Fault diagnosis method of wheel diameter difference based on stacked autoencoder and multiple kernel learning

Sui, Shunqi; Wang, Kaiyun; Ling, Liang; Chen, Shiqian; Bo, Xie

doi:10.1177/10775463221147156

Cited by 2 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the track random irregularity changes greatly, the impulse signal appears for the wheelset with the WDD. The influence can be noted more easily for the larger WDD [21]. So, the subband with a bigger SESGI can be selected for the fault diagnosis of the WDD.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…For all subbands, the sequence of RMS and SESGI can be expressed as [R 1 , R 2 ,…, R j ] and [S 1 , S 2 ,…, S j ] respectively. The standard deviation of the sequence is used to generate the weight of RMS or SESGI, and the new fusion index FI can be defined according to equation (21). It can be found that FI can be considered as a compromise between the energy factor and the impulse factor.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…It is crucial to identify the WDD condition of the wheelset accurately and timely. At present, the condition monitoring of the WDD mostly depends on manual measurement by the operators in regular [21,22], which is time-consuming and unreliable. Therefore, the detection of the WDD, especially in quantitative assessment, has become an urgent problem.…”

Section: Problem Statementmentioning

confidence: 99%

See 2 more Smart Citations

Fault detection and quantitative assessment of wheel diameter difference based on ensemble adaptive tunable Q-factor wavelet transform and mixed kernel principal component analysis

Sui,

Wang,

Chen

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Tread wear is inevitable for railway vehicles. Because of the complicated railway condition, the wear rates of the two wheels of a wheelset are usually unequal, which leads to the wheel diameter difference (WDD). The WDD shortens the service life of the wheelset and deteriorates the dynamic performance of railway vehicles. Therefore, it has long been desired to monitor and quantify the WDD condition. However, influenced by the random irregularity, the effective vibration features induced by the WDD may be completely submerged in noise. In this paper, an adaptive TQWT decomposition method is proposed for denoise and feature enhancement. In this method, a new evaluation index is constructed and used to determine parameters. The influence of the WDD on the vibration of the wheelset can be more obvious after denoised by the adaptive TQWT decomposition. Mixed kernel principal component analysis is introduced into the condition monitoring and quantitative assessment of the WDD. By calculating the Hoteling’s T 2 and SPE statistics, control charts are employed to identify and assess the WDD conditions quantitatively in conjunction with the corresponding control limits. The effectiveness of the proposed method is validated by the simulation and experimental study. For the experimental datasets, the proposed method gives the average fault detection rate (FDR), false alarm rate (FAR), false alarm rate (PA) of 92.74%, 2.23%, 97.47% for the T 2 statistic and the average FDR, FAR, PA of 96.57%, 2.60%, 97.29% for the SPE statistic. The results show that the proposed method can effectively monitor the WDD conditions.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

Section: The Proposed Methodsmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Fault detection and quantitative assessment of wheel diameter difference based on ensemble adaptive tunable Q-factor wavelet transform and mixed kernel principal component analysis

Sui,

Wang,

Chen

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…As a key component in urban rail vehicles, once the axle-box bearing fails, it will lead to several accidents and even impact the operation safety of vehicles (Yu et al, 2022a). Axle-box bearings are the most frequently damaged component in urban rail vehicles (Zhang et al, 2022; Yu et al, 2022b; Sui et al, 2022). In accordance, it is urgent to improve the dynamic performance of axle-box bearings, such as nice stability, small vibration, and long service life.…”

Section: Introductionmentioning

confidence: 99%

Skidding characteristics of urban rail vehicle axle-box bearings considering surface waviness on races

Guo

Chen

et al. 2023

Journal of Vibration and Control

View full text Add to dashboard Cite

As one of the core transmission components, axle-box bearings have been widely applied in urban rail vehicles and played a crucial role in their safe and stable operation. No matter in the starting and stopping stage or stable operation stage of the vehicle, the skidding phenomenon in axle-box bearings exists and impacts their own dynamic characteristics. Furthermore, as one of the main shape errors of the bearing surface, waviness may cause fluctuations for skidding characteristics of axle-box bearings. This study investigates the skidding dynamic analysis of axle-box bearings, taking into account race surface waviness. Firstly, a dynamics model for double-row cylindrical roller bearings is established, considering the cage flexibility and friction forces between different components. Then, this model is coupled with a three-dimension vehicle–track model, allowing for more precise dynamic simulation of axle-box bearings under actual running conditions. Furthermore, an excitation related to race surface waviness is added to the coupling model through time-varying displacement and contact stiffness. At last, the influence of race surface waviness on skidding characteristics of axle-box bearings is analyzed. The effectiveness of the proposed model is validated through theoretical analysis and field tests. Simulation results demonstrate that race surface waviness can impact the cage and roller slip ratio of axle-box bearings. Overall, this study provides valuable insights into the skidding dynamic analysis of axle-box bearings, highlighting the importance of considering race surface waviness in designing and maintaining axle-box bearings.

show abstract

Fault diagnosis method of wheel diameter difference based on stacked autoencoder and multiple kernel learning

Cited by 2 publications

References 25 publications

Fault detection and quantitative assessment of wheel diameter difference based on ensemble adaptive tunable Q-factor wavelet transform and mixed kernel principal component analysis

Fault detection and quantitative assessment of wheel diameter difference based on ensemble adaptive tunable Q-factor wavelet transform and mixed kernel principal component analysis

Skidding characteristics of urban rail vehicle axle-box bearings considering surface waviness on races

Contact Info

Product

Resources

About