Intelligent fault diagnosis of train axle box bearing based on parameter optimization VMD and improved DBN

Jin, Zhenzhen; He, Deqiang; Wei, Zexian

doi:10.1016/j.engappai.2022.104713

Cited by 166 publications

(71 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although these two parameters can be directly pre-set by experience or experiments, the method has the drawback of blindness and is difficult to obtain excellent performance of VMD. Consequently, researchers usually utilize some intelligent optimization algorithms to determine the values of the two parameters, such as the genetic algorithm [ 24 , 25 ], particle swarm optimization [ 16 , 26 ], differential search algorithm [ 27 ], Archimedes optimization algorithm [ 28 ], grey wolf optimization [ 29 , 30 ], whale optimization algorithm [ 31 ], cuckoo search algorithm [ 32 ], sparrow search algorithm [ 33 ], and so on.…”

Section: Introductionmentioning

confidence: 99%

Rolling Bearing Fault Diagnosis Based on Successive Variational Mode Decomposition and the EP Index

Guo

Yang

Jiang

et al. 2022

Sensors

View full text Add to dashboard Cite

Rolling bearing is an important part guaranteeing the normal operation of rotating machinery, which is also prone to various damages due to severe running conditions. However, it is usually difficult to extract the weak fault characteristic information from rolling bearing vibration signals and to realize a rolling bearing fault diagnosis. Hence, this paper offers a rolling bearing fault diagnosis method based on successive variational mode decomposition (SVMD) and the energy concentration and position accuracy (EP) index. Since SVMD decomposes a vibration signal of a rolling bearing into a number of modes, it is difficult to select the target mode with the ideal fault characteristic information. Comprehensively considering the energy concentration degree and frequency position accuracy of the fault characteristic component, the EP index is proposed to indicate the target mode. As the balancing parameter is crucial to the performance of SVMD and must be set properly, the line search method guided by the EP index is introduced to determine an optimal value for the balancing parameter of SVMD. The simulation and experiment results demonstrate that the proposed SVMD method is effective for rolling bearing fault diagnosis and superior to the variational mode decomposition (VMD) method.

show abstract

Section: Introductionmentioning

confidence: 99%

Rolling Bearing Fault Diagnosis Based on Successive Variational Mode Decomposition and the EP Index

Guo

Yang

Jiang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In summary, we draw the following conclusions from the literature: (i) compared with the first category of feature extraction approaches, mode components-based feature extraction approaches have better separability and classification performance; and (ii) within the second category of feature extraction approaches, the entropy-based feature is better than other features—VMD and CEEMDAN have more advantages for S-NS feature extraction than EMD and EEMD. However, a limitation of VMD is that its influence parameters need to be set in advance [ 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

Optimized Ship-Radiated Noise Feature Extraction Approaches Based on CEEMDAN and Slope Entropy

Tang

Jiao

2022

Entropy

View full text Add to dashboard Cite

Slope entropy (Slopen) has been demonstrated to be an excellent approach to extracting ship-radiated noise signals (S-NSs) features by analyzing the complexity of the signals; however, its recognition ability is limited because it extracts the features of undecomposed S-NSs. To solve this problem, in this study, we combined complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to explore the differences of Slopen between the intrinsic mode components (IMFs) of the S-NSs and proposed a single-IMF optimized feature extraction approach. Aiming to further enhance its performance, the optimized combination of dual-IMFs was selected, and a dual-IMF optimized feature extraction approach was also proposed. We conducted three experiments to demonstrate the effectiveness of CEEMDAN, Slopen, and the proposed approaches. The experimental and comparative results revealed both of the proposed single- and dual-IMF optimized feature extraction approaches based on Slopen and CEEMDAN to be more effective than the original ship signal-based and IMF-based feature extraction approaches.

show abstract

“…Common deep learning algorithms include deep belief networks (DBNs), long-and short-term memory, and convolutional neural networks. Jin et al [14] managed to improve the deep confidence network by means of the gray wolf optimization algorithm, thus resolving parameter setting problems. In this case, early bearing faults could be meticulously monitored.…”

Section: Introductionmentioning

confidence: 99%

Multi-Source Information Fusion Fault Diagnosis for Gearboxes Based on SDP and VGG

Chen

Liu

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

A decision-level approach using multi-sensor-based symmetry dot pattern (SDP) analysis with a Visual Geometry Group 16 network (VGG16) fault diagnosis model for multi-source information fusion was proposed to realize accurate and comprehensive fault diagnosis of gearbox gear teeth. Firstly, the SDP technique was used to perform a feature-level fusion of the fault states of gearbox gear collected by multiple sensors, which could initially visualize the vibration states of the gear teeth in different states. Secondly, the SDP images obtained were combined with the deep learning VGG16. In this way, the local diagnostic results of each sensor can be easily obtained. Finally, the local diagnostic results of each sensor were combined with the DS evidence theory to achieve decision-level fusion, which can better realize comprehensive fault detection for gearbox gear teeth. Before fusion, the accuracies of the three sensors were 96.43%, 93.97%, and 93.28%, respectively. When sensor 1 and sensor 2 were fused, the accuracy reached 99.93%, which is 3.52% and 6.34% better than when using sensors 1 and 2, respectively, alone. When sensor 1 and sensor 3 were fused, the accuracy reached 99.96%, marking an improvement of 3.36% and 6.85% over individual use of sensors 1 and 3, respectively. When sensor 2 and sensor 3 were fused, the accuracy reached 99.40%, which is 5.78% and 6.56% better than individual use of sensors 2 and 3, respectively. When the three sensors were fused simultaneously, the accuracy reached 99.98%, which is 3.68%, 6.40%, and 7.18% better than individual use of sensors 1, 2, and 3, respectively.

show abstract

Intelligent fault diagnosis of train axle box bearing based on parameter optimization VMD and improved DBN

Cited by 166 publications

References 18 publications

Rolling Bearing Fault Diagnosis Based on Successive Variational Mode Decomposition and the EP Index

Rolling Bearing Fault Diagnosis Based on Successive Variational Mode Decomposition and the EP Index

Optimized Ship-Radiated Noise Feature Extraction Approaches Based on CEEMDAN and Slope Entropy

Multi-Source Information Fusion Fault Diagnosis for Gearboxes Based on SDP and VGG

Contact Info

Product

Resources

About