scholarly journals A Semi-Supervised Fault Diagnosis Method Based on Improved Bidirectional Generative Adversarial Network

2021 ◽  
Vol 11 (20) ◽  
pp. 9401
Author(s):  
Long Cui ◽  
Xincheng Tian ◽  
Xiaorui Shi ◽  
Xiujing Wang ◽  
Yigang Cui
Keyword(s):  
Fault Diagnosis ◽  
Wasserstein Distance ◽  
Unlabeled Data ◽  
Fine Tuning ◽  
Training Procedure ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Diagnosis Method ◽  
Diagnosis Accuracy ◽  
The Stability

With the assumption of sufficient labeled data, deep learning based machinery fault diagnosis methods show effectiveness. However, in real-industrial scenarios, it is costly to label the data, and unlabeled data is underutilized. Therefore, this paper proposes a semi-supervised fault diagnosis method called Bidirectional Wasserstein Generative Adversarial Network with Gradient Penalty (BiWGAN-GP). First, by unsupervised pre-training, the proposed method takes full advantage of a large amount of unlabeled data and can extract features from vibration signals effectively. Then, using only a few labeled data to conduct supervised fine-tuning, the model can perform an accurate fault diagnosis. Additionally, Wasserstein distance is used to improve the stability of the model’s training procedure. Validation is performed on the bearing and gearbox fault datasets with limited labeled data. The results show that the proposed method can achieve 99.42% and 91.97% of diagnosis accuracy on the bearing and gear dataset, respectively, when the size of the training set is only 10% of the testing set.

scholarly journals A Novel Deep Learning System with Data Augmentation for Machine Fault Diagnosis from Vibration Signals

2020 ◽  
Vol 10 (17) ◽  
pp. 5765
Author(s):  
Qiang Fu ◽  
Huawei Wang
Keyword(s):  
Fault Diagnosis ◽  
Working Conditions ◽  
Data Augmentation ◽  
Measured Data ◽  
Learning System ◽  
Generative Adversarial Network ◽  
Vibration Signals ◽  
Adversarial Network ◽  
Diagnosis Method ◽  
Diagnosis Accuracy

In real engineering scenarios, it is difficult to collect adequate cases with faulty conditions to train an intelligent diagnosis system. To alleviate the problem of limited fault data, this paper proposes a fault diagnosis method combining a generative adversarial network (GAN) and stacked denoising auto-encoder (SDAE). The GAN approach augments the limited real measured data, especially in faulty conditions. The generated data are then transformed into the SDAE fault diagnosis model. The GAN-SDAE approach improves the accuracy of the fault diagnosis from the vibration signals, especially when the measured samples are few. The usefulness of this method is assessed through two condition-monitoring cases: one is a classic bearing example and the other is a more general gear failure. The results demonstrate that diagnosis accuracy for both cases is above 90% for various working conditions, and the GAN-SDAE system is stable.

scholarly journals Fault Diagnosis Method for Rolling Mill Multi Row Bearings Based on AMVMD-MC1DCNN under Unbalanced Dataset

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5494
Author(s):  
Chen Zhao ◽  
Jianliang Sun ◽  
Shuilin Lin ◽  
Yan Peng
Keyword(s):  
Fault Diagnosis ◽  
Rolling Mill ◽  
Real Data ◽  
Vibration Signal ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Mode Decomposition ◽  
Unbalanced Dataset ◽  
Diagnosis Method ◽  
Diagnosis Accuracy

Rolling mill multi-row bearings are subjected to axial loads, which cause damage of rolling elements and cages, so the axial vibration signal contains rich fault character information. The vertical shock caused by the failure is weakened because multiple rows of bearings are subjected to radial forces together. Considering the special characters of rolling mill bearing vibration signals, a fault diagnosis method combining Adaptive Multivariate Variational Mode Decomposition (AMVMD) and Multi-channel One-dimensional Convolution Neural Network (MC1DCNN) is proposed to improve the diagnosis accuracy. Additionally, Deep Convolutional Generative Adversarial Network (DCGAN) is embedded in models to solve the problem of fault data scarcity. DCGAN is used to generate AMVMD reconstruction data to supplement the unbalanced dataset, and the MC1DCNN model is trained by the dataset to diagnose the real data. The proposed method is compared with a variety of diagnostic models, and the experimental results show that the method can effectively improve the diagnosis accuracy of rolling mill multi-row bearing under unbalanced dataset conditions. It is an important guide to the current problem of insufficient data and low diagnosis accuracy faced in the fault diagnosis of multi-row bearings such as rolling mills.

scholarly journals Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Gang Xiang ◽  
Kun Tian
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Working Conditions ◽  
Manufacturing Industry ◽  
Probability Distributions ◽  
Wasserstein Distance ◽  
Target Domain ◽  
Target Feature ◽  
Generative Adversarial Network ◽  
Adversarial Network

In recent years, deep learning methods which promote the accuracy and efficiency of fault diagnosis task without any extra requirement of artificial feature extraction have elicited the attention of researchers in the field of manufacturing industry as well as aerospace. However, the problems that data in source and target domains usually have different probability distributions because of different working conditions and there are insufficient labeled or even unlabeled data in target domain significantly deteriorate the performance and generalization of deep fault diagnosis models. To address these problems, we propose a novel Wasserstein Generative Adversarial Network with Gradient Penalty- (WGAN-GP-) based deep adversarial transfer learning (WDATL) model in this study, which exploits a domain critic to learn domain invariant feature representations by minimizing the Wasserstein distance between the source and target feature distributions through adversarial training. Moreover, an improved one-dimensional convolutional neural network- (CNN-) based feature extractor which utilizes exponential linear units (ELU) as activation functions and wide kernels is designed to automatically extract the latent features of raw time-series input data. Then, the fault model classifier trained in one working condition (source domain) with sufficient labeled samples could be generalized to diagnose data in other working conditions (target domain) with insufficient labeled samples. Experiments on two open datasets demonstrate that our proposed WDATL model outperforms most of the state-of-the-art approaches on transfer diagnosis tasks under diverse working circumstances.

scholarly journals WDA: An Improved Wasserstein Distance-Based Transfer Learning Fault Diagnosis Method

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4394
Author(s):  
Zhiyu Zhu ◽  
Lanzhi Wang ◽  
Gaoliang Peng ◽  
Sijue Li
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Wasserstein Distance ◽  
Health Condition ◽  
Ball Screw ◽  
Computing Power ◽  
Bearing Fault Diagnosis ◽  
Average Accuracy ◽  
Diagnosis Method ◽  
Diagnosis Accuracy

With the growth of computing power, deep learning methods have recently been widely used in machine fault diagnosis. In order to realize highly efficient diagnosis accuracy, people need to know the detailed health condition of collected signals from equipment. However, in the actual situation, it is costly and time-consuming to close down machines and inspect components. This seriously impedes the practical application of data-driven diagnosis. In comparison, the full-labeled machine signals from test rigs or online datasets can be achieved easily, which is helpful for the diagnosis of real equipment. Thus, we introduced an improved Wasserstein distance-based transfer learning method (WDA), which learns transferable features between labeled and unlabeled signals from different forms of equipment. In WDA, Wasserstein distance with cosine similarity is applied to narrow the gap between signals collected from different machines. Meanwhile, we use the Kuhn–Munkres algorithm to calculate the Wasserstein distance. In order to further verify the proposed method, we developed a set of case studies, including two different mechanical parts, five transfer scenarios, and eight transfer learning fault diagnosis experiments. WDA reached an average accuracy of 93.72% in bearing fault diagnosis and 84.84% in ball screw fault diagnosis, which greatly surpasses state-of-the-art transfer learning fault diagnosis methods. In addition, comprehensive analysis and feature visualization are also presented.

scholarly journals A Fault Diagnosis Method for Rolling Bearings Based on Parameter Transfer Learning under Imbalance Data Sets

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 944
Author(s):  
Cheng Peng ◽  
Lingling Li ◽  
Qing Chen ◽  
Zhaohui Tang ◽  
Weihua Gui ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Hot Spot ◽  
Data Sets ◽  
Target Domain ◽  
Rolling Bearings ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Recognition Ability ◽  
Diagnosis Method

Fault diagnosis under the condition of data sets or samples with only a few fault labels has become a hot spot in the field of machinery fault diagnosis. To solve this problem, a fault diagnosis method based on deep transfer learning is proposed. Firstly, the discriminator of the generative adversarial network (GAN) is improved by enhancing its sparsity, and then adopts the adversarial mechanism to continuously optimize the recognition ability of the discriminator; finally, the parameter transfer learning (PTL) method is applied to transfer the trained discriminator to target domain to solve the fault diagnosis problem with only a small number of label samples. Experimental results show that this method has good fault diagnosis performance.

Generative Adversarial Network and Transfer Learning Based Fault Detection for Rotating Machinery with Imbalance Data Condition

2021 ◽  
Author(s):  
jun li ◽  
Yongbao Liu ◽  
Qijie Li
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Rolling Bearing ◽  
Rotating Machinery ◽  
Learning Method ◽  
Intelligent Fault Diagnosis ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Proposed Model ◽  
Diagnosis Method

Abstract Intelligent fault diagnosis achieves tremendous success in machine fault diagnosis because of the outstanding data-driven capability. However, the severe imbalanced dataset in practical scenarios of industrial rotating machinery is still a big challenge for the development of intelligent fault diagnosis method. In this paper, we solve this issue by constructing a novel deep learning model incorporated with a transfer learning method based on the Time-GAN and Efficient-Net models. Firstly, the proposed model so called Time-GAN-TL extends the imbalanced fault diagnosis of rolling bearings by using time series generative adversarial network. Secondly, balanced vibration signals are converted into two-dimensional images for training and classification by implementing the Efficient-Net into the transfer learning method. Finally, the proposed method is validated using two-types of rolling bearing experimental data. The high-precision diagnosis results of the transfer learning experiments and the comparison with other representative fault diagnosis classification methods reveal the efficiency, reliability, and generalization performance of the presented model.

scholarly journals Gas Turbine Rotor System Fault Diagnosis Method based on Improved Deep Convolutional Generative Adversarial Networks

2021 ◽  
Author(s):  
Shucong Liu ◽  
Hongjun Wang ◽  
Fengxia Han ◽  
Xiang Zhang
Keyword(s):  
Fault Diagnosis ◽  
Gas Turbine ◽  
Turbine Rotor ◽  
Rotor System ◽  
Fault Classification ◽  
Small Samples ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Diagnosis Method

Abstract In gas turbine rotor system fault diagnosis intelligent method based on data-driven is an important means to monitor the health status of gas turbine, it is necessary to obtain sufficient effective fault data to train the intelligent diagnosis model. In the actual operation of gas turbine, the collected gas turbine fault data is limited, and the small and imbalanced fault samples seriously affect the accuracy of fault diagnosis method. Aiming at the imbalance of gas turbine fault data, an Improved Deep Convolutional Generative Adversarial Network (Improved DCGAN) suitable for gas turbine signal is proposed, an structural optimization on generator of Deep Convolutional Generative Adversarial Network (DCGAN) and gradient penalty improvement on the loss function are introduced to generate effective fault data and improve the classification accuracy. The experiment results of gas turbine test bench demonstrated that the proposed method generated effective fault samples as a supplementary set of fault samples to balance the dataset, effectively improved the fault classification and diagnosis performance of gas turbine rotor in the case of small samples, The proposed method can be used as a solution to the problems of small unbalanced fault samples, and provides an effective method for gas turbine fault diagnosis.

Sign in / Sign up

Export Citation Format

Share Document