Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method

An, Zenghui; Li, Shunming; Wang, Jinrui; Xin, Yu; Xu, Kun

doi:10.1016/j.neucom.2019.04.010

Cited by 129 publications

(69 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wen et al [29] proposed a new method for fault diagnostics, which used a three-layer sparse auto-encoder to extract the features of raw data and applied the maximum mean discrepancy (MMD) term to minimizing the discrepancy penalty between the features from training data and testing data. Similar work based on deep transfer learning can also be found in [30]- [33].…”

Section: Introductionmentioning

confidence: 85%

A Multistage Deep Transfer Learning Method for Machinery Fault Diagnostics Across Diverse Working Conditions and Devices

et al. 2020

View full text Add to dashboard Cite

Deep learning methods have promoted the vibration-based machinery fault diagnostics from manual feature extraction to an end-to-end solution in the past few years and exhibited great success on various diagnostics tasks. However, this success is based on the assumptions that sufficient labeled data are available, and that the training and testing data are from the same distribution, which is normally difficult to satisfy in practice. To overcome this issue, we propose a multistage deep convolutional transfer learning method (MSDCTL) aimed at transferring vibration-based fault diagnostics capabilities to new working conditions, experimental protocols and instrumented devices while avoiding the requirement for new labeled fault data. MSDCTL is constructed as a one-dimensional convolutional neural network (CNN) with double-input structure that accepts raw data from different domains as input. The features from different domains are automatically learned and a customized layer is designed to compute the distribution discrepancy of the features. This discrepancy is further minimized such that the features learned from different domains are domain-invariant. A multistage training strategy including pre-train and fine-tuning is proposed to transfer the weight of a pre-trained model to new diagnostics tasks, which drastically reduces the requirement on the amount of data in the new task. The proposed model is validated on three bearing fault datasets from three institutes, including one from our own. We designed nine transfer tasks covering fault diagnostics transfer across diverse working conditions and devices to test the effectiveness and robustness of our model. The results show high diagnostics accuracies on all the designed transfer tasks with strong robustness. Especially for transfer to new devices the improvement over state of the art is very significant. INDEX TERMS Fault diagnostics, transfer learning, convolutional neural network, maximum mean difference, multistage training.

show abstract

Section: Introductionmentioning

confidence: 85%

A Multistage Deep Transfer Learning Method for Machinery Fault Diagnostics Across Diverse Working Conditions and Devices

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The ability to diagnose the bearing dataset under different loads was verified. An et al [19] generalized the deep neural network using multiple kernel method and improved the accuracy of bearing fault diagnosis under different working conditions. They both get the satisfying testing accuracies under their experiment condition.…”

Section: Meanwhile Rotating Machinery In Modern Industry Becomesmentioning

confidence: 99%

“…For ACFE, we randomly selected an experiment and give out the changes of losses in Figure 4 In order to compare with the existing successful fault diagnosis method based on transfer learning, the results of generalization of deep neural network (GDN) reported in Ref. [19] are also shown in Table 1 and Table 2. The results (r 1 , r 2 ) denote the average accuracy and standard deviation, respectively.…”

Section: B Setup Of Proposed Modelmentioning

confidence: 99%

“…To show the effectiveness of ACFE, we compare it with the methods in related work such as Transfer Component Analysis (TCA) [35], Joint Distribution Adaptation (JDA) [36], Balanced Distribution Adaptation (BDA) [37] and GDN [19] using the same rolling bearing dataset in section IV.A. The comparisons under transfer condition 3-0 of dataset A are displayed in Table 3.…”

Section: Comparing With Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Cross-Domain Feature Extraction Method and Its Application on Machinery Intelligent Fault Diagnosis Under Different Working Conditions

Jiang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Transfer learning based models have been employed for intelligent fault diagnosis under different working conditions. However, an actual and important problem is neglected in existing intelligent fault diagnosis methods, which is that target domain mechanical fault datasets are always highly imbalanced with abundant normal condition mechanical samples but a paucity of samples from rare fault conditions. To solve this actual problem, this paper proposed a novel adaptive cross-domain feature extraction (ACFE) method which can automatically extract similar features between different feature spaces. ACFE wants to obtain more information for determining the category of each training target sample, so it avoids the distribution adaptation and is suitable for the imbalanced problem. Specifically, high dimensional distance through kernel method is employed for ensuring the strong identify ability first. Then, for automatically extracting cross-domain feature, we calculate the posterior probability of category of each target domain training sample based on high dimensional distance, and employ entropy loss to capture the cross-domain information. Besides, we propose the guide loss to avoid the features of a category overall falling into false category caused by imbalanced dataset. Based on ACFE, the intelligent fault diagnosis method for dealing with the imbalanced target dataset is described. To verify the effectiveness, we carry out two specially designed experiments, and the results shows that, comparing with related method, the proposed method achieve a superior performance. INDEX TERMS Transfer learning, imbalanced dataset, information entropy, intelligent fault diagnosis.

show abstract

“…Kernel methods have been developed as powerful tools for machine learning, statistical analysis and probability numeral calculations [16], [8]. In the recent years, scientists have paid large attention to kernel methods to study various learning frameworks, such as extreme learning [19], deep learning [2], Bayesian learning [10] and others [14], [4], [15]. We attempt to extend the kernel method to find a suitable loss function for CNN problem.…”

mentioning

confidence: 99%

An improved deep convolutional neural network model with kernel loss function in image classification

Xia¹,

Zhou²,

Xu³

et al. 2020

Mathematical Foundations of Computing

View full text Add to dashboard Cite

To further enhance the performance of the current convolutional neural network, an improved deep convolutional neural network model is shown in this paper. Different from the traditional network structure, in our proposed method the pooling layer is replaced by two continuous convolutional layers with 3 × 3 convolution kernel between which a dropout layer is added to reduce overfitting, and cross entropy kernel is used as loss function. Experimental results on Mnist and Cifar-10 data sets for image classification show that, compared to several classical neural networks such as Alexnet, VGGNet and GoogleNet, the improved network achieve better performance in learning efficiency and recognition accuracy at relatively shallow network depths.

show abstract

Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method

Cited by 129 publications

References 36 publications

A Multistage Deep Transfer Learning Method for Machinery Fault Diagnostics Across Diverse Working Conditions and Devices

A Multistage Deep Transfer Learning Method for Machinery Fault Diagnostics Across Diverse Working Conditions and Devices

Adaptive Cross-Domain Feature Extraction Method and Its Application on Machinery Intelligent Fault Diagnosis Under Different Working Conditions

An improved deep convolutional neural network model with kernel loss function in image classification

Contact Info

Product

Resources

About