Feb 12, 2020 12:30 JST

Source: Showa Denko K.K.

SDK Develops AI-Based Image Analysis System to Improve Spherical Alumina Production

TOKYO, Feb 12, 2020 - (JCN Newswire) - Showa Denko (SDK; TSE:4004) has developed an artificial intelligence-based image analysis system for spherical alumina production in cooperation with BLUE TAG. SDK will start using the system at its production line in April this year.

A picture under the image-analysis system
 


Spherical alumina is produced from molten material, using surface tension. The product is in the form of particles with diameters ranging from several microns to 70 um. Due to high fluidity and compatibility, it is used as filler for heatsinks for electronic components and as abrasive. In the production process, operators visually inspect the product using optical microscopes to see if there is a defect in sphericity. Production conditions are adjusted through feedback of the inspection information to the preceding process. As there are many types of defective shapes, operators make a judgement on particle conditions based on their own experience. Furthermore, it is difficult to quantitatively grasp particle conditions, resulting in difficulty in using relevant information for the purpose of productivity improvement and quality stabilization.

SDK has therefore developed the AI-based image analysis system to visualize experience-based knowledge of skilled operators. This was not possible under the conventional image-analysis software. The new system is also aimed at ensuring quick feedback of digitalized data to the production process to stabilize product quality. To use examples of skilled operators' judgement as training data, SDK utilized BLUE TAG's high technology of micro-level-image processing.

As a result of initial tests, we confirmed the system's ability to make a judgment at the same level as that of skilled operators in about 20 seconds. This system also enables accumulation of data for relearning processes. Thus, inspection accuracy under the system can be improved based on operation results at the production line. SDK's spherical alumina product has the advantage of uniformity in sphericity and stability in product quality. Fully utilizing the new AI-based image analysis system, we will work to further improve product quality and productivity.

The Showa Denko Group is promoting AI and IoT technologies under its medium-term business plan "The TOP 2021." SDK will continue utilizing these technologies at production sites to visualize and quantify technology and experience-based knowledge possessed by experts, thereby ensuring safe and stable operation and strengthening competitive power.

Outline of BLUE TAG
2-12-18, Uyeno, Taito-ku, Tokyo
Incorporated: May 16, 2018
Representative Director: Jun-ichi Shibuya
Scope of business: Development of AI technology and image-processing solutions (TAG STREAM), Development of AI technology and image-processing product to meet the needs of individual companies, Data analysis, construction of deduction models, and consulting
URL: https://www.btag.jp/

Contact:
Showa Denko K.K., Public Relations Office, Tel: 81-3-5470-3235
Source: Showa Denko K.K.
Sectors: Metals & Mining, Chemicals, Spec.Chem, Artificial Intel [AI]

Copyright ©2024 JCN Newswire. All rights reserved. A division of Japan Corporate News Network.

Related Press Release


Showa Denko Launches Mass Production of 6-inch SiC Single Crystal Wafers
March 28 2022 11:00 JST
 
SDK Corrects Segment Information in 2021 Consolidated Financial Statements
March 11 2022 14:00 JST
 
Showa Denko Group Starts to Consider Transformation into Holding Company Structure
March 09 2022 14:00 JST
 
Showa Denko Decides Firm Name of the Newly Integrated Company
March 09 2022 14:00 JST
 
SDK Announces 2021 Consolidated Financial Results
February 14 2022 13:00 JST
 
SDK to Revise Amount of Director Compensation (in Money) Following Revision of Director Compensation Scheme and to Partially Revise Performance-Linked Stock Compensation Scheme
February 14 2022 13:00 JST
 
Showa Denko Accelerates Search for Optimal Formulation of Semiconductor Materials with Quantum Computing Technology
February 10 2022 12:00 JST
 
Showa Denko Revises Forecast of Consolidated Performance
February 09 2022 15:00 JST
 
New Year Message from Hidehito Takahashi, Showa Denko President and CEO
January 04 2022 13:00 JST
 
Showa Denko Develops HD Media for MAS-MAMR Technology
December 10 2021 12:30 JST
 
More Press release >>

Latest Press Release


More Latest Release >>