Inverse design of organic light-emitting diode structure based on deep neural networks

Nanophotonics

Park Chan Y.¹  Park Sehong²  Park Juho³  Seo Dongjin³  Lee Jaeho³  Park Chanhyung³  Shin Jeong Min³  Jang Min Seok³  Lee Songju³  Kim Sanmun³ 

[1] KC Machine Learning Lab, Seoul06181, Republic of Korea;OC Optical Technology Task, LG Display, Seoul, 07796, Republic of Korea;School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea;

关键词: deep neural network;    genetic algorithm;    inverse design;    light extraction efficiency;    organic light-emitting diodes;   

DOI  :  10.1515/nanoph-2021-0434

来源: DOAJ

【 摘 要 】

The optical properties of thin-film light emitting diodes (LEDs) are strongly dependent on their structures due to light interference inside the devices. However, the complexity of the design space grows exponentially with the number of design parameters, making it challenging to optimize the optical properties of multilayer LEDs with rigorous electromagnetic simulations. In this work, we demonstrate an artificial neural network that can predict the light extraction efficiency of an organic LED structure in 30 ms, which is ∼103 times faster than the rigorous simulation in a single-treaded execution with root-mean-squared error of 1.86 × 10−3. The effective inference time per structure is brought down to ∼0.6 μs with unaltered error rate with parallelization. We also show that our neural networks can efficiently solve the inverse problem – finding a device design that exhibits the desired light extraction spectrum – within the similar time scale. We investigate the one-to-many mapping issue of the inverse problem and find that the degeneracy can be lifted by incorporating additional emission spectra at different observing angles. Furthermore, the forward neural network is combined with a conventional genetic algorithm to address additional large-scale optimization problems including maximization of light extraction efficiency and minimization of angle dependent color shift. Our approach establishes a platform for tackling computation-heavy optimization tasks with one-time computational cost.

【 授权许可】

Unknown