A novel vibration indicator to monitor gear natural fatigue pitting propagation

Feng, Ke; Ji, Jinchen; Ni, Qing; Yun, Hongguang; Zheng, Jinde; Liu, Zheng

doi:10.1177/14759217221142622

Cited by 18 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, train sensor data (such as swing and temperature data) are used to identify early signs of gear failure. In addition, they can be used to predict the remaining service life of the positive gear and thus avoid accidental downtime [ 28 ]. In addition, the normal operation of hydropower units is also strongly related to the working conditions of the bearings.…”

Section: Related Workmentioning

confidence: 99%

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Li,

Xu,

Guo

2024

Sensors

View full text Add to dashboard Cite

Hydropower units are the core equipment of hydropower stations, and research on the fault prediction and health management of these units can help improve their safety, stability, and the level of reliable operation and can effectively reduce costs. Therefore, it is necessary to predict the swing trend of these units. Firstly, this study considers the influence of various factors, such as electrical, mechanical, and hydraulic swing factors, on the swing signal of the main guide bearing y-axis. Before swing trend prediction, the multi-index feature selection algorithm is used to obtain suitable state variables, and the low-dimensional effective feature subset is obtained using the Pearson correlation coefficient and distance correlation coefficient algorithms. Secondly, the dilated convolution graph neural network (DCGNN) algorithm, with a dilated convolution graph, is used to predict the swing trend of the main guide bearing. Existing GNN methods rely heavily on predefined graph structures for prediction. The DCGNN algorithm can solve the problem of spatial dependence between variables without defining the graph structure and provides the adjacency matrix of the graph learning layer simulation, avoiding the over-smoothing problem often seen in graph convolutional networks; furthermore, it effectively improves the prediction accuracy. The experimental results showed that, compared with the RNN-GRU, LSTNet, and TAP-LSTM algorithms, the MAEs of the DCGNN algorithm decreased by 6.05%, 6.32%, and 3.04%; the RMSEs decreased by 9.21%, 9.01%, and 2.83%; and the CORR values increased by 0.63%, 1.05%, and 0.37%, respectively. Thus, the prediction accuracy was effectively improved.

show abstract

Section: Related Workmentioning

confidence: 99%

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Li,

Xu,

Guo

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Wear scar feature could analyze the morphology of the wear surface to determine the wear forms and characteristics of spherical contact friction pairs 38 . Besides, surface roughness S a was selected as the feature of surface morphology at the microlevel to represent the degradation process of the gear surface quantitatively 39 . However, this statistical parameter of roughness is limited by the instrument resolution and sampling length 40,41 .…”

Section: Experimental Setup and Designmentioning

confidence: 99%

“…38 Besides, surface roughness S a was selected as the feature of surface morphology at the microlevel to represent the degradation process of the gear surface quantitatively. 39 However, this statistical parameter of roughness is limited by the instrument resolution and sampling length. 40,41 In fact, the profiles of machined surfaces are random, multiscale, disordered, and self-affine in rough structures.…”

Section: Fractal Parameters Of Spur Gearsmentioning

confidence: 99%

Experimental‐based study of gear vibration characteristics incorporating the fractal topography of tooth surface

Qiu

Yuan

et al. 2023

Int Journal of Mech Sys Dyn

View full text Add to dashboard Cite

Microscopic roughness is inevitable on the gear meshing surface, which is also a key parameter affecting the dynamic response. The surface roughness exhibits self‐affine characteristics across multiscales. To explore the influence of surface fractal topography on the vibration amplitude of the gear system under different rotational speeds and loads, an experimental setup of spur gear transmission is devised. The fractal dimension and fractal roughness of the meshing surface are calculated by the power spectral density method. The relationships between gear response and fractal parameters are revealed experimentally. Results indicate that a rougher tooth surface, that is, a smaller fractal dimension or larger fractal roughness, corresponds to an intense vibration amplitude. The sensitivity of dynamic response to the tooth surface topography varies at different rotational speeds and loads. Under low speed and light load conditions, the fractal dimension and fractal roughness have a more obvious influence on the dynamic response of the gear transmission system. With the increase of speed and load, the macroworking conditions gradually become the main factor attributed to vibration amplitude.

show abstract

“…Monitoring the vibration signal is widely acknowledged as an effective approach for detecting structural defects in rotating machine components due to its ability to capture dynamic information. This sensing technology has been extensively employed in RCF and wear tests for detecting and diagnosing localised faults in rolling element bearings and gears [2,3]. In recent decades, acoustic emission (AE) has emerged as another notable sensing technology for structural health monitoring, specifically in the detection of early-stage damage.…”

Section: Introductionmentioning

confidence: 99%

Condition monitoring of pitting evolution using multiple sensing

Tian,

Wang,

Merk

et al. 2023

Proceedings of the International Conference on Condition Monito

View full text Add to dashboard Cite

Pitting on surfaces is a type of rolling contact fatigue (RCF) occurs in rolling-sliding contacts operating under mixed or boundary lubrication conditions. The early detection of pitting is of great importance due to its potential detrimental effects on the performance and reliability of machinery components, such as rolling element bearings and gears. This research aims to investigate the responses of multiple sensors to the progression of pitting and achieve early detection of pitting initiation. Experiments were conducted on a TE74 twin-disc tribometer to investigate the behaviour of bearing steel discs. Mild wear and pitting fatigue were obtained with specimens of different roughness combinations. During testing, vibration, acoustic emission (AE) and electrostatic (ES) data were recorded, and post-test signal analysis was conducted in both the time domain and frequency domain. After testing, the worn surfaces were examined to determine the mechanisms responsible for specific features seen in the sensor data.The presence of pitting in the near-surface region was observed, and its development was effectively monitored using the employed sensing techniques. The stages of running-in, pitting initiation, and pitting formation were identified through the analysis of timedomain parameters and frequency spectrums. Vibration signal analysis exhibited a more prominent indication of pitting formation, whereas AE and ES methods demonstrated an ability to detect the onset of pitting at an earlier stage.

show abstract

A novel vibration indicator to monitor gear natural fatigue pitting propagation

Cited by 18 publications

References 42 publications

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Swing Trend Prediction of Main Guide Bearing in Hydropower Units Based on MFS-DCGNN

Experimental‐based study of gear vibration characteristics incorporating the fractal topography of tooth surface

Condition monitoring of pitting evolution using multiple sensing

Contact Info

Product

Resources

About