An effective crack position diagnosis method for the hollow shaft rotor system based on the convolutional neural network and deep metric learning

Jin, Yuhong; Hou, Lei; Chen, Yushu; Lu, Zhenyong

doi:10.1016/j.cja.2021.09.010

Cited by 14 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, there was a slight fluctuation in the whole training curve, which cated that the whole training process was very stable. T-SNE is a nonlinear dimension reduction algorithm that overcomes the shortc ings of data congestion and the poor visualization effect after dimensionality reduc by other methods [34]. It effectively realizes data dimensionality reduction and data v alization by mapping a low-dimensional manifold structure from high-dimensional d Figure 11a,b shows the dimension-reduced visualization results of impact position be and after training in the training set.…”

Section: Multi-task 2d-cnn Trainingmentioning

confidence: 99%

An Improved Impact Damage Monitoring Method for High-Speed Trains Using Lamb Waves and Multi-Task Learning

Yang,

Gan,

Zhang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

High-speed trains may be subjected to various forms of physical impacts during long-term operation, causing structural damage and endangering driving safety. Therefore, impact damage monitoring remains a daunting challenge for the stable operation of high-speed train structures. The existing methods cannot simultaneously detect the location and severity of impact damage, which poses challenges to structural integrity assessment and preventive maintenance. This article proposes an impact damage monitoring method based on multi-task 2D-CNN. Sensor data fusion is performed using a 2D image processing method to convert a 1D impact damage signal into a 2D grayscale image. The fused grayscale image contains information related to the location and severity of impact damage. A damage detection framework was established using multi-task 2D-CNN for feature extraction, impact location classification, and impact energy quantification. This model can learn the commonalities and characteristics of each task by sharing network structure and parameters and can effectively improve the accuracy of each task. Compared with single-task learning, multi-task learning performs better on the metrics of the impact location task recognizing the impact energy task and reduces the training time by 30.83%. With a reduced number of samples, the performance of multi-task learning is more stable and can still effectively identify the location and severity of impact damage.

show abstract

Section: Multi-task 2d-cnn Trainingmentioning

confidence: 99%

An Improved Impact Damage Monitoring Method for High-Speed Trains Using Lamb Waves and Multi-Task Learning

Yang,

Gan,

Zhang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In [32], Jin et al worked on the classification of a cracked hollow shaft according to the crack location. The amplitude-frequency responses of the defective rotary machine were introduced as the input data; in addition, CNNs and deep metric learning procedures were utilized for the classification.…”

Section: State Of the Artmentioning

confidence: 99%

Unbalanced, cracked, and misaligned rotating machines: a comparison between classification procedures throughout the steady-state operation

Rezazadeh

Luca

Perfetto

2022

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

This article compares two intelligent methods for automatic detection of unbalancing, cracks, and parallel misalignment in rotary machines. The finite element method is used to model the faults in a rotating system. The modeled system then operates virtually under different conditions in the steady-state operation; the vibrational responses are calculated numerically. To compare the accuracy of different manners in the classification of defective systems, firstly, four distinct types of features, i.e., statistical, frequency, time–frequency, and uncertainty are exploited. The T test process is utilized to test the extracted characteristics; the unreliable features are removed from feature vectors, then the remained ones are used in four supervised machine learning classifiers, i.e., support vector machine, k-nearest neighbors, Naive Bayes, and decision trees. In the following, as the convolution neural networks (CNNs) approach, the persistence spectrums of raw signals are plotted, and these graphs are introduced as input data. Comparing results of the different classification methods, it has been observed that although CNNs based on persistence spectrum graphs are computationally heavy and time-consuming, they provide more accurate results than the other classifiers. The results show that the proposed approach for rotor fault detection is effective, accurate, and robust and that it has promise for real engineering applications.

show abstract

“…Lu et al [23] analyzed the dynamic behavior of the dual-rotor system with the misalignment, the rubbing, and the coupling fault, respectively. Jin et al [24] developed an approach that was applied for identifying the position of the cracks of the hollow rotor structure by CNN-C. Han et al [25] presented a nonlinear joint element to study the dynamical responses of the bolt-connected rotor structure with the skewness of disk. Chen et al [26] proposed a novel HB-AFT approach to investigate the vibrational responses of the rotor-bearing-casing system, and the approach is more efficient than the traditional method.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Analysis of Three-Rotor System with Hollow Shaft under Clutch Misalignment

Nan,

Wang,

2024

Aerospace

View full text Add to dashboard Cite

Rotor system of aviation engines is often made of multiple rotors connected by the clutch. Due to manufacturing and assembly errors, there is a clutch misalignment, including the parallel misalignment and the angle misalignment. This misalignment produces additional torque in the operation of the system, leading to an abnormal increase in its oscillation, which causes the rubbing between the stator and the rotor. The rub-collision poses great harm to the safety and stability of the aero-engine. The analytical model of the rotor system with misalignment and rubbing faults is established, and the influence of the rotational speed, the misalignment, and the rubbing on the nonlinear characteristics of the rotor is investigated. Considering the nonlinear Hertz contact force and bearing gap, the model of the inter-shaft bearing is built; the parallel and angle misalignments of clutch are taken into account to analyze the characteristic frequency of the faults. For raising the thrust-to-weight ratio of aviation engines, the hollow shaft is often adopted, and the effect of the wall thickness for the shaft on the nonlinear vibration of the system is also investigated. It is innovative to study the transfer mechanism from wall thickness to the nonlinear vibrational responses of the overall structure. The result indicates that, with the increase in the wall thickness of the shaft, the second critical rotating speed increases, while the first critical rotating speed is almost unchanged. The characteristic frequencies for the three-rotor system with coupling faults are obtained. Despite intuition, the parallel misalignment can inhibit rub-collision vibration to a certain extent. The research has important reference values for the fault recognition and structural optimization of the three-rotor system.

show abstract

An effective crack position diagnosis method for the hollow shaft rotor system based on the convolutional neural network and deep metric learning

Cited by 14 publications

References 34 publications

An Improved Impact Damage Monitoring Method for High-Speed Trains Using Lamb Waves and Multi-Task Learning

An Improved Impact Damage Monitoring Method for High-Speed Trains Using Lamb Waves and Multi-Task Learning

Unbalanced, cracked, and misaligned rotating machines: a comparison between classification procedures throughout the steady-state operation

Dynamic Analysis of Three-Rotor System with Hollow Shaft under Clutch Misalignment

Contact Info

Product

Resources

About