouaoudaAHashimFASayoutiY, et al. Pied kingfisher optimizer: a new bio-inspired algorithm for solving numerical optimization and industrial engineering problems. Neural Comput Appl2024; 36: 15455–15513.
23.
GuoM. Long-short term memory modeling and performance analysis of extended-state Kalman filter-based energy-saving model predictive control for supercritical unit. Appl Therm Eng2025; 272: 126202.
24.
WangBGuoYZhangZ, et al. Developing and applying OEGOA-VMD algorithm for feature extraction for early fault detection in cryogenic rolling bearing. Measurement2023; 216: 112908.
25.
KeshunYPuzhouWPengH, et al. A sound-vibration physical-information fusion constraint-guided deep learning method for rolling bearing fault diagnosis. Reliab Eng Syst Saf2025; 253: 110556.
26.
WangLWeiC. Study on the diagnosis of transformer failure diagnosis based on the BWODO-VMD-LSTM model. In: 2023 3rd international conference on new energy and power engineering (ICNEPE), Huzhou, China, 24–26 November 2023, pp. 273–279.
27.
WangXWangYYuanP, et al. An adaptive daily runoff forecast model using VMD-LSTM-PSO hybrid approach. Hydrol Sci J2021; 66: 1488–1502.
28.
FangMZhangFYangY, et al. The influence of optimization algorithm on the signal prediction accuracy of VMD-LSTM for the pumped storage hydropower unit. J Energy Storage2024; 78: 110187.
29.
JiaXJiancunHCiweiQ, et al. Fault diagnosis of high-pressure fuel pump based on parameter optimization VMD and dispersion entropy. Trans CSICE2023; 41: 166–174.
30.
XueSGuiHQinX, et al. Fault diagnosis of rolling bearing based on WOA-VMD-LSTM. In: 2024 6th international conference on intelligent control, measurement and signal processing (ICMSP), Xi’an, China, 29 November–1 December 2024, pp. 203–208.
