Deep multi-scale convolutional transfer learning network: A novel method for intelligent fault diagnosis of rolling bearings under variable working conditions and domains

Bo, Zhao; Zhang, Xianmin; Zhan, Zhenhui; Pang, Shuiquan

doi:10.1016/j.neucom.2020.04.073

Cited by 135 publications

(53 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a useful technology, research on the multiscale structure is increasing gradually. Zhao et al [40] present a novel transfer learning framework based on a deep multi-scale convolutional neural network (MSCNN). MSCNN is applied to the intelligent fault diagnosis of rolling bearings and has excellent performance.…”

Section: Multi-scale Structurementioning

confidence: 99%

AMS-Net: An Attention-Based Multi-Scale Network for Classification of 3D Terracotta Warrior Fragments

et al. 2021

View full text Add to dashboard Cite

As an essential step in the restoration of Terracotta Warriors, the results of fragments classification will directly affect the performance of fragments matching and splicing. However, most of the existing methods are based on traditional technology and have low accuracy in classification. A practical and effective classification method for fragments is an urgent need. In this case, an attention-based multi-scale neural network named AMS-Net is proposed to extract significant geometric and semantic features. AMS-Net is a hierarchical structure consisting of a multi-scale set abstraction block (MS-BLOCK) and a fully connected (FC) layer. MS-BLOCK consists of a local-global layer (LGLayer) and an improved multi-layer perceptron (IMLP). With a multi-scale strategy, LGLayer can parallel extract the local and global features from different scales. IMLP can concatenate the high-level and low-level features for classification tasks. Extensive experiments on the public data set (ModelNet40/10) and the real-world Terracotta Warrior fragments data set are conducted. The accuracy results with normal can achieve 93.52% and 96.22%, respectively. For real-world data sets, the accuracy is best among the existing methods. The robustness and effectiveness of the performance on the task of 3D point cloud classification are also investigated. It proves that the proposed end-to-end learning network is more effective and suitable for the classification of the Terracotta Warrior fragments.

show abstract

Section: Multi-scale Structurementioning

confidence: 99%

AMS-Net: An Attention-Based Multi-Scale Network for Classification of 3D Terracotta Warrior Fragments

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has been tightly related to various fault diagnosis tasks, and it has been put into the intelligent fault diagnosis applications for a large number of complex equipment and systems [3]- [5]. Compared with the fault diagnosis methods used in the past, the deep learning algorithm demonstrates its better fault diagnosis capacity to a certain extent.…”

Section: Introductionmentioning

confidence: 99%

Fusion Fault Diagnosis Model for Six-Rotor UAVs Based on Conformal Fourier Transform and Improved Self-Organizing Feature Map

Che

2021

IEEE Access

View full text Add to dashboard Cite

If the fault sources can be located in a timely and accurate manner when an unmanned aerial vehicle (UAV) has an early minor fault, a major accident can be avoided. In light of the early fault of the six-rotor UAV motors, this paper proposes a fusion fault diagnosis model based on Conformal Fourier Transform (CFT) and the improved Self-Organizing Feature Map (SOM) neural network. Firstly, to overcome the weakening of UAV fault information caused by external interference and solve the problem that the non-uniform distribution of the collected flight data affects the accuracy of the frequency domain processing, on the basis of changing the processing method of the Fourier integral kernel and using high-order numerical integration, an improved Conformal Fourier Transform (CFT) algorithm optimized by spectrum refinement strategy is proposed. Then this algorithm is used to further intensify the main features and build a clear fault state in a cycle processing method. Secondly, an improved SOM neural network is designed. We use the unweighted average distance (UPGMA) of the agglomerative hierarchical clustering algorithm to detect the clustering areas of each pattern category of the data samples, and the weight vectors of different clustering areas are used to randomly initialize the connection weights of SOM network, thereby improving the clustering speed and convergence effect. On this basis, CFT algorithm is integrated into the improved SOM network to realize the multi-module collaboration strategy and finally form a new fusion fault diagnosis model. INDEX TERMS CFT algorithm, improved SOM network, main feature intensification, hierarchical clustering, fault diagnosis.

show abstract

“…This learning method is commonly used for mechanical fault diagnosis [12][13][14][15][16]. For example, Zhao et al [17] reported a transfer learning framework based on the deep multi-scale convolutional neural network. In this framework, the adaptive layer's weighting parameters are adjusted slightly to diagnose the rolling bearings intelligently.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Rolling Bearings of Different Working Conditions Based on Multi-Feature Spatial Domain Adaptation

2021

View full text Add to dashboard Cite

The running state of rolling bearings is complex in operation, and the data are generally collected under different working conditions. However, when single-source domain adaptation is used to model the heterogeneously distributed data obtained under different working conditions, the domaininvariant representations can hardly be used for representation, which directly affects the fault diagnosis rate. To this end, a method for the fault diagnosis of rolling bearings under different working conditions based on multi-feature spatial domain adaptation is proposed. Firstly, all the data from source and target domains are mapped into a feature space to learn the common representations of all domains. Secondly, the data for each pair of source and target domains are mapped into different feature spaces to get the fault feature representations under various working conditions. And the multi-domain adaptation network is used for the domain-specific distribution alignment to learn multiple domain-invariant representations. Thirdly, these representations are used to train multiple domain-specific classifiers, thus obtaining the recognition result for each domain-invariant representation. Finally, the domain-specific decision boundaries predicted by multiple classifiers are employed to align the classifiers' output of target samples and thus to reduce the influence from different classifiers. The effectiveness and feasibility of this proposed method have been verified by diagnostic experiments conducted according to the rolling bearing data from Case Western Reserve University and Laboratory, respectively.

show abstract

Deep multi-scale convolutional transfer learning network: A novel method for intelligent fault diagnosis of rolling bearings under variable working conditions and domains

Cited by 135 publications

References 38 publications

AMS-Net: An Attention-Based Multi-Scale Network for Classification of 3D Terracotta Warrior Fragments

AMS-Net: An Attention-Based Multi-Scale Network for Classification of 3D Terracotta Warrior Fragments

Fusion Fault Diagnosis Model for Six-Rotor UAVs Based on Conformal Fourier Transform and Improved Self-Organizing Feature Map

Fault Diagnosis of Rolling Bearings of Different Working Conditions Based on Multi-Feature Spatial Domain Adaptation

Contact Info

Product

Resources

About