Deep Focus Parallel Convolutional Neural Network for Imbalanced Classification of Machinery Fault Diagnostics

Duan, Andongzhe; Guo, Liang; Gao, Hongli; Wu, Xiangdong; Dong, Xun

doi:10.1109/tim.2020.2998233

Cited by 78 publications

(19 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the normal vibration data and the time-domain feature of rolling bearings satisfies Gaussian distribution, the Pauta criterion can be used to judge the fault data [23]. Root mean square is used as the feature to calculate the fault threshold in this study.…”

Section: Fault Diagnosis Of Xjtu-sy Bearing Datasetsmentioning

confidence: 99%

Rolling Bearing Fault Diagnosis Based on SVM Optimized with Adaptive Quantum DE Algorithm

Sun

et al. 2022

Shock and Vibration

View full text Add to dashboard Cite

In order to optimize traditional fault diagnosis models for practical applications, a fault diagnosis model based on support vector machines optimized with the adaptive quantum differential evolution of (AQDE-SVM) is proposed in this study. First, the traditional differential evolution is rewritten based on real number encoded into a qubit encoding. Second, this study proposes an adaptive quantum rotation gate and uses this gate to update the probability amplitude of the qubits. Finally, compared with quantum genetic algorithm support vector machines (QGA-SVM) and differential evolution-support vector machines (DE-SVM), etc., the results show that the algorithm proposed in this study has a higher diagnosis accuracy and shorter running time, providing great practical engineering value in the application of rolling bearing fault diagnosis.

show abstract

Section: Fault Diagnosis Of Xjtu-sy Bearing Datasetsmentioning

confidence: 99%

Rolling Bearing Fault Diagnosis Based on SVM Optimized with Adaptive Quantum DE Algorithm

Sun

et al. 2022

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…In terms of wavelet transform, in view of the shortcomings of traditional singular value, Hua [31] an enhanced SVD is introduced in paper to detect the bearing fault. In terms of deep learning, In view of the shortcomings of traditional fault diagnosis methods based on time domain vibration analysis, which require complicated calculations of feature vectors, Duan [32] proposed a learning framework called deep focus parallel CNN to overcome the shortcomings of traditional fault diagnosis. These method provided an efficient means for troubleshooting of rotating equipment.…”

Section: B Fault Diagnosismentioning

confidence: 99%

Fault Diagnosis Method Based on Encoding Time Series and Convolutional Neural Network

Xiong

Zhu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In view of the shortcomings of traditional fault diagnosis methods based on time domain vibration analysis, which require complicated calculations of feature vectors, and are over-dependent on a prior diagnosis knowledge, effort for the design of the feature extraction algorithms, and have limited ability to extract the complex relationships in fault signals, in this paper we propose a convolutional neural network (CNN) framework for machine health monitoring based on the encoding of one-dimension (1-D) time series to two-dimension (2-D) images. This paper defines a new Gram matrix and through the Python programming environment, we emulate the new Gram matrix in 2-D images, thus feature extraction and recognition can be performed by CNNs. The proposed method which is tested on two datasets, including multi-stage centrifugal fan dataset for our lab, motor bearing dataset for Case Western Reserve University, has achieved prediction average accuracy of 94.07% and 96.28%, respectively. The results have been compared with other deep learning and traditional methods, including Recurrent neural network (RNN), Support Vector Machines (SVM), Multi-Genetic algorithm, shallow CNN and BP neural network. The results show that the method can improve fault diagnosis accuracy in an effective way and stability than other advanced techniques. INDEX TERMS fault diagnosis, encoding, convolutional neural network, petrochemical unit.

show abstract

“…Data-level methods include oversampling for small population classes and undersampling for large population classes. State-of-the-art research favors the former [ 15 ]. Regarding the oversampling method, random oversampling (RAMO) is the simplest oversampling technique, but it is prone to overfitting [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

“…For algorithm-level methods, cost-sensitive learning is the mainstream way to deal with imbalanced classification problems [ 15 ]. It is a learning paradigm that allocates the cost of misclassification to the categories involved in the classification task.…”

Section: Introductionmentioning

confidence: 99%

Unbalanced Fault Diagnosis Based on an Invariant Temporal-Spatial Attention Fusion Network

Liu

Yang

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The health status of mechanical bearings concerns the safety of equipment usage. Therefore, it is of crucial importance to monitor mechanical bearings. Currently, deep learning is the mainstream approach for this task. However, in practical situations, the majority of fault samples have the issue of severe class unbalancing, which renders conventional deep learning inapplicable. Targeted at this issue, this paper proposes an invariant temporal-spatial attention fusion network called ITSA-FN for bearing fault diagnosis under unbalanced conditions. First, the proposed method utilizes the invariant temporal-spatial attention representation section, which consists of a pretrained convolutional auto-encoder model, a convolutional block attention module, and a long short-term memory network, to extract independent features and invariant features of spatial-temporal characteristics from input signals. Then, a multilayer perceptron is used to fuse and infer from the extracted features and design a new loss function from the focal loss for network training. Finally, this article validates proposed model’s effectiveness through comparative experiments, ablation studies, and generalization performance experiments.

show abstract

Deep Focus Parallel Convolutional Neural Network for Imbalanced Classification of Machinery Fault Diagnostics

Cited by 78 publications

References 36 publications

Rolling Bearing Fault Diagnosis Based on SVM Optimized with Adaptive Quantum DE Algorithm

Rolling Bearing Fault Diagnosis Based on SVM Optimized with Adaptive Quantum DE Algorithm

Fault Diagnosis Method Based on Encoding Time Series and Convolutional Neural Network

Unbalanced Fault Diagnosis Based on an Invariant Temporal-Spatial Attention Fusion Network

Contact Info

Product

Resources

About