LG CNS and Google to use AI to read faulty manufacturing
LG CNS and Google to use AI to read faulty manufacturing
  • Lee Jun-sung
  • 승인 2019.04.12 07:30
  • 댓글 0
이 기사를 공유합니다

Lee Sung-wook, executive vice president of LG CNS, announces a case of manufacturing AI innovation at 'Google Cloud Next'

 

LG CNS is accelerating its manufacturing intelligence by applying Google Cloud AI solution. 

LG CNS announced the case of manufacturing AI innovation with Google at the Google Cloud NEXT 2019 held in San Francisco on April 10.

"Google Cloud NEXT" is a developer's event held by Google Cloud organization and marks its fourth anniversary this year. 

It is Google's largest event this year, with more than 30,000 developers and partners attending.

Lee Seong-wook, executive vice president of AI Big Data at LG CNS, who was working with Google to introduce a vision test that applied AI image reading technology to determine faulty parts at manufacturing plants.

Since last year, LG CNS has been combining AI Big Data platform "DAP" with Google Cloud's AI solution "Auto Machine Learning(AutoML)" to make innovative improvements in manufacturing defect rates.

AutoML is a service that develops artificial intelligence through artificial intelligence and is a technology that learns artificial intelligence through various data such as pictures and text that are owned by businesses and uses it in certain areas.

In the vision inspection area, LG CNS DAP analyzes tens of thousands of defective data with AI Deep Learning and is in charge of overall implementation of intelligentization of plants. 

LG CNS applied AutoML to test hundreds of thousands of data from LG affiliates' manufacturing plants, cutting the production period of AI models to up to two hours from a week and recording about 30 times faster reading time. 

It is also possible to achieve a 99.9% reading rate even during processes with high judgment difficulty due to combination technologies from both companies.


댓글삭제
삭제한 댓글은 다시 복구할 수 없습니다.
그래도 삭제하시겠습니까?
댓글 0
댓글쓰기
계정을 선택하시면 로그인·계정인증을 통해
댓글을 남기실 수 있습니다.

  • ABOUT
  • CONTACT US
  • SIGN UP MEMBERSHIP
  • RSS
  • 2-D 678, National Assembly-daero, 36-gil, Yeongdeungpo-gu, Seoul, Korea (Postal code: 07257)
  • URL: www.koreaittimes.com | Editorial Div: 82-2-578- 0434 / 82-10-2442-9446 | North America Dept: 070-7008-0005 | Email: info@koreaittimes.com
  • Publisher and Editor in Chief: Monica Younsoo Chung | Chief Editorial Writer: Hyoung Joong Kim | Editor: Yeon Jin Jung
  • Juvenile Protection Manager: Choul Woong Yeon
  • Masthead: Korea IT Times. Copyright(C) Korea IT Times, All rights reserved.
ND소프트