scholarly journals A Multimodel Decision Fusion Method Based on DCNN-IDST for Fault Diagnosis of Rolling Bearing

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Weixiao Xu ◽  
Luyang Jing ◽  
Jiwen Tan ◽  
Lianchen Dou
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Rbf Neural Network ◽  
Evidence Theory ◽  
Rolling Bearing ◽  
Original Data ◽  
Decision Fusion ◽  
Fusion Method ◽  
Rolling Bearings ◽  
Advantages And Disadvantages

Each pattern recognition method has its advantages and disadvantages to diagnose the state of rotating machinery. There are many fault types of rolling bearings with apparent uncertainty. The optimal fusion level is usually challenging to be selected for a specific fault diagnosis task, and extensive human labour and prior knowledge are also highly required during these selections. To solve the above problems, a multimodel decision fusion method based on Deep Convolutional Neural Network and Improved Dempster-Shafer Evidence Theory (DCNN-IDST) is proposed for the inspection of rolling bearing. To solve the defect of the original evidence theory method in the fusion of high-conflict evidence, the fuzzy consistency matrix is introduced. By calculating the factor weight, the reliability and rationality of D-S evidence theory are improved. The DCNN model can learn features from the original data and carry out adaptive feature extraction for multiple sensor information. The features extracted by DCNN adaptively are input into multiple network models for decision fusion. The new method of DCNN-IDST multimodel decision fusion is applied to detect the damage of rolling bearings. To evaluate the effectiveness of the proposed method, both the BP neural network and RBF neural network are used to set up a multigroup comparison test. The result demonstrates that the proposed method can detect the fault of the rolling bearing effectively and achieve the highest diagnosis accuracy among all the tested methods in the experiment.

Multiscale convolutional neural network and decision fusion for rolling bearing fault diagnosis

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Defeng Lv ◽  
Huawei Wang ◽  
Changchang Che
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Rolling Bearing ◽  
Decision Fusion ◽  
Fusion Model ◽  
Vibration Signals ◽  
Content Type ◽  
Proposed Model

Purpose The purpose of this study is to achieve an accurate intelligent fault diagnosis of rolling bearing. Design/methodology/approach To extract deep features of the original vibration signal and improve the generalization ability and robustness of the fault diagnosis model, this paper proposes a fault diagnosis method of rolling bearing based on multiscale convolutional neural network (MCNN) and decision fusion. The original vibration signals are normalized and matrixed to form grayscale image samples. In addition, multiscale samples can be achieved by convoluting these samples with different convolution kernels. Subsequently, MCNN is constructed for fault diagnosis. The results of MCNN are put into a data fusion model to obtain comprehensive fault diagnosis results. Findings The bearing data sets with multiple multivariate time series are used to testify the effectiveness of the proposed method. The proposed model can achieve 99.8% accuracy of fault diagnosis. Based on MCNN and decision fusion, the accuracy can be improved by 0.7%–3.4% compared with other models. Originality/value The proposed model can extract deep general features of vibration signals by MCNN and obtained robust fault diagnosis results based on the decision fusion model. For a long time series of vibration signals with noise, the proposed model can still achieve accurate fault diagnosis.

scholarly journals Rolling Bearing Fault Diagnosis Based on Deep Learning and Autoencoder Information Fusion

Symmetry ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 13
Author(s):  
Jianpeng Ma ◽  
Chengwei Li ◽  
Guangzhu Zhang
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Rolling Bearing ◽  
Fusion Method ◽  
Rolling Bearings ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Evolution Analysis ◽  
Comparison Results

The multisource information fusion technique is currently one of the common methods for rolling bearing fault diagnosis. However, the current research rarely fuses information from the data of different sensors. At the same time, the dispersion itself in the VAE method has asymmetric characteristics, which can enhance the robustness of the system. Therefore, in this paper, the information fusion method of the variational autoencoder (VAE) and random forest (RF) methods are targeted for subsequent lifetime evolution analysis. This fusion method achieves, for the first time, the simultaneous monitoring of acceleration signals, weak magnetic signals and temperature signals of rolling bearings, thus improving the fault diagnosis capability and laying the foundation for subsequent life evolution analysis and the study of the fault–slip correlation. Drawing on the experimental procedure of the CWRU’s rolling bearing dataset, the proposed VAERF technique was evaluated by conducting inner ring fault diagnosis experiments on the experimental platform of the self-research project. The proposed method exhibits the best performance compared to other point-to-point algorithms, achieving a classification rate of 98.19%. The comparison results further demonstrate that the deep learning fusion of weak magnetic and vibration signals can improve the fault diagnosis of rolling bearings.

scholarly journals A Novel Intelligent Fault Diagnosis Method for Rolling Bearings Based on Wasserstein Generative Adversarial Network and Convolutional Neural Network under Unbalanced Dataset

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6754
Author(s):  
Hongtao Tang ◽  
Shengbo Gao ◽  
Lei Wang ◽  
Xixing Li ◽  
Bing Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Rolling Bearing ◽  
Environmental Noise ◽  
Experimental Result ◽  
Grayscale Image ◽  
Intelligent Fault Diagnosis ◽  
Rolling Bearings ◽  
Generative Adversarial Network

Rolling bearings are widely used in industrial manufacturing, and ensuring their stable and effective fault detection is a core requirement in the manufacturing process. However, it is a great challenge to achieve a highly accurate rolling bearing fault diagnosis because of the severe imbalance and distribution differences in fault data due to weak early fault features and interference from environmental noise. An intelligent fault diagnosis strategy for rolling bearings based on grayscale image transformation, a generative adversative network, and a convolutional neural network was proposed to solve this problem. First, the original vibration signal is converted into a grayscale image. Then more training samples are generated using GANs to solve severe imbalance and distribution differences in fault data. Finally, the rolling bearing condition detection and fault identification are carried out by using SECNN. The availability of the method is substantiated by experiments on datasets with different data imbalance ratios. In addition, the superiority of this diagnosis strategy is verified by comparing it with other mainstream intelligent diagnosis techniques. The experimental result demonstrates that this strategy can reach more than 99.6% recognition accuracy even under substantial environmental noise interference or changing working conditions and has good stability in the presence of a severe imbalance in fault data.

Comparison of RBF Neural Network and Support Vector Machine on Aero-Engine Vibration Fault Diagnosis

2007 ◽  
Vol 347 ◽  
pp. 323-328
Author(s):  
Kai Xiong ◽  
Dong Xiang Jiang ◽  
Yong Shan Ding ◽  
Kai Li
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Rbf Neural Network ◽  
Diagnostic Methods ◽  
Support Vector ◽  
Advantages And Disadvantages ◽  
Engine Vibration ◽  
Aero Engine ◽  
Speed Accuracy

RBF neural network and support vector machine (SVM), two Artificial Intelligent (AI) methods, have been extensively applied on machinery fault diagnosis. Aero-engine, as one kind of rotating machine with complex structure and high rotating speed, has complicated vibration faults. As one kind of AI methods, RBF neural network has the advantages of fast learning, high accuracy and strong self-adapting ability. Support vector machine, another AI method, only needs a small quantity of fault data samples to train the classifier and does not need to extract signal features. In this paper, the applications of two AI methods on aero-engine vibration fault diagnosis are introduced. Firstly, the principles and algorithm of both two methods are presented. Secondly the fundamentals of two-shaft aero-engine vibration fault diagnosis are described and gotten the standard fault samples (training samples) and simulation samples (testing samples). Third, two AI methods are applied to the vibration fault diagnosis and obtained the diagnostic results. Finally, the advantages and disadvantages of the two methods are compared such as the computing speed, accuracy of diagnosis and complexity of algorithm, and given a suggestion of selecting the diagnostic methods.

Fault Diagnosis of Rolling Bearing Based on Rough Set and Neural Network

2011 ◽  
Vol 58-60 ◽  
pp. 974-977 ◽  
Author(s):  
Jun Rong Yan ◽  
Yong Min ◽  
Xia Cui ◽  
Yan Huang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Rough Set ◽  
Rolling Bearing ◽  
Original Data ◽  
Training Data ◽  
Resolving Power ◽  
Self Learning ◽  
Test Result ◽  
The Greedy Algorithm

Artificial neural network was one of the most important methods in intelligent fault diagnosis because it has the performance of nonlinear pattern classification and the capacity of self-learning and self-organization, but it can not judge redundancy and usefulness of information. Rough set can reduce the knowledge of information system and dislodge redundant information. In this paper, fault data of rolling bearing was reduced by the greedy algorithm of rough set. Training data and test data of BP neural network had been reduced by rough set. By comparison of two test result about simply data and original data, it was indicated that resolving power was unchanged and database was simply.

scholarly journals Deep transfer learning for rolling bearing fault diagnosis under variable operating conditions

2019 ◽  
Vol 11 (12) ◽  
pp. 168781401989721 ◽  
Author(s):  
Changchang Che ◽  
Huawei Wang ◽  
Qiang Fu ◽  
Xiaomei Ni
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Rolling Bearing ◽  
Operating Conditions ◽  
Feature Representation ◽  
Target Domain ◽  
Rolling Bearings ◽  
Variable Operating Conditions

Rolling bearings are the vital components of rotary machines. The collected data of rolling bearing have strong noise interference, massive unlabeled samples, and different fault features. Thus, a deep transfer learning method is proposed for rolling bearings fault diagnosis under variable operating conditions. To obtain robust feature representation, the denoising autoencoder is used to denoise and reduce dimension of unlabeled rolling bearing signals. For those unlabeled target domain signals, a feature matching method based on multi-kernel maximum mean discrepancies between source domain and target domain is adopted to get enough labeled target domain samples. Then, these rolling bearing signals are converted to multi-dimensional graph samples and fed into a convolutional neural network model for fault diagnosis. To improve the generalization of convolutional neural network under variable operating conditions, we combine model-based transfer learning with feature-based transfer learning to initialize and optimize the convolutional neural network parameters. The effectiveness of the proposed method is validated through several comparative experiments of Case Western Reserve University data. The results demonstrate that the proposed method can learn features adaptively from noisy data and increase the accuracy rate by 2%–8% comparing with other models.

Application of a Optimized Wavelet Neural Networks in Rolling Bearing Fault Diagnosis

2012 ◽  
Vol 190-191 ◽  
pp. 919-922 ◽  
Author(s):  
Yuan Yan Lin ◽  
Bin Wu Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Fault Diagnosis ◽  
Rolling Bearing ◽  
Wavelet Neural Networks ◽  
Rolling Bearings ◽  
Swarm Optimization ◽  
Bearing Fault Diagnosis ◽  
Fault Type

According to the fault type and fault signal of rolling bearing is difficult to predict, the paper proposed a new method to diagnose fault of rolling bearings with the wavelet neural network optimizated by simulated annealing particle swarm optimization. And it was applied to the fault diagnosis of rolling bearing. The experiment shows that this method can reduce the iteration time and improve the accuracy of convergence.

Data-Driven Based Gas Path Fault Diagnosis for Turbo-Shaft Engine

2012 ◽  
Vol 249-250 ◽  
pp. 400-404 ◽  
Author(s):  
Feng Lu ◽  
Tie Bin Zhu ◽  
Yi Qiu Lv
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Rbf Neural Network ◽  
Evidence Theory ◽  
Aircraft Engine ◽  
Data Driven ◽  
Support Vector ◽  
Diagnosis Method ◽  
Gas Path Fault

In order to improve diagnostic accuracy and reduce the rate of misdiagnosis to the aircraft engine gas path faulty, the methods based on data-driven and information fusion are developed and analyzed. BP neural network (NN) and RBF neural network based on data-driven single gas path fault diagnosis method is introduced firstly. Design gas path performance estimators and the fault type classification for turbo-shaft engine. Then the gas path fused diagnostic structure based on D-S evidence theory and least squares support vector machine are developed. Comparisons of the turbo-shaft engine gas path fault diagnosis verify the feasibility and effectiveness of the gas path fault diagnosis based on information fusion.

Sign in / Sign up

Export Citation Format

Share Document