Inverse Design for Coating Parameters in Nano-Film Growth Based on Deep Learning Neural Network and Particle Swarm Optimization Algorithm

• Published in: Photonics Vol. 9; no. 8; p. 513
• Main Authors: Guo, Xiaohan, Lu, Jinsu, Li, Yu, Li, Jianhong, Huang, Weiping
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2022
• Subjects: Accuracy; Algorithms; Bragg reflectors; Coating; Coatings; Computer simulation; Deep learning; deep learning neural network; Design parameters; Failure analysis; Film growth; Inverse design; Machine learning; Mathematical optimization; Multilayers; nano-film coating; Neural networks; Numerical analysis; Optimization; parameter extraction; Particle swarm optimization; Simulation; single-solution problem
• ISSN: 2304-6732; 2304-6732
• DOI: 10.3390/photonics9080513

The NN (neural network)-PSO (particle swarm optimization) method is demonstrated to be able to inversely extract the coating parameters for the multilayer nano-films through a simulation case and two experimental cases to verify its accuracy and robustness. In the simulation case, the relative error (RE) between the average layer values and the original one was less than 3.45% for 50 inverse designs. In the experimental anti-reflection (AR) coating case, the mean thickness values of the inverse design results had a RE of around 5.05%, and in the Bragg reflector case, the RE was less than 1.03% for the repeated inverse simulations. The method can also be used to solve the single-solution problem of a tandem neural network in the inverse process.