A grouping-attention convolutional neural network for performance degradation estimation of high-speed train lateral damper

Ren, Junxiao; Jin, Weidong; Wu, Yunpu; Sun, Zhanquan

doi:10.1007/s10489-022-03368-9

Cited by 3 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 1D-DSC-Module consists of three one-dimensional depthwise separable convolutions (1D-DSCNN) [ 21 ] and a pointwise convolution (PW-CNN). This design of the 1D-DSC-Module referred to existing research results of high-speed train bogie performance degradation estimations [ 2 , 9 ]. The specific structure and hyperparameters of the 1D-DSC-Module are shown in Figure 12 ; the module has low computational complexity and multi-scale feature learning capability.…”

Section: Methodsmentioning

confidence: 99%

“…However, during the long-term service of the train, the bogie is subject to vibration and impact caused by wheel–rail contact, and the damper components on the bogie inevitably suffer from performance degradation and failure. Therefore, detecting the health condition of the bogie to maximize its operating condition at all times is an important means to ensure the safe operation of the train [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, current studies are usually carried out in a data-driven manner. The high-speed train vibration signal is a nonlinear and complex signal [ 1 ], and the metrics obtained by manual feature extraction methods, such as information entropy, cannot accurately achieve performance degradation estimations [ 2 ]. Deep learning algorithms can avoid the process of manual feature selection and learn the key information contained in the signal more effectively and adaptively, which is a promising alternative to the traditional information theory and signal processing methods for processing complex signals and has achieved a large number of valuable research results.…”

Section: Introductionmentioning

confidence: 99%

“…In the research on performance degradation estimations of high-speed train bogies, Ren et al [ 2 ] proposed a novel grouping-attention convolutional neural network to implement performance degradation estimations of lateral dampers for high-speed trains. The model fully considers the differences and similarities between different channels of vibration signals, and the signals of different channels are grouped as the input of the model, which improves the efficiency of key feature learning and greatly reduces the error of performance degradation estimations.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Research on Performance Degradation Estimation of Key Components of High-Speed Train Bogie Based on Multi-Task Learning

Ren

Jin²,

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

The safe and comfortable operation of high-speed trains has attracted extensive attention. With the operation of the train, the performance of high-speed train bogie components inevitably degrades and eventually leads to failures. At present, it is a common method to achieve performance degradation estimation of bogie components by processing high-speed train vibration signals and analyzing the information contained in the signals. In the face of complex signals, the usage of information theory, such as information entropy, to achieve performance degradation estimations is not satisfactory, and recent studies have more often used deep learning methods instead of traditional methods, such as information theory or signal processing, to obtain higher estimation accuracy. However, current research is more focused on the estimation for a certain component of the bogie and does not consider the bogie as a whole system to accomplish the performance degradation estimation task for several key components at the same time. In this paper, based on soft parameter sharing multi-task deep learning, a multi-task and multi-scale convolutional neural network is proposed to realize performance degradation state estimations of key components of a high-speed train bogie. Firstly, the structure takes into account the multi-scale characteristics of high-speed train vibration signals and uses a multi-scale convolution structure to better extract the key features of the signal. Secondly, considering that the vibration signal of high-speed trains contains the information of all components, the soft parameter sharing method is adopted to realize feature sharing in the depth structure and improve the utilization of information. The effectiveness and superiority of the structure proposed by the experiment is a feasible scheme for improving the performance degradation estimation of a high-speed train bogie.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%