2022 Fiscal Year Final Research Report
Study of optimal design of LED packaging using artificial intelligence
| Project/Area Number |
19K04145
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 18030:Design engineering-related
|
|---|
| Research Institution | Kindai University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2023-03-31
|
| Keywords | 白色LED / パッケージング / 最適設計 / 機械学習 / ニューラルネットワーク / CNN / ディープラーニング / 人工知能 |
|---|
| Outline of Final Research Achievements |
In this study, we used artificial intelligence (machine learning) for modeling the relationship between the design parameters of white LED packaging and the optical properties of white LEDs. The optical properties, namely, total luminous flux and chromaticity, were successfully predicted from the main design parameters of white LEDs, which were radiant flux of a blue chip and amount of phosphor. We also succeeded in obtaining the model that predicts the total luminous flux from the structure of the phosphor layer.
Furthermore, we succeeded in predicting the total luminous flux of white LEDs from cross-sectional images of the white LED packaging using a Convolutional Neural Network (CNN), and the results showed that CNN can analyze the packaging structure from the feature map in the process of learning the cross-sectional image by the CNN.
|
| Free Research Field |
光半導体
|
| Academic Significance and Societal Importance of the Research Achievements |
LEDパッケージング構造と構成部材の光学特性の組み合わせによる発光効率を調査し，設計・最適化手法を学術的に提案した研究例は数少ない．機械学習（人工知能）技術を用いて，LEDパッケージングをモデル化できたことは，理想的な構造と光学特性の関係を明らかにできる可能を示しており，学術のみならず産業界においても，今後の構成部材開発とパッケージング設計のさらなる高効率化に大きく貢献するものと考えられる．
|
