News
SEOUL, South Korea — The electronic component manufacturer LG Innotek is implementing AI to detect raw materials that aren't suitable for production.
LG Innotek, part of LG Group, developed and applied an AI-based inspection system for raw materials that's designed to detect defects and prevent the use of substandard raw materials in production, according to the company today.
The company expects the system to enhance the quality of its high-value semiconductor substrate products.
LG Innotek applied the AI-based inspection technology to its radio frequency system-in-package (RF-SiP) and flip chip ball grid array (FC-BGA) production processes.
Previously, raw materials underwent a visual inspection before entering the production process. Despite improving in-process defect causes, failures in reliability evaluations continued to rise, according to the company. The quality of raw materials was a "decisive factor affecting reliability evaluations."
LG Innotek developed the AI-based inspection system by combing material information and AI image processing technologies. The system was trained with tens of thousands of data sets on material composition that is suitable or unsuitable for a product.
The system analyzes semiconductor substrate raw materials in one minute and visualizes quality deviations in each lot, with an accuracy rate of over 90%, according to the company. The time required to analyze defects is down by up to 90%.
