993. AI-Driven Machine Learning Approach for Accurate Structural Modeling of Organic Light-Emitting Diodes
Invited abstract in session WA-38: Industrial Optimization, stream Data Science meets Optimization.
Wednesday, 8:30-10:00Room: Michael Sadler LG19
Authors (first author is the speaker)
| 1. | InnJun Choi
|
| Industrial Engineering, Inha University | |
| 2. | Sung Woo Kang
|
| Industrial Engineering, Inha University |
Abstract
Designing organic light-emitting diodes (OLEDs) with desired emission colors and efficiencies requires complex optimization of material selection and device structure due to their multilayered architecture. The cavity structure in OLEDs enables a broad range of emission colors and efficiencies by adjusting the thickness and optical constants of the layers, even when using a fixed set of materials. However, conventional approaches for optimizing OLED designs are costly, labor-intensive, and time-consuming due to the vast number of possible combinations in multilayer structures.
To address these challenges, this study introduces a novel rule-based machine learning (ML) algorithm capable of intelligently predicting the ideal OLED structure based on the thickness and refractive index of organic layers. The proposed ML algorithm demonstrates remarkable accuracy, achieving an error margin of less than 0.5% for red, green, and blue OLEDs. These findings highlight the potential of ML-driven optimization as an efficient and precise solution, significantly reducing time and resource expenditures in OLED design.
Keywords
- Algorithms
- Machine Learning
- Optimization Modeling
Status: accepted
Back to the list of papers