An intelligent vehicle-oriented EMC fault dataset augmentation and validity verification method

Xiaozhi Li; Shijie Fang; Lingqiu Zeng; Yong Chai; Qingwen Han; Lei Ye; Dongmei Chen

doi:10.1117/12.2656592

20 October 2022 An intelligent vehicle-oriented EMC fault dataset augmentation and validity verification method

Xiaozhi Li, Shijie Fang, Lingqiu Zeng, Yong Chai, Qingwen Han, Lei Ye, Dongmei Chen

Proceedings Volume 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022); 124514W (2022) https://doi.org/10.1117/12.2656592
Event: 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 2022, Chongqing, China

Abstract

With the increasing complexity of vehicle Electronic & Electrical infrastructure, fault diagnosis of EMC (electromagnetic compatibility) becomes more difficult. Although performance of fault diagnosis system is deadly influenced by diagnosis model, small sample problem of EMC test dataset had puzzled researchers for many years. According to this, a SMOTE based data augmentation method is proposed in this paper. Moreover, the effectiveness of augmentation dataset is verified from two aspects: sample similarity feature and attributes’ distribution feature. A random forest model is used for EMC fault diagnosis. The experimental results show that fault diagnosis accuracy is improved by using augmentation dataset.

Citation Download Citation

Xiaozhi Li, Shijie Fang, Lingqiu Zeng, Yong Chai, Qingwen Han, Lei Ye, and Dongmei Chen "An intelligent vehicle-oriented EMC fault dataset augmentation and validity verification method", Proc. SPIE 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 124514W (20 October 2022); https://doi.org/10.1117/12.2656592

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available