Convolutional neural network (CNNs) based image diagnosis for failure analysis of power devices

Watanabe, Akihiko; Hirose, Naoto; Kim, Hyoungseop; Omura, Ichiro

doi:10.1016/j.microrel.2019.113399

Cited by 6 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantages of CNN can solve the problem of low fault diagnosis rate due to the lack of obvious features. Watanabe et al [2] used a real-time monitoring scanning acoustic microscope to capture images during a [26], but also obtain the number of images per block that will enter in the training phase [27]. The optimized CNN is applied in the field of recognition and image classification.…”

Section: Related Workmentioning

confidence: 99%

Adaptive feature extraction and fault diagnosis for three-phase inverter based on hybrid-CNN models under variable operating conditions

Sun

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

The increasing reliability and availability requirements of power electronic systems have drawn great concern in many industrial applications. Aiming at the difficulty in fault characteristics extraction and fault modes classification of the three-phase full-bridge inverter (TFI) that used as the drive module of brushless DC motor (BLDCM). A hybrid convolutional neural network (HCNN) model consists of one-dimensional CNN (1D-CNN) and two-dimensional CNN (2D-CNN) is proposed in this paper, which can tap more effective spatial feature for TFI fault diagnosis. The frequency spectrum from the three-phase current signal preprocess are applied as the input for 1D-CNN and 2D-CNN to conduct feature extraction, respectively. Then, the feature layers information are combined in the fully connected layer of HCNN. Finally, the performance status of TFI could be identified by the softmax classifier with Adam optimizer. Several groups of experiments have been studied when the BLDCM under different operating conditions. The results show that the fusion features can get a higher degree of discrimination so as to the presented network model also obtains better classification accuracy, which verify the feasibility and superiority to the other networks.

show abstract

Section: Related Workmentioning

confidence: 99%

Adaptive feature extraction and fault diagnosis for three-phase inverter based on hybrid-CNN models under variable operating conditions

Sun

et al. 2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Several studies are also conducted in the domain of electrical engineering related to the implementation of CNN. In [14], Watanabe et al has implemented CNN to classify a series of Scanning Acoustic Microscopy (SAM) images into 2 different classes, namely "normal device" and "abnormal device". An area of interest (AOI) is extracted from the images obtained from SAM.…”

Section: Introductionmentioning

confidence: 99%

“…Then, the extracted image will be fed into the classifier. Authors in [14] also mentioned that since the number of sample image is small, data augmentation process is required by rotation and mirroring the images, hence the number of image samples can be increased. In [15], Plathottam et al has implemented CNN to solve multi-class multi-label classification problem.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Network for Voltage Stability Prediction in Power System Operation

Zamani¹

2020

IJETER

View full text Add to dashboard Cite

It is desirable for power system operators to maintain healthy power system operation. Increase in load demand will stress a power system, hence demands voltage stability study to be conducted to plan further mitigation action. Established voltage stability assessment methods requires long computational time despite of providing accurate results. To address this issue, Convolutional Neural Network (CNN) is implemented to predict the voltage stability of IEEE 26-bus Reliability Test System based on the load demand in the system. Experimental work on the proposed study has indicated that CNN is capable of producing predicted outputs with low prediction error indicated by low value of Root Mean Square Error (RMSE). Comparative studies with respect to Artificial Neural Network (ANN) and Support Vector Machine (SVM) indicates CNN can predict outputs with lower RMSE value compare to ANN and SVM, which highlights the superiority of CNN in producing better prediction. The results of this study can benefit power system operators to assess the voltage stability of the system with faster computational time, hence speeding up mitigation actions when required.

show abstract

Motion Time Study with Convolutional Neural Network

Pannakkong

Tai

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Convolutional neural network (CNNs) based image diagnosis for failure analysis of power devices

Cited by 6 publications

References 9 publications

Adaptive feature extraction and fault diagnosis for three-phase inverter based on hybrid-CNN models under variable operating conditions

Adaptive feature extraction and fault diagnosis for three-phase inverter based on hybrid-CNN models under variable operating conditions

Convolutional Neural Network for Voltage Stability Prediction in Power System Operation

Motion Time Study with Convolutional Neural Network

Contact Info

Product

Resources

About