scholarly journals Power Electric Transformer Fault Diagnosis Based on Infrared Thermal Images Using Wasserstein Generative Adversarial Networks and Deep Learning Classifier

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1161
Author(s):  
Kuo-Hao Fanchiang ◽  
Yen-Chih Huang ◽  
Cheng-Chien Kuo
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Monitoring System ◽  
Absolute Difference ◽  
Generative Adversarial Networks ◽  
Economic Losses ◽  
Maintenance Cost ◽  
Full Time ◽  
Noise Interference ◽  
In Series

The safety of electric power networks depends on the health of the transformer. However, once a variety of transformer failure occurs, it will not only reduce the reliability of the power system but also cause major accidents and huge economic losses. Until now, many diagnosis methods have been proposed to monitor the operation of the transformer. Most of these methods cannot be detected and diagnosed online and are prone to noise interference and high maintenance cost that will cause obstacles to the real-time monitoring system of the transformer. This paper presents a full-time online fault monitoring system for cast-resin transformer and proposes an overheating fault diagnosis method based on infrared thermography (IRT) images. First, the normal and fault IRT images of the cast-resin transformer are collected by the proposed thermal camera monitoring system. Next is the model training for the Wasserstein Autoencoder Reconstruction (WAR) model and the Differential Image Classification (DIC) model. The differential image can be acquired by the calculation of pixel-wise absolute difference between real images and regenerated images. Finally, in the test phase, the well-trained WAR and DIC models are connected in series to form a module for fault diagnosis. Compared with the existing deep learning algorithms, the experimental results demonstrate the great advantages of the proposed model, which can obtain the comprehensive performance with lightweight, small storage size, rapid inference time and adequate diagnostic accuracy.

scholarly journals Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Rodrigo P. Monteiro ◽  
Mariela Cerrada ◽  
Diego R. Cabrera ◽  
René V. Sánchez ◽  
Carmelo J. A. Bastos-Filho
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Activation Function ◽  
Economic Losses ◽  
Support Vector ◽  
Training Time ◽  
Decision Stage ◽  
Average Accuracy ◽  
Graphical Processing ◽  
Mechanical Devices

Gearboxes are mechanical devices that play an essential role in several applications, e.g., the transmission of automotive vehicles. Their malfunctioning may result in economic losses and accidents, among others. The rise of powerful graphical processing units spreads the use of deep learning-based solutions to many problems, which includes the fault diagnosis on gearboxes. Those solutions usually require a significant amount of data, high computational power, and a long training process. The training of deep learning-based systems may not be feasible when GPUs are not available. This paper proposes a solution to reduce the training time of deep learning-based fault diagnosis systems without compromising their accuracy. The solution is based on the use of a decision stage to interpret all the probability outputs of a classifier whose output layer has the softmax activation function. Two classification algorithms were applied to perform the decision. We have reduced the training time by almost 80% without compromising the average accuracy of the fault diagnosis system.

scholarly journals A digital twin auxiliary approach based on adaptive sparse attention network for diesel engine fault diagnosis

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Jiajie Jiang ◽  
Hui Li ◽  
Zhiwei Mao ◽  
Fengchun Liu ◽  
Jinjie Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Diesel Engine ◽  
Physical Model ◽  
Attention Mechanism ◽  
Maintenance Cost ◽  
Attention Network ◽  
Digital Twin ◽  
Mechanism Model ◽  
Fault Information

AbstractCondition monitoring and fault diagnosis of diesel engines are of great significance for safety production and maintenance cost control. The digital twin method based on data-driven and physical model fusion has attracted more and more attention. However, the existing methods lack deeper integration and optimization facing complex physical systems. Most of the algorithms based on deep learning transform the data into the substitution of the physical model. The lack of interpretability of the deep learning diagnosis model limits its practical application. The attention mechanism is gradually developed to access interpretability. In this study, a digital twin auxiliary approach based on adaptive sparse attention network for diesel engine fault diagnosis is proposed with considering its signal characteristics of strong angle domain correlation and transient non-stationary, in which a new soft threshold filter is designed to draw more attention to multi decentralized local fault information dynamically in real time. Based on this attention mechanism, the distribution of fault information in the original signal can be better visualized to help explain the fault mechanism. The valve failure experiment on a diesel engine test rig is conducted, of which the results show that the proposed adaptive sparse attention mechanism model has better training efficiency and clearer interpretability on the premise of maintaining performance.

scholarly journals Fault Diagnosis of Gearbox using Machine Learning and Deep Learning Techniques

2019 ◽  
Vol 9 (1) ◽  
pp. 3940-3943
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Maintenance Cost ◽  
Support Vector ◽  
Machine Condition Monitoring ◽  
Learning Techniques ◽  
Catastrophic Failures ◽  
Better Than

Gearbox is an important component used for automobiles, machine tools, industries etc. Failure of any component in gearbox will cause huge maintenance cost and production loss. Failure should be detected as early as possible in order to avoid sudden breakdown which even cause catastrophic failures. Vibration signals are used for machine condition monitoring for predictive maintenance and efficiently predicts fault in the gearbox. In this paper signals from vibration is used for diagnosis of gearbox fault. The experiment uses four different conditions of gearbox in four different load conditions. Then statistical feature extraction is done and obtained result is given to Decision Tree, Support Vector Machine (SVM), Convolutional Neural Network (CNN) and Deep Neural Network (DNN) for fault diagnosis. The efficiency of these four techniques is compared and shows that machine learning is better than deep learning in gearbox fault diagnosis.

scholarly journals Application of Rotating Machinery Fault Diagnosis Based on Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-30
Author(s):  
Wei Cui ◽  
Guoying Meng ◽  
Aiming Wang ◽  
Xinge Zhang ◽  
Jun Ding
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Rotating Machinery ◽  
Normal Operation ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Safe Production ◽  
Continuous Progress ◽  
Machinery Fault Diagnosis

With the continuous progress of modern industry, rotating machinery is gradually developing toward complexity and intelligence. The fault diagnosis technology of rotating machinery is one of the key means to ensure the normal operation of equipment and safe production, which has very important significance. Deep learning is a useful tool for analyzing and processing big data, which has been widely used in various fields. After a brief review of early fault diagnosis methods, this paper focuses on the method models that are widely used in deep learning: deep belief networks (DBN), autoencoders (AE), convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), and transfer learning methods are summarized from the two aspects of principle and application in the field of fault diagnosis of rotating machinery. Then, the commonly used evaluation indicators used to evaluate the performance of rotating machinery fault diagnosis methods are summarized. Finally, according to the current research status in the field of rotating machinery fault diagnosis, the current problems and possible future development and research trends are discussed.

scholarly journals Research on Rolling Bearing Fault Diagnosis Using Improved Majorization-Minimization-Based Total Variation and Empirical Wavelet Transform

2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Yangli Ou ◽  
Shuilong He ◽  
Chaofan Hu ◽  
Jiading Bao ◽  
Wenjie Li
Keyword(s):  
Genetic Algorithms ◽  
Wavelet Transform ◽  
Fault Diagnosis ◽  
Total Variation ◽  
Adaptive Signal Processing ◽  
Economic Losses ◽  
Particle Swarm Algorithm ◽  
Rolling Bearings ◽  
Noise Interference ◽  
Empirical Wavelet Transform

Bearings are among the most widely used core components in mechanical equipment. Their failure creates the potential for serious accidents and economic losses. Vibration signature analyses are the most common approach to assess the viability of bearings due to its ease of measurement and high correlation with structural dynamics. However, the collected vibration signals of rolling bearings are usually nonstationary and are inevitably accompanied by noise interference. This makes it difficult to extract the feature frequency for the failed bearing and affects the diagnosis accuracy. The majorization-minimization-based total variation (TV-MM) denoising algorithm effectively removes the noise interference from the signal and highlights the related feature information. The value of its main parameter λ determines the quality of the denoising effect. However, manually selecting parameters requires professional experience in a process that it is time-consuming and laborious, while the use of genetic algorithms is cumbersome. Therefore, an improved particle swarm algorithm (IPSO) is used to find the optimal solution of λ. The IPSO utilises the mutation concept in genetic algorithms to reinitialise the particles with a certain probability after each update. In addition, the empirical wavelet transform (EWT) is an adaptive signal processing method suitable for processing nonlinear and nonstationary signals. Therefore, this paper presents an ensemble analysis method that combines the IPSO, TV-MM, and EWT. First, IPSO is used to optimise the denoising parameter λ. The TV-MM under this parameter effectively removes the background noise interference and improves the accuracy of the subsequent modal decomposition. Then, the EWT is used for the adaptive division to produce a set of sequences. Finally, Hilbert envelope demodulation is performed on each component to realise fault diagnosis. The results from simulations and signals received from defective bearings with outer race fault, inner race fault, and rolling element fault demonstrate the effectiveness of the proposed method for fault diagnosis of rolling bearings.

scholarly journals A Novel Generative Method for Machine Fault Diagnosis

2022 ◽  
Vol 2022 ◽  
pp. 1-11
Author(s):  
Zhipeng Dong ◽  
Yucheng Liu ◽  
Jianshe Kang ◽  
Shaohui Zhang
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Test Sample ◽  
Training Sample ◽  
Generative Adversarial Networks ◽  
Mechanical Equipment ◽  
Learning Models ◽  
Machine Fault Diagnosis ◽  
Machine Fault ◽  
Generative Method

Deep learning is widely used in fault diagnosis of mechanical equipment and has achieved good results. However, these deep learning models require a large number of labeled samples for training, which is difficult to obtain enough labeled samples in the actual production process. However, it is easier to obtain unlabeled samples in the industrial environment. To overcome this problem, this paper proposes a novel method to generative enough label samples for training deep learning models. Unlike the generative adversarial networks, which required complex computing time, the calculation of the proposed novel generative method is simple and effective. First, we calculate the Euclidean distance between the training sample and the test sample; then, the weight coefficient between the training sample and the test sample is settled to generate pseudosamples; finally, combine with the pseudosamples, the deep learning method is training for machine fault diagnosis. In order to verify the effectiveness of the proposed method, two experiment datasets with planetary gearboxes and wind gearboxes are carried out with different activation functions. Experimental results show that the proposed method is effective for most activation function models.

COMPOUND FAULT DIAGNOSIS OF BEARINGS USING AN IMPROVED SPECTRAL KURTOSIS BY MAXIMUM CORRELATION KURTOSIS DECONVOLUTION (MCKD).

2020 ◽  
Vol 9 (8) ◽  
pp. 66-72
Keyword(s):  
Fault Diagnosis ◽  
Resonance Frequency ◽  
Background Noise ◽  
Maximum Correlation ◽  
Vibration Signals ◽  
Filter Length ◽  
Frequency Bands ◽  
Noise Interference ◽  
Spectral Kurtosis

This paper discusses the use of Maximum Correlation kurtosis deconvolution (MCKD) method as a pre-processor in fast spectral kurtosis (FSK) method in order to find the compound fault characteristics of the bearing, by enhancing the vibration signals. FSK only extracts the resonance bands which have maximum kurtosis value, but sometimes it might possible that faults occur in the resonance bands which has low kurtosis value, also the faulty signals missed due to noise interference. In order to overcome these limitations FSK used with MCKD, MCKD extracts various faults present in different resonance frequency bands; also detect the weak impact component, as MCKD also dealt with strong background noise. By obtaining the MCKD parameters like, filter length & deconvolution period, we can extract the compound fault feature characteristics.

scholarly journals A deep learning method for automatic segmentation of the bony orbit in MRI and CT images

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jared Hamwood ◽  
Beat Schmutz ◽  
Michael J. Collins ◽  
Mark C. Allenby ◽  
David Alonso-Caneiro
Keyword(s):  
Deep Learning ◽  
Human Performance ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Human Observer ◽  
In Series ◽  
Magnetic Resonance Imaging Mri ◽  
High Degree ◽  
Orbital Region ◽  
Ct And Mri

AbstractThis paper proposes a fully automatic method to segment the inner boundary of the bony orbit in two different image modalities: magnetic resonance imaging (MRI) and computed tomography (CT). The method, based on a deep learning architecture, uses two fully convolutional neural networks in series followed by a graph-search method to generate a boundary for the orbit. When compared to human performance for segmentation of both CT and MRI data, the proposed method achieves high Dice coefficients on both orbit and background, with scores of 0.813 and 0.975 in CT images and 0.930 and 0.995 in MRI images, showing a high degree of agreement with a manual segmentation by a human expert. Given the volumetric characteristics of these imaging modalities and the complexity and time-consuming nature of the segmentation of the orbital region in the human skull, it is often impractical to manually segment these images. Thus, the proposed method provides a valid clinical and research tool that performs similarly to the human observer.

Sign in / Sign up

Export Citation Format

Share Document