A rolling bearing fault diagnosis method using novel lightweight neural network

He, Deqiang; Liu, Chenyu; Yan-jun, Chen; Jin, Zhenzhen; Li, Xianwang; Shan, Sheng

doi:10.1088/1361-6501/ac1a5e

Cited by 19 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, machine learning (ML) based big data driven methods have played an important role in developing a predictive capability for material properties and lightweight design based on extensive experimental evidence [20][21][22][23] . Indeed, support vector machine (SVM), Random-Forest (RF), Gaussian process regression (GPR), shallow neural network (SNN), deep neural network (DNN), Linear regression (LR), and artificial neural networks (ANN) have all been found to make accurate life and crack propagation predictions, based on fatigue-related data for conventionally processed metals and alloys [24][25][26][27][28][29][30][31][32] .…”

Section: Introductionmentioning

confidence: 99%

The potency of defects on fatigue of additively manufactured metals

Peng

Qian

et al. 2022

International Journal of Mechanical Sciences

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

The potency of defects on fatigue of additively manufactured metals

Peng

Qian

et al. 2022

International Journal of Mechanical Sciences

View full text Add to dashboard Cite

“…Pengfei et al [26] Despite the long-term development of deep learning, the development of CNN has been a major milestone in the development of deep learning. Early fully connected networks have too many parameters, especially for large images, and were unable to distinguish objects in different positions [27][28][29][30]. The CNN were developed to overcome these limitations, and it has two main features.…”

Section: Introductionmentioning

confidence: 99%

Non-negative wavelet matrix factorization-based bearing fault intelligent classification method

Dong

Zhao

Cui

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

With the increasing number of classifications in bearing fault diagnosis, it is difficult to achieve accurate results based on the original signal or time-frequency features calculated by the time-frequency analysis method, such as the continuous wavelet transform. Aiming at this issue, a time-frequency joint metric features extraction technique named non-negative wavelet matrix factorization (NWMF) is developed to apply in bearing fault intelligent classification. In the proposed technique, the NWMF is used to calculate bearing fault-related internal core information from the original time-frequency spectrum, as a result, the time-frequency characteristic dimension decrease, and the computational efficiency increase. In addition, a novel convolutional neural network model is developed to identify locations and sizes of fault bearing based on the calculated internal core information. For verifying the effectiveness of the proposed method, the types of bearing faults in the experiments are set up to fifteen, the results and comparative analysis reveal that the feasibility and superiority of the proposed method are much better than the other traditional machine learning methods and original deep learning methods, such as the support vector machine, random forest and residual neural network.

show abstract

“…This led to the creation of the ResNet series [ 31 , 32 ]. ResNet has been used for fault diagnosis in industrial manufacturing [ 33 , 34 ], rolling bearings [ 35 ], and rotating machinery [ 36 ]. The increases in network depth and width facilitated by the ResNet architecture led to tremendous improvements in CNN performance.…”

Section: Introductionmentioning

confidence: 99%

Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks

Yang

Huang

Lin

2023

Sensors

View full text Add to dashboard Cite

Fused deposition modeling (FDM) is a form of additive manufacturing where three-dimensional (3D) models are created by depositing melted thermoplastic polymer filaments in layers. Although FDM is a mature process, defects can occur during printing. Therefore, an image-based quality inspection method for 3D-printed objects of varying geometries was developed in this study. Transfer learning with pretrained models, which were used as feature extractors, was combined with ensemble learning, and the resulting model combinations were used to inspect the quality of FDM-printed objects. Model combinations with VGG16 and VGG19 had the highest accuracy in most situations. Furthermore, the classification accuracies of these model combinations were not significantly affected by differences in color. In summary, the combination of transfer learning with ensemble learning is an effective method for inspecting the quality of 3D-printed objects. It reduces time and material wastage and improves 3D printing quality.

show abstract

A rolling bearing fault diagnosis method using novel lightweight neural network

Cited by 19 publications

References 28 publications

The potency of defects on fatigue of additively manufactured metals

The potency of defects on fatigue of additively manufactured metals

Non-negative wavelet matrix factorization-based bearing fault intelligent classification method

Three-Dimensional Printing Quality Inspection Based on Transfer Learning with Convolutional Neural Networks

Contact Info

Product

Resources

About