WeChat Mini Program
Old Version Features

Determination of Abnormality of IGBT Images Using VGG16

2021 21st International Conference on Control, Automation and Systems (ICCAS)(2021)

Kyushu Inst Technol

Cited 0|Views0
Abstract
A power device is a semiconductor device for power control used for power conversion such as converting direct current to alternating current and alternating current to direct current. It is widely used such as refrigerators, air conditioners which is implemented electronic components that are closely related to our daily lives. Therefore, high reliability and safety are required, and power cycle tests are conducted for the purpose of evaluating them. In the conventional test, there is a problem that it is difficult to perform analysis because sparks are generated during the test and the device is severely damaged after the test. To solve this problem, a new technology has been developed that adds ultrasonic that enable internal observation during the test. However, there are remains a problem that the method for analyzing the ultrasonic image obtained in the new technology has not been established. Also, few abnormal images are obtained in the test. In this paper, we propose a method for detection of abnormal devices based on CNN. Especially, we implement a Cycle-GAN to extend the abnormal data and classify the known image based on improved VGG16. As an experimental result, classification accuracy of Precision = 97.06%, Recall = 93.58%, $F$ - measure = 95.17% were obtained.
More
Translated text
Key words
Ultrasound images,Convolutional neural network,Cycle-GAN,Data augmentation,VGG16,Batch normalization,Global average pooling
求助PDF
上传PDF
Bibtex
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
  • Pretraining has recently greatly promoted the development of natural language processing (NLP)
  • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
  • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
  • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
  • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined